{"type":"ScholarlyArticle","title":"Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy","authors":[{"name":"Tathagata Chakraborti","slug":"tathagata-chakraborti","given":"Tathagata","family":"Chakraborti","affiliation":"School of Computing, Informatics, and Decision Systems Engineering Arizona State University , Tempe , AZ 85281 USA"},{"name":"Sarath Sreedharan","slug":"sarath-sreedharan","given":"Sarath","family":"Sreedharan","affiliation":"School of Computing, Informatics, and Decision Systems Engineering Arizona State University , Tempe , AZ 85281 USA"},{"name":"Yu Zhang","slug":"yu-zhang","given":"Yu","family":"Zhang","affiliation":"School of Computing, Informatics, and Decision Systems Engineering Arizona State University , Tempe , AZ 85281 USA"},{"name":"Subbarao Kambhampati","slug":"subbarao-kambhampati","given":"Subbarao","family":"Kambhampati","affiliation":"School of Computing, Informatics, and Decision Systems Engineering Arizona State University , Tempe , AZ 85281 USA"}],"abstract":"When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior. Past work on plan explanations primarily involved the AI system explaining the correctness of its plan and the rationale for its decision in terms of its own model. Such soliloquy is wholly inadequate in most realistic scenarios where the humans have domain and task models that differ significantly from that used by the AI system. We posit that the explanations are best studied in light of these differing models. In particular, we show how explanation can be seen as a \"model reconciliation problem\" (MRP), where the AI system in effect suggests changes to the human's model, so as to make its plan be optimal with respect to that changed human model. We will study the properties of such explanations, present algorithms for automatically computing them, and evaluate the performance of the algorithms.","doi":"10.24963/ijcai.2017/23","url":"https://ijcai.org/proceedings/2017/23","pdf":"https://ijcai.org/proceedings/2017/0023.pdf","markdown":"https://ijcai.org/proceedings/2017/23.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/23","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Agent-based and Multi-agent Systems","track":"Main track","number":23,"pages":{"first":156,"last":163},"keywords":["Agent-based and Multi-agent Systems: Agent Theories and Models","Multidisciplinary Topics and Applications: Human-Computer Interaction","Planning and Scheduling: Planning and Scheduling","Robotics and Vision: Human Robot Interaction"],"videos":[],"references":[{"position":1,"raw":"[Ai-Chang et al., 2004] Mitchell Ai-Chang, John Bresina, Len Charest, Adam Chase, JC-J Hsu, Ari Jonsson, Bob Kanefsky, Paul Morris, Kanna Rajan, Jeffrey Yglesias, et al. Mapgen: mixed-initiative planning and scheduling for the mars exploration rover mission. IEEE Intelligent Systems, 19(1):8-12, 2004.","title":"Mapgen: mixed-initiative planning and scheduling for the mars exploration rover mission","authors":"Mitchell Ai-Chang, John Bresina, Len Charest, Adam Chase, Jc-J Hsu, Ari Jonsson, Bob Kanefsky, Paul Morris, Kanna Rajan, Jeffrey Yglesias","year":"2004","venue":"IEEE Intelligent Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Alkhazraji et al., 2016] Yusra Alkhazraji, Matthias Frorath, Markus Grützner, Thomas Liebetraut, Manuela Ortlieb, Jendrik Seipp, Tobias Springenberg, Philip Stahl, Jan Wülfing, Malte Helmert, and Robert Mattmüller. Pyper- plan. https://bitbucket.org/malte/pyperplan, 2016.","title":"Pyperplan","authors":"Yusra Alkhazraji, Matthias Frorath, Markus Grützner, Thomas Liebetraut, Manuela Ortlieb, Jendrik Seipp, Tobias Springenberg, Philip Stahl, Jan Wülfing, Malte Helmert, Robert Mattmüller","year":null,"venue":null,"doi":null,"url":"https://bitbucket.org/malte/pyperplan,2016","internal_url":null},{"position":3,"raw":"[Boella et al., 2009] Guido Boella, Jan Broersen, Leendert van der Torre, and Serena Villata. Representing Excuses in Social Dependence Networks, pages 365-374. Springer Berlin Heidelberg, 2009.","title":"Representing Excuses in Social Dependence Networks","authors":"Guido Boella, Jan Broersen, Serena Leendert Van Der Torre, Villata","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bryce et al., 2016] Dan Bryce, J. Benton, and Michael W. Boldt. Maintaining evolving domain models. In IJCAI, 2016.","title":"Maintaining evolving domain models","authors":"Dan Bryce, J Benton, Michael W Boldt","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/433"},{"position":5,"raw":"[Ferguson