DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Hyunkyu | ko |
dc.contributor.author | Park, Kyungseo | ko |
dc.contributor.author | Mo, Sangwoo | ko |
dc.contributor.author | Kim, Jung | ko |
dc.date.accessioned | 2021-10-14T05:30:16Z | - |
dc.date.available | 2021-10-14T05:30:16Z | - |
dc.date.created | 2021-10-11 | - |
dc.date.created | 2021-10-11 | - |
dc.date.created | 2021-10-11 | - |
dc.date.created | 2021-10-11 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON ROBOTICS, v.37, no.5, pp.1570 - 1583 | - |
dc.identifier.issn | 1552-3098 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288172 | - |
dc.description.abstract | Electrical impedance tomography (EIT) based tactile sensor offers significant benefits on practical deployment because of its sparse electrode allocation, including durability, large-area scalability, and low fabrication cost, but the degradation of a tactile spatial resolution has remained challenging. This article describes a deep neural network based EIT reconstruction framework, the EIT neural network (EIT-NN), alleviating this tradeoff between tactile sensing performance and hardware simplicity. EIT-NN learns a computationally efficient, nonlinear reconstruction attribute, achieving high-resolution tactile sensation and well-generalized reconstruction capability to address arbitrary complex touch modalities. We train EIT-NN by presenting a sim-to-real dataset synthesis strategy for computationally efficient generalizability. Furthermore, we propose a spatial sensitivity aware mean-squared error loss function, which uses an intrinsic spatial sensitivity of the sensor to guarantee a well-posed EIT operation. We validate an outperformance of EIT-NN against conventional EIT sensing methods by conducting a simulation study, a single-touch indentation test, and a two-point discrimination test. The results show improved spatial resolution, sensitivity, and localization accuracy. The beneficial features of the generalized sensing of EIT-NN were demonstrated by examining touch modality discrimination performance. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Deep Neural Network Based Electrical Impedance Tomographic Sensing Methodology for Large-Area Robotic Tactile Sensing | - |
dc.type | Article | - |
dc.identifier.wosid | 000702631200017 | - |
dc.identifier.scopusid | 2-s2.0-85102707031 | - |
dc.type.rims | ART | - |
dc.citation.volume | 37 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 1570 | - |
dc.citation.endingpage | 1583 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON ROBOTICS | - |
dc.identifier.doi | 10.1109/TRO.2021.3060342 | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kim, Jung | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Robot sensing systems | - |
dc.subject.keywordAuthor | Tomography | - |
dc.subject.keywordAuthor | Sensors | - |
dc.subject.keywordAuthor | Conductivity | - |
dc.subject.keywordAuthor | Electrodes | - |
dc.subject.keywordAuthor | Image reconstruction | - |
dc.subject.keywordAuthor | Voltage measurement | - |
dc.subject.keywordAuthor | Artificial intelligence (AI) based methods | - |
dc.subject.keywordAuthor | deep learning in robotics and automation | - |
dc.subject.keywordAuthor | force and tactile sensing | - |
dc.subject.keywordAuthor | image reconstruction | - |
dc.subject.keywordPlus | IMAGE-RECONSTRUCTION | - |
dc.subject.keywordPlus | SENSOR | - |
dc.subject.keywordPlus | SKIN | - |
dc.subject.keywordPlus | SOFT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.