Vehicles traditionally comprise a body, an internal combustion engine, steering, braking, and electrical systems. This basic design quickly moves towards a rich ecosystem assembling complex networking, software, and computing resources. The still-evolving computing power inside cars aims to completely change the driving experience by using AI-powered assistance and, eventually, by allowing autonomous driving operation. This substantial change faces many strategic R&D issues for manufacturers, where drivers’ safety, automation, and decarbonization are top targets.

Today, the interplay between cars and clouds via more and more sophisticated software can provide intelligent services, making cloud computing a fundamental piece of the vehicular puzzle. Vehicles export all the data collected from different internal control units to the manufacturers’ cloud or to authorized third parties for analytics and service customization. In the cloud, driving assistance, including secure and eco-friendly driving, infotainment, and predictive or reactive maintenance, heavily rely on AI models. On the one hand, large volumes of data need to be transferred, requiring high-capacity wireless links. Also, data transmission and remote processing raise privacy concerns as data may carry drivers’ sensitive content.

Vehiclouds 2024 focuses on all challenges involving vehicular technologies for cloud-assisted AI computation. A non-exhaustive list of topics of interest is seen below:

Connected Vehicles (CVs) and Software Defined vehicles (SDVs);
Radio technologies for vehicular networks and emerging technologies;
Integrated sensing and communication (ISAC) / joint communication and sensing (JCAS) with cloud integration;
V2X communications (vehicles, road-side units, infrastructure, pedestrians), vehicular ad-hoc networks, and cloud integration;
Cloud-based Advanced Driver-Assistance Systems (ADAS) and Autonomous Vehicles (AVs);
Connected Vehicles data quality, selection, transmission, and storage;
Network security and trust execution environments for vehicular systems;
Data privacy management;
Cloud and mobile edge computing collaboration;
In-Vehicle Cloud Computing and Applications;
Cloud-enabled telematics and Fleet Management Systems (FMS);
AI-aided mechanisms for communication and applications;
Emerging Machine Learning (ML) techniques for vehicular data analysis and modeling (e.g., Federated Learning);
Applied ML for driver behavior analysis, fleet management, predictive maintenance, anomaly detection, navigation, recharging optimization, and other vehicle-related applications;
Innovative services and smart mobility solutions;
Vehicle digital twin of a vehicle;
Sustainability and energy efficiency with Connected Vehicles.