1.海军装备部驻武汉地区军事代表局;2.海军装备部驻广州地区军事代表局
***项目“项目名称”(项目编号)。
水下机器人避碰控制是自主作业的重要基础，但复杂的约束条件和模型的不精确性增加了避障路径跟踪的技术难度。本文在传统模型预测控制的基础上，结合作业场景多种约束条件，引入径向基函数神经网络，提出了一种水平面避碰控制方法。首先，采用径向基神经网络建立误差补偿函数，提高传统动力学预测模型精度。然后，结合避碰路径跟踪控制，在滚动优化环节选取性能指标函数，并显式引入障碍物、执行机构与控制稳定性等约束条件。最后，通过仿真试验证明该方法能够控制水下机器人跟踪避碰路径实现水平面内障碍物规避。
avoidance of underwater vehicles is an important basis for autonomous operation, but complicated constraints and imprecision of models increase the technical difficulty of path tracking in avoidance. Based on the traditional model predictive control, this paper proposes a horizontal plane collision avoidance control method, combining with many constraints of operation scene and introducing radial basis function neural network. Firstly, radial basis neural network is used to establish error compensation function to improve the accuracy of traditional dynamic model. Then, combined with the collision avoidance, the performance index function is selected in the rolling optimization stage, and the constraints such as obstacles, actuator and control stability are explicitly introduced. Finally, the simulation results show that the proposed method can control the underwater vehicle to track the path of collision avoidance in the horizontal plane.
