Feed aggregator

Past work has shown model predictive control (MPC) to be an effective strategy for controlling continuum joint soft robots using basic lumped-parameter models. However, the inaccuracies of these models often mean that an integral control scheme must be combined with MPC. In this paper we present a novel dynamic model formulation for continuum joint soft robots that is more accurate than previous models yet remains tractable for fast MPC. This model is based on a piecewise constant curvature (PCC) assumption and a relatively new kinematic representation that allows for computationally efficient state prediction. However, due to the difficulty in determining model parameters (e.g., inertias, damping, and spring effects) as well as effects common in continuum joint soft robots (hysteresis, complex pressure dynamics, etc.), we submit that regardless of the model selected, most model-based controllers of continuum joint soft robots would benefit from online model adaptation. Therefore, in this paper we also present a form of adaptive model predictive control based on model reference adaptive control (MRAC). We show that like MRAC, model reference predictive adaptive control (MRPAC) is able to compensate for “parameter mismatch" such as unknown inertia values. Our experiments also show that like MPC, MRPAC is robust to “structure mismatch” such as unmodeled disturbance forces not represented in the form of the adaptive regressor model. Experiments in simulation and hardware show that MRPAC outperforms individual MPC and MRAC.

Recently Yujin Robot launched a new 3D LiDAR for indoor service robot, AGVs/AMRs and smart factory.  The YRL3 series is a line of precise laser sensors for vertical and horizontal scanning to detect environments or objects.  The Yujin Robot YRL3 series LiDAR is designed for indoor applications and utilizes an innovative 3D scanning LiDAR for a 270°(Horizontal) x 90°(vertical) dynamic field of view as a single channel.  The fundamental principle is based on direct ToF (Time of Flight) and designed to measure distances towards surroundings.  YRL3 collect useful data including ranges, angles, intensities and Cartesian coordinates (x,y,z).  Real-time vertical right-angle adjustment is possible and supports powerful S/W package for autonomous driving devices.

“In recent years, our product lineup expanded to include models for the Fourth Industrial Revolution,” shares the marketing team of Yujin Robot.  These models namely are Kobuki, the ROS reference research robot platform used by robotics research labs around the world, the Yujin LiDAR range-finding scanning sensor for LiDAR-based autonomous driving, AMS solution (Autonomous Mobility Solution) for customized autonomous driving.  The company continues to push the boundaries of robotics and artificial intelligence, developing game-changing autonomous solutions that give companies around the world an edge over the competition.

aside.inlay.xlrg { display: none; } aside.inlay.pullquote.xlrg { display: block; }

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):

AUVSI EXPONENTIAL 2020 – October 5-8, 2020 – [Online] IROS 2020 – October 25-29, 2020 – [Online] ROS World 2020 – November 12, 2020 – [Online] CYBATHLON 2020 – November 13-14, 2020 – [Online] ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA

Let us know if you have suggestions for next week, and enjoy today’s videos.

Bear Robotics, a robotics and artificial intelligence company, and SoftBank Robotics Group, a leading robotics manufacturer and solutions provider, have collaborated to bring a new robot named Servi to the food service and hospitality field.

[ Bear Robotics ]

A literal in-depth look at Engineered Arts’ Mesmer android.

Engineered Arts ]

Is your robot running ROS? Is it connected to the Internet? Are you actually in control of it right now? Are you sure?

I appreciate how the researchers admitted to finding two of their own robots as part of the scan, a Baxter and a drone.

[ Brown ]

Smile Robotics describes this as “(possibly) world’s first full-autonomous clear-up-the-table robot.”

We’re not qualified to make a judgement on the world firstness, but personally I hate clearing tables, so this robot has my vote.

Smile Robotics founder and CEO Takashi Ogura, along with chief engineer Mitsutaka Kabasawa and engineer Kazuya Kobayashi, are former Google roboticists. Ogura also worked at SCHAFT. Smile says its robot uses ROS and is controlled by a framework written mainly in Rust, adding: “We are hiring Rustacean Roboticists!”  

[ Smile Robotics ]

We’re not entirely sure why, but Panasonic has released plans for an Internet of Things system for hamsters.

We devised a recipe for a "small animal healthcare device" that can measure the weight and activity of small animals, the temperature and humidity of the breeding environment, and manage their health. This healthcare device visualizes the health status and breeding environment of small animals and manages their health to promote early detection of diseases. While imagining the scene where a healthcare device is actually used for an important small animal that we treat with affection, we hope to help overcome the current difficult situation through manufacturing.

[ Panasonic ] via [ RobotStart ]

Researchers at Yale have developed a robotic fabric, a breakthrough that could lead to such innovations as adaptive clothing, self-deploying shelters, or lightweight shape-changing machinery.

The researchers focused on processing functional materials into fiber-form so they could be integrated into fabrics while retaining its advantageous properties. For example, they made variable stiffness fibers out of an epoxy embedded with particles of Field’s metal, an alloy that liquifies at relatively low temperatures. When cool, the particles are solid metal and make the material stiffer; when warm, the particles melt into liquid and make the material softer.

Yale ]

In collaboration with Armasuisse and SBB, RSL demonstrated the use of a teleoperated Menzi Muck M545 to clean up a rock slide in Central Switzerland. The machine can be operated from a teloperation platform with visual and motion feedback. The walking excavator features an active chassis that can adapt to uneven terrain.


An international team of JKU researchers is continuing to develop their vision for robots made out of soft materials. A new article in the journal "Communications Materials" demonstrates just how these kinds of soft machines react using weak magnetic fields to move very quickly. A triangle-shaped robot can roll itself in air at high speed and walk forward when exposed to an alternating in-plane square wave magnetic field (3.5 mT, 1.5 Hz). The diameter of the robot is 18 mm with a thickness of 80 µm. A six-arm robot can grab, transport, and release non-magnetic objects such as a polyurethane foam cube controlled by a permanent magnet.

Okay but tell me more about that cute sheep.


Interbotix has this “research level robotic crawler,” which both looks mean and runs ROS, a dangerous combination.

And here’s how it all came together:

[ Interbotix ]

I guess if you call them “loitering missile systems” rather than “drones that blow things up” people are less likely to get upset?

[ AeroVironment ]

In this video, we show a planner for a master dual-arm robot to manipulate tethered tools with an assistant dual-arm robot’s help. The assistant robot provides assistance to the master robot by manipulating the tool cable and avoiding collisions. The provided assistance allows the master robot to perform tool placements on the robot workspace table to regrasp the tool, which would typically fail since the tool cable tension may change the tool positions. It also allows the master robot to perform tool handovers, which would normally cause entanglements or collisions with the cable and the environment without the assistance.

[ Harada Lab ]

This video shows a flexible and robust robotic system for autonomous drawing on 3D surfaces. The system takes 2D drawing strokes and a 3D target surface (mesh or point clouds) as input. It maps the 2D strokes onto the 3D surface and generates a robot motion to draw the mapped strokes using visual recognition, grasp pose reasoning, and motion planning.

[ Harada Lab ]

Weekly mobility test. This time the Warthog takes on a fallen tree. Will it cross it? The answer is in the video!

And the answer is: kinda?


One of the advantages of walking machines is their ability to apply forces in all directions and of various magnitudes to the environment. Many of the multi-legged robots are equipped with point contact feet as these simplify the design and control of the robot. The iStruct project focuses on the development of a foot that allows extensive contact with the environment.

[ DFKI ]

An urgent medical transport was simulated in NASA’s second Systems Integration and Operationalization (SIO) demonstration Sept. 28 with partner Bell Textron Inc. Bell used the remotely-piloted APT 70 to conduct a flight representing an urgent medical transport mission. It is envisioned in the future that an operational APT 70 could provide rapid medical transport for blood, organs, and perishable medical supplies (payload up to 70 pounds). The APT 70 is estimated to move three times as fast as ground transportation.

Always a little suspicious when the video just shows the drone flying, and sitting on the ground, but not that tricky transition between those two states.

[ NASA ]

A Lockheed Martin Robotics Seminar on “Socially Assistive Mobile Robots,” by Yi Guo from Stevens Institute of Technology.

