27 مستودعات
Libraries for simulating rigid body dynamics and physics.
Explore 27 awesome GitHub repositories matching part of an awesome list · Physics and Simulation. Refine with filters or upvote what's useful.
Matter-js is a 2D rigid body physics engine written in JavaScript for simulating realistic physical interactions, collisions, and dynamics in web browsers. It functions as a web physics simulation library that calculates motion, gravity, and constraints for objects rendered on a web canvas. The library includes a built-in canvas physics visualizer to draw physical bodies, joints, and constraints for debugging and gameplay. It distinguishes itself through a plugin system that supports recursive dependency resolution and internal method patching to inject custom logic into the engine's executio
Acts as a specialized physics simulation library for calculating motion and gravity on a web canvas.
Infinigen is a procedural 3D scene generation framework that creates photorealistic indoor and outdoor environments for computer vision training data. It combines constraint-based object placement, GPU geometry shaders, and ground-truth rendering passes to produce scenes with depth, normals, and segmentation masks alongside final images. The framework distinguishes itself through modular asset composition, a node-graph material system, and physics simulation integration that embeds rigid-body and fluid dynamics directly into the generation pipeline. Procedural rule-based scene composition and
Embeds rigid-body and fluid dynamics solvers directly into the generation pipeline for physically accurate interactions.
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
Provides the core Omniverse-PhysX simulation backend that models rigid bodies, articulated systems, deformable objects, and sensors.
Provides a physically based simulation environment for training and testing robot policies with GPU-accelerated physics.
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
Runs RL training loops at high speed by eliminating inter-process communication and offloading simulation to compiled C extensions.
Rapier هو محرك فيزياء عبر المنصات وحلال ديناميكيات الأجسام الصلبة مصمم لمحاكاة 2D و3D. يعمل كنظام لاكتشاف التصادم وإطار عمل لمحاكاة الروبوتات، مما يوفر واجهة برمجة تطبيقات متسقة لحساب التفاعلات الفيزيائية عبر بيئات مختلفة. يتميز المحرك بقدرات روبوتية متخصصة، بما في ذلك مجموعة أدوات لاستيراد نماذج URDF وSTL للتحكم في سلاسل الأجسام المتعددة. يدعم الحركة الميكانيكية الدقيقة من خلال حسابات الحركية العكسية (inverse kinematics) وتطبيق وحدات تحكم PID للتحكم الديناميكي في الجسم. تغطي مساحة المحاكاة مجموعة واسعة من القدرات الفيزيائية، بما في ذلك وحدات تحكم الشخصيات الحركية لاجتياز التضاريس ونماذج ray-cast لديناميكيات المركبات. يتميز بخط أنابيب تصادم متعدد المراحل مع اكتشاف تصادم مستمر لمنع نفق الأجسام، بالإضافة إلى نظام لقيود الحركة المشتركة باستخدام مفاصل دوارة، ومنشورية، وكروية. يتضمن إطار العمل أدوات مساعدة لاستيراد التعريفات الهندسية الخارجية عبر تنسيقات STL وURDF وXML، ويوفر واجهة تصحيح مستقلة عن الخلفية لتصور حالات الفيزياء الداخلية ومشاهد 3D.
Offers a cross-platform library for simulating rigid body dynamics and physical interactions.
هذا المشروع عبارة عن محاكاة طائرات مفتوحة المصدر لـ Microsoft Flight Simulator، توفر إعادة إنشاء عالية الدقة لطائرة ركاب تجارية. يتكون من نموذج طيران مفصل، وقمرة قيادة افتراضية تفاعلية، وأنظمة طائرات محاكاة مصممة لتكرار سلوك طائرة ركاب واقعية. تستخدم المحاكاة بنية إلكترونيات طيران معيارية ومزامنة قمرة القيادة القائمة على الحالة لإدارة أدوات قمرة القيادة. تستخدم وقت تشغيل WebAssembly لمنطق الأنظمة عالي الأداء وتتميز بشبكة جسر بيانات لتوجيه بيانات المحاكاة إلى الأجهزة الخارجية وأدوات الطرف الثالث. يغطي المشروع مجالات محاكاة الطيران الواسعة، بما في ذلك ديناميكيات طيران الطائرات، وتكرار إجراءات الطيران الواقعية، وإنشاء كسوات خارجية مخصصة. كما يتضمن موارد تعليمية لعمليات الطيران وأدوات تفاعلية لاستكشاف قمرة القيادة. يتم صيانة البرنامج من خلال نظام إدارة إضافات مخصص لتثبيت وتحديث المحاكاة وتوسعاتها المتوافقة.
Connects simulation aircraft to external hardware and data sources by routing traffic into the primary simulator.
