Foundation Models Verification in Autonomous Driving Systems

Dear Colleagues,

Autonomous driving systems are at the forefront of technological innovation, promising to transform transportation and mobility. Central to this transformation are foundation models, including Large Language Models (LLMs), Visual Language Models (VLMs), and Visual Language Action (VLAs) models. These models leverage large-scale data to improve the performance and reliability of autonomous vehicles, enhancing their capabilities in perception, decision-making, and control in complex driving environments. However, the deployment of these systems raises critical challenges concerning safety, interpretability, and robustness.

This Special Issue on "Foundation Models Verification in Autonomous Driving Systems" seeks to explore the intersection of advanced AI models and their verification in the context of autonomous driving. We invite contributions that delve into the development and application of LLMs, VLMs, and VLAs in various aspects of autonomous vehicles, along with methodologies for rigorous verification and validation of these systems.

The topics of interest for this Special Issue include, but are not limited to:

• Development and training of LLMs for natural language processing tasks in user interaction and command recognition
• Integration of VLMs for interpreting visual data in conjunction with textual inputs, enhancing situational awareness
• Application of VLAs for generating and executing actions based on visual stimuli in dynamic environments
• Verification frameworks for ensuring the safety and reliability of autonomous driving systems powered by these foundation models
• Case studies involving real-world applications and challenges of LLMs, VLMs, and VLAs in autonomous vehicles
• Methods for interpretability and transparency in AI-driven decision-making processes
• Evaluation metrics and benchmarks for assessing the performance of foundation models in diverse driving scenarios
• Approaches for mitigating risks associated with model bias and failure in critical situations

We welcome original research articles, review papers, and case studies that contribute to a deeper understanding of how foundation models can be effectively integrated into autonomous driving systems and strategies for their rigorous verification and validation. This Special Issue aims to foster collaboration among researchers, industry practitioners, and policymakers to advance the field of autonomous driving and promote the responsible development of this transformative technology.

Dr. Shahpour Alirezaee
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Robotics 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 1800 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.