Enhanced Human-UAV Collaborative Control Strategies for Multi-UAVs in Complex Task Environments

This study introduces an innovative approach to integrating Unmanned Aerial Vehicles (UAVs) into squad personnel sensing systems by developing advanced control strategies, with a particular focus on the Human-UAV Collaborative Control (HUCC) algorithm. These strategies are crucial in establishing an effective human-UAV collaborative sensing system by enhancing spatial coverage and optimizing task allocation. Utilizing Long Short-Term Memory (LSTM) networks, the algorithm accurately predicts the movement trajectories of squad personnel, thereby enhancing the selection process within communication networks. Comparative analyses demonstrate that the HUCC algorithm outperforms traditional heuristic greedy (HG) and hybrid greedy worker recruitment (H-GWR) methods in terms of coverage rate and operational efficiency, achieving superior results in a relatively short timeframe. This underscores the algorithm's potential in operational scenarios, particularly in leveraging participatory sensing modes among squad personnel and facilitating parallel sensing tasks between humans and UAVs. Future research directions include developing models for participatory human-UAV collaboration and creating parallel task allocation algorithms. These advancements aim to further enhance the operational capabilities of human-UAV teams in complex and dynamic environments, emphasizing the critical role of machine intelligence in augmenting human efforts within the realms of squad personnel sensing and surveillance.