Maritime domain awareness increasingly relies on Automatic Identification System (AIS) data. Yet, traditional monolithic backends struggle to scale with rising message volumes and offer limited resilience, data sovereignty, or rapid deployability. This study addresses the challenges by introducing a novel federated learning and microservices architecture for distributed vessel tracking. Each end node trains local models on a proprietary AIS Maritime environment via Dockerized microservices: Data Pre-Processor, Client Trainer, Aggregator, Global Model Updater, and XAI Service, enabling independent scaling, fault isolation, and federated governance without exposing raw feeds. A global model is aggregated using FedAvg and served with a sub-second latency of 10 ms of aggregation and 406 ms of inference. Experimental evaluation on four benchmark AIS snapshots yields strong predictive performance (MAE = 0.31, RMSE = 0.39, R2 = 0.78) and demonstrates transparent feature attribution via SHAP. These results validate the proposed architecture’s capability to deliver accurate, low-latency energy predictions while preserving data sovereignty and cross-node consistency. This study lays the foundation for robust, interoperable maritime analytics by bridging microservice agility with federated intelligence and XAI.

Haptic bilateral teleoperation holds promise for applications such as telemaintenance, remote manipulation, and disaster response, yet delivering precise, low-latency force and video feedback remains challenging. This study advances haptic bilateral teleoperation by combining live video with Model Mediated Teleoperation (MMT) to enable predictive force feedback. While this method has benefits, several non-trivial challenges, such as synchronizing the model with user's and remote robot's actions, arise. A novel algorithm is developed that allows the robotic device to replicate interactions predictively experienced by the operator. We validated this approach in a fully functional system that performs reliably despite significant network delays. The latency performance of the system is extensively characterized, achieving a motion-to-pixel latency of 58 ms. A user study revealed that operators did not perceive network latency of at least 75 ms, resulting in a 133 ms motion-to-pixel delay requirement. Additionally, a 5G latency analysis demonstrated that effective haptic teleoperation is achievable with both operator and remote ends connected via 5G. This provides a path away from strict latency requirements toward practical teleoperation solutions using currently available technology.

This article presents an overview of how Artificial Intelligence (AI) and edge technology have been used to improve wireless connectivity in multiple industrial Use Cases (UCs) of the EU project “Intelligent Secure Trustable Things” (InSecTT). We present a brief introduction of the InSecTT framework for cross-domain architecture design, which targets UCs assisted by reusable and/or interoperable technical Building Blocks (BBs). These BBs constitute the “bricks” containing AI and supporting components that were used to build different UCs. The framework consists of multiple stages based on the processing of UC/BB requirements (RQs). These stages include collection, harmonization, refinement, classification, architecture alignment, and functionality modeling of RQs. The most relevant results of these stages are discussed here, with emphasis on the need for a refined granularity of technical components with common functionalities named Sub-Building blocks (SBBs), where collaboration and cross-domain reusability were optimized. The design process shed light on how AI and SBBs were implemented across different layers and entities of our reference architecture for the Internet-of-Things (IoT), including the interfaces used for information exchange. This detailed interface analysis is expected to reveal issues such as bottlenecks, constraints, vulnerabilities, scalability problems, security threats, etc. This will, in turn, contribute to identifying design gaps of AI-enabled IoT systems. The article summarizes the SBBs related to wireless connectivity, including a general description, implementation issues, a comparison of results, adopted interfaces, and conclusions across domains.

The efficient execution of inferences at the edge is becoming increasingly critical for communication systems that are expected to provide users with fast and accurate mobile data analytics. These inference tasks are inherently latency-sensitive and computationally demanding, whereas edge nodes are limited by energy budgets and heterogeneous resources. This article studies how a set of edge nodes can collaborate in executing demanding streaming inference tasks to optimize their aggregate performance. Such collaborative task exchange schemes enable the sharing of scarce computing resources and machine learning (ML) models (which perform the inferences) and constitute a scalable approach to this intricate problem. We formulate this exchange process as an online convex optimization (OCO) problem and design a dynamic task assignment algorithm, which is proven to have optimality guarantees even when the network and service parameters (resources and task properties) are unknown and vary arbitrarily over time. The algorithm aims to maximize inference accuracy while minimizing overall task latency and energy (including for data transfers) and simultaneously ensures that collaborating nodes do not suffer imbalanced energy costs. Through a series of data-driven experiments, we quantify the cooperation benefits under different weight combinations and validate the convergence and adaptability of the proposed learning algorithm across diverse conditions, including variations of system parameters, as well as heterogeneity across nodes and tasks.

