Main Content

モーション プランニング

パス メトリクス、RRT パス プランナー、パス追従

モーション プランニングを使用して、環境内を通るパスを計画します。RRT、RRT*、ハイブリッド A* などの一般的なサンプリングベースのプランナーを使用するか、独自のカスタマイズ可能なパス計画インターフェイスを指定することができます。パス メトリクスと状態検証を使用して、パスが有効であり障害物とのクリアランスまたは滑らかさが適切であることを確認します。単純追跡と Vector Field Histogram アルゴリズムを使用して、パスを追従し障害物を回避します。

関数

すべて展開する

navPath計画されたパス
navPathControlPath representing control-based kinematic trajectory
dubinsConnectionDubins path connection type
dubinsPathSegmentDubins path segment connecting two poses
reedsSheppConnectionReeds-Shepp path connection type
reedsSheppPathSegmentReeds-Shepp path segment connecting two poses
pathmetricsInformation for path metrics
clearanceMinimum clearance of path
isPathValidDetermine if planned path is obstacle free
smoothnessSmoothness of path
showVisualize path metrics in map environment
stateSpaceSE2SE(2) state space
stateSpaceSE3SE(3) state space
stateSpaceDubinsState space for Dubins vehicles
stateSpaceReedsSheppState space for Reeds-Shepp vehicles
validatorOccupancyMap2-D グリッド マップに基づいた状態バリデーター
validatorOccupancyMap3DState validator based on 3-D grid map
validatorVehicleCostmap2-D コストマップに基づいた状態バリデーター
isStateValidCheck if state is valid
isMotionValidCheck if path between states is valid
nav.StatePropagatorState propagator for control-based planning
mobileRobotPropagatorState propagator for wheeled robotic systems
distanceEstimate cost of propagating to target state
propagatePropagate system without validation
propagateWhileValidPropagate system and return valid motion
sampleControlGenerate control command and duration
setupSet up the mobile robot state propagator
plannerRRTCreate an RRT planner for geometric planning
plannerRRTStarオプションの RRT パス プランナー (RRT*) の作成
plannerBiRRTCreate bidirectional RRT planner for geometric planning
plannerControlRRTControl-based RRT planner
plannerAStarGridA* path planner for grid map
plannerHybridAStarハイブリッド A* パス プランナー
plannerPRMCreate probabilistic roadmap path planner
plannerBenchmarkBenchmark path planners using generated metrics
optimizePathOptionsCreate optimization options for optimizePath function
optimizePathOptimize path while maintaining safe distance from obstacle
referencePathFrenetSmooth reference path fit to waypoints
trajectoryGeneratorFrenetFind optimal trajectory along reference path
trajectoryOptimalFrenetFind optimal trajectory along reference path
createPlanningTemplateCreate sample implementation for path planning interface
nav.StateSpaceCreate state space for path planning
nav.StateValidatorCreate state validator for path planning
controllerVFHAvoid obstacles using vector field histogram
controllerPurePursuit一連のウェイポイントに追従するコントローラーの作成
dynamicCapsuleListDynamic capsule-based obstacle list
dynamicCapsuleList3DDynamic capsule-based obstacle list
addEgoAdd ego bodies to capsule list
addObstacleAdd obstacles to 2-D capsule list
checkCollisionCheck for collisions between ego bodies and obstacles
egoGeometryGeometric properties of ego bodies
egoPosePoses of ego bodies
obstacleGeometryGeometric properties of obstacles
obstaclePosePoses of obstacles

ブロック

Pure Pursuit線形速度と角速度の制御コマンド
Vector Field HistogramAvoid obstacles using vector field histogram

トピック

  • ナビゲーションのためのパス プランニング アルゴリズムの選択

    さまざまなパスおよびモーション プランニング アルゴリズムの利点に関する詳細。

  • RRT を使用したモバイル ロボットのパスの計画

    この例では、Rapidly-exploring Random Tree (RRT) アルゴリズムを使用して、既知のマップで車両のパスを計画する方法を説明します。

  • Moving Furniture in a Cluttered Room with RRT

    This example shows how to plan a path to move bulky furniture in a tight space avoiding poles. This example shows a workflow of the "Piano Mover's Problem", which is used for testing path planning algorithms with constrained state spaces. This example uses the plannerRRTStar object to implement a custom optimized rapidly-exploring tree (RRT*) algoirthm. Provided example helpers illustrate how to define custom state spaces and state valdiation for any motion planning application.

  • Motion Planning with RRT for a Robot Manipulator

    Plan a grasping motion for a Kinova Jaco Assistive Robotics Arm using the rapidly-exploring random tree (RRT) algorithm. This example uses a plannerRRTStar object to sample states and plan the robot motion. Provided example helpers illustrate how to define custom state spaces and state validation for motion planning applications.

  • 屋内マップでの動的再計画

    この例では、距離計と A* パス プランナーを使用して、倉庫のマップで動的な再計画を行う方法を説明します。

  • Highway Lane Change

    This example shows how to perceive surround-view information and use it to design an automated lane change maneuver system for highway driving scenarios.

  • Highway Trajectory Planning Using Frenet Reference Path

    This example demonstrates how to plan a local trajectory in a highway driving scenario. This example uses a reference path and dynamic list of obstacles to generate alternative trajectories for an ego vehicle. The ego vehicle navigates through traffic defined in a provided driving scenario from a drivingScenario object. The vehicle alternates between adaptive cruise control, lane changing, and vehicle following maneuvers based on cost, feasibility, and collision-free motion.

  • Optimal Trajectory Generation for Urban Driving

    This example shows how to perform dynamic replanning in an urban scenario using trajectoryOptimalFrenet.

  • Motion Planning in Urban Environments Using Dynamic Occupancy Grid Map

    This example shows you how to perform dynamic replanning in an urban driving scene using a Frenet reference path. In this example, you use a dynamic occupancy grid map estimate of the local environment to find optimal local trajectories.

  • Path Following with Obstacle Avoidance in Simulink®

    This example shows you how to use Simulink to avoid obstacles while following a path for a differential drive robot. This example uses ROS to send and receive information from a MATLAB®-based simulator. You can replace the simulator with other ROS-based simulators such as Gazebo®.

  • Obstacle Avoidance with TurtleBot and VFH

    This example shows how to use ROS Toolbox and a TurtleBot® with vector field histograms (VFH) to perform obstacle avoidance when driving a robot in an environment. The robot wanders by driving forward until obstacles get in the way. The controllerVFH object computes steering directions to avoid objects while trying to drive forward.

  • Vector Field Histogram

    VFH algorithm details and tunable properties.

  • 単純追跡コントローラー

    単純追跡コントローラーの機能とアルゴリズムの詳細。