Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

New research: Quadruped robots climbing ladders! 🦾🚀 Using RL-based control and a hooked end-effector, we're expanding robot capabilities in industrial environments. More info in the paper: Video:

Robotic Systems Lab

38,312 subscribers

16,424 views • 2 years ago •via X (Twitter)

Health & Wellness Science & Technology Education

Anya Rossi• Live Now

Private livecam show

4 Comments

Synthical2 years ago

Dark mode for this paper for those who read at night 🌚

Anthund2 years ago

so no safe place in the robots apocalypse.

Kordel France2 years ago

Wow, that robustness is very difficult to simulate, let alone achieve in reality. Well done!

Saar Reshef2 years ago

Cool

Related Videos

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,107 views • 2 years ago

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Circuit

11,802 views • 1 year ago

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:

Humanoid

23,975 views • 8 months ago

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Lerrel Pinto

46,221 views • 1 year ago

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,600 views • 2 years ago

Co-CEO Weekly Update 045 FF continues expanding the real-world deployment of its EAI Robotics ecosystem with new deliveries and scenario expansion. ① FF completed delivery of the Master robot and pilot delivery of the Aegis robot to Texas-based NS Federation, expanding real-world EAI Robotics deployment. ② The delivery introduces two new “Robot + Vehicle +” application scenarios: education and performance, backed by real market demand. ③ In “Robot & Vehicle + Education,” EAI robots support robotics training, research assistance, data collection, and hands-on AI education across schools, labs, and research institutions. ④ In “Robot & Vehicle + Performance,” robots serve as interactive performers for events, competitions, and entertainment environments—unlocking new consumer and light commercial markets. ⑤ On the EAI EV side, FF leadership held discussions in Washington, D.C. with the U.S. Department of Transportation and Department of Commerce on tariff policy, industry development, and technology innovation. #FFAI #AIXC #Robotics #FaradayFuture

Co-CEO Weekly Update 045 FF continues expanding the real-world deployment of its EAI Robotics ecosystem with new deliveries and scenario expansion. ① FF completed delivery of the Master robot and pilot delivery of the Aegis robot to Texas-based NS Federation, expanding real-world EAI Robotics deployment. ② The delivery introduces two new “Robot + Vehicle +” application scenarios: education and performance, backed by real market demand. ③ In “Robot & Vehicle + Education,” EAI robots support robotics training, research assistance, data collection, and hands-on AI education across schools, labs, and research institutions. ④ In “Robot & Vehicle + Performance,” robots serve as interactive performers for events, competitions, and entertainment environments—unlocking new consumer and light commercial markets. ⑤ On the EAI EV side, FF leadership held discussions in Washington, D.C. with the U.S. Department of Transportation and Department of Commerce on tariff policy, industry development, and technology innovation. #FFAI #AIXC #Robotics #FaradayFuture

YT Jia 贾跃亭

16,323 views • 7 months ago

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

Xiaolong Wang

113,042 views • 3 years ago

Check out our #ICRA2024 paper "Actor-Critic Model Predictive Control." Model-free #reinforcementlearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) benefits from robustness and online replanning capabilities. We combine both approaches by introducing a new framework called Actor-Critic Model Predictive Control. The key idea is to embed a differentiable MPC within an Actor-Critic RL framework. The proposed approach leverages the short-term predictive optimization capabilities of MPC with the exploratory and end-to-end training properties of RL. The resulting policy effectively manages both short-term decisions through the MPC-based actor and long-term prediction via the critic network, unifying the benefits of both model-based control and end-to-end learning. We validate our method in simulation and the real world with a quadcopter across various high-level tasks. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out-of-distribution behavior. Paper: Full Video with more details: Kudos to Ángel Romero, Yunlong Song IEEE ICRA University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

Check out our #ICRA2024 paper "Actor-Critic Model Predictive Control." Model-free #reinforcementlearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) benefits from robustness and online replanning capabilities. We combine both approaches by introducing a new framework called Actor-Critic Model Predictive Control. The key idea is to embed a differentiable MPC within an Actor-Critic RL framework. The proposed approach leverages the short-term predictive optimization capabilities of MPC with the exploratory and end-to-end training properties of RL. The resulting policy effectively manages both short-term decisions through the MPC-based actor and long-term prediction via the critic network, unifying the benefits of both model-based control and end-to-end learning. We validate our method in simulation and the real world with a quadcopter across various high-level tasks. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out-of-distribution behavior. Paper: Full Video with more details: Kudos to Ángel Romero, Yunlong Song IEEE ICRA University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

