A toolkit for robot learning research.

VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation (CoRL 2024)

PIPs++

Tracking Any Point (TAP)

CoTracker is a model for tracking any point (pixel) on a video.

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Flat'n'Fold: A Diverse Multi-Modal Dataset for Garment Perception and Manipulation

Dataset and Code for ICRA 2024 paper "Grasp-Anything: Large-scale Grasp Dataset from Foundation Models."

[ICRA 2023] GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF

ROS-Industrial movit meta-package (https://wiki.ros.org/industrial_moveit)

Playground for a hand-eye calibration with easy_handeye2, no hardware required.

ROS2 node for AprilTag detection

NVIDIA-accelerated packages for arm motion planning and control

使用panda机械臂接收grasp pose，执行抓取和一些其他操作

使用UR5机械臂&AG95夹爪执行给定位姿的抓取

Teaching a Franka Emika Panda robot to grasp objects using deep reinforcement learning

Using Computer Vision and Machine Learning to Move the Franka Panda Robot Arm with Teleoperation

URDFs, meshes, and config packages for MoveIt testing

Repo for Bring Your Own Vision-Language-Action (VLA) model, arxiv 2024

NVIDIA-accelerated, deep learned semantic image segmentation

NVIDIA-accelerated Apriltag detection and pose estimation.

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

C++ library for Franka research robots

Azure OpenAI code resources for using gpt-4o-realtime capabilities.

The open source hardware data for Orbbec series cameras includes 2D and 3D model files, as well as interface-related information.