V2V Cooperative Sensing using Reinforcement Learning with Action Branching

Cooperative perception plays a vital role in extending a vehicle's sensing range beyond its line-of-sight. However, exchanging raw sensory data under limited communication resources is infeasible. Towards enabling an efficient cooperative perception, vehicles need to address fundamental questions such as: what sensory data needs to be shared? at which resolution? with which vehicles? In this view, this paper proposes a reinforcement learning (RL)-based vehicular association, resource block (RB) allocation, and content selection of cooperative perception messages by utilizing a quad-tree-based point cloud compression mechanism. Simulation results show the ability of the RL agents to efficiently learn the vehicles' association, RB allocation and message content selection that maximizes the fulfillment of the vehicles in terms of the received sensory information.