{"date_updated":"2021-01-12T08:09:28Z","alternative_title":["ICRA"],"oa_version":"Submitted Version","conference":{"end_date":"2019-05-24","name":"ICRA: International Conference on Robotics and Automation","location":"Montreal, QC, Canada","start_date":"2019-05-20"},"author":[{"first_name":"Mathias","last_name":"Lechner","full_name":"Lechner, Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Hasani","first_name":"Ramin","full_name":"Hasani, Ramin"},{"full_name":"Zimmer, Manuel","last_name":"Zimmer","first_name":"Manuel"},{"last_name":"Henzinger","first_name":"Thomas A","orcid":"0000−0002−2985−7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A"},{"full_name":"Grosu, Radu","last_name":"Grosu","first_name":"Radu"}],"status":"public","ddc":["000"],"article_number":"8793840","doi":"10.1109/icra.2019.8793840","type":"conference","has_accepted_license":"1","date_published":"2019-05-01T00:00:00Z","citation":{"chicago":"Lechner, Mathias, Ramin Hasani, Manuel Zimmer, Thomas A Henzinger, and Radu Grosu. “Designing Worm-Inspired Neural Networks for Interpretable Robotic Control.” In <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, Vol. 2019–May. IEEE, 2019. <a href=\"https://doi.org/10.1109/icra.2019.8793840\">https://doi.org/10.1109/icra.2019.8793840</a>.","ista":"Lechner M, Hasani R, Zimmer M, Henzinger TA, Grosu R. 2019. Designing worm-inspired neural networks for interpretable robotic control. Proceedings - IEEE International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, ICRA, vol. 2019–May, 8793840.","apa":"Lechner, M., Hasani, R., Zimmer, M., Henzinger, T. A., &#38; Grosu, R. (2019). Designing worm-inspired neural networks for interpretable robotic control. In <i>Proceedings - IEEE International Conference on Robotics and Automation</i> (Vol. 2019–May). Montreal, QC, Canada: IEEE. <a href=\"https://doi.org/10.1109/icra.2019.8793840\">https://doi.org/10.1109/icra.2019.8793840</a>","mla":"Lechner, Mathias, et al. “Designing Worm-Inspired Neural Networks for Interpretable Robotic Control.” <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, vol. 2019–May, 8793840, IEEE, 2019, doi:<a href=\"https://doi.org/10.1109/icra.2019.8793840\">10.1109/icra.2019.8793840</a>.","short":"M. Lechner, R. Hasani, M. Zimmer, T.A. Henzinger, R. Grosu, in:, Proceedings - IEEE International Conference on Robotics and Automation, IEEE, 2019.","ieee":"M. Lechner, R. Hasani, M. Zimmer, T. A. Henzinger, and R. Grosu, “Designing worm-inspired neural networks for interpretable robotic control,” in <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, Montreal, QC, Canada, 2019, vol. 2019–May.","ama":"Lechner M, Hasani R, Zimmer M, Henzinger TA, Grosu R. Designing worm-inspired neural networks for interpretable robotic control. In: <i>Proceedings - IEEE International Conference on Robotics and Automation</i>. Vol 2019-May. IEEE; 2019. doi:<a href=\"https://doi.org/10.1109/icra.2019.8793840\">10.1109/icra.2019.8793840</a>"},"project":[{"grant_number":"Z211","_id":"25F42A32-B435-11E9-9278-68D0E5697425","call_identifier":"FWF","name":"The Wittgenstein Prize"}],"title":"Designing worm-inspired neural networks for interpretable robotic control","quality_controlled":"1","publication_identifier":{"isbn":["9781538660270"]},"year":"2019","month":"05","volume":"2019-May","abstract":[{"text":"In this paper, we design novel liquid time-constant recurrent neural networks for robotic control, inspired by the brain of the nematode, C. elegans. In the worm's nervous system, neurons communicate through nonlinear time-varying synaptic links established amongst them by their particular wiring structure. This property enables neurons to express liquid time-constants dynamics and therefore allows the network to originate complex behaviors with a small number of neurons. We identify neuron-pair communication motifs as design operators and use them to configure compact neuronal network structures to govern sequential robotic tasks. The networks are systematically designed to map the environmental observations to motor actions, by their hierarchical topology from sensory neurons, through recurrently-wired interneurons, to motor neurons. The networks are then parametrized in a supervised-learning scheme by a search-based algorithm. We demonstrate that obtained networks realize interpretable dynamics. We evaluate their performance in controlling mobile and arm robots, and compare their attributes to other artificial neural network-based control agents. Finally, we experimentally show their superior resilience to environmental noise, compared to the existing machine learning-based methods.","lang":"eng"}],"file_date_updated":"2020-10-08T17:30:38Z","date_created":"2019-09-18T08:09:51Z","publication":"Proceedings - IEEE International Conference on Robotics and Automation","language":[{"iso":"eng"}],"publication_status":"published","oa":1,"_id":"6888","scopus_import":"1","file":[{"relation":"main_file","file_size":3265107,"checksum":"f5545a6b60c3ffd01feb3613f81d03b6","access_level":"open_access","date_created":"2020-10-08T17:30:38Z","date_updated":"2020-10-08T17:30:38Z","success":1,"content_type":"application/pdf","file_id":"8636","file_name":"2019_ICRA_Lechner.pdf","creator":"dernst"}],"department":[{"_id":"ToHe"}],"day":"01","publisher":"IEEE","article_processing_charge":"No","user_id":"D865714E-FA4E-11E9-B85B-F5C5E5697425"}