Preference-Guided Planning: An Active Elicitation Approach
This work addresses the problem of integrating human preferences into automated planning systems, particularly in HTN planning, with incremental improvements in efficiency and user interaction.
The paper tackles the challenge of actively eliciting preferences from human experts during planning to improve plan quality and speed, showing that the proposed approach reduces expert burden and enhances planner performance across diverse domains.
Planning with preferences has been employed extensively to quickly generate high-quality plans. However, it may be difficult for the human expert to supply this information without knowledge of the reasoning employed by the planner and the distribution of planning problems. We consider the problem of actively eliciting preferences from a human expert during the planning process. Specifically, we study this problem in the context of the Hierarchical Task Network (HTN) planning framework as it allows easy interaction with the human. Our experimental results on several diverse planning domains show that the preferences gathered using the proposed approach improve the quality and speed of the planner, while reducing the burden on the human expert.