As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture
This work addresses the problem of making robotic mission planning accessible to non-experts in precision agriculture by using LLMs and formal verification, but the contribution is incremental.
The paper extends a mission planner for precision agriculture that uses LLMs to synthesize plans from natural language, adding feedback loops with linear temporal logic (LTL) to ensure specifications are met. Experiments show the system can generate valuable LTL formulas and address ambiguities, but no concrete performance numbers are provided.
Though robotic systems are now being commercialized and deployed in various industries, many of these systems are highly specialized and often require an advanced skill set to operate and ensure they perform as instructed. To mitigate this problem, we recently introduced a mission planner leveraging LLMs to synthesize mission plans in precision agriculture based on mission descriptions provided in natural language. While the system demonstrates impressive performance, it also suffers from the inherent ambiguities of natural language. In this paper, we extend our system to address this issue by introducing multiple feedback loops in the planning architecture that leverage linear temporal logic (LTL) to ensure the mission planning system meets the specifications formulated by the user while still using natural language. To mitigate potential bias, this is achieved by using two different commercial LLMs in charge of the specification and verification subtasks. Through extensive experiments, we highlight the strengths and limitations of integrating mission verification into a fully autonomous pipeline, particularly regarding an LLM's ability to generate valuable LTL formulas, and show how our proposed implementation addresses and solves these challenges.