Remote Monitoring Algorithm for Unmanned Surface Vessel:A System Based on Classification and Learning
作者单位：School of Telecommunications EngineeringXidian University
会议名称：《第40届中国控制会议》
会议日期：2021年
学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术]
关 键 词：reinforcement learning particle swarm optimization support vector machine unmanned surface vessel remote monitoring system
摘 要：The Unmanned Surface Vessel（USV） is a type of driverless and intelligent vessel capable of automatic *** can perform the extremely dangerous tasks that humans cannot complete. Through a method that combines classification and learning, we have built a remote monitoring system for USV. This system uses the Chebyshev fitting algorithm to process the data features of the UAV working states by preprocessing the telemetry data. Feature vectors substitute the original data. Based on reinforcement learning and PSO-improved SVM, state analysis of the USV is implemented in the Microsoft Foundation Classes（MFC） environment. By comparing with other algorithms, the performance of the designed system verifies its effectiveness, and at the end of this paper, we also discussed the limitations of the algorithm.