PDDLFuse: A Tool for Generating Diverse Planning Domains

TL;DR

PDDLFuse is a novel tool that generates diverse and complex planning domains in PDDL, inspired by domain randomization, to improve testing and validation of planning algorithms.

Contribution

It introduces a method to generate varied planning domains with adjustable difficulty, advancing domain diversity and complexity in planning research.

Findings

Efficient creation of intricate, varied planning domains.

Enhanced testing capabilities for planning algorithms.

Significant improvement over traditional domain generation methods.

Abstract

Various real-world challenges require planning algorithms that can adapt to a broad range of domains. Traditionally, the creation of planning domains has relied heavily on human implementation, which limits the scale and diversity of available domains. While recent advancements have leveraged generative AI technologies such as large language models (LLMs) for domain creation, these efforts have predominantly focused on translating existing domains from natural language descriptions rather than generating novel ones. In contrast, the concept of domain randomization, which has been highly effective in reinforcement learning, enhances performance and generalizability by training on a diverse array of randomized new domains. Inspired by this success, our tool, PDDLFuse, aims to bridge this gap in Planning Domain Definition Language (PDDL). PDDLFuse is designed to generate new, diverse planning domains that can be used to validate new planners or test foundational planning models. We have developed methods to adjust the domain generators parameters to modulate the difficulty of the domains it generates. This adaptability is crucial as existing domain-independent planners often struggle with more complex problems. Initial tests indicate that PDDLFuse efficiently creates intricate and varied domains, representing a significant advancement over traditional domain generation methods and making a contribution towards planning research.