用少量示例训练模型，让机器人更安全地理解指令。
How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach
- 用少量示例微调GPT-4o，结合知识图谱提示提升可靠性。
- 在模拟环境中验证无人机代码，确保符合飞行规范。
- 适合关注机器人安全与自然语言交互的开发者。
大型语言模型（LLMs）正推动机器人领域发展，使机器人能够理解并执行自然语言指令。其核心优势在于处理技术手册、操作说明、学术论文及用户查询中的文本信息。然而，在未经过安全验证的情况下直接部署由LLM生成的代码，可能带来显著风险。本文提出一种安全层，用于在模拟环境中执行前验证ChatGPT生成的代码，以控制无人机。该安全层采用基于少样本学习（Few-Shot learning）微调的GPT-4o模型，并结合知识图谱提示（KGP）。实验表明，该方法有效提升了机器人行为的安全性与合规性，确保其遵循无人机操作规范。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are transforming the robotics domain by enabling robots to comprehend and execute natural language instructions. The cornerstone benefits of LLM include processing textual data from technical manuals, instructions, academic papers, and user queries based on the knowledge provided. However, deploying LLM-generated code in robotic systems without safety verification poses significant risks. This paper outlines a safety layer that verifies the code generated by ChatGPT before executing it to control a drone in a simulated environment. The safety layer consists of a fine-tuned GPT-4o model using Few-Shot learning, supported by knowledge graph prompting (KGP). Our approach improves the safety and compliance of robotic actions, ensuring that they adhere to the regulations of drone operations.
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。