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。

New study introduces a system to generate realistic, physically plausible human-object interactions from natural language instructions. It uses LLMs for planning, a motion generator for synchronized body and finger movements, and RL for physical accuracy.

The Humanoid Hub

102,423 subscribers

27,606 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

6 条评论

name 的头像

name1 年前

Very impressive, but I don't like his attitude...

Uri Gil 的头像

Uri Gil1 年前

Is it transferable to a real robot?

The Humanoid Hub 的头像

The Humanoid Hub1 年前

Simulating hardware-specific constraints for motion generation is challenging, so is fine-tuning to bridge the reality gap.

thechrismiddleton.bsky.social 的头像

thechrismiddleton.bsky.social1 年前

Large Behaviour Model. Not Large Language Model.

Kuxipa 的头像

Kuxipa1 年前

what kind of real-world data (non synthetic) collected by hardware (glass, gloves, ring for finger motion) or by just videos (first person view or) would be very useful for training a foundational embodied AI model? (whatever this means) or put it differently if real-world data collection would not be a problem to think, what data of that kind would be super useful for what embodied AI development that would be a game changer and substantial uplift? can you give a top N list?

Risichad 🦾 的头像

Risichad 🦾1 年前

Amazing ! We are so close to droids Era

相关视频

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:

Jiaman Li

104,609 次观看 • 1 年前

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 次观看 • 1 年前

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference.

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference.

Angela Dai

20,508 次观看 • 2 年前

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.

The Humanoid Hub

27,879 次观看 • 1 年前

With Helix 02, Figure has introduced a new foundational layer for whole-body control that replaces 109k lines of hand-engineered C++ with a single neural prior for stable, natural motion. - Learned from 1,000+ hours of human motion data and sim-to-real RL across 200,000+ parallel environments. - A 10M-parameter neural network that takes full-body joint state and base motion as input and outputs joint-level actuator commands at 1 kHz (1,000 times a second).

With Helix 02, Figure has introduced a new foundational layer for whole-body control that replaces 109k lines of hand-engineered C++ with a single neural prior for stable, natural motion. - Learned from 1,000+ hours of human motion data and sim-to-real RL across 200,000+ parallel environments. - A 10M-parameter neural network that takes full-body joint state and base motion as input and outputs joint-level actuator commands at 1 kHz (1,000 times a second).

The Humanoid Hub

28,004 次观看 • 4 个月前

Big news from the TeleAI embodied intelligence team! They unveiled TextOp, a general cerebellar framework for real-time, text-driven humanoid control. TextOp lets humans control the robot via natural language, dynamically modifying instructions during runtime to instantly generate smooth, whole-body actions. This enables precise and highly versatile control. The framework uses a two-layer architecture: an action diffusion model (High-Level) and a general motion tracking policy (Low-Level). It’s a new paradigm that eliminates the need for pre-recorded scripts or manual programming.

Big news from the TeleAI embodied intelligence team! They unveiled TextOp, a general cerebellar framework for real-time, text-driven humanoid control. TextOp lets humans control the robot via natural language, dynamically modifying instructions during runtime to instantly generate smooth, whole-body actions. This enables precise and highly versatile control. The framework uses a two-layer architecture: an action diffusion model (High-Level) and a general motion tracking policy (Low-Level). It’s a new paradigm that eliminates the need for pre-recorded scripts or manual programming.

RoboHub🤖

23,804 次观看 • 7 个月前

⟡ Object interactions! ⟡ A little spoiler from System for the in-game content. #svsss #ScumVillainsSelfSavingSystem

⟡ Object interactions! ⟡ A little spoiler from System for the in-game content. #svsss #ScumVillainsSelfSavingSystem

Regrowth

84,283 次观看 • 1 年前

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

The Humanoid Hub

17,395 次观看 • 9 个月前

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,430 次观看 • 1 年前

HumanX: a scalable framework that converts single monocular human videos into agile, generalizable interaction skills for humanoid robots without task-specific rewards. Core parts: - XGen: retargets human motion + synthesizes diverse physically plausible training data (via physics-driven object trajectories and augmentation). - XMimic: unified imitation pipeline for robust generalization. Shows promising results for both Blind (no external sensors) and MoCap modes.