We present a novel concept of an electromagnetic mechanism for shifting the centre of gravity (CoG) in a small unmanned aerial vehicle with four rotors (quadrotor). Shifting the CoG is essential for controlling drones in which the thrust is unbalanced (e.g., upon the failure of one of the drives). The concept presented here involves using electromagnetic coils mounted under the drone and moving permanent magnets inside a cylindrical tube. Moving the positions of the masses can be controlled by means of currents in the coils. Changing the position of the magnets relative to the arms of the drone causes a shift in the CoG, allowing for controllability even when one of the four engines is not working, and making it possible for the drone to land safely. This article describes the geometrical and mechanical relationships in the proposed system, the design and numerical calculations of the electromagnetic mechanism with coils and permanent magnets, as well as the results of a simulation of the control variant. Additionally, the practical implementation of the mechanism, from CAD modelling through the manufacturing of its elements to the final structure prepared for mounting on a quadrotor, is discussed.

Haptic teleoperation is a promising technology with applications in telemaintenance and disaster management. However, it faces significant challenges when the application is subjected to a high network latency and environments with moving objects. This work aims to extend Model Mediated Teleoperation (MMT) to overcome challenges in supporting dynamic environments. Instead of striving for perfect model alignment, we acknowledge the inevitable mismatch between the remote environment and its model at the operator. We propose a set of design principles and an accompanying framework for designing MMT solutions that prioritize operator intent. Our approach is exemplified through an application where an operator, located 8000 km away (The Netherlands - India) and subjected to an average of 179 ms end-to-end latency, guides a robot arm to draw on a whiteboard whose position is actively altered. We evaluate the effectiveness of our approach through a user study. We show a 3-point improvement on a 7-point Likert scale when users utilize our approach to teleoperate over significant network latency of up to 1 s.

Autonomous Underwater Vehicles (AUVs) face persistent challenges in localization compared to their counterparts on the ground due to limitations with methods like Global Positioning System (GPS). We propose a novel system for localization, Pisces, that leverages the Angle of Arrival (AoA) and Received Signal Strength Ratio (RSSR) of robot-mounted blue LED signals. This method provides a spectrally efficient training-free solution for estimating 3D underwater positions. The system remains effective despite high water turbidity with a relatively low impact on marine life compared to similar acoustic methods. Pisces is less complex, computationally efficient, and uses less power than camera-based solutions. Pisces enables robust relative localization, especially in swarms of robots with the potential for additional applications like docking. We demonstrate high localization accuracy with a Mean Absolute Error (MAE) of 0.031 m at 0.32 m separation and 0.16 m MAE at 1 m separation. Moreover, it achieved this with minimal power consumption, utilizing only 11 mA of transmitter LED current and performing 3D localization within 10 ms for distances up to 3 m.

To address the critical need for secure IoT networks, this study presents a scalable and lightweight Curriculum Learning framework enhanced with Explainable AI (XAI) techniques, like LIME, to ensure transparency and adaptability. The proposed model employs a novel neural network architecture utilized at every stage of Curriculum Learning to efficiently capture and focus on both short- and long-term temporal dependencies, improve learning stability, and enhance accuracy while remaining lightweight and robust against noise in sequential IoT data. Robustness is achieved through staged learning, where the model iteratively refines itself by removing low-relevance features and optimizing performance. The workflow includes edge-optimized quantization and pruning to ensure portability that could easily be deployed in edge IoT devices. An ensemble model incorporating Random Forest, XGBoost, and the staged learning base further enhances generalization. The results demonstrate 98% accuracy on CIC-IoV-2024 and CIC-APT-IIoT-2024 datasets and 97% on EDGE-IIoT, establishing this framework as a robust, transparent, and high-performance solution for IoT network security.

This chapter presents a summary of the description and preliminary results of the use case related to the implementation of artificial intelligence tools in the emerging technology called wireless avionics intra-communications (WAICs). WAICs aims to replace some of the cable buses of modern aircraft. This replacement of infrastructure leads to: (1) complexity reduction of future airplanes, (2) creation of innovative services where wireless links are more flexible than wireline links, and mainly (3) a considerable weight reduction, which in turn leads to fuel consumption efficiency, increase of payload, as well as range extension. Therefore, WAICs is expected to have a large impact on the aeronautics industry, propelling a new generation of greener, more efficient, and less expensive aeronautical services. However, there are still several reliability, trust, interoperability and latency issues that need to be addressed before this technology becomes commercial. It is expected that AI will boost the applicability of this technology, contributing to the realization of the concept of “fly-by-wireless”.