Pts هي مكتبة TypeScript للبرمجة الإبداعية وإطار عمل لتصور البيانات مصمم لبناء الفن التوليدي والمرئيات التفاعلية. تعمل المكتبة كمحرك رسومات متعدد الأهداف يرسل أوامر مرئية إلى HTML5 Canvas وSVG من خلال واجهة موحدة. تعمل مجموعة الأدوات كأداة لتصور الجبر الخطي، حيث توفر بدائيات رياضية للتحويلات المكانية والحسابات الهندسية. وهذا يسمح بإنشاء أنماط خوارزمية ومحاكاة السلوكيات الهندسية. يغطي إطار العمل سطح قدرات واسع يشمل تصميم المخططات التفاعلية، وتطبيق الجبر الخطي للرسومات، وعرض العناصر المرئية عبر تنسيقات مخرجات متعددة.
Simulates geometric behaviors and physics to create interactive art and generative patterns.
Urho3D is a cross-platform 3D game engine written in C++. It uses a component-based scene graph to compose game objects from nodes and attached components, separating transforms from behaviors for modular design. The engine integrates AngelScript and Lua scripting for game logic, uses the Bullet library for physics simulation, and renders scenes with OpenGL or Direct3D through forward, deferred, or light pre-pass pipelines with customizable render passes and shadow mapping. The engine distinguishes itself with a built-in visual scene and UI editor for composing 3D worlds and interface layouts
Ships a full physics simulation engine for rigid bodies, vehicles, and constraints in 2D and 3D.
Webots هو محاكي روبوتات قائم على الفيزياء وبيئة تطوير تستخدم لنمذجة وبرمجة واختبار سلوك الروبوتات في عالم فيزيائي ثلاثي الأبعاد محاكى. يعمل كأداة نماذج أولية افتراضية للتحقق من الأنظمة الميكانيكية والإلكترونية من خلال إنشاء نماذج روبوت افتراضية ومنطق تحكم. تتيح المنصة سير عمل محاكاة روبوتات كامل، بما في ذلك تطوير وحدات تحكم الروبوت وبرمجة سلوكيات الوكيل المستقل. يركز على نمذجة النظام الفيزيائي لتمثيل الخصائص الميكانيكية للأجهزة ومحاكاة التفاعلات في العالم الحقيقي. تغطي قدرات النظام تطوير وحدة تحكم الروبوت، وبرمجة الوكيل المستقل، والنمذجة والمحاكاة العامة لأنظمة الروبوتات.
Acts as a physics-based simulator for rigid bodies and articulated systems with realistic sensor interaction.
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
Executes physical simulations of multibody systems using various contact models like point and hydroelastic contact.
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
Builds virtual environments that mimic real-world physical constraints to safely validate robot behavior before deploying code to physical hardware.
Goxel: Free and Open Source 3D Voxel Editor
Voxel-based 3D modeling and editing tool.
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
Executes high-fidelity rigid body dynamics directly on the graphics processor to enable massive parallelization of robotic training environments.
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
Simulates complex interactions between robots and objects within a physics-enabled environment.
Avian is a 2D physics engine and rigid body dynamics simulator designed to calculate physical motion using mass, forces, and velocity. It provides a framework for simulating rigid body dynamics, collision detection, and joint constraints for games and applications. The engine utilizes a modular physics pipeline with a plugin-based architecture, allowing for the customization of simulation fidelity settings and the extension of collision backends. It includes a specialized kinematic character controller for implementing entity movement and sliding behavior against physical geometry. The syste
Adjusts simulation speed, gravity, and substeps to balance physical accuracy and performance.
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
Offers a physically based simulation environment leveraging GPU acceleration for contact-rich robotic tasks.
KawaiiPhysics is an Unreal Engine physics plugin that provides a skeletal mesh simulation tool for calculating pseudo-physics bone sway. It is designed to create natural movement for hair and clothing by controlling bone rotation based on stiffness and damping without requiring a full rigid body physics engine. The system features a character physics constraint framework and a runtime controller that allows for the dynamic adjustment of simulation parameters and external forces. It utilizes data-asset preset management to ensure consistent physics behavior across different characters and obje
Allows saving and reusing simulation settings through data assets to ensure consistency.
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
Connects the 3D simulator to external robotics frameworks through a ROS interface for real-time control and sensor feedback.
This project is a parallel simulation engine and molecular dynamics simulator designed to model the physical movements of atoms and molecules. It functions as an interatomic potential framework for calculating forces between particles and a materials analysis tool for computing thermodynamic, structural, and transport properties of solids and fluids. The engine is distinguished by its high-performance computing capabilities, utilizing spatial-domain decomposition and message-passing interface communication to distribute workloads across processors. It supports multi-backend GPU acceleration v
Manages the physical volume and spatial regions of the simulation domain.