et al., 1996] George Ferguson, James F Allen, Bradford W Miller, et al. Trains-95: Towards a mixed- initiative planning assistant. In AIPS, pages 70-77, 1996.","title":"Trains-95: Towards a mixedinitiative planning assistant","authors":"George Ferguson, Bradford W James F Allen, Miller","year":"1996","venue":"AIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fritz and McIlraith, 2007] Christian Fritz and Sheila A McIlraith. Monitoring plan optimality during execution. In ICAPS, pages 144-151, 2007.","title":"Monitoring plan optimality during execution","authors":"Mcilraith Fritz, Christian Fritz, Sheila A Mcilraith","year":"2007","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Göbelbecker et al., 2010] Moritz Göbelbecker, Thomas Keller, Patrick Eyerich, Michael Brenner, and Bernhard Nebel. Coming up with good excuses: What to do when no plan can be found. 2010.","title":"Coming up with good excuses: What to do when no plan can be found","authors":"Moritz Göbelbecker, Thomas Keller, Patrick Eyerich, Michael Brenner, Bernhard Nebel","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Helmert, 2006] Malte Helmert. The fast downward plan- ning system. J. Artif. Intell. Res.(JAIR), 26:191-246, 2006.","title":"The fast downward planning system","authors":"Malte Helmert","year":"2006","venue":"J. Artif. Intell. Res.(JAIR)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Herzig et al., 2014] Andreas Herzig, Viviane Menezes, Leliane Nunes de Barros, and Renata Wassermann. On the revision of planning tasks. In Proceedings of the Twenty-first European Conference on Artificial Intelli- gence, ECAI'14, 2014.","title":"On the revision of planning tasks","authors":"Andreas Herzig, Viviane Menezes, Leliane Nunes De Barros, Renata Wassermann","year":"2014","venue":"Proceedings of the Twenty-first European Conference on Artificial Intelligence, ECAI'14","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Howey et al., 2004] Richard Howey, Derek Long, and Maria Fox. Val: Automatic plan validation, continuous ef- fects and mixed initiative planning using pddl. In Tools with Artificial Intelligence, 2004. ICTAI 2004. 16th IEEE International Conference on, pages 294-301. IEEE, 2004.","title":"Val: Automatic plan validation, continuous effects and mixed initiative planning using pddl","authors":"Richard Howey, Derek Long, Maria Fox","year":"2004","venue":"ICTAI 2004. 16th IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kambhampati, 1990] Subbarao Kambhampati. A classifica- tion of plan modification strategies based on coverage and information requirements. In AAAI 1990 Spring Sympo- sium on Case Based Reasoning, 1990.","title":"A classification of plan modification strategies based on coverage and information requirements","authors":"Subbarao Kambhampati","year":"1990","venue":"AAAI 1990 Spring Symposium on Case Based Reasoning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kulkarni et al., 2016] Anagha Kulkarni, Tathagata Chakraborti, Yantian Zha, Satya Gautam Vadlamudi, Yu Zhang, and Subbarao Kambhampati. Explicable robot planning as minimizing distance from expected behavior. CoRR, abs/1611.05497, 2016.","title":"Explicable robot planning as minimizing distance from expected behavior","authors":"Anagha Kulkarni, Tathagata Chakraborti, Yantian Zha, Gautam Satya, Yu Vadlamudi, Subbarao Zhang, Kambhampati","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Langley, 2016] Pat Langley. Explainable agency in human- robot interaction. In AAAI Fall Symposium Series, 2016.","title":"Explainable agency in humanrobot interaction","authors":"Pat Langley","year":"2016","venue":"AAAI Fall Symposium Series","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lombrozo, 2006] Tania Lombrozo. The structure and func- tion of explanations. Trends in Cognitive Sciences, 10(10):464 -470, 2006.","title":"The structure and function of explanations","authors":"Tania Lombrozo","year":"2006","venue":"Trends in Cognitive Sciences","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lombrozo, 2012] Tania Lombrozo. Explanation and abduc- tive inference. Oxford handbook of thinking and reason- ing, pages 260-276, 2012.","title":"Tania Lombrozo. Explanation and abductive inference","authors":"Lombrozo","year":"2012","venue":"Oxford handbook of thinking and reasoning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[McDermott et al., 1998] Drew McDermott, Malik Ghallab, Adele Howe, Craig Knoblock, Ashwin Ram, Manuela Veloso, Daniel Weld, and David Wilkins. Pddl-the plan- ning domain definition language. 