Mapping the spatial distribution of soil organic carbon (SOC) is crucial for monitoring soil health, understanding ecosystem functions, and contributing to global carbon cycling. However, few studies have directly compared the influence of hybrid models and individual models with varying spatial resolutions on SOC prediction at a national scale. In this study, by combining remote sensing data, we utilized the LUCAS 2018 soil dataset to evaluate the potential capacities of hybrid models for predicting SOC content at different spatial resolutions in Germany. The hybrid models PLSRK and RFK consisted of partial least square regression (PLSR) with residual original kriging (OK) models, and random forest (RF) models with residual OK models, respectively. Individual PLSR and RF models were used as reference models. All these models were applied to estimate SOC content at 10 m, 50 m, 100 m, and 200 m spatial resolutions. Sentinel-2 bands, band indices, and topography variables were as predictors. The results revealed that hybrid models had a more accurate prediction of SOC content with higher explanations and lower prediction errors compared with individual models. The RFK model at the spatial resolution of 100 m was the fittest model with R² = 0.416, RMSE = 0.545, and RPIQ = 1.647, which enhanced 3.74% of explanation compared with the performance of RF model. The results also showed that hybrid models at a relatively coarse resolution (100 m) had better accuracy instead of those at high spatial resolution (10 m, 50 m). Sentinel-2 remote sensing data showed significant predictive capabilities for estimating SOC content. The predicted spatial distribution of SOC content revealed that the high SOC concentrated in the northwest grassland, central and southwestern mountains, and the Alps in Germany. Our study provided a benchmark SOC map in Germany for monitoring the changes resulting from land use and climate impacts, and we illustrated the accuracy of hybrid models and the effects of spatial resolutions on SOC predictions at a national scale.

Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exist. To get insights into the strengths and weaknesses of DRL versus ESs, an analysis of their respective capabilities and limitations is provided. After presenting their fundamental concepts and algorithms, a comparison is provided on key aspects, such as scalability, exploration, adaptation to dynamic environments, and multiagent learning. Current research challenges are also discussed, including sample efficiency, exploration versus exploitation, dealing with sparse rewards, and learning to plan. Then, the benefits of hybrid algorithms that combine DRL and ESs are highlighted.

Smart autonomous vehicles can cooperatively drive as platoons offering benefits like enhanced safety, traffic efficiency, and fuel conservation. While traditionally platoons have followed a single-lane, train-like structure they face challenges when scaling that include communication range limitations and lane-change difficulties. In this article, we propose a new paradigm of multi-lane platoons that spreads platoons across multiple lanes. We explore the characteristics of multi-lane platoons particularly focusing on communication parameters. Additionally, we propose a cross-layer mechanism to seamlessly integrate this concept within the existing communication standard, ETSI. Our work significantly enhances platoon communication performance in mixed traffic scenarios and we propose optimizations to improve its effectiveness.

The next frontier in communications is teleoperation - manipulation and control of remote environments with haptic feedback. Compared to conventional networked applications, teleoperation poses widely different requirements, ultra-low latency (ULL) is primary. Realizing ULL communication demands significant redesign of conventional networking techniques, and the network infrastructure envisioned for achieving this is termed as Tactile Internet (TI). The design of meaningful performance metrics is crucial for seamless TI communication. However, existing performance metrics fall severely short of comprehensively characterizing TI performance due to their inability to capture how well sensed signals are reproduced. We take Dynamic Time Warping(DTW) as the basis of our work and identify necessary changes for characterizing TI performance. Through substantial refinements to DTW, we design Effective Time- and Value-Offset (ETVO) - a new method for measuring the fine-grained performance of TI systems. Through an in-depth objective analysis, we demonstrate the improvements of ETVO over DTW. Through subjective experiments, we demonstrate that existing QoS and QoE methods fall short of estimating the TI session performance accurately. Using subjective experiments, we demonstrate the behavior of the proposed metrics, their ability to match theoretically derived performance, and finally, their ability to reflect user satisfaction in a practical setting.

