Unitree Go2, Unitree G1 support for Nvidia Isaac Lab (Isaac Gym / Isaac Sim)

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

OmniGibson: a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse engine. Join our Discord for support: https://discord.gg/bccR5vGFEx

ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

Set-of-Mark Prompting for GPT-4V and LMMs

Code for "Learning Affordance Landscapes for Interaction Exploration in 3D Environments" (NeurIPS 20)

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

《古月 · ROS入门21讲》课件&源码

Inference code for Llama models

DROID Policy Learning and Evaluation

RLAfford: End-to-End Affordance Learning for Robotic Manipulation, ICRA 2023

Toolkit for creating, sharing and using natural language prompts.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

OpenVLA: An open-source vision-language-action model for robotic manipulation.

robomimic: A Modular Framework for Robot Learning from Demonstration

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Isaac Gym Reinforcement Learning Environments

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

Codebase for paper: RoCo: Dialectic Multi-Robot Collaboration with Large Language Models

Grounded Language-Image Pre-training

Code for LGX (Language Guided Exploration). We use LLMs to perform embodied robot navigation in a zero-shot manner.

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

ProgPrompt for Virtualhome