Загрузка видео...

Не удалось загрузить видео

На главную

We just open-sourced luwu_mjlab: an RL training environment for Luwu Dynamics quadruped robots. Built on mjlab + MuJoCo Warp, it lets us train locomotion and get-up policies in simulation, then validate them on real robots. GitHub:

luwu_dynamics's profile picture

XGO Robot

4,711 subscribers

11,541 просмотров • 14 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Training fully autonomous robots takes more data than the real world can easily provide. Simulation lets us train, test, and deploy autonomous software without being limited by robots, space, or cost. Here’s OM1 running in simulation side-by-side to the real world.
1:26

Training fully autonomous robots takes more data than the real world can easily provide. Simulation lets us train, test, and deploy autonomous software without being limited by robots, space, or cost. Here’s OM1 running in simulation side-by-side to the real world.

OpenMind

120,843 просмотров • 6 месяцев назад

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.
0:37

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.

Kevin Zakka

91,840 просмотров • 9 месяцев назад

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.
0:22

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 просмотров • 1 год назад

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
1:13

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

15,533 просмотров • 1 год назад

Learning H-Infinity Locomotion Control Stable locomotion in precipitous environments is an essential capability of quadruped robots, demanding the ability to resist various external disturbances. However, recent learning-based policies only use basic domain randomization to
2:01

Learning H-Infinity Locomotion Control Stable locomotion in precipitous environments is an essential capability of quadruped robots, demanding the ability to resist various external disturbances. However, recent learning-based policies only use basic domain randomization to

AK

38,603 просмотров • 2 лет назад

Jensen just announced Newton, an open-source physics engine for robotics simulation developed by NVIDIA, Google DeepMind, and Disney Research. ⦿ Built on NVIDIA Warp, it offers GPU-accelerated performance and compatibility with frameworks like MuJoCo and Isaac Lab. ⦿ Features differentiable physics, extensibility for multiphysics simulations, and integration with OpenUSD for flexible data modeling. ⦿ Newton addresses the sim-to-real gap by creating realistic virtual environments for robot training and testing. ⦿ Disney Research is using Newton to power next-gen entertainment robots, including Star Wars-inspired BDX droids.
3:32

Jensen just announced Newton, an open-source physics engine for robotics simulation developed by NVIDIA, Google DeepMind, and Disney Research. ⦿ Built on NVIDIA Warp, it offers GPU-accelerated performance and compatibility with frameworks like MuJoCo and Isaac Lab. ⦿ Features differentiable physics, extensibility for multiphysics simulations, and integration with OpenUSD for flexible data modeling. ⦿ Newton addresses the sim-to-real gap by creating realistic virtual environments for robot training and testing. ⦿ Disney Research is using Newton to power next-gen entertainment robots, including Star Wars-inspired BDX droids.

The Humanoid Hub

127,482 просмотров • 1 год назад

Meet mjlab. Powered by MuJoCo Warp. Drops Monday.
0:52

Meet mjlab. Powered by MuJoCo Warp. Drops Monday.

Kevin Zakka

25,004 просмотров • 9 месяцев назад

We built an entire VR game....and open sourced the entire thing. Introducing "North Star" - play it today on Quest, and download the entire project on Github!
0:55

We built an entire VR game....and open sourced the entire thing. Introducing "North Star" - play it today on Quest, and download the entire project on Github!

Jake Steinerman 🔜 Meta Connect

38,043 просмотров • 1 год назад

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:
2:34

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:

Dave Lee

372,039 просмотров • 3 лет назад

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion Robotics to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla
1:06:07

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion Robotics to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

The TWIML AI Podcast

22,264 просмотров • 5 месяцев назад

🤖🤖🤖 Following RoboVerse, we introduce another work focused on Robotic Tactile Simulation - Taccel Simulator. Taccel is a high-performance simulation platform for vision-based tactile sensors and robots. 🚀🚀🚀 Boosted by Nvidia Warp, we optimize Taccel with highly parallelized simulations and support 900fps simulation with 4k+ parallel training envs. 🤝🤝🤝 Taccel is designed with user-friendly APIs and is easy to use. We open-sourced all the code and documentation. Feel free to try! Project: Preprint: Code:
2:27

