Display options
Cite
Rongala UB, Mazzoni A, Oddo CM. Neuromorphic Artificial Touch for Categorization of Naturalistic Textures. IEEE Trans Neural Netw Learn Syst. 2015;28(4):819-829doi: 10.1109/TNNLS.2015.2472477.
Rongala, U. B., Mazzoni, A., & Oddo, C. M. (2017). Neuromorphic Artificial Touch for Categorization of Naturalistic Textures. IEEE transactions on neural networks and learning systems, 28(4), 819-829. https://doi.org/10.1109/TNNLS.2015.2472477
Rongala, Udaya Bhaskar, et al. "Neuromorphic Artificial Touch for Categorization of Naturalistic Textures." IEEE transactions on neural networks and learning systems vol. 28,4 (2017): 819-829. doi: https://doi.org/10.1109/TNNLS.2015.2472477
Rongala UB, Mazzoni A, Oddo CM. Neuromorphic Artificial Touch for Categorization of Naturalistic Textures. IEEE Trans Neural Netw Learn Syst. 2017 Apr;28(4):819-829. doi: 10.1109/TNNLS.2015.2472477. Epub 2015 Sep 10. PMID: 26372658.
Copy Download .nbib Format: NLM
Share it on

IEEE Trans Neural Netw Learn Syst. 2017 Apr;28(4):819-829. doi: 10.1109/TNNLS.2015.2472477. Epub 2015 Sep 10.

Neuromorphic Artificial Touch for Categorization of Naturalistic Textures.

IEEE transactions on neural networks and learning systems

Udaya Bhaskar Rongala, Alberto Mazzoni, Calogero Maria Oddo

PMID: 26372658 DOI: 10.1109/TNNLS.2015.2472477

Abstract

We implemented neuromorphic artificial touch and emulated the firing behavior of mechanoreceptors by injecting the raw outputs of a biomimetic tactile sensor into an Izhikevich neuronal model. Naturalistic textures were evaluated with a passive touch protocol. The resulting neuromorphic spike trains were able to classify ten naturalistic textures ranging from textiles to glass to BioSkin, with accuracy as high as 97%. Remarkably, rather than on firing rate features calculated over the stimulation window, the highest achieved decoding performance was based on the precise spike timing of the neuromorphic output as captured by Victor Purpura distance. We also systematically varied the sliding velocity and the contact force to investigate the role of sensing conditions in categorizing the stimuli via the artificial sensory system. We found that the decoding performance based on the timing of neuromorphic spike events was robust for a broad range of sensing conditions. Being able to categorize naturalistic textures in different sensing conditions, these neurorobotic results pave the way to the use of neuromorphic tactile sensors in future real-life neuroprosthetic applications.

Publication Types