Mobile Robot Algorithm Design

Mapping, path planning, path following, state estimation

These Robotics System Toolbox™ algorithms focus on mobile robotics or ground vehicle applications. These algorithms help you with the entire mobile robotics workflow from mapping to planning and control. You can create maps of environments using occupancy grids, develop path planning algorithms for robots in a given environment, and tune controllers to follow a set of waypoints. Perform state estimation based on lidar sensor data from your robot.

Functions

expand all

Mapping

`binaryOccupancyMap`	Create occupancy grid with binary values
`getOccupancy`	Get occupancy value of locations
`inflate`	Inflate each occupied grid location
`move`	Move map in world frame
`occupancyMatrix`	Convert occupancy grid to matrix
`raycast`	Compute cell indices along a ray

Laser Scans

`lidarScan`	Create object for storing 2-D lidar scan
`plot`	Display laser or lidar scan readings
`removeInvalidData`	Remove invalid range and angle data
`transformScan`	Transform laser scan based on relative pose

Localization

`stateEstimatorPF`	Create particle filter state estimator
`initialize`	Initialize the state of the particle filter
`predict`	Predict state of robot in next time step
`correct`	Adjust state estimate based on sensor measurement
`getStateEstimate`	Extract best state estimate and covariance from particles

Path Planning and Following

`mobileRobotPRM`	Create probabilistic roadmap path planner
`findpath`	Find path between start and goal points on roadmap
`controllerPurePursuit`	Create controller to follow set of waypoints

Kinematic Motion Models

`ackermannKinematics`	Car-like steering vehicle model
`bicycleKinematics`	Bicycle vehicle model
`differentialDriveKinematics`	Differential-drive vehicle model
`unicycleKinematics`	Unicycle vehicle model

Blocks

Ackermann Kinematic Model	Car-like vehicle motion using Ackermann kinematic model
Bicycle Kinematic Model	Compute car-like vehicle motion using bicycle kinematic model
Differential Drive Kinematic Model	Compute vehicle motion using differential drive kinematic model
Unicycle Kinematic Model	Compute vehicle motion using unicycle kinematic model
Pure Pursuit	Linear and angular velocity control commands

Topics

Mapping and Path Planning

Occupancy Grids
Details of occupancy grid functionality and map structure.
Probabilistic Roadmaps (PRM)
How the PRM algorithm works and specific tuning parameters.
Path Planning in Environments of Different Complexity
This example demonstrates how to compute an obstacle-free path between two locations on a given map using the Probabilistic Roadmap (PRM) path planner.
Mapping with Known Poses
This example shows how to create a map of an environment using range sensor readings and robot poses for a differential drive robot.
Plan Path for a Differential Drive Robot in Simulink
This example demonstrates how to execute an obstacle-free path between two locations on a given map in Simulink®.

Motion Modeling

Mobile Robot Kinematics Equations
Learn details about mobile robot kinematics equations including unicycle, bicycle, differential drive, and Ackermann models.
Simulate Different Kinematic Models for Mobile Robots
This example shows how to model different robot kinematics models in an environment and compare them.

Robot Control

Pure Pursuit Controller
Pure Pursuit Controller functionality and algorithm details.
Path Following for a Differential Drive Robot
This example demonstrates how to control a robot to follow a desired path using a Robot Simulator.
Control a Differential Drive Robot in Gazebo with Simulink
This example shows how to control a differential drive robot in Gazebo co-simulation using Simulink.

State Estimation

Particle Filter Parameters
To use thestateEstimatorPFparticle filter, you must specify parameters such as the number of particles, the initial particle location, and the state estimation method.
Particle Filter Workflow
A particle filter is a recursive, Bayesian state estimator that uses discrete particles to approximate the posterior distribution of the estimated state.
Track a Car-Like Robot Using Particle Filter
Particle filter is a sampling-based recursive Bayesian estimation algorithm, which is implemented in thestateEstimatorPFobject.

Featured Examples

Mapping with Known Poses

Create a map of an environment using range sensor readings and robot poses for a differential drive robot. You create a map from range sensor readings that are simulated using the rangeSensor object. The differentialDriveKinematics motion model simulates driving the robot around the room based on velocity commands. The rangeSensor gives range readings based on the pose of the robot as it follows the path.

Open Live Script

Path Planning in Environments of Different Complexity

Demonstrates how to compute an obstacle-free path between two locations on a given map using the Probabilistic Roadmap (PRM) path planner. PRM path planner constructs a roadmap in the free space of a given map using randomly sampled nodes in the free space and connecting them with each other. Once the roadmap has been constructed, you can query for a path from a given start location to a given end location on the map.

Open Live Script

Execute Tasks for a Warehouse Robot

演示如何执行一个无障碍路径for a mobile robot between three locations on a given map. The robot is expected to visit the three locations in a warehouse: a charging station, loading station, and unloading location. The sequence in which these locations are visited is dictated by a scheduler. The scheduler gives each robot a goal pose to navigate to. The robot plans a path and uses a Pure Pursuit controller to follow the waypoints based on the current pose of the robot. The Differential Drive Kinematic Model block models the simplified kinematics, which takes the linear and angular velocities from the Pure Pursuit Controller. This example builds on top of the Plan Path for a Differential Robot in Simulink example.

Open Live Script

Control and Simulate Multiple Warehouse Robots

Control and simulate multiple robots working in a warehouse facility or distribution center. The robots drive around the facility picking up packages and delivering them to stations for storing or processing. This example builds on top of the Execute Tasks for a Warehouse Robot example, which drives a single robot around the same facility.

Open Live Script

Simulate a Mobile Robot in a Warehouse Using Gazebo

Simulate a warehouse robot in Gazebo. Gazebo enabled you to simulate a mobile robot that uses a range sensor, while executing certain tasks in a simulated environment. This example details how to use a simulator to apply the Execute Tasks for A Warehouse Robot example, where a robot delivers packages in a warehouse scenario. The robot makes use of the simulated range sensor in Gazebo to detect possible collisions with a dynamic environment and avoid them.

Open Live Script

A* Path Planning and Obstacle Avoidance in a Warehouse

An extension to the Simulate A Mobile Robot in a Warehouse using Gazebo example. The example shows to change the PRM path planner with an A* planner, and add a vector field histogram (VFH) algorithm to avoid obstacles.

Open Live Script

Avoid Obstacles Using Reinforcement Learning for Mobile Robots

Uses Deep Deterministic Policy Gradient (DDPG) based reinforcement learning to develop a strategy for a mobile robot to avoid obstacles. For a brief summary of the DDPG algorithm, see Deep Deterministic Policy Gradient Agents.

Open Live Script