Feed aggregator



A new prototype is laying claim to the title of smallest, lightest untethered flying robot.

At less than a centimeter in wingspan, the wirelessly powered robot is currently very limited in how far it can travel away from the magnetic fields that drive its flight. However, the scientists who developed it suggest there are ways to boost its range, which could lead to potential applications such as search and rescue operations, inspecting damaged machinery in industrial settings, and even plant pollination.

One strategy to shrink flying robots involves removing their batteries and supplying them electricity using tethers. However, tethered flying robots face problems operating freely in complex environments. This has led some researchers to explore wireless methods of powering robot flight.

“The dream was to make flying robots to fly anywhere and anytime without using an electrical wire for the power source,” says Liwei Lin, a professor of mechanical engineering at University of California at Berkeley. Lin and his fellow researchers detailed their findings in Science Advances.

3D-Printed Flying Robot Design

Each flying robot has a 3D-printed body that consists of a propeller with four blades. This rotor is encircled by a ring that helps the robot stay balanced during flight. On top of each body are two tiny permanent magnets.

All in all, the insect-scale prototypes have wingspans as small as 9.4 millimeters and weigh as little as 21 milligrams. Previously, the smallest reported flying robot, either tethered or untethered, was 28 millimeters wide.

When exposed to an external alternating magnetic field, the robots spin and fly without tethers. The lowest magnetic field strength needed to maintain flight is 3.1 millitesla. (In comparison, a refrigerator magnet has a strength of about 10 mT.)

When the applied magnetic field alternates with a frequency of 310 hertz, the robots can hover. At 340 Hz, they accelerate upward. The researchers could steer the robots laterally by adjusting the applied magnetic fields. The robots could also right themselves after collisions to stay airborne without complex sensing or controlling electronics, as long as the impacts were not too large.

Experiments show the lift force the robots generate can exceed their weight by 14 percent, to help them carry payloads. For instance, a prototype that’s 20.5 millimeters wide and weighing 162.4 milligrams could carry an infrared sensor weighing 110 mg to scan its environment. The robots proved efficient at converting the energy given them into lift force—better than nearly all other reported flying robots, tethered or untethered, and also better than fruit flies and hummingbirds.

Currently the maximum operating range of these prototypes is about 10 centimeters away from the magnetic coils. One way to extend the operating range of these robots is to increase the magnetic field strength they experience tenfold by adding more coils, optimizing the configuration of these coils, and using beamforming coils, Lin notes. Such developments could allow the robots to fly up to a meter away from the magnetic coils.

The scientists could also miniaturize the robots even further. This would make them lighter, and so reduce the magnetic field strength they need for propulsion. “It could be possible to drive micro flying robots using electromagnetic waves such as those in radio or cell phone transmission signals,” Lin says. Future research could also place devices that can convert magnetic energy to electricity onboard the robots to power electronic components, the researchers add.



A new prototype is laying claim to the title of smallest, lightest untethered flying robot.

At less than a centimeter in wingspan, the wirelessly powered robot is currently very limited in how far it can travel away from the magnetic fields that drive its flight. However, the scientists who developed it suggest there are ways to boost its range, which could lead to potential applications such as search and rescue operations, inspecting damaged machinery in industrial settings, and even plant pollination.

One strategy to shrink flying robots involves removing their batteries and supplying them electricity using tethers. However, tethered flying robots face problems operating freely in complex environments. This has led some researchers to explore wireless methods of powering robot flight.

“The dream was to make flying robots to fly anywhere and anytime without using an electrical wire for the power source,” says Liwei Lin, a professor of mechanical engineering at University of California at Berkeley. Lin and his fellow researchers detailed their findings in Science Advances.

3D-Printed Flying Robot Design

Each flying robot has a 3D-printed body that consists of a propeller with four blades. This rotor is encircled by a ring that helps the robot stay balanced during flight. On top of each body are two tiny permanent magnets.

All in all, the insect-scale prototypes have wingspans as small as 9.4 millimeters and weigh as little as 21 milligrams. Previously, the smallest reported flying robot, either tethered or untethered, was 28 millimeters wide.

When exposed to an external alternating magnetic field, the robots spin and fly without tethers. The lowest magnetic field strength needed to maintain flight is 3.1 millitesla. (In comparison, a refrigerator magnet has a strength of about 10 mT.)

When the applied magnetic field alternates with a frequency of 310 hertz, the robots can hover. At 340 Hz, they accelerate upward. The researchers could steer the robots laterally by adjusting the applied magnetic fields. The robots could also right themselves after collisions to stay airborne without complex sensing or controlling electronics, as long as the impacts were not too large.

Experiments show the lift force the robots generate can exceed their weight by 14 percent, to help them carry payloads. For instance, a prototype that’s 20.5 millimeters wide and weighing 162.4 milligrams could carry an infrared sensor weighing 110 mg to scan its environment. The robots proved efficient at converting the energy given them into lift force—better than nearly all other reported flying robots, tethered or untethered, and also better than fruit flies and hummingbirds.

Currently the maximum operating range of these prototypes is about 10 centimeters away from the magnetic coils. One way to extend the operating range of these robots is to increase the magnetic field strength they experience tenfold by adding more coils, optimizing the configuration of these coils, and using beamforming coils, Lin notes. Such developments could allow the robots to fly up to a meter away from the magnetic coils.

The scientists could also miniaturize the robots even further. This would make them lighter, and so reduce the magnetic field strength they need for propulsion. “It could be possible to drive micro flying robots using electromagnetic waves such as those in radio or cell phone transmission signals,” Lin says. Future research could also place devices that can convert magnetic energy to electricity onboard the robots to power electronic components, the researchers add.



Your weekly selection of awesome robot videos

Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

RoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZILRO-MAN 2025: 25–29 August 2025, EINDHOVEN, NETHERLANDS

Enjoy today’s videos!

This robot can walk, without electronics, and only with the addition of a cartridge of compressed gas, right off the 3D-printer. It can also be printed in one go, from one material. Researchers from the University of California San Diego and BASF, describe how they developed the robot in an advanced online publication in the journal Advanced Intelligent Systems. They used the simplest technology available: a desktop 3D-printer and an off-the-shelf printing material. This design approach is not only robust, it is also cheap—each robot costs about $20 to manufacture.

And details!

[ Paper ] via [ University of California San Diego ]

Why do you want a humanoid robot to walk like a human? So that it doesn’t look weird, I guess, but it’s hard to imagine that a system that doesn’t have the same arrangement of joints and muscles that we do will move optimally by just trying to mimic us.

[ Figure ]

I don’t know how it manages it, but this little soft robotic worm somehow moves with an incredible amount of personality.

Soft actuators are critical for enabling soft robots, medical devices, and haptic systems. Many soft actuators, however, require power to hold a configuration and rely on hard circuitry for control, limiting their potential applications. In this work, the first soft electromagnetic system is demonstrated for externally-controlled bistable actuation or self-regulated astable oscillation.

[ Paper ] via [ Georgia Tech ]

Thanks, Ellen!

A 180-degree pelvis rotation would put the “break” in “breakdancing” if this were a human doing it.

[ Boston Dynamics ]

My colleagues were impressed by this cooking robot, but that may be because journalists are always impressed by free food.

[ Posha ]

This is our latest work about a hybrid aerial-terrestrial quadruped robot called SPIDAR, which shows unique and complex locomotion styles in both aerial and terrestrial domains including thrust-assisted crawling motion. This work has been presented in the International Symposium of Robotics Research (ISRR) 2024.

[ Paper ] via [ Dragon Lab ]

Thanks, Moju!

This fresh, newly captured video from Unitree’s testing grounds showcases the breakneck speed of humanoid intelligence advancement. Every day brings something thrilling!

[ Unitree ]

There should be more robots that you can ride around on.

[ AgileX Robotics ]

There should be more robots that wear hats at work.

[ Ugo ]

iRobot, who pioneered giant docks for robot vacuums, is now moving away from giant docks for robot vacuums.

[ iRobot ]

There’s a famous experiment where if you put a dead fish in current, it starts swimming, just because of its biomechanical design. Somehow, you can do the same thing with an unactuated quadruped robot on a treadmill.

[ Delft University of Technology ]

Mush! Narrowly!

[ Hybrid Robotics ]

It’s freaking me out a little bit that this couple is apparently wandering around a huge mall that is populated only by robots and zero other humans.

[ MagicLab ]

I’m trying, I really am, but the yellow is just not working for me.

[ Kepler ]

By having Stretch take on the physically demanding task of unloading trailers stacked floor to ceiling with boxes, Gap Inc has reduced injuries, lowered turnover, and watched employees get excited about automation intended to keep them safe.

[ Boston Dynamics ]

Since arriving at Mars in 2012, NASA’s Curiosity rover has been ingesting samples of Martian rock, soil, and air to better understand the past and present habitability of the Red Planet. Of particular interest to its search are organic molecules: the building blocks of life. Now, Curiosity’s onboard chemistry lab has detected long-chain hydrocarbons in a mudstone called “Cumberland,” the largest organics yet discovered on Mars.

[ NASA ]

This University of Toronto Robotics Institute Seminar is from Sergey Levine at UC Berkeley, on Robotics Foundation Models.

General-purpose pretrained models have transformed natural language processing, computer vision, and other fields. In principle, such approaches should be ideal in robotics: since gathering large amounts of data for any given robotic platform and application is likely to be difficult, general pretrained models that provide broad capabilities present an ideal recipe to enable robotic learning at scale for real-world applications.
From the perspective of general AI research, such approaches also offer a promising and intriguing approach to some of the grandest AI challenges: if large-scale training on embodied experience can provide diverse physical capabilities, this would shed light not only on the practical questions around designing broadly capable robots, but the foundations of situated problem-solving, physical understanding, and decision making. However, realizing this potential requires handling a number of challenging obstacles. What data shall we use to train robotic foundation models? What will be the training objective? How should alignment or post-training be done? In this talk, I will discuss how we can approach some of these challenges.

[ University of Toronto ]



Your weekly selection of awesome robot videos

Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

RoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZILRO-MAN 2025: 25–29 August 2025, EINDHOVEN, NETHERLANDS

Enjoy today’s videos!

