Awesome GitHub RepositoriesRobotic Physics and Sensor Simulators

Isaac Lab is an open-source framework for training robot policies in physically simulated environments, supporting both single-agent and multi-agent reinforcement learning. It is built on an Omniverse-PhysX simulation backend that models rigid bodies, articulated systems, deformable objects, and sensors, and provides a task-based environment configuration system where each training environment is defined as a modular class specifying observation spaces, action spaces, reward functions, and termination conditions. The framework distinguishes itself through an RL-library abstraction layer that

PufferLib is a reinforcement learning framework built around high-speed environment simulation and automatic hyperparameter optimization. It is designed to accelerate the entire RL training pipeline by running simulations at near-native speed and enabling the training of tiny models to super-human performance within seconds. The framework achieves its speed through a single-process training loop that eliminates inter-process communication overhead, vectorized batched simulation for parallel environment execution, and compiled C extensions that offload performance-critical computations. It als

Rapier est un moteur physique multiplateforme et un solveur de dynamique de corps rigides conçu pour les simulations 2D et 3D. Il fonctionne comme un système de détection de collision et un framework de simulation robotique, fournissant une API cohérente pour calculer les interactions physiques à travers différents environnements. Le moteur se distingue par des capacités robotiques spécialisées, incluant une boîte à outils pour importer des modèles URDF et STL afin de contrôler des chaînes multicorps. Il prend en charge un mouvement mécanique précis via des calculs de cinématique inverse et l'application de contrôleurs PID pour le contrôle dynamique des corps. La surface de simulation couvre un large éventail de capacités physiques, incluant des contrôleurs de personnage cinématiques pour la traversée de terrain et des modèles de ray-cast pour la dynamique des véhicules. Il dispose d'un pipeline de collision multi-phases avec détection de collision continue pour empêcher le tunneling d'objets, ainsi qu'un système pour les contraintes de mouvement articulé utilisant des joints rotatifs, prismatiques et sphériques. Le framework inclut des utilitaires pour importer des définitions géométriques externes via des formats STL, URDF et XML, et fournit une interface de débogage agnostique au backend pour visualiser les états physiques internes et les scènes 3D.

Ce projet est une simulation d'avion open source pour Microsoft Flight Simulator, fournissant une recréation haute fidélité d'un avion de ligne commercial. Il consiste en un modèle de vol détaillé, un cockpit virtuel interactif et des systèmes d'avion simulés conçus pour reproduire le comportement d'un jet de passagers réel. La simulation emploie une architecture avionique modulaire et une synchronisation de cockpit basée sur l'état pour gérer les instruments du poste de pilotage. Elle utilise un runtime WebAssembly pour une logique de systèmes haute performance et dispose d'un réseau de pont de données pour router les données de simulation vers du matériel externe et des outils tiers. Le projet couvre de larges domaines de simulation aéronautique, notamment la dynamique de vol des avions de ligne, la réplication des procédures de vol réelles et la création de livrées extérieures personnalisées. Il inclut également des ressources pédagogiques pour les opérations de vol et des outils interactifs pour l'exploration du cockpit. Le logiciel est maintenu via un système de gestion d'add-ons dédié pour installer et mettre à jour la simulation et ses extensions compatibles.

Webots is a physics-based robot simulator and development environment used for modeling, programming, and testing the behavior of robots in a simulated 3D physical world. It serves as a virtual prototyping tool to verify mechanical and electronic systems through the creation of virtual robot models and control logic. The platform enables a full robotics simulation workflow, including the development of robot controllers and the programming of autonomous agent behaviors. It focuses on physical system modeling to represent the mechanical properties of hardware and simulate real-world interactio

Drake is a robotics simulation framework and control system modeling tool used for designing, simulating, and verifying the dynamics of complex robotic systems. It functions as a multibody dynamics simulator and a mathematical optimization library, providing a suite of algorithms for trajectory optimization and the simulation of articulated robots. The framework is distinguished by its block-diagram system for composing dynamical subsystems and its ability to formulate and solve diverse mathematical programs, including linear, quadratic, and nonconvex nonlinear problems. It supports specializ

Unitree RL Gym is an integrated software framework designed for the simulation, training, and deployment of motion control policies for legged robotic platforms. It provides a comprehensive environment for developing locomotion strategies for quadruped and humanoid robots by leveraging reinforcement learning algorithms within high-fidelity physics-based simulations. The platform distinguishes itself by offering an end-to-end workflow that bridges the gap between virtual training and physical execution. It includes specialized tools for mapping raw sensor data into normalized state-space obser

