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

arXiv: https://arxiv.org/abs/2309.15049 · HTML: https://mlsanity.com/paper/2309.15049/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 26 Sep 2023.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [A Survey of Behavior Trees in Robotics and AI](https://mlsanity.com/paper/2005.05842/) (2020)
- [A Survey of Knowledge Representation in Service Robotics](https://mlsanity.com/paper/1807.02192/) (2018)
- [COLIN: Planning with Continuous Linear Numeric Change](https://mlsanity.com/paper/1401.5857/) (2014)
- [PlanSys2: A Planning System Framework for ROS2](https://mlsanity.com/paper/2107.00376/) (2021)
- [Understanding Natural Language in Context](https://mlsanity.com/paper/2205.12691/) (2022)

## Built on by (most cited first, 2 of 2)

- [Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications](https://mlsanity.com/paper/2511.23143/) (2025)
- [Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs](https://mlsanity.com/paper/2510.09970/) (2025)

## Abstract (arXiv)

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.