Towards Explainability in Modular Autonomous Vehicle Software

TL;DR

This paper discusses the importance of explainability and interpretability in autonomous vehicle systems, emphasizing their role in safety, transparency, and post-hoc analysis, and proposes integrating these aspects into AV module design.

Contribution

It provides a framework for incorporating explainability into autonomous vehicle modules like perception, planning, and control, highlighting its significance for safety and trust.

Findings

Explainability enhances trust in AV decision-making.

Integrating interpretability aids in safety validation and blame assignment.

Framework guides future research in transparent AV systems.

Abstract

Safety-critical Autonomous Systems require trustworthy and transparent decision-making process to be deployable in the real world. The advancement of Machine Learning introduces high performance but largely through black-box algorithms. We focus the discussion of explainability specifically with Autonomous Vehicles (AVs). As a safety-critical system, AVs provide the unique opportunity to utilize cutting-edge Machine Learning techniques while requiring transparency in decision making. Interpretability in every action the AV takes becomes crucial in post-hoc analysis where blame assignment might be necessary. In this paper, we provide positioning on how researchers could consider incorporating explainability and interpretability into design and optimization of separate Autonomous Vehicle modules including Perception, Planning, and Control.