Advances in Perception and Artificial Intelligence for Autonomous Vehicles

Dear Colleagues,

Recent strides in Perception and Artificial Intelligence (AI) have transformed robotics, particularly in the realm of autonomous vehicles (AVs). The integration of Generative AI and large language models (LLMs) with semantic communication has bolstered AVs' potential for advanced autonomous navigation in unfamiliar surroundings. This Special Issue seeks to consolidate the latest research in these domains, paving the way for a forward-thinking and visionary trajectory in the field.

To collate advanced research, overview, and survey articles that delve into the integration, challenges, and solutions offered by large language models, AI-driven perception and semantic communication algorithms, multi-agent learning, and generative AI in AVs.

This Special Issue invites submissions related to the following topics:

1. Large Language Models (LLMs) in Autonomous Driving:
   • Utilizing Conversational AI to improve user engagement with Autonomous Vehicles (AVs).
   • Implementing Natural Language Understanding for enhanced decision-making in AVs navigating areas with human presence.
   • Realizing LLMs for Avs.
2. AI-driven or AI-accelerated Perception Models for Navigation:
   • Exploring Perception Models predominantly accelerated by deep learning.
   • Examining the role of Edge Computing in AV Perception Models.
   • Modeling Semantic Communication in AV Perceptions.
3. Multi-Agent Reinforcement Learning (MARL) for Autonomous Systems:
   • Investigating collaborative and competitive learning scenarios involving multiple AVs in shared spaces.
   • Ensuring the seamless integration and co-adaptation of diverse agents in real-world navigation situations.
   • Federated Learning and Semantic Communication with MARL over Avs.
4. Generative AI for Driving Scenarios:
   • Creating realistic simulation environments for the training and testing of autonomous systems.
   • Employing generative techniques to predict potential future scenarios and agent behaviours in shared environments.
   • Experiences, experiments and datasets of Generative AI of AVs.
5. Safety, Ethics, and Interpretability:
   • Advocating for transparent decision-making in AI-driven AVs.
   • Addressing ethical considerations in the deployment of large language models and generative AI techniques in navigation.
   • Interpretability of LLMs over AVs.
6. Sensor Fusion for Autonomous Driving:
   • Enhancing AI models through the application of sensor fusion techniques.
   • LLMs with Sensor fusion for AVs.

Outcomes: This Special Issue aims to compile a curated collection showcasing state-of-the-art AI and deep learning perception methods, highlighting their transformative potential in AVs autonomy and navigation. Additionally, it aims to chart new directions for multi-disciplinary research, fostering collaboration between AI technologists and roboticists. The insights derived from accepted submissions will provide practical guidance for the industry, steering the next wave of innovations in smart transportation, AVs and robotics.

We look forward to receiving your original research articles and reviews.

Dr. Rohan Chandra
Dr. Shiva Raj Pokhrel
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.

• generative AI
• perception
• large language models
• foundation models
• deep learning
• sensor fusion
• autonomous vehicles
• semantic communication