A novel hybrid Chaotic Aquila Optimization algorithm with Simulated Annealing for Unmanned Aerial Vehicles path planning

Abstract

In recent years, research on Unmanned Aerial Vehicles (UAVs) has become one of the interest- ing topics for industry and academic. UAV path plan- ning is one of the critical issues in terms of guaran- teeing the autonomy and good performance of UAVs in real-world applications. Its main objective is to de- termine and ensure an optimal and collision-free path between two positions from a starting point (source) to a destination one (target) while satisfying some UAV requirements (i.e. UAV’s safety, environment complex- ity, obstacle avoidance, energy consumption,etc). Due to the complexity of this topic, an efficient path plan- ning algorithm is required. This paper presents an opti- mal and hybrid algorithm, called CAOSA, based on the hybridization of Chaotic Aquila Optimization (CAO) and Simulated Annealing (SA) algorithms for solving the UAV path planning problem in a 3D environment. As a first step, chaotic map is introduced to enhance the chaotic stochastic behavior of the Aquila Optimization (AO) algorithm. In the second step, the SA algorithm is combined with CAO algorithm to improve the best so- lution (path quality) obtained after each iteration of COA. The main purpose of using SA is to increase the exploitation by searching for the most promising regions identified by the CAO algorithm. The perfor- mance of the proposed CAOSA algorithm is evaluated on several scenarios under different settings consider- ing the fitness value, path cost, and execution time metrics. Simulation results showed superiority and ro- bustness of CAOSA algorithm compared to nine meta- heuristics such as Simulated Annealing (SA), Particle Swarm Optimization (PSO), Bat Algorithm (BA), Fire- fly optimization (FA), Grey Wolf Optimizer (GWO), Sine Cosine Algorithm (SCA), Whale Optimization Al- gorithm (WOA), Dragonfly Algorithm (DA), and the original Aquila Optimization (AO). It is also revealed that CAOSA can offer an optimized path that improves UAV path planning requirements significantly in com- plex environments