Human-inspired neurorobotic system for classifying surface textures by touch

Friedl, K., Voelker, A., Peer, A. and Eliasmith, C. (2016) Human-inspired neurorobotic system for classifying surface textures by touch. Robotics and Automation Letters. pp. 516-523. ISSN 2377-3766 Available from: http://eprints.uwe.ac.uk/31681

[img]
Preview
PDF
Available under License All Rights Reserved.

5MB

Publisher's URL: http://dx.doi.org/10.1109/LRA.2016.2517213

Abstract/Description

Giving robots the ability to classify surface textures requires appropriate sensors and algorithms. Inspired by the biology of human tactile perception, we implement a neurorobotic texture classifier with a recurrent spiking neural network, using a novel semi-supervised approach for classifying dynamic stimuli. Input to the network is supplied by accelerometers mounted on a robotic arm. The sensor data is encoded by a heterogeneous population of neurons, modeled to match the spiking activity of mechanoreceptor cells. This activity is convolved by a hidden layer using bandpass filters to extract nonlinear frequency information from the spike trains. The resulting high-dimensional feature representation is then continuously classified using a neurally implemented support vector machine. We demonstrate that our system classifies 18 metal surface textures scanned in two opposite directions at a constant velocity. We also demonstrate that our approach significantly improves upon a baseline model that does not use the described feature extraction. This method can be performed in real-time using neuromorphic hardware, and can be extended to other applications that process dynamic stimuli online.

Item Type:Article
Uncontrolled Keywords:neurorobotics, biologically-inspired robots, force and tactile sensing
Faculty/Department:Faculty of Environment and Technology > Department of Engineering Design and Mathematics
ID Code:31681
Deposited By: Professor A. Peer
Deposited On:27 Apr 2017 10:30
Last Modified:29 Apr 2017 02:29

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...