In human-aware planning systems, when the planning agent recommends a plan (e.g., a route from A to B) to a human user, it is often the case that the user might not understand why the recommended plan is good, for example, compared to an alternative plan in the user’s mind. In such a scenario, there is a need for the agent to explain its plan to the user, providing them with the necessary information to understand properties of the plan (e.g., optimality, feasibility, etc.).
We are approaching this problem from a knowledge representation and reasoning (KR) perspective, where we represent the mental models of both the planning agent and the human user using logical facts and rules. Within this framework, we adapt and generalize KR notions (e.g., entailment, hitting sets, model counting) to solve this problem.
- Michael Cashmore, University of Strathclyde
- Ashwin Kumar, Washington University in St. Louis
- Daniele Magazzeni, J.P. Morgan AI Research and King’s College London
- Alvitta Ottley, Washington University in St. Louis
- Alessandro Previti, Ericsson Research
- Tran Cao Son, New Mexico State University
- Stylianos Vasilieou, Washington University in St. Louis
RI: Small: Collaborative Research: Preference Elicitation and Device Scheduling for Smart Homes.
National Science Foundation (2018 – 2021).
- Ashwin Kumar, Stylianos Loukas Vasileiou, Melanie Bancilhon, Alvitta Ottley, and William Yeoh. “VizXP: A Visualization Framework for Conveying Explanations to Users in Model Reconciliation Problems.” In Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), to appear, 2022.
- Stylianos Loukas Vasileiou, Alessandro Previti, and William Yeoh. “On Exploiting Hitting Sets for Model Reconciliation.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 6514-6521, 2021.
- Tran Cao Son, Van Nguyen, Stylianos Loukas Vasileiou, and William Yeoh. “Model Reconciliation in Logic Programs.” In Proceedings of the European Conference on Logics in Artificial Intelligence (JELIA), pages 393-406, 2021.
- Stylianos Loukas Vasileiou, William Yeoh, Tran Cao Son, and Alessandro Previti. “Explanations as Model Reconciliation via Probabilistic Logical Reasoning.” In Proceedings of the Explainable Logic-Based Knowledge Representation (XLoKR), 2021.
- Van Nguyen, Tran Cao Son, Stylianos Loukas Vasileiou, and William Yeoh. “Explainable Planning Using Answer Set Programming.” In Proceedings of the International Conference on Principles of Knowledge Reasoning and Representation (KR), pages 662-666, 2020.
- Stylianos Loukas Vasileiou, William Yeoh, and Tran Cao Son. “On the Relationship Between KR Approaches for Explainable Planning.” In Proceedings of the Workshop on Explainable Planning (XAIP), 2020.