Feed aggregator

Manual annotation for human action recognition with content semantics using 3D Point Cloud (3D-PC) in industrial environments consumes a lot of time and resources. This work aims to recognize, analyze, and model human actions to develop a framework for automatically extracting content semantics. Main Contributions of this work: 1. design a multi-layer structure of various DNN classifiers to detect and extract humans and dynamic objects using 3D-PC preciously, 2. empirical experiments with over 10 subjects for collecting datasets of human actions and activities in one industrial setting, 3. development of an intuitive GUI to verify human actions and its interaction activities with the environment, 4. design and implement a methodology for automatic sequence matching of human actions in 3D-PC. All these procedures are merged in the proposed framework and evaluated in one industrial Use-Case with flexible patch sizes. Comparing the new approach with standard methods has shown that the annotation process can be accelerated by 5.2 times through automation.

Introduction: Event cameras report pixel-wise brightness changes at high temporal resolutions, allowing for high speed tracking of features in visual inertial odometry (VIO) estimation, but require a paradigm shift, as common practices from the past decades using conventional cameras, such as feature detection and tracking, do not translate directly. One method for feature detection and tracking is the Eventbased Kanade-Lucas-Tomasi tracker (EKLT), an hybrid approach that combines frames with events to provide a high speed tracking of features. Despite the high temporal resolution of the events, the local nature of the registration of features imposes conservative limits to the camera motion speed.

Methods: Our proposed approach expands on EKLT by relying on the concurrent use of the event-based feature tracker with a visual inertial odometry system performing pose estimation, leveraging frames, events and Inertial Measurement Unit (IMU) information to improve tracking. The problem of temporally combining high-rate IMU information with asynchronous event cameras is solved by means of an asynchronous probabilistic filter, in particular an Unscented Kalman Filter (UKF). The proposed method of feature tracking based on EKLT takes into account the state estimation of the pose estimator running in parallel and provides this information to the feature tracker, resulting in a synergy that can improve not only the feature tracking, but also the pose estimation. This approach can be seen as a feedback, where the state estimation of the filter is fed back into the tracker, which then produces visual information for the filter, creating a “closed loop”.

Results: The method is tested on rotational motions only, and comparisons between a conventional (not event-based) approach and the proposed approach are made, using synthetic and real datasets. Results support that the use of events for the task improve performance.

Discussion: To the best of our knowledge, this is the first work proposing the fusion of visual with inertial information using events cameras by means of an UKF, as well as the use of EKLT in the context of pose estimation. Furthermore, our closed loop approach proved to be an improvement over the base EKLT, resulting in better feature tracking and pose estimation. The inertial information, despite prone to drifting over time, allows keeping track of the features that would otherwise be lost. Then, feature tracking synergically helps estimating and minimizing the drift.

On-orbit service spacecraft with redundant actuators need to overcome orbital and attitude coupling when performing proximity maneuvers. In addition, transient/steady-state performance is required to fulfill the user-defined requirements. To these ends, this paper introduces a fixed-time tracking regulation and actuation allocation scheme for redundantly actuated spacecraft. The coupling effect of translational and rotational motions is described by dual quaternion. Based on this, we propose a non-singular fast terminal sliding mode controller to guarantee fixed-time tracking performance in the presence of external disturbances and system uncertainties, where the settling time is only dependent on user-defined control parameters rather than initial values. The unwinding problem caused by the redundancy of dual quaternion is handled by a novel attitude error function. Moreover, optimal quadratic programming is incorporated into null space pseudo-inverse control allocation that ensures the actuation smoothness and never violates the maximum output capability of each actuator. Numerical simulations on a spacecraft platform with symmetric thruster configuration demonstrate the validity of the proposed approach.

A few years ago, powered prostheses triggered new technological advances in diverse areas such as mobility, comfort, and design, which have been essential to improving the quality of life of individuals with lower limb disability. The human body is a complex system involving mental and physical health, meaning a dependant relationship between its organs and lifestyle. The elements used in the design of these prostheses are critical and related to lower limb amputation level, user morphology and human-prosthetic interaction. Hence, several technologies have been employed to accomplish the end user’s needs, for example, advanced materials, control systems, electronics, energy management, signal processing, and artificial intelligence. This paper presents a systematic literature review on such technologies, to identify the latest advances, challenges, and opportunities in developing lower limb prostheses with the analysis on the most significant papers. Powered prostheses for walking in different terrains were illustrated and examined, with the kind of movement the device should perform by considering the electronics, automatic control, and energy efficiency. Results show a lack of a specific and generalised structure to be followed by new developments, gaps in energy management and improved smoother patient interaction. Additionally, Human Prosthetic Interaction (HPI) is a term introduced in this paper since no other research has integrated this interaction in communication between the artificial limb and the end-user. The main goal of this paper is to provide, with the found evidence, a set of steps and components to be followed by new researchers and experts looking to improve knowledge in this field.



A couple decades ago Kiva Systems had the brilliant and certainly very valuable realization that it was possible to make an entire environment (like a fulfillment warehouse) robotic without filling that entire environment with robots. Rather than making every shelf in a warehouse into a robot, you could instead leave every shelf as a shelf, and simply make a robot that could interface with shelves on-demand, giving them mobility when required.

