show

Visualize deep-learning-based CHOMP trajectory of rigid body tree

Since R2024a

Syntax

show(dlchomp)

show(dlchomp,optimtraj)

show(___,Parent=parentAx)

ax = show(___)

Description

The show object function shows one or more configuration trajectories in a Deep-Learning-Based Covariant Hamiltonian Optimization for Motion Planning (DLCHOMP) environment with obstacles. CHOMP is a gradient-descent based planner that plans and optimizes trajectories for smoothness and collision avoidance. For more information about CHOMP, see the manipulatorCHOMP or dlCHOMP object.

show(dlchomp) shows the rigid body tree in the home configuration of the rigid body tree and the spherical obstacles. The rigid body tree has its spherical approximation overlaid on top of the rigid body tree meshes.

show(dlchomp,optimtraj) shows the rigid body tree at each of the specified waypoints in the optimized trajectory.

show(___,Parent=parentAx) visualizes the DLCHOMP visualization on the specified axes.

ax = show(___) returns the axes that the DLCHOMP visualization was plotted onto.

Examples

Optimize Trajectory Using dlCHOMP

Download a pretrained dlCHOMP object for the KUKA LBR iiwa 7 robot.

dataZip = matlab.internal.examples.downloadSupportFile("rst/data/dlCHOMP/R2024a/","kukaIiwa7DLCHOMPTrained.zip");
dataFilePaths = unzip(dataZip);

Load the trainedDLCHOMP MAT file. The file contains the trained DLCHOMP optimizer, obstacles, and start and goal configurations.

load trainedDLCHOMP.mat

Warning: Cannot load an object of class 'dlCHOMPDatastore':
Its class cannot be found.

Add the obstacles to the dlCHOMP object and show the robot in the home configuration with the loaded obstacles.

trainedDLCHOMP.SphericalObstacles = unseenObstacles;
show(trainedDLCHOMP);
title(["Robot at Home Configuration","in Obstacle Environment"])
axis auto

Optimize trajectory between the start and goal configuration.

trainedDLCHOMP.RigidBodyTree.DataFormat = "column"

trainedDLCHOMP = 
  dlCHOMP with properties:

           RigidBodyTree: [1×1 rigidBodyTree]
    RigidBodyTreeSpheres: [11×1 table]
       SmoothnessOptions: [1×1 chompSmoothnessOptions]
           SolverOptions: [1×1 chompSolverOptions]
        CollisionOptions: [1×1 chompCollisionOptions]
      SphericalObstacles: [4×24 double]
              BPSEncoder: [1×1 bpsEncoder]
            NumWaypoints: 40
                 Network: [1×1 dlnetwork]
               NumInputs: [14 10000]
              NumOutputs: 266

[wpts,tpts,solninfo] = optimize(trainedDLCHOMP,unseenStart,unseenGoal);

Visualize the trajectory.

figure
a = show(trainedDLCHOMP,wpts);
title("Optimized Trajectory")
axis equal

Input Arguments

dlchomp — Deep-learning-based CHOMP optimizer

dlCHOMP object

Deep-learning-based CHOMP optimizer, specified as an dlCHOMP object.

optimtraj — DLCHOMP-optimized trajectory waypoints

M-by-N matrix

DLCHOMP-optimized trajectory waypoints, specified as an M-by-N matrix. M is the number of waypoints and N is the number of joints in the rigid body tree of dlchomp.

Specify this argument using the optimtraj output of the optimize function.

parentAx — Parent axes to plot trajectory visualization onto

Axes object

Parent axes to plot trajectory visualization onto, specified as an Axes object.

Output Arguments

ax — Axes graphic handle

Axes

Axes graphic handle, returned as an Axes object. This object contains the properties of the figure that you plot the DLCHOMP visualization onto.

Version History

Introduced in R2024a