Diep Quoc Bao, Truong Thanh-Cong, Zelinka Ivan
Faculty of Mechanical-Electrical and Computer Engineering, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam.
Faculty of Information Technology, University of Finance-Marketing, Ho Chi Minh City, Vietnam.
PLoS One. 2025 Jul 7;20(7):e0327016. doi: 10.1371/journal.pone.0327016. eCollection 2025.
Ensuring efficient and safe trajectory planning for UAVs in complex and dynamic environments is a critical challenge, especially for UAVs that are increasingly deployed in applications like environmental monitoring, disaster management, and surveillance. The primary complications in the safe control of UAVs include real-time obstacle avoidance, adaptation to unpredictable environmental changes, and coordination among multiple UAVs to prevent collisions. This paper addresses these challenges by proposing a novel approach for UAV trajectory planning that integrates obstacle avoidance and target acquisition. We introduce a new cost function designed to minimize the distance to the target while maximizing the distance from obstacles, effectively balancing these competing objectives to ensure safety and efficiency. To optimize this cost function, we employ the self-organizing migrating algorithm, a swarm intelligence algorithm inspired by the cooperative and competitive behaviors observed in natural organisms. Our method enables UAVs to autonomously generate safe and efficient paths in real-time, adapt to dynamic changes, and scale to large swarms without relying on centralized control. Simulation results across three scenarios-including a complex environment with ten UAVs and multiple obstacles-demonstrate the effectiveness of our approach. The UAVs successfully reach their targets while avoiding collisions, confirming the reliability and robustness of the proposed method. This work contributes to advancing autonomous UAV operations by providing a scalable and adaptable solution for trajectory planning in challenging environments.
在复杂动态环境中确保无人机高效且安全的轨迹规划是一项关键挑战，对于越来越多地部署在环境监测、灾害管理和监视等应用中的无人机而言尤为如此。无人机安全控制中的主要复杂问题包括实时避障、适应不可预测的环境变化以及多架无人机之间的协调以防止碰撞。本文通过提出一种集成避障和目标获取的无人机轨迹规划新方法来应对这些挑战。我们引入了一种新的成本函数，旨在最小化到目标的距离，同时最大化与障碍物的距离，有效平衡这些相互竞争的目标以确保安全性和效率。为了优化此成本函数，我们采用自组织迁移算法，这是一种受自然生物中观察到的合作与竞争行为启发的群体智能算法。我们的方法使无人机能够实时自主生成安全高效的路径，适应动态变化，并扩展到大型机群，而无需依赖集中控制。在包括具有十架无人机和多个障碍物的复杂环境在内的三种场景下的仿真结果证明了我们方法的有效性。无人机成功避开碰撞并到达目标，证实了所提方法的可靠性和鲁棒性。这项工作通过为具有挑战性环境中的轨迹规划提供一种可扩展且适应性强的解决方案，有助于推进无人机自主操作。
