Localization

Simultaneous localization and mapping, map building, odometry

Use simultaneous localization and mapping (SLAM) algorithms to build maps surrounding the ego vehicle based on visual or lidar data. Use visual-inertial odometry to estimate the pose (position and orientation) of a vehicle based on data from onboard sensors such as inertial measurement units (IMUs).

Functions

expand all

Rotations

`rigid3d`	3-D rigid geometric transformation
`quaternion`	Create a quaternion array
`dist`	Angular distance in radians
`rotateframe`	Quaternion frame rotation
`rotatepoint`	Quaternion point rotation
`rotmat`	Convert quaternion to rotation matrix
`rotvec`	Convert quaternion to rotation vector (radians)
`rotvecd`	Convert quaternion to rotation vector (degrees)
`parts`	Extract quaternion parts
`euler`	Convert quaternion to Euler angles (radians)
`eulerd`	Convert quaternion to Euler angles (degrees)
`compact`	Convert quaternion array to N-by-4 matrix

Visual SLAM

`imageviewset`	Manage data for structure-from-motion, visual odometry, and visual SLAM
`optimizePoses`	Optimize absolute poses using relative pose constraints
`createPoseGraph`	Create pose graph
`relativeCameraPose`	Compute relative rotation and translation between camera poses
`triangulate`	3-D locations of undistorted matching points in stereo images
`bundleAdjustment`	Refine camera poses and 3-D points
`bundleAdjustmentMotion`	Refine camera pose using motion-only bundle adjustment
`bundleAdjustmentStructure`	Refine 3-D points using structure-only bundle adjustment

Point Cloud SLAM

`pcviewset`	Manage data for point cloud based visual odometry and SLAM
`optimizePoses`	Optimize absolute poses using relative pose constraints
`createPoseGraph`	Create pose graph
`scanContextDistance`	Distance between scan context descriptors
`scanContextDescriptor`	Extract scan context descriptor from point cloud
`pctransform`	Transform 3-D point cloud
`pcalign`	Align an array point clouds
`pcregistercorr`	Register two point clouds using phase correlation
`pcregistercpd`	Register two point clouds using CPD algorithm
`pcregistericp`	Register two point clouds using ICP algorithm
`pcregisterndt`	Register two point clouds using NDT algorithm
`pcmapndt`	Localization map based on normal distributions transform (NDT)

Topics

Rotations, Orientations, and Quaternions for Automated Driving

Quaternions are four-part hypercomplex numbers that are used to describe three-dimensional rotations and orientations. Learn how to use them for automated driving applications.

Visual SLAM Overview

Understand visual simultaneous localization and mapping (SLAM) workflow.

Monocular Visual Simultaneous Localization and Mapping

Visual simultaneous localization and mapping (vSLAM).

Build a Map from Lidar Data

Process 3-D lidar sensor data to progressively build a map, with assistance from inertial measurement unit (IMU) readings.

Build a Map from Lidar Data Using SLAM

Process lidar data to build a map and estimate a vehicle trajectory using simultaneous localization and mapping.

Build Occupancy Map from 3-D Lidar Data Using SLAM

Build a 2-D Occupancy map from 3-D Lidar data using a simultaneous localization and mapping (SLAM) algorithm.

Point Cloud SLAM Overview

Understand point cloud registration and mapping workflow.

Build Map and Localize Using Segment Matching (Lidar Toolbox)

This example shows how to build a map with lidar data and localize the position of a vehicle on the map using SegMatch [1] (Lidar Toolbox), a place recognition algorithm based on segment matching.