Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

6,525 subscribers

11,114 Aufrufe • vor 4 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

This is a demonstration video of in-hand object rotation with new Torobo Hand. By leveraging large-scale parallel reinforcement learning in NVIDIA Isaac Sim, the learned policy can perform object manipulation in MuJoCo and on the real robot without any additional training.

東京ロボティクス株式会社

10,860 Aufrufe • vor 1 Jahr

The "reality gap" is narrowing. Sanctuary AI has demonstrated a sim-to-real breakthrough: "zero-shot" transfer for complex in-hand manipulation. By leveraging high-DOF hydraulic hands, the company successfully reoriented a cube in the physical world using a policy trained entirely in simulation.

The "reality gap" is narrowing. Sanctuary AI has demonstrated a sim-to-real breakthrough: "zero-shot" transfer for complex in-hand manipulation. By leveraging high-DOF hydraulic hands, the company successfully reoriented a cube in the physical world using a policy trained entirely in simulation.

Humanoids daily

12,391 Aufrufe • vor 4 Monaten

🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach. 😌After sustained effort, we’re now seeing encouraging progress. 🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision. Incredible teamwork with KL Hongyang Li Yue Xiangyu Hao Zhao Chonghao Sima

🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach. 😌After sustained effort, we’re now seeing encouraging progress. 🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision. Incredible teamwork with KL Hongyang Li Yue Xiangyu Hao Zhao Chonghao Sima

Jiazhi Yang

76,900 Aufrufe • vor 6 Monaten

🦾 Our robot hand can rotate objects over 6+ axes in the real-world! Introducing RotateIt (CoRL 2023), a Sim-to-Real policy that can rotate many objects over many axes, using vision and touch! Check it out: Paper: #CoRL2023

🦾 Our robot hand can rotate objects over 6+ axes in the real-world! Introducing RotateIt (CoRL 2023), a Sim-to-Real policy that can rotate many objects over many axes, using vision and touch! Check it out: Paper: #CoRL2023

Haozhi Qi

51,041 Aufrufe • vor 2 Jahren

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.

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

39,842 Aufrufe • vor 3 Monaten

By unifying prediction and control, NavWAM acts as a closed-loop policy out of the box. In evaluations, it outperforms planning-based world models without needing test-time action search, matches a much larger 7B VLA policy, and transfers successfully to real mobile robots.

By unifying prediction and control, NavWAM acts as a closed-loop policy out of the box. In evaluations, it outperforms planning-based world models without needing test-time action search, matches a much larger 7B VLA policy, and transfers successfully to real mobile robots.

Robots Digest 🤖

11,076 Aufrufe • vor 2 Monaten

A touch-aware humanoid manipulation policy that cleans the lab for you🧹🧪 Introducing Humanoid Touch Dream: a real-world system for dexterous, contact-rich humanoid loco-manipulation. Our key idea is simple: the policy predicts future hand forces and tactile latents alongside actions, within a single-stage training framework. 1/7

A touch-aware humanoid manipulation policy that cleans the lab for you🧹🧪 Introducing Humanoid Touch Dream: a real-world system for dexterous, contact-rich humanoid loco-manipulation. Our key idea is simple: the policy predicts future hand forces and tactile latents alongside actions, within a single-stage training framework. 1/7

Yaru Niu

87,966 Aufrufe • vor 4 Monaten

Democratic leadership plans to hand Middle East policy to a Congressman who described himself last year as "to the right" of JD Vance on the Iran war and more in line with Lindsey Graham on the matter:

Democratic leadership plans to hand Middle East policy to a Congressman who described himself last year as "to the right" of JD Vance on the Iran war and more in line with Lindsey Graham on the matter:

Branko Marcetic

137,521 Aufrufe • vor 2 Tagen

Crypto Policy is being written in real time Kevin Wysocki leads policy at Anchorage Digital ⚓️ and advocates in the rooms where these rules are getting shaped and how their frameworks will impact across industries and countries alike Keep an eye on policy as it gets shaped and the people helping the industry move forward like Kevin Wysocki Brought to you by Wrapped and Real Motion

Crypto Policy is being written in real time Kevin Wysocki leads policy at Anchorage Digital ⚓️ and advocates in the rooms where these rules are getting shaped and how their frameworks will impact across industries and countries alike Keep an eye on policy as it gets shaped and the people helping the industry move forward like Kevin Wysocki Brought to you by Wrapped and Real Motion

Real Motion

12,992 Aufrufe • vor 10 Tagen

🤖Adding new RL algorithms to LeRobot just got much easier. Demo: HIL-SERL training with a SAC-based RL algorithm on an SO-100 for a hole-in-hand peg-in-hole task. Sparse reward, only 30 offline demos mixed with live robot experience, and ~1 hour of online training with human interventions only when the policy fails. The bottom graph tracks intervention rate: high at the start, steadily dropping as the policy improves. The refactor separates algorithm logic from training infrastructure: • RLAlgorithm owns learning logic • RLTrainer handles orchestration • DataMixer combines rollouts, demos, interventions, and future data sources Adding an RL algorithm now looks much closer to adding a policy: one algorithm file, one config, one registry entry. SAC is first. RLT, RECAP, ConRFT, QC-FQL, DSRL, and VLA RL fine-tuning next! Thomas Wolf clem 🤗

