Context-aware, Ante-hoc Explanations of Driving Behaviour

TL;DR

This paper presents a novel approach for providing real-time, context-aware explanations of autonomous vehicle driving decisions using formal language and runtime monitoring to enhance safety and trust.

Contribution

It introduces a method for ante-hoc, context-aware explanations of driving maneuvers at runtime, bridging explanation correctness and quality.

Findings

Successful demonstration in simulated overtaking scenario

Supports real-time, formalized explanations of driving behavior

Enhances trust and safety in autonomous vehicles

Abstract

Autonomous vehicles (AVs) must be both safe and trustworthy to gain social acceptance and become a viable option for everyday public transportation. Explanations about the system behaviour can increase safety and trust in AVs. Unfortunately, explaining the system behaviour of AI-based driving functions is particularly challenging, as decision-making processes are often opaque. The field of Explainability Engineering tackles this challenge by developing explanation models at design time. These models are designed from system design artefacts and stakeholder needs to develop correct and good explanations. To support this field, we propose an approach that enables context-aware, ante-hoc explanations of (un)expectable driving manoeuvres at runtime. The visual yet formal language Traffic Sequence Charts is used to formalise explanation contexts, as well as corresponding (un)expectable driving manoeuvres. A dedicated runtime monitoring enables context-recognition and ante-hoc presentation of explanations at runtime. In combination, we aim to support the bridging of correct and good explanations. Our method is demonstrated in a simulated overtaking.