Pengyu Chen

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

CasyOS. 一个极轻量 Cortex-M3/M4 学习型 RTOS 支持抢占式调度、任务延时，以及内建 IPC（信号量 / 消息队列 / 事件标志组 / 互斥量）。 仅用于初学者学习与内核实验，不适用于商业/工业场景。

isaac_berkeley_humanoid. Python

wococo. Python

playful-doggybot. Project code.

PyDog. Python

lifelike-agility-and-play. Project Page for Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models

robot_lab. RL Extension Library for Robots, Based on IsaacLab.

isaacLab.manipulation. An independent extension based on IsaacLab. It provides support for Robot Manipulation tasks (Robot Arm and Dextrous Hand).

go2_omniverse. Unitree Go2, Unitree G1 support for Nvidia Isaac Lab (Isaac Gym / Isaac Sim)

A_Example_for_Calculating_Robot_Dynamics_Using_Pinocchio_Library. Python

Nabo_Pointfoot_Bipedal_Robot. Open-Sourecd project for pointfoot bipedal robot walking control in MuJoCo simulation. Built on top of nabo(https://github.com/tryingfly/nabo)

Moveit-Gazebo-for-yumi-ABB. The aim of this project is to use Moveit and Gazebo in ROS to jointly simulate the basic and collaborative simulation of Yumi dual arm robots, and to use code programming to implement simple motion planning

LocomotionWithNP3O. unitree Go2 robot learns locomotion with N-P3O algorithm and HIM alike policy trained by isaacgym

towr. A light-weight, Eigen-based C++ library for trajectory optimization for legged robots.

rl_sar. Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

Navigation-Learning. 我的导航算法学习笔记，内容涵盖导航定位开源程序的源码解读、开源项目梳理、书籍讲义、博客翻译、教程讲座推荐；所有内容都可以随意转载，原始文件都放在这里了，大家可以在我的基础上整理出自己的一些文档。（Tips：①主要是写给初学者，已经有基础的同学应该多看论文和代码，看我的笔记学不到啥；②仓库持续更新中，不建议 fork）

robopal. robopal: a multi-platform, modular robot simulation framework based on MuJoCo, mainly used for reinforcement learning and control algorithm implementation of robotic arms.

humanoid-bench. Python

Cerberus. Visual-Inertial-Leg Odometry For Legged Robots

BaselineFootstepPlanner. Humanoid footstep planner based on baseline methods with graph search

rocket. c++ rpc framework, simplified version of tinyrpc。

Paper-List. A paper list of my history reading. Robotics, Learning, Vision.

Interview. CPP面试修炼

Adapt. Actuator Degeneration Adaptation Transformer

fld. Repository for our paper: FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning, Proceedings of the 12th International Conference on Learning Representations (ICLR)

humanoid-gym. Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

iTransformer. Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)

time-disentanglement-lib. 🤗 [ICLR 2024] Disentangling Time Series Representations via Contrastive based l-Variational Inference

MetaRobotics. Jupyter Notebook

OP3_Mujoco_Simulator. Python

pkGym. Python

extreme-parkour. [ICRA 2024]: Train your parkour robot in less than 20 hours.

CS-Notes. :books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

ORCAgym. phase-based Observations, Rewards, Coupling Ablation

legged_gym_bolt10_rma. Python

rma_rsl_rl. Python

15445-bootcamp. A basic introduction to coding in modern C++.

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

RE-Skill. Python

tsid. Efficient Task Space Inverse Dynamics (TSID) based on Pinocchio

pympc-quadruped. A Python implementation about quadruped locomotion using convex model predictive control (MPC).

