A Vehicular Edge Computing-Based Architecture and Task Scheduling Scheme for Cooperative Perception in Autonomous Driving

Cooperative perception is an important domain of autonomous driving that helps to improve road safety and traffic efficiency. Nevertheless, the large amount sensed data complicated algorithms make storage computation for vehicles (AVs) challenging. Furthermore, not every AV needs individually process all from other AVs because environmental information same in a small region. Inspired by vehicular edge computing (VEC), where are interconnected with help roadside units (RSUs) better capabilities, we propose VEC-based architecture cooperative design key task scheduling algorithm above challenges. Specifically, time slot-based VEC RSU designed, problem proposed formulated as multitask multitarget assignment restrictions. A two-stage heuristic scheme (TSHS) designed problem. Finally, extensive simulations indicate TSHS can enable perception, fast running speed advanced performance, superior benchmarks, especially when most face limitations terms computation.