The use of autonomous mobile robots in human environments is on the rise. Assistive robots have been seen in real-world environments, such as robot guides in airports, robot polices in public parks, and patrolling robots in supermarkets. In this talk, I will first present current research activities conducted in the Robotics and Automation Laboratory at Stevens. I’ll then focus on robot-assisted pedestrian regulation, where pedestrian flows are regulated and optimized through passive human-robot interaction.

[ UMD ]

This week’s CMU RI Seminar is by CMU’s Zachary Manchester, on “The World’s Tiniest Space Program.”

The aerospace industry has experienced a dramatic shift over the last decade: Flying a spacecraft has gone from something only national governments and large defense contractors could afford to something a small startup can accomplish on a shoestring budget. A virtuous cycle has developed where lower costs have led to more launches and the growth of new markets for space-based data. However, many barriers remain. This talk will focus on driving these trends to their ultimate limit by harnessing advances in electronics, planning, and control to build spacecraft that cost less than a new smartphone and can be deployed in large numbers.

[ CMU RI ]

Brain-computer interfaces (BCIs) have long been seen as control interfaces that translate changes in brain activity, produced either by means of a volitional modulation or in response to an external stimulation. However, recent trends in the BCI and neurofeedback research highlight passive monitoring of a user's brain activity in order to estimate cognitive load, attention level, perceived errors and emotions. Extraction of such higher order information from brain signals is seen as a gateway for facilitation of interaction between humans and intelligent systems. Particularly in the field of robotics, passive BCIs provide a promising channel for prediction of user's cognitive and affective state for development of a user-adaptive interaction. In this paper, we first illustrate the state of the art in passive BCI technology and then provide examples of BCI employment in human-robot interaction (HRI). We finally discuss the prospects and challenges in integration of passive BCIs in socially demanding HRI settings. This work intends to inform HRI community of the opportunities offered by passive BCI systems for enhancement of human-robot interaction while recognizing potential pitfalls.

aside.inlay.xlrg { display: none; } aside.inlay.pullquote.xlrg { display: block; }

Yesterday, the Toyota Research Institute (TRI) showed off some of the projects that it’s been working on recently, including a ceiling-mounted robot that could one day help us with household chores. That system is just one example of how TRI envisions the future of robotics and artificial intelligence. As TRI CEO Gill Pratt told us, the company is focusing on robotics and AI technology for “amplifying, rather than replacing, human beings.” In other words, Toyota wants to develop robots not for convenience or to do our jobs for us, but rather to allow people to continue to live and work independently even as we age.

To better understand Toyota’s vision of robotics 15 to 20 years from now, it’s worth watching the 20-minute video below, which depicts various scenarios “where the application of robotic capabilities is enabling members of an aging society to live full and independent lives in spite of the challenges that getting older brings.” It’s a long video, but it helps explains TRI’s perspective on how robots will collaborate with humans in our daily lives over the next couple of decades.

Those are some interesting conceptual telepresence-controlled bipeds they’ve got running around in that video, right?

For more details, we sent TRI some questions on how it plans to go from concepts like the ones shown in the video to real products that can be deployed in human environments. Below are answers from TRI CEO Gill Pratt, who is also chief scientist for Toyota Motor Corp.; Steffi Paepcke, senior UX designer at TRI; and Max Bajracharya, VP of robotics at TRI.

IEEE Spectrum: TRI seems to have a more explicit focus on eventual commercialization than most of the robotics research that we cover. At what point TRI starts to think about things like reliability and cost?

Photo: TRI Toyota is exploring robots capable of manipulating dishes in a sink and a dishwasher, performing experiments and simulations to make sure that the robots can handle a wide range of conditions. 

Gill Pratt: It’s a really interesting question, because the normal way to think about this would be to say, well, both reliability and cost are product development tasks. But actually, we need to think about it at the earliest possible stage with research as well. The hardware that we use in the laboratory for doing experiments, we don’t worry about cost there, or not nearly as much as you’d worry about for a product. However, in terms of what research we do, we very much have to think about, is it possible (if the research is successful) for it to end up in a product that has a reasonable cost. Because if a customer can’t afford what we come up with, maybe it has some academic value but it’s not actually going to make a difference in their quality of life in the real world. So we think about cost very much from the beginning.

The same is true with reliability. Right now, we’re working very hard to make our control techniques robust to wide variations in the environment. For instance, in work that Russ Tedrake is doing with manipulating dishes in a sink and a dishwasher, both in physical testing and in simulation, we’re doing thousands and now millions of different experiments to make sure that we can handle the edge cases and it works over a very wide range of conditions.

A tremendous amount of work that we do is trying to bring robotics out of the age of doing demonstrations. There’s been a history of robotics where for some time, things have not been reliable, so we’d catch the robot succeeding just once and then show that video to the world, and people would get the mis-impression that it worked all of the time. Some researchers have been very good about showing the blooper reel too, to show that some of the time, robots don’t work.

“A tremendous amount of work that we do is trying to bring robotics out of the age of doing demonstrations. There’s been a history of robotics where for some time, things have not been reliable, so we’d catch the robot succeeding just once and then show that video to the world, and people would get the mis-impression that it worked all of the time.” —Gill Pratt, TRI

In the spirit of sharing things that didn’t work, can you tell us a bit about some of the robots that TRI has had under development that didn’t make it into the demo yesterday because they were abandoned along the way?

Steffi Paepcke: We’re really looking at how we can connect people; it can be hard to stay in touch and see our loved ones as much as we would like to. There have been a few prototypes that we’ve worked on that had to be put on the shelf, at least for the time being. We were exploring how to use light so that people could be ambiently aware of one another across distances. I was very excited about that—the internal name was “glowing orb.” For a variety of reasons, it didn’t work out, but it was really fascinating to investigate different modalities for keeping in touch.

Another prototype we worked on—we found through our research that grocery shopping is obviously an important part of life, and for a lot of older adults, it’s not necessarily the right answer to always have groceries delivered. Getting up and getting out of the house keeps you physically active, and a lot of people prefer to continue doing it themselves. But it can be challenging, especially if you’re purchasing heavy items that you need to transport. We had a prototype that assisted with grocery shopping, but when we pivoted our focus to Japan, we found that the inside of a Japanese home really needs to stay inside, and the outside needs to stay outside, so a robot that traverses both domains is probably not the right fit for a Japanese audience, and those were some really valuable lessons for us.

Photo: TRI

Toyota recently demonstrated a gantry robot that would hang from the ceiling to perform tasks like wiping surfaces and clearing clutter.

I love that TRI is exploring things like the gantry robot both in terms of near-term research and as part of its long-term vision, but is a robot like this actually worth pursuing? Or more generally, what’s the right way to compromise between making an environment robot friendly, and asking humans to make changes to their homes?

Max Bajracharya: We think a lot about the problems that we’re trying to address in a holistic way. We don’t want to just give people a robot, and assume that they’re not going to change anything about their lifestyle. We have a lot of evidence from people who use automated vacuum cleaners that people will adapt to the tools you give them, and they’ll change their lifestyle. So we want to think about what is that trade between changing the environment, and giving people robotic assistance and tools.

We certainly think that there are ways to make the gantry system plausible. The one you saw today is obviously a prototype and does require significant infrastructure. If we’re going to retrofit a home, that isn’t going to be the way to do it. But we still feel like we’re very much in the prototype phase, where we’re trying to understand whether this is worth it to be able to bypass navigation challenges, and coming up with the pros and cons of the gantry system. We’re evaluating whether we think this is the right approach to solving the problem.

To what extent do you think humans should be either directly or indirectly in the loop with home and service robots?

Bajracharya: Our goal is to amplify people, so achieving this is going to require robots to be in a loop with people in some form. One thing we have learned is that using people in a slow loop with robots, such as teaching them or helping them when they make mistakes, gives a robot an important advantage over one that has to do everything perfectly 100 percent of the time. In unstructured human environments, robots are going to encounter corner cases, and are going to need to learn to adapt. People will likely play an important role in helping the robots learn.

