Comparative Study of SSVEP- and P300-Based Models for the Telepresence Control of Humanoid Robots

摘要: In this paper, we evaluate the control performance of SSVEP (steady-state visual evoked potential)- and P300-based models using Cerebot—a mind-controlled humanoid robot platform. Seven subjects with diverse experience participated in experiments concerning open-loop closed-loop a via brain signals. The stimuli both SSVEP- P300- based were implemented on LCD computer monitor refresh frequency 60 Hz. Considering operation safety, set classification accuracy model over 90.0% as most important mandatory for telepresence robot. demonstrated that at four stimulus targets achieved average accurate rate about 90%, whereas P300 six or more under five repetitions per trial was able to achieve rates 90.0%. Therefore, used types behavior; while chosen behavior. Both 4-class 6-class success 90.3% 91.3%, response times 3.65 s 6.6 s, information transfer (ITR) 24.7 bits/min 18.8 bits/min, respectively. addressed robot; objective cause walk along white lane marked an office environment live video feedback. Comparative studies reveal yielded faster subject’s mental activity less reliance channel selection, found be suitable classifiable required training. To conclude, discuss existing robots, including proposed paper.