Autonomous trajectory optimization for UAVs in disaster zone using henry gas optimization scheme

Unmanned aerial vehicles (UAVs) can assist post-disaster assessment by rapidly surveying affected areas and supporting response teams. In cluttered regions, path planning becomes challenging because candidate solutions may violate obstacle constraints and many metaheuristics may stagnate around locally feasible routes. This paper presents a cluster optimization scheme (COS) built on the Henry Gas Optimization (HGO) algorithm for generating collision-free UAV paths represented by a small set of control points. The approach is evaluated in four static environments of increasing difficulty and is compared with PSO, GWO, CSA, and BMO under the same iteration budget. The results indicate that COS–HGO yields shorter feasible paths with competitive runtime across the tested settings. The present study focuses on offline geometric planning in a 2D workspace; extensions toward dynamic environments, energy-aware objectives, and communication constraints are left as directions for subsequent work.