🤖Adding new RL algorithms to LeRobot just got much easier. Demo: HIL-SERL training with a SAC-based RL algorithm on an SO-100 for a hole-in-hand peg-in-hole task. Sparse reward, only 30 offline demos mixed with live robot experience, and ~1 hour of online training with human interventions only when the policy fails. The bottom graph tracks intervention rate: high at the start, steadily dropping as the policy improves. The refactor separates algorithm logic from training infrastructure: • RLAlgorithm owns learning logic • RLTrainer handles orchestration • DataMixer combines rollouts, demos, interventions, and future data sources Adding an RL algorithm now looks much closer to adding a policy: one algorithm file, one config, one registry entry. SAC is first. RLT, RECAP, ConRFT, QC-FQL, DSRL, and VLA RL fine-tuning next! Thomas Wolf clem 🤗

LeRobot

30,600 Aufrufe • vor 3 Monaten

“The problem is policy makers are accepting transgenderism as a real thing… it is an ideology, it is not reality & policy has to be based on reality… People who call themselves trans simply have to follow the same rules as everyone else & play according to their sex”

“The problem is policy makers are accepting transgenderism as a real thing… it is an ideology, it is not reality & policy has to be based on reality… People who call themselves trans simply have to follow the same rules as everyone else & play according to their sex”

Sall Grover

71,487 Aufrufe • vor 19 Tagen

Can a single neural network policy generalize over poses, objects, obstacles, backgrounds, scene arrangements, in-hand objects, and start/goal states? Introducing Neural MP: A generalist policy for solving motion planning tasks in the real world 🤖 1/N

Can a single neural network policy generalize over poses, objects, obstacles, backgrounds, scene arrangements, in-hand objects, and start/goal states? Introducing Neural MP: A generalist policy for solving motion planning tasks in the real world 🤖 1/N

Murtaza Dalal

114,720 Aufrufe • vor 1 Jahr

We can learn a model that provides shaped "process rewards" for robotic RL, that evolves automatically as the policy gets better. This improves performance on benchmarks, and works in the real world! Some fun new work with Raymond Tsao & Andrew Wagenmaker

We can learn a model that provides shaped "process rewards" for robotic RL, that evolves automatically as the policy gets better. This improves performance on benchmarks, and works in the real world! Some fun new work with Raymond Tsao & Andrew Wagenmaker

Sergey Levine

37,474 Aufrufe • vor 2 Monaten

Gen2Act: Casting language-conditioned manipulation as *human video generation* followed by *closed-loop policy execution conditioned on the generated video* enables solving diverse real-world tasks unseen in the robot dataset! 1/n

Gen2Act: Casting language-conditioned manipulation as human video generation followed by closed-loop policy execution conditioned on the generated video enables solving diverse real-world tasks unseen in the robot dataset! 1/n

Homanga Bharadhwaj

71,235 Aufrufe • vor 1 Jahr

I’ve found the video of the viral robot going nuts SIM training. The way it moved in the SIM was very similar to how the policy ran in real life. So yea, they probably did this intentionally, watch how it moves.

I’ve found the video of the viral robot going nuts SIM training. The way it moved in the SIM was very similar to how the policy ran in real life. So yea, they probably did this intentionally, watch how it moves.

CIX 🦾

69,303 Aufrufe • vor 1 Jahr

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.

Jianlan Luo

95,100 Aufrufe • vor 8 Monaten

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.

AK

26,855 Aufrufe • vor 1 Jahr

For large-scale robotic deployment🤖 in the real-world 🌏, robots must adapt to changes in environment and objects. Ever questioned the generalizability of your robot's manipulation policy? Put it to the test with The Colosseum 🏛️. Check out our project:

For large-scale robotic deployment🤖 in the real-world 🌏, robots must adapt to changes in environment and objects. Ever questioned the generalizability of your robot's manipulation policy? Put it to the test with The Colosseum 🏛️. Check out our project:

Jiafei Duan

36,617 Aufrufe • vor 2 Jahren

More Americans believe we’ll colonize the moon before we fix K-12 education. This is a policy problem. We have been building a solution that’s already trusted by many of the Fortune 500 as well as 1/3 of federal and state elected officials in the United States. Organizations are more impacted by policy than by financial markets. Yet financial markets have been real-time for decades, and policy markets are still nearly impossible to follow. State Affairs has raised over $70M from Keith Rabois, Khosla Ventures, Founders Fund and others to fix that. We are creating the world’s first real-time knowledge graph for policy and regulatory markets. This platform is foundationally built on non-partisan journalism and the collection of on-the-ground data that isn’t digitally accessible. In the future, we believe every executive will watch policy markets the way they watch financial markets. Instead of reacting to regulation, they’ll navigate it proactively. Policy should iterate at the speed of our most innovative industries.

More Americans believe we’ll colonize the moon before we fix K-12 education. This is a policy problem. We have been building a solution that’s already trusted by many of the Fortune 500 as well as 1/3 of federal and state elected officials in the United States. Organizations are more impacted by policy than by financial markets. Yet financial markets have been real-time for decades, and policy markets are still nearly impossible to follow. State Affairs has raised over $70M from Keith Rabois, Khosla Ventures, Founders Fund and others to fix that. We are creating the world’s first real-time knowledge graph for policy and regulatory markets. This platform is foundationally built on non-partisan journalism and the collection of on-the-ground data that isn’t digitally accessible. In the future, we believe every executive will watch policy markets the way they watch financial markets. Instead of reacting to regulation, they’ll navigate it proactively. Policy should iterate at the speed of our most innovative industries.

Brady Evan Burns

318,577 Aufrufe • vor 9 Tagen