build details

Show: section status errors & todos local changes recent changes last change in-page changes feedback controls

Lane following

Modified 2019-05-08 by Gianmarco

This is the description of lane following demo.

Joystick demo has been successfully launched.

Video of expected results

Modified 2019-05-08 by Gianmarco

The video is at https://vimeo.com/334931570.

Outcome of the lane following demo.

Duckietown setup notes

Modified 2019-04-02 by gibernas

Assumption about Duckietown:

  • A Duckietown with white and yellow lanes. No obstacles on the lane.
  • Layout conform to Duckietown Appearance Specifications (unknown ref opmanual_duckietown/dt-ops-appearance-specifications)
    previous warning next (8 of 14) index
    warning
    I will ignore this because it is an external link. 
    
     > I do not know what is indicated by the link '#opmanual_duckietown/dt-ops-appearance-specifications'.

    Location not known more precisely.

    Created by function n/a in module n/a.
  • Required tiles types: straight tile, turn tile
  • Configurated wireless network for communicating with Duckiebot.
  • Good consistent lighting, avoid natural lighting.

Duckiebot setup notes

Modified 2019-04-09 by gibernas

  • Make sure the camera is heading ahead.
  • Duckiebot in configuration DB18

Pre-flight checklist

Modified 2019-04-09 by gibernas

  • Turn on joystick (if applicable).
  • Turn on battery of the duckiebot.
  • Place duckiebot in lane so that enough of the lane lines are visible to the camera.
  • Verify you can ping your duckiebot over the network.
  • IMPORTANT Make sure no containers are running on the duckiebot which use either the camera or joystick. We will run these ROS nodes together in a new container.

Demo instructions

Modified 2018-06-22 by Andrea Censi

Start the demo containers

Modified 2020-07-28 by frank-qcd-qk

Running this demo requires almost all of the main Duckietown ROS nodes to be up and running. As these span 3 Docker images (dt-duckiebot-interface, dt-car-interface, and dt-core). The dt-duckiebot-interface and dt-car-interface container typically starts with robot startup. You will need to start dt-core manually.

First, check to make sure that dt-duckiebot-interface and dt-car-interface are running on your duckiebot via portainer, if not, do:

laptop $ dts duckiebot demo --demo_name duckiebot-interface --duckiebot_name DUCKIEBOT_NAME --package_name duckiebot_interface --image duckietown/dt-duckiebot-interface:daffy-arm32v7

laptop $ dts duckiebot demo --demo_name car-interface --duckiebot_name DUCKIEBOT_NAME --package_name car_interface --image duckietown/dt-car-interface:daffy-arm32v7

Then, we are ready to start the high-level pipeline for lane following:

laptop $ dts duckiebot demo --demo_name lane_following --duckiebot_name DUCKIEBOT_NAME --package_name duckietown_demos

You have to wait a while for everything to start working. While you wait, you can check in Portainer if all the containers started successfully and in their logs for any possible issues.

Make your Duckiebot drive autonomously!

Modified 2020-07-28 by frank-qcd-qk

If you have a joystick you can skip this next command, otherwise we need to run the keyboard controller:

laptop $ dts duckiebot keyboard_control DUCKIEBOT_NAME
Controls Joystick Keyboard
Start Lane Following R1 a
Stop Lane Following L1 s

Start the lane following. The Duckiebot should drive autonomously in the lane. Intersections and red lines are neglected and the Duckiebot will drive across them like it is a normal lane. You can regain control of the bot at any moment by stopping the lane following and using the (virtual) joystick. Resuming the demo is as easy as pressing the corresponding start button.

Et voilà! We are ready to drive around autonomously.

Visualize the detected line segments (optional)

Modified 2020-07-28 by frank-qcd-qk

This step is not neccessary but provides a nice visualization of the line segments that the Duckiebot detects.

For that, we need to make lane_filter_node publish all the image topics. To do that, you can use start_gui_tools to get a shell that is connected to the ROS system.

laptop $ dts start_gui_tools DUCKIEBOT_NAME

Then, set the ROS parameter verbose to true:

container $ rosparam set /DUCKIEBOT_NAME/line_detector_node/verbose true

so that line_detector_node will publish the image_with_lines.

For this part, you can also use no-vnc, or directly use any container that can communicate with the ROS system.

Now you can run rqt_image_view and select the /DUCKIEBOT_NAME/line_detector_node/image_with_lines and you should see something like this:

The video is at https://vimeo.com/334931437.

Outcome of the line detector node.

Extras

Modified 2019-09-29 by Aleksandar Petrov

Here are some additional things you can try:

  • Get a remote stream of your Duckiebot.
  • Try to change some of the ROS parameters to see how your Duckiebot’s behavior will change.

Troubleshooting

Modified 2018-10-20 by Russell

The duckiebot does not move

Modified 2019-05-08 by Gianmarco

  • Check if you can manually drive the duckiebot
  • Try re launching dts duckiebot keyboard_control hostname
  • Check if ROS messages are received on the robot on the hostname/joy topic

The Duckiebot does not stay in a straight lane

Modified 2018-10-20 by Russell

  • Check rqt_image_view and look at image_with_lines.
  • Check if you see enough segments. If not enough segments are visible, reset the Anti-Instagram filter.
  • Check if you see more segments and the color of the segments are according to the color of the lines in Duckietown
  • Check your camera calibrations are good.

The Duckiebot does not drive nicely through intersections

Modified 2018-10-20 by Russell

This feature is not implemented for this demo. The duckiebot assumes only normal lanes during this demo.

The Duckiebot cuts white line while driving on inner curves (avanced)

Modified 2019-09-27 by Aleksandar Petrov

Solution (advanced):

Set alternative controller gains. While running the demo on the Duckiebot use the following to set the gains to the alternative values:

laptop $ rosparam set /DUCKIEBOT_NAME/lane_controller_node/k_d -45

laptop $ rosparam set /DUCKIEBOT_NAME/lane_controller_node/k_theta -11

Those changes are only active while running the demo and need to be repeated at every start of the demo if needed. If this improved the performance of your Duckiebot, you should think about permenantly change the default values in your catkin_ws.