正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

GR-RL Going Dexterous and Precise for Long-Horizon Robotic Manipulation

AK

501,352 subscribers

17,630 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Demonstrating tethered debris capture in space using visual servoing, motion prediction, and a parallel end-effector for precise manipulation. 🚀 #SpaceTech #Robotics #ISRO

Demonstrating tethered debris capture in space using visual servoing, motion prediction, and a parallel end-effector for precise manipulation. 🚀 #SpaceTech #Robotics #ISRO

ISRO

152,286 次观看 • 1 年前

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 次观看 • 5 个月前

A robotic hand doing what it does best. 🤖⚙️ Fast. Precise. Relentless.

A robotic hand doing what it does best. 🤖⚙️ Fast. Precise. Relentless.

Mao Ning 毛宁

41,001 次观看 • 2 个月前

RL X-mas came early. 🎄 For too long, building powerful AI agents with Reinforcement Learning has been blocked by GPU scarcity and complex infrastructure. That ends today. Introducing Serverless RL from wandb, powered by CoreWeave! We're making RL accessible to all.

RL X-mas came early. 🎄 For too long, building powerful AI agents with Reinforcement Learning has been blocked by GPU scarcity and complex infrastructure. That ends today. Introducing Serverless RL from wandb, powered by CoreWeave! We're making RL accessible to all.

Weights & Biases

112,643 次观看 • 8 个月前

How many dexterous robotic hands are capable of drawing a circle? Not by moving the arm around but by wiggling the fingers. Full autonomy, too.

How many dexterous robotic hands are capable of drawing a circle? Not by moving the arm around but by wiggling the fingers. Full autonomy, too.

Tom Zhang

99,889 次观看 • 10 个月前

1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code:

1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code:

Kevin Wang

154,580 次观看 • 1 年前

Vision alone isn’t enough to solve dexterous manipulation. The sense of touch is needed. UMI-FT uses a custom PCB to provide 6-axis force-torque sensing at each finger for under $10.

Vision alone isn’t enough to solve dexterous manipulation. The sense of touch is needed. UMI-FT uses a custom PCB to provide 6-axis force-torque sensing at each finger for under $10.

Simon Kalouche

20,634 次观看 • 4 个月前

Elastigirl, the elastic and highly dexterous superhero is ready for 3D Printing!!

Elastigirl, the elastic and highly dexterous superhero is ready for 3D Printing!!

PolyBits

11,079 次观看 • 3 年前

RGB Human Videos -> Dexterous Manipulation Policies No teleoperation. No wearables. No robot interaction. The 🔑: Reliable 3D hand-object trajectory reconstruction and efficient action augmentation Fun collaboration led by Hongyi Chen

RGB Human Videos -> Dexterous Manipulation Policies No teleoperation. No wearables. No robot interaction. The 🔑: Reliable 3D hand-object trajectory reconstruction and efficient action augmentation Fun collaboration led by Hongyi Chen

Homanga Bharadhwaj

10,775 次观看 • 4 个月前

BEAMDOJO is a new RL framework developed by Chinese researchers that teaches humanoid robots to walk on tricky terrains like stepping blocks. It uses a two-stage training process: a specialized reward system, and LiDAR mapping for precise foot placement.

BEAMDOJO is a new RL framework developed by Chinese researchers that teaches humanoid robots to walk on tricky terrains like stepping blocks. It uses a two-stage training process: a specialized reward system, and LiDAR mapping for precise foot placement.

The Humanoid Hub

57,347 次观看 • 1 年前

What is the best architecture for robotic manipulation? In our new CoRL 2023 paper Act3D, we efficiently produce high-resolution 3D action maps from pre-trained 2D backbones. (1/n)

What is the best architecture for robotic manipulation? In our new CoRL 2023 paper Act3D, we efficiently produce high-resolution 3D action maps from pre-trained 2D backbones. (1/n)

Theophile Gervet

44,863 次观看 • 2 年前

Leffa from Meta is a 🆕 unified framework for controllable person image generation that enables precise manipulation of both appearance (i.e., Virtual try-on) and pose (i.e., Pose transfer). Learn more about 📚 Code,🔥 Demo, and 🤗 Model ⬇️

Leffa from Meta is a 🆕 unified framework for controllable person image generation that enables precise manipulation of both appearance (i.e., Virtual try-on) and pose (i.e., Pose transfer). Learn more about 📚 Code,🔥 Demo, and 🤗 Model ⬇️

Gradio

52,913 次观看 • 1 年前

Introducing CQN: Coarse-to-fine Q-Network, a value-based RL algorithm for continuous control🦾Initialized with 20~50 demonstrations, it learns to solve real-world robotic tasks within 10 mins of training, without any pre-training and shaped rewards! (1/4)

