Registration and SLAM

Register point clouds using algorithms, such as ICP or NDT, or feature-based techniques, implement SLAM algorithms with 3-D point cloud data or 2-D lidar scans

Point cloud registration is the process of aligning two 3-D point clouds of the same scene into a common coordinate system. Lidar Toolbox™ functions enable you to register point clouds to one another using local and global methods, including iterative closest point (ICP), lidar odometry and mapping (LOAM), normal-distributions transform (NDT), fast global registration (FGR), and coherent point drift (CPD). You can also use the Lidar Registration Analyzer app to interactively register point clouds and compare the results of different registration methods, tune parameters, and add preprocessing steps. For more information, see Get Started with the Lidar Registration Analyzer App.

Simultaneous localization and mapping (SLAM) is the process of calculating the position and orientation of a vehicle or robot with respect to its surroundings while simultaneously building a map of that environment. The toolbox supports graph-based 3-D SLAM using point cloud data. For more information, see Implement Point Cloud SLAM in MATLAB.

You can also perform SLAM with 2-D lidar scans by using the lidarscanmap object. For more information, see Build Map from 2-D Lidar Scans Using SLAM.

Apps

Lidar Registration AnalyzerAnalyze results of lidar point cloud registration (Since R2024a)

Functions

expand all

pctransformTransform 3-D point cloud
rigidtform3d3-D rigid geometric transformation (Since R2022b)
affinetform3d3-D affine geometric transformation (Since R2022b)
simtform3d3-D similarity geometric transformation (Since R2022b)
transltform3d3-D translation geometric transformation (Since R2022b)
estgeotform3dEstimate 3-D geometric transformation from matching point pairs (Since R2022b)
undistortEgoMotionUndistort point cloud affected by ego motion (Since R2023a)
pcalignAlign array of point clouds (Since R2020b)
pcmergeMerge two 3-D point clouds
pccatConcatenate 3-D point cloud array (Since R2020b)

Detect Features

detectISSFeaturesDetect ISS feature points in point cloud (Since R2022a)
detectLOAMFeaturesDetect LOAM feature points in point cloud (Since R2022a)
LOAMPointsObject for storing LOAM feature points (Since R2022a)
detectRectangularPlanePointsDetect rectangular plane of specified dimensions in point cloud (Since R2020b)
detectRoadAnglesDetect road angles in point cloud (Since R2022b)

Extract Features

extractFPFHFeaturesExtract fast point feature histogram (FPFH) descriptors from point cloud (Since R2020b)
extractEigenFeaturesExtract eigenvalue-based features from point cloud segments (Since R2021a)
eigenFeatureObject for storing eigenvalue-based features (Since R2021a)

Match Features

pcmatchfeaturesFind matching features between point clouds (Since R2020b)
pcregistericpRegister two point clouds using ICP algorithm
pcregisterloamRegister two point clouds using LOAM algorithm (Since R2022a)
pcregisterfgrRegister two point clouds using FGR algorithm (Since R2022b)
pcregisterndtRegister two point clouds using NDT algorithm
pcregistercorrRegister two point clouds using phase correlation (Since R2020b)
pcregistercpdRegister two point clouds using CPD algorithm

Localization and Mapping

lidarscanmapSimultaneous localization and mapping using 2-D lidar scans (Since R2022b)
addScanAdd 2-D lidar scan to map (Since R2022b)
lidarScanCreate object for storing 2-D lidar scan (Since R2020b)

Pose Optimization

poseGraphCreate 2-D pose graph from lidar scan map (Since R2022b)
updateScanPosesUpdate absolute poses of 2-D lidar scans (Since R2022b)
findPoseFind absolute pose of 2-D lidar scan in map (Since R2022b)
matchScansEstimate pose between two laser scans (Since R2020b)
matchScansGridEstimate pose between two lidar scans using grid-based search (Since R2020b)
matchScansLineEstimate pose between two laser scans using line features (Since R2020b)
transformScanTransform laser scan based on relative pose (Since R2021a)

Loop Closure Detection

detectLoopClosureDetect loop closure in 2-D lidar scan map (Since R2022b)
addLoopClosureAdd loop closure to map (Since R2022b)
deleteLoopClosureDelete loop closure between 2-D lidar scans (Since R2022b)

