Planning and Control

Vehicle costmaps, optimal RRT* path planning, lateral and longitudinal controllers

Automated Driving Toolbox™ provides several features that support path planning and vehicle control.

To plan driving paths, you can use a vehicle costmap and the optimal rapidly exploring random tree (RRT*) motion-planning algorithm. You can also check the validity of the path, smooth the path, and generate a velocity profile along the path.
To design vehicle control systems, you can use lateral and longitudinal controllers that enable autonomous vehicles to follow a planned trajectory.

Functions

Vehicle Costmaps

`vehicleCostmap`	Costmap representing planning space around vehicle
`vehicleDimensions`	Store vehicle dimensions
`checkFree`	Check vehicle costmap for collision-free poses or points
`checkOccupied`	Check vehicle costmap for occupied poses or points
`getCosts`	Get cost value of cells in vehicle costmap
`setCosts`	Set cost value of cells in vehicle costmap
`inflationCollisionChecker`	Collision-checking configuration for costmap based on inflation

Path Planning

`pathPlannerRRT`	Configure RRT* path planner
`plan`	Plan vehicle path using RRT* path planner
`checkPathValidity`	Check validity of planned vehicle path
`driving.Path`	Planned vehicle path
`interpolate`	Interpolate poses along planned vehicle path
`smoothPathSpline`	Smooth vehicle path using cubic spline interpolation

Vehicle Control

lateralControllerStanley Compute steering angle command for path following by using Stanley method

Blocks

Path Smoother Spline	Smooth vehicle path using cubic spline interpolation
Velocity Profiler	Generate velocity profile of vehicle path given kinematic constraints
Lateral Controller Stanley	Control steering angle of vehicle for path following by using Stanley method
Longitudinal Controller Stanley	Control longitudinal velocity of vehicle by using Stanley method

Topics

Lateral Control Tutorial
Control the steering angle of a vehicle following a planned path and perform lane changing.
Code Generation for Path Planning and Vehicle Control
Generate C++ code for a path planning and vehicle control algorithm, and verify the code using software-in-the-loop simulation.

Featured Examples

Create Occupancy Grid Using Monocular Camera and Semantic Segmentation

Estimate free space and create an occupancy grid using semantic segmentation and deep learning.

Open Live Script

Traffic Light Negotiation

Design and test decision logic for negotiating a traffic light at an intersection.

Open Example

Highway Lane Change Planner and Controller

Design and test the planner and controller components of a lane change maneuver system designed for highway driving.

Open Example

Generate Code for Highway Lane Change Planner

Design, test, and generate C++ code for a lane change planner for highway driving. This example closely follows the Highway Trajectory Planning Using Frenet Reference Path example. In this example, you:

Open Example

Automate Testing for Highway Lane Change

Automate the testing of the components and generated code for highway lane change application.

Open Example

Highway Trajectory Planning Using Frenet Reference Path

Plan a local trajectory in a highway driving scenario by using a reference path in Frenet coordinates and a dynamic list of obstacles.

Open Live Script

Object Tracking and Motion Planning Using Frenet Reference Path

动态重新计划一个自治veh的运动icle 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.

Open Live Script

Motion Planning in Urban Environments Using Dynamic Occupancy Grid Map

Perform dynamic replanning in an urban driving scene by using a grid-based tracker.

Open Live Script

Generate Code for Highway Lane Following Controller

Test the highway lane following controller and generate C++ code for real-time applications on a prebuilt 3D scene from the Unreal Engine® driving simulation environment.

Open Example

Automate Testing for Highway Lane Following Controller

Automate the testing of a lane following controller and generated code for highway lane following application.

Open Example