Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network
Dexterous manipulation in robotic hands relies on an accurate sense of artificial touch. Here we investigate neuromorphic tactile sensation with an event-based optical tactile sensor combined with spiking neural networks for edge orientation detection. The sensor incorporates an event-based vision s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/18/6998 |
| _version_ | 1797482471558742016 |
|---|---|
| author | Fraser L. A. Macdonald Nathan F. Lepora Jörg Conradt Benjamin Ward-Cherrier |
| author_facet | Fraser L. A. Macdonald Nathan F. Lepora Jörg Conradt Benjamin Ward-Cherrier |
| author_sort | Fraser L. A. Macdonald |
| collection | DOAJ |
| description | Dexterous manipulation in robotic hands relies on an accurate sense of artificial touch. Here we investigate neuromorphic tactile sensation with an event-based optical tactile sensor combined with spiking neural networks for edge orientation detection. The sensor incorporates an event-based vision system (mini-eDVS) into a low-form factor artificial fingertip (the NeuroTac). The processing of tactile information is performed through a Spiking Neural Network with unsupervised Spike-Timing-Dependent Plasticity (STDP) learning, and the resultant output is classified with a 3-nearest neighbours classifier. Edge orientations were classified in 10-degree increments while tapping vertically downward and sliding horizontally across the edge. In both cases, we demonstrate that the sensor is able to reliably detect edge orientation, and could lead to accurate, bio-inspired, tactile processing in robotics and prosthetics applications. |
| first_indexed | 2024-03-09T22:33:49Z |
| format | Article |
| id | doaj.art-642a705b896a4f8fbda67152e0bd14b7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:33:49Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-642a705b896a4f8fbda67152e0bd14b72023-11-23T18:52:44ZengMDPI AGSensors1424-82202022-09-012218699810.3390/s22186998Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural NetworkFraser L. A. Macdonald0Nathan F. Lepora1Jörg Conradt2Benjamin Ward-Cherrier3Department of Engineering Mathematics, University of Bristol, Bristol BS8 1TW, UKDepartment of Engineering Mathematics, University of Bristol, Bristol BS8 1TW, UKSchool of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, 114 28 Stockholm, SwedenDepartment of Engineering Mathematics, University of Bristol, Bristol BS8 1TW, UKDexterous manipulation in robotic hands relies on an accurate sense of artificial touch. Here we investigate neuromorphic tactile sensation with an event-based optical tactile sensor combined with spiking neural networks for edge orientation detection. The sensor incorporates an event-based vision system (mini-eDVS) into a low-form factor artificial fingertip (the NeuroTac). The processing of tactile information is performed through a Spiking Neural Network with unsupervised Spike-Timing-Dependent Plasticity (STDP) learning, and the resultant output is classified with a 3-nearest neighbours classifier. Edge orientations were classified in 10-degree increments while tapping vertically downward and sliding horizontally across the edge. In both cases, we demonstrate that the sensor is able to reliably detect edge orientation, and could lead to accurate, bio-inspired, tactile processing in robotics and prosthetics applications.https://www.mdpi.com/1424-8220/22/18/6998tactile roboticsneuromorphicspiking neural network |
| spellingShingle | Fraser L. A. Macdonald Nathan F. Lepora Jörg Conradt Benjamin Ward-Cherrier Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network Sensors tactile robotics neuromorphic spiking neural network |
| title | Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network |
| title_full | Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network |
| title_fullStr | Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network |
| title_full_unstemmed | Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network |
| title_short | Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network |
| title_sort | neuromorphic tactile edge orientation classification in an unsupervised spiking neural network |
| topic | tactile robotics neuromorphic spiking neural network |
| url | https://www.mdpi.com/1424-8220/22/18/6998 |
| work_keys_str_mv | AT fraserlamacdonald neuromorphictactileedgeorientationclassificationinanunsupervisedspikingneuralnetwork AT nathanflepora neuromorphictactileedgeorientationclassificationinanunsupervisedspikingneuralnetwork AT jorgconradt neuromorphictactileedgeorientationclassificationinanunsupervisedspikingneuralnetwork AT benjaminwardcherrier neuromorphictactileedgeorientationclassificationinanunsupervisedspikingneuralnetwork |