DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning
This work addresses robot planning challenges in unpredictable environments, offering a hybrid solution that is incremental over existing methods.
The paper tackles the problem of robot task planning in open worlds by proposing DKPROMPT, a framework that automates vision-language model prompting using domain knowledge from PDDL, resulting in improved task completion rates compared to classical planning and VLM-based baselines.
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.