skip to main content
research-article

A Contrastive Plan Explanation Framework for Hybrid System Models

Published:24 January 2023Publication History
Skip Abstract Section

Abstract

In artificial intelligence planning, having an explanation of a plan given by a planner is often desirable. The ability to explain various aspects of a synthesized plan to an end user not only brings in trust on the planner but also reveals insights of the planning domain and the planning process. Contrastive questions such as “Why action A instead of action B?” can be answered with a contrastive explanation that compares properties of the original plan containing A against the contrastive plan containing B. In this article, we explore a set of contrastive questions that a user of a planning tool may raise and propose a re-model and re-plan framework to provide explanations to such questions. Earlier work has reported this framework on planning instances for discrete problem domains described in the Planning Domain Definition Language (PDDL) and its variants. In this article, we propose an extension for planning instances described by PDDL+ for hybrid systems that portray a mix of discrete-continuous dynamics. Specifically, given a mixed discrete-continuous system model in PDDL+ and a plan describing the set of desirable actions on the same to achieve a destined goal, we present a framework that can integrate contrastive questions in PDDL+ and synthesize alternate plans. We present a detailed case study on our approach and propose a comparison metric to compare the original plan with the alternate ones.

REFERENCES

  1. [1] GitHub. [n.d.]. KCL-Planning/SMTPlan. Retrieved September 22, 2022 from https://github.com/KCL-Planning/SMTPlan/tree/master/benchmarks.Google ScholarGoogle Scholar
  2. [2] Ghallab Malik, Howe Adele, Knoblock Craig, McDermott Drew, Ram Ashwin, Veloso Manuela, Weld Daniel, et al. 1998. PDDL—The Planning Domain Definition Language. Technical Report. Yale Center for Computational Vision and Control.Google ScholarGoogle Scholar
  3. [3] Alur R., Courcoubetis C., Halbwachs N., Henzinger T. A., Ho P.-H., Nicollin X., Olivero A., Sifakis J., and Yovine S.. 1995. The algorithmic analysis of hybrid systems. Theoretical Computer Science 138, 1 (1995), 334. Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. [4] Alur Rajeev, Courcoubetis Costas, Henzinger Thomas A., and Ho Pei Hsin. 1993. Hybrid automata: An algorithmic approach to the specification and verification of hybrid systems. In Hybrid Systems, Grossman Robert L., Nerode Anil, Ravn Anders P., and Rischel Hans (Eds.). Springer, Berlin, Germany, 209229. Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Bonet Blai and Geffner Hector. 1999. Planning as heuristic search: New results. In Recent Advances in AI Planning. Lecture Notes in Computer Science, Vol. 1089. Springer, 360–372. Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Cashmore Michael, Collins Anna, Krarup Benjamin, Krivic Senka, Magazzeni Daniele, and Smith David. 2019. Towards explainable AI planning as a service. In Proceedings of the 2nd ICAPS Workshop on Explainable Planning. https://strathprints.strath.ac.uk/69987/.Google ScholarGoogle Scholar
  7. [7] Cashmore Michael, Magazzeni Daniele, and Zehtabi Parisa. 2020. Planning for hybrid systems via satisfiability modulo theories. Journal of Artificial Intelligence Research 67 (2020), 235283. Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] Chakraborti Tathagata, Kulkarni Anagha, Sreedharan Sarath, Smith David E., and Kambhampati Subbarao. 2018. Explicability? Legibility? Predictability? Transparency? Privacy? Security? The emerging landscape of interpretable agent behavior. arXiv E-prints, arXiv:1811.09722 (2018).Google ScholarGoogle Scholar