This robot can walk, without electronics, and only with the addition of a cartridge of compressed gas, right off the 3D-printer. It can also be printed in one go, from one material. Researchers from the University of California San Diego and BASF, describe how they developed the robot in an advanced online publication in the journal Advanced Intelligent Systems. They used the simplest technology available: a desktop 3D-printer and an off-the-shelf printing material. This design approach is not only robust, it is also cheap—each robot costs about $20 to manufacture.

And details!

[ Paper ] via [ University of California San Diego ]

Why do you want a humanoid robot to walk like a human? So that it doesn’t look weird, I guess, but it’s hard to imagine that a system that doesn’t have the same arrangement of joints and muscles that we do will move optimally by just trying to mimic us.

[ Figure ]

I don’t know how it manages it, but this little soft robotic worm somehow moves with an incredible amount of personality.

Soft actuators are critical for enabling soft robots, medical devices, and haptic systems. Many soft actuators, however, require power to hold a configuration and rely on hard circuitry for control, limiting their potential applications. In this work, the first soft electromagnetic system is demonstrated for externally-controlled bistable actuation or self-regulated astable oscillation.

[ Paper ] via [ Georgia Tech ]

Thanks, Ellen!

A 180-degree pelvis rotation would put the “break” in “breakdancing” if this were a human doing it.

[ Boston Dynamics ]

My colleagues were impressed by this cooking robot, but that may be because journalists are always impressed by free food.

[ Posha ]

This is our latest work about a hybrid aerial-terrestrial quadruped robot called SPIDAR, which shows unique and complex locomotion styles in both aerial and terrestrial domains including thrust-assisted crawling motion. This work has been presented in the International Symposium of Robotics Research (ISRR) 2024.

[ Paper ] via [ Dragon Lab ]

Thanks, Moju!

This fresh, newly captured video from Unitree’s testing grounds showcases the breakneck speed of humanoid intelligence advancement. Every day brings something thrilling!

[ Unitree ]

There should be more robots that you can ride around on.

[ AgileX Robotics ]

There should be more robots that wear hats at work.

[ Ugo ]

iRobot, who pioneered giant docks for robot vacuums, is now moving away from giant docks for robot vacuums.

[ iRobot ]

There’s a famous experiment where if you put a dead fish in current, it starts swimming, just because of its biomechanical design. Somehow, you can do the same thing with an unactuated quadruped robot on a treadmill.

[ Delft University of Technology ]

Mush! Narrowly!

[ Hybrid Robotics ]

It’s freaking me out a little bit that this couple is apparently wandering around a huge mall that is populated only by robots and zero other humans.

[ MagicLab ]

I’m trying, I really am, but the yellow is just not working for me.

[ Kepler ]

By having Stretch take on the physically demanding task of unloading trailers stacked floor to ceiling with boxes, Gap Inc has reduced injuries, lowered turnover, and watched employees get excited about automation intended to keep them safe.

[ Boston Dynamics ]

Since arriving at Mars in 2012, NASA’s Curiosity rover has been ingesting samples of Martian rock, soil, and air to better understand the past and present habitability of the Red Planet. Of particular interest to its search are organic molecules: the building blocks of life. Now, Curiosity’s onboard chemistry lab has detected long-chain hydrocarbons in a mudstone called “Cumberland,” the largest organics yet discovered on Mars.

[ NASA ]

This University of Toronto Robotics Institute Seminar is from Sergey Levine at UC Berkeley, on Robotics Foundation Models.

General-purpose pretrained models have transformed natural language processing, computer vision, and other fields. In principle, such approaches should be ideal in robotics: since gathering large amounts of data for any given robotic platform and application is likely to be difficult, general pretrained models that provide broad capabilities present an ideal recipe to enable robotic learning at scale for real-world applications.
From the perspective of general AI research, such approaches also offer a promising and intriguing approach to some of the grandest AI challenges: if large-scale training on embodied experience can provide diverse physical capabilities, this would shed light not only on the practical questions around designing broadly capable robots, but the foundations of situated problem-solving, physical understanding, and decision making. However, realizing this potential requires handling a number of challenging obstacles. What data shall we use to train robotic foundation models? What will be the training objective? How should alignment or post-training be done? In this talk, I will discuss how we can approach some of these challenges.

[ University of Toronto ]



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

European Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

Every time you see a humanoid demo in a warehouse or factory, ask yourself: Would a “superhumanoid” like this actually be a better answer?

[ Dexterity ]

The only reason that this is the second video in Video Friday this week, and not the first, is because you’ve almost certainly already seen it.

This is a collaboration between the Robotics and AI Institute and Boston Dynamics, and RAI has its own video, which is slightly different:

- YouTube

[ Boston Dynamics ] via [ RAI ]

Well this just looks a little bit like magic.

[ University of Pennsylvania Sung Robotics Lab ]

After hours of dance battles with professional choreographers (yes, real human dancers!), PM01 now nails every iconic move from Kung Fu Hustle.

[ EngineAI ]

Sanctuary AI has demonstrated industry-leading sim-to-real transfer of learned dexterous manipulation policies for our unique, high degree-of-freedom, high strength, and high speed hydraulic hands.

[ Sanctuary AI ]

This video is “introducing BotQ, Figure’s new high-volume manufacturing facility for humanoid robots,” but I just see some injection molding and finishing of a few plastic parts.

[ Figure ]

DEEP Robotics recently showcased its “One-Touch Navigation” feature, enhancing the intelligent control experience of its robotic dog. This feature offers two modes: map-based point selection and navigation and video-based point navigation, designed for open terrains and confined spaces respectively. By simply typing on a tablet screen or selecting a point in the video feed, the robotic dog can autonomously navigate to the target point, automatically planning its path and intelligently avoiding obstacles, significantly improving traversal efficiency.

What’s in the bags, though?

[ Deep Robotics ]

This hurts my knees to watch, in a few different ways.

[ Unitree ]

Why the recent obsession with two legs when instead robots could have six? So much cuter!

[ Jizai ] via [ RobotStart ]

The world must know: who killed Mini-Duck?

[ Pollen ]

Seven hours of Digit robots at work at ProMat.

And there are two more days of these livestreams if you need more!

[ Agility ]



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

European Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

Every time you see a humanoid demo in a warehouse or factory, ask yourself: Would a “superhumanoid” like this actually be a better answer?

[ Dexterity ]

The only reason that this is the second video in Video Friday this week, and not the first, is because you’ve almost certainly already seen it.

This is a collaboration between the Robotics and AI Institute and Boston Dynamics, and RAI has its own video, which is slightly different:

- YouTube

[ Boston Dynamics ] via [ RAI ]

Well this just looks a little bit like magic.

[ University of Pennsylvania Sung Robotics Lab ]

After hours of dance battles with professional choreographers (yes, real human dancers!), PM01 now nails every iconic move from Kung Fu Hustle.

[ EngineAI ]

Sanctuary AI has demonstrated industry-leading sim-to-real transfer of learned dexterous manipulation policies for our unique, high degree-of-freedom, high strength, and high speed hydraulic hands.

[ Sanctuary AI ]

This video is “introducing BotQ, Figure’s new high-volume manufacturing facility for humanoid robots,” but I just see some injection molding and finishing of a few plastic parts.

[ Figure ]

DEEP Robotics recently showcased its “One-Touch Navigation” feature, enhancing the intelligent control experience of its robotic dog. This feature offers two modes: map-based point selection and navigation and video-based point navigation, designed for open terrains and confined spaces respectively. By simply typing on a tablet screen or selecting a point in the video feed, the robotic dog can autonomously navigate to the target point, automatically planning its path and intelligently avoiding obstacles, significantly improving traversal efficiency.

What’s in the bags, though?

[ Deep Robotics ]

This hurts my knees to watch, in a few different ways.

[ Unitree ]

Why the recent obsession with two legs when instead robots could have six? So much cuter!

[ Jizai ] via [ RobotStart ]

The world must know: who killed Mini-Duck?

[ Pollen ]

Seven hours of Digit robots at work at ProMat.

And there are two more days of these livestreams if you need more!

[ Agility ]



When you see a squirrel jump to a branch, you might think (and I myself thought, up until just now) that they’re doing what birds and primates would do to stick the landing: just grabbing the branch and hanging on. But it turns out that squirrels, being squirrels, don’t actually have prehensile hands or feet, meaning that they can’t grasp things with any significant amount of strength. Instead, they manage to land on branches using a “palmar” grasp, which isn’t really a grasp at all, in the sense that there’s not much grabbing going on. It’s more accurate to say that the squirrel is mostly landing on its palms and then balancing, which is very impressive.

This kind of dynamic stability is a trait that squirrels share with one of our favorite robots: Salto. Salto is a jumper too, and it’s about as non-prehensile as it’s possible to get, having just one limb with basically no grip strength at all. The robot is great at bouncing around on the ground, but if it could move vertically, that’s an entire new mobility dimension that could lead to some potentially interesting applications, including environmental scouting, search and rescue, and disaster relief.

In a paper published today in Science Robotics, roboticists have now taught Salto to leap from one branch to another like squirrels do, using a low torque gripper and relying on its balancing skills instead.

Squirrel Landing Techniques in Robotics

While we’re going to be mostly talking about robots here (because that’s what we do), there’s an entire paper by many of the same robotics researchers that was published in late February in the Journal of Experimental Biology about how squirrels land on branches this way. While you’d think that the researchers might have found some domesticated squirrels for this, they actually spent about a month bribing wild squirrels on the UC Berkeley campus to bounce around some instrumented perches while high speed cameras were rolling.

Squirrels aim for perfectly balanced landings, which allow them to immediately jump again. They don’t always get it quite right, of course, and they’re excellent at recovering from branch landings where they go a little bit over or under where they want to be. The research showed how squirrels use their musculoskeletal system to adjust their body position, dynamically absorbing the impact of landing with their forelimbs and altering their mass distribution to turn near misses into successful perches.

It’s these kinds of skills that Salto really needs to be able to usefully make jumps in the real world. When everything goes exactly the way it’s supposed to, jumping and perching is easy, but that almost never happens and the squirrel research shows how important it is to be able to adapt when things go wonky. It’s not like the little robot has a lot of degrees of freedom to work with—it’s got just one leg, just one foot, a couple of thrusters, and that spinning component which, believe it or not, functions as a tail. And yet, Salto manages to (sometimes!) make it work.

