Lidar Teach and Repeat

This page provides an offline demo of VT&R3 using data from a Waymo Honeycomb Lidar for teach and repeat navigation.

Prerequisites

• Install VT&R3
• Download sample datasets - download the utias_20210921_ros2bag dataset.

Follow this video. Commands are provided below. Note that, if you install VT&R3 in a docker container, then all commands should be run inside the container.

tmuxp load ${VTRSRC}/launch/offline_honeycomb_grizzly.launch.yaml

Note: we use tmux and tmuxp to launch and run VT&R3. They are useful tools that allow multiple terminal sessions to be launched and accessed simultaneously in a single window.

Data playback for teaching a path:

• Run these lines in a separate terminal after initializing the UI into teach mode.

  # replay the first ros2 bag
  source /opt/ros/galactic/setup.bash
  ros2 bag play ${VTRDATA}/utias_20210921_ros2bag/rosbag2_2021_09_21-16_25_56

Data playback for repeating a path:

• Run these lines in a separate terminal after teaching a path, entering repeat mode, and specifying repeat waypoints.

  # replay the second ros2 bag
  source /opt/ros/galactic/setup.bash
  ros2 bag play ${VTRDATA}/utias_20210921_ros2bag/rosbag2_2021_09_21-16_28_53

• Terminate VT&R3 (Ctrl-C once in terminal)

Note: after running the commands above, the resulting pose graph and local maps will be stored at ${VTRTEMP}/lidar. Unless you clear this directory, launching VT&R3 again will automatically reload the pose graph and local maps (allowing you to perform more repeats using the same taught path).