So what if you take that philosophy out of the warehouse and into your living room? Well, it’s probably not going to massively boost your productivity or increase your own personal fulfillment all that much, but it’s an interesting idea that might make some things a little more convenient from time to time.

Kachaka is an autonomous mobile robot that shares many features with the kinds of autonomous mobile robots that you find in warehouses. It’s got a planar lidar sensor, front-mounted cameras and a basic 3D sensor, and a set of drive wheels plus casters. It can make maps and navigate autonomously and whatnot. On top, it’s got a little pin of sorts that it can extend and retract, which enables the robot’s entire purpose: it can drive underneath specially made wheeled shelving units, extend that pin into a slot underneath the bottom shelf, and then drive off, bringing the shelves along with it.

You could imagine having several different shelving units that are brought to you automatically depending on what’s on your schedule, and when not in use, the shelves can be stored out of the way, reducing clutter and giving you more usable space. Of course, all of this only works if you have the right stuff on your mobile shelves to begin with, a problem that Labrador has solved for food with a custom actuated fridge.

What Kachaka has going for it is that it’s building off of robotic technology that’s already very mature—functionally identical systems have been operating in warehouses for years. But at the same time, the issue that Kachaka may struggle with is that it’s not operating in a warehouse, meaning that it has to deal with home environments that have far less structure to them, as well as a much different value proposition. Unlike with warehouse robots, Kachaka will likely spend most of its time not in use, which could make its cost hard to justify. Buying the robot plus one two-tier shelf will cost you about $2000 in total, plus an $8 per month subscription fee.

It’s fun to imagine what a system like this could do in the future, if more pieces of furniture (and floors) were compatible with it. For example, you could have one room of your house dedicated to furniture storage, while most other rooms could be multipurpose, with robots adding and removing furniture as you require. A breakfast nook, dining room, craft room, exercise room, workshop, all of these could potentially be the same room, just at different times, enabled by furniture moving robots. Kachaka isn’t that, obviously, but it’s wheeling its cute little shelf in the right direction.



A couple decades ago Kiva Systems had the brilliant and certainly very valuable realization that it was possible to make an entire environment (like a fulfillment warehouse) robotic without filling that entire environment with robots. Rather than making every shelf in a warehouse into a robot, you could instead leave every shelf as a shelf, and simply make a robot that could interface with shelves on-demand, giving them mobility when required.

So what if you take that philosophy out of the warehouse and into your living room? Well, it’s probably not going to massively boost your productivity or increase your own personal fulfillment all that much, but it’s an interesting idea that might make some things a little more convenient from time to time.

Kachaka is an autonomous mobile robot that shares many features with the kinds of autonomous mobile robots that you find in warehouses. It’s got a planar lidar sensor, front-mounted cameras and a basic 3D sensor, and a set of drive wheels plus casters. It can make maps and navigate autonomously and whatnot. On top, it’s got a little pin of sorts that it can extend and retract, which enables the robot’s entire purpose: it can drive underneath specially made wheeled shelving units, extend that pin into a slot underneath the bottom shelf, and then drive off, bringing the shelves along with it.

You could imagine having several different shelving units that are brought to you automatically depending on what’s on your schedule, and when not in use, the shelves can be stored out of the way, reducing clutter and giving you more usable space. Of course, all of this only works if you have the right stuff on your mobile shelves to begin with, a problem that Labrador has solved for food with a custom actuated fridge.

What Kachaka has going for it is that it’s building off of robotic technology that’s already very mature—functionally identical systems have been operating in warehouses for years. But at the same time, the issue that Kachaka may struggle with is that it’s not operating in a warehouse, meaning that it has to deal with home environments that have far less structure to them, as well as a much different value proposition. Unlike with warehouse robots, Kachaka will likely spend most of its time not in use, which could make its cost hard to justify. Buying the robot plus one two-tier shelf will cost you about $2000 in total, plus an $8 per month subscription fee.

It’s fun to imagine what a system like this could do in the future, if more pieces of furniture (and floors) were compatible with it. For example, you could have one room of your house dedicated to furniture storage, while most other rooms could be multipurpose, with robots adding and removing furniture as you require. A breakfast nook, dining room, craft room, exercise room, workshop, all of these could potentially be the same room, just at different times, enabled by furniture moving robots. Kachaka isn’t that, obviously, but it’s wheeling its cute little shelf in the right direction.



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.

HRI 2023: 13–16 March 2023, STOCKHOLMRobotics Summit & Expo: 10–11 May 2023, BOSTONICRA 2023: 29 May–2 June 2023, LONDONRoboCup 2023: 4–10 July 2023, BORDEAUX, FRANCERSS 2023: 10–14 July 2023, DAEGU, KOREAIEEE RO-MAN 2023: 28–31 August 2023, BUSAN, KOREACLAWAR 2023: 2–4 October 2023, FLORIANOPOLIS, BRAZIL

Enjoy today’s videos!

Flexiv’s Grav Enhanced gripper uses a gecko adhesive, which has historically been difficult to do in a commercial context. We’re looking forward to more details on how the company is making it work.

[ Flexiv ]

A team of engineers has devised a modular system to produce efficient, scalable aquabots. The system’s simple repeating elements can assemble into swimming forms ranging from eel-like to wing-shaped.

