Scholarlink

<p>The proposed framework presents a novel hybrid UAV Coordination and Trajectory Optimization Framework (H-UAV-CTOF) for adaptive and efficient multi-UAV mission management using Low Altitude Performance (LAP)–based UAV selection, Receding Horizon (RH)–driven trajectory optimization, and a supervisory Hybrid Decision and Optimization Coordinator (HDOC). Within the framework, the UAV-task suitability is assessed by the LAP module which combines altitude-dependent performance metrics with mission-specific constraints. The RH planner is tasked with the generation of optimal trajectories in response to evolving environmental conditions. The unification of these modules through reinforcement-informed supervision happens in the HDOC layer which produces physics-aware trajectories while balancing energy efficiency and stability. The framework ensures multi-layered adaptability through its hierarchical architecture. Extensive simulations across urban, semi-urban, and open-terrain scenarios demonstrate up to 2.8 times improvement in Mission Efficiency Index (MEI), 1.9 times higher Assignment Consistency Score (ACS), and 1.6 times enhancement in Path Optimality Ratio (POR) relative to conventional models. H-UAV-CTOF therefore provides a robust, scalable, and self-adaptive paradigm for intelligent UAV coordination in surveillance, logistics, and disaster-response operations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel hybrid framework to optimize UAVs selection paths using LAP and RH trajectory planning

  • 期刊论文

  • 发表日期：

    2025年11月21日

查看全文
  • Sumati,
  • Nikhil Kumar Marriwala,
  • Ram Avtar Jaswal

摘要

The proposed framework presents a novel hybrid UAV Coordination and Trajectory Optimization Framework (H-UAV-CTOF) for adaptive and efficient multi-UAV mission management using Low Altitude Performance (LAP)–based UAV selection, Receding Horizon (RH)–driven trajectory optimization, and a supervisory Hybrid Decision and Optimization Coordinator (HDOC). Within the framework, the UAV-task suitability is assessed by the LAP module which combines altitude-dependent performance metrics with mission-specific constraints. The RH planner is tasked with the generation of optimal trajectories in response to evolving environmental conditions. The unification of these modules through reinforcement-informed supervision happens in the HDOC layer which produces physics-aware trajectories while balancing energy efficiency and stability. The framework ensures multi-layered adaptability through its hierarchical architecture. Extensive simulations across urban, semi-urban, and open-terrain scenarios demonstrate up to 2.8 times improvement in Mission Efficiency Index (MEI), 1.9 times higher Assignment Consistency Score (ACS), and 1.6 times enhancement in Path Optimality Ratio (POR) relative to conventional models. H-UAV-CTOF therefore provides a robust, scalable, and self-adaptive paradigm for intelligent UAV coordination in surveillance, logistics, and disaster-response operations.