Explainable Deep Architectures for Saliency-Based Autonomous Vehicle Driving Monitoring

Dear Colleagues,

The latest generation of autonomous vehicles needs to collect a wide variety of multi-modal sampled data processed by several sensing systems embedded in the car. The data which are most relevant in reducing the autonomous driving risk level are those of the perceptual type including vision, LiDAR, RADAR, accelerometer data and so on. Through advanced deep learning-based solutions, it is possible to reconstruct the driving scene, driving dynamics, and driving risk level in order to constantly monitor the safety level of the self-driving vehicle as well as the actions to be taken in order to minimize the driving risk. In order to better characterize the criteria analyzed by the deep learning engines embedded in self-driving cars, recent scientific research proposes the use of explainable architectures that highlight the activations used by the networks to determine autonomous driving actions. Furthermore, the visual analysis of driving scenarios based on the salience concept will make the autonomous driving system more efficient and robust.

This Special Issue on “Explainable Deep Architectures for Saliency-based Autonomous Vehicle Driving Monitoring” aims to collect studies on the recent advances of explainable deep learning for autonomous driving in a wide range of topics, including (but are not limited to) the following:

• Car-driver vision explainable systems and physiological big data processing systems for self-driving vehicles;
• Saliency-based visual scene understanding for autonomous vehicles;
• Explainable deep solutions for autonomous vehicles sensing-data fusion;
• Software Deep Learning embedded architectures for autonomous vehicles;
• Vision, LiDAR , RADAR, near-infrared-thermal, physiological data for explainable self-driving safety assessment;
• Explainable Visual Transformers for autonomous driving applications;
• Saliency perceptual visual assessment for personalized self-driving solutions;
• Intelligent multi-modal bio-sensing data analysis and modeling for autonomous driving risk assessment;
• Adversarial attack stabilization deep solutions for self-driving applications;
• Saliency-based domain adaptation for robust self-driving scene understanding/reconstruction;
• Car-driver saliency-based scene reconstruction and object detection and tracking in self-driving scenario.

On behalf of Drones, we invite you to consider this Special Issue as an opportunity to publish your research results in the field of explainable deep learning for autonomous driving. We are looking forward to receiving your submissions.

Prof. Dr. Francesco Rundo
Prof. Dr. Sebastiano Battiato
Dr. Angelo Alberto Messina
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Drones is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.