[ MIT ]

RoboCup teams probably use their humanoids more aggressively than anyone else, so they have to come up with new techniques to keep them walking even as they gradually get more and more worn out.

In this video, our previous walk approach (Walking 2022) is compared to our new one (Walking 2023). A worn-out robot with high joint play is used for this demonstration. Our new walk uses the previous approach as a baseline. To ensure stability, we use a regulation to modify the allowed rotation speed of the support foot’s joints. Thus, the different leg parts will still execute the intended motion, but, based on the center of mass and the measured rotation errors of the support foot, some leg parts are slowed down if needed.

[ B-Human ]

Most legged robots are built with leg structures from serially mounted links and actuators and are controlled through complex controllers and sensor feedback. In comparison, animals developed multisegment legs, mechanical coupling between joints, and multisegmented feet. We report how multisegmented feet provide a large range of viable center-of-pressure points well suited for bipedal robots, but also for quadruped robots on slopes and natural terrain. Our results also offer a functional understanding of segmented feet in animals like ratite birds.

[ Paper ]

A millipede/centipede, despite its legs being small in comparison with the body, is able to stably traverse complex 3D terrain (terrain with concave and convex curves or slopes of varying degrees). This is due to its body being split into multiple segments, which allow for upward and downward bending behavior, resulting in low ground clearance and stable locomotion. The body-bending behavior also exhibits successive propagation from anterior to posterior body segments. Inspired by the millipede body-bending behavior, we propose proactive neural control with fast online, unsupervised learning and short-term memory mechanisms, allowing legged, multisegmented robots to proactively adapt their bodies to follow the surface contour and maintain efficient ground contact like millipedes.

[ VISTEC ]

Thanks, Poramate!

Rollovers and jackknifes are a dangerous risk to trucks when navigating highways. For the Waymo Driver, we use outrigger tests to help our system prioritize balance when navigating curved roads at high speeds. Take a look at how it all comes together at our closed-course testing facilities.

[ Waymo ]

Imagine if one test could tell you if you were protected from the latest COVID-19 variant. An innovative robotic neutralizing antibody testing system developed by ABB Robotics and UTMB is helping to achieve this by enabling hundreds of tests to be conducted each day, with the resulting test data being used to assess individuals’ immunity against different strains of the virus.

[ ABB ]

At Agility, we make robots that are made for work. Our robot Digit works alongside us in spaces designed for people. Digit handles the boring and repetitive tasks that are meant for a machine, which allows companies and their people to focus on the work that requires the human element.
We put out an open invitation to our followers on Twitter, Instagram, and LinkedIn to ask our CEO Damion Shelton and CTO Jonathan Hurst anything related to Agility and robotics in general.

[ Agility Robotics ]

This is exactly how I set the table.

[ Sanctuary AI ]

The Zoox robotaxi is designed for city streets, but that doesn’t mean it can’t go fast. Operating at high speeds requires rigorous testing, first in simulation and then IRL. Meet some of the crew who are ensuring you’ll have a safe and comfortable ride, whether it’s at 5 miles per hour or 75 mph.

[ Zoox ]

At Capacity, a forward-thinking third-party logistics firm with expertise in health and beauty products, AI-robotic putwalls from Covariant are key to delivering superior customer experiences. With the ability to act autonomously to pick virtually any of the diverse SKUs that come through Capacity’s operations, Covariant putwalls help streamline operations.

[ Covariant ]

Sure Bak, who worked as an interactive product UX designer at Porsche, currently works on designing HRI (human-robot interaction) at Naver Labs. He clearly defines the difference between a car and a robot as a car being “me” and a robot being “you.”

[ Naver Labs ]

This year, we celebrate the tenth anniversary of NASA Kennedy Space Center’s Swamp Works. Swamp Works was developed as a space devoted to innovation and collaboration across Kennedy’s research facilities, which include the granular mechanics and regolith operations (GMRO), applied chemistry, electrostatics and surface physics, and applied physics laboratories.

[ KSC ]

Social home robots have had a hard time of it, but ElliQ has promise with its focused value proposition.

[ ElliQ ]

Tech Panel: The progression of robotics since Shakey the robot has been remarkable. Yet there are still many challenges that field robotics must surmount: outmatching humans in pick- and place-like applications, maneuvering in tight spaces at high speeds, dealing with adversaries, being resilient and finding a representation of the physical environment that allows for dexterity, manipulation of objects, and mobility through deformable or unstable terrains. This panel will address the next breakthroughs in field robotics, define future challenges, and explore ways that DARPA can accelerate their development.

[ DARPA ]

Tech Panel: In 2004, DARPA launched interest in self-driving vehicles with a Grand Challenge. Back then, none of the vehicles could even finish the course. Today, we have fully driverless taxi services in San Francisco and Phoenix. But while rapid progress has been made, fully automated vehicles aren’t yet the norm. What are the challenges remaining to get us to truly autonomous vehicles in any environment, and what are the important distinctions for military use as compared with consumer use?

[ DARPA ]

Leaders in Lidar | Chapter 3: Take the Next Steps. Riding on the success of MOLA, the Goddard team develops new lidar instruments for Earth, the moon, and Mercury. Each new instrument is a major leap forward in technology and scientific ambition, and equally fraught with challenges.

