Autonomous_Exploration is framework for exploration planning and mapping. It is based on Symbolic controller based approach, to tackle navigation and exploration while providing safety guarantees. It can be used to perform Autonomous Navigation (SMP) or Exploration.
Credits
- Video
Setup
For a short overview of the system check out our video on youtube.
Installation instructions for Linux.
Prerequisites
- If not already done so, install ROS (Desktop-Full is recommended).
Installation
-
Move to your catkin workspace:
cd ~/catkin_ws/src
-
Download repo using a SSH key or via HTTPS:
git clone https://github.com/FocasLab/autonomous_exploration
-
Install system dependencies:
sudo apt-get install python-wstool python-catkin-tools
-
Download and install turtlebot3 packages from
https://emanual.robotis.com/docs/en/platform/turtlebot3/simulation/#gazebo-simulation
or other Robot Simulation such as AgileX Limo, Clearpath Jackal, etc.
-
Compile and source:
catkin build autoexpl source ../devel/setup.bash
NOTE: This Package can be configured to be used with other robots (simulation or physical robot) with minimal changes. Here we use turtlebot3 to showcase a simple example.
After successful installation now we will launch a minimal example in on Turtlebot3 in a Maze environment.
roslaunch autoexpl_simulations autoexpl_world.launch world:=docker
roslaunch autoexpl_simulations autoexpl_slam.launch slam_methods:=karto
roslaunch autoexpl_ros autonomous_exploration.launch
NOTE: As discussed in the paper, this approach is computationally expensive, we recommend using a high spec'd system or run small experiments on small arena.
Recommended Specs ( equivalent or higher )
- Processor - Intel i7
- RAM - 16GB
- Graphics Card - 4GB
- OS - Ubuntu 20.04 with ROS Noetic