Davide Scaramuzza

34,920 views • 2 years ago

Another American industrial humanoid robot🤖🏭 Noble Machines (formerly UCR) has just emerged from stealth mode. Launching the first humanoid robot. Founded only 18 months ago, it has already been deployed in a Fortune Global 500 factory. Teams from SpaceX, NASA, and Apple specialize in the toughest, most tiring, and most dangerous industrial tasks: >27kg heavy load >5-hour battery life >Walking speed 0.8m/s >Climbing stairs, traversing scaffolding, and navigating chaotic construction sites > Modular end effector, allowing for quick tool change. > AI-controlled operation with end-to-end autonomy; learns new skills in hours >Autonomous operation + Telep-op mode >Rapid integration with existing enterprise workflows > Human-robot collaboration

Another American industrial humanoid robot🤖🏭 Noble Machines (formerly UCR) has just emerged from stealth mode. Launching the first humanoid robot. Founded only 18 months ago, it has already been deployed in a Fortune Global 500 factory. Teams from SpaceX, NASA, and Apple specialize in the toughest, most tiring, and most dangerous industrial tasks: >27kg heavy load >5-hour battery life >Walking speed 0.8m/s >Climbing stairs, traversing scaffolding, and navigating chaotic construction sites > Modular end effector, allowing for quick tool change. > AI-controlled operation with end-to-end autonomy; learns new skills in hours >Autonomous operation + Telep-op mode >Rapid integration with existing enterprise workflows > Human-robot collaboration

CyberRobo

44,908 views • 7 months ago

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Prime Intellect

1,150,419 views • 10 months ago

Germany-based Agile Robots has introduced its humanoid robot, Agile One, designed for industrial environments. It features a dexterous robotic hand and runs on a physical AI system trained using real factory data, allowing it to work and interact autonomously. The company is now aiming to move Agile One into full-scale production.

Germany-based Agile Robots has introduced its humanoid robot, Agile One, designed for industrial environments. It features a dexterous robotic hand and runs on a physical AI system trained using real factory data, allowing it to work and interact autonomously. The company is now aiming to move Agile One into full-scale production.

Space and Technology

37,743 views • 6 months ago

Cyber Vibes at Full Throttle! On July 25, Nanjing took on Lianyungang in the Jiangsu Super League. Robots from more than ten local Nanjing-based enterprises stole the show in the pre-match parade, including quadruped robot dogs, humanoid robots, fire-fighting unmanned ground vehicles, rescue robots and intelligent inspection vehicles. Innovative technological energy resonates wonderfully with the passion on the football pitch.

Cyber Vibes at Full Throttle! On July 25, Nanjing took on Lianyungang in the Jiangsu Super League. Robots from more than ten local Nanjing-based enterprises stole the show in the pre-match parade, including quadruped robot dogs, humanoid robots, fire-fighting unmanned ground vehicles, rescue robots and intelligent inspection vehicles. Innovative technological energy resonates wonderfully with the passion on the football pitch.

iNanjing

11,066 views • 2 months ago

Figure says it has increased humanoid robot production from one robot per day to one robot per hour in just 120 days. The robots undergo intensive testing, including repeated squats and jogging movements. Figure also demonstrated the robot's ability to climb stairs and navigate complex terrain using vision-based control.

Figure says it has increased humanoid robot production from one robot per day to one robot per hour in just 120 days. The robots undergo intensive testing, including repeated squats and jogging movements. Figure also demonstrated the robot's ability to climb stairs and navigate complex terrain using vision-based control.

