See, Attend and Brake: An Attention-based Saliency Map Prediction Model for End-to-End Driving
This work addresses the need for improved visual perception in autonomous driving systems, though it appears incremental as it builds on existing attention mechanisms and datasets.
The paper tackles the problem of understanding the relationship between visual saliency and driving decisions by proposing an attention-based saliency map prediction model for braking decisions, achieving results evaluated on the BDD-A and CAT2000 datasets.
Visual perception is the most critical input for driving decisions. In this study, our aim is to understand relationship between saliency and driving decisions. We present a novel attention-based saliency map prediction model for making braking decisions This approach constructs a holistic model to the driving task and can be extended for other driving decisions like steering and acceleration. The proposed model is a deep neural network model that feeds extracted features from input image to a recurrent neural network with an attention mechanism. Then predicted saliency map is used to make braking decision. We trained and evaluated using driving attention dataset BDD-A, and saliency dataset CAT2000.