Kyle

troncamp-mani. TronCamp ACT 4-task hackathon — self-contained contestant package (Tron2 dual-arm / RoboTwin / single-GPU ACT): setup, platform, starter, eval-kit. Tasks adjust_bottle/grab_roller/stack_bowls_two/stack_bowls_three on a cumulative freedom ladder; T4 graded leaderboard.

Qwen-VLA. The official repository of Qwen-VLA

DepthVLM. 🔥 Official code repository for "Unlocking Dense Metric Depth Estimation in VLMs"

NavGSim. C++

habitat-gs. [ECCV 2026] Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

sru-depth-pretraining. Depth Perception Pretraining - SRU Project

worldstring. [Highlight] Official implementation for Actionable World Representation

WorldGrow. WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]

GN0. The official Implementation of GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation

JanusVLN. [ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"

Genie-Envisioner-V1. Python

embodied-ai-start. [PKU EPIC Lab] 面向小白的具身智能入门指南

lingbot-map. A feed-forward 3D foundation model for reconstructing scenes from streaming data

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

SceneSplat. [ICCV 2025 Oral] SceneSplat - Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

dino_wm. Python

jepa. PyTorch code and models for V-JEPA self-supervised learning from video.

Academic-Resume-Template. 学术双语简历模板，涵盖教育背景、论文发表、项目经历、竞赛经历和个人陈述等关键部分，可适用于申请研究生项目、学术职位或相关行业岗位。

vggt-omega. [CVPR 2026 Oral] VGGT Omega

ppt-master. AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

ABot-Explorer. Python

SocialNav. Official implementation for "SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation"

Click-and-Traverse. Official implementation of Click-and-Traverse

gs_playground. Jupyter Notebook

FINO. Official implementation of "Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning" (ICLR 2026).

fql. The official implementation of flow Q-learning (FQL)

A2A_Flow_Matching. Accept by RSS 2026 :tada:

TrajectoryFlowMatching. Code repository for Trajectory Flow Matching

superpowers. An agentic skills framework & software development methodology that works.

awesome-coding-plan. 各厂家 Coding Plan 实际价值对比

DPNet. RA-L '26 [DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments]

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

maniparena-repo. Python

InternNav. InternRobotics' open platform for building generalized navigation foundation models.

DMWM. This is a repository for the paper "DMWM: Dual-Mind World Model with Long-Term Imagination" accepted by NeurIPS 2025

Motus. Official code of Motus: A Unified Latent Action World Model

Psi0. [RSS26'] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

REASAN. Fully modularized learning framework for legged reactive navigation

OpenHomie. Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

awesome-loco-manipulation. CMake

DoorBot. [ICRA'25] DoorBot: Closed-Loop Task Planning and Manipulation for Door Opening in the Wild with Haptic Feedback

Paper2Slides. "Paper2Slides: From Paper to Presentation in One Click"

Gallant. This is the official implementation of the voxel-based humanoid locomotion in "Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains"

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

diamond. DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

WMNavigation. [IROS'25 Oral] WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation

gaussianwm. [ICCV'25] Towards Scalable Gaussian World Models for Robotic Manipulation

SysNav. C++

UniWM. Official implementation of paper "Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation"

ManiGaussian_Bimanual. [IROS 2025] ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model

ManiGaussian. [ECCV 2024] ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

GaussianAD. GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

GaussianWorld. [CVPR 2025] Gaussian World Model for Streaming 3D Occupancy Prediction

GaussNav. PyTorch implementation of paper: GaussNav: Gaussian Splatting for Visual Navigation

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

ABot-Navigation. Python

DiT4DiT. This is the official code repo for DiT4DiT, a Vision-Action-Model (VAM) framework that combines video generation model with flow-matching-based action prediction for generalizable robotic manipulation.

IsaacLab-Arena. Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. The framework enables developers to rapidly prototype and test robotic tasks with various robot embodiments, objects, and environments.

STRNet. [CVPR2026] STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation

FastWAM. Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

cosmos-policy. Cosmos Policy

Dynam3D. Official implementation of "Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation" (NeurIPS'25 Oral)

NaVILA. [RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

Awesome-LLM4AD. A curated list of awesome LLM/VLM/VLA/World Model for Autonomous Driving(LLM4AD) resources (continually updated)

Awesome-VLA4AD. Vision–Language–Action models for Autonomous Driving (VLA4AD) resources, serving as the companion repository to the survey paper “A Survey on Vision–Language–Action Models for Autonomous Driving”.

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

claude-scholar. Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

dimos. 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).

