{"id":{"repo_id":"marshall","oai_identifier":"oai:mds.marshall.edu:etd-3052"},"canonical_url":"https://search.ndltd.org/etd/marshall/oai:mds.marshall.edu:etd-3052","repository":{"repo_id":"marshall","name":"Marshall University","base_url":"https://mds.marshall.edu/do/oai/"},"display":{"title":"Ablative study of large language model-based gesture inference for autonomous navigation","abstract":"Human gesture inference has broad applications ranging from sign language interpretation to device control. Traditional methods often rely on extensive manually labeled hand datasets for deep learning. Furthermore, they are typically limited to a discrete set of gestures existing in these datasets. Large Language Models (LLMs) created by enterprise companies such as OpenAI have demonstrated positive results in many artificial intelligence tasks, with a notable strength being their adaptability. Existing literature has shown that LLM based systems can not only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference time, and token expenditure. We intend to iteratively measure several techniques to determine the optimal LLM architecture for gesture based guidance.","abstract_html":"Human gesture inference has broad applications ranging from sign language interpretation to device control. Traditional methods often rely on extensive manually labeled hand datasets for deep learning. Furthermore, they are typically limited to a discrete set of gestures existing in these datasets. Large Language Models (LLMs) created by enterprise companies such as OpenAI have demonstrated positive results in many artificial intelligence tasks, with a notable strength being their adaptability. Existing literature has shown that LLM based systems can not only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference time, and token expenditure. We intend to iteratively measure several techniques to determine the optimal LLM architecture for gesture based guidance.","abstract_has_math":false,"creators":["Loftus, Neil"],"institution":null,"degree_name":"Computer Science","degree_level":"Thesis","degree_discipline":"College of Engineering and Computer Sciences","degree_department":null,"school":null,"contributors":["Dr. Husnu Narman","Dr. Pingping Zhu","Dr. Haroon Malik"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-21T19:58:30Z","subjects":["Artificial Intelligence and Robotics","Computer Sciences","Physical Sciences and Mathematics","artificial intelligence","autonomous guidance","computer science","gesture inference","large language models"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://mds.marshall.edu/etd/2047","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://mds.marshall.edu/etd/2047","record_label":"Repository record","record_kind":"record","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://mds.marshall.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Amds.marshall.edu%3Aetd-3052","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Husnu Narman","Dr. Pingping Zhu","Dr. Haroon Malik"]},{"key":"dc:creator","label":"Author","values":["Loftus, Neil"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-04-16T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["College of Engineering and Computer Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence and Robotics","Computer Sciences","Physical Sciences and Mathematics","artificial intelligence","autonomous guidance","computer science","gesture inference","large language models"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://mds.marshall.edu/etd/2047"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Human gesture inference has broad applications ranging from sign language interpretation to device control. Traditional methods often rely on extensive manually labeled hand datasets for deep learning. Furthermore, they are typically limited to a discrete set of gestures existing in these datasets. Large Language Models (LLMs) created by enterprise companies such as OpenAI have demonstrated positive results in many artificial intelligence tasks, with a notable strength being their adaptability. Existing literature has shown that LLM based systems can not only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference time, and token expenditure. We intend to iteratively measure several techniques to determine the optimal LLM architecture for gesture based guidance."]},{"key":"dc:title","label":"Title","values":["Ablative study of large language model-based gesture inference for autonomous navigation"]}]}],"canonical_facts":{"dc:contributor":["Dr. Husnu Narman","Dr. Pingping Zhu","Dr. Haroon Malik"],"dc:creator":["Loftus, Neil"],"dc:date.available":["2026-04-16T07:00:00Z"],"dc:date.created":["2026-01-01T08:00:00Z"],"dc:description.abstract":["Human gesture inference has broad applications ranging from sign language interpretation to device control. Traditional methods often rely on extensive manually labeled hand datasets for deep learning. Furthermore, they are typically limited to a discrete set of gestures existing in these datasets. Large Language Models (LLMs) created by enterprise companies such as OpenAI have demonstrated positive results in many artificial intelligence tasks, with a notable strength being their adaptability. Existing literature has shown that LLM based systems can not only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference time, and token expenditure. We intend to iteratively measure several techniques to determine the optimal LLM architecture for gesture based guidance."],"dc:identifier":["https://mds.marshall.edu/etd/2047"],"dc:subject":["Artificial Intelligence and Robotics","Computer Sciences","Physical Sciences and Mathematics","artificial intelligence","autonomous guidance","computer science","gesture inference","large language models"],"dc:title":["Ablative study of large language model-based gesture inference for autonomous navigation"],"thesis:degree_discipline":["College of Engineering and Computer Sciences"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Computer Science"]},"updated_at":"2026-11-21T19:58:30Z"}