Localization and Mapping

pcmaploamCreate map of LOAM feature points for map building (Since R2022b)
pcmapndtLocalization map based on normal distributions transform (NDT) (Since R2021a)
pcmapsegmatchMap of segments and features for localization and loop closure detection (Since R2021a)

Pose Optimization

pcviewsetManage data for point cloud based visual odometry and SLAM
createPoseGraphCreate pose graph
optimizePosesOptimize absolute poses using relative pose constraints

Loop Closure Detection

scanContextDistanceDistance between scan context descriptors (Since R2020b)
scanContextDescriptorExtract scan context descriptor from point cloud (Since R2020b)
scanContextLoopDetectorDetect loop closures using scan context descriptors (Since R2021b)

Topics

Featured Examples

Register Point Clouds Using Global and Local Registration Techniques

Register Point Clouds Using Global and Local Registration Techniques

Combine global and local registration techniques to align significantly misaligned point clouds.

Simulate Safe Landing of UAV in Unexplored Environment Using Unreal Engine

Simulate Safe Landing of UAV in Unexplored Environment Using Unreal Engine

Simulate the safe landing operation of an Unmanned Aerial Vehicle (UAV) in an unexplored environment.

Motion Compensation in 3-D Lidar Point Clouds Using Sensor Fusion

Motion Compensation in 3-D Lidar Point Clouds Using Sensor Fusion

Compensate point cloud distortion due to ego vehicle motion by fusing data from Global Positioning System (GPS) and inertial measurement unit (IMU) sensors. The goal of this example is to compensate the distortion in the point cloud data and recreate the surroundings accurately.

Build a Map with Lidar Odometry and Mapping (LOAM) Using Unreal Engine Simulation

Build a Map with Lidar Odometry and Mapping (LOAM) Using Unreal Engine Simulation

Build a map with the lidar odometry and mapping (LOAM) [1] algorithm by using synthetic lidar data from the Unreal Engine® simulation environment. In this example, you learn how to:

Map Indoor Area Using Lidar SLAM and Factor Graph

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.

(Navigation Toolbox)

Build Map and Localize Using Segment Matching

Build Map and Localize Using Segment Matching

Build a map with lidar data and localize the position of a vehicle on the map using SegMatch [1], a place recognition algorithm based on segment matching.

Feature-Based Map Building from Lidar Data

Feature-Based Map Building from Lidar Data

Demonstrates how to process 3-D lidar data from a sensor mounted on a vehicle to progressively build a map. Such a map is suitable for automated driving workflows such as localization and navigation. These maps can be used to localize a vehicle within a few centimeters.

Aerial Lidar SLAM Using FPFH Descriptors

Aerial Lidar SLAM Using FPFH Descriptors

Demonstrates how to implement the simultaneous localization and mapping (SLAM) algorithm for aerial mapping using 3-D features. The goal of this example is to estimate the trajectory of a robot and create a point cloud map of its environment.

Build Occupancy Map from 3-D Lidar Data Using SLAM

Build Occupancy Map from 3-D Lidar Data Using SLAM

Demonstrates how to build a 2-D occupancy map from 3-D Lidar data using a simultaneous localization and mapping (SLAM) algorithm. This occupancy map is useful for localization and path planning for vehicle navigation. You can also use this map as a prebuilt map to incorporate sensor information.

Build Map from 2-D Lidar Scans Using SLAM

Build Map from 2-D Lidar Scans Using SLAM

Implement the SLAM algorithm on a series of 2-D lidar scans using scan processing and pose graph optimization (PGO). The goal of this example is to estimate the trajectory of the robot and build a map of the environment.

Collision Warning Using 2-D Lidar

Collision Warning Using 2-D Lidar

Detect obstacles and warn of possible collisions using 2-D lidar data.

Build a Map from Lidar Data Using SLAM on GPU

Build a Map from Lidar Data Using SLAM on GPU

Perform 3-D simultaneous localization and mapping (SLAM) using generated code on an NVIDIA® GPU.

(GPU Coder)

Code Generation for Map Building from Lidar Data Using SLAM

Code Generation for Map Building from Lidar Data Using SLAM

Generate C++ code for building a map from lidar data using the simultaneous localization and mapping (SLAM) algorithm.