InternVLA-M1. InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

dreamzero. Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

awesome-embodied-vla-va-vln. A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

3D-Mem. [CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"

feature-3dgs. [CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

GOTPR. GOTPR: General Outdoor Text-based Place Recognition Using Scene Graph Retrieval with OpenStreetMap

remembr. Python

wall-x. Building General-Purpose Robots Based on Embodied Foundation Model

kaggle-cli. Official Kaggle CLI

Clipper2. Polygon Clipping, Offsetting & Triangulation in C++, C# and Delphi

notebooklm-skill. Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your uploaded documents and get source-grounded, citation-backed answers from Gemini. Features browser automation, library management, persistent authentication, and answers exclusively from your own knowledge base.

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

ManiDreams. An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics

mamba. Mamba SSM architecture

mjlab. Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Wheel_legged_gym. Python

hunter_bipedal_control. An open source bipedal robot control framework, based on non-linear MPC and WBC, tailered for EC-hunter80-v01 bipedal robot.

UniFP. CoRL2025 UniFP: Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation

MobileSAM. This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

sru-navigation-sim. IsaacLab SRU RL Navigation Extension - SRU Project

DrivoR. [CVPR2026] DrivoR: an end-to-end driving model by driving on registers

go2_rl_gym. This is a repository for reinforcement learning implementation based on Unitree Go2. Official implementation of RSS 2026.

RoboTwin. [ICML 2026] RoboTwin 2.0 Offical Repo

ManiSkill. Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

Depth-Anything-3. Depth Anything 3

habitat-challenge. Code for the habitat challenge

CE-Nav. official implementation of [CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation]

nwm. Official code for the CVPR 2025 paper "Navigation World Models".

dreamerv3-torch. Implementation of Dreamer v3 in pytorch.

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

LS-Imagine. [ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"

sindy-rl. Code for "SINDy-RL for Interpretable and Efficient Model-Based Reinforcement Learning" by Zolman et al.

openpi. Python

dsrl_pi0. Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

Awesome-World-Model. Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

sru-pytorch-spatial-learning. Spatially-Enhanced Recurrent Units (SRU) - PyTorch Implementation

Aerobatic-Planner. An autonomous aerobatic system that is capable of complex flight maneuvers.

Odin-Nav-Stack. An open-source navigation stack based on Odin1.

patchwork-plusplus. Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

WholebodyVLA. [ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control

Xbotics-Embodied-Guide. Xbotics 社区具身智能学习指南：我们把“具身综述→学习路线→仿真学习→开源实物→人物访谈→公司图谱”串起来，帮助新手和实战者快速定位路径、落地项目与参与开源。

disco_rl. Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

Dftpav. A lightweight differential flatness-based trajectory planner for car-like robots

Pure-tracking-slam-automatic-navigation-system. simulate，ros2，gazebo，navigation，slam

dicp. Official implementation for ICLR 2025 paper "Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning"

apollo. An open autonomous driving platform

seb_naver. SEB-Naver: A SE(2)-based Local Navigation Framework for Car-like Robots on Uneven Terrain

mavrl. MAVRL: Learn to Fly in Cluttered Environmants with Varying Speed

robotic_world_model. Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots

YOPO. You Only Plan Once: A Learning Based Quadrotor Planner

DLPA. Python

self-supervised-rl. Python

PCT_planner. 3D navigation based on point cloud tomography

OCL-RPF. [RAL2024] Person Re-Identification for Robot Person Following with Online Continual Learning.

3EED. [NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D

FastTD3. Python

ReinFlow. [NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

GPI. Code for paper Geometry-aware Policy Imitation

mp-df-ds. From Movement Primitives to Distance Fields to Dynamical Systems

DiffPhysDrone. Published on Nature Machine Intelligence! The first real robot(quadrotor) based on differentiable physics training.

Awesome-Robotics-Diffusion. A curated list of recent robot learning papers incorporating diffusion models for robotics tasks.

flow_mp. [IROS '25] FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matching

DistillDrive. [ICCV 2025] End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model

Diffusion-Planner. [ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"

DifferentiableCollisions.jl. Differentiable collision detection for polytopes, capsules, cylinders, cones, spheres, and polygons.

Bench2Drive. [NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

matrix. MATRiX is an advanced simulation platform that integrates MuJoCo, Unreal Engine 5, and CARLA to provide high-fidelity, interactive environments for robotics research.

OCLTrav. Dockerfile

STAR-Searcher. Open-source code for the RA-L paper "Star-Searcher: An Efficient Aerial System for Target Search in Unknown Environments".

HOPE. Reinforcement Learning-based Hybrid Policy Path Planning in Diverse Parking Scenarios

neuralmotionplanner. PyTorch Code for Neural MP: A Generalist Neural Motion Planner

derl. Code for "Embodied Intelligence via Learning and Evolution", Gupta et al, Nature Communications

dial-mpc. Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged robot full-order torque-level control with both precision and agility in a training-free manner.

LeRobot-Anything-U-Arm. U-Arm: Lerobot-Everything-Cross-Embodiment-Teleoperation

isaac-wild-go2. This project contains a framework that allows the quadruped robot to explore and adapt to the open wild environment in a safe manner.

flow-maps. Official codebase for the paper "How to build a consistency model: Learning flow maps via self-distillation" (NeurIPS 2025).

CusLab. Direct IsaacLab Workflow using CusRL

BodyGen. [ICLR 2025 Spotlight] Official PyTorch Implementation of "BodyGen: Advancing Towards Efficient Embodiment Co-Design"

MoLE. [ICML 2025 Oral] Mixture of Lookup Experts

Conference-Accepted-Paper-List. Some Conferences' accepted paper lists (including AI, ML, Robotic)

whole_body_tracking. Python

HALO. Python

mpd-splines-public. This repository implements Motion Planning Diffusion (MPD) - a method for learning and planning robot motions with diffusion models.

Awesome-Flow-RL-Papers. A collection of paper/projects that trains flow matching model/policies via RL.

MICE. Python

MRQ. MR.Q is a general-purpose model-free reinforcement learning algorithm.

geometry_rl. [ICLR25 Oral] RL framework for manipulation of diverse shapes and deformable objects

SafeDiffuser. Safe Planning with Diffusion Probabilistic Models

sitt. Repository relating to "Student-Informed Teacher Training" (ICLR, 2025).

SDA. The official PyTorch implementation of "Following the Human Thread in Social Navigation", International Conference on Learning Representations (ICLR) 2025

rewarped. Reinforcement learning in differentiable multiphysics simulation with NVIDIA Warp.

purejaxql. Simple single-file baselines for Q-Learning in pure-GPU setting

TOP_ERL_ICLR25_Code. ICLR 25 Spotlight, Transformer-based Off-Policy Episodic RL

ICLR2025-Papers-with-Code. 历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

teb_local_planner. An optimal trajectory planner considering distinctive topologies for mobile robots based on Timed-Elastic-Bands (ROS Package)

wlr-competition-2025. C++

neural-robot-dynamics. [CoRL 2025] Neural Robot Dynamics

anki-jlpt-decks. 【egg rolls】JLPT N1～N5 一万词 Anki 牌组【简／繁】【语音＆例句】；Anki，日语，日文，日本語，牌组，卡组，牌組，卡組，能力考，日檢

MASS-AAAI. C++

GenSafeNav. Codebase for "Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling" [CoRL 2025].

recon-ng. Open Source Intelligence gathering tool aimed at reducing the time spent harvesting information from open sources.

serl. SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

ApexNav. [RA-L'25 & ICRA'26] An Reliable and Efficient Framework for Zero-Shot Object Navigation

CookLikeHOC. 🥢像老乡鸡🐔那样做饭。已添加2026年发布的《老乡鸡菜品溯源报告 2.0中新出现的菜品。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Graph-Neural-Network-Note. A blog for understanding graph neural network

ros-mcp-server. Connect AI models like Claude & GPT with robots using MCP and ROS.

Unity-RL-Playground. Reinforcement Learning & Robot Simulation & Embodied Intelligence

scope_nav. [TRO-2025] SCOPE: Stochastic Cartographic Occupancy Prediction Engine for Uncertainty-Aware Dynamic Navigation

UncertaintyAware_DRL_CrowdNav. Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space (IEEE-IV-2024)

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

Point-LIO. High-Bandwidth LiDAR Inertial Odometry

Isaac-RL-Two-wheel-Legged-Bot. two wheel legged robot for IsaacLab - reinforcement learning

ModernTCN. This is an official implementation of "ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis" (ICLR 2024 Spotlight), https://openreview.net/forum?id=vpJMJerXHU

scalingup. [CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down

neptune. A trajectory planning framework for multiple robots: paper accepted in IEEE T-RO

TCN. Sequence modeling benchmarks and temporal convolutional networks

lqr-flow-matching. (RSS 2025) Flow Matching Ergodic Coverage

Awesome_Quadrupedal_Robots. Awesome Quadrupedal Robots

DRL-robot-navigation-IR-SIM. Deep Reinforcement Learning for mobile robot navigation in IR-SIM simulation. Using DRL (SAC, TD3, PPO, DDPG) neural networks, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.

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

AEMCARL. Reinforcement Learning Based Collision Avoidance with Adaptive Environment Modeling for Crowded Scenes

CrowdNav_HEIGHT. [T-ASE 2026] "HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments"

mppi-isaac. Model Predictive Path Integral Control using isaacgym for rollouts, gpu-accelerated

Implicit-SDF-Planner. [IROS 2023] Continuous Implicit SDF Based Any-shape Robot Trajectory Optimization

OmniPerception. Python

Col_DIABLO_Issac_RL. RL example in IssacGym, using DIABLO model. Developed by L-SY

AVOCADO. Repository of the work AVOCADO: Adaptive Optimal Collision Avoidance driven by Opinion (IEEE Transactions on Robotics, 2025)