The autonomous vehicles (AVs) are also known as self-driving cars, which fall under the Society of Automotive Engineers (SAE) Level 5 category; these vehicles operate autonomously without human intervention. The AVs are expected to mitigate transportation issues, including alleviating heavy traffic, reducing road accidents, facilitating carpooling for both the younger and elderly demographics, and optimizing performance across a diverse range of energy sources to minimize pollution. However, autonomous vehicles (AVs) still face various developmental challenges, such as the integration of affordable sensor technology, the implementation of advanced artificial intelligence (AI) algorithms, the availability of high-level simulation platforms, and the necessity for real-time testing. Additionally, gaining public acceptance of this technology remains a crucial aspect for the success of AVs. The widely used AVs architecture includes perception, planning, and control. AVs utilize a blend of sensor technologies, including cameras, LiDAR, and RADAR, to perceive their surroundings. GNSS, IMU, and HD maps are then employed to estimate the state of the AVs as they operate in various conditions. This chapter provides a comprehensive understanding of how AVs operate, detailing current approaches employed in AVs technology. It extensively explores the machine learning (ML) algorithms utilized for AVs, highlighting the most prominent technology at each stage of their operation.
Machine Learning Algorithms for Autonomous Vehicles
Handbook of Formal Optimization ; Kapitel : 58 ; 479-532
2024-07-17
54 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch