�ݺ�ߣ

MAZE RUNNER and the best of u to do the needful

NAVIGATING
COMPLEXITY
MAZE-SOLVING ROBOT
BATCH NO:04
NAME
1. R B KAILASH C
2. ROHITH
3. SUDAHVA V A B
4. VIKAS A RAM
1JS21RA013
1JS21RA015
1JS21RA018
1JS21RA023
GUIDE: K S MAHESH
[ASSISTANT PROF]
23 JULY 2024
TUESDAY

INTRODUCTION
This project develops an autonomous robot that navigates mazes
using sensors to detect obstacles and an algorithm to find the shortest
path to the exit. Equipped with infrared and ultrasonic sensors, a
microcontroller, and motors, the robot demonstrates efficient maze-
solving capabilities. Potential applications include search and rescue
missions, automated delivery systems, and robotic pathfinding.
OVERVIEW
 Develop an autonomous robot capable of navigating
through a maze and finding the shortest path to the exit
 Implement algorithms to efficiently explore the maze and
determine the optimal route, such as the A* algorithm
 Explore potential real-world applications of maze-solving
robots including search and rescue missions, automated
delivery systems, and robotic pathfinding
OBJECTIVES AND GOALS

PROBLEM STATEMENT
Search and Rescue
• Urban environments: Navigating through
collapsed buildings or disaster zones to
locate survivors.
• Underground environments: Exploring caves
or mines for trapped individuals.
Exploration and Mapping
• Uncharted territories: Mapping
unknown environments like caves,
forests, or underwater terrains.
• Planetary exploration: Sending
robots to explore other planets or
moons.
Logistics and Warehousing
• Inventory management: Optimizing
warehouse layouts and locating items
efficiently.
• Autonomous delivery: Navigating
through complex indoor environments to
deliver packages.

TITLE AUTHOR WORKING
FIELD
SUMMARY
Design and Implementation of
Autonomous Maze-Solving
Robot based on an Enhanced
Maze Solving Techniques
R Ramesh; D Selvalakshmi; M
Naven Karthick; S L
Nikileshkumar; S Cibivarshan; K
Prasanth
IEEE This article discusses a self-governing robot that uses
distance sensors and wheel pivot encoders to navigate
and solve mazes by storing past information and
following the shortest path.
Maze Solving Robot-B-Eng
Design Project [2016]
Mohamed Mohamed-Ahmed Department of
Electronic and
Electrical
Engineering
The details the development of two autonomous
robots for maze navigation, using microcontrollers,
sensors, wireless communication, and data loggers.
An Autonomous Maze-
Solving Robotic System Based
on an Enhanced Wall-Follower
Approach
Shatha Alamri ,Hadeel
Alamri ,Wejdan Alshehri ,Shuruq
Alshehri ,Ahad Alaklabi and Tareq
Alhmiedat
College of
Computer
Sciences and
Information, King
Saud University,
Riyadh 11421,
Saudi Arabia
Reviewing the recently developed wall-follower
maze-solving robotic systems. Designing and
implementing a maze-solving robotic system by
employing a modified wall-follower method.

METHODOLOGY
ALGORITHM SELECTION:
- WALL FOLLOWING: SIMPLE BUT NOT ALWAYS
OPTIMAL.
- DEPTH-FIRST SEARCH (DFS): EXPLORES EACH
BRANCH DEEPLY BEFORE BACKTRACKING.
- BREADTH-FIRST SEARCH (BFS): EXPLORES ALL
NEIGHBORS AT THE PRESENT DEPTH PRIOR TO MOVING
ON TO NODES AT THE NEXT DEPTH LEVEL.
- FLOOD-FILL: COMMON IN MICRO MOUSE
COMPETITIONS, FILLING THE MAZE WITH DISTANCE
VALUES FROM THE ENDPOINT AND FOLLOWING THE
SHORTEST PATH.
EQUIPMENT:
• AURDINO UNO
• L298N MOTOR DRIVER
• 2* N20 MINI MOTOR
• 2* ULTRASONIC SENSOR
• 3* IR SENSORS
• LI-PO BATTERY(12V)
• JUMPER CABLES
• CHASSI
• ESP32 WIFI MODULE
• BREAD BOARD

DESIGN
• Understand how maze solving robots work by
referring to previous research papers.
• Understand A* algorithm and figure out a way to
use it to solve maze.
• Develop a code for finding the shortest path to
solve the maze using A* algorithm in with the
help of Code Composer Studio .
• Making a 6’ * 6’ maze to test the robot.

