Feed aggregator



The tricked out version of the ANYmal quadruped, as customized by Zürich-based Swiss-Mile, just keeps getting better and better. Starting with a commercial quadruped, adding powered wheels made the robot fast and efficient, while still allowing it to handle curbs and stairs. A few years ago, the robot learned how to stand up, which is an efficient way of moving and made the robot much more pleasant to hug, but more importantly, it unlocked the potential for the robot to start doing manipulation with its wheel-hand-leg-arms.

Doing any sort of practical manipulation with ANYmal is complicated, because its limbs were designed to be legs, not arms. But at the Robotic Systems Lab at ETH Zurich, they’ve managed to teach this robot to use its limbs to open doors, and even to grasp a package off of a table and toss it into a box.

When it makes a mistake in the real world, the robot has already learned the skills to recover.

The ETHZ researchers got the robot to reliably perform these complex behaviors using a kind of reinforcement learning called ‘curiosity driven’ learning. In simulation, the robot is given a goal that it needs to achieve—in this case, the robot is rewarded for achieving the goal of passing through a doorway, or for getting a package into a box. These are very high-level goals (also called “sparse rewards”), and the robot doesn’t get any encouragement along the way. Instead, it has to figure out how to complete the entire task from scratch.

The next step is to endow the robot with a sense of contact-based surprise.

Given an impractical amount of simulation time, the robot would likely figure out how to do these tasks on its own. But to give it a useful starting point, the researchers introduced the concept of curiosity, which encourages the robot to play with goal-related objects. “In the context of this work, ‘curiosity’ refers to a natural desire or motivation for our robot to explore and learn about its environment,” says author Marko Bjelonic, “Allowing it to discover solutions for tasks without needing engineers to explicitly specify what to do.” For the door-opening task, the robot is instructed to be curious about the position of the door handle, while for the package-grasping task, the robot is told to be curious about the motion and location of the package. Leveraging this curiosity to find ways of playing around and changing those parameters helps the robot achieve its goals, without the researchers having to provide any other kind of input.

The behaviors that the robot comes up with through this process are reliable, and they’re also diverse, which is one of the benefits of using sparse rewards. “The learning process is sensitive to small changes in the training environment,” explains Bjelonic. “This sensitivity allows the agent to explore various solutions and trajectories, potentially leading to more innovative task completion in complex, dynamic scenarios.” For example, with the door opening task, the robot discovered how to open it with either one of its end-effectors, or both at the same time, which makes it better at actually completing the task in the real world. The package manipulation is even more interesting, because the robot sometimes dropped the package in training, but it autonomously learned how to pick it up again. So, when it makes a mistake in the real world, the robot has already learned the skills to recover.

There’s still a bit of research-y cheating going on here, since the robot is relying on the visual code-based AprilTags system to tell it where relevant things (like door handles) are in the real world. But that’s a fairly minor shortcut, since direct detection of things like doors and packages is a fairly well understood problem. Bjelonic says that the next step is to endow the robot with a sense of contact-based surprise, in order to encourage exploration, which is a little bit gentler than what we see here.

Remember, too, that while this is definitely a research paper, Swiss-Mile is a company that wants to get this robot out into the world doing useful stuff. So, unlike most pure research that we cover, there’s a slightly better chance here for this ANYmal to wheel-hand-leg-arm its way into some practical application.



The tricked out version of the ANYmal quadruped, as customized by Zürich-based Swiss-Mile, just keeps getting better and better. Starting with a commercial quadruped, adding powered wheels made the robot fast and efficient, while still allowing it to handle curbs and stairs. A few years ago, the robot learned how to stand up, which is an efficient way of moving and made the robot much more pleasant to hug, but more importantly, it unlocked the potential for the robot to start doing manipulation with its wheel-hand-leg-arms.

Doing any sort of practical manipulation with ANYmal is complicated, because its limbs were designed to be legs, not arms. But at the Robotic Systems Lab at ETH Zurich, they’ve managed to teach this robot to use its limbs to open doors, and even to grasp a package off of a table and toss it into a box.

When it makes a mistake in the real world, the robot has already learned the skills to recover.

The ETHZ researchers got the robot to reliably perform these complex behaviors using a kind of reinforcement learning called ‘curiosity driven’ learning. In simulation, the robot is given a goal that it needs to achieve—in this case, the robot is rewarded for achieving the goal of passing through a doorway, or for getting a package into a box. These are very high-level goals (also called “sparse rewards”), and the robot doesn’t get any encouragement along the way. Instead, it has to figure out how to complete the entire task from scratch.

