iRDRC: An Intelligent Real-time Dual-functional Radar-Communication System for Automotive Vehicles

TL;DR

This paper presents iRDRC, a dual-functional radar-communication system for autonomous vehicles that uses deep reinforcement learning to optimize mode switching, enhancing safety and data throughput in uncertain environments.

Contribution

The paper introduces a novel real-time dual-functional radar-communication system with a deep reinforcement learning-based mode selection algorithm for autonomous vehicles.

Findings

Outperforms baseline schemes in data throughput

Reduces miss detection probability

Achieves faster convergence in simulations

Abstract

This letter introduces an intelligent Real-time Dual-functional Radar-Communication (iRDRC) system for autonomous vehicles (AVs). This system enables an AV to perform both radar and data communications functions to maximize bandwidth utilization as well as significantly enhance safety. In particular, the data communications function allows the AV to transmit data, e.g., of current traffic, to edge computing systems and the radar function is used to enhance the reliability and reduce the collision risks of the AV, e.g., under bad weather conditions. The problem of the iRDRC is to decide when to use the communication mode or the radar mode to maximize the data throughput while minimizing the miss detection probability of unexpected events given the uncertainty of surrounding environment. To solve the problem, we develop a deep reinforcement learning algorithm that allows the AV to quickly obtain the optimal policy without requiring any prior information about the environment. Simulation results show that the proposed scheme outperforms baseline schemes in terms of data throughput, miss detection probability, and convergence rate.