Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications
This work addresses the challenge of making probabilistic planning more accessible and scalable for robotic applications, representing an incremental advancement by combining existing methods like LLMs and formal verification.
The paper tackles the problem of creating Markov Decision Processes (MDPs) for robotics by integrating Large Language Models (LLMs) with automated planning and formal verification, resulting in a framework that generates executable policies from natural language descriptions with minimal manual effort, validated in three human-robot interaction scenarios.
We present a novel framework that integrates Large Language Models (LLMs) with automated planning and formal verification to streamline the creation and use of Markov Decision Processes (MDP). Our system leverages LLMs to extract structured knowledge in the form of a Prolog knowledge base from natural language (NL) descriptions. It then automatically constructs an MDP through reachability analysis, and synthesises optimal policies using the Storm model checker. The resulting policy is exported as a state-action table for execution. We validate the framework in three human-robot interaction scenarios, demonstrating its ability to produce executable policies with minimal manual effort. This work highlights the potential of combining language models with formal methods to enable more accessible and scalable probabilistic planning in robotics.