Those balanced upright landings are super impressive, although we should mention that Salto only achieved that level of success with two out of 30 trials. It only actually fell off the perch five times, and the rest of the time, it did manage a landing but then didn’t quite balance and either overshot or undershot the branch. There are some mechanical reasons why this is particularly difficult for Salto—for example, having just one leg to use for both jumping and landing means that the robot’s leg has to be rotated mid-jump. This takes time, and causes Salto to jump more vertically than squirrels do, since squirrels jump with their back legs and land with their front legs.

Based on these tests, the researchers identified four key features for balanced landings that apply to robots (and squirrels):

  1. Power and accuracy are important!
  2. It’s easier to land a shallower jump with a more horizontal trajectory.
  3. Being able to squish down close to the branch helps with balancing.
  4. Responsive actuation is also important!

Of these, Salto is great at the first one, very much not great at the second one, and also not great at the third and fourth ones. So in some sense, it’s amazing that the roboticists have been able to get it to do this branch-to-branch jumping as well as they have. There’s plenty more to do, though. Squirrels aren’t the only arboreal jumpers out there, and there’s likely more to learn from other animals—Salto was originally inspired by the galago (also known as bush babies), although those are more difficult to find on the UC Berkeley campus. And while the researchers don’t mention it, the obvious extension to this work is to chain together multiple jumps, and eventually to combine branch jumping with the ground jumping and wall jumping that Salto can do already to really give those squirrels a jump for their nuts.



When you see a squirrel jump to a branch, you might think (and I myself thought, up until just now) that they’re doing what birds and primates would do to stick the landing: just grabbing the branch and hanging on. But it turns out that squirrels, being squirrels, don’t actually have prehensile hands or feet, meaning that they can’t grasp things with any significant amount of strength. Instead, they manage to land on branches using a “palmar” grasp, which isn’t really a grasp at all, in the sense that there’s not much grabbing going on. It’s more accurate to say that the squirrel is mostly landing on its palms and then balancing, which is very impressive.

This kind of dynamic stability is a trait that squirrels share with one of our favorite robots: Salto. Salto is a jumper too, and it’s about as non-prehensile as it’s possible to get, having just one limb with basically no grip strength at all. The robot is great at bouncing around on the ground, but if it could move vertically, that’s an entire new mobility dimension that could lead to some potentially interesting applications, including environmental scouting, search and rescue, and disaster relief.

In a paper published today in Science Robotics, roboticists have now taught Salto to leap from one branch to another like squirrels do, using a low torque gripper and relying on its balancing skills instead.

Squirrel Landing Techniques in Robotics

While we’re going to be mostly talking about robots here (because that’s what we do), there’s an entire paper by many of the same robotics researchers that was published in late February in the Journal of Experimental Biology about how squirrels land on branches this way. While you’d think that the researchers might have found some domesticated squirrels for this, they actually spent about a month bribing wild squirrels on the UC Berkeley campus to bounce around some instrumented perches while high speed cameras were rolling.

Squirrels aim for perfectly balanced landings, which allow them to immediately jump again. They don’t always get it quite right, of course, and they’re excellent at recovering from branch landings where they go a little bit over or under where they want to be. The research showed how squirrels use their musculoskeletal system to adjust their body position, dynamically absorbing the impact of landing with their forelimbs and altering their mass distribution to turn near misses into successful perches.

It’s these kinds of skills that Salto really needs to be able to usefully make jumps in the real world. When everything goes exactly the way it’s supposed to, jumping and perching is easy, but that almost never happens and the squirrel research shows how important it is to be able to adapt when things go wonky. It’s not like the little robot has a lot of degrees of freedom to work with—it’s got just one leg, just one foot, a couple of thrusters, and that spinning component which, believe it or not, functions as a tail. And yet, Salto manages to (sometimes!) make it work.

Those balanced upright landings are super impressive, although we should mention that Salto only achieved that level of success with two out of 30 trials. It only actually fell off the perch five times, and the rest of the time, it did manage a landing but then didn’t quite balance and either overshot or undershot the branch. There are some mechanical reasons why this is particularly difficult for Salto—for example, having just one leg to use for both jumping and landing means that the robot’s leg has to be rotated mid-jump. This takes time, and causes Salto to jump more vertically than squirrels do, since squirrels jump with their back legs and land with their front legs.

Based on these tests, the researchers identified four key features for balanced landings that apply to robots (and squirrels):

  1. Power and accuracy are important!
  2. It’s easier to land a shallower jump with a more horizontal trajectory.
  3. Being able to squish down close to the branch helps with balancing.
  4. Responsive actuation is also important!

Of these, Salto is great at the first one, very much not great at the second one, and also not great at the third and fourth ones. So in some sense, it’s amazing that the roboticists have been able to get it to do this branch-to-branch jumping as well as they have. There’s plenty more to do, though. Squirrels aren’t the only arboreal jumpers out there, and there’s likely more to learn from other animals—Salto was originally inspired by the galago (also known as bush babies), although those are more difficult to find on the UC Berkeley campus. And while the researchers don’t mention it, the obvious extension to this work is to chain together multiple jumps, and eventually to combine branch jumping with the ground jumping and wall jumping that Salto can do already to really give those squirrels a jump for their nuts.



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

European Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

In 2026, a JAXA spacecraft is heading to the Martian moon Phobos to chuck a little rover at it.

[ DLR ]

Happy International Women’s Day! UBTECH humanoid robots Walker S1 deliver flowers to incredible women and wish all women a day filled with love, joy and empowerment.

[ UBTECH ]

TRON 1 demonstrates Multi-Terrain Mobility as a versatile biped mobility platform, empowering innovators to push the boundaries of robotic locomotion, unlocking limitless possibilities in algorithm validation and advanced application development.

[ LimX Dynamics ]

This is indeed a very fluid running gait, and the flip is also impressive, but I’m wondering what sort of actual value these skills add, you know? Or even what kind of potential value they’re leading up to.

[ EngineAI ]

Designing trajectories for manipulation through contact is challenging as it requires reasoning of object & robot trajectories as well as complex contact sequences simultaneously. In this paper, we present a novel framework for simultaneously designing trajectories of robots, objects, and contacts efficiently for contact-rich manipulation.

[ Paper ] via [ Mitsubishi Electric Research Laboratories ]

Thanks, Yuki!

Running robot, you say? I’m thinking it might actually be a power walking robot.

[ MagicLab ]

Wake up, Reachy!

[ Pollen ]

Robot vacuum docks have gotten large enough that we’re now all supposed to pretend that we’re happy they’ve become pieces of furniture.

[ Roborock ]

The SeaPerch underwater robot, a “do-it-yourself” maker project, is a popular educational tool for middle and high school students. Developed by MIT Sea Grant, the remotely operated vehicle (ROV) teaches hand fabrication processes, electronics techniques, and STEM concepts, while encouraging exploration of structures, electronics, and underwater dynamics.

[ MIT Sea Grant ]

I was at this RoboGames match! In 2010! And now I feel old!

[ Hardcore Robotics ]

Daniel Simu with a detailed breakdown of his circus acrobat partner robot. If you don’t want to watch the whole thing, make sure and check out 3:30.

[ Daniel Simu ]



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

European Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

In 2026, a JAXA spacecraft is heading to the Martian moon Phobos to chuck a little rover at it.

[ DLR ]

Happy International Women’s Day! UBTECH humanoid robots Walker S1 deliver flowers to incredible women and wish all women a day filled with love, joy and empowerment.

[ UBTECH ]

TRON 1 demonstrates Multi-Terrain Mobility as a versatile biped mobility platform, empowering innovators to push the boundaries of robotic locomotion, unlocking limitless possibilities in algorithm validation and advanced application development.

[ LimX Dynamics ]

This is indeed a very fluid running gait, and the flip is also impressive, but I’m wondering what sort of actual value these skills add, you know? Or even what kind of potential value they’re leading up to.

[ EngineAI ]

Designing trajectories for manipulation through contact is challenging as it requires reasoning of object & robot trajectories as well as complex contact sequences simultaneously. In this paper, we present a novel framework for simultaneously designing trajectories of robots, objects, and contacts efficiently for contact-rich manipulation.

[ Paper ] via [ Mitsubishi Electric Research Laboratories ]

Thanks, Yuki!

Running robot, you say? I’m thinking it might actually be a power walking robot.

[ MagicLab ]

Wake up, Reachy!

[ Pollen ]

Robot vacuum docks have gotten large enough that we’re now all supposed to pretend that we’re happy they’ve become pieces of furniture.

[ Roborock ]

The SeaPerch underwater robot, a “do-it-yourself” maker project, is a popular educational tool for middle and high school students. Developed by MIT Sea Grant, the remotely operated vehicle (ROV) teaches hand fabrication processes, electronics techniques, and STEM concepts, while encouraging exploration of structures, electronics, and underwater dynamics.

[ MIT Sea Grant ]

I was at this RoboGames match! In 2010! And now I feel old!

[ Hardcore Robotics ]

Daniel Simu with a detailed breakdown of his circus acrobat partner robot. If you don’t want to watch the whole thing, make sure and check out 3:30.

[ Daniel Simu ]



Ukraine’s young tech entrepreneurs think that a combination of robots and lessons from war-gaming could turn the tide in the war against Russia. They are developing an intelligent operating system to enable a single controller to remotely operate swarms of interconnected drones and cannon-equipped land robots. The tech, they say, could help Ukraine cope with Russia’s numerical advantage.

Kyiv-based start-up Ark Robotics is conducting trials on an embryo of such a system in cooperation with one of the brigades of Ukraine’s ground forces. The company emerged about a year ago, when a group of young roboticists heard a speech by one of the Ukrainian commanders detailing challenges on the frontline.

“At that time, we were building unmanned ground vehicles [UGVs],” Andryi Udovychenko, Ark Robotics’s operations lead, told IEEE Spectrum on the sidelines of the Brave 1 Defense Tech Innovations Forum held in Kyiv last month. “But we heard that what we had [to offer] wasn’t enough. They said they needed something more.”

