When Prolog meets generative models: a new approach for managing knowledge and planning in robotic applications
This addresses the challenge of integrating symbolic reasoning and generative models for robotic planning, offering a practical framework for multi-robot systems.
The paper tackles the problem of managing knowledge and planning in robotic applications by proposing a robot-oriented knowledge management system using Prolog, which enables efficient population from natural language texts with LLMs, generation of temporal parallel plans for multi-robot systems, and translation into executable behavior trees, demonstrated on a realistic application.
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.