Skip to content

Autonomous Navigation Toolbox using Symbolic controller for safe navigation in unknown environments.

Notifications You must be signed in to change notification settings

JeelChatrola/autonomous_exploration

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Autonomous Exploration using Symbolic Motion Planner (SMP)

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.

Table of Contents

Credits

  • Video

Setup

Video

For a short overview of the system check out our video on youtube.

AutoExpl Demo

Installation

Installation instructions for Linux.

Prerequisites

  1. If not already done so, install ROS (Desktop-Full is recommended).

Installation

  1. Move to your catkin workspace:

    cd ~/catkin_ws/src
  2. Download repo using a SSH key or via HTTPS:

    git clone https://github.com/FocasLab/autonomous_exploration
  3. Install system dependencies:

    sudo apt-get install python-wstool python-catkin-tools
  4. 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.

  5. 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.

Example

After successful installation now we will launch a minimal example in on Turtlebot3 in a Maze environment.

Launch the environment

roslaunch autoexpl_simulations autoexpl_world.launch world:=docker

Launch the slam

roslaunch autoexpl_simulations autoexpl_slam.launch slam_methods:=karto

Launch the autonomous exploration nodes

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

About

Autonomous Navigation Toolbox using Symbolic controller for safe navigation in unknown environments.

Resources

Stars

Watchers

Forks

Languages

  • C++ 78.1%
  • Python 11.7%
  • CMake 9.3%
  • Dockerfile 0.9%