Since the war began, a vibrant defense tech innovation ecosystem has emerged in Ukraine, having started from modest beginnings of modifying China-made DJI MAVIC drones to make up for the lack of artillery. Today, Ukraine is a drone-making powerhouse. Dozens of startup companies are churning out newer and better tech and rapidly refining it to improve the effectiveness of the beleaguered nation’s troops. First-person-view drones have become a symbol of this war, but since last year they have begun to be complemented by UGVs, which help on the ground with logistics, evacuation of the wounded and also act as a new means of attack.

The new approach allows the Ukrainians to keep their soldiers away from the battle ground for longer periods but doesn’t erase the fact that Ukraine has far fewer soldiers than Russia does.

“Every single drone needs one operator, complicated drones need two or three operators, and we don’t have that many people,” Serhii Kupriienko, the CEO and founder of Swarmer, said during a panel at the Kyiv event. Swarmer is a Kyiv-based start-up developing technologies to allow groups of drones to operate as one self-coordinated swarm.

Ark Robotics are trying to take that idea yet another step. The company’s Frontier OS aspires to become a unifying interface that would allow drones and UGVs made by various makers to work together under the control of operators seated in control rooms miles away from the action.

One Controller for Many Drones and Robots

“We have many types of drones that are using different controls, different interfaces and it’s really hard to build cohesion,” Udovychenko says. “To move forward, we need a system where we can control multiple different types of vehicles in a cohesive manner in complex operations.”

Udovychenko, a gaming enthusiast, is excited about the progress Ark Robotics has made. It could be a game-changer, he says, a new foundational technology for defense. It would make Ukraine “like Protoss,” the fictional technologically advanced nation in the military science fiction strategy game StarCraft.

But what powers him is much more than youthful geekiness. Building up Ukraine’s technological dominance is a mission fueled by grief and outrage.

“I don’t want to lose any more friends,” he remarks at one point, becoming visibly emotional. “We don’t want to be dying in the trenches, but we need to be able to defend our country and given that the societal math doesn’t favor us, we need to make our own math to win.”

Soldiers at an undisclosed location used laptops to test software from Ark Robotics.Ark Robotics

The scope of the challenge isn’t lost on him. The company has so far built a vehicle computing unit that serves as a central hub and control board for various unmanned vehicles including flying drones, UGVs and even marine vehicles.

“We are building this as a solution that enables the integration of various team developers and software, allowing us to extract the best components and rapidly scale them,” Udovychenko says. “This system pairs a high-performance computing module with an interface board that provides multiple connections for vehicle systems.

The platform allows a single operator to remotely guide a flock of robots but will in the future also incorporate autonomous navigation and task execution, according to Udovychenko. So far, the team has tested the technology in simple logistics exercises. For the grand vision to work, though, the biggest challenge will be maintaining reliable communication links between the controller and the robotic fleet, but also between the robots and drones.

Tests on Ukraine Battlefields to Begin Soon

“We’re not talking about communications in a relatively safe environment when you have an LTE network that has enough bandwidth to accommodate thousands of phones,” Udovychenko notes. “At the frontline, everything is affected by electronic warfare, so you need to be able to switch between different solutions including satellite, digital radio and radio mesh so that even if you lose connection to the server, you still have connection between the drones and robots so that they can move together and maintain some level of control between them.”

Udovychenko expects Ark Robotics’s partner brigade in the Ukraine armed forces to test the early version of the tech in a real-life situation within the next couple of months. His young drone operator friends are excited, he says. And how could they not be? The technology promises to turn warfighting into a kind of real-life video game. The new class of multi-drone operators will likely be recruited from the ranks of gaming aficionados.

“If we can take the best pilots and give them tools to combine the operations, we might see a tremendous advantage,” Udovychenko says. “It’s like in StarCraft. Some people are simply able to play the game right and obliterate their opponents within minutes even if they’re starting from the same basic conditions.”

Speaking at the Brave 1 Defense Tech Innovations Forum, Colonel Andrii Lebedenko, Deputy Commander-in-Chief of the Armed Forces of Ukraine, acknowledged that land battles have so far been Ukraine’s weakest area. He said that replacing “humans with robots as much as possible” is Ukraine’s near-term goal and he expressed confidence that upcoming technologies will give greater autonomy to the robot swarms.

Some roboticists, however, are more skeptical that swarms of autonomous robots will crawl en-masse across the battlefields of Eastern Ukraine any time soon. “Swarming is certainly a goal we should reach but it’s much easier with FPV drones than with ground-based robots,” Ivan Movchan, CEO of the Ukrainian Scale Company, a Kharkiv-based robot maker, told Spectrum.

“Navigation on the ground is more challenging simply because of the obstacles,” he adds. “But I do expect UGVs to become very common in Ukraine over the next year.”



Ukraine’s young tech entrepreneurs think that a combination of robots and lessons from war-gaming could turn the tide in the war against Russia. They are developing an intelligent operating system to enable a single controller to remotely operate swarms of interconnected drones and cannon-equipped land robots. The tech, they say, could help Ukraine cope with Russia’s numerical advantage.

Kyiv-based start-up Ark Robotics is conducting trials on an embryo of such a system in cooperation with one of the brigades of Ukraine’s ground forces. The company emerged about a year ago, when a group of young roboticists heard a speech by one of the Ukrainian commanders detailing challenges on the frontline.

“At that time, we were building unmanned ground vehicles [UGVs],” Andryi Udovychenko, Ark Robotics’s operations lead, told IEEE Spectrum on the sidelines of the Brave 1 Defense Tech Innovations Forum held in Kyiv last month. “But we heard that what we had [to offer] wasn’t enough. They said they needed something more.”

Since the war began, a vibrant defense tech innovation ecosystem has emerged in Ukraine, having started from modest beginnings of modifying China-made DJI MAVIC drones to make up for the lack of artillery. Today, Ukraine is a drone-making powerhouse. Dozens of startup companies are churning out newer and better tech and rapidly refining it to improve the effectiveness of the beleaguered nation’s troops. First-person-view drones have become a symbol of this war, but since last year they have begun to be complemented by UGVs, which help on the ground with logistics, evacuation of the wounded and also act as a new means of attack.

The new approach allows the Ukrainians to keep their soldiers away from the battle ground for longer periods but doesn’t erase the fact that Ukraine has far fewer soldiers than Russia does.

“Every single drone needs one operator, complicated drones need two or three operators, and we don’t have that many people,” Serhii Kupriienko, the CEO and founder of Swarmer, said during a panel at the Kyiv event. Swarmer is a Kyiv-based start-up developing technologies to allow groups of drones to operate as one self-coordinated swarm.

Ark Robotics are trying to take that idea yet another step. The company’s Frontier OS aspires to become a unifying interface that would allow drones and UGVs made by various makers to work together under the control of operators seated in control rooms miles away from the action.

One Controller for Many Drones and Robots

“We have many types of drones that are using different controls, different interfaces and it’s really hard to build cohesion,” Udovychenko says. “To move forward, we need a system where we can control multiple different types of vehicles in a cohesive manner in complex operations.”

Udovychenko, a gaming enthusiast, is excited about the progress Ark Robotics has made. It could be a game-changer, he says, a new foundational technology for defense. It would make Ukraine “like Protoss,” the fictional technologically advanced nation in the military science fiction strategy game StarCraft.

But what powers him is much more than youthful geekiness. Building up Ukraine’s technological dominance is a mission fueled by grief and outrage.

“I don’t want to lose any more friends,” he remarks at one point, becoming visibly emotional. “We don’t want to be dying in the trenches, but we need to be able to defend our country and given that the societal math doesn’t favor us, we need to make our own math to win.”

Soldiers at an undisclosed location used laptops to test software from Ark Robotics.Ark Robotics

The scope of the challenge isn’t lost on him. The company has so far built a vehicle computing unit that serves as a central hub and control board for various unmanned vehicles including flying drones, UGVs and even marine vehicles.

“We are building this as a solution that enables the integration of various team developers and software, allowing us to extract the best components and rapidly scale them,” Udovychenko says. “This system pairs a high-performance computing module with an interface board that provides multiple connections for vehicle systems.

The platform allows a single operator to remotely guide a flock of robots but will in the future also incorporate autonomous navigation and task execution, according to Udovychenko. So far, the team has tested the technology in simple logistics exercises. For the grand vision to work, though, the biggest challenge will be maintaining reliable communication links between the controller and the robotic fleet, but also between the robots and drones.

Tests on Ukraine Battlefields to Begin Soon

“We’re not talking about communications in a relatively safe environment when you have an LTE network that has enough bandwidth to accommodate thousands of phones,” Udovychenko notes. “At the frontline, everything is affected by electronic warfare, so you need to be able to switch between different solutions including satellite, digital radio and radio mesh so that even if you lose connection to the server, you still have connection between the drones and robots so that they can move together and maintain some level of control between them.”

Udovychenko expects Ark Robotics’s partner brigade in the Ukraine armed forces to test the early version of the tech in a real-life situation within the next couple of months. His young drone operator friends are excited, he says. And how could they not be? The technology promises to turn warfighting into a kind of real-life video game. The new class of multi-drone operators will likely be recruited from the ranks of gaming aficionados.

“If we can take the best pilots and give them tools to combine the operations, we might see a tremendous advantage,” Udovychenko says. “It’s like in StarCraft. Some people are simply able to play the game right and obliterate their opponents within minutes even if they’re starting from the same basic conditions.”

Speaking at the Brave 1 Defense Tech Innovations Forum, Colonel Andrii Lebedenko, Deputy Commander-in-Chief of the Armed Forces of Ukraine, acknowledged that land battles have so far been Ukraine’s weakest area. He said that replacing “humans with robots as much as possible” is Ukraine’s near-term goal and he expressed confidence that upcoming technologies will give greater autonomy to the robot swarms.

Some roboticists, however, are more skeptical that swarms of autonomous robots will crawl en-masse across the battlefields of Eastern Ukraine any time soon. “Swarming is certainly a goal we should reach but it’s much easier with FPV drones than with ground-based robots,” Ivan Movchan, CEO of the Ukrainian Scale Company, a Kharkiv-based robot maker, told Spectrum.

“Navigation on the ground is more challenging simply because of the obstacles,” he adds. “But I do expect UGVs to become very common in Ukraine over the next year.”