Introducing CQN: Coarse-to-fine Q-Network, a value-based RL algorithm for continuous control🦾Initialized with 20~50 demonstrations, it learns to solve real-world robotic tasks within 10 mins of training, without any pre-training and shaped rewards! (1/4)

Younggyo Seo

16,413 次观看 • 1 年前

ManiFeel is a benchmark for contact-rich manipulation tasks. Force- and tactile-based tasks with occlusions and partially-observable state are going to be crucial for true general purpose robotics. Website:

ManiFeel is a benchmark for contact-rich manipulation tasks. Force- and tactile-based tasks with occlusions and partially-observable state are going to be crucial for true general purpose robotics. Website:

Chris Paxton

12,059 次观看 • 3 个月前

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA announces the first open humanoid robot reference design built for robotics research. The NVIDIA Isaac GR00T Reference Humanoid Robot combines the Unitree H2 humanoid robot, Sharpa Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment. Read the #NVIDIAGTC Taipei announcement:

NVIDIA Robotics

160,844 次观看 • 17 天前

Why am I working on RL for LLMs, when I can go work on RL for Olaf... #humanoidssummit

Why am I working on RL for LLMs, when I can go work on RL for Olaf... #humanoidssummit

Shane Gu

12,440 次观看 • 6 个月前

RL is painfully slow 😭 — bottlenecked by super-long CoT rollout. 🔭 Sparse attention should help, but naive sparse rollout hits a brutal efficiency–stability tradeoff: A tedious trial-and-error sparsity sweep for each dense policy is required before an actual RL run. 🐤Sparrow chirps no more pain! Introduce Sparrow: Sparse Rollout for stable and efficient long-context RL. Sparrow finds that: 💡As long as we keep the tail distribution mismatch throughout the sparse rollout above a critical threshold, the RL training will be stable. 💡Even cooler! Through comprehensive control studies of Qwen3-1.7B, 4B, 8B thinking models RL with 40K rollout max length, the critical threshold stays constant across model sizes. 💡Sparrow then finds the optimal dynamic sparse schedule to reach the threshold with minimal cost. 💡Sparrow's findings are empirically validated to generalize in Qwen3-14B, and hold on both Math and Coding RL. 🐤Sparrow empirically helps achieve 2.2× / 2.4× / 2.0× rollout speedup on Qwen3 1.7B / 4B / 8B thinking models, while keeping training stability over extended RL steps. We release the 🐤bird in the following formats. [1/n] Paper: Code: Blog:

RL is painfully slow 😭 — bottlenecked by super-long CoT rollout. 🔭 Sparse attention should help, but naive sparse rollout hits a brutal efficiency–stability tradeoff: A tedious trial-and-error sparsity sweep for each dense policy is required before an actual RL run. 🐤Sparrow chirps no more pain! Introduce Sparrow: Sparse Rollout for stable and efficient long-context RL. Sparrow finds that: 💡As long as we keep the tail distribution mismatch throughout the sparse rollout above a critical threshold, the RL training will be stable. 💡Even cooler! Through comprehensive control studies of Qwen3-1.7B, 4B, 8B thinking models RL with 40K rollout max length, the critical threshold stays constant across model sizes. 💡Sparrow then finds the optimal dynamic sparse schedule to reach the threshold with minimal cost. 💡Sparrow's findings are empirically validated to generalize in Qwen3-14B, and hold on both Math and Coding RL. 🐤Sparrow empirically helps achieve 2.2× / 2.4× / 2.0× rollout speedup on Qwen3 1.7B / 4B / 8B thinking models, while keeping training stability over extended RL steps. We release the 🐤bird in the following formats. [1/n] Paper: Code: Blog:

Infini-AI-Lab

75,961 次观看 • 7 天前

Thanks AK! Finally, robot can do continuous, agile, autonomous, adaptive jumping over stair and stepping stone Key idea: combine the pros of model-free RL and model-based control. RL (for CoM refs) + QP (for GRF) + WBC (for torque) Open-sourced:

Thanks AK! Finally, robot can do continuous, agile, autonomous, adaptive jumping over stair and stepping stone Key idea: combine the pros of model-free RL and model-based control. RL (for CoM refs) + QP (for GRF) + WBC (for torque) Open-sourced:

Guanya Shi

32,142 次观看 • 1 年前

There are many things going on in the world, many evil things, the most important is the manipulation of our the air we breathe and the manipulation of the weather. Stay focused.

There are many things going on in the world, many evil things, the most important is the manipulation of our the air we breathe and the manipulation of the weather. Stay focused.

The GeoFight

58,442 次观看 • 4 个月前

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

Google DeepMind

297,100 次观看 • 1 年前