Date of Award
5-1-2025
Degree Name
Master of Science
Department
Computer Science
First Advisor
Hexmoor, Henry
Abstract
Mobile robots traditionally relied on programming languages for commands, which made them difficult to operate for non-experts. Without a Natural Language Interface (NLI), robots also struggled to perform tasks requiring multiple steps or understanding contextual nuances.This research aims to develop a Natural Language Interface (NLI) for mobile robots, eliminating the need for specialized programming knowledge and enabling intuitive human-robot interaction. The study compares a voice-controlled navigation system for two mobile robots, TurtleBot2i and ROSbot XL, by integrating Natural Language Processing (NLP) with the Robot Operating System (ROS).The system utilizes Large Language Models (LLMs) such as OpenAI’s Whisper and GPT-4o to convert speech into accurate robot commands, ensuring reliable execution even in noisy environments. Key innovations include real-time voice-to-command translation, the ability to handle informal commands, and dynamic audio feedback. This research presents a detailed analysis of the system's architecture, the challenges faced, and the solutions implemented to create an efficient and user-friendly voice-controlled robotic interface.
Access
This thesis is only available for download to the SIUC community. Current SIUC affiliates may also access this paper off campus by searching Dissertations & Theses @ Southern Illinois University Carbondale from ProQuest. Others should contact the interlibrary loan department of your local library or contact ProQuest's Dissertation Express service.