Generative AI models are getting closer to taking action in the real world. Already, the big AI companies are introducing AI agents that can take care of web-based busywork for you, ordering your groceries or making your dinner reservation. Today, Google DeepMind announced two generative AI models designed to power tomorrow’s robots.

The models are both built on Google Gemini, a multimodal foundation model that can process text, voice, and image data to answer questions, give advice, and generally help out. DeepMind calls the first of the new models, Gemini Robotics, an “advanced vision-language-action model,” meaning that it can take all those same inputs and then output instructions for a robot’s physical actions. The models are designed to work with any hardware system, but were mostly tested on the two-armed Aloha 2 system that DeepMind introduced last year.

In a demonstration video, a voice says: “Pick up the basketball and slam dunk it” (at 2:27 in the video below). Then a robot arm carefully picks up a miniature basketball and drops it into a miniature net—and while it wasn’t a NBA-level dunk, it was enough to get the DeepMind researchers excited.

Google DeepMind released this demo video showing off the capabilities of its Gemini Robotics foundation model to control robots. Gemini Robotics

“This basketball example is one of my favorites,” said Kanishka Rao, the principal software engineer for the project, in a press briefing. He explains that the robot had “never, ever seen anything related to basketball,” but that its underlying foundation model had a general understanding of the game, knew what a basketball net looks like, and understood what the term “slam dunk” meant. The robot was therefore “able to connect those [concepts] to actually accomplish the task in the physical world,” says Rao.

What are the advances of Gemini Robotics?

Carolina Parada, head of robotics at Google DeepMind, said in the briefing that the new models improve over the company’s prior robots in three dimensions: generalization, adaptability, and dexterity. All of these advances are necessary, she said, to create “a new generation of helpful robots.”

Generalization means that a robot can apply a concept that it has learned in one context to another situation, and the researchers looked at visual generalization (for example, does it get confused if the color of an object or background changed), instruction generalization (can it interpret commands that are worded in different ways), and action generalization (can it perform an action it had never done before).

Parada also says that robots powered by Gemini can better adapt to changing instructions and circumstances. To demonstrate that point in a video, a researcher told a robot arm to put a bunch of plastic grapes into a clear Tupperware container, then proceeded to shift three containers around on the table in an approximation of a shyster’s shell game. The robot arm dutifully followed the clear container around until it could fulfill its directive.

Google DeepMind says Gemini Robotics is better than previous models at adapting to changing instructions and circumstances. Google DeepMind

As for dexterity, demo videos showed the robotic arms folding a piece of paper into an origami fox and performing other delicate tasks. However, it’s important to note that the impressive performance here is in the context of a narrow set of high-quality data that the robot was trained on for these specific tasks, so the level of dexterity that these tasks represent is not being generalized.

What is embodied reasoning?

The second model introduced today is Gemini Robotics-ER, with the ER standing for “embodied reasoning,” which is the sort of intuitive physical world understanding that humans develop with experience over time. We’re able to do clever things like look at an object we’ve never seen before and make an educated guess about the best way to interact with it, and this is what DeepMind seeks to emulate with Gemini Robotics-ER.

Parada gave an example of Gemini Robotics-ER’s ability to identify an appropriate grasping point for picking up a coffee cup. The model correctly identifies the handle, because that’s where humans tend to grasp coffee mugs. However, this illustrates a potential weakness of relying on human-centric training data: for a robot, especially a robot that might be able to comfortably handle a mug of hot coffee, a thin handle might be a much less reliable grasping point than a more enveloping grasp of the mug itself.

DeepMind’s Approach to Robotic Safety

Vikas Sindhwani, DeepMind’s head of robotic safety for the project, says the team took a layered approach to safety. It starts with classic physical safety controls that manage things like collision avoidance and stability, but also includes “semantic safety” systems that evaluate both its instructions and the consequences of following them. These systems are most sophisticated in the Gemini Robotics-ER model, says Sindhwani, which is “trained to evaluate whether or not a potential action is safe to perform in a given scenario.”

And because “safety is not a competitive endeavor,” Sindhwani says, DeepMind is releasing a new data set and what it calls the Asimov benchmark, which is intended to measure a model’s ability to understand common-sense rules of life. The benchmark contains both questions about visual scenes and text scenarios, asking models’ opinions on things like the desirability of mixing bleach and vinegar (a combination that make chlorine gas) and putting a soft toy on a hot stove. In the press briefing, Sindhwani said that the Gemini models had “strong performance” on that benchmark, and the technical report showed that the models got more than 80 percent of questions correct.

DeepMind’s Robotic Partnerships

Back in December, DeepMind and the humanoid robotics company Apptronik announced a partnership, and Parada says that the two companies are working together “to build the next generation of humanoid robots with Gemini at its core.” DeepMind is also making its models available to an elite group of “trusted testers”: Agile Robots, Agility Robotics, Boston Dynamics, and Enchanted Tools.



Generative AI models are getting closer to taking action in the real world. Already, the big AI companies are introducing AI agents that can take care of web-based busywork for you, ordering your groceries or making your dinner reservation. Today, Google DeepMind announced two generative AI models designed to power tomorrow’s robots.

The models are both built on Google Gemini, a multimodal foundation model that can process text, voice, and image data to answer questions, give advice, and generally help out. DeepMind calls the first of the new models, Gemini Robotics, an “advanced vision-language-action model,” meaning that it can take all those same inputs and then output instructions for a robot’s physical actions. The models are designed to work with any hardware system, but were mostly tested on the two-armed Aloha 2 system that DeepMind introduced last year.

In a demonstration video, a voice says: “Pick up the basketball and slam dunk it” (at 2:27 in the video below). Then a robot arm carefully picks up a miniature basketball and drops it into a miniature net—and while it wasn’t a NBA-level dunk, it was enough to get the DeepMind researchers excited.

Google DeepMind released this demo video showing off the capabilities of its Gemini Robotics foundation model to control robots. Gemini Robotics

“This basketball example is one of my favorites,” said Kanishka Rao, the principal software engineer for the project, in a press briefing. He explains that the robot had “never, ever seen anything related to basketball,” but that its underlying foundation model had a general understanding of the game, knew what a basketball net looks like, and understood what the term “slam dunk” meant. The robot was therefore “able to connect those [concepts] to actually accomplish the task in the physical world,” says Rao.

What are the advances of Gemini Robotics?

Carolina Parada, head of robotics at Google DeepMind, said in the briefing that the new models improve over the company’s prior robots in three dimensions: generalization, adaptability, and dexterity. All of these advances are necessary, she said, to create “a new generation of helpful robots.”

Generalization means that a robot can apply a concept that it has learned in one context to another situation, and the researchers looked at visual generalization (for example, does it get confused if the color of an object or background changed), instruction generalization (can it interpret commands that are worded in different ways), and action generalization (can it perform an action it had never done before).

Parada also says that robots powered by Gemini can better adapt to changing instructions and circumstances. To demonstrate that point in a video, a researcher told a robot arm to put a bunch of plastic grapes into a clear Tupperware container, then proceeded to shift three containers around on the table in an approximation of a shyster’s shell game. The robot arm dutifully followed the clear container around until it could fulfill its directive.

Google DeepMind says Gemini Robotics is better than previous models at adapting to changing instructions and circumstances. Google DeepMind

As for dexterity, demo videos showed the robotic arms folding a piece of paper into an origami fox and performing other delicate tasks. However, it’s important to note that the impressive performance here is in the context of a narrow set of high-quality data that the robot was trained on for these specific tasks, so the level of dexterity that these tasks represent is not being generalized.

What is embodied reasoning?

The second model introduced today is Gemini Robotics-ER, with the ER standing for “embodied reasoning,” which is the sort of intuitive physical world understanding that humans develop with experience over time. We’re able to do clever things like look at an object we’ve never seen before and make an educated guess about the best way to interact with it, and this is what DeepMind seeks to emulate with Gemini Robotics-ER.

Parada gave an example of Gemini Robotics-ER’s ability to identify an appropriate grasping point for picking up a coffee cup. The model correctly identifies the handle, because that’s where humans tend to grasp coffee mugs. However, this illustrates a potential weakness of relying on human-centric training data: for a robot, especially a robot that might be able to comfortably handle a mug of hot coffee, a thin handle might be a much less reliable grasping point than a more enveloping grasp of the mug itself.

DeepMind’s Approach to Robotic Safety

Vikas Sindhwani, DeepMind’s head of robotic safety for the project, says the team took a layered approach to safety. It starts with classic physical safety controls that manage things like collision avoidance and stability, but also includes “semantic safety” systems that evaluate both its instructions and the consequences of following them. These systems are most sophisticated in the Gemini Robotics-ER model, says Sindhwani, which is “trained to evaluate whether or not a potential action is safe to perform in a given scenario.”

And because “safety is not a competitive endeavor,” Sindhwani says, DeepMind is releasing a new data set and what it calls the Asimov benchmark, which is intended to measure a model’s ability to understand common-sense rules of life. The benchmark contains both questions about visual scenes and text scenarios, asking models’ opinions on things like the desirability of mixing bleach and vinegar (a combination that make chlorine gas) and putting a soft toy on a hot stove. In the press briefing, Sindhwani said that the Gemini models had “strong performance” on that benchmark, and the technical report showed that the models got more than 80 percent of questions correct.

DeepMind’s Robotic Partnerships

Back in December, DeepMind and the humanoid robotics company Apptronik announced a partnership, and Parada says that the two companies are working together “to build the next generation of humanoid robots with Gemini at its core.” DeepMind is also making its models available to an elite group of “trusted testers”: Agile Robots, Agility Robotics, Boston Dynamics, and Enchanted Tools.



After January’s Southern California wildfires, the question of burying energy infrastructure to prevent future fires has gained renewed urgency in the state. While the exact cause of the fires remains under investigation, California utilities have spent years undergrounding power lines to mitigate fire risks. Pacific Gas & Electric, which has installed over 1,287 kilometers of underground power lines since 2021, estimates the method is 98 percent effective in reducing ignition threats. Southern California Edison has buried over 40 percent of its high-risk distribution lines, and 63 percent of San Diego Gas & Electric’s regional distribution system is now underground.

