Sensing, Prediction, and Virtual Validation Technologies for Connected and Automated Vehicles

Dear Colleagues,

Connected and automated driving technologies have the potential to revolutionize transportation by facilitating access to mobility services to a wider population, improving safety and traffic efficiency. Automated driving technology is expected to reduce the number of accidents caused by human error and avert deadly crashes, ensure mobility for all, including elderly and impaired individuals, allow the human driver to perform alternative (secondary) tasks, increase traffic flow efficiency, reduce fuel consumption, and lower emissions.

Driven by these goals, humankind is experiencing an exponential growth in vehicle automation, with automated systems taking over the monitoring of surroundings and vehicle control tasks from human drivers in a quest towards full autonomy. Connected and automated vehicles are equipped with multimodal sensors that allow continuous perception and monitoring of driving tasks to assist drivers in lower levels of SAE automation or to fully take control of driving tasks under full SAE automation. Numerous sensors, both inside and outside vehicles, allow the detection and identification of oncoming obstacles, the determination of their velocity, and the prediction of future behaviours to avoid potential collisions. Each sensor has its own strengths and weaknesses in terms of range, accuracy, energy consumption, and sensitivity towards external conditions such as weather and light. Automated vehicles usually rely on a mix of signals to improve operational reliability and robustness under the dynamic external conditions of real-world deployments. Generally, we can divide external AV sensors into two major groups: active and passive. Active sensors generate an active signal (electromagnetic or light) transmitted to the external environment to analyse its reflection (e.g., radar, lidar), whereas passive sensors just record the information from the environment (e.g., camera). Additionally, advances in intelligent transportation infrastructure are enabling real-time monitoring of road users, predictive analytics, remote diagnostics, remote guidance, and collaborative perception services. In this context, digital twins are gaining momentum as a strategic enabler for safe and scalable automated driving. These virtual counterparts of physical systems can integrate real-time sensor data, simulate edge-case scenarios, and support decision-making and functional safety monitoring. Recent developments explore how digital twins can enhance perception accuracy, improve testing pipelines, and support transparency, traceability, and lifecycle management in AI-driven vehicle behaviour.

The increasing commercial availability of conditional automation (SAE level 3) and the emergence of robotaxi services (SAE Level 4) have also fuelled rapid progress in in-cabin monitoring technologies sensors dedicated to monitoring both driver and passenger behaviours. These include systems for detecting driver and passenger behaviours, physiological states, and activity levels, which is critical for managing transitions between automated and manual control safely. In-cabin sensing supports the assessment of driver readiness, detection of fatigue, discomfort, distraction, or stress and monitoring of correct usage of automation.

Furthermore, a new frontier in automotive AI involves the use of generative AI techniques like Large Language Models (LLMs) and agentic AI to enhance perception, decision-making, explainability, and human–machine interactions in and around the vehicle. LLM-based automotive agents are being explored for a range of applications, including the development of automated data annotation, language-guided simulation, scenario generation, and explainable AI pipelines. The new abilities unlocked by the emerging reasoning capabilities of LLMs are powering new use-cases that integrate reasoning over multimodal inputs such as sensor streams, vehicle logs, HD maps and human speech. LLM-powered agents can also serve as intermediaries in infrastructure to vehicle communications transforming raw sensor data into actionable natural-language interpretable messages.

This Special issue aims to collect original theoretical and empirical articles on sensing technologies, agent-based architectures, and AI-driven solutions, and applications for automated vehicles. We welcome interdisciplinary submissions that explore novel uses of external and internal sensing in automotive context. Potential topics include, but are not limited to, the following:

Topics of interest:

• External sensing technologies:
  • Detection and ranging technologies: radar, lidar, sonar, cameras;
  • Localization and mapping: GPS and HD maps;
  • Object detection, classification, and scene segmentation algorithms;
  • Object tracking and prediction algorithms;
  • Data annotation;
  • External HMI;
  • ICT infrastructure.
• Internal sensing technologies:
  • Driver monitoring systems, including related usability acceptance challenges, e.g., privacy;
  • Detection of driver’s physiological states: fatigue, discomfort, sickness, including ‘wearable’ technology;
  • Driver fitness/risk assessment for conditional automation;
  • User experience improvements through sensors.
• Digital twins:
  • Development and deployment of digital twin frameworks for automated and connected vehicles;
  • Simulation-based validation and testing of perception, decision-making, and control algorithms using digital twins;
  • Digital twins for infrastructure–vehicle interaction and collaborative perception;
  • Use of digital twins for explainability, traceability, and lifecycle monitoring in AI-driven mobility systems.
• Applications of Large Language Models (LLMs) in Automotive Industry:
  • LLM applications for automated data annotation and dataset validation to improve the efficiency and quality of labelled data across perception and behaviour modelling tasks;
  • Use of LLMs in scenario generation tools, including language-based test case creation;
  • Application of LLMs to cross-modal information retrieval and summarization across vehicle logs, maps, and sensor data;
  • LLMs use in explainable AI frameworks, to improve interpretable summaries and justifications for AV decisions, predictions, and sensor outputs;
  • LLM-based multimodal agents for in-cabin sensing, combining visual, auditory, and contextual information ;
  • Use of LLM agents in driver/passenger support systems, for contextual assistance, safety feedback, and personalized infotainment recommendations;
  • Implementation of LLM-powered infrastructure-to-vehicle communication agents to translate sensor-rich traffic or road status data into actionable, human-readable messages for AV systems.

Prof. Dr. Jaka Sodnik
Prof. Dr. Ignacio Alvarez
Dr. Eleni Mantouka
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. Sensors 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 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.

• automated and autonomous driving
• vehicle sensing technologies
• sensor fusion
• object detection and identification
• driver monitoring
• large language models in automotive industry