Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies
This work addresses safety concerns in autonomous driving by enhancing robustness against adversarial attacks, though it is incremental as it builds on existing adversarial training methods.
The paper tackles the vulnerability of autonomous cars to adversarial attacks by proposing a two-step methodology that first finds failure states using an adversarial agent and then retrains the cars with adversarial inputs to improve robustness. The results show that this approach reduces collision and offroad steering errors in a simulated multi-agent driving environment.
Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous cars for finding driving errors but to improve the robustness of the cars to these errors. To this end, in this paper, we propose a two-step methodology for autonomous cars that consists of (i) finding failure states in autonomous cars by training the adversarial driving agent, and (ii) improving the robustness of autonomous cars by retraining them with effective adversarial inputs. Our methodology supports testing autonomous cars in a multi-agent environment, where we train and compare adversarial car policy on two custom reward functions to test the driving control decision of autonomous cars. We run experiments in a vision-based high-fidelity urban driving simulated environment. Our results show that adversarial testing can be used for finding erroneous autonomous driving behavior, followed by adversarial training for improving the robustness of deep reinforcement learning-based autonomous driving policies. We demonstrate that the autonomous cars retrained using the effective adversarial inputs noticeably increase the performance of their driving policies in terms of reduced collision and offroad steering errors.