Trajectory Planning for UAV Based on Improved ACO Algorithm

Bo Li,Lifang Liu,Baoguo Yu,Xiaogang Qi

doi:10.1109/access.2019.2962340

Abstract

Trajectory planning is an important subject in the field of unmanned aerial vehicles (UAVs). However, existing methods do not solve some problems well, such as slow convergence speed and low searching efficiency of related algorithms and collisions between UAVs and the obstacles. Therefore, a method is proposed to solve a trajectory planning problem for multi-UAV in a static environment, which includes three main phases: the initial trajectory generation, the trajectory correction, and the smooth trajectory planning. First, the improved algorithm called MACO which introduces the metropolis criterion into the node screening mechanism of the ant colony optimization (ACO) algorithm is presented to generate the initial trajectory that can effectively avoid falling into the local optimal solution and stagnation. Then, considering size constraint of UAVs, this paper gives three trajectory correction schemes to solve the collision avoidance problem and further to optimize the initial trajectory. Last, the discontinuity originated from the sharp turn which occurred in the trajectory planning is solved by the inscribed circle (IC) smooth method, and the produced trajectory has shown better performance in reducing fuel consumption and improving the trajectory safety. Experimental results demonstrate that the proposed method has the high feasibility and effectiveness from aspects of the optimal solution, the collision avoidance, and the smooth trajectory in the trajectory planning problem for UAVs.

Highlights

Unmanned aerial vehicle (UAV) is an unmanned aircraft that can autonomously complete a given task [1], such as monitoring and assessment of natural disaster, search, rescue, and surveillance
Experimental results show that the MACO algorithm significantly reduces the probability of falling into local optimum, and it improves the ability of finding the optimal trajectory
2) RESULTS OF THE PATH PLANNING IN SCENARIO 2 Considering the geometric size of the aircraft, it can be seen that three initial trajectories generated by the MACO algorithm collide with the obstacles, and this problem can be well solved using scheme 3

Summary

Introduction

Unmanned aerial vehicle (UAV) is an unmanned aircraft that can autonomously complete a given task [1], such as monitoring and assessment of natural disaster, search, rescue, and surveillance. Due to the advantages of multi-UAV in information sharing, strong robustness, and the ability, it can perform significantly better than the single UAV in the complex tasks. It has been the subject of the trajectory planning. When the environmental state is known and the geographic information is non-dynamic, the global trajectory planning can achieve a safe and feasible trajectory. It is composed of orderly trajectory nodes from the initial point to the target point. The local trajectory planning can generate higher quality trajectory efficiently in a dynamic environment with unknown environmental conditions and variable terrains

Objectives

Results

Conclusion