Title: Neural network-based optimisation of smart odometry classification in a self-governing robot for precise position and location estimation

Authors: Shaik Mohammad Rafi; A. Prakash; Firdouse Banu; P. Muthu Krishnammal; K. Bhavana Raj; J.E. Anusha Linda Kostka

Addresses: Department of Artificial Intelligence and Information Technology, Sri Mittapalli College of Engineering, Guntur, Andhra Pradesh, India ' Department of Electrical and Electronics Engineering, QIS College of Engineering and Technology, Ongole, Andhra Pradesh, India ' Department of Applied Information System, King Khalid University, Mahala, Saudi Arabia ' School of Electronics Engineering, VIT-AP University, Amaravati, Andhrapradesh, India ' Department of Management Studies, Institute of Public Enterprise, Hyderabad, India ' Department of Electrical and Electronics Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India

Abstract: The Verdino self-governing robot's intelligent dummy device will benefit greatly from this study's findings. An odometric mathematical model based on the robot's trajectory equations determines the robot's position. Odometer devices are system inputs, and a model is constructed using the wheel diameter and distance. This model determines the optimal nominal parameters by trying to conduct a restricted squares reduction. This model is computed using the current wheel diameter to assure the accuracy of the findings. A neural network model is used to train an odometric model using data. There is no doubt that the neural network works.

Keywords: neural network; autonomous robot; position, and orientation estimate; odometry system.

DOI: 10.1504/IJESMS.2024.140797

International Journal of Engineering Systems Modelling and Simulation, 2024 Vol.15 No.5, pp.222 - 227

Received: 21 Dec 2021
Accepted: 17 Mar 2022
Published online: 03 Sep 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article