[ NASA ] [Leaders in Lidar Chapter 1, Chapter 2]

This Carnegie Mellon University Robotics Institute seminar comes from Sarcos chief operating officer Jorgen Pedersen: “RE2 Robotics: From RI Spinout to Acquisition.”

It was July 2001. Jorgen Pedersen founded RE2 Robotics. It was supposed to be a temporary venture while he figured out his next career move. But the journey took an unexpected course. RE2 became a leading developer of mobile manipulation systems. Fast forward to 2022: RE2 Robotics exited via an acquisition to Sarcos Technology and Robotics Corp. for US $100 million. In this talk, Jorgen will share the 20-year journey of RE2 Robotics, which includes bootstrapping a robotics business, leveraging government funding as a nondilutive investment, pivoting at critical moments, raising capital in order to scale, commercializing cutting-edge robotics technology, and most important, recognizing the importance of vision, mission, and core values to build a strong culture that can overcome any obstacle.

[ CMU RI ]



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.

HRI 2023: 13–16 March 2023, STOCKHOLMRobotics Summit & Expo: 10–11 May 2023, BOSTONICRA 2023: 29 May–2 June 2023, LONDONRoboCup 2023: 4–10 July 2023, BORDEAUX, FRANCERSS 2023: 10–14 July 2023, DAEGU, KOREAIEEE RO-MAN 2023: 28–31 August 2023, BUSAN, KOREACLAWAR 2023: 2–4 October 2023, FLORIANOPOLIS, BRAZIL

Enjoy today’s videos!

Flexiv’s Grav Enhanced gripper uses a gecko adhesive, which has historically been difficult to do in a commercial context. We’re looking forward to more details on how the company is making it work.

[ Flexiv ]

A team of engineers has devised a modular system to produce efficient, scalable aquabots. The system’s simple repeating elements can assemble into swimming forms ranging from eel-like to wing-shaped.

[ MIT ]

RoboCup teams probably use their humanoids more aggressively than anyone else, so they have to come up with new techniques to keep them walking even as they gradually get more and more worn out.

In this video, our previous walk approach (Walking 2022) is compared to our new one (Walking 2023). A worn-out robot with high joint play is used for this demonstration. Our new walk uses the previous approach as a baseline. To ensure stability, we use a regulation to modify the allowed rotation speed of the support foot’s joints. Thus, the different leg parts will still execute the intended motion, but, based on the center of mass and the measured rotation errors of the support foot, some leg parts are slowed down if needed.

[ B-Human ]

Most legged robots are built with leg structures from serially mounted links and actuators and are controlled through complex controllers and sensor feedback. In comparison, animals developed multisegment legs, mechanical coupling between joints, and multisegmented feet. We report how multisegmented feet provide a large range of viable center-of-pressure points well suited for bipedal robots, but also for quadruped robots on slopes and natural terrain. Our results also offer a functional understanding of segmented feet in animals like ratite birds.

[ Paper ]

A millipede/centipede, despite its legs being small in comparison with the body, is able to stably traverse complex 3D terrain (terrain with concave and convex curves or slopes of varying degrees). This is due to its body being split into multiple segments, which allow for upward and downward bending behavior, resulting in low ground clearance and stable locomotion. The body-bending behavior also exhibits successive propagation from anterior to posterior body segments. Inspired by the millipede body-bending behavior, we propose proactive neural control with fast online, unsupervised learning and short-term memory mechanisms, allowing legged, multisegmented robots to proactively adapt their bodies to follow the surface contour and maintain efficient ground contact like millipedes.

[ VISTEC ]

Thanks, Poramate!

Rollovers and jackknifes are a dangerous risk to trucks when navigating highways. For the Waymo Driver, we use outrigger tests to help our system prioritize balance when navigating curved roads at high speeds. Take a look at how it all comes together at our closed-course testing facilities.

[ Waymo ]

Imagine if one test could tell you if you were protected from the latest COVID-19 variant. An innovative robotic neutralizing antibody testing system developed by ABB Robotics and UTMB is helping to achieve this by enabling hundreds of tests to be conducted each day, with the resulting test data being used to assess individuals’ immunity against different strains of the virus.

[ ABB ]

At Agility, we make robots that are made for work. Our robot Digit works alongside us in spaces designed for people. Digit handles the boring and repetitive tasks that are meant for a machine, which allows companies and their people to focus on the work that requires the human element.
We put out an open invitation to our followers on Twitter, Instagram, and LinkedIn to ask our CEO Damion Shelton and CTO Jonathan Hurst anything related to Agility and robotics in general.

[ Agility Robotics ]

This is exactly how I set the table.

[ Sanctuary AI ]

The Zoox robotaxi is designed for city streets, but that doesn’t mean it can’t go fast. Operating at high speeds requires rigorous testing, first in simulation and then IRL. Meet some of the crew who are ensuring you’ll have a safe and comfortable ride, whether it’s at 5 miles per hour or 75 mph.

[ Zoox ]

At Capacity, a forward-thinking third-party logistics firm with expertise in health and beauty products, AI-robotic putwalls from Covariant are key to delivering superior customer experiences. With the ability to act autonomously to pick virtually any of the diverse SKUs that come through Capacity’s operations, Covariant putwalls help streamline operations.

[ Covariant ]

Sure Bak, who worked as an interactive product UX designer at Porsche, currently works on designing HRI (human-robot interaction) at Naver Labs. He clearly defines the difference between a car and a robot as a car being “me” and a robot being “you.”

