Research, science & education

Robotics & embodied agents

Robotics and embodied agents control physical hardware or simulate it: quadcopters, humanoids, quadrupeds, and drones. Some, like dimos, translate natural language commands into robot actions, while others such as habitat-lab provide simulated environments for training embodied agents on navigation and manipulation tasks.

809 agents · most starred first

Top 100 of 809

lab★ 7,394

A customisable 3D platform for agent-based AI research

dimos★ 4,753

Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

habitat-lab★ 3,189

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

MindPaw★ 2,790

🐕 MindPaw — 基于 ESP8266 的开源桌面四足机器狗,支持语音、手势、网页遥控、豆包 AI 对话与 PAD 情感交互。可选 AI Infra 网关,适合机器人入门、嵌入式 AI、边缘 Agent 与 HRI 研究。

ego-planner-swarm★ 2,262

An efficient single/multi-agent trajectory planner for multicopters.

gym-pybullet-drones★ 2,212

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

Awesome-Embodied-Robotics-and-Agent★ 1,922

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

PhyAgentOS-core★ 1,882

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

RPent★ 1,789

RPent: Agentic Infrastructure for the Physical World

PhyAgentOS★ 1,756

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

PhyAgentOS★ 1,734

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

PhyAgentOS★ 1,710

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

rosa★ 1,692

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

multi_agent_path_planning★ 1,470

Python implementation of a bunch of multi-robot path-planning algorithms.

ir-sim★ 1,240

A Python-based lightweight robot simulator designed for navigation, control, and learning

RoboGen★ 1,227

A generative and self-guided robotic agent that endlessly propose and master new skills.

SMARTS★ 1,136

Scalable Multi-Agent RL Training School for Autonomous Driving

rex-gym★ 1,108

OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

libMultiRobotPlanning★ 1,049

Library with search algorithms for task and path planning for multi robot/agent systems

CityFlow★ 1,032

A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario

cap-x★ 933

[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

SenseNova-RoboRSI★ 839

A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.

SimWorld★ 819

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds

HiVT★ 754

[CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction

aerial-autonomy-stack★ 666

An open harness to simulate and deploy PX4/ArduPilot/Betaflight perception-based drone swarms with ROS2, YOLO, NVIDIA Jetson

matsim-libs★ 652

Multi-Agent Transport Simulation

virtualhome★ 645

API to run VirtualHome, a Multi-Agent Household Simulator

Collaborative_Perception★ 639

This repository is a paper digest of recent advances in collaborative / cooperative / multi-agent perception for V2I / V2V / V2X autonomous driving scenario.

VectorizedMultiAgentSimulator★ 631

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

mader★ 629

Trajectory Planner in Multi-Agent and Dynamic Environments

robosimstudio★ 627

An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks

gpudrive★ 624

1 million FPS multi-agent driving simulator

rai★ 619

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Gamma-World★ 579

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

lampOS★ 579

The open-source operating system for physical AI.

Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning★ 567

Deep Reinforcement Learning (PPO) in Autonomous Driving (Carla) [from scratch]

RoboHarness★ 536

A robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks.

Deep-QLearning-Agent-for-Traffic-Signal-Control★ 509

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.

embodied-generalist★ 492

[ICML 2024] LEO: An Embodied Generalist Agent in 3D World

VLABench★ 483

A large-scale benchmark for evaluating vision-language-action models, embodied agents, and vision-language models

Show-Harness★ 475

Just a VLM Agent Can Play Robots

covins★ 465

COVINS-(G) -- A (Generic) Framework for Collaborative Visual-Inertial SLAM and Multi-Agent 3D Mapping

SpatialClaw★ 454

[NeurIPS 2026] SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

PRIMAL★ 448

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Distributed RL/IL code for Multi-Agent Path Finding (MAPF)

Multi-Agent-Path-Finding★ 447

Anonymous Multi-Agent Path Finding (MAPF) with Conflict-Based Search and Space-Time A*

robotic-warehouse★ 447

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

gymfc★ 442

A universal flight control tuning framework

gym-electric-motor★ 437

Gym Electric Motor (GEM): An OpenAI Gym Environment for Electric Motors

ChatSim★ 435

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

mighty★ 435

MIGHTY: Hermite spline-based real-time trajectory planner for single- and multi-agent UAVs and ground robots (ROS 2). Accepted to IEEE RA-L.

deeprl_signal_control★ 425

multi-agent deep reinforcement learning for large-scale traffic signal control.

HoloAgent★ 424

A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localization, and autonomous mobility and manipulation, with intelligent interaction with users.

