一种基于视觉的无人船回坞控制方法

A vision-based control method for unmanned surface vehicle returning to dock

为了解决小型无人船(Unmanned Surface Vehicle,USV)作业后的回收以及能源补给的问题,提高无人船无人系统的自主性,提出了一种基于视觉的回坞控制方法。首先,通过分析目标图像与船舶航向之间的联系提出了视觉航向轨迹的概念;然后,根据特定的船坞立体靶标结构计算出视觉航向轨迹;最后,运用PID控制算法对视觉航向轨迹进行跟踪,从而完成回坞任务。在VRX(Virtual RobotX)仿真系统中进行零级海况和二级海况下的USV自主回坞实验,实验结果表明,提出的基于视觉的回坞控制方法能实时跟踪视觉航向轨迹并顺利完成回坞任务。

In order to address the problems of recovery and energy supply for small Unmanned Surface Vehicles(USVs)and improve the autonomy of unmanned systems,a vision-based docking control method is proposed.Firstly,the concept of visual heading trajectory is introduced by analyzing the relationship between the target image and the USV's heading.Then,the visual heading trajectory is calculated based on the specific structure of the docking stereoscopic target.Finally,the PID control algorithm is used to track the visual heading trajectory and complete the docking task.Zero-level and level-2 sea state autonomous docking experiments of USVs are conducted in the Virtual RobotX(VRX)simulation system.Experimental results show that the proposed vision-based docking control method can track the visual heading trajectory in real-time and complete the docking task smoothly.