Acquiring Qualitative Explainable Graphs for Automated Driving Scene Interpretation

TL;DR

This paper introduces a novel Qualitative eXplainable Graph (QXG) representation for automated driving scenes, enabling real-time, space-efficient qualitative reasoning to improve explainability and trustworthiness of autonomous vehicle perception.

Contribution

The paper presents a new qualitative scene representation, QXG, based on qualitative constraint acquisition, suitable for real-time, long-term scene analysis in automated driving.

Findings

QXG can be computed in real-time on a 40-frame scene

QXG is lightweight in storage and suitable for long-term scene reasoning

Experimental validation on NuScenes dataset demonstrates effectiveness

Abstract

The future of automated driving (AD) is rooted in the development of robust, fair and explainable artificial intelligence methods. Upon request, automated vehicles must be able to explain their decisions to the driver and the car passengers, to the pedestrians and other vulnerable road users and potentially to external auditors in case of accidents. However, nowadays, most explainable methods still rely on quantitative analysis of the AD scene representations captured by multiple sensors. This paper proposes a novel representation of AD scenes, called Qualitative eXplainable Graph (QXG), dedicated to qualitative spatiotemporal reasoning of long-term scenes. The construction of this graph exploits the recent Qualitative Constraint Acquisition paradigm. Our experimental results on NuScenes, an open real-world multi-modal dataset, show that the qualitative eXplainable graph of an AD scene composed of 40 frames can be computed in real-time and light in space storage which makes it a potentially interesting tool for improved and more trustworthy perception and control processes in AD.