Explaining Autonomous Driving Actions with Visual Question Answering

TL;DR

This paper introduces a Visual Question Answering framework to interpret and explain autonomous driving decisions, aiming to improve safety and transparency in self-driving vehicles.

Contribution

It presents a novel VQA-based approach for explaining autonomous driving actions using annotated driving videos and causal reasoning.

Findings

VQA can accurately predict explanations for driving actions

The framework enhances interpretability of autonomous vehicle decisions

Results support real-time application in safety-critical scenarios

Abstract

The end-to-end learning ability of self-driving vehicles has achieved significant milestones over the last decade owing to rapid advances in deep learning and computer vision algorithms. However, as autonomous driving technology is a safety-critical application of artificial intelligence (AI), road accidents and established regulatory principles necessitate the need for the explainability of intelligent action choices for self-driving vehicles. To facilitate interpretability of decision-making in autonomous driving, we present a Visual Question Answering (VQA) framework, which explains driving actions with question-answering-based causal reasoning. To do so, we first collect driving videos in a simulation environment using reinforcement learning (RL) and extract consecutive frames from this log data uniformly for five selected action categories. Further, we manually annotate the extracted frames using question-answer pairs as justifications for the actions chosen in each scenario. Finally, we evaluate the correctness of the VQA-predicted answers for actions on unseen driving scenes. The empirical results suggest that the VQA mechanism can provide support to interpret real-time decisions of autonomous vehicles and help enhance overall driving safety.