Artificial intelligence algorithms used in autonomous driving to reduce private vehicle accidents: A Review

Denys Rios Peña D.; Baca Marroquin E. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2024) · DOI: 10.18687/laccei2024.1.1.1073

Resumen

Artificial intelligence (AI) algorithms have become the backbone of autonomous driving, enabling vehicles to make critical decisions and operate safely in diverse driving environments. Despite advances, significant limitations exist as highly changing environments, such as urban traffic, can affect a car's ability to adjust quickly to unforeseen situations, inability to handle the unknown, and route interpretation. This review examines artificial intelligence algorithms used in autonomous driving to reduce private vehicle accidents. The review included 115 original articles published from 2019 to 2023 identified in the Scopus database that met the inclusion criteria. The results identified algorithms used commonly to reduce accidents in autonomous driving. The review highlights diverse academic contributions to neural networks, path planning, sensor fusion, radar object detection, and rule-based systems. Despite evidence of the effectiveness of artificial intelligence in reducing traffic accidents, certain challenges are evidenced, such as the lack of training data and the need to improve the accuracy of the algorithms.

Instituciones: Universidad Tecnológica del Perú