Scribd Logo
Upload

Welcome to Scribd!

  • 2 views

    6. Pure Visual 2D Mapping and Navigation

    Uploaded by

    Minh Nhật Võ Thanh

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    6. Pure Visual 2D Mapping and Navigation

    Uploaded by

    Minh Nhật Võ Thanh
    2 views7 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    2 views7 pages

    6. Pure Visual 2D Mapping and Navigation

    Uploaded by

    Minh Nhật Võ Thanh

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    6.

    Pure visual 2D mapping navigation


    6. Pure visual 2D mapping navigation
    6.1. Introduction
    6.2. Use
    6.2.1. Map construction
    6.2.2. Controlling the robot
    6.2.3. Map saving
    6.2.4. Navigation
    6.3. Topics and services
    6.4. Configuration parameters
    6.5, TF transformation

    depthimage_to_laserscan: http://wiki.ros.org/depthimage_to_laserscan

    depthimage_to_laserscan source code: https://github.com/ros-perception/depthimage_to_lasersca


    n

    6.1. Introduction
    depthimage_to_laserscan takes a depth image (float encoded meters or preferably uint16
    encoded millimeters for OpenNI devices) and generates a 2D laser scan based on the provided
    parameters. depthimage_to_laserscan uses delayed subscription, which does not subscribe to
    image or camera information until a user scans.

    The depthimage_to_laserscan function package converts depth images into lidar data, and its
    mapping and navigation functions are the same as lidar. Note: The scanning range of the depth
    camera is not 360°.

    6.2. Use
    Note: Pure depth mapping navigation in this section does not work well and is not
    recommended.

    Note: When building a map, the slower the speed, the better the effect (note that the
    rotation speed should be slower). If the speed is too fast, the effect will be poor.

    According to different models, you only need to set the purchased model in [.bashrc], X1 (normal
    four-wheel drive) X3 (Mailun) Take X3 as an example

    #Raspberry Pi 5 master needs to enter docker first, please perform this step
    #If running the script into docker fails, please refer to ROS/07, Docker tutorial
    ~/run_docker.sh

    Open the [.bashrc] file

    sudo vim .bashrc

    Find the [ROBOT_TYPE] parameters and modify the corresponding car model

    export ROBOT_TYPE=X3 # ROBOT_TYPE: X1 X3 X3plus R2 X7


    6.2.1. Map construction

    Start command (robot side)

    roslaunch yahboomcar_nav astrapro_bringup.launch

    <PI5 needs to open another terminal to enter the same docker container

    Mapping command (robot side)

    roslaunch yahboomcar_nav yahboomcar_map.launch use_rviz:=false map_type:=gmapping

    [use_rviz] parameter: whether to enable rviz visualization.

    [map_type] parameter: Set the mapping algorithm [gmapping].

    Turn on the visual interface (virtual machine side)

    roslaunch yahboomcar_nav view_vision_mapping.launch


    6.2.2. Controlling the robot

    Keyboard controls robot movement

    rosrun teleop_twist_keyboard teleop_twist_keyboard.py # System integration


    roslaunch yahboomcar_ctrl yahboom_keyboard.launch # Custom

    Control the robot movement with the handle

    There may be some scattered points during the mapping process. If the mapping environment is
    well closed, relatively regular, and the movement is slow, the scattering phenomenon will be much
    smaller.

    6.2.3. Map saving

    rosrun map_server map_saver -f ~/yahboomcar_ws/src/yahboomcar_nav/maps/my_map #


    The first way
    bash ~/yahboomcar_ws/src/yahboomcar_nav/maps/map.sh # The second way

    The map will be saved to the ~/yahboomcar_ws/src/yahboomcar_nav/maps/ folder, a pgm image


    and a yaml file.

    map.yaml

    image: map.pgm
    resolution: 0.05
    origin: [-15.4,-12.2,0.0]
    Negate: 0
    occupied_thresh: 0.65
    free_thresh: 0.196

    Parameter analysis:
    image: The path of the map file, which can be an absolute path or a relative path.

    resolution: resolution of the map, meters/pixel

    Origin: 2D pose (x, y, yaw) in the lower left corner of the map. The yaw here is rotated
    counterclockwise (yaw=0 means no rotation). Many parts of the current system ignore the
    yaw value.

    negate: whether to reverse the meaning of white/black and free/occupied (the interpretation
    of the threshold is not affected)

    occupied_thresh: Pixels with an occupation probability greater than this threshold will be
    considered fully occupied.

    free_thresh: Pixels with occupancy probability less than this threshold will be considered
    completely free.

