VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications

TL;DR

VernaCopter is a novel LLM-based robot motion planner that uses formal STL specifications to interpret natural language commands, resulting in more reliable and consistent robot paths.

Contribution

It introduces a formal specification-based approach to disambiguate natural language commands for robot control, improving stability and reliability over conventional NL prompting methods.

Findings

VernaCopter generates high-quality, consistent robot paths.

The approach reduces ambiguity and uncertainty in NL commands.

Validated in two challenging experimental scenarios.

Abstract

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.