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

FCPCodebase. FC Portugal Codebase

HIMLoco. Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

biped_pybullet_sim. Learning 高擎机电's biped robot walking simulation using pybullet

MIT-Cheetah-Note. MIT Cheetah仿真平台源码笔记以及一部分第三方组件

ppo_transformer. Implementation of Proximal Policy Optimization using Transformer

episodic-transformer-memory-ppo. Clean baseline implementation of PPO using an episodic TransformerXL memory

UTDS. Pessimistic Value Iteration for Multi-Task Data Sharing in Offline RL

hgap. Code release for H-GAP Humanoid Control with a Generalist Planner

sin-cassie-rl-python. Python

AdaptNet. [SIGGRAPH Asia 2023] AdaptNet: Policy Adaptation for Physics-Based Character Control

pybullet-op3. Python

rk_ffmpeg. 在rockchip3588上实现用ffmpeg进行推拉流，其中推拉流使用硬件加速编解码

swing-trajectory-generator. Swing trajectory generation for walking robots

Hector_Simulation. Simulation Software for HECTOR Humanoid Robot (ROS/MATLAB)

IK-MPC. Inverse Kinematics-based Model Predictive Control for Robot Motion Planning

deep-rl-humanoid-motions-masters. Repository for code from the Master's Thesis "Imitation Learning and Meta-Reinforcement Learning for Optimizing Humanoid Robot Motions".

LAG. An environment based on JSBSIM aimed at one-to-one close air combat.

PHC. Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

Optimization-based-robot-control. In this repository there are the projects developed during the course of Advance Optimization-based Robot Control. The main topics are Task Space Inverse Dynamics (TSID), Differential Dynamic Programming (DDP) and Deep Q-Network (DQN).

loco-mujoco. Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

RL_augmented_MPC. C++

log.c. A simple logging library implemented in C99

free_dog_sdk_cpp. C++

mqtt-camera-streamer. Stream images from a connected camera over MQTT, view using Streamlit, record to file and sqlite

RoboFlamingo. Code for RoboFlamingo

Change-Detection-Dataset-for-High-Resolution-Satellite-Imagery. This repository is for releasing a dataset for high-resolution satellite imagery

APRL. Efficient Real-World RL for Legged Locomotion via Adaptive Policy Regularization

Hector_Simulation. Simulation Software (ROS/MATLAB) for HECTOR Humanoid Robot Locomotion Control/Bipedal Locomotion Control/Force-and-moment-based MPC

linux-source-code-analyze. Linux内核源码分析

RL-X. A framework for Reinforcement Learning research.

rom-mpc-rl. Python

PokemonRedExperiments. Playing Pokemon Red with Reinforcement Learning

interaction_AMP. Python

Rofunc. 🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

prompt2walk. Code for Prompt a Robot to Walk with Large Language Models https://arxiv.org/abs/2309.09969

depRL. Repository for our ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

omnisafe. JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

safety-gymnasium. NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

linux_camera_project. 嵌入式linux相机项目

UHC. Official Implementation of the Universal Humanoid Controller in Mujoco. Supports Kinpoly (NeurIPS 2021) and EmbodiedPose (NeurIPS 2022).

RFC. [NeurIPS 2020] Official PyTorch Implementation of "Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis". NeurIPS 2020.

imx6ull_ElectronicsTestSuite. 萌新跟着韦东山老师做项目基础——电子产品量产工具

linux_kernel_wiki. linux内核学习资料：200+经典内核文章，100+内核论文，50+内核项目，500+内核面试题，80+内核视频

Waifu2x-Extension-GUI. Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.

PyPnC. Python Implementation of Planning and Control

ungar. Simplifying optimal control with metaprogramming

TRILL. Official codebase for TRILL (Teleoperation and Imitation Learning for Loco-manipulation)

parkour. [CoRL 2023] Robot Parkour Learning

hello-algo. 《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持简中、繁中、English、日本語，提供 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 等代码实现

SND. Self-supervised Network Distillation is class of intrinsic motivation algorithms for reinforcement learning

Tiny-WebServer. 此项目是基于 Linux 轻量级多线程的 Web 服务器，应用层实现了一个简单的 HTTP 服务器，支持静态资源的访问 与动态消息的回显。

Effective-Cpp-Reading-Note. :book: Effective C++: 55 Specific Ways to Improve Your Programs and Designs (Ver.3) Reading Notes

effective-cpp-note. Note Of Effective C++ 、More Effective C++ And Effective Modern C++

muduo_study. Linux多线程服务端编程[muduo C++网络库]

meta-qlearning-humanoid. Meta QLearning experiments to optimize robot walking patterns

imx6ull_project. 这是基于正点原子的imx6ull做的一个学习项目

Robinion-Balance-Board-PPO. Humanoid robot playing balance board in NVIDIA Isaac Gym using PPO.

