12: Follow Bot
Adding perception to our robot algorithms

Introduction

• How can the robot follow lines on the ground?
  • Acquire images
  • Filter the images
  • Steer the robot

Acquiring Images

• Message: sensor_msgs/Image
• Run Gazebo to simulate a robot with a camera
• Since the TB3 Waffle has a camera, we will use those models, and then run gazebo

$ export TURTLEBOT3_MODEL="waffle"
$ export TB3_MODEL="waffle"
$ roslaunch turtlebot3_gazebo turtlebot3_world.launch
$ rostopic list | grep /camera

• Note all the camera related topics being published
• The image itself can be found under /camera/rgb/image_raw
• ../compressed is good for sending the images over wifi
• ../theora applies even more compression

Look at image

• Lets visualize the image
• Choose from each of the topics relating to the camera
• Move the robot in Gazebo and watch the picture change

$ rqt_image_view

Run the simplest program

• $ /follower.py
• We can see the new node subscribing to the topic:

$ rosrun
$ rosnode info follower
--------------------------------------------------------------------------------
Node [/follower]
Publications: 
 * /rosout [rosgraph_msgs/Log]

Subscriptions: 
 * /camera/rgb/image_raw [sensor_msgs/Image]
 * /clock [rosgraph_msgs/Clock]

Services: 
 * /follower/get_loggers
 * /follower/set_logger_level


contacting node http://10.0.0.95:39103/ ...
Pid: 17179
Connections:
 * topic: /rosout
    * to: /rosout
    * direction: outbound
    * transport: TCPROS
 * topic: /clock
    * to: /gazebo (http://10.0.0.95:42857/)
    * direction: inbound
    * transport: TCPROS
 * topic: /camera/rgb/image_raw
    * to: /gazebo (http://10.0.0.95:42857/)
    * direction: inbound
    * transport: TCPROS

• First section is information determined from roscore about what /follower is doing
• Second section is information directly from the /follower node about it’s connections
  • We see that it is publishing to /rosout
  • And is subscribed to /clock (from gazebo)
  • And /camera/rgb/image_raw (from gazebo too)
• Lets find out the frame rate (simulated by gazebo)

rostopic hz /camera/rgb/image_raw
subscribed to [/camera/rgb/image_raw]
WARNING: may be using simulated time
average rate: 10.204
	min: 0.019s max: 0.131s std dev: 0.03037s window: 10

• So, we are receiving about 10 images per second
• Which is why my computer is so slow :)

Race Course

• Load a new world into gazebo

roslaunch turtlebot3_gazebo turtlebot3_autorace.launch

• You will see in gazebo, a TB3 Waffle on a little racetrack
• Here’s the track, and the view from the camera:

• Our goal is to detect the line using OpenCV, so we can then actually follow it
• Technique will be simplistic: filter a block of rows by image color and drive the robot towards the center of the pixels that pass the filte
• Note that this will fail in many normal cases!