[ Naver Labs ]

This year, we celebrate the tenth anniversary of NASA Kennedy Space Center’s Swamp Works. Swamp Works was developed as a space devoted to innovation and collaboration across Kennedy’s research facilities, which include the granular mechanics and regolith operations (GMRO), applied chemistry, electrostatics and surface physics, and applied physics laboratories.

[ KSC ]

Social home robots have had a hard time of it, but ElliQ has promise with its focused value proposition.

[ ElliQ ]

Tech Panel: The progression of robotics since Shakey the robot has been remarkable. Yet there are still many challenges that field robotics must surmount: outmatching humans in pick- and place-like applications, maneuvering in tight spaces at high speeds, dealing with adversaries, being resilient and finding a representation of the physical environment that allows for dexterity, manipulation of objects, and mobility through deformable or unstable terrains. This panel will address the next breakthroughs in field robotics, define future challenges, and explore ways that DARPA can accelerate their development.

[ DARPA ]

Tech Panel: In 2004, DARPA launched interest in self-driving vehicles with a Grand Challenge. Back then, none of the vehicles could even finish the course. Today, we have fully driverless taxi services in San Francisco and Phoenix. But while rapid progress has been made, fully automated vehicles aren’t yet the norm. What are the challenges remaining to get us to truly autonomous vehicles in any environment, and what are the important distinctions for military use as compared with consumer use?

[ DARPA ]

Leaders in Lidar | Chapter 3: Take the Next Steps. Riding on the success of MOLA, the Goddard team develops new lidar instruments for Earth, the moon, and Mercury. Each new instrument is a major leap forward in technology and scientific ambition, and equally fraught with challenges.

[ NASA ] [Leaders in Lidar Chapter 1, Chapter 2]

This Carnegie Mellon University Robotics Institute seminar comes from Sarcos chief operating officer Jorgen Pedersen: “RE2 Robotics: From RI Spinout to Acquisition.”

It was July 2001. Jorgen Pedersen founded RE2 Robotics. It was supposed to be a temporary venture while he figured out his next career move. But the journey took an unexpected course. RE2 became a leading developer of mobile manipulation systems. Fast forward to 2022: RE2 Robotics exited via an acquisition to Sarcos Technology and Robotics Corp. for US $100 million. In this talk, Jorgen will share the 20-year journey of RE2 Robotics, which includes bootstrapping a robotics business, leveraging government funding as a nondilutive investment, pivoting at critical moments, raising capital in order to scale, commercializing cutting-edge robotics technology, and most important, recognizing the importance of vision, mission, and core values to build a strong culture that can overcome any obstacle.

[ CMU RI ]

Recently, soft robotics has gained considerable attention as it promises numerous applications thanks to unique features originating from the physical compliance of the robots. Biomimetic underwater robots are a promising application in soft robotics and are expected to achieve efficient swimming comparable to the real aquatic life in nature. However, the energy efficiency of soft robots of this type has not gained much attention and has been fully investigated previously. This paper presents a comparative study to verify the effect of soft-body dynamics on energy efficiency in underwater locomotion by comparing the swimming of soft and rigid snake robots. These robots have the same motor capacity, mass, and body dimensions while maintaining the same actuation degrees of freedom. Different gait patterns are explored using a controller based on grid search and the deep reinforcement learning controller to cover the large solution space for the actuation space. The quantitative analysis of the energy consumption of these gaits indicates that the soft snake robot consumed less energy to reach the same velocity as the rigid snake robot. When the robots swim at the same average velocity of 0.024 m/s, the required power for the soft-body robot is reduced by 80.4% compared to the rigid counterpart. The present study is expected to contribute to promoting a new research direction to emphasize the energy efficiency advantage of soft-body dynamics in robot design.

This work explores the recent research conducted towards the development of novel classes of devices in wearable and implantable medical applications allowed by the introduction of the soft robotics approach. In the medical field, the need for materials with mechanical properties similar to biological tissues is one of the first considerations that arises to improve comfort and safety in the physical interaction with the human body. Thus, soft robotic devices are expected to be able of accomplishing tasks no traditional rigid systems can do. In this paper, we describe future perspectives and possible routes to address scientific and clinical issues still hampering the accomplishment of ideal solutions in clinical practice.

Recent investigations of the electric braking booster (E-Booster) focus on its potential to enhance brake energy regeneration. A vehicle’s hydraulic system is composed of the E-Booster and electric stability control to control the master cylinder and wheel cylinders. This paper aims to address the independent closed-loop control of the position and pressure as well as the maintenance of the pedal feel. To track both the reference signals related to piston displacement and the wheel cylinder pressure, an explicit model predictive control (MPC) is developed. First, the new flow model is introduced as the foundation for controller design and simulation. Next, in accordance with the operational conditions, the entire system is divided into three switchable subsystems. The three distributed MPCs are constructed based on the linearized subsystems, and a state machine is used to perform the state jump across the controllers. A linear piecewise affine control law can then be obtained by solving the quadratic program (QP) of explicit MPC. Afterwards, the non-linear extended Kalman filter including the recorded time-variant process noise is used to estimate all the state variables. The effectiveness of the explicit MPC is evidenced by the simulations compared with a single MPC in regenerative and dead-zone conditions. The proposed controller decreases the latency significantly by 85 milliseconds, which also helps to improve accuracy by 22.6%. Furthermore, the pedal feel remains consistent, even when factoring in the number of vibrations caused by the inherent hydraulic characteristic of pressure versus volume.

