Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

我的超迷你机械臂机器人项目。

This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym

SAPIEN Manipulation Skill Framework, a open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

Bimanual Dexterous Teleoperation with Real-Time Retargeting using VisionPro

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

A model and controller of UR5 (Universal Robots UR5) in Unity3D, supporting Augmented Reality (AR) and Virtual Reality (VR) applications.

The Pytorch implementation of Grounding 3D Object Affordance from 2D Interactios in Images.

[Submitted to ICRA2025]COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models

Google Research

Normalizing flows in PyTorch

Isaac Gym Reinforcement Learning Environments

"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation" code repository

A generative world for general-purpose robotics & embodied AI learning.

API for controlling LEAP Hand

Official code for "UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy" (CVPR 2023)

Robot kinematics implemented in pytorch

Isaac Gym repository for LEAP Hand

Digit 360 is a modular platform that unlocks new capabilities, and enables future research on the nature of touch.

[IROS 2023] Open-Vocabulary Affordance Detection in 3d Point Clouds

[ACM MM-2024] RefMask3D: Language-Guided Transformer for 3D Referring Segmentation

(NeurIPS 2024) Official repository of paper "Grasp as You Say: Language-guided Dexterous Grasp Generation"

[ICRA 2024] Language-Conditioned Affordance-Pose Detection in 3D Point Clouds

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

[ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

[CVPR 2022] PointCLIP: Point Cloud Understanding by CLIP

[CoRL2024] ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter. https://arxiv.org/abs/2407.11298