CMPSO: A novel co-evolutionary multigroup particle swarm optimization for multi-mission UAVs path planning

To cope with the situation where an unmanned aerial vehicle (UVA) needs to perform missions to multiple locations, this paper presents a new multi-mission UAVs path planning model and proposes a novel co-evolutionary multigroup particle swarm optimization (CMPSO) for solving this complex model. In this model, a new ball curve, the ball λ-Bezier curve (BλB), is used to represent the path of UAVs. In particular, UAV needs to satisfy G0 and G1 continuity at the must-pass points. Using this as a basis, a new model is built to generate a feasible path that is safe, smooth and constrained by the angle of climb and flight altitude. To solve this model efficiently, CMPSO framed by two novel different grouping learning mechanisms is proposed. Two different group learning mechanisms, grouping based on fitness values and activity level, replace the original speed and position update methods in PSO. The grouping mechanism based on the activity level uses the median of the velocity vector modes as a criterion to divide the whole population into two. They effectively facilitate the transfer of information between particles. In addition, a mutation mechanism based on the activity level is introduced to address the defect of PSO’s proneness to converge to local optima. By comparing CMPSO with 15 excellent metaheuristics at CEC 2017, CMPSO is ranked first with an average ranking of 3.72. Also, CMPSO has the best and most stable performance on 18 of the 21 engineering application problems. Finally, CMPSO is applied to three different environments of the path planning model. CMPSO outperforms the other compared algorithms in all three environments with a success rate of 100. This shows the efficiency and practicality of CMPSO in facing complex path planning problems.