The rapid growth of Autonomous Aerial Vehicles (AAVs) has underscored their importance across commercial and civil applications. Combining multi-AAVs with Deep Reinforcement Learning (DRL) approaches can achieve significant results, particularly in navigation and path-planning operations. Nevertheless, collaborative decision-making among AAV swarms faces major challenges, including handling partial observability and re-path planning under uncertainty. To address these challenges, we propose an Adaptive Distributional deep Q-network Graph ATtention (ADGAT) learning framework with a Partially Observable Markov Decision Process (POMDP) modeling approach to perform effective AAV swarm navigation. The proposed ADGAT framework combines an adaptive Distributional Deep Q-Network (Di-DQN) reinforcement learning algorithm with a multi-head Graph Attention (GAT) mechanism to enable effective decision-making by distributing rewards rather than estimating the expected value. Additionally, the GAT mechanism enhances each AAV's capabilities by aggregating information from neighboring AAVs. We compare the proposed ADGAT framework against state-of-the-art baselines and validate it using three key performance metrics, achieving an average success rate of 98%, a collision rate of 3%, and a path efficiency of 96%. The extensive simulation results prove the adaptability of the ADGAT framework for enhancing AAV swarm navigation in partially observable spaces.

Open-RAN is transforming 5G and Beyond-5G networks by promoting openness, flexibility, and interoperability across network components. However, this architectural shift introduces new security challenges due to expanded attack surfaces, distributed control mechanisms, and exposed interfaces. Traditional Intrusion Detection Systems (IDS) struggle to address the dynamic threat landscape of O-RAN environments. To address this challenge, we propose ORANGuard, an Artificial Intelligence-driven dual-tier intrusion detection and mitigation framework for O-RAN environments. ORANGuard comprises two core modules: Real-Time Guard (RT-Guard), a real-time threat detection model deployed in the Near-Real-Time RAN Intelligent Controller (Near-RT RIC), and Non-Real-Time Guard (NRT-Guard), a periodic anomaly analysis model operating within the Non-Real-Time RIC, together enabling multi-level threat detection. The framework is built on an end-to-end 5G O-RAN testbed using srsRAN and Open5GS, capturing E2 measurements under both benign and attack conditions. Custom scripts simulated anomalous scenarios, including DDoS, producing a dataset of 17,052 E2 measurement records across a testbed of 4 gNodeBs and 12 UEs. RT-Guard, based on Random Forest, achieved 96.7% accuracy, while NRT-Guard, using an Autoencoder, reached 95.6%. The hierarchical dual-tier decision rule achieved 99.5% accuracy on the held-out test set. RT-Guard required a median detection latency of 5.2 ms and a median detect-and-enforce latency of 17.9 ms, whereas NRT-Guard required 283.6 ms after closure of its one-second analysis window. These results demonstrate the complementary low-latency and anomaly-analysis capabilities of ORANGuard for O-RAN security.

Accurate, real-time collision detection is essential for ensuring player safety and effective refereeing in high-contact sports such as rugby, particularly given the severe risks associated with traumatic brain injuries (TBI). Traditional collision-monitoring methods employing fixed cameras or wearable sensors face limitations in visibility, coverage, and responsiveness. Previously, we introduced a framework using unmanned aerial vehicles (UAVs) for monitoring and real time kinematics extraction from videos of collision events. In this paper, we show that the strategies operating on the objective of ensuring at least one UAV captures every incident on the pitch have an emergent property of fulfilling a stronger key condition for successful kinematics extraction. Namely, they ensure that almost all collisions are captured by multiple drones, establishing multi-view fidelity and redundancy, while not requiring any drone-to-drone communication.

We present a reinforcement learning strategy for use in multi-agent foraging systems in which the learning is centralised to a single agent and its model is periodically disseminated among the population of non-learning agents. In a domain where multi-agent reinforcement learning (MARL) is the common approach, this approach aims to significantly reduce the computational and energy demands compared to approaches such as MARL and centralised learning models. By developing high performing foraging agents, these approaches can be translated into real-world applications such as logistics, environmental monitoring, and autonomous exploration. A re-ward function was incorporated into this approach that promotes role development among agents, without explicit directives. This led to the differentiation of behaviours among the agents. The implicit encouragement of role differentiation allows for dynamic actions in which agents can alter roles dependent on their interactions with the environment without the need for explicit communication between agents.

The problem of robotic synchronisation and coordi-nation is a long-standing one. Combining autonomous, comput-erised systems with unpredictable real-world conditions can have consequences ranging from poor performance to collisions and damage. This paper proposes using coupled oscillators to create a drone swarm that is decentralised and self organising. This allows for greater flexibility and adaptiveness than a hard-coded swarm, with more resilience and scalability than a centralised system. Our method allows for a variable number of drones to spontaneously form a swarm and react to changing swarm conditions. Additionally, this method includes provisions to prevent communication interference between drones, and signal processing techniques to ensure a smooth and cohesive swarm.

O-RAN (Open-Radio Access Network) offers a flexible, open architecture for next-generation wireless networks. Network slicing within O-RAN allows network operators to create customized virtual networks, each tailored to meet the specific needs of a particular application or service. Efficiently managing these slices is crucial for future 6G networks. O-RAN introduces specialized software applications called xApps that manage different network functions. In network slicing, an xApp can be responsible for managing a separate network slice. To optimize resource allocation across numerous network slices, these xApps must coordinate. Traditional methods where all xApps communicate freely can lead to excessive overhead, hindering network performance. In this paper, we address the issue of xApp conflict mitigation by proposing an innovative Zero-Touch Management (ZTM) solution for radio resource management in O-RAN. Our approach leverages Multi-Agent Reinforcement Learning (MARL) to enable xApps to learn and optimize resource allocation without the need for constant manual intervention. We introduce a Graph Convolutional Network (GCN)-based attention mechanism to streamline communication among xApps, reducing overhead and improving overall system efficiency. Our results compare traditional MARL, where all xApps communicate, against our MARL GCN-based attention method. The findings demonstrate the superiority of our approach, especially as the number of xApps increases, ultimately providing a scalable and efficient solution for optimal network slicing management in O-RAN.