CL-CBS★ 421

An Efficient Multi-Agent Path Finding Solver for Car-Like Robots

robonix★ 419

The Agentic Operating System for Robots

JARVIS-1★ 417

JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models

NextBoard★ 405

面向硬件产品PCB方案设计的AI Agent,Agent会自动帮你进行需求确认,实时分析国内外各类芯片技术方案,进行器件选型,下载datasheet,输出BOM表,计算价格,输出模块原理图,最终整合成可落地技术方案。

EMERGE-Policy★ 397

EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy

multiagent_mujoco★ 375

Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.

macad-gym★ 372

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

ENPIRE★ 369

ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution

GRANT★ 368

[AAAI 2026 Oral] Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

GPT-Policy★ 367

GPT-Policy: In-Context Robot Learning with VLM Agents

autonomous-os★ 358

The open-source operating system for robots — install it and your robot comes alive

MAGiC-SLAM★ 343

[CVPR 2025]MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

LEGENT★ 341

Open Platform for Embodied Agents

mavsdk_drone_show★ 339

Open-source MAVLink fleet operations for PX4: SITL, drone shows, search and rescue, cooperative autonomy, and field validation

streetlearn★ 324

A C++/Python implementation of the StreetLearn environment based on images from Street View, as well as a TensorFlow implementation of goal-driven navigation agents solving the task published in “Learning to Navigate in Cities Without a Map”, NeurIPS 2018

AgentFormer★ 316

[ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

EmbodiedQA★ 315

Train embodied agents that can answer questions in environments

SIMPL★ 315

SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving

marathon-envs★ 313

A set of high-dimensional continuous control environments for use with Unity ML-Agents Toolkit.

bark★ 310

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

SurveyBrainBody★ 309

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

pogema★ 305

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.

embodied-first-exam★ 303

The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.

Agent-Driver★ 302

A Language Agent for Autonomous Driving

embodied-agent-interface★ 302

Embodied Agent Interface (EAI): Benchmarking LLMs for Embodied Decision Making (NeurIPS D&B 2024 Oral)

CoELA★ 301

[ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"

GPT4V-AD-Exploration★ 300

On the Road with GPT-4V(ision): Explorations of Utilizing Visual-Language Model as Autonomous Driving Agent

SMART★ 300

[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

nocturne★ 298

A data-driven, fast driving simulator for multi-agent coordination under partial observability.

rl_rvo_nav★ 298

[RA-Letter 2022] Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards

quackd★ 297

The communication layer between people and robots, and between robots. Talk to any robot in your own words, with an LLM for its brain. Robots that have never met check each other's passports and share the work. Microduck, Huebot, Open Duck Mini, LeRobot arms, XLeRobot carts, AlohaMini, ToddlerBot, MOSS, ROS bases and industrial arms on ROS 2.

VectorNet★ 294

Pytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”

LLMTSCS★ 294

Official code for article "LLMLight: Large Language Models as Traffic Signal Control Agents".

Awesome-Multimodal-Embodied-Agent★ 293

Survey on Multimodal Embodied Agents: Computer-Use → Robot-Use

ROScribe★ 292

Write your robot software in minutes.

multimaster_fkie★ 291

DEPRICATED! Use the multi-agent suite instead!

MARLspectrumSharingV2X★ 280

Spectrum sharing in vehicular networks based on multi-agent reinforcement learning, IEEE Journal on Selected Areas in Communications

Continuous-CBS★ 273

Continuous CBS - a modification of conflict based search algorithm, that allows to perform actions (move, wait) of arbitrary duration. Timeline is not discretized, i.e. is continuous.

Phyzical_org★ 272

Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.

llama_ros★ 268

llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2

PyRUA-Lean★ 268

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens

robot-collab★ 267

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

rl_CARLA★ 263

Use Reinforcement Learning to train an autonomous driving agent in CARLA Simulator

mapf_ros★ 254

This is a multi-agent path planning(also known as Multi-Agent Path Finding, MAPF) algorithm package for ROS/ROS2.

gym-ignition★ 252

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

ros2-engineering-skills★ 250

Agent skill for production-grade ROS 2 development. Progressive-disclosure SKILL.md covering workspace, nodes, executors, QoS, ros2_control, Nav2, MoveIt 2, real-time, and deployment. Works with Claude Code, Codex, Cursor, Gemini CLI.

robotics-skills-suite★ 244

76 audit-ready Claude skills automating the industrial robot, cobot, AMR, ROS2, V&V, AI/ML, and IEC 62443 lifecycle. 38 builder + reviewer pairs anchored to ISO 10218, 13849, 62061, 12100, 9283, 15066, 3691-4, and IEC 62443.

GenAI4AD★ 232

a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack

More in Research, science & education