bat365 Homepage

SLAM

2-D and 3-D simultaneous localization and mapping

Simultaneous localization and mapping (SLAM) uses both Mapping and Localization and Pose Estimation algorithms to build a map and localize your vehicle in that map at the same time. Use lidarSLAM to tune your own SLAM algorithm that processes lidar scans and odometry pose estimates to iteratively build a map. Use buildMap to take logged and filtered data to create a map using SLAM. The SLAM Map Builder app lets you manually modify relative poses and align scans to improve the accuracy of your map.

Apps

SLAM Map Builder

Build 2-D grid maps using lidar-based SLAM (Since R2019b)

Functions

expand all

EKF SLAM

ekfSLAM Perform simultaneous localization and mapping using extended Kalman filter (Since R2021b)

LiDAR SLAM

`lidarSLAM`	Perform localization and mapping using lidar scans (Since R2019b)
`buildMap`	Build occupancy map from lidar scans (Since R2019b)

Pose Graphs

`poseGraph`	Create 2-D pose graph (Since R2019b)
`poseGraph3D`	Create 3-D pose graph (Since R2019b)
`poseGraphSolverOptions`	Solver options for pose graph optimization (Since R2020b)
`optimizePoseGraph`	Optimize nodes in pose graph (Since R2019b)
`trimLoopClosures`	Optimize pose graph and remove bad loop closures (Since R2020b)
`poseplot`	3-D pose plot (Since R2021b)

Factor Graph

`factorGraph`	Bipartite graph of factors and nodes (Since R2022a)
`factorGraphSolverOptions`	Solver options for factor graph (Since R2022a)
`importFactorGraph`	Import factor graph from g2o log file (Since R2022a)
`factorIMU`	Convert IMU readings to factor (Since R2022a)
`factorIMUParameters`	Factor IMU parameters (Since R2023a)
`factorGPS`	Factor for GPS measurement (Since R2022a)
`factorTwoPoseSE2`	Factor relating two SE(2) poses (Since R2022a)
`factorTwoPoseSE3`	Factor relating two SE(3) poses (Since R2022a)
`factorPoseSE2AndPointXY`	Factor relating SE(2) position and 2-D point (Since R2022b)
`factorPoseSE3AndPointXYZ`	Factor relating SE(3) position and 3-D point (Since R2022b)
`factorIMUBiasPrior`	Prior factor for IMU bias (Since R2022a)
`factorVelocity3Prior`	Prior factor for 3-D velocity (Since R2022a)
`factorPoseSE3Prior`	Full-state prior factor for SE(3) pose (Since R2022a)
`factorCameraSE3AndPointXYZ`	Factor relating SE(3) camera pose and 3-D point (Since R2023a)
`estimateGravityRotation`	Estimate gravity rotation using IMU measurements and factor graph optimization (Since R2023a)
`estimateGravityRotationAndPoseScale`	Estimate gravity rotation and pose scale using IMU measurements and factor graph optimization (Since R2023a)

Featured Examples

EKF-Based Landmark SLAM

Use the ekfSLAM object for a reliable implementation of landmark Simultaneous Localization and Mapping (SLAM) using the Extended Kalman Filter (EKF) algorithm and maximum likelihood algorithm for data association. In this example, you create a landmark map of the immediate surroundings of a vehicle and simultaneously track the path of the vehicle. Generate a trajectory by moving the vehicle using the noisy control commands, and form the map using the landmarks it encounters along the path. Correct the vehicle trajectory and landmark estimates by observing the landmarks again.

Open Live Script

Landmark SLAM Using AprilTag Markers

Combine robot odometry data and observed fiducial markers called AprilTags to better estimate the robot trajectory and the landmark positions in the environment. The example uses a pose graph approach and a factor graph approach, and compares the two graphs.

Open Live Script

Perform SLAM Using 3-D Lidar Point Clouds

Demonstrates how to implement the simultaneous localization and mapping (SLAM) algorithm on collected 3-D lidar sensor data using point cloud processing algorithms and pose graph optimization. The goal of this example is to estimate the trajectory of the robot and create a 3-D occupancy map of the environment from the 3-D lidar point clouds and estimated trajectory.

Open Live Script

Implement Simultaneous Localization And Mapping (SLAM) with Lidar Scans

Demonstrates how to implement the Simultaneous Localization And Mapping (SLAM) algorithm on a collected series of lidar scans using pose graph optimization. The goal of this example is to build a map of the environment using the lidar scans and retrieve the trajectory of the robot.

Open Live Script

Implement Online Simultaneous Localization And Mapping (SLAM) with Lidar Scans

Demonstrates how to implement the Simultaneous Localization And Mapping (SLAM) algorithm on lidar scans obtained from simulated environment using pose graph optimization. This example requires Simulink® 3D Animation™ and Navigation Toolbox™.

Open Live Script

Map Indoor Area Using Lidar SLAM and Factor Graph

Implement offline lidar SLAM on collected lidar scans to map an indoor area using a factor graph and lidar scan map.

Open Live Script