Parameterized Quantum Circuits (PQCs) with fixed structures severely degrade the performance of Quantum Machine Learning (QML). To address this, a Hybrid Quantum-Classical Classifier (HQCC) is proposed. It adaptively optimizes the PQC through a dynamic circuit generator driven by Long Short Term Memory (LSTM) and exploits architectural plasticity to balance the entanglement performance and expressiveness, opening up a practical pathway for efficiently deploying QML in the Noisy Intermediate-Scale Quantum (NISQ) era. Extensive experiments on MNIST and Fashion-MNIST demonstrate that HQCC achieves up to 99.86% accuracy in binary classification and 97.12% in multi-class tasks, surpassing state-of-the-art quantum and classical baselines.

Recent advancements in uncrewed aerial vehicle (UAV) technology have opened new avenues for dynamic data collection in challenging environments, such as sports fields during fast-paced sports action. For the purposes of monitoring sports events for dangerous injuries, we envision a coordinated UAV fleet designed to capture high-quality, multiview video footage of collision events in real time. The extracted video data are crucial for analyzing athletes’ motions and investigating the probability of sports-related traumatic brain injuries (TBIs) during impacts. This article implemented a UAV fleet system on the NetLogo platform, utilizing custom collision observation algorithms to compare against traditional television (TV)-coverage strategies. Our system supports decentralized data capture and autonomous processing, providing resilience in the rapidly evolving dynamics of sports collisions. The collaboration algorithm integrates both shared and local data to generate multistep analyses aimed at determining the efficacy of custom methods in enhancing the accuracy of TBI prediction models. Missions are simulated in real time within a 2-D model, focusing on the strategic capture of collision events that could lead to TBI, while considering operational constraints such as rapid UAV maneuvering and optimal positioning. Preliminary results from the NetLogo simulations suggest that custom collision record methods offer superior performance over standard TV-coverage strategies by enabling more precise and timely data capture. This comparative analysis highlights the advantages of tailored algorithmic approaches in critical sports safety applications.

In this study, we develop an in silico model of a neuron’s behaviour under demyelination caused by a cytokine storm to investigate the effects of viral infections in the brain. We use a comprehensive model to measure how cytokine-induced demyelination affects the propagation of action potential (AP) signals within a neuron. We analysed the effects of neuron-neuron communications by applying information and communication theory at different levels of demyelination. Our simulations demonstrate that virus-induced degeneration can play a role in the signal power and spiking rate, which compromise the propagation and processing of information between neurons. We propose a transfer function to model the weakening effects on the AP. Our results show that demyelination induced by a cytokine storm not only degrades the signal but also impairs its propagation within the axon. Our proposed in silico model can analyse virus-induced neurodegeneration and enhance our understanding of virus-induced demyelination.

Post-disaster scene understanding frameworks are increasingly crucial in Search And Rescue (SAR) operations. Unmanned Aerial Vehicles (UAVs) provide an efficient means to carry out the task of scene understanding due to the higher altitudes at which they function. However, complex environments in post-disaster scenarios make it difficult for UAVs to detect humans or objects accurately. Inefficient object detection mechanisms lead to low accuracy for object detection tasks. Hence, to mitigate these issues, we propose a UAV and GAN-aided Ensemble Network (UGEN) framework for efficient ORAN-based post-disaster survivor detection. This approach deploys a Context-Conditional Generative Adversarial Network (CCGAN)-based model to remove occlusion in the images obtained from the UAVs. The UGEN framework classifies entities present in the visual scope of the UAV using a semantic segmentation framework deployed on the CCGAN-enhanced images, resulting in a pixel-level prediction of entities present in the post-disaster images. An ensemble network comprising a combination of single-stage and multi-stage detectors detects survivors present in the post-disaster scenario, thereby combining the benefits of both architectures, resulting in a reduced false negative rate and improved performance. An Open Radio Access Network (ORAN) executes data propagation between the UAV and the ground station for reduced transmission latency. The proposed model achieved a survivor detection accuracy of 96.7%.

This paper proposes a decentralized planning constructed as a cyber-physical system to jointly manage supply and demand, including aspects related to production and circulation, without the mediation of money. Our aim is to provide a concrete technical solution for a future society based on communizing and commons-based resource allocation as an attempt to move in-against-and-beyond the value-form, which is the social “force-field” that characterizes the capitalist mode of production. This contribution is divided into three articulated parts: (i) a review of the elementary forms that jointly determine the capitalist social organization, (ii) a defense of the proposition that the money-form must be destroyed to enable a new mode of production based on communizing, and (iii) a proposal of a cyber-physical implementation of a jointly decentralized production planning and resource allocation over large infrastructures that enable a multilevel polycentric governance as a variation of the Interactive Economic Planning and Optimized Selections (I-EPOS) algorithm when coordination is needed.

This work introduces a new perspective for physical media sharing in multiuser communication systems by proposing a novel scheme that enables the recovery of the content of the transmitted message whenever collisions happen. An alarm monitoring system is taken as a merely illustrative toy-model, but indeed the framework is generally applicable. In this scenario, the alarm system is designed to first decide whether a predetermined event has happened over a certain period; if such an event has been identified, the decision node also needs to correctly classify from which sensor the message comes. Simulations corroborate the effectiveness of the proposed method in terms of the event transmission efficiency, when compared with variations of conventional methods like TDMA and slotted ALOHA.