Evolutionary robot systems are usually affected by the properties of the environment indirectly through selection. In this paper, we present and investigate a system where the environment also has a direct effect—through regulation. We propose a novel robot encoding method where a genotype encodes multiple possible phenotypes, and the incarnation of a robot depends on the environmental conditions taking place in a determined moment of its life. This means that the morphology, controller, and behavior of a robot can change according to the environment. Importantly, this process of development can happen at any moment of a robot's lifetime, according to its experienced environmental stimuli. We provide an empirical proof-of-concept, and the analysis of the experimental results shows that environmental regulation improves adaptation (task performance) while leading to different evolved morphologies, controllers, and behavior.

Over the last several years, Toyota has been putting more muscle into forward-looking robotics research than just about anyone. In addition to the Toyota Research Institute (TRI), there’s that massive 175-acre robot-powered city of the future that Toyota still plans to build next to Mount Fuji. Even Toyota itself acknowledges that it might be crazy, but that’s just how they roll—as TRI CEO Gill Pratt told me a while back, when Toyota decides to do something, they really do go all-in on it.

TRI has been focusing heavily on home robots, which is reflective of the long-term nature of what TRI is trying to do, because home robots are both the place where we’ll need robots the most at the same time as they’re the place where it’s going to be hardest to deploy them. The unpredictable nature of homes, and the fact that homes tend to have squishy fragile people in them, are robot-unfriendly characteristics, but as the population continues to age (an increasingly acute problem in Japan), homes offer an enormous amount of potential for helping us maintain our independence.

Today, Toyota is showing off some of the research that it’s been working on recently, in the form of a virtual reality presentation in lieu of an in-person press event. For journalists, TRI pre-loaded the recording onto a VR headset, which was FedEx’ed to my house. You can watch the entire 40-minute presentation in 360 video on YouTube (or in VR if you have a headset of your own), but if you don’t watch the whole thing, you should at least check out the full-on GLaDOS (with arms) that TRI thinks belongs in your home.

The presentation features an introduction from Gill Pratt, who looks entirely too comfortable embedded inside of one of TRI’s telepresence robots. The event also covers a lot of territory, but the highlight is almost certainly the new hardware that TRI demonstrates.

Soft bubble gripper Photo: TRI

This is a “soft bubble gripper,” under development at TRI’s Cambridge, Mass., branch. These passively-compliant, air-filled grippers make it easier to grasp many different kinds of objects safely, but the nifty thing is that they’ve got cameras inside of them watching a pattern of dots on the interior of the soft membrane.

When the outside of the bubble makes contact with an object, the bubble deforms, and the deformation of the dot pattern on the inside can be tracked by the camera to determine both directions and magnitudes of forces. This is a concept that we’ve seen elsewhere before, but TRI’s implementation is a clever way of making an inherently safe end effector that can still perform all the sensing you need it to do for relatively complex manipulation tasks. 

The bubble gripper was presented at ICRA this year, and you can read the technical paper here.

Ceiling-mounted home robot Photo: TRI

I don’t know whether robots dangling from the ceiling was somehow sinister pre-Portal, but it sure as heck is for me having played through that game a couple of times, and it’s since been reinforced by AUTO from WALL-E.

The reason that we generally see robots mounted on the floor or on tables or on mobile bases is that we’re bipeds, not bats, and giving a robot access to a human-like workspace is easiest to do if you also give that robot a human-like position and orientation. And if you want to be able to reach stuff high up, you do what TRI did with their previous generation of kitchen manipulator, and just give it the ability to make itself super tall. But TRI is convinced it’s a good place to put our future home robots:

One innovative concept is a “gantry robot” that would descend from an overhead framework to perform tasks such as loading the dishwasher, wiping surfaces, and clearing clutter. By traveling on the ceiling, the robot avoids the problems of navigating household floor clutter and navigating cramped spaces. When not in use, the robot would tuck itself up out of the way. To further investigate this idea, the team has built a laboratory prototype robot that can do all the same tasks as a floor-based mobile robot but with the innovative overhead mobility system.

Another obvious problem with the gantry robot is that you have to install all kinds of stuff in your ceiling for this to work, which makes it very impractical (if not totally impossible) to introduce a system like this into a home that wasn’t built specifically for it. If, however, you do build a home with a robot like this in mind, the animation below from TRI shows how it could be extra useful. Suddenly, stairs are a non-issue. Payload is presumably also a non-issue, since loads can be transferred to the ceiling. Batteries become unnecessary, so the whole robot can be much lighter weight, which in turn makes it safer. Sensors get a fantastic view, and obstacle avoidance becomes trivial.

Robots as “time machines” Photo: TRI

TRI’s presentation covered more than what we’ve highlighted here—our focus has been on the hardware prototypes, but TRI had more to talk about, including learning through demonstration, scaling learning through simulation, and how TRI has been working with users to figure out what research directions should be explored. It’s all available right now on YouTube, and it’s well worth 40 minutes of your time.

“What we’re really focused on is this principle idea of amplifying, rather than replacing, human beings” —Gill Pratt, TRI

It’s only been five years since Toyota announced the $1 billion investment that established TRI, and it feels like the progress that’s been made since then has been substantial. It’s not often that vision, resources, and long-term commitment come together like this, and TRI’s emphasis on making life better for people is one of the things that helps to keep us optimistic about the future of robotics.

“What we’re really focused on is this principle idea of amplifying, rather than replacing, human beings,” Gill Pratt told us. “And what it means to amplify a person, particularly as they’re aging—what we’re really trying to do is build a time machine. This may sound fanciful, and of course we can’t build a real time machine, but maybe we can build robotic assistants to make our lives as we age seem as if we are actually using a time machine.” He explains that it doesn’t mean building robots for convenience or to do our jobs for us. “It means building technology that enables us to continue to live and to work and to relate to each other as if we were younger,” he says. “And that’s really what our main goal is.”

A huge number of machine learning applications could receive a performance upgrade, thanks to a relatively minor modification to their underlying neural networks. 

If you are a developer creating a new machine learning application, you typically build on top of a existing neural network architecture, one that is already tuned for the kind of problem you are trying to solve—creating your own architecture from scratch is a difficult job that’s typically more trouble than it’s worth. Even with an existing architecture in hand, reengineering it for better performance is no small task. But one team has come up with new neural network module that can boost AI performance when plugged into four of the most widely used architectures.

Critically, the research funded by the U.S. National Science Foundation and Army Research Office achieves this performance boost through the new module without requiring much of an increase in computing power. It’s part of a broader project by North Carolina State University researchers to rethink the architecture of the neural networks involved in modern AI’s deep learning capabilities. 

“At the macro level, we try to redesign the entire neural network as a whole,” says Tianfu Wu, an electrical and computer engineer at North Carolina State University in Raleigh. “Then we try to focus on the specific components of the neural network.”

Wu and his colleagues presented their work (PDF) on the new neural network component, or module, named Attentive Normalization, at the virtual version of the 16th European Conference on Computer Vision in August. They have also released the code so that other researchers can plug the module into their own deep learning models.

The most noticeable improvement in performance came in the neural network architectures suited for mobile platforms such as smartphones

In preliminary testing, the group found that the new module improved performance in four mainstream neural network architectures: ResNets, DenseNets, MobileNetsV2 and AOGNets. The researchers checked the upgraded networks’ performances against two industry benchmarks for testing visual object recognition and classification, including ImageNet-1000 and MS-COCO 2017. For example, the new module boosted the top-1 accuracy in the ImageNet-1000 benchmark by between 0.5 percent and 2.7 percent. This may seem small, but it can make a significant difference in practice, not least because of the large scale of many machine learning deployments. 

Altogether, the diverse array of architectures are suitable for performing AI-driven tasks on both large computing systems and mobile devices with more limited computing power. But the most noticeable improvement in performance came in the neural network architectures suited for mobile platforms such as smartphones.

The key to the team’s success came from combining two neural network modules that usually operate separately. “In order to make a neural network more powerful or easier to train, feature normalization and feature attention are probably two of the most important components,” Wu says.

