Search

Abstract Artificial intelligence techniques are increasingly applied in the study of autonomous decision-making in unmanned clustered distributed systems. However, communication constraints has become a big bottleneck that restricts its performance. To address the need for unmanned aerial vehicles(UAVs) to execute collaborative attack missions in complex communication-constrained environments, this paper propose an autonomous decision-making method for UAVs based on Multi-Agent Reinforcement Learning (MARL). Firstly, the autonomous decision-making processes of UAV clusters are modeled as Decentralized Partially Observable Markov Decision Processes(Dec-POMDPs). Next, the algorithm is enhanced within the framework of Multi-Agent Deep Deterministic Policy Gradient(MADDPG) by designing an explicit inter-intelligent communication mechanism to achieve information exchange among UAVs. Subsequently, the algorithm utilizes Long Short-Term Memory(LSTM) networks to process the local observations of the UAVs, enhancing the effectiveness of the information sent by combining historical data with current observations. Finally, multiple rounds of experiments are conducted across various communication-constrained scenarios. Simulation results indicate that the proposed method improves the task completion capability by 46.0% and enhances stability by 24.9% compared to baseline algorithm MADDPG. Additionally, the algorithm demonstrates better generalization and exhibits good scalability, effectively adapting to varying numbers of UAVs. This research provides new theoretical insights and a technical framework for the collaboration of UAVs in environments with communication constraints, which holds great practical importance in improving the ability and application scope of UAV systems.

Osteoporosis (OP) is a systemic bone disorder marked by reduced bone mass and disrupted microstructure, leading to higher fracture risk. Epidemiological data from China show a 20.7% prevalence in women and 14.4% in men over 50, underscoring a pressing health issue given the aging population. More drugs to inhibit OP progression should be explored, and their biological mechanisms confirmed in preclinical studies.

Guided by the goal of carbon neutrality，the optimization of shared energy-storage planning has become key for solving （i） the volatility and uncertainty of power supply for new power systems with new energy as the main body and （ii） the mismatch with user demands. Therefore，based on a comprehensive analysis of the physical characteristics，operation characterization function，and cost-benefit model of typical flexibility-regulation resources of new power systems，this study performs a characteristic analysis of system flexibility-regulation demand as guidance and aims to maximize the social welfare of flexibility regulation. The operation strategy and progressive planning-optimization model for six scenarios of lithium battery-supercapacitor shared energy-storage system under the coordination of multiple flexible-regulation resources，such as smoothing fluctuations，peaking and valley filling，alleviating transmission and distribution circuit congestion and delaying grid upgrading，reducing wind and power rejection，achieving supply-and-demand balance，and reducing load cutting，are proposed. Additionally，a scientific and effective solution method is proposed to facilitate the dynamic construction of new power systems. Numerical results show that the proposed model can improve the absorption level of renewable energy and effectively reduce the system flexibility-adjustment cost.

To build world science and technology power, industry, universities, and research institutes must complement each other in technological innovation. Currently, China has not yet fully shifted from a university- and research-centered to an enterprise-centered innovation system. Investigating and comparing the spatiotemporal changes and influencing factors of technological innovation efficiencies of firms, universities, and research institutes to optimize the allocation of regional innovation resources and improve regional innovation policy is important. Using 31 provincial-level administrative regions in China as decision-making units, this study measures and compares the spatiotemporal changes in technological innovation efficiencies and the factors influencing the technical inefficiencies of the three entities using GIS spatial analysis and Stochastic Frontier Analysis. The main findings are as follows: 1) The technological innovation efficiencies of firms, universities, and research institutes show a steady increase over the study period, with a 45%-55% improvement space. Firms have the lowest technological innovation efficiency but the fastest growth rate in technological innovation efficiency. Firms are expected to surpass the technological innovation efficiency of research institutes in the next two years; however, there is still a large gap with universities, indicating that firms have not yet become key players in the innovation system. 2) The spatial differences between the technological innovation efficiencies of firms, universities, and research institutes are significant. Only a few provinces have formed a situation of industry-university research in tandem, suggesting a certain degree of spatial mismatch between technological innovation efficiency and regional economic development. Our analysis shows that regional differences in the technological innovation efficiency of innovation entities are closely related to regional innovation modes. 3) Technological inefficiency factors coexist in the regional innovation milieu and industry-university research cooperative innovation. The direction and magnitude of the impacts of exogenous environmental variables— infrastructure, market environment, labor quality, financial markets, and entrepreneurship—on technological inefficiencies vary with the type of innovation entity. Collaborative innovation among enterprises, universities, and research institutes has significant positive effects on technological innovation efficiency, except for research institutes technological innovation efficiency when collaborating with enterprises. The reason for the insignificant effect of enterprise-research institute collaborative innovation on research institutes' efficiency may be that both research institutes and firms consider technological application and development as the main goal of collaborative innovation, and collaborative innovation with firms crowds out the internal innovation resources of research institutes and inhibits their technological innovation activities. We contribute to the literature on regional innovation systems by comparing the differences in the technological innovation efficiency of the main innovation entities in the regional innovation systems of a transition economy. Our findings provide a basis for the rational allocation of technological innovation resources and the optimization of the regional innovation environment.