用增强推理的提示框架，让大模型更可靠地控制无人机
GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control
- 设计GSCE框架，融合指南、技能接口、约束和示例提升推理能力
- 在复杂任务中任务成功率与完成度显著优于基线方法
- 适合需要高可靠性的大模型无人机控制系统研究者
将大型语言模型（LLMs）融入机器人控制，包括无人机，有望革新自主系统。已有研究表明，LLMs可用于支持机器人操作。然而，在面对需要复杂推理的任务时，人们对LLMs生成解决方案的可靠性提出质疑。本文提出一种具备增强推理能力的提示框架，以实现可靠的LLM驱动无人机控制。该框架由新设计的技术组件构成，包括指南（Guidelines）、技能API（Skill APIs）、约束（Constraints）和示例（Examples），统称为GSCE。GSCE具有生成可靠且符合约束的代码的能力。我们通过广泛实验评估了GSCE在不同任务复杂度下的无人机控制表现。实验结果表明，相比基线方法，GSCE能显著提升任务成功率与完整性，凸显其在可靠LLM驱动自主无人机系统中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。