Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
- self-driving-car
- tensorflow
- reinforcement-learning
- unreal-engine
142,273 visible repositories in the index
169–192 of 229 · Most stars
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training
Learning Heterogeneous Tactile Representation for General Dexterous Manipulation
Fast Robot Kinematics and Dynamics in JAX
Training Reasoning Models in Simulation to Natively Use Real Robots
[ICRA] Crowd-aware Robot Navigation
OverlapNet - Loop Closing for 3D LiDAR-based SLAM (chen2020rss)
This repository contains multiple approaches for generating global racetrajectories.
An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks
Modular autonomous driving platform running on the CARLA simulator and real-world vehicles.
A robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks.
A Unified Robot-Use Agent Harness Across Environments
Open-source embodied agent framework: execution, feedback, and continual improvement
Independent reproduction of SuperMimic (arXiv:2610.28480) on mjlab/MuJoCo Warp, written from the paper before the official release. For the authors' code see HybridRobotics/supermimic. Kept as a record: experiment log, full BONES-SEED results, checkpoint.
HALO: Perceptive Humanoid Motion from Simulation
Unmanned Surface Vehicle simulation on Gazebo with water current and winds
Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).
HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World
A high-performance, general-purpose toolkit for versatile robotic tasks.
Behavior Trees Library for ROS (Robot Operating System). In C++ and python
[LIBERO-MAX] A paired benchmark for robot-policy robustness to controlled changes introduced during execution.
World In-Context Learning for Agentic Robot Manipulation
Python parser for URDFs
Whole-body motion tracking for the Unitree G1 in about 3 minutes on one GPU.