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

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Real-time behaviour synthesis with MuJoCo, using Predictive Control

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Trajectory optimization for grasping

This repository provides ready-to-use ROS2 (Humble) packages to execute simple programs and sequences and control different Industrial and Collaborative Robots using ROS 2.

The simplest, fastest repository for training/finetuning small-sized VLMs.

A repository containing general tutorials I'd like to share with the world.

A lightweight Social Force Model library

A simulator of human navigation behaviors for Robotics based on ROS2

Wrappers, tools and additional API's for using ROS with MuJoCo

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

[ICCV 2023] Official code repository for ARNOLD benchmark

Sensor Fusion ROS2 Package enabling dynamic simplified tuning of an Extended Kalman Filter

A software framework integrating various imitation learning methods and benchmark environments for robotic manipulation

Habitat ROS is a ROS 1 package for robot simulation in habitat-sim providing customizable robotic sensors (2D Laser, 3D Lidar, RGBD camera, semantic, odometer) and TF broadcasting

AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback

Robotics Toolbox for Python

API to run VirtualHome, a Multi-Agent Household Simulator

RosNav-RL: A flexible, modular framework for building, training, and deploying reinforcement learning navigation agents in ROS. Supports multiple RL backends with ready-to-use components for rapid …

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Rex is a JAX-powered framework for sim-to-real robotics.

Overview about state-of-art imitation learning techniques for robotic manipulation, enabling generalization across diverse tasks and environments.

A web app that lets you track issues in your favorite open-source projects based on your selected labels, and receive notifications through Discord.

Embodied Reasoning Question Answer (ERQA) Benchmark