Back to search

Marshall University

Ablative study of large language model-based gesture inference for autonomous navigation

Abstract

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.

Degree

thesis:*
Name thesis:degree_name
Computer Science
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
College of Engineering and Computer Sciences

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Loftus, Neil
Contributors dc:contributor
  • Dr. Husnu Narman
  • Dr. Pingping Zhu
  • Dr. Haroon Malik

Subjects

dc:subject × 8

Identifiers

dc:identifier.*
Repository record dc:identifier
https://mds.marshall.edu/etd/2047

Chain of custody

source
Harvested from
Marshall University
Base URL
mds.marshall.edu/do/oai/
Last updated
2026-11-21
Source record
OAI-PMH GetRecord
citation

Loftus, Neil. Ablative study of large language model-based gesture inference for autonomous navigation. Thesis thesis, https://mds.marshall.edu/etd/2047