[ICRA2023] Implementation of Visual Language Maps for Robot Navigation

collecting some new ideas for slam (Semantic, 3DGS, BEV, Nav, LLM, Multi-session) and will update this repo weekly, for both engineering and academic usings.

🚗🗣️📡🗾🏁 A framework for navigation tasks that can build the 3D scene graph in real-time and utilize large language model (LLM) to guide the robot.

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

Legged Robot environments for reinforcement learning in Genesis and other simulators

ROS 2 bridge for LeRobot mobile base, arm and sensors.

This repository contains a full wrapper class for running ORB-SLAM3 on a docker container with ROS2 Humble with Ubuntu 22.04.

A library of reinforcement learning components and agents

A networking protocol for agent-environment communication

Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)

Implementation of Dreamer v3 in pytorch.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

A Python-based toolbox of various methods in decision making, uncertainty quantification and statistical emulation: multi-fidelity, experimental design, Bayesian optimisation, Bayesian quadrature, …

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.

Code for "Unsupervised State Representation Learning in Atari"

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

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

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Official NetHack Git Repository

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

Mastering Diverse Domains through World Models

A lightweight, powerful framework for multi-agent workflows

Embodied Reasoning Question Answer (ERQA) Benchmark

[ICCV 2025, Highlight] BUFFER-X: Zero-Shot Point Cloud Registration