GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control

2025-02-18

AI Summary

This work addresses the insufficient reliability of large language models (LLMs) in complex, reasoning-intensive drone control tasks. We propose GSCE, a novel prompting framework integrating Guidelines, Skills (as modular APIs), Constraints, and Examples. GSCE introduces three key innovations: (1) explicit skill encapsulation via callable APIs, (2) hard constraint injection for formal safety and regulatory compliance modeling, and (3) multi-granularity example co-embedding to guide structured, multi-stage reasoning chains. These mechanisms collectively enhance the interpretability, safety, and regulatory adherence of generated control code. Evaluated on multi-level real-world drone tasks—including navigation, obstacle avoidance, and mission sequencing—GSCE achieves average improvements of 37.2% in task success rate and 41.5% in task completion rate over state-of-the-art prompting methods. Results demonstrate its robustness and practical efficacy in autonomous aerial systems.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The integration of Large Language Models (LLMs) into robotic control, including drones, has the potential to revolutionize autonomous systems. Research studies have demonstrated that LLMs can be leveraged to support robotic operations. However, when facing tasks with complex reasoning, concerns and challenges are raised about the reliability of solutions produced by LLMs. In this paper, we propose a prompt framework with enhanced reasoning to enable reliable LLM-driven control for drones. Our framework consists of novel technical components designed using Guidelines, Skill APIs, Constraints, and Examples, namely GSCE. GSCE is featured by its reliable and constraint-compliant code generation. We performed thorough experiments using GSCE for the control of drones with a wide level of task complexities. Our experiment results demonstrate that GSCE can significantly improve task success rates and completeness compared to baseline approaches, highlighting its potential for reliable LLM-driven autonomous drone systems.

Problem

• Enhance reasoning for reliable drone control
• Address LLM reliability in complex tasks
• Improve task success with GSCE framework

Innovation

• Prompt framework with enhanced reasoning
• GSCE for reliable code generation
• Improved drone control task success