We present HUM-High-frequency UAV Messaging: an acoustic side channel communication system we design for localized drone-to-drone communications. We generate Pulse Width Modulated (PWM) signals from drone motors to carry information and improve communication reliability by mitigating propeller noise interference through modifications to the propeller's physical design. These modifications reduce propeller noise in the designated acoustic spectrum by up to 7 dB. We deploy a custom ultrasonic microphone shield specifically designed for decoding in the receiver. HUM's improved signal-to-noise ratio enables up to 80x higher data rates compared to the existing design from the literature while providing better scalability. HUM supports simultaneous decoding across 16 drones within 8 m, range as seen in real flight tests. The cost of this performance is minimal; we experimentally demonstrate that HUM has a marginal impact on flight dynamics and battery life.

Healthy urban greenery is a fundamental asset to mitigate climate change phenomena such as extreme heat and air pollution. However, urban trees are often affected by abiotic and biotic stressors that hamper their functionality, and whenever not timely managed, even their survival. While the current greenery inspection techniques can help in taking effective measures, they often require a high amount of human labor, making frequent assessments infeasible at city-wide scales. In this article, we present GreenScan, a ground-based sensing system designed to provide health assessments of urban trees at high spatio-temporal resolutions, with low costs. The system uses thermal and multispectral imaging sensors fused using a custom computer vision model to estimate two tree health indexes. The evaluation of the system was performed through data collection experiments in Cambridge, USA. Overall, this work illustrates a novel approach for autonomous mobile ground-based tree health monitoring on city-wide scales at high temporal resolutions with low costs.

With the advent of the multimodal immersive communication system, people can interact with each other using multiple devices for sensing, communication and/or application level control either onsite or remotely. As a breakthrough concept, a distributed sensing, computing, communications, and control (DS3C) fabric is introduced in this paper for provisioning 6G services in multi-tenant environments in a unified manner. The DS3C fabric can be further enhanced by natively incorporating intelligent algorithms for network automation and managing networking, computing, and sensing resources efficiently to serve vertical use cases with extreme and/or conflicting requirements. As such, the paper proposes a novel end-to-end 6G system architecture with enhanced intelligence spanning across different network, computing, and business domains, identifies vertical use cases and presents an overview of the relevant standardisation and pre-standardisation landscape.

Urban greenery supports cities in achieving Sustainable Development Goals, but it is increasingly affected by multiple stressors impacting its health. Owing to the high costs of greenery inspection and monitoring, local governments often lack adequate data to effectively manage their urban greenery and prevent damage. In this Review, we present an overview of technology-supported methods and tools to measure the health of urban greenery and discuss the space–time resolution trade-offs associated with the various methods presented. To inform researchers and policymakers in global cities, we highlight how high-resolution urban greenery health data can support in achieving Sustainable Development Goals at scale.

The increasing popularity of helium-assisted blimps for extended monitoring or data collection applications is hindered by a critical limitation-single-point failure when the balloon malfunctions or bursts. To address this, we introduce Janus, a hybrid blimp-drone platform equipped with integrated balloon failure detection and recovery capability. Janus employs a triggered mechanism that seamlessly transitions the platform from a blimp to a standard quad-rotor drone. Utilizing multiple sensors and fusing their readings, we have developed a robust balloon failure detection system. Janus demonstrates omnidirectional mobility in blimp mode and transitions promptly into quadrotor mode upon receiving the signal. Our results affirm the successful recovery of the system from balloon failure, with a rapid response time of 66 ms to balloon failure detection. The drone morphs into a quadrotor and achieves recovery within 0.362 seconds in 90% of cases. By amalgamating the enduring flight capabilities of blimps with the agility of quad-rotors within a morphing platform like Janus, we cater to applications demanding both prolonged flight duration and enhanced agility.

The recent spate of natural disasters such as earthquakes and floods destroyed buildings and caused loss of lives. Many times, the loss of life is attributed to slow response and not being able to reach the survivors. In such scenarios, the staggering number of deaths in the aftermath of a disaster can be reduced if information about survivors under debris is available to first responders and rescue workers. Large-scale destruction of roads and other communication infrastructure makes it hard to deploy advanced technologies for life detection. We explore the possibility of using low-cost, low-power, short-range communication technologies to assist rescue personnel in locating life under debris. We have designed and prototyped a thermopile-based sensor and communication device that provides information about the presence of survivors. The system weighs under 20 gm and costs US $30 per unit. The device can easily be fitted on battery-powered toy bugs and robots that can autonomously maneuver under the debris. We have proposed three simple algorithms, which together detect humans with 100% to 88% accuracy for 0.5 to 4.5 m range with fewer false alarms. Our evaluation shows that the detection is robust enough under several harsh ambient conditions, temperature ranges as well and partial exposure of the human body.