HumanX: a scalable framework that converts single monocular human videos into agile, generalizable interaction skills for humanoid robots without task-specific rewards. Core parts: - XGen: retargets human motion + synthesizes diverse physically plausible training data (via physics-driven object trajectories and augmentation). - XMimic: unified imitation pipeline for robust generalization. Shows promising results for both Blind (no external sensors) and MoCap modes.

The Humanoid Hub

20,358 次观看 • 4 个月前

China’s momentum is unstoppable. Hollywood-style AI filmmaking is here. Hailuo AI (MiniMax) released a new model: T2V-01-Director. - Allows you to guide the camera using natural language or specific commands. - It’s getting closer for creators to truly generate shots and tell stories according to their own ideas. - 🔄 Combine movements for flawless, cinematic transitions. ✨ What’s New: - Reduced randomness in movements. - Enhanced control accuracy. - Revolutionized camera aesthetics.

China’s momentum is unstoppable. Hollywood-style AI filmmaking is here. Hailuo AI (MiniMax) released a new model: T2V-01-Director. - Allows you to guide the camera using natural language or specific commands. - It’s getting closer for creators to truly generate shots and tell stories according to their own ideas. - 🔄 Combine movements for flawless, cinematic transitions. ✨ What’s New: - Reduced randomness in movements. - Enhanced control accuracy. - Revolutionized camera aesthetics.

Rohan Paul

12,377 次观看 • 1 年前

Create realistic and smooth movements for basic humanoid locomotion with AiKodex's Learned Motion Matching tool for Unity. Get it here:

Create realistic and smooth movements for basic humanoid locomotion with AiKodex's Learned Motion Matching tool for Unity. Get it here:

80 LEVEL

87,640 次观看 • 1 年前

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

179,503 次观看 • 17 天前

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

Siqiao Huang

11,938 次观看 • 13 天前

AI + robotics research is starting to pick up steam. We can now instruct Spot using natural language using Language-guided Skill Coordination (LSC). A user provides a natural language instruction: "Bring me the chocolates box, cereal box, and pill bottle, and put them on the bedroom table" and the robot navigates to the location of the target objects and places them on the room table. Current versions of Spot rely on a fixed-set vocabulary that cannot generalize to diverse instructions. In this demo, the researchers presented a method that uses large language models to receive a free-form natural language instruction for object rearrangement, which it then executes. It combines: -A voice-to-text model that processes the instructions into text -An LLM that converts natural language instruction to call a library of skills -A perception module that provides ground truth locations and visual object detection And what your left with is a glimpse into what our future will hold: robots executing tasks from human voice prompts.

AI + robotics research is starting to pick up steam. We can now instruct Spot using natural language using Language-guided Skill Coordination (LSC). A user provides a natural language instruction: "Bring me the chocolates box, cereal box, and pill bottle, and put them on the bedroom table" and the robot navigates to the location of the target objects and places them on the room table. Current versions of Spot rely on a fixed-set vocabulary that cannot generalize to diverse instructions. In this demo, the researchers presented a method that uses large language models to receive a free-form natural language instruction for object rearrangement, which it then executes. It combines: -A voice-to-text model that processes the instructions into text -An LLM that converts natural language instruction to call a library of skills -A perception module that provides ground truth locations and visual object detection And what your left with is a glimpse into what our future will hold: robots executing tasks from human voice prompts.

AI Breakfast

33,718 次观看 • 3 年前

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

MIT CSAIL

59,152 次观看 • 2 年前

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,319 次观看 • 3 年前

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

20,051 次观看 • 1 年前

Introducing ClickDiffusion! We developed a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface.

Introducing ClickDiffusion! We developed a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface.

Alec Helbling

36,293 次观看 • 2 年前