The next step is to endow the robot with a sense of contact-based surprise.

Given an impractical amount of simulation time, the robot would likely figure out how to do these tasks on its own. But to give it a useful starting point, the researchers introduced the concept of curiosity, which encourages the robot to play with goal-related objects. “In the context of this work, ‘curiosity’ refers to a natural desire or motivation for our robot to explore and learn about its environment,” says author Marko Bjelonic, “Allowing it to discover solutions for tasks without needing engineers to explicitly specify what to do.” For the door-opening task, the robot is instructed to be curious about the position of the door handle, while for the package-grasping task, the robot is told to be curious about the motion and location of the package. Leveraging this curiosity to find ways of playing around and changing those parameters helps the robot achieve its goals, without the researchers having to provide any other kind of input.

The behaviors that the robot comes up with through this process are reliable, and they’re also diverse, which is one of the benefits of using sparse rewards. “The learning process is sensitive to small changes in the training environment,” explains Bjelonic. “This sensitivity allows the agent to explore various solutions and trajectories, potentially leading to more innovative task completion in complex, dynamic scenarios.” For example, with the door opening task, the robot discovered how to open it with either one of its end-effectors, or both at the same time, which makes it better at actually completing the task in the real world. The package manipulation is even more interesting, because the robot sometimes dropped the package in training, but it autonomously learned how to pick it up again. So, when it makes a mistake in the real world, the robot has already learned the skills to recover.

There’s still a bit of research-y cheating going on here, since the robot is relying on the visual code-based AprilTags system to tell it where relevant things (like door handles) are in the real world. But that’s a fairly minor shortcut, since direct detection of things like doors and packages is a fairly well understood problem. Bjelonic says that the next step is to endow the robot with a sense of contact-based surprise, in order to encourage exploration, which is a little bit gentler than what we see here.

Remember, too, that while this is definitely a research paper, Swiss-Mile is a company that wants to get this robot out into the world doing useful stuff. So, unlike most pure research that we cover, there’s a slightly better chance here for this ANYmal to wheel-hand-leg-arm its way into some practical application.



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.

Humanoids 2023: 12–14 December 2023, AUSTIN, TEXASCybathlon Challenges: 2 February 2024, ZURICHEurobot Open 2024: 8–11 May 2024, LA ROCHE-SUR-YON, FRANCE

Enjoy today’s videos!

This is such an excellent use for autonomous robots: difficult, precise work that benefits from having access to lots of data. Push a button, stand back, and let the robot completely reshape your landscape.

[ Gravis Robotics ]

Universal Robots introduced the UR30 at IREX, in Tokyo, which can lift 30 kilograms—not the 63.5 kg that it says on the tire. That’s the weight of the UR30 itself.

Available for preorder now.

[ Universal Robots ]

IREX is taking place in Japan right now, and here’s a demo of Kaleido, a humanoid robot from Kawasaki.

[ Kawasaki ] via [ YouTube ]

The Unitree H1 is a full-size humanoid for under US $90,000 (!).

[ Unitree ]

This is extremely impressive but freaks me out a little to watch, and I’m not entirely sure why.

[ MIT CSAIL ]

If you look in the background of this video, there’s a person wearing an exoskeleton controlling the robot in the foreground. This is an ideal system for imitation learning, and the robot is then able to perform a similar task autonomously.

[ Github ]

Thanks, Kento!

The video shows highlights from the RoboCup 2023 Humanoid AdultSize competition in Bordeaux, France. The winning team NimbRo is based in the Autonomous Intelligent Systems lab of University of Bonn, Germany.

[ NimbRo ]

This video describes an approach to generate complex, multicontact motion trajectories using user guidance provided through Virtual Reality. User input is useful to reduce the search space through defined key frame. We show these results on the humanoid robot, Valkyrie, from NASA Johnson Space Center, in both simulation and on hardware.

[ Paper ] via [ IHMC ]

For the foreseeable future, this is likely going to be necessary for most robots doing semi-structured tasks like trailer unloading: human in (or on) the loop supervision.

Of course, one human can supervise many robots at once, so as long as most of the robots are autonomous most of the time, it’s all good.

