Kenji Takeda, Mikihito Hayakawa, Motokuni Ishibashi, Takumi Ishihama, Minori Ishihara, Megumi Aibara, M. Kaneko, Ken Saito, F. Uchikoba
{"title":"Artificial Spinal Cord IC with Pulse-Type Hardware Neural Networks Mimicking Function of The Spinal Cord","authors":"Kenji Takeda, Mikihito Hayakawa, Motokuni Ishibashi, Takumi Ishihama, Minori Ishihara, Megumi Aibara, M. Kaneko, Ken Saito, F. Uchikoba","doi":"10.23919/ICEP55381.2022.9795499","DOIUrl":null,"url":null,"abstract":"An artificial spinal cord IC for motor neuron control using an analog CMOS circuit instead of a conventional digital system is reported. A circuit configuration was proposed for P-HNNs for quadrupedal walking control to enable reflex movements by sensors. It was shown that the gait pattern was changed by actual measurement. Pulse-type hardware neural networks (P-HNNs) were proposed to control human biped gait. The proposed circuit was confirmed to generate walking and running patterns.","PeriodicalId":413776,"journal":{"name":"2022 International Conference on Electronics Packaging (ICEP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Electronics Packaging (ICEP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/ICEP55381.2022.9795499","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
An artificial spinal cord IC for motor neuron control using an analog CMOS circuit instead of a conventional digital system is reported. A circuit configuration was proposed for P-HNNs for quadrupedal walking control to enable reflex movements by sensors. It was shown that the gait pattern was changed by actual measurement. Pulse-type hardware neural networks (P-HNNs) were proposed to control human biped gait. The proposed circuit was confirmed to generate walking and running patterns.