Explaining autonomous driving with visual attention and end-to-end trainable region proposals

Abstract

Autonomous driving is advancing at a fast pace, with driving algorithms becoming more and more accurate and reliable. Despite this, it is of utter importance to develop models that can offer a certain degree of explainability in order to be trusted, understood and accepted by researchers and, especially, society. In this work we present a conditional imitation learning agent based on a visual attention mechanism in order to provide visually explainable decisions by design. We propose different variations of the method, relying on end-to-end trainable regions proposal functions, generating regions of interest to be weighed by an attention module. We show that visual attention can improve driving capabilities and provide at the same time explainable decisions.

Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving

“…Whereas these methods have access to environmental data, either as inputs or as additional sources of supervision, we assume to have access only to the RGB stream and the state of the vehicle (i.e., current speed, steer, acceleration, and brake), which is a direct consequence of the driving policy. A similar assumption is done in recent works such as [5], [40], [41].…”

“…Every stage of the model performs token-to-token attention, thanks to the transformer's self-attention. The advantages are twofold: on the one hand, prior work has shown that explicitly modeling attention improves driving capabilities [17], [40]; on the other hand, it provides a built-in interpretability mechanism that can be used to visually explain decisions.…”

“…In our model, the attention involves not only visual patches as in [17], [40] but also the state of the vehicle. First, the output of the convolutional backbone, i.e.…”

Subjective Scoring Framework for VQA Models in Autonomous Driving

“…A UTONOMOUS driving has been a large area of development, both commercially and in academic research, over the last decade or more [1], and continues to be an area of deep interest in the research community. However, while perception and control tasks are still undergoing significant research [2], [3], there has been an increase in interest in incorporating elements of trustworthiness [4], [5] and explainability [6]- [8] into autonomous driving.…”