Plan and Goal Recognition as HTN Planning

Plan and Goal Recognition as HTN Planning. Höller, D., Bercher, P., Behnke, G., & Biundo, S. In Proceedings of the AAAI 2018 Workshop on Plan, Activity, and Intent Recognition (PAIR 2018), 2018.

Paper abstract bibtex

Companion systems are cooperative, cognitive systems aiming at assisting a user in everyday situations. Therefore, these systems require a high level of availability. One option to meet this requirement is to use a web-deployable architecture. In this demo paper, we present a multimodal cloud-based dialogue framework for the development of a distributed, web-based companion system. The proposed framework is intended to provide an efficient, easily extensible, and scalable approach for this kind of systems and will be demonstrated in a do-it-yourself assistance scenario. Plan- and Goal Recognition (PGR) is the task of inferring the goals and plans of an agent based on its actions. Traditional approaches in PGR are based on a plan library including pairs of plans and corresponding goals. In recent years, the field successfully exploited the performance of planning systems for PGR. The main benefits are the presence of efficient solvers and well-established, compact formalisms for behavior representation. However, the expressivity of the STRIPS planning models used so far is limited, and models in PGR are often structured in a hierarchical way. We present the approach Plan and Goal Recognition as HTN Planning that combines the expressive but still compact grammar-like HTN representation with the advantage of using unmodified, off-the-shelf planning systems for PGR. Our evaluation shows that – using our approach – current planning systems are able to handle large models with thousands of possible goals, that the approach results in high recognition rates, and that it works even when the environment is partially observable, i.e., if the observer might miss observations.

@Inproceedings{Hoeller2018PlanRecognitionWorkshop,
title = {Plan and Goal Recognition as HTN Planning},
year = {2018},
booktitle = {Proceedings of the AAAI 2018 Workshop on Plan, Activity, and Intent Recognition (PAIR 2018)},
author = {H{\"o}ller, Daniel and Pascal Bercher and Behnke, Gregor and Biundo, Susanne},
abstract = {Companion systems are cooperative, cognitive systems aiming at assisting a user in everyday situations. Therefore, these systems require a high level of availability. One option to meet this requirement is to use a web-deployable architecture. In this demo paper, we present a multimodal cloud-based dialogue framework for the development of a distributed, web-based companion system. The proposed framework is intended to provide an efficient, easily extensible, and scalable approach for this kind of systems and will be demonstrated in a do-it-yourself assistance scenario. Plan- and Goal Recognition (PGR) is the task of inferring the goals and plans of an agent based on its actions. Traditional approaches in PGR are based on a plan library including pairs of plans and corresponding goals. In recent years, the field successfully exploited the performance of planning systems for PGR. The main benefits are the presence of efficient solvers and well-established, compact formalisms for behavior representation. However, the expressivity of the STRIPS planning models used so far is limited, and models in PGR are often structured in a hierarchical way. We present the approach Plan and Goal Recognition as HTN Planning that combines the expressive but still compact grammar-like HTN representation with the advantage of using unmodified, off-the-shelf planning systems for PGR. Our evaluation shows that -- using our approach -- current planning systems are able to handle large models with thousands of possible goals, that the approach results in high recognition rates, and that it works even when the environment is partially observable, i.e., if the observer might miss observations.},
url_Paper = {https://bercher.net/publications/2018/Hoeller2018aPlanRecognition.pdf},
keywords = {workshop}
}

Downloads: 0