Visual Attention for Behavioral Cloning in Autonomous Driving

TL;DR

This paper explores the use of visual attention mechanisms, both supervised and unsupervised, to improve autonomous driving by predicting attention maps, demonstrating that supervised methods yield better performance.

Contribution

It introduces a novel unsupervised approach for predicting attention maps in autonomous driving and compares it with supervised methods, highlighting the effectiveness of supervised attention prediction.

Findings

Supervised attention prediction outperforms unsupervised methods.

Incorporating attention maps improves driving performance.

The unsupervised approach learns attention without gaze data.

Abstract

The goal of our work is to use visual attention to enhance autonomous driving performance. We present two methods of predicting visual attention maps. The first method is a supervised learning approach in which we collect eye-gaze data for the task of driving and use this to train a model for predicting the attention map. The second method is a novel unsupervised approach where we train a model to learn to predict attention as it learns to drive a car. Finally, we present a comparative study of our results and show that the supervised approach for predicting attention when incorporated performs better than other approaches.