Organic neuromorphic electronics for sensorimotor integration and learning in robotics

Thumbnail
Name:
sciadv.abl5068.pdf
Size:
2.147Mb
Format:
PDF
Description:
Publisher's Version/PDF
Download
Type
Article
Authors
Krauhausen, Imke cc
Koutsouras, Dimitrios A. cc
Melianas, Armantas cc
Keene, S. T. cc
Lieberth, Katharina cc
Ledanseur, Hadrien
Sheelamanthula, Rajendar cc
Giovannitti, Alexander cc
Torricelli, Fabrizio cc
McCulloch, Iain cc
Blom, Paul W. M. cc
Salleo, Alberto cc
van de Burgt, Yoeri cc
Gkoupidenis, Paschalis cc
KAUST Department
KAUST Solar Center (KSC)
Chemical Science Program
Date
2021-12-10
Permanent link to this record
http://hdl.handle.net/10754/673986

Metadata
Show full item record
Abstract
In living organisms, sensory and motor processes are distributed, locally merged, and capable of forming dynamic sensorimotor associations. We introduce a simple and efficient organic neuromorphic circuit for local sensorimo-tor merging and processing on a robot that is placed in a maze. While the robot is exposed to external environ-mental stimuli, visuomotor associations are formed on the adaptable neuromorphic circuit. With this on-chip sensorimotor integration, the robot learns to follow a path to the exit of a maze, while being guided by visually indicated paths. The ease of processability of organic neuromorphic electronics and their unconventional form factors, in combination with education-purpose robotics, showcase a promising approach of an affordable, versatile, and readily accessible platform for exploring, designing, and evaluating behavioral intelligence through decen-tralized sensorimotor integration.
Citation
Krauhausen, I., Koutsouras, D. A., Melianas, A., Keene, S. T., Lieberth, K., Ledanseur, H., … Gkoupidenis, P. (2021). Organic neuromorphic electronics for sensorimotor integration and learning in robotics. Science Advances, 7(50). doi:10.1126/sciadv.abl5068
Sponsors
We acknowledge F. Keller, A. Steinmetz, and A. Becker from the Max Planck Institute for Polymer Research (MPIP) for significant contribution in the design and realization of the experimental setup (maze, 3D-printed parts, and video recording) and electronics (customization of the robot and additional hardware for conditioning). We also acknowledge H.-J. Guttmann and C. Bauer for assistance in the clean room facilities of MPIP. We also acknowledge G. Malliaras for relevant preliminary discussions and B. Meijer for support
Funding Facilities of MPIP (clean room, device metrology, electronics, and mechanical workshop) are supported by the Max Planck Society (to P.W.M.B. and P.G.). nano@Stanford laboratories are supported by the National Science Foundation as part of the National Nanotechnology Coordinated Infrastructure under award ECCS-1542152 (to A.S.). This study is funded by a joint project between MPIP and the Institute for Complex Molecular Systems (ICMS), Eindhoven University of Technology, grant no. MPIPICMS2019001 (to Y.v.d.B., I.K., and P.G.); European Union’s Horizon 2020 Research and Innovation Programme, grant agreement no. 802615 (to Y.v.d.B.); the Carl-Zeiss Foundation (to P.G.); National Science Foundation and the Semiconductor Research Corporation, E2CDA award no. 1739795 (to A.S. and S.T.K.); and Stanford Graduate Fellowship fund (to S.T.K.)
Publisher
American Association for the Advancement of Science (AAAS)
Journal
Science Advances
DOI
10.1126/sciadv.abl5068
Additional Links
https://www.science.org/doi/10.1126/sciadv.abl5068
Collections
Articles; Chemical Science Program; KAUST Solar Center (KSC)
Archived with thanks to Science Advances. Copyright © 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC). This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.
Except where otherwise noted, this item's license is described as Archived with thanks to Science Advances. Copyright © 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC). This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.