Joint Sensing, Communication, and Computation Resources Allocation for Cooperative Perception

Abstract

Cooperative perception is a promising approach to improve safety in autonomous driving by utilizing sensing data from cooperative devices. However, the real-time transmission and processing of large amounts of sensing data with limited network resources and different vehicle requirements pose significant challenges. To address this issue, we propose a joint sensing tasks and communication-computation resource allocation approach. The proposed approach considers a multi-objective optimization problem of total value of information and delay-energy consumption under resource-constrained and differentiated information quality conditions. To solve the formulated problem, we decompose it into two stages. In the first stage, the sensing tasks allocation algorithm is proposed to select optimal sensing data for vehicle requirements based on differences in information quality. In the second stage, the communication-computation resource allocation algorithm is proposed to balance the delay and energy consumption of sensing tasks execution. Simulation results demonstrate that the proposed scheme is more effective than the benchmark schemes in addressing the challenges posed by cooperative perception with limited resources.