Nowadays, unmanned aerial vehicle (UAV) communication systems are commonly considered as one of the key enabling technologies for 6G. The hybrid free space optical (FSO)/radio frequency (RF) system has the advantages of both FSO and RF links to improve communication system performance, and the relay-assisted system adopts multi-hop transmission and cooperative diversity methods to extend communication coverage. Thus, a joint consideration of UAV-assistedUAV assisted relay in hybrid FSO/RF transmission is meaningful. In this paper, we aim to analyze the performance of UAV-assisted multi-hop parallel hybrid FSO/RF communication systems with and without pointing errors (PE) in terms of Bit Error Rate (BER) and outage probability. In our considered system, the FSO sub-link adopts the Exponential Weibull turbulence model and the RF sub-link suffers the Nakagami fading model. With these, new mathematical formulas of both BER and outage probability are derived under the UAV-assisted hybrid FSO/RF with different modulation methods. Through numerical evaluationnumerical simulations, the performances of UAV-assisted hybrid FSO/RF systems are analyzed under different weather conditions, modulation methods, optical receiver aperture, RF fading parameters, pointing errors, and relay structures. The results demonstrate that (1) compared to hybrid FSO/RF direct links, UAV-assisted hybrid FSO/RF systems can further improve system performance; (2) the performance of UAV-assisted hybrid FSO/RF systems varies with different relay structures; (3) large receiver aperture and RF fading parameters can further improve the communication performance of hybrid FSO/RF direct links and UAV-assisted hybrid FSO/RF systems.

In intelligent multi-agent systems, particularly in drone combat scenarios, the challenges posed by rapidly changing environments and incomplete information significantly hinder effective strategy optimization. Traditional multi-agent reinforcement learning (MARL) approaches often encounter difficulties in adapting to the dynamic nature of adversarial environments, especially when enemy strategies are subject to continuous evolution, complicating agents’ ability to respond effectively. To address these challenges, this paper introduces a novel enhanced MARL framework, MADDPG-SASP, which integrates an improved self-attention mechanism with self-play within the MADDPG algorithm, thereby facilitating superior strategy optimization. The self-attention mechanism empowers agents to adaptively extract critical environmental features, thereby enhancing both the speed and accuracy of perception and decision-making processes. Concurrently, the adaptive self-battling mechanism iteratively refines agent strategies through continuous adversarial interactions, thereby bolstering the stability and flexibility of their responses. Empirical results indicate that after 600 rounds, the win rate of agents employing this framework saw a substantial increase, rising from 26.17% with the original MADDPG to a perfect 100%. Further validation through comparative experiments underscores the method’s efficacy, demonstrating considerable advantages in strategy optimization and agent performance in complex, dynamic environments. Moreover, in the Predator–Prey Scenario combat environment, when the enemy side employs a multi-agent strategy, the win rate for the drone agent side can reach 98.5% and 100%.

Skeleton-based action recognition algorithms have made extensive use of graph topologies to model the connections between human skeletal joints. Constructing graph topology models with greater representational power is key to obtaining powerful feature extractors. However, existing methods are not as effective in achieving stronger modelling of associations between physically connected joints in the human skeleton. To tackle these concerns, we put forward an innovative approach involving a distinct graph topology-a graph convolutional neural network (SGC-GCN) that amalgamates a dynamic, refined graph topology with a static, shared graph topology. The dynamic partial feature extractor (CTR-GC) and the static partial feature extractor (SGC-GC) are used in conjunction with each other to obtain a stronger feature aggregation capability in the form of static reinforcement of dynamic weaker features and to achieve the objective of strengthening the correlation modelling between interconnected joints within the human skeletal structure. The combined use of the two also introduces only a small number of additional parameters, ensuring that the refined features are not affected by the noise of statically shared features. Combining SGC-GC with the temporal modelling module has resulted in the development of SGC-GCN, a graphical convolutional network with even greater feature aggregation capability. Our network demonstrates a remarkable performance surpassing existing advanced methods on the dataset(NTU RGB+D), yielding substantial advancements in action recognition accuracy.