The feature normalization module helps to make sure that no single subset of the data used to train a neural network outweighs the other subsets in shaping the deep learning model. By comparing neural network training to driving a car on a dark road, Wu describes feature normalization as the car’s suspension system smoothing out the jolts from any bumps in the road.

By comparison, the feature attention module helps to focus on certain features in the training data that could better achieve the learning task at hand. Going back to the car analogy for training neural networks, the feature attention module represents the vehicle headlights showing what to look out for on the dark road ahead.

After scrutinizing both modules, the researchers realized that certain sub-processes in both modules overlap in the shared goal of re-calibrating certain features in the training data. That provided a natural integration point for combining feature normalization and feature attention in the new module. “We want to see different micro components in neural architecture that can be and should be integrated together to make them more effective,” Wu says. 

Wu and his colleagues also designed the new module so that it could perform the re-calibration task in a more dynamic and adaptive way than the standard modules. That may offer benefits when it comes to transfer learning—taking AI trained on one set of data to perform a given task and applying it to new data for a related task (for example, in a face recognition application, developers typically start with a network that’s good at identifying what objects in a camera’s view are faces, and then train it to recognize specific people).

The new module represents just one small part of the North Carolina State group’s vision for redesigning modern AI. For example, the researchers are trying to develop interpretable AI systems that allow humans to better understand the logic of AI decisions—a not insignificant problem for deep learning models based on neural networks. As one possible step toward that goal, Wu and his colleagues previously developed a framework for building deep neural networks based on a compositional grammar system.

Meanwhile, Wu still sees many other opportunities for fine-tuning smaller parts of neural networks without requiring a complete overhaul of the main architecture.

“There are so many other components in deep neural networks,” Wu says. “We probably also can take a similar angle and try to look at whether there are natural integration points to put them together, or try to redesign them in better a form.”

Photo: Sivaram V/Reuters A robot, developed by Asimov Robotics to spread awareness about the coronavirus, holds a tray with face masks and sanitizer.

As the coronavirus emergency exploded into a full-blown pandemic in early 2020, forcing countless businesses to shutter, robot-making companies found themselves in an unusual situation: Many saw a surge in orders. Robots don’t need masks, can be easily disinfected, and, of course, they don’t get sick.

An army of automatons has since been deployed all over the world to help with the crisis: They are monitoring patientssanitizing hospitalsmaking deliveries, and helping frontline medical workers reduce their exposure to the virus. Not all robots operate autonomously—many, in fact, require direct human supervision, and most are limited to simple, repetitive tasks. But robot makers say the experience they’ve gained during this trial-by-fire deployment will make their future machines smarter and more capable. These photos illustrate how robots are helping us fight this pandemic—and how they might be able to assist with the next one.

DROID TEAM Photo: Clement Uwiringiyimana/Reuters

A squad of robots serves as the first line of defense against person-to-person transmission at a medical center in Kigali, Rwanda. Patients walking into the facility get their temperature checked by the machines, which are equipped with thermal cameras atop their heads. Developed by UBTech Robotics, in China, the robots also use their distinctive appearance—they resemble characters out of a Star Wars movie—to get people’s attention and remind them to wash their hands and wear masks.

Photo: Clement Uwiringiyimana/Reuters SAY “AAH”

To speed up COVID-19 testing, a team of Danish doctors and engineers at the University of Southern Denmark and at Lifeline Robotics is developing a fully automated swab robot. It uses computer vision and machine learning to identify the perfect target spot inside the person’s throat; then a robotic arm with a long swab reaches in to collect the sample—all done with a swiftness and consistency that humans can’t match. In this photo, one of the creators, Esben Østergaard, puts his neck on the line to demonstrate that the robot is safe.

Photo: University of Southern Denmark GERM ZAPPER

After six of its doctors became infected with the coronavirus, the Sassarese hospital in Sardinia, Italy, tightened its safety measures. It also brought in the robots. The machines, developed by UVD Robots, use lidar to navigate autonomously. Each bot carries an array of powerful short-wavelength ultraviolet-C lights that destroy the genetic material of viruses and other pathogens after a few minutes of exposure. Now there is a spike in demand for UV-disinfection robots as hospitals worldwide deploy them to sterilize intensive care units and operating theaters.


In medical facilities, an ideal role for robots is taking over repetitive chores so that nurses and physicians can spend their time doing more important tasks. At Shenzhen Third People’s Hospital, in China, a robot called Aimbot drives down the hallways, enforcing face-mask and social-distancing rules and spraying disinfectant. At a hospital near Austin, Texas, a humanoid robot developed by Diligent Robotics fetches supplies and brings them to patients’ rooms. It repeats this task day and night, tirelessly, allowing the hospital staff to spend more time interacting with patients.

Photos, left: Diligent Robotics; Right: UBTech Robotics THE DOCTOR IS IN

Nurses and doctors at Circolo Hospital in Varese, in northern Italy—the country’s hardest-hit region—use robots as their avatars, enabling them to check on their patients around the clock while minimizing exposure and conserving protective equipment. The robots, developed by Chinese firm Sanbot, are equipped with cameras and microphones and can also access patient data like blood oxygen levels. Telepresence robots, originally designed for offices, are becoming an invaluable tool for medical workers treating highly infectious diseases like COVID-19, reducing the risk that they’ll contract the pathogen they’re fighting against.

Photo: Miguel Medina/AFP/Getty Images

HELP FROM ABOVE Photo: Zipline

Authorities in several countries attempted to use drones to enforce lockdowns and social-distancing rules, but the effectiveness of such measures remains unclear. A better use of drones was for making deliveries. In the United States, startup Zipline deployed its fixed-wing autonomous aircraft to connect two medical facilities 17 kilometers apart. For the staff at the Huntersville Medical Center, in North Carolina, masks, gowns, and gloves literally fell from the skies. The hope is that drones like Zipline’s will one day be able to deliver other kinds of critical materials, transport test samples, and distribute drugs and vaccines.


It’s not quite a robot takeover, but the streets and sidewalks of dozens of cities around the world have seen a proliferation of hurrying wheeled machines. Delivery robots are now in high demand as online orders continue to skyrocket.

In Hamburg, the six-wheeled robots developed by Starship Technologies navigate using cameras, GPS, and radar to bring groceries to customers.

Photo: Christian Charisius/Picture Alliance/Getty Images

In Medellín, Colombia, a startup called Rappi deployed a fleet of robots, built by Kiwibot, to deliver takeout to people in lockdown. 

Photo: Joaquin Sarmiento/AFP/Getty Images

China’s JD.com, one of the country’s largest e-commerce companies, is using 20 robots to transport goods in Changsha, Hunan province; each vehicle has 22 separate compartments, which customers unlock using face authentication.


Robots can’t replace real human interaction, of course, but they can help people feel more connected at a time when meetings and other social activities are mostly on hold.

In Ostend, Belgium, ZoraBots brought one of its waist-high robots, equipped with cameras, microphones, and a screen, to a nursing home, allowing residents like Jozef Gouwy to virtually communicate with loved ones despite a ban on in-person visits. 

Photo: Yves Herman/Reuters

In Manila, nearly 200 high school students took turns “teleporting” into a tall wheeled robot, developed by the school’s robotics club, to walk on stage during their graduation ceremony. 

Photo: Ezra Acayan/Getty Images

And while Japan’s Chiba Zoological Park was temporarily closed due to the pandemic, the zoo used an autonomous robotic vehicle called RakuRo, equipped with 360-degree cameras, to offer virtual tours to children quarantined at home.

Photo: Tomohiro Ohsumi/Getty Images SENTRY ROBOTS

Offices, stores, and medical centers are adopting robots as enforcers of a new coronavirus code.

At Fortis Hospital in Bangalore, India, a robot called Mitra uses a thermal camera to perform a preliminary screening of patients.

Photo: Manjunath Kiran/AFP/Getty Images

In Tunisia, the police use a tanklike robot to patrol the streets of its capital city, Tunis, verifying that citizens have permission to go out during curfew hours.

