Robotics

Hello World for DARPA SubT Challenge

INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.

开源六轴协作机械臂系统，包含机械结构、电路和软件

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

Simulation Description Format (SDFormat) parser and description files.

Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.

[ICRA'23] A Prediction-boosted Planner for Fast and High-quality Autonomous Aerial Reconstruction

RRT*, RRT-connect, lazy RRT and RRT extend have been implemented for 2d and 3d c-spaces with visualization

[ICLR 2026] The official implementation associated with the paper "3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras"

RRT, RRT*, RRT*FN algorithms for MATLAB

Groki Bot desktop robot (M5Stack CoreS3): firmware, a voice and MCP gateway for your computer, and a hand-off to Grok Bot agents

Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras.

An embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop

ROS 2 Jazzy software for the OpenAMRobot mobile base: simulation, Nav2, SLAM, docking, control, drivers, and bringup.

🔥 Data Pyramid for Embodied Manipulation: A Survey

FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.

[ECCV 26] Official implementation of "SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds "

Open-source AI paper index and fine-grained topic atlas across major conferences and journals.

A curated list of software, simulators, policies, agent tools and coverage for the Pollen Robotics / Hugging Face Microduck robot

A differentiable physics engine and multibody dynamics library for control and robot learning.

Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design

Motion Planning Library to accompany turtlebot3_from_scratch repository. Deployed PRM, Grid Map, A*, Theta*, LPA*, D* Lite*, Potential Field, and MPPI.

2,000 curated embodied AI and robotics resources with bilingual metadata and transparent ranking

[arXiv 26] Language-guided whole-body control for general humanoid robots

Snap Spectacles AR integration with Dimensional OS - contoller for Unitree GO2 and G1 robots.

MultiModalWBC is a fully open-source, IsaacLab-based framework for multi-modal whole-body control, designed for motion imitation, motion tracking, and task-conditioned control in legged robots. The framework unifies robot proprioceptive states and multi-modal human motion conditions into a consistent interface

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

An open-source robotics workshop for agents: simulate complete robots on high-fidelity physics, build digital twins, make the parts on CNC, laser and 3D-printer twins, connect simulation to real robots, and let AI agents program, test and debug it all, just by talking to it.

SDK and stack for physical AI layer

[Tutorial] The Embodied Intelligence Introductory Practice of OpenMOSS Lab, SII&Fudan

基于 Livox MID-360 3D LiDAR 的 ROS 2 自主导航工作空间，集成 LIO 里程计、重定位、Nav2 导航，支持仿真与实机部署。

Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

An open-source SO-ARM102 robot arm, successor to SO-ARM100 and SO-ARM101. LeRobot-compatible leader-follower kit for teleoperation and imitation learning, with improved rigidity, parallel gripper, STEP/STL files and BOM.

[CVPR 2026 (Oral)] MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping

A transparent LiDAR-inertial odometry for Livox. written to be read :D For more in depth course you can check the website below

Robotics Data Toolkit | Convert between robotics dataset formats (RLDS, LeRobot v2/v3, Zarr, HDF5, Rosbag). Inspect, visualize, and analyze datasets. Works with HuggingFace Hub. Built for OpenVLA, Octo, LeRobot, and Diffusion Policy workflows.

One policy. Any motion. Train universal whole-body tracking in mjlab—swap clips, not checkpoints.

Research reading list on memory for robotics

HOI-Retarget: Contact-Centric Retargeting for Human-Object Interaction

Autonomous UAV navigation in GNSS-denied indoor spaces with no prior map: stereo VIO (MSCKF) and lidar-inertial odometry with map-based relocalization (SLAM), 3D occupancy mapping, D* Lite path planning and GPU MPPI obstacle avoidance. PX4 + ROS 2 + Gazebo SITL, DARPA SubT Urban.

SfM, MVS, visual-inertial SLAM, 3D Gaussian Splatting and map-based localization in Rust

GenZ-LIO: SOTA robust LiDAR-inertial odometry (IEEE T-FR 2026)

闪猫造物Flashduck — an open-source ESP32-S3 desktop duck robot with six servos, a single animated eye, wide-stance walking and two interaction systems (voice assistant / DuckClaw local agent).

A source-backed Jev / System One knowledge map: projects, papers, evaluations, robotics, and social discovery.

preview of PhysicalRSI infra an engine

UAV simulation platform for development, testing, and research.

This repository includes codes for comprehensive tutorials in Control / Robotics Engineering. The link of YouTube video tutorials are mentioned in description.

Code for Watch Your Step: Anticipated Perception for Humanoid Locomotion, training a humanoid with a foothold prediction model.

Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).

[CVPR 2026] Official code of "EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding"