A Framework for Neurosymbolic Robot Action Planning using Large Language Models

Abstract

Symbolic task planning is a widely used approach to enforce robot autonomy due to its ease of understanding and deployment in robot architectures. However, techniques for symbolic task planning are difficult to scale in real-world, human-robot collaboration scenarios because of the poor performance in complex planning domains or when frequent re-planning is needed. We present a framework, Teriyaki, specifically aimed at bridging the gap between symbolic task planning and machine learning approaches. The rationale is training Large Language Models (LLMs), namely GPT-3, into a neurosymbolic task planner compatible with the Planning Domain Definition Language (PDDL), and then leveraging its generative capabilities to overcome a number of limitations inherent to symbolic task planners. Potential benefits include (i) a better scalability in so far as the planning domain complexity increases, since LLMs' response time linearly scales with the combined length of the input and the output, and (ii) the ability to synthesize a plan action-by-action instead of end-to-end, making each action available for execution as soon as it is generated instead of waiting for the whole plan to be available, which in turn enables concurrent planning and execution. Recently, significant efforts have been devoted by the research community to evaluate the cognitive capabilities of LLMs, with alternate successes. Instead, with Teriyaki we aim to provide an overall planning performance comparable to traditional planners in specific planning domains, while leveraging LLMs capabilities to build a look-ahead predictive planning model. Preliminary results in selected domains show that our method can: (i) solve 95.5% of problems in a test data set of 1,000 samples; (ii) produce plans up to 13.5% shorter than a traditional symbolic planner; (iii) reduce average overall waiting times for a plan availability by up to 61.4%

36 pages, 7 figures, 2 tables. Updated according to reviewers' comments. Previous title: A Framework to Generate Neurosymbolic PDDL-compliant Planners

References in corpus (14)

• Llama 2: Open Foundation and Fine-Tuned Chat Models
• PaLM: Scaling Language Modeling with Pathways
• Evaluating Large Language Models Trained on Code
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• LaMDA: Language Models for Dialog Applications
• The Fast Downward Planning System
• PaLM-E: An Embodied Multimodal Language Model
• Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
• ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case Application
• Neurosymbolic AI: The 3rd Wave
• Deployment and Evaluation of a Flexible Human-Robot Collaboration Model Based on AND/OR Graphs in a Manufacturing Environment
• Grammar Prompting for Domain-Specific Language Generation with Large Language Models
• Generalized Planning in PDDL Domains with Pretrained Large Language Models
• GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs

Cited by in corpus (2)

• Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach
• Aligning LLM+PDDL Symbolic Plans with Human Objective Specifications through Evolutionary Algorithm Guidance