CALM. Python

robust-safe-rl. Robust and safe deep reinforcement learning algorithms

tcrl. Jupyter Notebook

mastering-urlb. [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.

cic_gym. Adaptation of original "Contrastive Intrinsic Control for Unsupervised Skill Discovery" implementation to OpenAI Gym

biped_stance_planner. A simple biped stance planner utility based on MuJoCo. Torso, left foot and right foot position and orientation can be adjusted to obtain a suitable robot posture.

terrain_benchmark. terrain-robustness benchmark for legged locomotion

dairlib. C++

legged-rnn-planning. Python

generate-humanoid-walking-gaits. This repository shows how to follow the guidelines from Pinocchio to generate walking gaits for a humanoid robot.

OmniIsaacGymEnvs-Cassie. This is a clone of OmniIsaacGymEnvs, and it is used for my rl env test.

crocoddyl. Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

RM_Isaac. Train quadruped locomotion policies with reward machines in Isaac Gym

pql. Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation

Legged-Robots. This repository contains papers in the field of legged robots.

NWPU-MOC. This is a repository about NWPU-MOC dataset and code.

Legged-Robots-Projects. Implementation of two legged robots controller. One bipedal (ATLAS) using the inverted pendulum model as well as a quadruped robot. For the quadruped robot multiple controller are implemented, from CPG and VMC, PD controller and reinforcement learning.

learning-safety-in-mpc-based-rl. Safety-aware MPC-based RL framework

ARTO-AL. C++

bipedal_walker_terrain. Learning Perceptive Bipedal Locomotion over Irregular Terrain

bipedal-locomotion-framework. Suite of libraries for achieving bipedal locomotion on humanoid robots

pbrs-humanoid. Python

Awesome-Robot-Learning. This repo contains a curative list of robot learning (mainly for manipulation) resources.

6.S081-All-in-one. 6.S081课程全记录，包括课程使用的书籍、论文、实验要求的中文翻译，以及实验过程记录

szu-xv6-riscv-adapted. C

contrastive-learning-iSogCLR. Python

rl. A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

CDP. Python

robopianist. [CoRL '23] Dexterous piano playing with deep reinforcement learning.

DA-CL-4Rec. Official repository for TKDE 2026 paper: Data Augmentation for Sequential Recommendation: A Survey

rl-mpc-locomotion. Deep RL for MPC control of Quadruped Robot Locomotion

nscc2022_personal. NSCSCC2022龙芯杯个人赛，MIPS32，59MHz经典五级流水线架构，易于初学者阅读（计算机组成原理，自己动手写CPU）

BookLiveRipper. Qt-Based tool to download full novels from Booklive.jp

pyrobolearn. PyRoboLearn: a Python framework for Robot Learning

walk-these-ways. Sim-to-real RL training and deployment tools for the Unitree Go1 robot.

DARWIN-OP2-in-Webots. 在Webots中使DARWIN-OP2按官方动作库生成轨迹，并记录、模仿之

Yet-Another-LaTeX-Template-for-NPU-Thesis. 西北工业大学硕博学位论文模版 | Yet Another Thesis Template for Northwestern Polytechnical University

PRELUDE. Official codebase for PRELUDE (Perceptive Locomotion Under Dynamic Environments)

quadruped_nmpc_dcbf_duality. C++

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

cassie_alip_mpc. This repository provides an implementation of a bipedal locomotion controller, described in the paper Terrain-Adaptive, ALIP-Based Bipedal Locomotion Controller via Model Predictive Control and Virtual Constraints(pdf)(arXiv). The controller has two components: (1) an Angular Momentum Linear Inverted Pendulum (ALIP)-based Model Predictive Control (MPC) foot placement planner and (2) a gait controller which takes the foot placement solution as an input. This controller enables improved stability for walking on a variety of sloped and textured terrains. The controller is implemented on the Agility Robotics Cassie Robot.