Space and Technology

546,264 views • 4 months ago

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

NVIDIA Robotics

23,392 views • 3 months ago

Chelsea Finn (Chelsea Finn) on building general-purpose robotics, and bringing intelligence into the physical world. At AI Startup School in San Francisco. 00:00 - General Purpose Robots 00:11 - Challenges in Robotics Applications 00:57 - Physical Intelligence: A New Approach 01:47 - Learning from Language Models 02:08 - Data Sources for Training Robots 03:32 - Training with Real-World Data 04:39 - Initial Successes and Challenges 09:10 - Breakthrough in Robot Training 11:03 - Improving Performance 15:43 - Expanding Capabilities 17:34 - Robots in Unseen Environments 25:54 - Handling Open-Ended Prompts 29:36 - Evaluating Robot Performance 30:03 - Future Directions and Challenges 31:27 - Audience Q&A

Chelsea Finn (Chelsea Finn) on building general-purpose robotics, and bringing intelligence into the physical world. At AI Startup School in San Francisco. 00:00 - General Purpose Robots 00:11 - Challenges in Robotics Applications 00:57 - Physical Intelligence: A New Approach 01:47 - Learning from Language Models 02:08 - Data Sources for Training Robots 03:32 - Training with Real-World Data 04:39 - Initial Successes and Challenges 09:10 - Breakthrough in Robot Training 11:03 - Improving Performance 15:43 - Expanding Capabilities 17:34 - Robots in Unseen Environments 25:54 - Handling Open-Ended Prompts 29:36 - Evaluating Robot Performance 30:03 - Future Directions and Challenges 31:27 - Audience Q&A

Y Combinator

129,834 views • 1 year ago

Our new paper on 3D single-cell mapping of immune cells near pre-cancer lesions using CODA in a video. Watch until the end. More here:

Our new paper on 3D single-cell mapping of immune cells near pre-cancer lesions using CODA in a video. Watch until the end. More here:

Denis Wirtz

34,188 views • 2 years ago

We are excited to share our #CORL2024 paper (oral) on "Learning Quadruped Locomotion Using Differentiable Simulation" done in collaboration with Sangbae Kim Massachusetts Institute of Technology (MIT). We present a new way to learn to walk in minutes without parallelization, outperforming PPO in sample efficiency! PDF: Video: We present a new framework for learning quadruped locomotion. By leveraging differentiable simulation for policy optimization, our approach achieves fast convergence and stable training, significantly outperforming model-free #ReinforcementLearning methods like PPO in sample efficiency. The key enabler is to combine a high-fidelity, non-differentiable simulator for forward dynamics with a simplified surrogate model for gradient backpropagation. Our framework enables learning quadruped walking in simulation in minutes without parallelization. When augmented with GPU parallelization, our approach allows the quadruped robot to master diverse locomotion skills on challenging terrains in minutes. This work highlights one of the first successful real-world applications of differentiable simulation for quadruped robots, offering a compelling alternative to traditional RL methods. Kudos to Yunlong Song! UZH Science University of Zurich UZH Space Hub UZH IfI European Research Council (ERC) Massachusetts Institute of Technology (MIT)MechE

We are excited to share our #CORL2024 paper (oral) on "Learning Quadruped Locomotion Using Differentiable Simulation" done in collaboration with Sangbae Kim Massachusetts Institute of Technology (MIT). We present a new way to learn to walk in minutes without parallelization, outperforming PPO in sample efficiency! PDF: Video: We present a new framework for learning quadruped locomotion. By leveraging differentiable simulation for policy optimization, our approach achieves fast convergence and stable training, significantly outperforming model-free #ReinforcementLearning methods like PPO in sample efficiency. The key enabler is to combine a high-fidelity, non-differentiable simulator for forward dynamics with a simplified surrogate model for gradient backpropagation. Our framework enables learning quadruped walking in simulation in minutes without parallelization. When augmented with GPU parallelization, our approach allows the quadruped robot to master diverse locomotion skills on challenging terrains in minutes. This work highlights one of the first successful real-world applications of differentiable simulation for quadruped robots, offering a compelling alternative to traditional RL methods. Kudos to Yunlong Song! UZH Science University of Zurich UZH Space Hub UZH IfI European Research Council (ERC) Massachusetts Institute of Technology (MIT)MechE

Davide Scaramuzza

15,572 views • 1 year ago

A new approach to wildfire prevention！ DEEP Robotics has deployed China’s first robot dog patrol team for forest fire protection in the West Lake area. Powered by embodied AI, these quadruped robots support early detection, patrol, and risk monitoring—using technology to protect nature and strengthen emergency response.

A new approach to wildfire prevention！ DEEP Robotics has deployed China’s first robot dog patrol team for forest fire protection in the West Lake area. Powered by embodied AI, these quadruped robots support early detection, patrol, and risk monitoring—using technology to protect nature and strengthen emergency response.

DEEP Robotics

1,232,224 views • 9 months ago