| Abstract |
In this research, different state-of-the-art metaheuristic algorithms are examined in order to incorporate a collision-free path planning technique for Unmanned Air Vehicles (UAV) in crisis situations. The effective path planning is utilized to identify the major cause of disasters such as bushfires, which are wreaking havoc on the global forest environment. This new approach is a first step toward a pre-disaster evaluation and options for saving survivors in a shorter amount of time. For UAV path optimization, a novel meta-heuristic algorithm i.e. Smart Flower Optimization Algorithm (SFOA) is presented. Comparison is made between different metaheuristic algorithms such as Particle Swarm Optimization (PSO), Flower Pollination Algorithm (FPA) and Grasshopper Optimization (GHO). Four different scenarios are offered to demonstrate the resilience of our proposed model that are dynamic environment (DE), general environment (GE), condensed environment (CE) and maze environment (ME). The barriers in each scenario are put in such a way that the overall path complexity for a UAV to reach the destination is increased. In SFOA, two growth methods are controlled on the movement of immature flower and mathematical modelling is used to update particles position. The SFOA method beats other algorithms based on the parameters chosen, saving up to 24.5% in transportation costs and 13.3% in computational time. As a result, SFOA can be used to optimize UAV path planning in any of the foregoing environment. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. |