    6.2.4. Navigation

    Start command (robot side)

    roslaunch yahboomcar_nav astrapro_bringup.launch

    <PI5 needs to open another terminal to enter the same docker container

    Navigation commands (robot side)

    roslaunch yahboomcar_nav yahboomcar_navigation.launch use_rviz:=false map:=house

    [use_rviz] parameter: whether to enable rviz visualization.

    [map_type] parameter: Set the mapping algorithm [gmapping].

    Turn on the visual interface (virtual machine side)

    roslaunch yahboomcar_nav view_navigate.launch

    1. Single point navigation


    Use the [2D Pose Estimate] of the [rviz] tool to set the initial pose until the position of the car
    in the simulation is consistent with the position of the actual car.

    Click [2D Nav Goal] of the [rviz] tool, and then select a target point on the map where there
    are no obstacles. Release the mouse to start navigation. Only one target point can be
    selected, and it will stop when it is reached.

    2. Multi-point navigation

    Same as the first step of single-point navigation, first set the initial pose of the car.

    Click [Publish Point] of the [rviz] tool, and then select the target point on the map where there
    are no obstacles. Release the mouse to start navigation. You can click [Publish Point] again,
    and then select the point, and the robot will click on it. Cruising between points.

    When using the [2D Pose Estimate] tool of the [rviz] tool to set the initial pose of the car, the
    multi-point navigation function is automatically canceled.

    6.3. Topics and services

    Subscription
    Type Description
    topic

    Input image. This can be in floating point or


    raw uint16 format. For OpenNI devices,
    uint16 is the native representation and is
    more efficient to handle. This is usually
    image sensor_msgs/Image /camera/depth/image_raw. If your image is
    distorted, you should remap this theme to
    image_rect. OpenNI cameras typically have
    very little distortion, so correction can be
    skipped for this application.

    Camera information for the associated


    camera_info sensor_msgs/CameraInfo
    image.

    Post Topic Type Description

    Output laser scan. and will output a range


    scan sensor_msgs/LaserScan
    array containing NAN and +-INF.

    Node view

    rqt_graph
    6.4. Configuration parameters

    Parameters Type Default value Description

    Number of rows of pixels used to


    generate the laser scan. For each
    scan_height int 1 pixel column, the scan returns the
    minimum value of the vertically
    centered pixel in the image.

    Scan interval time (seconds).


    Typically, a rate of 1.0/frame. This
    scan_time double 1/30.0Hz (0.033s) value is not easily calculated from
    consecutive messages and is
    therefore set correctly by the user.

    The minimum range returned in


    range_min double 0.45m meters. Ranges smaller than this
    value will be output as -Inf.

    The maximum range returned in


    range_max double 10.0m meters. Ranges larger than this
    value will be output as +Inf.

    Laser scanning frame id. For point


    clouds from Z-forward "optical"
    output_frame_id str camera_depth_frame frames, this value should be set to
    the corresponding frames in X-
    forward and Z-up
    6.5, TF transformation

    Required TF
    Description
    transformation

    The transformation between the laser radar coordinate system and


    laser-->base_link the base coordinate system is generally published by
    robot_state_publisher or static_transform_publisher

    Transformation between the map coordinate system and the robot


    base_link-->odom
    odometer coordinate system, estimating the robot's pose in the map

    Released TF
    Description
    Transform

    Transformation between the map coordinate system and the robot's


    map-->odom
    odometry coordinate system, estimating the robot's pose in the map

    View tf tree

    rosrun rqt_tf_tree rqt_tf_tree

    You might also like