Legged Gym is a high-performance simulation platform and toolkit engineered for training autonomous robotic agents in complex, physics-based environments. It provides a comprehensive framework for developing legged locomotion control policies, enabling robots to learn movement strategies for navigating uneven terrain and managing physical disturbances through reinforcement learning. The platform distinguishes itself by utilizing hardware-accelerated physics and headless execution to maximize computational throughput during training. It incorporates a domain randomization pipeline that injects

mujoco_menagerie is a curated library of physical robot specifications and XML model definitions designed for standardized dynamics and contact simulation. It provides a collection of high-quality robot model files for humanoids, quadrupeds, and manipulators, alongside detailed kinematic and inertial parameters used to reproduce real-world robot behavior in virtual environments. The project serves as a repository of robotics simulation assets and MJCF model definitions optimized for accuracy. It includes standardized model libraries specifically for bipedal, quadrupedal, and humanoid hardware

IsaacGymEnvs is a GPU-accelerated physics sandbox and robotics policy training suite designed for reinforcement learning. It serves as a vectorized robotic simulator that runs thousands of parallel environments on GPUs to accelerate the training of neural networks. The project provides a sim-to-real transfer framework that utilizes domain randomization and physics variations to ensure policies trained in simulation are robust enough for deployment on real hardware. It distinguishes itself through a high-performance architecture that uses tensor-based state management to handle observations an

Habitat-Lab is an open-source platform for training and evaluating embodied AI agents in photorealistic 3D indoor environments. It functions as a high-performance 3D indoor environment simulator that supports physics-based interaction, enabling research into navigation and manipulation tasks. The platform provides a modular task-environment abstraction that separates task logic from environment simulation, using configuration-driven pipeline assembly to compose simulation and training pipelines. It includes a hierarchical sensor-actuator architecture for mixing and matching perception and act

ManiSkill is a GPU-accelerated robot simulation framework designed for training robotic manipulation skills, benchmarking learning algorithms, and generating synthetic datasets. It serves as a reinforcement learning environment where robot control policies can be developed and evaluated using parallelized physics and rendering on the GPU. The platform is distinguished by its ability to perform sim-to-real transfer, allowing policies trained in virtual environments to be deployed onto physical robotic hardware. It features ray-traced parallel rendering for producing high-frame-rate RGBD and se

Newton is a GPU-accelerated physics engine and robotics simulation platform designed for high-performance modeling of rigid bodies and complex articulations. It functions as a differentiable physics engine, calculating gradients to enable mathematical optimization and machine learning. The platform is distinguished by its ability to execute multiple parallel physics worlds on a single GPU, which accelerates data collection for reinforcement learning. It also supports the simulation of deformable bodies, such as cloth and cables, using particle-based methods and multi-physics coupling. Newton

Rotors Simulator is a physics-based simulation framework designed for testing multirotor unmanned aerial vehicles and their control algorithms within a virtual environment. It models aerial vehicle movement, rotor thrust, and aerodynamic interactions by computing individual motor speeds directly to apply thrust and torque forces to rigid body dynamics. Aircraft kinematics, visual meshes, and sensor attachment points are described declaratively using unified robot description format files. The environment integrates dynamic models and aerodynamic forces through native runtime plugins while coo

DRL-robot-navigation is a deep reinforcement learning platform and robotic simulation framework designed to train autonomous mobile robots for collision-free path planning. It uses neural network policies and physics-engine simulation environments to teach robots how to navigate toward target coordinates while avoiding obstacles. The software trains continuous control policies using twin delayed deep deterministic policy gradients over continuous state and action spaces. Training is guided by scalar reward signals derived from target proximity and obstacle avoidance distances. System compone

The project provides a software simulation framework and physics engine for modeling underwater vehicles, subsea sensors, and ocean environments. It runs within robotics middleware to test autonomous and remotely operated underwater vehicles by combining hydrodynamic physics, ocean currents, and sensor modeling. The platform computes hydrodynamic forces, buoyancy, equations of motion, and thruster dynamics to accurately replicate underwater physics. It loads pre-configured mechanical assemblies, manipulator panels, and environmental sensors, while generating three-dimensional water movement f