When Prolog meets generative models: a new approach for managing knowledge and planning in robotic applications

TL;DR

This paper introduces a Prolog-based knowledge management system for robotics that leverages large language models for knowledge population, generates multi-robot plans, and translates them into executable behavior trees, demonstrated on a real application.

Contribution

It presents a novel framework combining Prolog, LLMs, and formal planning for robotic knowledge management and multi-robot planning, supported by open source tools.

Findings

Efficient knowledge population from natural language texts.

Bumpless generation of temporal parallel plans.

Automated translation into executable behavior trees.

Abstract

In this paper, we propose a robot oriented knowledge management system based on the use of the Prolog language. Our framework hinges on a special organisation of knowledge base that enables: 1. its efficient population from natural language texts using semi-automated procedures based on Large Language Models, 2. the bumpless generation of temporal parallel plans for multi-robot systems through a sequence of transformations, 3. the automated translation of the plan into an executable formalism (the behaviour trees). The framework is supported by a set of open source tools and is shown on a realistic application.