The ability to adapt and conform to angular and uneven surfaces improves the suction cup’s performance in grasping and manipulation. However, in most cases, the adaptation costs lack of required stiffness for manipulation after surface attachment; thus, the ideal scenario is to have compliance during adaptation and stiffness after attachment to the surface. Inspired by the capability of stiffness regulation in octopus suction cup, this article presents a suction cup that adapts to steep angular surfaces due to compliance and has high stiffness after attachment. In this design, the stiffness after attachment is provided by using granular jamming as vacuum driven stiffness modulation. Thus, the design is composed of a conventional active suction pad connected to a granular stalk, emulating a hinge behavior during adaptation and creating high stiffness by jamming granular particles driven by the same vacuum as the suction pad. During the experiment, the suction cup can adapt to angles up to 85° with a force lower than 0.5 N. We also investigated the effect of granular stalk’s length on the adaptation and how this design performs compared to passive adaptation without stiffness modulation.

In Cable-Suspended Parallel Robots (CSPRs), reconfigurability, i.e., the possibility of modifying the position of the cable connection points on the base frame, is particularly interesting to investigate, since it paves the way for future industrial and service applications of CSPRs, where the base frame can also be replaced by mobile agents. This report focuses on fully actuated Translational Reconfigurable CSPRs (TR-CSPRs), i.e., reconfigurable CSPRs with a point mass end-effector driven by three cables. The objective of the work is twofold. First, it is shown that the Wrench Exertion Capability (WEC) performance index can be exploited to identify the configurations of the cable connection points optimizing a task-related performance in a single point or throughout the workspace, and hence to implement a workspace analysis. Then, by referring to the case of a TR-CSPR with a single reconfigurable connection point and in quasi-static working condition, an analytical approach is provided to reconfigure the robot while executing a task to avoid one of the paramount problems of cable robots: cable slackness. Brought together, the two contributions allow defining a reconfiguration strategy for TR-CSPRs. The strategy is presented by applying it to a numerical example of a TR-CSPR used for lifting and moving a load along a prescribed path: the use of the WEC allows analyzing the workspace and predicting if robot reconfigurability makes it possible to pass quasi-statically along all the points of a given path; then reconfigurability is exploited to avoid cable slackness along the path.

Self-organized groups of robots have generally coordinated their behaviors using quite simple social interactions. Although simple interactions are sufficient for some group behaviors, future research needs to investigate more elaborate forms of coordination, such as social cognition, to progress towards real deployments. In this perspective, we define social cognition among robots as the combination of social inference, social learning, social influence, and knowledge transfer, and propose that these abilities can be established in robots by building underlying mechanisms based on behaviors observed in humans. We review key social processes observed in humans that could inspire valuable capabilities in robots and propose that relevant insights from human social cognition can be obtained by studying human-controlled avatars in virtual environments that have the correct balance of embodiment and constraints. Such environments need to allow participants to engage in embodied social behaviors, for instance through situatedness and bodily involvement, but, at the same time, need to artificially constrain humans to the operational conditions of robots, for instance in terms of perception and communication. We illustrate our proposed experimental method with example setups in a multi-user virtual environment.

Introduction: Robot-assisted neurorehabilitation is becoming an established method to complement conventional therapy after stroke and provide intensive therapy regimes in unsupervised settings (e.g., home rehabilitation). Intensive therapies may temporarily contribute to increasing muscle tone and spasticity, especially in stroke patients presenting tone alterations. If sustained without supervision, such an increase in muscle tone could have negative effects (e.g., functional disability, pain). We propose an online perturbation-based method that monitors finger muscle tone during unsupervised robot-assisted hand therapy exercises.

Methods: We used the ReHandyBot, a novel 2 degrees of freedom (DOF) haptic device to perform robot-assisted therapy exercises training hand grasping (i.e., flexion-extension of the fingers) and forearm pronosupination. The tone estimation method consisted of fast (150 ms) and slow (250 ms) 20 mm ramp-and-hold perturbations on the grasping DOF, which were applied during the exercises to stretch the finger flexors. The perturbation-induced peak force at the finger pads was used to compute tone. In this work, we evaluated the method performance in a stiffness identification experiment with springs (0.97 and 1.57 N/mm), which simulated the stiffness of a human hand, and in a pilot study with subjects with increased muscle tone after stroke and unimpaired, which performed one active sensorimotor exercise embedding the tone monitoring method.

Results: The method accurately estimates forces with root mean square percentage errors of 3.8% and 11.3% for the soft and stiff spring, respectively. In the pilot study, six chronic ischemic stroke patients [141.8 (56.7) months after stroke, 64.3 (9.5) years old, expressed as mean (std)] and ten unimpaired subjects [59.9 (6.1) years old] were tested without adverse events. The average reaction force at the level of the fingertip during slow and fast perturbations in the exercise were respectively 10.7 (5.6) N and 13.7 (5.6) N for the patients and 5.8 (4.2) N and 6.8 (5.1) N for the unimpaired subjects.

