机构地区: 中国科学院沈阳自动化研究所机器人学国家重点实验室
出 处: 《机器人》 2017年第4期395-404,共10页
摘 要: 为了解放水下机械手操作人员的双手,本文将脑-机接口(BCI)技术应用到水下机器人作业中,通过解析脑电信号并将其映射为具体指令从而控制机械手.现有的脑电波控制机械手方法在实时性、准确性方面无法满足实际的水下作业要求,提出了基于视觉诱发模式的ERP(事件相关电位)脑电信号来控制水下机械手的策略.通过融合脑电波控制与水下机械手作业的各自特点和优化ERP视觉诱发界面,使操作人员能够快速地完成给定任务.8位被试被邀请在建立的实验平台上进行控制实验,最终得到的辨识操作人员意图平均准确率、系统信息传输率与完成任务平均控制时间分别为91.5%、27.7 bits/min与90.1 s.与同类系统相比,本文所提控制策略系统性能更好,且作业效率满足实际作业要求. To free two hands of the underwater manipulator operator, the BCI(brain-computer interface) technology is applied to underwater operational tasks in this paper, where the manipulator follows instructions transformed from the brainwaves. As the current brainwave-based manipulator control methods can't satisfy requirements for the actual underwater tasks in terms of real-time performance and accuracy, a control strategy is proposed for controlling the underwater manipulator via event-related potentials(ERP) of brainwaves(evoked by visual stimuli). The operator can quickly complete a given task after optimizing the visual evoked ERP interface and combining the characteristics of the brainwaves control and the underwater manipulator operation. Eight subjects are invited to conduct experiments on a self-developed experimental platform. The average accuracy of identifying an operator's intention, the system information transfer rate and the average control time of completing the task are 91.5%, 27.7 bits/min and 90.1 s, respectively. Comparing with the similar systems, the system performance of the proposed control strategy is better, and the operational efficiency satisfies the practical operational requirements.