DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning

TL;DR

DKPROMPT integrates domain knowledge from PDDL with vision-language models to enhance open-world robot task planning, outperforming existing methods in task completion rates.

Contribution

The paper introduces DKPROMPT, a novel framework that automates VLM prompting with domain knowledge for improved open-world planning.

Findings

DKPROMPT achieves higher task completion rates than baselines.

It effectively combines classical planning with vision-language models.

Experimental results validate its superiority in open-world scenarios.

Abstract

Vision-language models (VLMs) have been applied to robot task planning problems, where the robot receives a task in natural language and generates plans based on visual inputs. While current VLMs have demonstrated strong vision-language understanding capabilities, their performance is still far from being satisfactory in planning tasks. At the same time, although classical task planners, such as PDDL-based, are strong in planning for long-horizon tasks, they do not work well in open worlds where unforeseen situations are common. In this paper, we propose a novel task planning and execution framework, called DKPROMPT, which automates VLM prompting using domain knowledge in PDDL for classical planning in open worlds. Results from quantitative experiments show that DKPROMPT outperforms classical planning, pure VLM-based and a few other competitive baselines in task completion rate.