LLM-Driven Corrective Robot Operation Code Generation with Static Text-Based Simulation

TL;DR

This paper introduces a static text-based simulation framework leveraging LLMs to reliably generate and correct robot operation code without the need for physical experiments or dynamic simulation, improving deployment efficiency.

Contribution

The paper presents a novel static simulation approach using LLMs for robot code validation and correction, eliminating reliance on dynamic execution environments.

Findings

High accuracy in static simulation of robot code

Reliable code correction comparable to state-of-the-art methods

Effective across various robot types and tasks

Abstract

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective designs with feedback from the observation of executing code have been increasingly adopted in existing research. However, the code execution in these designs relies on either a physical experiment or a customized simulation environment, which limits their deployment due to the high configuration effort of the environment and the potential long execution time. In this paper, we explore the possibility of directly leveraging LLM to enable static simulation of robot operation code, and then leverage it to design a new reliable LLM-driven corrective robot operation code generation framework. Our framework configures the LLM as a static simulator with enhanced capabilities that reliably simulate robot code execution by interpreting actions, reasoning over state transitions, analyzing execution outcomes, and generating semantic observations that accurately capture trajectory dynamics. To validate the performance of our framework, we performed experiments on various operation tasks for different robots, including UAVs and small ground vehicles. The experiment results not only demonstrated the high accuracy of our static text-based simulation but also the reliable code generation of our LLM-driven corrective framework, which achieves a comparable performance with state-of-the-art research while does not rely on dynamic code execution using physical experiments or simulators.