Emerging Research of Artificial Intelligence in Autonomous Vehicles: Balancing Innovation with Safety and Acceptability

Dear Colleagues,

Artificial intelligence (AI) has become integral to the ‘Sense’, ‘Plan’, ‘Act’ paradigm, enabling vehicles to achieve high levels of automation safely and acceptably. AI is becoming increasingly employed across the entire lifecycle of intelligent vehicles, from conception and design to testing, verification, validation, updating, and maintenance. We are witnessing a fast-paced evolution, exemplified by the rapid adoption of large language models (LLMs) to support specification and design stages, allowing companies to leverage previous work while incorporating complex standards to ensure the safety and security of next-generation vehicles.

AI-enabled systems are being integrated into all functions of driver assistance systems and autonomous vehicles, including perception, localization, decision-making, behavior generation, and vehicle control. Moreover, their application extends to verification and validation processes to address the increased complexity of operational domains, ensuring that these vehicles can operate safely.

However, focusing solely on vehicle-centered approaches is not enough for the widespread adoption of autonomous vehicles; we must consider the entire autonomous vehicle ecosystem and all its stakeholders. This necessitates a system-of-systems approach that encompasses not only the whole vehicle but also its environment and ecosystem.

The introduction of data-driven AI solutions adds another layer of complexity to already intricate systems. These AI systems often function as black boxes, making their operations difficult to understand and exhaustive testing elusive. Uncertainty pervades every aspect, from the data used to develop machine learning models to the models themselves and the operating environments. For instance, LLMs are primarily associative solutions with limited causality, raising concerns about the trustworthiness of systems based on such models.

Additionally, the opportunities provided by new vehicle computing architectures, featuring powerful centralized computing units working alongside zone electronic control units (ECUs), pave the way for the safe and secure deployment of AI in autonomous vehicles.

This Special Issue aims to bridge the gap by exploring AI-enabled systems that address the complexities of the operating environments where driving assistance systems and autonomous vehicles will be deployed.

We invite original research articles and reviews that focus on (but are not limited to) the following topics:

1. AI/LLMs to facilitate and rationalize feature development in autonomous vehicles;
2. AI to accelerate autonomous vehicle testing and validation;
3. AI to expedite the design of autonomous vehicle parts and components, such as motors, batteries, and gearboxes;
4. AI to support autonomous vehicle operation, ensuring seamless integration into the current road and vehicle ecosystem;
5. AI combined with physics-based modeling and control techniques.

We look forward to receiving your contributions and advancing the field of AI in autonomous vehicles.

Dr. Olivier Haas
Dr. Javier Ibanez-Guzman
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. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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.

• artificial intelligence
• autonomous vehicle
• large language models
• path planning
• sensor
• vehicle control
• localization
• vehicle navigation