Logo image
An enhanced reasoning framework with closed-loop refinement for reliable LLM-driven drone control: a thesis in Computer Science
Thesis   Open access

An enhanced reasoning framework with closed-loop refinement for reliable LLM-driven drone control: a thesis in Computer Science

Wenhao Wang
Master of Science (MS), University of Massachusetts Dartmouth
2025
DOI:
https://doi.org/10.62791/20429

Abstract

Large Language Models (LLMs) have demonstrated revolutionary potential in autonomous systems. Studies have demonstrated that LLMs can be leveraged to support various robotic operations including visual navigation, planning, and drone controls. However, when facing tasks with complex reasoning, concerns and challenges are raised about the reliability of solutions produced by LLMs. This thesis proposed a closed-loop reasoning approach to enhance the reliability of LLM-driven drone control. The proposed method introduces a structured prompt framework designed with Guidelines, Skills, Constraints, and Examples integrated with a closed-loop feedback mechanism that iteratively refines the generated code based on its execution outcomes. The framework is featured by iteratively refining LLM-generated solutions, thereby improving reasoning quality and control reliability. We performed thorough experiments of our approach for drone control with a wide range of task complexities. The experiment result demonstrates that our framework significantly improves task success rates and completeness compared to baseline approaches, highlighting its potential for reliable LLM-driven autonomous drone systems.
pdf
Wang W. COE MS Thesis 20251.34 MBDownloadView
CC BY-NC-ND V4.0 Open Access

Metrics

28 File views/ downloads
91 Record Views

Details

Logo image