Collaborative Planning with Encoding of Users’ High-level Strategies

TitleCollaborative Planning with Encoding of Users’ High-level Strategies
Publication TypeConference Proceedings
Year of Conference2017
AuthorsKim, J., C. J. Banks, and J. A. Shah
Conference NameThe Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
Date Published02/2017
Conference LocationSan Francisco, California
KeywordsCollaborative Planning, Human-Aware AI, topic3
Abstract

The generation of near-optimal plans for multi-agent systems with numerical states and temporal actions is computationally challenging. Current off-the-shelf planners can take a very long time before generating a near-optimal solution. In an effort to reduce plan computation time, increase the quality of the resulting plans, and make them more interpretable by humans, we explore collaborative planning techniques that actively involve human users in plan generation. Specifically, we explore a framework in which users provide high-level strategies encoded as soft preferences to guide the low-level search of the planner. Through human subject experimentation, we empirically demonstrate that this approach results in statistically significant improvements to plan quality, without substantially increasing computation time. We also show that the resulting plans achieve greater similarity to those generated by humans with regard to the produced sequences of actions, as compared to plans that do not incorporate user-provided strategies.

URLhttp://interactive.mit.edu/sites/default/files/documents/Kim_AAAI_2017_preprint.pdf
Refereed DesignationRefereed