Still, the exorbitant cost of underground construction leaves much of the U.S. power grid’s 8.8 million kilometers of distribution lines and 180 million utility poles exposed to tree strikes, flying debris, and other opportunities for sparks to cascade into a multi-acre blaze. Recognizing the need for cost-effective undergrounding solutions, the U.S. Department of Energy launched GOPHURRS in January 2024. The three-year program pours $34 million into 12 projects to develop more efficient undergrounding technologies that minimize surface disruptions while supporting medium-voltage power lines.

One recipient, Case Western Reserve University in Cleveland, Ohio, is building a self-propelled robotic sleeve that mimics earthworms’ characteristic peristaltic movement to advance through soil. Awarded $2 million, Case’s “peristaltic conduit” concept hopes to more precisely navigate underground and reduce the risk of unintended damage, such as breaking an existing pipe.

Why Is Undergrounding So Expensive?

Despite its benefits, undergrounding remains cost-prohibitive at US $1.1 to $3.7 million per kilometer ($1.8 to $6 million per mile) for distribution lines and $3.7 to $62 million per kilometer for transmission lines, according to estimates from California’s three largest utilities. That’s significantly more than overhead infrastructure, which costs $394,000 to $472,000 per kilometer for distribution lines and $621,000 to $6.83 million per kilometer for transmission lines.

The most popular method of undergrounding power lines, called open trenching, requires extensive excavation, conduit installation, and backfilling, making it expensive and logistically complicated. And it’s often impractical in dense urban areas where underground infrastructure is already congested with plumbing, fiber optics, and other utilities.

Trenchless methods like horizontal directional drilling (HDD) provide a less invasive way to get power lines under roads and railways by creating a controlled, curved bore path that starts at a shallow entry angle, deepens to pass obstacles, and resurfaces at a precise exit point. But HDD is even more expensive than open trenching due to specialized equipment, complex workflows, and the risk of damaging existing infrastructure.

Given the steep costs, utilities often prioritize cheaper fire mitigation strategies like trimming back nearby trees and other plants, using insulated conductors, and stepping up routine inspections and repairs. While not as effective as undergrounding, these measures have been the go-to option, largely because faster, cheaper underground construction methods don’t yet exist.

Ted Kury, director of energy studies at the University of Florida’s Public Utility Research Center, who has extensively studied the costs and benefits of undergrounding, says technologies implementing directional drilling improvements “could make undergrounding more practical in urban or densely populated areas where open trenching, and its attendant disruptions to the surrounding infrastructure, could result in untenable costs.”

Earthworm-Inspired Robotics for Power Lines

In Case’s worm-inspired robot, alternating sections are designed to expand and retract to anchor and advance the machine. This flexible force increases precision and reduces the risk of impacting and breaking pipes. Conventional methods require large turning radii exceeding 300 meters, but Case’s 1.5-meter turning radius will enable the device to flexibly maneuver around existing infrastructure.

“We use actuators to change the length and diameter of each segment,” says Kathryn Daltorio, an associate engineering professor and co-director of Case’s Biologically-Inspired Robotics Lab. “The short and fat segments press against the walls of the burrow, then they anchor so the thin segments can advance forward. If two segments aren’t touching the ground but they’re changing length at the same time, your anchors don’t slip and you advance forward.”

Daltorio and her colleagues have studied earthworm-inspired robotics for over a decade, originally envisioning the technology for surgical and confined-space applications before recognizing its potential for undergrounding power lines.

Case Western Reserve University’s worm-like digging robot can turn faster than other drilling techniques to avoid obstacles.Kathryn Daltorio/Case School of Engineering

Traditional HDD relies on pushing a drill head through soil, requiring more force as the bore length grows. Case’s drilling concept generates the force needed for the tip from the peristaltic segments within the borehole. As the path gets longer, only the front segments dig deeper. “If the robot hits something, operators can pull back and change directions, burrowing along the way to complete the circuit by changing the depth,” Daltorio says.

Another key difference from HDD is integrated conduit installation. In HDD, the drill goes through the entire length first, and then the power conduit is pulled through. Case’s peristaltic robot lays the conduit while traveling, reducing the overall installation time.

Advancements in Burrowing Precision

“The peristaltic conduit approach is fascinating [and] certainly seems to be addressing concerns regarding the sheer variety of underground obstacles,” says the University of Florida’s Kury. However, he highlights a larger concern with undergrounding innovations—not just Case’s—in meeting a constantly evolving environment. Today’s underground will look very different in 10 years, as soil profiles shift, trees grow, animals tunnel, and people dig and build. “Underground cables will live for decades, and the sustainability of these technologies depends on how they adapt to this changing structure,” Kury added.

Daltorio notes that current undergrounding practices involve pouring concrete around the lines before backfilling to protect them from future excavation, a challenge for existing trenchless methods. But Case’s project brings two major benefits. First, by better understanding borehole design, engineers have more flexibility in choosing conduit materials to match the standards for particular environments. Also, advancements in burrowing precision could minimize the likelihood of future disruptions from human activities.

The research team is exploring different ways to reinforce the digging robot’s exterior while it’s underground.Olivia Gatchall

Daltorio’s team is collaborating with several partners, with Auburn University in Alabama contributing geotechnical expertise, Stony Brook University in New York running the modeling, and the University of Texas at Austin studying sediment interactions.

The project aims to halve undergrounding costs, though Daltorio cautions that it’s too early to commit to a specific cost model. Still, the time-saving potential appears promising. “With conventional approaches, planning, permitting and scheduling can take months,” Daltorio says. “By simplifying the process, it might be a few inspections at the endpoints, a few days of autonomous burrowing with minimal disruption to traffic above, followed by a few days of cleaning, splicing, and inspection.”



After January’s Southern California wildfires, the question of burying energy infrastructure to prevent future fires has gained renewed urgency in the state. While the exact cause of the fires remains under investigation, California utilities have spent years undergrounding power lines to mitigate fire risks. Pacific Gas & Electric, which has installed over 1,287 kilometers of underground power lines since 2021, estimates the method is 98 percent effective in reducing ignition threats. Southern California Edison has buried over 40 percent of its high-risk distribution lines, and 63 percent of San Diego Gas & Electric’s regional distribution system is now underground.

Still, the exorbitant cost of underground construction leaves much of the U.S. power grid’s 8.8 million kilometers of distribution lines and 180 million utility poles exposed to tree strikes, flying debris, and other opportunities for sparks to cascade into a multi-acre blaze. Recognizing the need for cost-effective undergrounding solutions, the U.S. Department of Energy launched GOPHURRS in January 2024. The three-year program pours $34 million into 12 projects to develop more efficient undergrounding technologies that minimize surface disruptions while supporting medium-voltage power lines.

One recipient, Case Western Reserve University in Cleveland, Ohio, is building a self-propelled robotic sleeve that mimics earthworms’ characteristic peristaltic movement to advance through soil. Awarded $2 million, Case’s “peristaltic conduit” concept hopes to more precisely navigate underground and reduce the risk of unintended damage, such as breaking an existing pipe.

Why Is Undergrounding So Expensive?

Despite its benefits, undergrounding remains cost-prohibitive at US $1.1 to $3.7 million per kilometer ($1.8 to $6 million per mile) for distribution lines and $3.7 to $62 million per kilometer for transmission lines, according to estimates from California’s three largest utilities. That’s significantly more than overhead infrastructure, which costs $394,000 to $472,000 per kilometer for distribution lines and $621,000 to $6.83 million per kilometer for transmission lines.

The most popular method of undergrounding power lines, called open trenching, requires extensive excavation, conduit installation, and backfilling, making it expensive and logistically complicated. And it’s often impractical in dense urban areas where underground infrastructure is already congested with plumbing, fiber optics, and other utilities.

Trenchless methods like horizontal directional drilling (HDD) provide a less invasive way to get power lines under roads and railways by creating a controlled, curved bore path that starts at a shallow entry angle, deepens to pass obstacles, and resurfaces at a precise exit point. But HDD is even more expensive than open trenching due to specialized equipment, complex workflows, and the risk of damaging existing infrastructure.

Given the steep costs, utilities often prioritize cheaper fire mitigation strategies like trimming back nearby trees and other plants, using insulated conductors, and stepping up routine inspections and repairs. While not as effective as undergrounding, these measures have been the go-to option, largely because faster, cheaper underground construction methods don’t yet exist.

Ted Kury, director of energy studies at the University of Florida’s Public Utility Research Center, who has extensively studied the costs and benefits of undergrounding, says technologies implementing directional drilling improvements “could make undergrounding more practical in urban or densely populated areas where open trenching, and its attendant disruptions to the surrounding infrastructure, could result in untenable costs.”

Earthworm-Inspired Robotics for Power Lines

In Case’s worm-inspired robot, alternating sections are designed to expand and retract to anchor and advance the machine. This flexible force increases precision and reduces the risk of impacting and breaking pipes. Conventional methods require large turning radii exceeding 300 meters, but Case’s 1.5-meter turning radius will enable the device to flexibly maneuver around existing infrastructure.

“We use actuators to change the length and diameter of each segment,” says Kathryn Daltorio, an associate engineering professor and co-director of Case’s Biologically-Inspired Robotics Lab. “The short and fat segments press against the walls of the burrow, then they anchor so the thin segments can advance forward. If two segments aren’t touching the ground but they’re changing length at the same time, your anchors don’t slip and you advance forward.”

Daltorio and her colleagues have studied earthworm-inspired robotics for over a decade, originally envisioning the technology for surgical and confined-space applications before recognizing its potential for undergrounding power lines.

Case Western Reserve University’s worm-like digging robot can turn faster than other drilling techniques to avoid obstacles.Kathryn Daltorio/Case School of Engineering

Traditional HDD relies on pushing a drill head through soil, requiring more force as the bore length grows. Case’s drilling concept generates the force needed for the tip from the peristaltic segments within the borehole. As the path gets longer, only the front segments dig deeper. “If the robot hits something, operators can pull back and change directions, burrowing along the way to complete the circuit by changing the depth,” Daltorio says.

Another key difference from HDD is integrated conduit installation. In HDD, the drill goes through the entire length first, and then the power conduit is pulled through. Case’s peristaltic robot lays the conduit while traveling, reducing the overall installation time.

