Predicting Steering Angle in Autonomous Driving Systems using Deep Learning

DOI

10.2991/978-94-6463-662-8_46How to use a DOI?

Keywords

Autonomous Driving; Steering Angle Prediction; CNN; Image Preprocessing; Deep-Learning

Abstract

This paper proposes a fully data-driven and complete solution for predicting steering angles in autonomous driving systems using exclusively Convolution Neural Networks (CNN’s). An autonomous car needs to make accurate control decisions to be to drive safely on the road and a great deal is dependent on the accuracy of steering angle forecasting. In order to achieve this, we make use of a large data set consisting of driving actions and demonstrate that visual input can be interpreted to steering angle prediction directly. The method as proposed consists of the few different levels of data preparation starting from changing image size and changing color images from RGB to HSV format, all aiming to increase the effectiveness of feature extraction. With this preprocessing, the essential road information including lane markings and road edges are preserved while the computational burden is also minimized. Essential features required for prediction of the steering angles are extracted using convolutional layers complemented with activation and pooling layers. A large validation set is used to evaluate the feasibility of the model developed generalizability, ensuring robustness in different driving scenarios. The results reveal the high accuracy of the image in estimating the angle of the wheel, and demonstrate the effectiveness of CNNs in this application. This approach highlights the potential of deep learning to advance autonomous driving technologies, delivering scalable and robust solutions for real-time operations controls in self-driving vehicles. The findings pave the way for future developments, such as the integration of time-data or real-world datasets, to further the real-world applicability of the model.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - C. Sreedhar
AU  - G. Udaya Kavya
AU  - K. Khaja Bee
AU  - A. Anusha
PY  - 2025
DA  - 2025/03/17
TI  - Predicting Steering Angle in Autonomous Driving Systems using Deep Learning
BT  - Proceedings of the International Conference on Advanced Materials, Manufacturing and Sustainable Development (ICAMMSD 2024)
PB  - Atlantis Press
SP  - 581
EP  - 591
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-662-8_46
DO  - 10.2991/978-94-6463-662-8_46
ID  - Sreedhar2025
ER  -