Li-ON 3D PLA Printing
Filament 1.75mm for
3D Printers- Smooth
Printing material with
Wide Color Option (1
kg Spool) (Red)
FABRICATION AND MANUFACTURING
Design and Planning: Determine maze type, robot
dimensions, sensor/actuator selection, microcontroller, and
power source.
Component Procurement: Gather necessary materials for the
robot's structure, electronics, and power supply.
Assembly: Construct the robot's chassis, mount sensors and
actuators, and create the electronic circuitry.
Software Development: Create algorithms for maze solving,
sensor data processing, and motor control.
Testing and Refinement: Test the robot's performance in
different mazes, calibrate sensors, and optimize performance.
MANUFACTURING A MAZE SOLVING ROBOT

TESTING AND VALIDATION
A* Algorithm in 5 Steps:
• Initialization: Create open and closed sets.
Add the start node to the open set with its
initial cost.
• Node Selection: Choose the node in the
open set with the lowest combined cost
(actual cost + estimated cost to goal).
• Goal Check: If the selected node is the
goal, return the path. Otherwise, move it
to the closed set.
• Neighbour Exploration: Evaluate each
neighbour of the current node. If a
neighbour is in the closed set, ignore it. If
it's not in the open set, add it with its
calculated cost. If it's already in the open
set, update its cost if a shorter path is
found.
• Iteration: Repeat steps 2-4 until the goal is
reached or the open set is empty
(indicating no path).

TESTING PHASE
Maze Variety:
Test the robot in different maze
configurations (simple, complex, open,
closed) to assess its adaptability.
Sensor Accuracy:
Evaluate sensor performance in various
lighting conditions and maze environments to
ensure reliable data collection.
Algorithm Efficiency:
Measure the robot's speed, path efficiency,
and success rate in solving mazes to refine
the algorithm.

RESULTS AND ANALYSIS
• Wheel Imperfection:
The robot's wheels experienced resistance
issues, causing it to deviate from a straight
path, necessitating modifications to the A*
algorithm.
• Bump Sensor Solution:
The integration of bump sensors effectively
detected walls and obstacles, playing a
crucial role in the robot's maze-solving
capabilities.
• Algorithm Adaptation:
Due to wheel inconsistencies, modifications
were made to the A* algorithm to
compensate for the robot's imperfect
movement, ensuring successful maze
navigation.

CONCLUSION
AI Application:
The project successfully demonstrated the application of artificial intelligence for
maze-solving, highlighting its potential for future advancements.
Project Challenges:
Implementing the project required adaptations to the original plan due to
unfamiliarity with the learning kit.
Performance and Future Scope:
While achieving success, the robot's navigation and obstacle avoidance capabilities
can be further enhanced.
Potential Impact:
Maze-solving robots represent a promising field with anticipated growth and
development in the coming years.
AI and Future:
The project's outcome suggests that AI could play a significant role in future
technological advancements.

FUTURE WORK
Future Work and Possibilities for Maze Solving Robots:
• Advanced Algorithms:
Explore more sophisticated algorithms like Deep Q-Learning for complex
maze environments and real-time decision making.
• Sensor Fusion:
Combine multiple sensors (lidar, camera, ultrasonic, etc.) for enhanced
perception and mapping capabilities.
• Dynamic Maze Environments:
Develop robots capable of adapting to changing maze conditions, such as
moving obstacles or walls.
• Real-World Applications:
Apply maze-solving technology to practical applications like search and
rescue, warehouse automation, and exploration.
• Autonomous Learning:
Implement machine learning techniques for robots to learn and improve
their maze-solving abilities through experience.

�ݺ�ߣ

MAZE RUNNER and the best of u to do the needful

Recommended

More Related Content

Similar to MAZE RUNNER and the best of u to do the needful (20)

Recently uploaded (20)

MAZE RUNNER and the best of u to do the needful