Path planning under obstacle-avoidance constraints based on ant colony optimization algorithm

Abstract

Taking the unmanned aerial vehicle (UAV) mission planning as the research background, we adopt the ant colony optimization algorithm (ACO) to establish an effective UAV path planning scheme under obstacle-avoidance constraint in this paper. UAV path planning is the basis and premise of UAV mission execution. The essence of UAV path planning is to obtain the feasible flight path planning from the starting point to the target point according to the specific task of UAV. Simultaneously, effective UAV path planning should reach the optimal performance while meeting the demand of different constraints. ACO is a swarm intelligence algorithm that ants cooperate with pheromone. That is, ACO has great scalability and robustness, which is compatible to UAV path planning problem. In this paper, taking the obstacle-avoidance constraint into consideration, we build an effective UAV path planning strategy based on ACO to acquire the shortest UAV route. Experiments and analyses demonstrate that, when the obstacle number gradually increased from one to three, the proposed algorithm can all achieve the optimal UAV path planning. Hence, the rationality and applicability of the proposed algorithm are verified. Besides, the proposed algorithm can still realize the optimal UAV path planning when further adding the obstacle number and increasing the complexity of multiple obstacles. Thus, the effectiveness and robustness of the proposed algorithm are ulteriorly proved. Accordingly, the proposed algorithm has certain practical significance.