Main Content

pcmapndt

Localization map based on normal distributions transform (NDT)

Since R2021a

    Description

    The pcmapndt object creates a normal distributions transform (NDT) map from a prebuilt point cloud map of the environment. The NDT map is a compressed, memory-efficient representation suitable for localization. The object converts the point cloud map into a set of voxels (3-D boxes), each represented by a 3-D normal distribution. Use the selectSubmap object function to select a submap within the map from a coarse position estimate. Use the findPose object function to localize the pose of the sensor based on the assembled map.

    Creation

    Description

    example

    ndtMap = pcmapndt(ptCloudMap,voxelSize) returns an NDT map from a point cloud map, ptCloudMap.

    Input Arguments

    expand all

    Point cloud map, specified as a pointCloud object. The pcmapndt object creates a normal distributions transform (NDT) map from the prebuilt map of the environment, specified by ptCloudMap.

    This property is read-only.

    Size of the voxels, specified as a scalar value in world units.

    Properties

    expand all

    This property is read-only.

    Currently selected submap, specified as a 6-element vector of the form [xmin,xmax ymin ymax zmin zmax] that describes the range of the submap along each axis. The elements of the vector describe the region of interest represented by the submap.

    This property is read-only.

    Size of the voxels, specified as a scalar value in world units.

    This property is read-only.

    Range of the map along the x-axis, specified as a 2-element vector of the form [xmin xmax].

    This property is read-only.

    Range of the map along the Y-axis, specified as a 2-element vector of the form [ymin ymax].

    This property is read-only.

    Range of the map along the z-axis, specified as a 2-element vector of the form [zmin zmax].

    This property is read-only.

    Mean value of each voxel, specified as an M-by-3 matrix. Each row of the matrix contains the [x y z] values for a voxel. M is the number of voxels.

    This property is read-only.

    Covariance of each voxel, specified as a 3-by-3-by-M array for M voxels.

    This property is read-only.

    Number of points in each voxel, specified as an M-by-1 vector for M voxels.

    Object Functions

    selectSubmapSelect submap within map
    isInsideSubmapCheck if query position is inside selected submap
    findPoseLocalize point cloud within map using normal distributions transform (NDT) algorithm
    showVisualize normal distributions transform (NDT) map

    Examples

    collapse all

    Load a point cloud view set, which was saved from a pcviewset object.

    data = load('vSetPointClouds.mat');
    vSet = data.vSet;

    Extract point clouds and absolute poses to build a map.

    ptClouds = vSet.Views.PointCloud;
    tforms   = vSet.Views.AbsolutePose;

    Create a point cloud map by aligning the point cloud scans using the absolute poses.

    ptCloudMap = pcalign(ptClouds,tforms);

    Create and visualize an NDT map from a point cloud map.

    voxelSize = 1;
    ndtMap = pcmapndt(ptCloudMap,voxelSize);
    figure
    show(ndtMap)
    view(2)     % Change viewing angle to top-view

    Load a normal distributions transform (NDT) map from a MAT file.

    data = load('ndtMapParkingLot.mat');
    ndtMap = data.ndtMapParkingLot;

    Load point cloud scans and pose estimates from a second MAT file.

    data = load('parkingLotData.mat');
    ptCloudScans = data.parkingLotData.ptCloudScans;
    initPoseEsts = data.parkingLotData.initPoseEsts;

    Display the NDT map.

    show(ndtMap)

    Change the viewing angle to top-view.

    view(2)

    Select the submap centered around the first estimate.

    center = initPoseEsts(1).Translation;
    sz = [70 50 20];
    ndtMap = selectSubmap(ndtMap,center,sz);

    Set the radius for visualization of the current location and the distance threshold to update the submap.

    radius = 0.5;
    distThresh = 15;

    Loop over the point clouds, localize them in the map, and update the selected submap as needed.

    numScans = numel(ptCloudScans);
      
    for n = 1:numScans
        ptCloud = ptCloudScans(n);
        initPose = initPoseEsts(n);
    
        poseTranslation = initPose.Translation;
        [isInside,distToEdge] = isInsideSubmap(ndtMap,poseTranslation);
            submapNeedsUpdate = ~isInside ...       % Current pose is outside submap
            || any(distToEdge(1:2) < distThresh);   % Current pose is close to submap edge
    
    if submapNeedsUpdate
        ndtMap = selectSubmap(ndtMap,poseTranslation,sz);
    end
    
    % Localize the point cloud scan in the map.
    currPose = findPose(ndtMap,ptCloud,initPose);
    
    % Display the position of the estimate as a circle.
    pos = [currPose.Translation(1:2) radius]; 
    showShape('circle',pos,'Color','r');
    
    % Pause to view the change.
    pause(0.05)
    end

    References

    Biber, P., and W. Strasser. “The Normal Distributions Transform: A New Approach to Laser Scan Matching.” In Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453) Vol. 3, 2743–48. Las Vegas, Nevada, USA: IEEE, 2003. https://doi.org/10.1109/IROS.2003.1249285.

    [1] Magnusson, Martin. "The Three-Dimensional Normal-Distributions Transform: An Efficient Representation for Registration, Surface Analysis, and Loop Detection." PhD thesis, Örebro universitet, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-8458 urn:nbn:se:oru:diva-8458.

    Extended Capabilities

    C/C++ Code Generation
    Generate C and C++ code using MATLAB® Coder™.

    Version History

    Introduced in R2021a