Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications

TL;DR

This paper introduces a framework that combines large language models with formal verification to automatically generate and verify Markov Decision Processes for robotic applications, reducing manual effort and increasing scalability.

Contribution

The work presents a novel integration of LLMs, automated planning, and formal verification to streamline MDP creation and policy synthesis in robotics.

Findings

Successfully generated executable policies in human-robot interaction scenarios

Reduced manual effort in MDP construction and policy synthesis

Demonstrated scalability and effectiveness of the approach

Abstract

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.