Photo: Khaled Nasraoui/Picture Alliance/Getty Images

And in Singapore, the Bishan-Ang Moh Kio Park unleashed a Spot robot dog, developed by Boston Dynamics, to search for social-distancing violators. Spot won’t bark at them but will rather play a recorded message reminding park-goers to keep their distance.

Photo: Roslan Rahman/AFP/Getty Images

This article appears in the October 2020 print issue as “How Robots Became Essential Workers.”

Fabrication of soft pneumatic bending actuators typically involves multiple steps to accommodate the formation of complex internal geometry and the alignment and bonding between soft and inextensible materials. The complexity of these processes intensifies when applied to multi-chamber and small-scale (~10 mm diameter) designs, resulting in poor repeatability. Designs regularly rely on combining multiple prefabricated single chamber actuators or are limited to simple (fixed cross-section) internal chamber geometry, which can result in excessive ballooning and reduced bending efficiency, compelling the addition of constraining materials. In this work, we address existing limitations by presenting a single material molding technique that uses parallel cores with helical features. We demonstrate that through specific orientation and alignment of these internal structures, small diameter actuators may be fabricated with complex internal geometry in a single material—without- additional design-critical steps. The helix design produces wall profiles that restrict radial expansion while allowing compact designs through chamber interlocking, and simplified demolding. We present and evaluate three-chambered designs with varied helical features, demonstrating appreciable bending angles (>180°), three-dimensional workspace coverage, and three-times bodyweight carrying capability. Through application and validation of the constant curvature assumption, forward kinematic models are presented for the actuator and calibrated to account for chamber-specific bending characteristics, resulting in a mean model tip error of 4.1 mm. This simple and inexpensive fabrication technique has potential to be scaled in size and chamber numbers, allowing for application-specific designs for soft, high-mobility actuators especially for surgical, or locomotion applications.

Given the features of a video, recurrent neural networks can be used to automatically generate a caption for the video. Existing methods for video captioning have at least three limitations. First, semantic information has been widely applied to boost the performance of video captioning models, but existing networks often fail to provide meaningful semantic features. Second, the Teacher Forcing algorithm is often utilized to optimize video captioning models, but during training and inference, different strategies are applied to guide word generation, leading to poor performance. Third, current video captioning models are prone to generate relatively short captions that express video contents inappropriately. Toward resolving these three problems, we suggest three corresponding improvements. First of all, we propose a metric to compare the quality of semantic features, and utilize appropriate features as input for a semantic detection network (SDN) with adequate complexity in order to generate meaningful semantic features for videos. Then, we apply a scheduled sampling strategy that gradually transfers the training phase from a teacher-guided manner toward a more self-teaching manner. Finally, the ordinary logarithm probability loss function is leveraged by sentence length so that the inclination of generating short sentences is alleviated. Our model achieves better results than previous models on the YouTube2Text dataset and is competitive with the previous best model on the MSR-VTT dataset.

Among all of the other in-person events that have been totally wrecked by COVID-19 is the Cave Circuit of the DARPA Subterranean Challenge. DARPA has already hosted the in-person events for the Tunnel and Urban SubT circuits (see our previous coverage here), and the plan had always been for a trio of events representing three uniquely different underground environments in advance of the SubT Finals, which will somehow combine everything into one bonkers course.

While the SubT Urban Circuit event snuck in just under the lockdown wire in late February, DARPA made the difficult (but prudent) decision to cancel the in-person Cave Circuit event. What this means is that there will be no Systems Track Cave competition, which is a serious disappointment—we were very much looking forward to watching teams of robots navigating through an entirely unpredictable natural environment with a lot of verticality. Fortunately, DARPA is still running a Virtual Cave Circuit, and 17 teams will be taking part in this competition featuring a simulated cave environment that’s as dynamic and detailed as DARPA can make it.

From DARPA’s press releases:

DARPA’s Subterranean (SubT) Challenge will host its Cave Circuit Virtual Competition, which focuses on innovative solutions to map, navigate, and search complex, simulated cave environments November 17. Qualified teams have until Oct. 15 to develop and submit software-based solutions for the Cave Circuit via the SubT Virtual Portal, where their technologies will face unknown cave environments in the cloud-based SubT Simulator. Until then, teams can refine their roster of selected virtual robot models, choose sensor payloads, and continue to test autonomy approaches to maximize their score.

The Cave Circuit also introduces new simulation capabilities, including digital twins of Systems Competition robots to choose from, marsupial-style platforms combining air and ground robots, and breadcrumb nodes that can be dropped by robots to serve as communications relays. Each robot configuration has an associated cost, measured in SubT Credits – an in-simulation currency – based on performance characteristics such as speed, mobility, sensing, and battery life.

Each team’s simulated robots must navigate realistic caves, with features including natural terrain and dynamic rock falls, while they search for and locate various artifacts on the course within five meters of accuracy to score points during a 60-minute timed run. A correct report is worth one point. Each course contains 20 artifacts, which means each team has the potential for a maximum score of 20 points. Teams can leverage numerous practice worlds and even build their own worlds using the cave tiles found in the SubT Tech Repo to perfect their approach before they submit one official solution for scoring. The DARPA team will then evaluate the solution on a set of hidden competition scenarios.

Of the 17 qualified teams (you can see all of them here), there are a handful that we’ll quickly point out. Team BARCS, from Michigan Tech, was the winner of the SubT Virtual Urban Circuit, meaning that they may be the team to beat on Cave as well, although the course is likely to be unique enough that things will get interesting. Some Systems Track teams to watch include Coordinated Robotics, CTU-CRAS-NORLAB, MARBLE, NUS SEDS, and Robotika, and there are also a handful of brand new teams as well.

Now, just because there’s no dedicated Cave Circuit for the Systems Track teams, it doesn’t mean that there won’t be a Cave component (perhaps even a significant one) in the final event, which as far as we know is still scheduled to happen in fall of next year. We’ve heard that many of the Systems Track teams have been testing out their robots in caves anyway, and as the virtual event gets closer, we’ll be doing a sort of Virtual Systems Track series that highlights how different teams are doing mock Cave Circuits in caves they’ve found for themselves. 

For more, we checked in with DARPA SubT program manager Dr. Timothy H. Chung.

IEEE Spectrum: Was it a difficult decision to cancel the Systems Track for Cave?

Tim Chung: The decision to go virtual only was heart wrenching, because I think DARPA’s role is to offer up opportunities that may be unimaginable for some of our competitors, like opening up a cave-type site for this competition. We crawled and climbed through a number of these sites, and I share the sense of disappointment that both our team and the competitors have that we won’t be able to share all the advances that have been made since the Urban Circuit. But what we’ve been able to do is pour a lot of our energy and the insights that we got from crawling around in those caves into what’s going to be a really great opportunity on the Virtual Competition side. And whether it’s a global pandemic, or just lack of access to physical sites like caves, virtual environments are an opportunity that we want to develop.

“The simulator offers us a chance to look at where things could be … it really allows for us to find where some of those limits are in the technology based only on our imagination.”  —Timothy H. Chung, DARPA

What kind of new features will be included in the Virtual Cave Circuit for this competition?

I’m really excited about these particular features because we’re seeing an opportunity for increased synergy between the physical and the virtual. The first I’d say is that we scanned some of the Systems Track robots using photogrammetry and combined that with some additional models that we got from the systems competitors themselves to turn their systems robots into virtual models. We often talk about the sim to real transfer and how successful we can get a simulation to transfer over to the physical world, but now we’ve taken something from the physical world and made it virtual. We’ve validated the controllers as well as the kinematics of the robots, we’ve iterated with the systems competitors themselves, and now we have these 13 robots (air and ground) in the SubT Tech Repo that now all virtual competitors can take advantage of.

We also have additional robot capability. Those comms bread crumbs are common among many of the competitors, so we’ve adopted that in the virtual world, and now you have comms relay nodes that are baked in to the SubT Simulator—you can have either six or twelve comms nodes that you can drop from a variety of our ground robot platforms. We have the marsupial deployment capability now, so now we have parent ground robots that can be mixed and matched with different child drones to become marsupial pairs. 