🤖🤖🤖 Following RoboVerse, we introduce another work focused on Robotic Tactile Simulation - Taccel Simulator. Taccel is a high-performance simulation platform for vision-based tactile sensors and robots. 🚀🚀🚀 Boosted by Nvidia Warp, we optimize Taccel with highly parallelized simulations and support 900fps simulation with 4k+ parallel training envs. 🤝🤝🤝 Taccel is designed with user-friendly APIs and is easy to use. We open-sourced all the code and documentation. Feel free to try! Project: Preprint: Code:

Siyuan Huang

10,650 просмотров • 1 год назад

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:
1:37

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:

The Humanoid Hub

106,447 просмотров • 8 месяцев назад

For this hackathon I taught a robot to beat you in Jenga. It sims every possible move, picks the block that's the best move, then an RL policy pushes it out. Built in MuJoCo & Three.js, running on a real AgileX Robotics arm.
0:30

For this hackathon I taught a robot to beat you in Jenga. It sims every possible move, picks the block that's the best move, then an RL policy pushes it out. Built in MuJoCo & Three.js, running on a real AgileX Robotics arm.

jonathanhawkins

39,496 просмотров • 1 месяц назад

Robots in theme parks! 🎢 Theme parks are starting to use robots to improve entertainment. Universal Studios Hollywood is turning Boston Dynamics robot dogs into baby dragons based on 'How to Train Your Dragon' movie. The robots walk, move, and act like real creatures, letting guests interact with them up close. This makes the park experience more fun and memorable. It also shows how robotics can be used in creative, hands-on ways. Expect to see more of this in future attractions. Enthusiasm for entertainment robots among humans is huge. This is proven, for example, by the robots created by Walt Disney Imagineering.
0:28

Robots in theme parks! 🎢 Theme parks are starting to use robots to improve entertainment. Universal Studios Hollywood is turning Boston Dynamics robot dogs into baby dragons based on 'How to Train Your Dragon' movie. The robots walk, move, and act like real creatures, letting guests interact with them up close. This makes the park experience more fun and memorable. It also shows how robotics can be used in creative, hands-on ways. Expect to see more of this in future attractions. Enthusiasm for entertainment robots among humans is huge. This is proven, for example, by the robots created by Walt Disney Imagineering.

Lukas Ziegler

30,005 просмотров • 1 год назад

We Luis Felipe Casas have successfully deployed an in-hand manipulation policy to the LEAP hand following RL training in MuJoCo Playground. Sim-to-real isn’t as straightforward as it seems. Policy design and real-world tuning matter. Working on improving the policy further.
0:49

We Luis Felipe Casas have successfully deployed an in-hand manipulation policy to the LEAP hand following RL training in MuJoCo Playground. Sim-to-real isn’t as straightforward as it seems. Policy design and real-world tuning matter. Working on improving the policy further.

Yu Xiang

11,030 просмотров • 2 месяцев назад

Elon : For Optimus, it’s difficult to match the flywheel of the existing vehicle fleet. The plan is to build a fleet of 10k–30k robots to perform self-play and testing. Millions of robotic agents will train in Tesla's "reality generator" (simulation), the real robots can then close the gap between simulation and reality.
1:21

Elon : For Optimus, it’s difficult to match the flywheel of the existing vehicle fleet. The plan is to build a fleet of 10k–30k robots to perform self-play and testing. Millions of robotic agents will train in Tesla's "reality generator" (simulation), the real robots can then close the gap between simulation and reality.

The Humanoid Hub

26,474 просмотров • 4 месяцев назад

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”
1:20

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Teslaconomics

42,563 просмотров • 4 месяцев назад

🇨🇳 China is deplying Robots everywhere. Here Unitree's humanoid robots + quadruped robot dogs patrol and perform duty in a team. You scale patrol hours without scaling headcount. Robots handle patrols, officers focus on judgment and de-escalation.
0:23

🇨🇳 China is deplying Robots everywhere. Here Unitree's humanoid robots + quadruped robot dogs patrol and perform duty in a team. You scale patrol hours without scaling headcount. Robots handle patrols, officers focus on judgment and de-escalation.

Rohan Paul

247,333 просмотров • 6 месяцев назад