VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots
This work addresses the critical need for robust pre-execution verification in autonomous systems, improving reliability and efficiency for robotics applications, though it appears incremental as it builds on existing LLM and LTL methods.
The paper tackles the challenge of ensuring reliable and efficient task planning in robotics by proposing an LLM-based architecture for pre-execution verification of high-level task plans, demonstrating broad applicability to household tasks through rigorous testing on datasets of varying complexity.
In the field of robotics, researchers face a critical challenge in ensuring reliable and efficient task planning. Verifying high-level task plans before execution significantly reduces errors and enhance the overall performance of these systems. In this paper, we propose an architecture for automatically verifying high-level task plans before their execution in simulator or real-world environments. Leveraging Large Language Models (LLMs), our approach consists of two key steps: first, the conversion of natural language instructions into Linear Temporal Logic (LTL), followed by a comprehensive analysis of action sequences. The module uses the reasoning capabilities of the LLM to evaluate logical coherence and identify potential gaps in the plan. Rigorous testing on datasets of varying complexity demonstrates the broad applicability of the module to household tasks. We contribute to improving the reliability and efficiency of task planning and addresses the critical need for robust pre-execution verification in autonomous systems. The code is available at https://verifyllm.github.io.