モーション プランニング

この例では、Rapidly-exploring Random Tree (RRT) アルゴリズムを使用して、既知のマップでビークルのパスを計画する方法を説明します。カスタム状態空間により、特殊なビークル制約も適用されます。カスタム状態空間とパス検証オブジェクトを使って、独自のプランナーを任意のナビゲーション アプリケーション用に調整できます。

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。

Perceive surround-view information and use it to design an automated lane change maneuver system for highway driving scenarios.

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.

Find global path-planning solutions for systems with complex kinematics using the kinematics-based planner, plannerControlRRT. The example is organized into three primary sections:

Dynamically replan the motion of an autonomous vehicle based on the estimate of the surrounding environment. You use a Frenet reference path and a joint probabilistic data association (JPDA) tracker to estimate and predict the motion of other vehicles on the highway. Compared to the Highway Trajectory Planning Using Frenet Reference Path example, you use these estimated trajectories from the multi-object tracker in this example instead of ground truth for motion planning.

Optimize the path for a car-like robot by maintaining a smooth curvature and a safe distance from the obstacles in a parking lot.

Choose the best 2-D path planner for a differential drive robot in a warehouse environment from the available path planners. Use the plannerBenchmark object to benchmark the path planners plannerRRT, plannerRRTStar, plannerBiRRT, plannerPRM, and plannerHybridAstar on the warehouse environment with the randomly chosen start and goal poses. Compare the path planners based on their ability to find a valid path, clearance from the obstacles, time taken to initialize a planner, time taken to find a path, length of the path, and smoothness of the path. A suitable planner is chosen based on the performance of each path planner on the above mentioned metrics.

Process and store 2.5-D information, and presents various techniques for using it for an offroad path planner.

Use a Hybrid A* planner to plan a path to a narrow parking space, while accounting for the shape of a car-like robot.

Plan a path for a mobile robot to a goal region using a rapidly exploring random tree (RRT) path planner. In this example, you can define a custom goal region as a 2-D polygon, and then plan a path to it.

Combine uniform sampling and Gaussian sampling approaches for motion planning in narrow passages and wide spaces.

Create a deep learning-based sampler using Motion Planning Networks to speed up path planning using sampling-based planners like RRT (rapidly-exploring random tree) and RRT*. For information about Motion Planning Networks (MPNet) for state space sampling, see Get Started with Motion Planning Networks.

The example shows how to use sampling-based planners such as RRT (rapidly-exploring random tree) and RRT* with Motion Planning Networks (MPNet), deep-learning-based sampler to find optimal paths efficiently.

Use navGraph and plannerAStar to find a path through rough terrain while accounting for vehicle-based requirements and constraints.