Discussion: The proposed method estimates reaction forces of physical springs accurately, and captures online increased reaction forces in persons with stroke compared to unimpaired subjects within unsupervised human-robot interactions. In the future, the identified range of muscle tone increase after stroke could be used to customize therapy for each subject and maintain safety during intensive robot-assisted rehabilitation.

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.

Robotics Summit & Expo: 10–11 May 2023, BOSTONICRA 2023: 29 May–2 June 2023, LONDONRoboCup 2023: 4–10 July 2023, BORDEAUX, FRANCERSS 2023: 10–14 July 2023, DAEGU, KOREAIEEE RO-MAN 2023: 28–31 August 2023, BUSAN, KOREACLAWAR 2023: 2–4 October 2023, FLORIANOPOLIS, BRAZIL

Enjoy today’s videos!

ReachBot is a new concept for planetary exploration, consisting of a small body and long, lightweight extending arms loaded primarily in tension. The arms are equipped with spined grippers for anchoring on rock surfaces. Experiments with rock grasping and coordinated locomotion illustrate the advantages of low inertia passive grippers, triggered by impact and using stored mechanical energy for the internal force.

[ Paper ]

DHL Supply Chain is deploying Stretch to automate trailer unloading and support warehouse associates. In the past 8-10 years there have been tremendous advancements in warehouse automation. DHL has been a leader in deploying automation technology to improve efficiency, drive cost-effectiveness, and support exceptional employee experiences. Discover how they are putting Stretch to work.

[ Boston Dynamics ]

Scientists at the University of Bristol have drawn on the design and life of a mysterious zooplankton to develop underwater robots. These robotic units called RoboSalps, after their animal namesakes, have been engineered to operate in unknown and extreme environments such as extra-terrestrial oceans.

RoboSalps are unique as each individual module can swim on its own. This is possible because of a small motor with rotor blades—typically used for drones—inserted into the soft tubular structure. When swimming on their own, RoboSalps modules are difficult to control, but after joining them together to form colonies, they become more stable and show sophisticated movements.

[ Bristol ]

AIce is an Autonomous Zamboni Convoy that is designed to automate ice resurfacing in any ice rink. The current goal of this product is to demonstrate an autonomous driving task based on leader-follower utilizing computer vision, motion planning, control, and localization. The team aspires to build this project in a manner that will give it potential to grow after the project is completed, to a fully autonomous Zamboni.

[ AIce ] via [ CMU ]

We propose a new neck design for legged robots to achieve robust visual-inertial state estimation in dynamic locomotion. While visual-inertial state estimation is widely used in robotics, it has a problem of being disturbed by the impacts and vibration generated when legged robots move dynamically. To address this problem, we develop a tunable neck system that absorbs the impacts and vibration during diverse gait locomotions.

[ Paper ]

I will not make any comments about meat-handling robots.

[ Soft Robotics ]

This should be pretty cool to see once it’s running on hardware.

[ Paper ]

A largely untapped potential for aerial robots is to capture airborne targets in flight. We present an approach in which a simple dynamic model of a quadrotor/target interaction leads to the design of a gripper and associated velocity sufficiency region with a high probability of capture. We demonstrate in-flight experiments that a 550 g drone can capture an 85 g target at various relative velocities between 1 m/s and 2.7 m/s.

[ Paper ]

The process of bin picking presents new challenges again and again. In order to be able to deal with small and flat component geometries as well as with entanglements and packaging material, methods of machine learning are used at Fraunhofer IPA. In addition to increasing the robustness of the removal process, attempts are also made to minimize the process time and the commissioning effort.

[ Fraunhofer ]

The history of lidar: After the devastating loss of Mars Observer, the Goddard team mourns and regroups to build a second MOLA instrument for the Mars Global Surveyor mission. But before their laser altimeter goes to Mars, the team seizes an opportunity to test it on the Space Shuttle.

[ NASA ] [Leaders in Lidar, Chapter 1]

What are the challenges in the development of humanoid robotic systems? What are the advantages and what are the criticalities? Bruno Siciliano, coordinator of PRISMA Lab, discusses these themes with Fabio Puglia, president and co-founder of Oversonic Robotics. Moderated by science journalist Riccardo Oldani, Siciliano and Puglia also bring concrete cases of the development of two humanoid robots, Rodyman and RoBee respectively, and their applications.

[ PRISMA Lab ]

Please join us for a lively panel discussion featuring GRASP Faculty members including Dr. Nadia Figueroa, Dr. Dinesh Jayaraman, and Dr. Marc Miskin. This panel will be moderated by Penn Engineering SEAS Dean Dr. Vijay Kumar.

[ UPenn ]

An interactive webinar discussing how progress in robotic materials is impacting the field of manipulation. The second conversation in the series, hosted by Northwestern’s Center for Robotics and Biosystems. Moderator: Carmel Majidi, Carnegie Mellon University. Panelists: Elliot W. Hawkes, UC Santa Barbara; Tess Hellebrekers, Meta AI; Nancy Pollard, Carnegie Mellon University; Yon Visell, UC Santa Barbara.

[ Northwestern ]

At the 2022 Conference on Robot Learning (CoRL), Waymo’s Head of Research Drago Anguelov shared some of his team’s recent research on improving models for behavior.