Advancements in Burrowing Precision

“The peristaltic conduit approach is fascinating [and] certainly seems to be addressing concerns regarding the sheer variety of underground obstacles,” says the University of Florida’s Kury. However, he highlights a larger concern with undergrounding innovations—not just Case’s—in meeting a constantly evolving environment. Today’s underground will look very different in 10 years, as soil profiles shift, trees grow, animals tunnel, and people dig and build. “Underground cables will live for decades, and the sustainability of these technologies depends on how they adapt to this changing structure,” Kury added.

Daltorio notes that current undergrounding practices involve pouring concrete around the lines before backfilling to protect them from future excavation, a challenge for existing trenchless methods. But Case’s project brings two major benefits. First, by better understanding borehole design, engineers have more flexibility in choosing conduit materials to match the standards for particular environments. Also, advancements in burrowing precision could minimize the likelihood of future disruptions from human activities.

The research team is exploring different ways to reinforce the digging robot’s exterior while it’s underground.Olivia Gatchall

Daltorio’s team is collaborating with several partners, with Auburn University in Alabama contributing geotechnical expertise, Stony Brook University in New York running the modeling, and the University of Texas at Austin studying sediment interactions.

The project aims to halve undergrounding costs, though Daltorio cautions that it’s too early to commit to a specific cost model. Still, the time-saving potential appears promising. “With conventional approaches, planning, permitting and scheduling can take months,” Daltorio says. “By simplifying the process, it might be a few inspections at the endpoints, a few days of autonomous burrowing with minimal disruption to traffic above, followed by a few days of cleaning, splicing, and inspection.”



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

RoboCup German Open: 12–16 March 2025, NUREMBERG, GERMANYGerman Robotics Conference: 13–15 March 2025, NUREMBERG, GERMANYEuropean Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

Last year, we unveiled the new Atlas—faster, stronger, more compact, and less messy. We’re designing the world’s most dynamic humanoid robot to do anything and everything, but we get there one step at a time. Our first task is part sequencing, a common logistics task in automotive manufacturing. Discover why we started with sequencing, how we are solving hard problems, and how we’re delivering a humanoid robot with real value.

My favorite part is 1:40, where Atlas squats down to pick a part up off the ground.

[ Boston Dynamics ]

I’m mostly impressed that making contact with that stick doesn’t cause the robot to fall over.

[ Unitree ]

Professor Patrícia Alves-Oliveira is studying authenticity of artworks co-created by an artist and a robot. Her research lab, Robot Studio, is developing methods to authenticate artwork by analyzing their entire creative process. This is accomplished by using the artist’s biometrics as well as the process of artwork creation, from the first brushstroke to the final painting. This work aims to bring ownership back to artists in the age of generative AI.

[ Robot Studio ] at [ University of Michigan ]

Hard to believe that RoMeLa has been developing humanoid robots for 20 (!) years. Here’s to 20 more!

[ RoMeLa ] at [ University of California Los Angeles ]

In this demo, Reachy 2 autonomously sorts healthy and unhealthy foods. No machine learning, no pre-trained AI—just real-time object detection!

[ Pollen ]

Biological snakes achieve high mobility with numerous joints, inspiring snake-like robots for rescue and inspection. However, conventional designs feature a limited number of joints. This paper presents an underactuated snake robot consisting of many passive links that can dynamically change its joint coupling configuration by repositioning motor-driven joint units along internal rack gears. Furthermore, a soft robot skin wirelessly powers the units, eliminating wire tangling and disconnection risks.

[ Paper ]

Thanks, Ayato!

Tech United Eindhoven is working on quadrupedal soccer robots, which should be fun.

[ Tech United ]

Autonomous manipulation in everyday tasks requires flexible action generation to handle complex, diverse real-world environments, such as objects with varying hardness and softness. Imitation Learning (IL) enables robots to learn complex tasks from expert demonstrations. However, a lot of existing methods rely on position/unilateral control, leaving challenges in tasks that require force information/control, like carefully grasping fragile or varying-hardness objects. To address these challenges, we introduce Bilateral Control-Based Imitation Learning via Action Chunking with Transformers(Bi-ACT) and”A” “L”ow-cost “P”hysical “Ha”rdware Considering Diverse Motor Control Modes for Research in Everyday Bimanual Robotic Manipulation (ALPHA-α).

[ Alpha-Biact ]

Thanks, Masato!

Powered by UBTECH’s revolutionary framework “BrainNet”, a team of Walker S1 humanoid robots work together to master complex tasks at Zeekr’s Smart Factory! Teamwork makes the dream of robots work.

[ UBTECH ]

Personal mobile robotic assistants are expected to find wide applications in industry and healthcare. However, manually steering a robot while in motion requires significant concentration from the operator, especially in tight or crowded spaces. This work presents a virtual leash with which a robot can naturally follow an operator. We successfully validate on the ANYmal platform the robustness and performance of our entire pipeline in real-world experiments.

[ ETH Zurich Robotic Systems Lab ]

I do not ever want to inspect a wind turbine blade from the inside.

[ Flyability ]

Sometimes you can learn more about a robot from an instructional unboxing video than from a fancy demo.

[ DEEP Robotics ]

Researchers at Penn Engineering have discovered that certain features of AI-governed robots carry security vulnerabilities and weaknesses that were previously unidentified and unknown. Funded by the National Science Foundation and the Army Research Laboratory, the research aims to address the emerging vulnerability for ensuring the safe deployment of large language models (LLMs) in robotics.

[ RoboPAIR ]

ReachBot is a joint project between Stanford and NASA to explore a new approach to mobility in challenging environments such as martian caves. It consists of a compact robot body with very long extending arms, based on booms used for extendable antennas. The booms unroll from a coil and can extend many meters in low gravity. In this talk I will introduce the ReachBot design and motion planning considerations, report on a field test with a single ReachBot arm in a lava tube in the Mojave Desert, and discuss future plans, which include the possibility of mounting one or more ReachBot arms equipped with wrists and grippers on a mobile platform – such as ANYMal.

[ ReachBot ]



Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

RoboCup German Open: 12–16 March 2025, NUREMBERG, GERMANYGerman Robotics Conference: 13–15 March 2025, NUREMBERG, GERMANYEuropean Robotics Forum: 25–27 March 2025, STUTTGART, GERMANYRoboSoft 2025: 23–26 April 2025, LAUSANNE, SWITZERLANDICUAS 2025: 14–17 May 2025, CHARLOTTE, NCICRA 2025: 19–23 May 2025, ATLANTA, GALondon Humanoids Summit: 29–30 May 2025, LONDONIEEE RCAR 2025: 1–6 June 2025, TOYAMA, JAPAN2025 Energy Drone & Robotics Summit: 16–18 June 2025, HOUSTON, TXRSS 2025: 21–25 June 2025, LOS ANGELESETH Robotics Summer School: 21–27 June 2025, GENEVAIAS 2025: 30 June–4 July 2025, GENOA, ITALYICRES 2025: 3–4 July 2025, PORTO, PORTUGALIEEE World Haptics: 8–11 July 2025, SUWON, KOREAIFAC Symposium on Robotics: 15–18 July 2025, PARISRoboCup 2025: 15–21 July 2025, BAHIA, BRAZIL

Enjoy today’s videos!

Last year, we unveiled the new Atlas—faster, stronger, more compact, and less messy. We’re designing the world’s most dynamic humanoid robot to do anything and everything, but we get there one step at a time. Our first task is part sequencing, a common logistics task in automotive manufacturing. Discover why we started with sequencing, how we are solving hard problems, and how we’re delivering a humanoid robot with real value.

My favorite part is 1:40, where Atlas squats down to pick a part up off the ground.

[ Boston Dynamics ]

I’m mostly impressed that making contact with that stick doesn’t cause the robot to fall over.

[ Unitree ]

Professor Patrícia Alves-Oliveira is studying authenticity of artworks co-created by an artist and a robot. Her research lab, Robot Studio, is developing methods to authenticate artwork by analyzing their entire creative process. This is accomplished by using the artist’s biometrics as well as the process of artwork creation, from the first brushstroke to the final painting. This work aims to bring ownership back to artists in the age of generative AI.

[ Robot Studio ] at [ University of Michigan ]

Hard to believe that RoMeLa has been developing humanoid robots for 20 (!) years. Here’s to 20 more!

[ RoMeLa ] at [ University of California Los Angeles ]

In this demo, Reachy 2 autonomously sorts healthy and unhealthy foods. No machine learning, no pre-trained AI—just real-time object detection!

[ Pollen ]

Biological snakes achieve high mobility with numerous joints, inspiring snake-like robots for rescue and inspection. However, conventional designs feature a limited number of joints. This paper presents an underactuated snake robot consisting of many passive links that can dynamically change its joint coupling configuration by repositioning motor-driven joint units along internal rack gears. Furthermore, a soft robot skin wirelessly powers the units, eliminating wire tangling and disconnection risks.

[ Paper ]

Thanks, Ayato!

Tech United Eindhoven is working on quadrupedal soccer robots, which should be fun.

[ Tech United ]

Autonomous manipulation in everyday tasks requires flexible action generation to handle complex, diverse real-world environments, such as objects with varying hardness and softness. Imitation Learning (IL) enables robots to learn complex tasks from expert demonstrations. However, a lot of existing methods rely on position/unilateral control, leaving challenges in tasks that require force information/control, like carefully grasping fragile or varying-hardness objects. To address these challenges, we introduce Bilateral Control-Based Imitation Learning via Action Chunking with Transformers(Bi-ACT) and”A” “L”ow-cost “P”hysical “Ha”rdware Considering Diverse Motor Control Modes for Research in Everyday Bimanual Robotic Manipulation (ALPHA-α).

[ Alpha-Biact ]

Thanks, Masato!

Powered by UBTECH’s revolutionary framework “BrainNet”, a team of Walker S1 humanoid robots work together to master complex tasks at Zeekr’s Smart Factory! Teamwork makes the dream of robots work.

[ UBTECH ]

Personal mobile robotic assistants are expected to find wide applications in industry and healthcare. However, manually steering a robot while in motion requires significant concentration from the operator, especially in tight or crowded spaces. This work presents a virtual leash with which a robot can naturally follow an operator. We successfully validate on the ANYmal platform the robustness and performance of our entire pipeline in real-world experiments.

