Collision Avoidance Algorithm for Unmanned Surface Vehicle Based on Improved Artificial Potential Field and Ant Colony Optimization

Abstract

There is a growing concern to design collision avoidance algorithm for unmanned surface vehicle (USV) as a solution to many naval and civilian requirements. Due to the anti-jamming performance of the traditional collision avoidance algorithm decrease with the influence of environmental disturbances, resulting in the problems of frequent steering and overshoot when USV is sailing under harsh sea condition. An improved collision avoidance algorithm based on improved artificial potential field and ant colony optimization is proposed in this paper. And, a power function based on the change of the distance to the obstacle is proposed. This improved combination is to solve the problem of frequent steering and overshoot of USV's control system with good robustness during collision avoidance. The results of simulation and experiment demonstrate the proposed method is more efficient and more capable to avoid the obstacles through route planning particularly in the presence of large disturbances.

Collision Avoidance Decision Method for Unmanned Surface Vehicle Based on an Improved Velocity Obstacle Algorithm

“…However, USVs should follow the International Regulations for Preventing Collisions at Sea (COLREGS) [3], which has become the consensus of relevant research. Common collision avoidance algorithms include the artificial potential field (APF) method [4][5][6][7][8], velocity obstacle (VO) algorithm [8][9][10][11][12][13] and some intelligent algorithms [13][14][15][16][17][18].…”

“…The basic principle of the APF method is to transform the influence of the target and the obstacle on the robot motion into an artificial potential field for description, and the robot moves along the combined force of the gravitational force of the target point and the repulsive force of the obstacle [19]. It is often used for path planning in the collision avoidance process, and the planned path is smooth and safe [4][5][6][7][8]. The main problem of this algorithm is that it can easily fall into the local optimum, which may cause the robot to stay at the local optimum point before reaching the target point.…”