And this is something I’ve been planning for for a while: we now have the ability to trigger things like rock falls. They still don’t quite look like Indiana Jones with the boulder coming down the corridor, but this comes really close. In addition to it just being an interesting and realistic consideration, we get to really dynamically test and stress the robots’ ability to navigate and recognize that something has changed in the environment and respond to it.

Image: DARPA DARPA is still running a Virtual Cave Circuit, and 17 teams will be taking part in this competition featuring a simulated cave environment.

No simulation is perfect, so can you talk to us about what kinds of things aren’t being simulated right now? Where does the simulator not match up to reality?

I think that question is foundational to any conversation about simulation. I’ll give you a couple of examples:

We have the ability to represent wholesale damage to a robot, but it’s not at the actuator or component level. So there’s not a reliability model, although I think that would be really interesting to incorporate so that you could do assessments on things like mean time to failure. But if a robot falls off a ledge, it can be disabled by virtue of being too damaged to continue.

With communications, and this is one that’s near and dear not only to my heart but also to all of those that have lived through developing communication systems and robotic systems, we’ve gone through and conducted RF surveys of underground environments to get a better handle on what propagation effects are. There’s a lot of research that has gone into this, and trying to carry through some of that realism, we do have path loss models for RF communications baked into the SubT Simulator. For example, when you drop a bread crumb node, it’s using a path loss model so that it can represent the degradation of signal as you go farther into a cave. Now, we’re not modeling it at the Maxwell equations level, which I think would be awesome, but we’re not quite there yet. 

We do have things like battery depletion, sensor degradation to the extent that simulators can degrade sensor inputs, and things like that. It’s just amazing how close we can get in some places, and how far away we still are in others, and I think showing where the limits are of how far you can get simulation is all part and parcel of why SubT Challenge wants to have both System and Virtual tracks. Simulation can be an accelerant, but it’s not going to be the panacea for development and innovation, and I think all the competitors are cognizant those limitations.

One of the most amazing things about the SubT Virtual Track is that all of the robots operate fully autonomously, without the human(s) in the loop that the System Track teams have when they compete. Why make the Virtual Track even more challenging in that way?

I think it’s one of the defining, delineating attributes of the Virtual Track. Our continued vision for the simulation side is that the simulator offers us a chance to look at where things could be, and allows for us to explore things like larger scales, or increased complexity, or types of environments that we can’t physically gain access to—it really allows for us to find where some of those limits are in the technology based only on our imagination, and this is one of the intrinsic values of simulation. 

But I think finding a way to incorporate human input, or more generally human factors like teleoperation interfaces and the in-situ stress that you might not be able to recreate in the context of a virtual competition provided a good reason for us to delineate the two competitions, with the Virtual Competition really being about the role of fully autonomous or self-sufficient systems going off and doing their solution without human guidance, while also acknowledging that the real world has conditions that would not necessarily be represented by a fully simulated version. Having said that, I think cognitive engineering still has an incredibly important role to play in human robot interaction.

What do we have to look forward to during the Virtual Competition Showcase?

We have a number of additional features and capabilities that we’ve baked into the simulator that will allow for us to derive some additional insights into our competition runs. Those insights might involve things like the performance of one or more robots in a given scenario, or the impact of the environment on different types of robots, and what I can tease is that this will be an opportunity for us to showcase both the technology and also the excitement of the robots competing in the virtual environment. I’m trying not to give too many spoilers, but we’ll have an opportunity to really get into the details.

Check back as we get closer to the 17 November event for more on the DARPA SubT Challenge.

Environments in which Global Positioning Systems (GPS), or more generally Global Navigation Satellite System (GNSS), signals are denied or degraded pose problems for the guidance, navigation, and control of autonomous systems. This can make operating in hostile GNSS-Impaired environments, such as indoors, or in urban and natural canyons, impossible or extremely difficult. Pixel Processor Array (PPA) cameras—in conjunction with other on-board sensors—can be used to address this problem, aiding in tracking, localization, and control. In this paper we demonstrate the use of a PPA device—the SCAMP vision chip—combining perception and compute capabilities on the same device for aiding in real-time navigation and control of aerial robots. A PPA consists of an array of Processing Elements (PEs), each of which features light capture, processing, and storage capabilities. This allows various image processing tasks to be efficiently performed directly on the sensor itself. Within this paper we demonstrate visual odometry and target identification running concurrently on-board a single PPA vision chip at a combined frequency in the region of 400 Hz. Results from outdoor multirotor test flights are given along with comparisons against baseline GPS results. The SCAMP PPA's High Dynamic Range (HDR) and ability to run multiple algorithms at adaptive rates makes the sensor well suited for addressing outdoor flight of small UAS in GNSS challenging or denied environments. HDR allows operation to continue during the transition from indoor to outdoor environments, and in other situations where there are significant variations in light levels. Additionally, the PPA only needs to output specific information such as the optic flow and target position, rather than having to output entire images. This significantly reduces the bandwidth required for communication between the sensor and on-board flight computer, enabling high frame rate, low power operation.

In the context of 3D mapping, larger and larger point clouds are acquired with lidar sensors. Although pleasing to the eye, dense maps are not necessarily tailored for practical applications. For instance, in a surface inspection scenario, keeping geometric information such as the edges of objects is essential to detect cracks, whereas very dense areas of very little information such as the ground could hinder the main goal of the application. Several strategies exist to address this problem by reducing the number of points. However, they tend to underperform with non-uniform density, large sensor noise, spurious measurements, and large-scale point clouds, which is the case in mobile robotics. This paper presents a novel sampling algorithm based on spectral decomposition analysis to derive local density measures for each geometric primitive. The proposed method, called Spectral Decomposition Filter (SpDF), identifies and preserves geometric information along the topology of point clouds and is able to scale to large environments with a non-uniform density. Finally, qualitative and quantitative experiments verify the feasibility of our method and present a large-scale evaluation of SpDF with other seven point cloud sampling algorithms, in the context of the 3D registration problem using the Iterative Closest Point (ICP) algorithm on real-world datasets. Results show that a compression ratio up to 97 % can be achieved when accepting a registration error within the range accuracy of the sensor, here for large scale environments of less than 2 cm.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):

ICRES 2020 – September 28-29, 2020 – Taipei, Taiwan AUVSI EXPONENTIAL 2020 – October 5-8, 2020 – [Online] IROS 2020 – October 25-29, 2020 – [Online] ROS World 2020 – November 12, 2020 – [Online] CYBATHLON 2020 – November 13-14, 2020 – [Online] ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA

Let us know if you have suggestions for next week, and enjoy today’s videos.

The Giant Gundam in Yokohama is actually way cooler than I thought it was going to be.

[ Gundam Factory ] via [ YouTube ]

A new 3D-printing method will make it easier to manufacture and control the shape of soft robots, artificial muscles and wearable devices. Researchers at UC San Diego show that by controlling the printing temperature of liquid crystal elastomer, or LCE, they can control the material’s degree of stiffness and ability to contract—also known as degree of actuation. What’s more, they are able to change the stiffness of different areas in the same material by exposing it to heat.

[ UCSD ]

Thanks Ioana!

This is the first successful reactive stepping test on our new torque-controlled biped robot named Bolt. The robot has 3 active degrees of freedom per leg and one passive joint in ankle. Since there is no active joint in ankle, the robot only relies on step location and timing adaptation to stabilize its motion. Not only can the robot perform stepping without active ankles, but it is also capable of rejecting external disturbances as we showed in this video.


The curling robot “Curly” is the first AI-based robot to demonstrate competitive curling skills in an icy real environment with its high uncertainties. Scientists from seven different Korean research institutions including Prof. Klaus-Robert Müller, head of the machine-learning group at TU Berlin and guest professor at Korea University, have developed an AI-based curling robot.

TU Berlin ]

MoonRanger, a small robotic rover being developed by Carnegie Mellon University and its spinoff Astrobotic, has completed its preliminary design review in preparation for a 2022 mission to search for signs of water at the moon’s south pole. Red Whittaker explains why the new MoonRanger Lunar Explorer design is innovative and different from prior planetary rovers.

