Skip to content

The visual-based navigation stack, AdMALL project, University of Shffield

Notifications You must be signed in to change notification settings

kevinlisun/jaguar_nav

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 

Repository files navigation

Video demos

drawing drawing

drawing drawing

drawing drawing

YouTube

Day-to-Night

LastmileDelivery

FieldTest

A Brief Description

  • cameleon_teleop: joystick control.
  • jaguar4x4_driver: drrobot jaguar 4x4 robot driver.
  • stroll_bearnav: V-T&R, visual teach and repeat.
  • zed-ros-wrapper: ZED stereo camera ros wrapper.

Prerequsites

Environment

  • Ubuntu 16.04 + ROS kinetic

Install jaguar_nav

  1. Create a catkin workspace:

    $ mkdir ~/jaguar_ws/; cd ~/jaguar_ws/
    $ git clone https://github.com/kevinlisun/jaguar_nav.git src
    $ cd ~/jaguar_ws/src
    
  2. Pull the repositories:

    $ wstool update
    $ cd ..
    $ rosdep install --from-paths src --ignore-src -r -y
    
  3. Compile:

    $ catkin_make -DCMAKE_BUILD_TYPE=Release
    
  4. Add ROS workspace to the environment.

    Add source ~/jaguar_ws/devel/setup.bash to ~/.bashrc

Joystick Control

  1. Launch the robot (drivers and camera).
    $ roslaunch jaguar4x4_2014 robot.launch
    
  2. Launch the joystick control.
$ roslaunch cameleon_teleop cameleon_teleop.launch

Now you should be able to drive the robot using the joystick (you will need to hold the LB button).

Teach (Mapping)

  1. Launch the stroll-nav core and GUI.

    $ roslaunch stroll_bearnav stroll-core.launch
    $ roslaunch stroll_bearnav stroll-gui.launch
    
  2. Input the file name in the "Mapper" window and click "SEND GOAL". Now you should be able to control the robot using "up down left right", and the robot will move with a constant and for continouly maneuver, you should press the button multiple times rather than hold it (you should NOT hold the LB button otherwise will switch to joystick control).

  3. Press the LB button to pause or intervene. Press button "A" on joystick to complete the mapping session and save the map.

Repeat (Autonomous Navigation)

  1. Load the "map" using the "loadMap" GUI. This may takes a while.
  2. Set the traversals: 1 and click "SEND GOAL".

You probably will need to give the robot an initial speed by pressing "up" button several times, then the robot should be able to navigate autonomously.

About

The visual-based navigation stack, AdMALL project, University of Shffield

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published