Reinforcement Learning in V2I Communication Assisted Autonomous Driving

Abstract

A novel framework is proposed for enhancing the driving safety and fuel economy of autonomous vehicles (AVs) with the aid of vehicle-to-infrastructure (V2I) communication networks. To solve this pertinent problem, a double deep Qnetwork (DDQN) algorithm is proposed for making collision-free decisions. Thus, the trajectory and velocity of the AV are determined by receiving real-time traffic information from the base stations (BSs). Compared to the conventional deep Q-network algorithm, the proposed DDQN algorithm is capable of overcoming the large overestimation of action values by decomposing the max-Q-value operation into action selection and action evaluation. Numerical results are provided for demonstrating that the proposed trajectory design algorithms are capable of enhancing the driving safety and fuel economy of AVs. We demonstrate that the proposed DDQN based algorithm outperforms the DQN based algorithm. Additionally, it is also demonstrated that the proposed fuel-economy (FE) based driving policy derived from the DRL algorithm is capable of achieving in excess of 24 of fuel savings over the benchmarks.