[ Contoro ]

The Danish medical technology start-up ROPCA ApS has launched its first medical product, the arthritis robot “ARTHUR”, which is already being used in the first hospitals. It is based on the lightweight robot LBR Med and supports the early diagnosis of rheumatoid arthritis using robot-assisted ultrasound. This ultrasound robot enables autonomous examination and can thus counteract the shortage of specialists in medicine. This enables earlier treatment, which is essential for a good therapeutic outcome.

[ ROPCA ]

Since 2020, KIMLAB has dedicated efforts to craft an affordable humanoid robot tailored for educational needs, boasting vital features like an ROS-enabled processor and multimodal sensory capabilities. By incorporating a commercially available product, we seamlessly integrated an SBC (Orange PI Lite 2), a camera, and an IMU to create a cost-effective humanoid robot, priced at less than $700 in total.

[ KIMLAB ]

As the newest product launched by WEILAN, the 6th generation AlphaDog, namely BabyAlpha, is defined as a new family member of the artificial intelligence era. Designed for domestic scenarios, it was born for the purpose of providing joyful companionship. Not only do they possess autonomous emotions and distinct personalities, but they also excel in various skills such as singing and dancing, FaceTime calling, English communication, and sports.

[ Weilan ] via [ ModernExpress ]



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.

Humanoids 2023: 12–14 December 2023, AUSTIN, TEXASCybathlon Challenges: 2 February 2024, ZURICHEurobot Open 2024: 8–11 May 2024, LA ROCHE-SUR-YON, FRANCE

Enjoy today’s videos!

This is such an excellent use for autonomous robots: difficult, precise work that benefits from having access to lots of data. Push a button, stand back, and let the robot completely reshape your landscape.

[ Gravis Robotics ]

Universal Robots introduced the UR30 at IREX, in Tokyo, which can lift 30 kilograms—not the 63.5 kg that it says on the tire. That’s the weight of the UR30 itself.

Available for preorder now.

[ Universal Robots ]

IREX is taking place in Japan right now, and here’s a demo of Kaleido, a humanoid robot from Kawasaki.

[ Kawasaki ] via [ YouTube ]

The Unitree H1 is a full-size humanoid for under US $90,000 (!).

[ Unitree ]

This is extremely impressive but freaks me out a little to watch, and I’m not entirely sure why.

[ MIT CSAIL ]

If you look in the background of this video, there’s a person wearing an exoskeleton controlling the robot in the foreground. This is an ideal system for imitation learning, and the robot is then able to perform a similar task autonomously.

[ Github ]

Thanks, Kento!

The video shows highlights from the RoboCup 2023 Humanoid AdultSize competition in Bordeaux, France. The winning team NimbRo is based in the Autonomous Intelligent Systems lab of University of Bonn, Germany.

[ NimbRo ]

This video describes an approach to generate complex, multicontact motion trajectories using user guidance provided through Virtual Reality. User input is useful to reduce the search space through defined key frame. We show these results on the humanoid robot, Valkyrie, from NASA Johnson Space Center, in both simulation and on hardware.

[ Paper ] via [ IHMC ]

For the foreseeable future, this is likely going to be necessary for most robots doing semi-structured tasks like trailer unloading: human in (or on) the loop supervision.

Of course, one human can supervise many robots at once, so as long as most of the robots are autonomous most of the time, it’s all good.

[ Contoro ]

The Danish medical technology start-up ROPCA ApS has launched its first medical product, the arthritis robot “ARTHUR”, which is already being used in the first hospitals. It is based on the lightweight robot LBR Med and supports the early diagnosis of rheumatoid arthritis using robot-assisted ultrasound. This ultrasound robot enables autonomous examination and can thus counteract the shortage of specialists in medicine. This enables earlier treatment, which is essential for a good therapeutic outcome.

[ ROPCA ]

Since 2020, KIMLAB has dedicated efforts to craft an affordable humanoid robot tailored for educational needs, boasting vital features like an ROS-enabled processor and multimodal sensory capabilities. By incorporating a commercially available product, we seamlessly integrated an SBC (Orange PI Lite 2), a camera, and an IMU to create a cost-effective humanoid robot, priced at less than $700 in total.

[ KIMLAB ]

As the newest product launched by WEILAN, the 6th generation AlphaDog, namely BabyAlpha, is defined as a new family member of the artificial intelligence era. Designed for domestic scenarios, it was born for the purpose of providing joyful companionship. Not only do they possess autonomous emotions and distinct personalities, but they also excel in various skills such as singing and dancing, FaceTime calling, English communication, and sports.

