Salus: A Novel Data-Driven Monitor that Enables Real-Time Safety in Autonomous Driving Systems

This paper proposes Salus, a data-driven real-time safety monitor, that detects and mitigates safety violations of an autonomous vehicle (AV). The key insight is that traffic situations that lead to AV safety violations fall into patterns and can be identified by learning from the safety violations of the AV. Our approach is to use machine learning (ML) techniques to model the traffic behaviors that result in safety violations in the AV, characterize their early symptoms for training a preemptive model, hence deploy and detect real-time safety violations before the actual crashes happen to the AV. In order to train our ML model, we leverage a pipeline of fuzzing techniques to tailor AVspecific safety violation symptoms and generate the training data via data argumentation techniques. Our evaluation demonstrates our proposed technique is effective in reducing over 97.2% of safety violations in industry-level autonomous driving systems, such as Baidu Apollo, with no more than 0.018 false positive values.

Automated summary

This paper proposes Salus, a data-driven real-time safety monitor that detects and mitigates safety violations of autonomous vehicles. By using machine learning techniques and learning from the safety violations of the vehicles, Salus models traffic behaviors, characterizes early symptoms, and deploys real-time safety violation detection before actual crashes happen. The evaluation demonstrates that the proposed technique is highly effective in reducing safety violations in industry-level autonomous driving systems.