AtsushiSakai/PythonRobotics
PythonRobotics
PythonRobotics est une collection complète d'algorithmes robotiques modulaires et de simulations éducatives conçues pour la navigation autonome, l'estimation d'état et le contrôle de mouvement. Le projet fournit une bibliothèque d'implémentations autonomes pour la planification de trajectoire, la localisation, la cartographie et la cinématique, servant de ressource aux chercheurs et aux étudiants pour expérimenter des théories robotiques fondamentales et avancées.
Le projet se distingue par une conception centrée sur les algorithmes où chaque module fonctionne comme un script isolé, permettant des tests indépendants et une démonstration pédagogique claire. Chaque implémentation est explicitement liée à la littérature académique ou aux manuels de robotique fondamentaux, garantissant que les modèles mathématiques et les stratégies de contrôle restent vérifiables et précis. Les utilisateurs peuvent exécuter ces scénarios dans un environnement de simulation découplé qui maintient son propre état interne et ses boucles de contrôle, sans nécessiter de dépendances externes.
La surface de capacités couvre un large éventail de domaines robotiques, y compris la navigation aérienne, la locomotion bipède et le contrôle de bras multi-articulés. Il propose des boîtes à outils étendues pour la fusion de capteurs probabilistes, la cartographie environnementale et le suivi de trajectoire, le tout alimenté par un calcul numérique haute performance. Les animations géométriques en temps réel et les estimations d'état sont rendues directement à partir des données de simulation en utilisant des bibliothèques de traçage standard.
Features
- Algorithm Libraries - Provides a comprehensive library of fundamental algorithms for autonomous robotic systems.
- Kinematics - Provides interactive simulation tools for multi-joint robotic arm control, including end-effector positioning and obstacle avoidance.
- Robotics Algorithms - Provides modular, standalone implementations of core robotics algorithms for educational purposes.
- SLAM Algorithms - Implements simultaneous localization and mapping using feature-based particle filtering and iterative point cloud matching.
- Motion Planning Toolkits - Calculates optimal paths and motion profiles for mobile robots and manipulators.
- Navigation Frameworks - Provides a modular framework for obstacle avoidance and trajectory generation.
- Path Planning Algorithms - Implements diverse path planning methods including sampling-based and optimization-driven approaches.
- Probabilistic Localization - Provides Kalman, histogram, and particle filters for robot position estimation.
- Sensor Fusion - Combines noisy sensor data with probabilistic filtering for robot localization.
- State Estimation Libraries - Provides probabilistic algorithms for sensor fusion and robot localization.
- Control Systems - Path tracking simulation with iterative linear model predictive speed and steering control. Reference - documentation - Real\-time Model Predictive Control \(MPC\), ACADO, Python \| Work\-is\-Playing
- Kinematic Path Planning - A sample code with Reeds Shepp path planning. Reference - 15.3.2 Reeds\-Shepp Curves - optimal paths for a car that goes both forwards and backwards - ghliu/pyReedsShepp: Implementation of Reeds Shepp curve\.
- Path Tracking Control - Implements LQR, MPC, and feedback steering for autonomous vehicle guidance.
- Sampling-Based Motion Planning - This is a path planning simulation with LQR-RRT\. A double integrator motion model is used for LQR local planner. Reference - LQR\-RRT\: Optimal Sampling\-Based Motion Planning with Automatically Derived Extension Heur
- Path Planning Algorithms - Implements A* algorithm for 2D grid-based shortest path planning.
- Simulation Frameworks - Ships a decoupled simulation environment for testing robotic scenarios without external dependencies.
- Frameworks de robotique - Collection d'algorithmes de robotique pour la navigation autonome.
- Scientific Computing - Compilation of robotics algorithms.
- Control Theory Libraries - Comprehensive collection of robotics algorithms and control simulations.
- Robotics Algorithms - Comprehensive collection of robotics algorithms implemented in Python.
- Robotics Frameworks - Collection of robotics algorithms implemented in Python.
- Reference Lists - Python sample code for robotics algorithms.
- Robotics Education - Collection of sample code for common robotic algorithms.
- Scientific Computing - Listed in the “Scientific Computing” section of the Awesome Python awesome list.
- Educational Robotics Libraries - Provides instructional simulations for teaching autonomous navigation concepts.
- Kinematics Simulators - Models multi-joint robotic arms and bipedal systems for movement simulation.
- Environmental Mapping Techniques - Provides grid-based occupancy, ray casting, and geometric shape fitting for spatial awareness.
- Bipedal Locomotion Planning - Optimizes footstep sequences for stable walking using inverted pendulum models.
- Hybrid Motion Planning - Path planning for a car robot with RRT\* and reeds shepp path planner.
- Potential Field Methods - This is a 2D grid based path planning with Potential Field algorithm. In the animation, the blue heat map shows potential value on each grid. Reference - Robotic Motion Planning:Potential Functions
- Trajectory Generation - This is optimal trajectory generation in a Frenet Frame. The cyan line is the target course and black crosses are obstacles. The red line is the predicted path. Reference - Optimal Trajectory Generation for Dynamic Stree
- Numerical Libraries - Performs core mathematical operations and linear algebra using high-performance array processing.
- Nonlinear Optimization Solvers - A motion planning and path tracking simulation with NMPC of C-GMRES Reference - documentation
- Kalman Filter Localization - Implements Extended Kalman Filter algorithms for robotic localization.
- Particle Filter Localization - Provides sensor fusion localization using particle filter algorithms.
- Aerial Navigation Simulators - Simulates three-dimensional trajectory following and rocket-powered landing maneuvers.
- Point Cloud Registration - Provides 2D Iterative Closest Point matching using singular value decomposition.
- Metaheuristic Optimization - This is a 2D path planning simulation using the Particle Swarm Optimization algorithm. PSO is a metaheuristic optimization algorithm inspired by bird flocking behavior. In path planning, particles explore the search spac
- Aerial Navigation Simulations - Provides a 3D trajectory following simulation for quadrotor aerial navigation.
- Arm Navigation Simulations - Simulates robotic arm navigation with integrated obstacle avoidance.
- Bipedal Planning Simulations - Simulates bipedal footstep planning using inverted pendulum models.
- Histogram Filter Localization - Demonstrates 2D localization using histogram filter probabilistic grid mapping.
- Lidar Mapping - Converts 2D Lidar range measurements into occupancy grid maps.
- Rocket Landing Simulations - Simulates 3D trajectory generation for rocket-powered landing scenarios.
- Robotics Prototyping Environments - Provides a simulated environment for testing path planning and control algorithms.
- 3D Math and Geometry Toolkits - Renders real-time geometric animations and state estimations from simulation data using standard plotting libraries.
- Steering Control Strategies - Provides Stanley steering control implementations for autonomous path tracking.
- Gaussian Grid Mapping - Demonstrates 2D Gaussian grid mapping for robotic environments.
- Manipulator Control Simulations - Provides an interactive simulation for N-joint robotic arm end-effector control.
- Ray Casting Mapping - Implements 2D ray casting techniques for grid map generation.
- Sampling-Based Planning - Demonstrates biased polar sampling techniques for robotic path planning.
