摘要
针对混合现实场景下脑控机械臂系统交互性差、指令集小的问题,设计了一种结合稳态视觉诱发电位(SSVEP)和眼动追踪技术的混合现实脑控机械臂系统。该系统通过眼动追踪技术实现目标区域的初选,而SSVEP信号则被用于在初选区域内识别最终的目标指令。在不增加刺激类别数量的前提下扩大了指令集,并根据受试者的视线停留区域实现异步控制。离线实验结果表明,在使用相同刺激类别数量的情况下,增加视觉刺激目标数量不会对分类准确率产生显著影响。通过在线实验验证了系统的适用性,相较于使用单一SSVEP范式的机械臂控制系统,所提出的系统具有更好的交互性和更大的指令集。
Brain computer interface,as an important part of brain science and brain-like intelligence research,is of strategic importance in multiple countries.A mixed reality brain controlled robotic arm system integrating steady-state visual evoked potential(SSVEP)and eye-tracking technology is designed to address the poor interactivity and small instruction set in brain controlled robotic arm systems in mixed reality scenarios.The system achieves the initial selection of the target area through eye-tracking technology,and the SSVEP signal is employed to identify the final target instruction within the initial selection area.The instruction set is expanded without increasing the number of stimulus categories,and asynchronous control is implemented based on the subject’s gaze retention area.The offline experimental results indicate that increasing the number of visual stimulus targets has no marked impact on classification accuracy when using the same number of stimulus categories.And the applicability of the system is verified through online experiments.Compared to the robotic arm control system using a single SSVEP paradigm,the proposed system achieves better interactivity and a larger instruction set.
作者
李奇
宗子彦
武岩
宋雨
张航
刘铭然
LI Qi;ZONG Ziyan;WU Yan;SONG Yu;ZHANG Hang;LIU Mingran(School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,China;Zhongshan Institute of Changchun University of Science and Technology,Zhongshan 528400,China;High School attached to NENU,Changchun 130021,China)
出处
《重庆理工大学学报(自然科学)》
CAS
北大核心
2024年第7期93-100,共8页
Journal of Chongqing University of Technology:Natural Science
基金
吉林省科技发展计划国际科技合作项目(20200801035GH)
吉林省科技发展计划国际联合研究中心建设项目(20200802004GH)。
关键词
脑机接口
机械臂
稳态视觉诱发电位
混合现实
眼动追踪
brain-computer interface
robotic arm
steady-state visual evoked potential
mixed reality
eye-tracking