• Our Lab
    • About
    • Research Themes
    • Gallery
    • Exhibitions
    • Workshops >
      • Workshop Info
      • FAQ
    • Intern Diaries
  • Projects
    • Flagship Projects
    • Summer Projects
  • Publications
  • Our Team
    • Professor Incharge
    • Alumni >
      • Batch 2014
      • Batch 2016
      • Batch 2017
      • Batch 2018
      • Batch 2019
      • Batch 2020
      • Batch 2021
      • Batch 2022
    • Core Coordinators
    • Junior Year Coordinators
  • Contact
  • Spin-offs
    • Makxenia
    • AidBots
  • Intranet
IvLabs
  • Our Lab
    • About
    • Research Themes
    • Gallery
    • Exhibitions
    • Workshops >
      • Workshop Info
      • FAQ
    • Intern Diaries
  • Projects
    • Flagship Projects
    • Summer Projects
  • Publications
  • Our Team
    • Professor Incharge
    • Alumni >
      • Batch 2014
      • Batch 2016
      • Batch 2017
      • Batch 2018
      • Batch 2019
      • Batch 2020
      • Batch 2021
      • Batch 2022
    • Core Coordinators
    • Junior Year Coordinators
  • Contact
  • Spin-offs
    • Makxenia
    • AidBots
  • Intranet

Maze Solver

Overview

As children, we've all solved mazes. People are captivated by mazes. Let's have a look at how a robot, equipped with a LiDAR sensor, solves a maze without having any prior knowledge of the environment. Our project's primary objective is to use the Robot Operating System (ROS) to simulate a robot solving a maze in a gazebo environment. The robot is completely unaware of the maze's surroundings.

Approach

This project was completed in three steps:
  1. Motion control of SAHAYAK Bot.
  2. Using the wall following algorithm on a single wall.
  3. Solving the Maze environment.   
 
  • The Sahayak bot is controlled by delivering velocity to the joint velocity controllers, which direct the speed of the Sahayak wheels.
  • The Sahayak bot was made to follow a wall from both sides and avoid any collisions while taking a turn by applying conditions to the joint velocity controllers using distance data gathered from the LiDAR sensor over a 180-degree span.
  • The LiDAR sensor sends laser beams and uses the time it takes for them to return to compute the distance to the object.
  • We used a simply connected maze in this project. A simply connected maze does not have detached walls or loops. 
  • The Wall Following Algorithm was used to solve the maze environment. 
  • The Sahayak bot was tested for various velocities to avoid collisions with the walls while testing the wall following algorithm which followed the left wall of the simply connected maze, thus solving the maze environment.
  • This algorithm does not provide the optimal solution.


Picture

A simply connected maze

Picture
LiDAR Sensor

Results

Motion control of Sahayak Bot

Picture


 Wall following algorithm on a single wall
Picture

Solving the maze environment

Picture
GitHub Repository

Tools and Libraries used

Picture
python
Picture
Picture
Picture
SAHAYAK BOT MOUNTED WITH A LiDAR SENSOR

Team

Members:
  1. Smit Gala
  2. Malhar Limaye
  3. Madhav Ishwar
  4. Laeba Sayed
  5. Jyoti Thakur

Mentors:
  1. Sania Subhedar
  2. Karthik Raman
  3. Prathamesh Ringe
  4. Yagnesh Devada
  5. Sushlok Shah
Powered by Create your own unique website with customizable templates.
  • Our Lab
    • About
    • Research Themes
    • Gallery
    • Exhibitions
    • Workshops >
      • Workshop Info
      • FAQ
    • Intern Diaries
  • Projects
    • Flagship Projects
    • Summer Projects
  • Publications
  • Our Team
    • Professor Incharge
    • Alumni >
      • Batch 2014
      • Batch 2016
      • Batch 2017
      • Batch 2018
      • Batch 2019
      • Batch 2020
      • Batch 2021
      • Batch 2022
    • Core Coordinators
    • Junior Year Coordinators
  • Contact
  • Spin-offs
    • Makxenia
    • AidBots
  • Intranet