VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications
This addresses the challenge of ambiguity in natural language commands for robotics, though it is incremental as it builds on existing LLM and formal specification techniques.
The paper tackles the problem of controlling robots with natural language by introducing VernaCopter, an LLM-based motion planner that uses signal temporal logic to reduce ambiguity, resulting in more stable and reliable paths compared to conventional methods.
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.