Edge Intelligence for Autonomous Driving Cars

Self-driving cars have shown an immense interest from both academia and industry due to their wide range of features. These features are infotainment, collision avoidance alerts, driving with minimum possible user intervention, lane changing guidance forminimizing congestion, and accident reporting, among others. To enable these features, there is a need to efficiently deploy secure, secure, faulttolerant, robust, scalable, and interoperable technologies. Additionally, there is a need for on-demand computing resources at the network edge to assist autonomous cars in performing complex computing tasks. To further improve the performance at the network edge, one can use machine learning. In this chapter, we investigate the key design aspects and technologies required for autonomous driving cars. A case study of using deep learning for enabling infotainment in autonomous cars is also presented. Finally, simulations results are presented for validation of the case study.