LearningHumanoidWalking. Training a humanoid robot for locomotion using Reinforcement Learning

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

legged_control. NMPC, WBC, state estimation, and sim2real framework for legged robots based on OCS2 and ros-controls

docker-wechat. DoChat is a Dockerized WeChat (盒装微信) PC Windows Client for Linux

SpaceRobotEnv. A gym environment designed for free-floating space robot control based on the MuJoCo platform.

IQ-Learn. (NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation

bipedal-robot-learning-collection. Collection of high-quality robo learning papers for bipedal robots.

StableBaselines3_SimpleCases. Jupyter Notebook

ElegantRL. Massively Parallel Deep Reinforcement Learning. 🔥

shifu. Lightweight Isaac Gym Environment Builder

Mujoco_walkingRobots. Python

awesome-legged-locomotion-learning. A curated list of resources relevant to legged locomotion learning of robotics.

awesome-robotics. A list of awesome Robotics resources

legged_gym. Isaac Gym Environments for Legged Robots

humanoid. Python

frobs_rl. Framework to easily develop robotics Reinforcement Learning tasks using Gazebo and stable-baselines-3.

Evangelion-typora-theme. An eye-friendly dark theme for Typora editor, based on the color scheme of Neon Genesis Evangelion.

good_robot. "Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

awesome-cpp. A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.

TNet_TMM2022. Python

Multi-level-TransUNet-for-Space-based-Infrared-Tiny-ship-Detection. Python

VHRShips. This study focuses on all stages of ship classification in the optical satellite images. The proposed “Hierarchical Design (HieD)” approach, which is based on deep learning techniques, performs Detection, Localization, Recognition and Identification (DLRI) of the ships in the optical satellite images. HieD is an end-to-end approach which allows the optimization of each stage of the DLRI independently. A unique and rich ship dataset (High Resolution Ships, HRShips), which is formed by the Google Earth Pro software, is used in this study. While Xception network is used in detection, recognition and identification stages; YOLOv4 is preferred for the localization of the ships.

ultralyticsPro. 🔥🔥🔥 专注于YOLO11，YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

awesome-audiovisual-learning. A curated list of audio-visual learning methods and datasets.

HorNet. [NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

DAN. The code of Cross-Modal Cross-Domain Dual Alignment Network for RGB-Infrared Person Re-Identification.

AI-System. System for AI Education Resource.

RGB-T-fusion-tracking-papers-and-results. The papers and results about RGB-T fusion tracking

Classic-and-state-of-the-art-image-fusion-methods. CBF,CVT,DTCWT,GTF,LP,MSVD,RP,Wavelet,CNN,Deepfuse,DenseFuse,FusionGAN,IFCNN,MDlatLRR,DDcGAN,ResNetFusion,NestFuse,NVCE,FusionDN,HybridMSD,PMGI,IFEVIP,StructAware,U2Fusion,MEF-GAN，JSR,ConvSR,DCHWT,MEFGAN,MWFG,PMGI,PANGAN,ect

swin-transformer-pytorch. Implementation of the Swin Transformer in PyTorch.

Awesome-RGBT-Fusion. A collection of deep learning based RGB-T-Fusion methods, codes, and datasets. The main directions involved are Multispectral Pedestrian Detection, RGB-T Aerial Object Detection, RGB-T Semantic Segmentation, RGB-T Crowd Counting, RGB-T Fusion Tracking.

huge-filter-to-segment-or-detect-object. I designed an extremely huge filter to segment or detect objects.

Stacked-Hourglass-on-Pytorch-1.6. I realized Hourglass published on CVPR 2016 using pytorch 1.6

Convolutional-Pose-Machine. realize CPM published on CVPR-20xx via Pytorch 1.6

Awesome-Crowd-Localization. Awesome Crowd Localization

Awesome-Crowd-Counting. Awesome Crowd Counting

deep-learning-for-image-processing. deep learning for image processing including classification and object-detection etc.

leetcode. LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)

2021-summer-vacation. Related content for summer vacation of 2021

batchnorm.