[ CMU ]

Cobalt’s security robot can now navigate unmodified elevators, which is an impressive feat.


[ Cobalt ]

OrionStar, the robotics company invested in by Cheetah Mobile, announced the Robotic Coffee Master. Incorporating 3,000 hours of AI learning, 30,000 hours of robotic arm testing and machine vision training, the Robotic Coffee Master can perform complex brewing techniques, such as curves and spirals, with millimeter-level stability and accuracy (reset error ≤ 0.1mm).

[ Cheetah Mobile ]

DARPA OFFensive Swarm-Enabled Tactics (OFFSET) researchers recently tested swarms of autonomous air and ground vehicles at the Leschi Town Combined Arms Collective Training Facility (CACTF), located at Joint Base Lewis-McChord (JBLM) in Washington. The Leschi Town field experiment is the fourth of six planned experiments for the OFFSET program, which seeks to develop large-scale teams of collaborative autonomous systems capable of supporting ground forces operating in urban environments.


Here are some highlights from Team Explorer’s SubT Urban competition back in February.

[ Team Explorer ]

Researchers with the Skoltech Intelligent Space Robotics Laboratory have developed a system that allows easy interaction with a micro-quadcopter with LEDs that can be used for light-painting. The researchers used a 92x92x29 mm Crazyflie 2.0 quadrotor that weighs just 27 grams, equipped with a light reflector and an array of controllable RGB LEDs. The control system consists of a glove equipped with an inertial measurement unit (IMU; an electronic device that tracks the movement of a user’s hand), and a base station that runs a machine learning algorithm.

[ Skoltech ]

“DeKonBot” is the prototype of a cleaning and disinfection robot for potentially contaminated surfaces in buildings such as door handles, light switches or elevator buttons. While other cleaning robots often spray the cleaning agents over a large area, DeKonBot autonomously identifies the surface to be cleaned.

[ Fraunhofer IPA ]

On Oct. 20, the OSIRIS-REx mission will perform the first attempt of its Touch-And-Go (TAG) sample collection event. Not only will the spacecraft navigate to the surface using innovative navigation techniques, but it could also collect the largest sample since the Apollo missions.

[ NASA ]

With all the robotics research that seems to happen in places where snow is more of an occasional novelty or annoyance, it’s good to see NORLAB taking things more seriously


Telexistence’s Model-T robot works very slowly, but very safely, restocking shelves.

[ Telexistence ] via [ YouTube ]

Roboy 3.0 will be unveiled next month!

[ Roboy ]

KUKA ready2_educate is your training cell for hands-on education in robotics. It is especially aimed at schools, universities and company training facilities. The training cell is a complete starter package and your perfect partner for entry into robotics.

[ KUKA ]

A UPenn GRASP Lab Special Seminar on Data Driven Perception for Autonomy, presented by Dapo Afolabi from UC Berkeley.

Perception systems form a crucial part of autonomous and artificial intelligence systems since they convert data about the relationship between an autonomous system and its environment into meaningful information. Perception systems can be difficult to build since they may involve modeling complex physical systems or other autonomous agents. In such scenarios, data driven models may be used to augment physics based models for perception. In this talk, I will present work making use of data driven models for perception tasks, highlighting the benefit of such approaches for autonomous systems.

[ GRASP Lab ]

A Maryland Robotics Center Special Robotics Seminar on Underwater Autonomy, presented by Ioannis Rekleitis from the University of South Carolina.

This talk presents an overview of algorithmic problems related to marine robotics, with a particular focus on increasing the autonomy of robotic systems in challenging environments. I will talk about vision-based state estimation and mapping of underwater caves. An application of monitoring coral reefs is going to be discussed. I will also talk about several vehicles used at the University of South Carolina such as drifters, underwater, and surface vehicles. In addition, a short overview of the current projects will be discussed. The work that I will present has a strong algorithmic flavour, while it is validated in real hardware. Experimental results from several testing campaigns will be presented.

[ MRC ]

This week’s CMU RI Seminar comes from Scott Niekum at UT Austin, on Scaling Probabilistically Safe Learning to Robotics.

Before learning robots can be deployed in the real world, it is critical that probabilistic guarantees can be made about the safety and performance of such systems. This talk focuses on new developments in three key areas for scaling safe learning to robotics: (1) a theory of safe imitation learning; (2) scalable reward inference in the absence of models; (3) efficient off-policy policy evaluation. The proposed algorithms offer a blend of safety and practicality, making a significant step towards safe robot learning with modest amounts of real-world data.

[ CMU RI ]

Yesterday, Ring, the smart home company owned by Amazon, announced the Always Home Cam, a “next-level indoor security” system in the form of a small autonomous drone. It costs US $250 and is designed to closely integrate with the rest of Ring’s home security hardware and software. Technologically, it’s impressive. But you almost certainly don’t want one.

I honestly don’t know why that fake burglar is any more worried about the Ring drone than he would be about a regular security camera. It’s not like the drone can do anything, and he could just knock it out of the air. But, it’s a product launch video, so, who knows?

Ring hasn’t revealed a lot of details on the drone itself, but here’s what we can puzzle out. My guess is that there’s a planar lidar right at the top that the drone uses to localize, and that it probably has a downward-looking camera as well. Ring says that you pre-map the areas that you want the drone to fly in, which works because the environment mostly doesn’t change. It’s also nice that you don’t have to worry about weather, and minimal battery life isn’t a big deal since you don’t need to fly for very long and the recharging dock is always close by. I like that the user can only direct the drone to specific waypoints rather than piloting it directly, which (depending on how well the drone actually performs) should help minimize crashes. Ring also says that “designed with privacy in mind, the motors even hum when in flight” which is a ridiculous statement to make because it’s a drone, of course the motors hum when in flight. 

So is this a realistic product? Sure, I don’t see why it wouldn’t be. It seems like it could do what it says it does under some amount of as yet to be revealed constraints. But is it a good idea, and should you buy one? Personally, I wouldn’t recommend it. My skepticism comes from a few different places. First, an important question to ask about any consumer robot that purports to be useful is whether the robot is, really, just a flashy and cool way of doing something that could be done more easily, more reliably, and more cheaply with a more conventional system. In this case, we can compare the drone to a network of indoor security cameras.

Today you can get a totally decent indoor security camera for as little as $25, and the cameras are usually trivial to set up and keep running. So you could get 10 of them for the cost of the Ring drone. Cameras are static (although you can pay a bit more for pan/tilt options), meaning that the drone can visually survey a lot more of your house than the cameras can. But the real question is, can a few cameras cover the parts of your house that you actually care about? For example, in my (admittedly small) apartment, one static camera covers most of the living room, the front door, and the stairs up to my office. My one camera can’t monitor the kitchen or bedroom or office the way a Ring’s drone could, but if I really felt the need to monitor those things, I could buy three more cameras and still have $150 left rather than going with the drone. That would still leave some odd corners and stuff that the drone could get to, but I can’t imagine ever needing to urgently look at those corners remotely.

For larger houses, scaling is going to be different, and you may get to the point where you would actually break even on all the cameras you’d need. However, I’d argue that for security purposes (which is what this drone seems to be all about), it’s not nearly as useful as a static camera is. Static cameras offer continuous monitoring, while the best the drone can do is reactive monitoring, as shown in the video. If a static camera detects a movement, it can ping you instantly and send you footage of the event itself as well as some amount of time both before and after. The drone is not nearly as effective, since it has to launch, travel, recharge, and can only be in one place at a time.

Ring also says that “designed with privacy in mind, the motors even hum when in flight” which is a ridiculous statement to make because it’s a drone, of course the motors hum when in flight. 

