Artificial intelligence (AI) is increasingly applied in a wide range of healthcare and Intensive Care Unit (ICU) areas to serve—among others—as a tool for disease detection and prediction, as well as for healthcare resources’ management. Since sepsis is a high mortality and rapidly developing organ dysfunction disease afflicting millions in ICUs and costing huge amounts to treat, the area can benefit from the use of AI tools for early and informed diagnosis and antibiotic administration. Additionally, resource allocation plays a crucial role when patient flow is increased, and resources are limited. At the same time, sensitive data use raises the need for ethical guidelines and reflective datasets. Additionally, explainable AI is applied to handle AI opaqueness. This study aims to present existing clinical approaches for infection assessment in terms of scoring systems and diagnostic biomarkers, along with their limitations, and an extensive overview of AI applications in healthcare and ICUs in terms of (a) sepsis detection/prediction and sepsis mortality prediction, (b) length of ICU/hospital stay prediction, and (c) ICU admission/hospitalization prediction after Emergency Department admission, each constituting an important factor towards either prompt interventions and improved patient wellbeing or efficient resource management. Challenges of AI applications in ICU are addressed, along with useful recommendations to mitigate them. Explainable AI applications in ICU are described, and their value in validating, and translating predictions in the clinical setting is highlighted. The most important findings and future directions including multimodal data use and Transformer-based models are discussed. The goal is to make research in AI advances in ICU and particularly sepsis prediction more accessible and provide useful directions on future work.

Unmanned Aerial Systems (UAS) have rapidly gained attraction in recent years as a promising solution to revolutionize numerous applications and meet the growing demand for efficient and timely delivery services due to their highly automated operation framework. Beyond Visual Line of Sight (BVLOS) operations, in particular, offer new means of delivering added-value services via a wide range of applications. This "plateau of productivity" holds enormous promise, but it is challenging to equip the drone with affordable technologies which support the BVLOS use case. To close this gap, this work showcases the convergence of the automotive and aviation industries to advance BVLOS aviation for UAS in a practical setting by studying a combination of Commercial Off-The-Shelf (COTS) technologies and systems. A novel risk-based approach of investigating the key technological components, architectures, algorithms, and protocols is proposed that facilitate highly reliable and autonomous BVLOS operations, aiming to enhance the alignment between market and operational needs and to better identify integration requirements between the different capabilities to be developed.

The deployment of autonomous robots in harsh and unpredictable environments has gained significant attention in recent years, driven by the need to improve safety and efficiency in tasks where human involvement poses significant risks. Technological advances in sensors and communication technologies, as well as the proliferation of AI, have catalysed the development of highly capable and robust robotic systems in diverse scenarios, optimising efficiency, particularly in the area of disaster response. However, despite the progress made in the field of autonomous Search and Rescue (SAR) operations in harsh environments, several challenges remain unresolved. This paper presents a comprehensive overview of the key technological advancements in components, algorithms and communication systems and how they facilitate highly efficient and robust autonomous missions in extreme subterranean conditions and SAR operations. Additionally, this paper aims to tackle some of the key challenges encountered during emergency response operations through a novel autonomous robotic design that leverages locomotion, perception, communication, and control capabilities to achieve effective exploration tasks in harsh and hazardous environments. Finally, it sets the scene for future enhancements in the area of autonomous and intelligent robots, suggesting potential avenues for further research and development in enhancing their capabilities and adaptability.

The exploration of the underwater environments has recently accelerated with the development of the Autonomous Underwater Vehicle (AUV). One of the key elements for enhancing the autonomy of AUVs navigation across various applications is efficient path planning. Reinforcement Learning (RL) methods have been successfully introduced for path planning of AUVs, particularly in high-dimensional state spaces, where prior knowledge of the environment is unfeasible. In this work, we propose a Deep Reinforcement Learning (DRL) method for efficient AUV navigation in 3 Dimension (3D) environments, utilizing input from vision sensors to obtain information about the motion of the AUV and the surrounding space. We adopt a multi-tier approach in order to validate the performance of the proposed DRL approach in three different neural network architectures leveraging on adaptation and accuracy, with path length, execution time and success of operation being considered as the optimization objectives. Finally, a simulation platform is built to evaluate the performance of the proposed method, with experimental results showcasing enhanced decision-making capability for the AUV navigation, which translates to a higher level of autonomy for the vehicle in unknown environments.

The emergence of Connected and Autonomous Vehicles (CAVs) has revolutionized the transportation landscape paving the way for enhanced traffic mobility and innovative and sustainable transportation. Autonomous vehicles rely on sensor data to obtain information of the internal state of the system and the impact of the external environment to achieve self-driving autonomy. In that sense, anomalies in sensor readings may reflect faults in sensor components, which in turn can compromise the decision-making functionality of the autonomous system. Video Anomaly Detection (VAD) serves as a pivotal technology in intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within video frames. This paper proposes a supervised video anomaly assessment framework for autonomous vehicles leveraging Image Quality Assessment (IQA) and Drift Detection techniques. On this basis we adopt a two-stage approach to validate the performance of the proposed methods against a baseline Convolutional Neural Network (CNN) in a controlled low-criticality environment, as well as in more complex real-world scenarios. Our experimental results demonstrate high accuracy and robustness for anomaly detection in comparison to existing supervised techniques, which is crucial for real-time and autonomous operations of CAVs.

Autonomous driving stands at the forefront of next-generation mobility, driven by advances in Artificial Intelligence (AI), deep learning, and real-time sensor data processing. While Foundation Models (FMs)—large, pre-trained neural networks capable of generalizing across tasks—have revolutionized fields such as natural language processing and computer vision, their integration into autonomous driving remains limited and fragmented. This paper addresses this critical gap by systematically reviewing the application of FMs across the autonomous driving pipeline, from perception and scene understanding to reasoning, planning, and synthetic dataset generation. We classify over 70 models by architecture, modality, task type, and input/output structure, and provide a unified framework for understanding their role in intelligent vehicle systems. Key contributions include: (i) a taxonomy of FMs deployed in perception, reasoning, and control; (ii) identification of current limitations in real-time deployment, interpretability, and safety assurance; and (iii) emerging trends such as prompt-based fine-tuning, multimodal grounding, and generative scenario synthesis. Our findings highlight both the opportunities and challenges of incorporating FMs into safety-critical autonomous systems and outline promising directions for future research in edge-efficient, robust, and explainable FM-based driving models.