[ ETH Zurich Robotic Systems Lab ]

I do not ever want to inspect a wind turbine blade from the inside.

[ Flyability ]

Sometimes you can learn more about a robot from an instructional unboxing video than from a fancy demo.

[ DEEP Robotics ]

Researchers at Penn Engineering have discovered that certain features of AI-governed robots carry security vulnerabilities and weaknesses that were previously unidentified and unknown. Funded by the National Science Foundation and the Army Research Laboratory, the research aims to address the emerging vulnerability for ensuring the safe deployment of large language models (LLMs) in robotics.

[ RoboPAIR ]

ReachBot is a joint project between Stanford and NASA to explore a new approach to mobility in challenging environments such as martian caves. It consists of a compact robot body with very long extending arms, based on booms used for extendable antennas. The booms unroll from a coil and can extend many meters in low gravity. In this talk I will introduce the ReachBot design and motion planning considerations, report on a field test with a single ReachBot arm in a lava tube in the Mojave Desert, and discuss future plans, which include the possibility of mounting one or more ReachBot arms equipped with wrists and grippers on a mobile platform – such as ANYMal.

[ ReachBot ]



Although they’re a staple of sci-fi movies and conspiracy theories, in real life, tiny flying microbots—weighed down by batteries and electronics—have struggled to get very far. But a new combination of circuits and lightweight solid-state batteries called a “flying batteries” topology could let these bots really take off, potentially powering microbots for hours from a system that weighs milligrams.

Microbots could be an important technology to find people buried in rubble or scout ahead in other dangerous situations. But they’re a difficult engineering challenge, says Patrick Mercier, an electrical and computer engineering professor at the University of California, San Diego. Mercier’s student Zixiao Lin described the new circuit last month at the IEEE International Solid State Circuits Conference (ISSCC). “You have these really tiny robots, and you want them to last as long as possible in the field,” Mercier says. “The best way to do that is to use lithium-ion batteries, because they have the best energy density. But there’s this fundamental problem, where the actuators need much higher voltage than what the battery is capable of providing.”

A lithium cell can provide about 4 volts, but piezoelectric actuators for microbots need tens to hundreds of volts, explains Mercier. Researchers, including Mercier’s own group, have developed circuits such as boost converters to pump up the voltage. But because they need relatively large inductors or a bunch of capacitors, these add too much mass and volume, typically taking up about as much room as the battery itself.

A new kind of solid-state battery, developed at the French national electronics laboratory CEA-Leti, offered a potential solution. The batteries are a thin-film stack of material, including lithium cobalt oxide and lithium phosphorus oxynitride, made using semiconductor processing technology, and they can be diced up into tiny cells. A 0.33-cubic-millimeter, 0.8-milligram cell can store 20 microampere-hours of charge, or about 60 ampere-hours per liter. (Lithium-ion earbud batteries provide more than 100 Ah/L, but are about 1,000 times as large.) A CEA-Leti spinoff based on the technology, Inject Power, in Grenoble, France, is gearing up to begin volume manufacturing in late 2026.

Stacking Batteries on the Fly

Because a solid-state battery can be diced up into tiny cells, researchers thought that they could achieve high voltages using a circuit that needs no capacitors or inductors. Instead, the circuit actively rearranges the connections among many tiny batteries moving them from parallel to serial and back again.

Imagine a microdrone that moves by flapping wings attached to a piezoelectric actuator. On its circuit board are a dozen or so of the solid-state microbatteries. Each battery is part of a circuit consisting of four transistors. These act as switches that can dynamically change the connection to that battery’s neighbor so that it is either parallel, so they share the same voltage, or serial, so their voltages are added.

At the start, all the batteries are in parallel, delivering a voltage that is nowhere near enough to trigger the actuator. The 2-square-millimeter IC the UCSD team built then begins opening and closing the transistor switches. This rearranges the connections between the cells so that first two cells are connected serially, then three, then four, and so on. In a few hundredths of a second, the batteries are all connected in series, and the voltage has piled so much charge onto the actuator that it snaps the microbot’s wings down. The IC then unwinds the process, making the batteries parallel again, one at a time.

The integrated circuit in the “flying battery” has a total area of 2 square millimeters.Patrick Mercier

Adiabatic Charging

Why not just connect every battery in series at once instead of going through this ramping up and down scheme? In a word, efficiency.

As long as the battery serialization and parallelization is done at a low-enough frequency, the system is charging adiabatically. That is, its power losses are minimized.

But it’s what happens after the actuator triggers “where the real magic comes in,” says Mercier. The piezoelectric actuator in the circuit acts like a capacitor, storing energy. “Just like you have regenerative breaking in a car, we can recover some of the energy that we stored in this actuator.” As each battery is unstacked, the remaining energy storage system has a lower voltage than the actuator, so some charge flows back into the batteries.

The UCSD team actually tested two varieties of solid-state microbatteries—1.5-volt ceramic version from Tokyo-based TDK (CeraCharge 1704-SSB) and a 4-V custom design from CEA-Leti. With 1.6 grams of TDK cells, the circuit reached 56.1 volts and delivered a power density of 79 milliwatts per gram, but with 0.014 grams of the custom storage, it maxed out at 68 V, and demonstrated a power density of 4,500 mW/g.

Mercier plans to test the system with robotics partners while his team and CEA-Leti work to improved the flying batteries system’s packaging, miniaturization, and other properties. One important characteristic that needs work is the internal resistance of the microbatteries. “The challenge there is that the more you stack, the higher the series resistance is, and therefore the lower the frequency we can operate the system,” he says.

Nevertheless, Mercier seems bullish on flying batteries’ chances of keeping microbots aloft. “Adiabatic charging with charge recovery and no passives: Those are two wins that help increase flight time.”



Although they’re a staple of sci-fi movies and conspiracy theories, in real life, tiny flying microbots—weighed down by batteries and electronics—have struggled to get very far. But a new combination of circuits and lightweight solid-state batteries called a “flying batteries” topology could let these bots really take off, potentially powering microbots for hours from a system that weighs milligrams.

Microbots could be an important technology to find people buried in rubble or scout ahead in other dangerous situations. But they’re a difficult engineering challenge, says Patrick Mercier, an electrical and computer engineering professor at the University of California, San Diego. Mercier’s student Zixiao Lin described the new circuit last month at the IEEE International Solid State Circuits Conference (ISSCC). “You have these really tiny robots, and you want them to last as long as possible in the field,” Mercier says. “The best way to do that is to use lithium-ion batteries, because they have the best energy density. But there’s this fundamental problem, where the actuators need much higher voltage than what the battery is capable of providing.”

A lithium cell can provide about 4 volts, but piezoelectric actuators for microbots need tens to hundreds of volts, explains Mercier. Researchers, including Mercier’s own group, have developed circuits such as boost converters to pump up the voltage. But because they need relatively large inductors or a bunch of capacitors, these add too much mass and volume, typically taking up about as much room as the battery itself.

A new kind of solid-state battery, developed at the French national electronics laboratory CEA-Leti, offered a potential solution. The batteries are a thin-film stack of material, including lithium cobalt oxide and lithium phosphorus oxynitride, made using semiconductor processing technology, and they can be diced up into tiny cells. A 0.33-cubic-millimeter, 0.8-milligram cell can store 20 microampere-hours of charge, or about 60 ampere-hours per liter. (Lithium-ion earbud batteries provide more than 100 Ah/L, but are about 1,000 times as large.) A CEA-Leti spinoff based on the technology, Inject Power, in Grenoble, France, is gearing up to begin volume manufacturing in late 2026.

Stacking Batteries on the Fly

Because a solid-state battery can be diced up into tiny cells, researchers thought that they could achieve high voltages using a circuit that needs no capacitors or inductors. Instead, the circuit actively rearranges the connections among many tiny batteries moving them from parallel to serial and back again.

Imagine a microdrone that moves by flapping wings attached to a piezoelectric actuator. On its circuit board are a dozen or so of the solid-state microbatteries. Each battery is part of a circuit consisting of four transistors. These act as switches that can dynamically change the connection to that battery’s neighbor so that it is either parallel, so they share the same voltage, or serial, so their voltages are added.

At the start, all the batteries are in parallel, delivering a voltage that is nowhere near enough to trigger the actuator. The 2-square-millimeter IC the UCSD team built then begins opening and closing the transistor switches. This rearranges the connections between the cells so that first two cells are connected serially, then three, then four, and so on. In a few hundredths of a second, the batteries are all connected in series, and the voltage has piled so much charge onto the actuator that it snaps the microbot’s wings down. The IC then unwinds the process, making the batteries parallel again, one at a time.

The integrated circuit in the “flying battery” has a total area of 2 square millimeters.Patrick Mercier

Adiabatic Charging

Why not just connect every battery in series at once instead of going through this ramping up and down scheme? In a word, efficiency.

As long as the battery serialization and parallelization is done at a low-enough frequency, the system is charging adiabatically. That is, its power losses are minimized.

But it’s what happens after the actuator triggers “where the real magic comes in,” says Mercier. The piezoelectric actuator in the circuit acts like a capacitor, storing energy. “Just like you have regenerative breaking in a car, we can recover some of the energy that we stored in this actuator.” As each battery is unstacked, the remaining energy storage system has a lower voltage than the actuator, so some charge flows back into the batteries.

The UCSD team actually tested two varieties of solid-state microbatteries—1.5-volt ceramic version from Tokyo-based TDK (CeraCharge 1704-SSB) and a 4-V custom design from CEA-Leti. With 1.6 grams of TDK cells, the circuit reached 56.1 volts and delivered a power density of 79 milliwatts per gram, but with 0.014 grams of the custom storage, it maxed out at 68 V, and demonstrated a power density of 4,500 mW/g.

Mercier plans to test the system with robotics partners while his team and CEA-Leti work to improved the flying batteries system’s packaging, miniaturization, and other properties. One important characteristic that needs work is the internal resistance of the microbatteries. “The challenge there is that the more you stack, the higher the series resistance is, and therefore the lower the frequency we can operate the system,” he says.

Nevertheless, Mercier seems bullish on flying batteries’ chances of keeping microbots aloft. “Adiabatic charging with charge recovery and no passives: Those are two wins that help increase flight time.”

Pages