Secure Control of Connected and Autonomous Electrified Vehicles Under Adversarial Cyber-Attacks

TL;DR

This paper proposes a reinforcement learning-based secure control architecture for connected autonomous electric vehicles to prevent collisions under cyber-attacks, enhancing safety in smart mobility systems.

Contribution

It introduces a novel RL-based control input for CAEV powertrains to mitigate cyber-attack effects, ensuring safe platoon operation.

Findings

The RL control approach effectively prevents collisions during cyber-attacks.

Simulation results demonstrate improved safety and robustness of CAEV platoons.

The method maintains vehicle coordination despite adversarial disruptions.

Abstract

Connected and Autonomous Electrified Vehicles (CAEV) is the solution to the future smart mobility having benefits of efficient traffic flow and cleaner environmental impact. Although CAEV has advantages they are still susceptible to adversarial cyber attacks due to their autonomous electric operation and the involved connectivity. To alleviate this issue, we propose a secure control architecture of CAEV. Particularly, we design an additional control input using Reinforcement Learning (RL) to be applied to the vehicle powertrain along with the input commanded by the battery. We present simulation case studies to demonstrate the potential of the proposed approach in keeping the CAEV platoon operating safely without collisions by curbing the effect of adversarial attacks.