Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.074429
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Intelligent Ridge Path Planning for Agriculture Robot Using Modified Q-Learning Algorithm

A. Sivasangari1,*, V. J. K. Kishor Sonti1, J. Cruz Antony1, E. Murali1, D. Deepa1, A. Happonen2
1 Department of Computer Science & Engineering, Sathyabama Institute of Science & Technology, Jeppiaar University, Chennai, India
2 School of Engineering Science, LUT University, Lappeenranta, Finland
* Corresponding Author: A. Sivasangari. Email: email
(This article belongs to the Special Issue: Software, Algorithms and Automation for Industrial, Societal and Technological Sustainable Development)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.074429

Received 10 October 2025; Accepted 14 January 2026; Published online 11 March 2026

Abstract

In the past two decades, Precision Agriculture has received research attention since the development of robotics. Agricultural robotic equipment and drones, which can be operated by farmers, are appearing more frequently and being used to make the process of farming easier and more productive. This paper attempts to develop a modified Q-learning algorithm. A reinforcement learning algorithm called Q-learning has Q-values that are updated in order to find the best routes for the robotic devices to follow while avoiding any obstacles. Different types of terrain and other factors that influence the development of good routes for the robotic devices are included in the experiments performed. Through an extensive set of experiments done with different types of terrain the researchers found that the modified Q-learning algorithm converges to the optimal path significantly quicker than the current benchmark Deep Q-Network (DQN) algorithms and that the average distance that the modified Q-learning algorithm travels to get to its destination over different terrane types was 28.7% shorter than the average distance traveled using the standard DQNs. The researchers also found that the modified Q-learning algorithm has been able to successfully avoid obstacles on 99.5% of all occasions tested. The shortest route to the destination is expected to take less time, and it demonstrates the benefit of using a robotic device that has the ability to detect and avoid obstacles in order to be effective on more difficult types of terrain.

Keywords

Path planning; agricultural robotics; reinforcement learning; Q-learning

  • 148

    View

  • 38

    Download

  • 1

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link