[ Waymo ]

This week’s CMU RI Seminar is from Russ Tedrake, on “Motion Planning Around Obstacles with Graphs of Convex Sets.”

[ CMU ]

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.

Robotics Summit & Expo: 10–11 May 2023, BOSTONICRA 2023: 29 May–2 June 2023, LONDONRoboCup 2023: 4–10 July 2023, BORDEAUX, FRANCERSS 2023: 10–14 July 2023, DAEGU, KOREAIEEE RO-MAN 2023: 28–31 August 2023, BUSAN, KOREACLAWAR 2023: 2–4 October 2023, FLORIANOPOLIS, BRAZIL

Enjoy today’s videos!

ReachBot is a new concept for planetary exploration, consisting of a small body and long, lightweight extending arms loaded primarily in tension. The arms are equipped with spined grippers for anchoring on rock surfaces. Experiments with rock grasping and coordinated locomotion illustrate the advantages of low inertia passive grippers, triggered by impact and using stored mechanical energy for the internal force.

[ Paper ]

DHL Supply Chain is deploying Stretch to automate trailer unloading and support warehouse associates. In the past 8-10 years there have been tremendous advancements in warehouse automation. DHL has been a leader in deploying automation technology to improve efficiency, drive cost-effectiveness, and support exceptional employee experiences. Discover how they are putting Stretch to work.

[ Boston Dynamics ]

Scientists at the University of Bristol have drawn on the design and life of a mysterious zooplankton to develop underwater robots. These robotic units called RoboSalps, after their animal namesakes, have been engineered to operate in unknown and extreme environments such as extra-terrestrial oceans.

RoboSalps are unique as each individual module can swim on its own. This is possible because of a small motor with rotor blades—typically used for drones—inserted into the soft tubular structure. When swimming on their own, RoboSalps modules are difficult to control, but after joining them together to form colonies, they become more stable and show sophisticated movements.

[ Bristol ]

AIce is an Autonomous Zamboni Convoy that is designed to automate ice resurfacing in any ice rink. The current goal of this product is to demonstrate an autonomous driving task based on leader-follower utilizing computer vision, motion planning, control, and localization. The team aspires to build this project in a manner that will give it potential to grow after the project is completed, to a fully autonomous Zamboni.

[ AIce ] via [ CMU ]

We propose a new neck design for legged robots to achieve robust visual-inertial state estimation in dynamic locomotion. While visual-inertial state estimation is widely used in robotics, it has a problem of being disturbed by the impacts and vibration generated when legged robots move dynamically. To address this problem, we develop a tunable neck system that absorbs the impacts and vibration during diverse gait locomotions.

[ Paper ]

I will not make any comments about meat-handling robots.

[ Soft Robotics ]

This should be pretty cool to see once it’s running on hardware.

[ Paper ]

A largely untapped potential for aerial robots is to capture airborne targets in flight. We present an approach in which a simple dynamic model of a quadrotor/target interaction leads to the design of a gripper and associated velocity sufficiency region with a high probability of capture. We demonstrate in-flight experiments that a 550 g drone can capture an 85 g target at various relative velocities between 1 m/s and 2.7 m/s.

[ Paper ]

The process of bin picking presents new challenges again and again. In order to be able to deal with small and flat component geometries as well as with entanglements and packaging material, methods of machine learning are used at Fraunhofer IPA. In addition to increasing the robustness of the removal process, attempts are also made to minimize the process time and the commissioning effort.

[ Fraunhofer ]

The history of lidar: After the devastating loss of Mars Observer, the Goddard team mourns and regroups to build a second MOLA instrument for the Mars Global Surveyor mission. But before their laser altimeter goes to Mars, the team seizes an opportunity to test it on the Space Shuttle.

[ NASA ] [Leaders in Lidar, Chapter 1]

What are the challenges in the development of humanoid robotic systems? What are the advantages and what are the criticalities? Bruno Siciliano, coordinator of PRISMA Lab, discusses these themes with Fabio Puglia, president and co-founder of Oversonic Robotics. Moderated by science journalist Riccardo Oldani, Siciliano and Puglia also bring concrete cases of the development of two humanoid robots, Rodyman and RoBee respectively, and their applications.

[ PRISMA Lab ]

Please join us for a lively panel discussion featuring GRASP Faculty members including Dr. Nadia Figueroa, Dr. Dinesh Jayaraman, and Dr. Marc Miskin. This panel will be moderated by Penn Engineering SEAS Dean Dr. Vijay Kumar.

[ UPenn ]

An interactive webinar discussing how progress in robotic materials is impacting the field of manipulation. The second conversation in the series, hosted by Northwestern’s Center for Robotics and Biosystems. Moderator: Carmel Majidi, Carnegie Mellon University. Panelists: Elliot W. Hawkes, UC Santa Barbara; Tess Hellebrekers, Meta AI; Nancy Pollard, Carnegie Mellon University; Yon Visell, UC Santa Barbara.

[ Northwestern ]

At the 2022 Conference on Robot Learning (CoRL), Waymo’s Head of Research Drago Anguelov shared some of his team’s recent research on improving models for behavior.

[ Waymo ]

This week’s CMU RI Seminar is from Russ Tedrake, on “Motion Planning Around Obstacles with Graphs of Convex Sets.”

[ CMU ]

Pages