[ Weilan ] via [ ModernExpress ]

Affective behaviors enable social robots to not only establish better connections with humans but also serve as a tool for the robots to express their internal states. It has been well established that emotions are important to signal understanding in Human-Robot Interaction (HRI). This work aims to harness the power of Large Language Models (LLM) and proposes an approach to control the affective behavior of robots. By interpreting emotion appraisal as an Emotion Recognition in Conversation (ERC) tasks, we used GPT-3.5 to predict the emotion of a robot’s turn in real-time, using the dialogue history of the ongoing conversation. The robot signaled the predicted emotion using facial expressions. The model was evaluated in a within-subjects user study (N = 47) where the model-driven emotion generation was compared against conditions where the robot did not display any emotions and where it displayed incongruent emotions. The participants interacted with the robot by playing a card sorting game that was specifically designed to evoke emotions. The results indicated that the emotions were reliably generated by the LLM and the participants were able to perceive the robot’s emotions. It was found that the robot expressing congruent model-driven facial emotion expressions were perceived to be significantly more human-like, emotionally appropriate, and elicit a more positive impression. Participants also scored significantly better in the card sorting game when the robot displayed congruent facial expressions. From a technical perspective, the study shows that LLMs can be used to control the affective behavior of robots reliably in real-time. Additionally, our results could be used in devising novel human-robot interactions, making robots more effective in roles where emotional interaction is important, such as therapy, companionship, or customer service.

This paper summarizes the structure and findings from the first Workshop on Troubles and Failures in Conversations between Humans and Robots. The workshop was organized to bring together a small, interdisciplinary group of researchers working on miscommunication from two complementary perspectives. One group of technology-oriented researchers was made up of roboticists, Human-Robot Interaction (HRI) researchers and dialogue system experts. The second group involved experts from conversation analysis, cognitive science, and linguistics. Uniting both groups of researchers is the belief that communication failures between humans and machines need to be taken seriously and that a systematic analysis of such failures may open fruitful avenues in research beyond current practices to improve such systems, including both speech-centric and multimodal interfaces. This workshop represents a starting point for this endeavour. The aim of the workshop was threefold: Firstly, to establish an interdisciplinary network of researchers that share a common interest in investigating communicative failures with a particular view towards robotic speech interfaces; secondly, to gain a partial overview of the “failure landscape” as experienced by roboticists and HRI researchers; and thirdly, to determine the potential for creating a robotic benchmark scenario for testing future speech interfaces with respect to the identified failures. The present article summarizes both the “failure landscape” surveyed during the workshop as well as the outcomes of the attempt to define a benchmark scenario.

Interaction with artificial social agents is often designed based on models of human interaction and dialogue. While this is certainly useful for basic interaction mechanisms, it has been argued that social communication strategies and social language use, a “particularly human” ability, may not be appropriate and transferable to interaction with artificial conversational agents. In this paper, we present qualitative research exploring whether users expect artificial agents to use politeness—a fundamental mechanism of social communication—in language-based human-robot interaction. Based on semi-structured interviews, we found that humans mostly ascribe a functional, rule-based use of polite language to humanoid robots and do not expect them to apply socially motivated politeness strategies that they expect in human interaction. This study 1) provides insights for interaction design for social robots’ politeness use from a user perspective, and 2) contributes to politeness research based on the analysis of our participants’ perspectives on politeness.

Identifying an accurate dynamics model remains challenging for humanoid robots. The difficulty is mainly due to the following two points. First, a good initial model is required to evaluate the feasibility of motions for data acquisition. Second, a highly nonlinear optimization problem needs to be solved to design movements to acquire the identification data. To cope with the first point, in this paper, we propose a curriculum of identification to gradually learn an accurate dynamics model from an unreliable initial model. For the second point, we propose using a large-scale human motion database to efficiently design the humanoid movements for the parameter identification. The contribution of our study is developing a humanoid identification method that does not require the good initial model and does not need to solve the highly nonlinear optimization problem. We showed that our curriculum-based approach was able to more efficiently identify humanoid model parameters than a method that just randomly picked reference motions for identification. We evaluated our proposed method in a simulation experiment and demonstrated that our curriculum was led to obtain a wide variety of motion data for efficient parameter estimation. Consequently, our approach successfully identified an accurate model of an 18-DoF, simulated upper-body humanoid robot.

Pages