1998.","title":"Pddl-the planning domain definition language","authors":"Drew Mcdermott, Malik Ghallab, Adele Howe, Craig Knoblock, Ashwin Ram, Manuela Veloso, Daniel Weld, David Wilkins","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Perera et al., 2016] Vittorio Perera, Sai P Selveraj, Stephanie Rosenthal, and Manuela Veloso. Dynamic generation and refinement of robot verbalization. In Robot and Human Interactive Communication (RO-MAN), 2016 25th IEEE International Symposium on, pages 212-218. IEEE, 2016.","title":"Dynamic generation and refinement of robot verbalization","authors":"Vittorio Perera, P Sai, Stephanie Selveraj, Manuela Rosenthal, Veloso","year":"2016","venue":"Robot and Human Interactive Communication (RO-MAN)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Riabov et al., 2014] Anton Riabov, Shirin Sohrabi, and Oc- tavian Udrea. New algorithms for the top-k planning prob- lem. In Proceedings of the Scheduling and Planning Appli- cations woRKshop (SPARK) at the 24th International Con- ference on Automated Planning and Scheduling (ICAPS), pages 10-16, 2014.","title":"New algorithms for the top-k planning problem","authors":"Anton Riabov, Shirin Sohrabi, Octavian Udrea","year":"2014","venue":"Proceedings of the Scheduling and Planning Applications woRKshop (SPARK) at the 24th International Conference on Automated Planning and Scheduling (ICAPS)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Russell et al., 2003] Stuart Jonathan Russell, Peter Norvig, John F Canny, Jitendra M Malik, and Douglas D Ed- wards. Artificial intelligence: a modern approach, vol- ume 2. Prentice hall Upper Saddle River, 2003.","title":"Artificial intelligence: a modern approach","authors":"Jonathan Stuart, Peter Russell, John F Norvig, Jitendra M Canny, Douglas D Malik, Edwards","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sohrabi et al., 2011] Shirin Sohrabi, Jorge A. Baier, and Sheila A. McIlraith. Preferred explanations: Theory and generation via planning. In Proceedings of the 25th Con- ference on Artificial Intelligence (AAAI-11), pages 261- 267, San Francisco, USA, August 2011.","title":"Preferred explanations: Theory and generation via planning","authors":"Shirin Sohrabi, Jorge A Baier, Sheila A Mcilraith","year":"2011","venue":"Proceedings of the 25th Conference on Artificial Intelligence (AAAI-11)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tian et al., 2016] Xin Tian, Hankz Hankui Zhuo, and Sub- barao Kambhampati. Discovering underlying plans based on distributed representations of actions. In Proceed- ings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, pages 1135-1143. Interna- tional Foundation for Autonomous Agents and Multiagent Systems, 2016.","title":"Discovering underlying plans based on distributed representations of actions","authors":"Xin Tian, Hankz Hankui Zhuo, Subbarao Kambhampati","year":"2016","venue":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[van Ditmarsch, 2014] Hans van Ditmarsch. The Ditmarsch Tale of Wonders, pages 1-12. Springer International Pub- lishing, Cham, 2014.","title":"The Ditmarsch Tale of Wonders","authors":"; Van Ditmarsch, Hans Van Ditmarsch","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wayllace et al., 2016] Christabel Wayllace, Ping Hou, William Yeoh, and Tran Cao Son. Goal recognition design with stochastic agent action outcomes. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016, New York, NY, USA, 9-15 July 2016, pages 3279-3285, 2016.","title":"Goal recognition design with stochastic agent action outcomes","authors":"Christabel Wayllace, Ping Hou, William Yeoh, Tran Cao, Son","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016","doi":null,"url":null,"internal_url":"/proceedings/2016/464"},{"position":24,"raw":"[Zhang et al., 2017] Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, and Subbarao Kambhampati. Plan explicability and pre- dictability for robot task planning. In Robotics and Au- tomation (ICRA), 2017 IEEE International Conference on. IEEE, 2017.","title":"Plan explicability and predictability for robot task planning","authors":"Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, Subbarao Kambhampati","year":"2017","venue":"Robotics and Automation (ICRA), 2017 IEEE International Conference on","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}