{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2747"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2747","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"Neuromorphic Computing Applications in Robotics","abstract":"Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationships between events and objects. This learning paradigm is referred to as associative learning. The successful implementation of associative learning imitates self-learning schemes analogous to animals which resolve the challenges of deep learning. Current state-of-the-art implementations of associative memory are limited to simulations with small-scale and offline paradigms. Thus, this work implements associative memory with an Unmanned Ground Vehicle (UGV) and neuromorphic hardware, specifically Intel’s Loihi, for an online learning scenario. This system emulates the classic associative learning in rats using the UGV in place of the rats. In specific, it successfully reproduces the fear conditioning with no pretraining procedure or labeled datasets. The UGV is rendered capable of autonomously learning the cause-and-effect relationship of the light stimulus and vibration stimulus and exhibiting a movement response to demonstrate the memorization. Hebbian learning dynamics are used to update the synaptic weights during the associative learning process. The Intel Loihi chip is integrated with this online learning system for processing visual signals with a specialized neural assembly. While processing, the Loihi’s average power usages for computing logic and memory are 30 mW and 29 mW, respectively.","abstract_html":"Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationships between events and objects. This learning paradigm is referred to as associative learning. The successful implementation of associative learning imitates self-learning schemes analogous to animals which resolve the challenges of deep learning. Current state-of-the-art implementations of associative memory are limited to simulations with small-scale and offline paradigms. Thus, this work implements associative memory with an Unmanned Ground Vehicle (UGV) and neuromorphic hardware, specifically Intel’s Loihi, for an online learning scenario. This system emulates the classic associative learning in rats using the UGV in place of the rats. In specific, it successfully reproduces the fear conditioning with no pretraining procedure or labeled datasets. The UGV is rendered capable of autonomously learning the cause-and-effect relationship of the light stimulus and vibration stimulus and exhibiting a movement response to demonstrate the memorization. Hebbian learning dynamics are used to update the synaptic weights during the associative learning process. The Intel Loihi chip is integrated with this online learning system for processing visual signals with a specialized neural assembly. While processing, the Loihi’s average power usages for computing logic and memory are 30 mW and 29 mW, respectively.","abstract_has_math":false,"creators":["Zins, Noah"],"institution":null,"degree_name":"Master of Science in Electrical and Computer Engineering (MS)","degree_level":"Open Access Master's Thesis","degree_discipline":"Department of Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Hongyu An"],"advisors":[],"committee_chairs":[],"committee_members":["Lan Zhang","Xiaoyong Yuan"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:18:53Z","subjects":["neuromorphic","associative learning","robotics","artificial intelligence","unsupervised learning","sparse coding","Artificial Intelligence and Robotics","Computational Engineering","Computer Engineering","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1608"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1608","href":"https://digitalcommons.mtu.edu/etdr/1608","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1608","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1608","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2747","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hongyu An"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Lan Zhang","Xiaoyong Yuan"]},{"key":"dc:creator","label":"Author","values":["Zins, Noah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2023-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Open Access Master's Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Electrical and Computer Engineering (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["neuromorphic","associative learning","robotics","artificial intelligence","unsupervised learning","sparse coding","Artificial Intelligence and Robotics","Computational Engineering","Computer Engineering","Electrical and Computer Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights.license","label":"Dc Rights License","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1608","https://digitalcommons.mtu.edu/etdr/1608"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationships between events and objects. This learning paradigm is referred to as associative learning. The successful implementation of associative learning imitates self-learning schemes analogous to animals which resolve the challenges of deep learning. Current state-of-the-art implementations of associative memory are limited to simulations with small-scale and offline paradigms. Thus, this work implements associative memory with an Unmanned Ground Vehicle (UGV) and neuromorphic hardware, specifically Intel’s Loihi, for an online learning scenario. This system emulates the classic associative learning in rats using the UGV in place of the rats. In specific, it successfully reproduces the fear conditioning with no pretraining procedure or labeled datasets. The UGV is rendered capable of autonomously learning the cause-and-effect relationship of the light stimulus and vibration stimulus and exhibiting a movement response to demonstrate the memorization. Hebbian learning dynamics are used to update the synaptic weights during the associative learning process. The Intel Loihi chip is integrated with this online learning system for processing visual signals with a specialized neural assembly. While processing, the Loihi’s average power usages for computing logic and memory are 30 mW and 29 mW, respectively."]},{"key":"dc:title","label":"Title","values":["Neuromorphic Computing Applications in Robotics"]}]}],"canonical_facts":{"dc:contributor":["Hongyu An"],"dc:contributor.committeemember":["Lan Zhang","Xiaoyong Yuan"],"dc:creator":["Zins, Noah"],"dc:date.created":["2023-01-01T08:00:00Z"],"dc:description.abstract":["Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationships between events and objects. This learning paradigm is referred to as associative learning. The successful implementation of associative learning imitates self-learning schemes analogous to animals which resolve the challenges of deep learning. Current state-of-the-art implementations of associative memory are limited to simulations with small-scale and offline paradigms. Thus, this work implements associative memory with an Unmanned Ground Vehicle (UGV) and neuromorphic hardware, specifically Intel’s Loihi, for an online learning scenario. This system emulates the classic associative learning in rats using the UGV in place of the rats. In specific, it successfully reproduces the fear conditioning with no pretraining procedure or labeled datasets. The UGV is rendered capable of autonomously learning the cause-and-effect relationship of the light stimulus and vibration stimulus and exhibiting a movement response to demonstrate the memorization. Hebbian learning dynamics are used to update the synaptic weights during the associative learning process. The Intel Loihi chip is integrated with this online learning system for processing visual signals with a specialized neural assembly. While processing, the Loihi’s average power usages for computing logic and memory are 30 mW and 29 mW, respectively."],"dc:identifier":["10.37099/mtu.dc.etdr/1608","https://digitalcommons.mtu.edu/etdr/1608"],"dc:rights.license":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["neuromorphic","associative learning","robotics","artificial intelligence","unsupervised learning","sparse coding","Artificial Intelligence and Robotics","Computational Engineering","Computer Engineering","Electrical and Computer Engineering"],"dc:title":["Neuromorphic Computing Applications in Robotics"],"thesis:degree_discipline":["Department of Electrical and Computer Engineering"],"thesis:degree_level":["Open Access Master's Thesis"],"thesis:degree_name":["Master of Science in Electrical and Computer Engineering (MS)"]},"updated_at":"2026-11-19T08:18:53Z"}