SPAR: Scalable LLM-based PDDL Domain Generation for Aerial Robotics

2025-09-17

AI Summary

Manually constructing PDDL planning domains for UAV missions (e.g., surveillance, delivery, inspection) is labor-intensive, error-prone, and hinders real-world deployment. Method: This paper introduces SPAR—the first end-to-end framework that automatically generates executable PDDL domains directly from natural language specifications. It establishes the first systematically validated, UAV-specific PDDL dataset; designs an LLM-oriented structured prompting mechanism integrating syntactic constraints, semantic alignment, and executability feedback; and incorporates PDDL syntax checking, planner-based feasibility validation, and interpretability assessment. Results: Experiments show that SPAR-generated domains achieve over 90% correctness in syntax, plan executability, and task feasibility—significantly lowering the modeling barrier and enabling users without formal planning expertise to efficiently construct complex UAV task models.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We investigate the problem of automatic domain generation for the Planning Domain Definition Language (PDDL) using Large Language Models (LLMs), with a particular focus on unmanned aerial vehicle (UAV) tasks. Although PDDL is a widely adopted standard in robotic planning, manually designing domains for diverse applications such as surveillance, delivery, and inspection is labor-intensive and error-prone, which hinders adoption and real-world deployment. To address these challenges, we propose SPAR, a framework that leverages the generative capabilities of LLMs to automatically produce valid, diverse, and semantically accurate PDDL domains from natural language input. To this end, we first introduce a systematically formulated and validated UAV planning dataset, consisting of ground-truth PDDL domains and associated problems, each paired with detailed domain and action descriptions. Building on this dataset, we design a prompting framework that generates high-quality PDDL domains from language input. The generated domains are evaluated through syntax validation, executability, feasibility, and interpretability. Overall, this work demonstrates that LLMs can substantially accelerate the creation of complex planning domains, providing a reproducible dataset and evaluation pipeline that enables application experts without prior experience to leverage it for practical tasks and advance future research in aerial robotics and automated planning.

Problem

• Automating PDDL domain generation for UAV tasks
• Reducing manual labor in robotic planning design
• Enabling non-experts to create planning domains

Innovation

• LLM-based PDDL domain generation
• Natural language to PDDL conversion
• Automated UAV planning framework