A second important question to ask about any robot, especially one with a camera on it, is whether the benefits of such a system outweigh the risks. And before we get into why having an autonomous internet-connected flying security camera could be a privacy nightmare, we should also point out a potentially significant privacy upside to the Ring drone over a more conventional static camera setup. I think it’s reasonable to point out (as Ring has) that with the drone, you always know when it’s recording and where it’s recording from, because it’ll be loudly airborne and making a nuisance of itself. This is not the case with most static security cameras, which are typically on all the time, and it’s hard to have perfect confidence that what those cameras are seeing is staying as private as it should. If the drone isn’t in the air and being noisy, I can’t see how it could be used to spy on you without you realizing it. And if you don’t want a permanent camera in (say) your bedroom but would like the option of monitoring it while you’re away, a mobile system like the Ring drone offers that capability, as long as you remember to leave your bedroom door open when you leave.

But this potential privacy feature also comes with privacy risks, says Ryan Calo, associate professor at the University of Washington School of Law, in Seattle. “Fixed cameras can be avoided, whereas mobile ones can’t, which can make it impossible for a child, spouse, or roommate to get away from the camera,” he explains. This is not unique to Ring’s drone, but for better or worse, Ring is among the first to offer a dedicated mobile surveillance robot. “If mobile surveillance is normalized,” he adds, “my concern is that it will permit an abuser to check in on their partner wherever they are, erase surveillance blind spots, and remove excuses that the surveilled individual was merely ‘off camera.’ In other words, Ring is offering a more complete surveillance. And surveillance is a well-known component of domestic abuse.”

In some ways, the Ring drone is like a telepresence robot, where someone can put themselves into your personal, private space from anywhere, with a level of physical agency that’s unique to robots. The potential for abuse of this capability is drastically higher than for a system that can see but can’t move. You can disable Ring’s system by throwing a blanket or something over it, and shutting doors will keep it out, but there is no reason why you should find yourself in that kind of situation in your own home.

Ring, and its parent company Amazon, also don’t have the greatest track record on security and privacy. And it’s not just keeping your data safe from hackers: Ring specifically has cultivated close ties with law enforcement. As this July article from the EFF points out, “with a warrant, police could also circumvent the device’s owner and get footage straight from Amazon, even if the owner denied the police.” The EFF is talking about the Ring doorbell camera here, but it’s not clear to me that the Ring drone would be an exception.

The Ring drone can also give Amazon even more opportunities to collect data about you, now from a mobile platform that can move around inside of your house and even look out your windows. “It helps Amazon build your digital twin,” says Julie Carpenter, a research fellow in the Ethics + Emerging Sciences Group at California Polytechnic State University, in San Luis Obispo. “They’re using this type of consumer data to create a database version of who you are, and then using it to sell you things. The data collected is increasingly invasive, as with the Ring drone capabilities, such as mapping your home and collecting audio and dynamic aerial video of you and your family in your bedrooms, bathrooms, everywhere you live.”

Opening up your home to internet-connected cameras is already a privacy compromise. Many people find that compromise to be worth it for the security and peace of mind that these systems offer. When we look at the advantages that you’d get from buying Ring’s drone over fixed cameras, though, the additional privacy risks that come with an autonomous mobile camera seem hard to justify. The technology is certainly impressive, and the idea of an autonomous indoor security drone is, as I’m sure Ring well knows, very cool. But is it worth $250, questionably better security versus cheap static cameras, and a much larger potential for misuse or abuse? I’m not convinced.

The Internet of Things (IoT) and Industrial IoT (IIoT) have developed rapidly in the past few years, as both the Internet and “things” have evolved significantly. “Things” now range from simple Radio Frequency Identification (RFID) devices to smart wireless sensors, intelligent wireless sensors and actuators, robotic things, and autonomous vehicles operating in consumer, business, and industrial environments. The emergence of “intelligent things” (static or mobile) in collaborative autonomous fleets requires new architectures, connectivity paradigms, trustworthiness frameworks, and platforms for the integration of applications across different business and industrial domains. These new applications accelerate the development of autonomous system design paradigms and the proliferation of the Internet of Robotic Things (IoRT). In IoRT, collaborative robotic things can communicate with other things, learn autonomously, interact safely with the environment, humans and other things, and gain qualities like self-maintenance, self-awareness, self-healing, and fail-operational behavior. IoRT applications can make use of the individual, collaborative, and collective intelligence of robotic things, as well as information from the infrastructure and operating context to plan, implement and accomplish tasks under different environmental conditions and uncertainties. The continuous, real-time interaction with the environment makes perception, location, communication, cognition, computation, connectivity, propulsion, and integration of federated IoRT and digital platforms important components of new-generation IoRT applications. This paper reviews the taxonomy of the IoRT, emphasizing the IoRT intelligent connectivity, architectures, interoperability, and trustworthiness framework, and surveys the technologies that enable the application of the IoRT across different domains to perform missions more efficiently, productively, and completely. The aim is to provide a novel perspective on the IoRT that involves communication among robotic things and humans and highlights the convergence of several technologies and interactions between different taxonomies used in the literature.

This paper describes a portable, prosthetic control system and the first at-home use of a multi-degree-of-freedom, proportionally controlled bionic arm. The system uses a modified Kalman filter to provide 6 degree-of-freedom, real-time, proportional control. We describe (a) how the system trains motor control algorithms for use with an advanced bionic arm, and (b) the system's ability to record an unprecedented and comprehensive dataset of EMG, hand positions and force sensor values. Intact participants and a transradial amputee used the system to perform activities-of-daily-living, including bi-manual tasks, in the lab and at home. This technology enables at-home dexterous bionic arm use, and provides a high-temporal resolution description of daily use—essential information to determine clinical relevance and improve future research for advanced bionic arms.

It has been 10 years since the publication of the first article looking at plants as a biomechatronic system and as model for robotics. Now, roboticists have started to look at plants differently and consider them as a model in the field of bioinspired robotics. Despite plants have been seen traditionally as passive entities, in reality they are able to grow, move, sense, and communicate. These features make plants an exceptional example of morphological computation - with probably the highest level of adaptability among all living beings. They are a unique model to design robots that can act in- and adapt to- unstructured, extreme, and dynamically changing environments exposed to sudden or long-term events. Although plant-inspired robotics is still a relatively new field, it has triggered the concept of growing robotics: an emerging area in which systems are designed to create their own body, adapt their morphology, and explore different environments. There is a reciprocal interest between biology and robotics: plants represent an excellent source of inspiration for achieving new robotic abilities, and engineering tools can be used to reveal new biological information. This way, a bidirectional biology-robotics strategy provides mutual benefits for both disciplines. This mini-review offers a brief overview of the fundamental aspects related to a bioengineering approach in plant-inspired robotics. It analyses the works in which both biological and engineering aspects have been investigated, and highlights the key elements of plants that have been milestones in the pioneering field of growing robots.

The ability to learn new tasks by sequencing already known skills is an important requirement for future robots. Reinforcement learning is a powerful tool for this as it allows for a robot to learn and improve on how to combine skills for sequential tasks. However, in real robotic applications, the cost of sample collection and exploration prevent the application of reinforcement learning for a variety of tasks. To overcome these limitations, human input during reinforcement can be beneficial to speed up learning, guide the exploration and prevent the choice of disastrous actions. Nevertheless, there is a lack of experimental evaluations of multi-channel interactive reinforcement learning systems solving robotic tasks with input from inexperienced human users, in particular for cases where human input might be partially wrong. Therefore, in this paper, we present an approach that incorporates multiple human input channels for interactive reinforcement learning in a unified framework and evaluate it on two robotic tasks with 20 inexperienced human subjects. To enable the robot to also handle potentially incorrect human input we incorporate a novel concept for self-confidence, which allows the robot to question human input after an initial learning phase. The second robotic task is specifically designed to investigate if this self-confidence can enable the robot to achieve learning progress even if the human input is partially incorrect. Further, we evaluate how humans react to suggestions of the robot, once the robot notices human input might be wrong. Our experimental evaluations show that our approach can successfully incorporate human input to accelerate the learning process in both robotic tasks even if it is partially wrong. However, not all humans were willing to accept the robot's suggestions or its questioning of their input, particularly if they do not understand the learning process and the reasons behind the robot's suggestions. We believe that the findings from this experimental evaluation can be beneficial for the future design of algorithms and interfaces of interactive reinforcement learning systems used by inexperienced users.