用形式化逻辑让机器人更准确理解自然语言指令。
VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications
- 用信号时序逻辑连接自然语言与任务目标，减少歧义。
- 在两个挑战性场景中表现更稳定可靠，路径一致性更高。
- 适合需要高可靠性自然语言控制的机器人研究者。
长期以来，人们希望用自然语言控制机器人完成复杂任务。大语言模型（LLMs）使这一目标更接近实现，但其仍受自然语言固有歧义和模型不确定性的影响。本文提出一种基于LLM的新型机器人运动规划器VernaCopter，利用信号时序逻辑（STL）作为自然语言指令与具体任务目标之间的桥梁。形式化规格的严谨性与抽象性使规划器能生成高质量且高度一致的路径，指导机器人运动控制。相比传统基于自然语言提示的规划器，VernaCopter因减少模糊不确定性而更具稳定性和可靠性。其有效性已在两个小型但具有挑战性的实验场景中得到验证，表明其在设计自然语言驱动机器人方面具有潜力。
原文摘要 · Abstract (English)
It has been an ambition of many to control a robot for a complex task using natural language (NL). The rise of large language models (LLMs) makes it closer to coming true. However, an LLM-powered system still suffers from the ambiguity inherent in an NL and the uncertainty brought up by LLMs. This paper proposes a novel LLM-based robot motion planner, named \textit{VernaCopter}, with signal temporal logic (STL) specifications serving as a bridge between NL commands and specific task objectives. The rigorous and abstract nature of formal specifications allows the planner to generate high-quality and highly consistent paths to guide the motion control of a robot. Compared to a conventional NL-prompting-based planner, the proposed VernaCopter planner is more stable and reliable due to less ambiguous uncertainty. Its efficacy and advantage have been validated by two small but challenging experimental scenarios, implying its potential in designing NL-driven robots.
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。