OpenDriveLab/UniVLA

Model for robot actions from videos

View on index · View in 3D Map

Related repos

• End-to-end autonomous driving with vision-language-action models
• Dataset and model for robot manipulation
• Platform for robot learning across simulators and embodiments
• open-source models for training and fine-tuning generalist robot control with vision, language, and action
• RoboBrain 2.0: open-source model for robotic reasoning, planning, spatial and temporal perception, and scene understanding
• Framework for autonomous agents with human-like intuition
• Open-source agent system for planning and producing videos
• Automates desktop and web GUIs with multimodal models
• Humanoid robot with open-source hardware and software