Textual Explanations for Automated Commentary Driving

TL;DR

This paper evaluates a state-of-the-art model for generating natural language explanations for vehicle control predictions, introduces improvements to the explainer, and benchmarks performance on the SAX dataset, advancing explainability in autonomous driving.

Contribution

It provides a thorough benchmark of existing models and proposes a new explainer with enhanced explanation quality for autonomous vehicle predictions.

Findings

Our explanation model outperforms SOTA by 7.7x on BLEU score.

The new explainer improves description generation by 1.3 times.

Benchmark results validate the effectiveness of the proposed improvements.

Abstract

The provision of natural language explanations for the predictions of deep-learning-based vehicle controllers is critical as it enhances transparency and easy audit. In this work, a state-of-the-art (SOTA) prediction and explanation model is thoroughly evaluated and validated (as a benchmark) on the new Sense--Assess--eXplain (SAX). Additionally, we developed a new explainer model that improved over the baseline architecture in two ways: (i) an integration of part of speech prediction and (ii) an introduction of special token penalties. On the BLEU metric, our explanation generation technique outperformed SOTA by a factor of 7.7 when applied on the BDD-X dataset. The description generation technique is also improved by a factor of 1.3. Hence, our work contributes to the realisation of future explainable autonomous vehicles.