  9. [9] Chakraborti Tathagata, Sreedharan Sarath, Zhang Yu, and Kambhampati Subbarao. 2017. Plan explanations as model reconciliation: Moving beyond explanation as soliloquy. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI’17). 156163.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Dhurandhar Amit, Chen Pin-Yu, Luss Ronny, Tu Chun-Chen, Ting Paishun, Shanmugam Karthikeyan, and Das Payel. 2018. Explanations based on the missing: Towards contrastive explanations with pertinent negatives. In Advances in Neural Information Processing Systems 31, Bengio S., Wallach H., Larochelle H., Grauman K., Cesa-Bianchi N., and Garnett R. (Eds.). Curran Associates, 592603. http://papers.nips.cc/paper/7340-explanations-based-on-the-missing-towards-contrastive-explanations-with-pertinent-negatives.pdf.Google ScholarGoogle Scholar
  11. [11] Dhurandhar Amit, Pedapati Tejaswini, Balakrishnan Avinash, Chen Pin-Yu, Shanmugam Karthikeyan, and Puri Ruchir. 2019. Model agnostic contrastive explanations for structured data. arXiv E-prints, arXiv:1906.00117 (2019).Google ScholarGoogle Scholar
  12. [12] Eifler Rebecca, Cashmore Michael, Hoffmann Jörg, Magazzeni Daniele, and Steinmetz Marcel. 2020. A new approach to plan-space explanation: Analyzing plan-property dependencies in oversubscription planning. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI’20), the 32nd Innovative Applications of Artificial Intelligence Conference (IAAI’20), and the 10th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI’20).98189826. https://ojs.aaai.org/index.php/AAAI/article/view/6534.Google ScholarGoogle Scholar
  13. [13] Eriksson Salomé and Helmert Malte. 2020. Certified unsolvability for SAT planning with property directed reachability. In Proceedings of the 30th International Conference on Automated Planning and Scheduling. 90–100. https://ojs.aaai.org/index.php/ICAPS/article/view/6649.Google ScholarGoogle Scholar
  14. [14] Eriksson Salomé, Röger Gabriele, and Helmert Malte. 2017. Unsolvability certificates for classical planning. In Proceedings of the 27th International Conference on Automated Planning and Scheduling (ICAPS’17). 88–97. https://aaai.org/ocs/index.php/ICAPS/ICAPS17/paper/view/15734.Google ScholarGoogle Scholar
  15. [15] Fikes Richard E. and Nilsson Nils J.. 1971. Strips: A new approach to the application of theorem proving to problem solving. Artificial Intelligence 2, 3 (1971), 189208. Google ScholarGoogle ScholarCross RefCross Ref
  16. [16] Fox M. and Long D.. 2006. Modelling mixed discrete-continuous domains for planning. Journal of Artificial Intelligence Research 27 (2006), 235297. Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. [17] Fox Maria, Long Derek, and Magazzeni Daniele. 2017. Explainable planning. arXiv E-prints, arXiv:1709.10256 (Sept.2017).Google ScholarGoogle Scholar
  18. [18] Gao Sicun, Avigad Jeremy, and Clarke Edmund M.. 2012. \(\delta\)-complete decision procedures for satisfiability over the reals. In Automated Reasoning, Gramlich Bernhard, Miller Dale, and Sattler Uli (Eds.). Springer, Berlin, Germany, 286300. Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. [19] Gao Sicun, Avigad Jeremy, and Clarke Edmund M.. 2012. Delta-decidability over the reals. In Proceedings of the 27th Annual IEEE Symposium on Logic in Computer Science (LICS’12). IEEE, Los Alamitos, CA, 305314. Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Gao Sicun, Kong Soonho, Chen Wei, and Clarke Edmund M.. 2014. Delta-complete analysis for bounded reachability of hybrid systems. CoRR abs/1404.7171 (2014).Google ScholarGoogle Scholar
  21. [21] Gerevini Alfonso and Serina Ivan. 2002. LPG: A planner based on local search for planning graphs with action costs. In Proceedings of the 6th International Conference on Artificial Intelligence Planning Systems. 13–22. http://www.aaai.org/Library/AIPS/2002/aips02-002.php.Google ScholarGoogle Scholar
  22. [22] Göbelbecker Moritz, Keller Thomas, Eyerich Patrick, Brenner Michael, and Nebel Bernhard. 2010. Coming up with good excuses: What to do when no plan can be found. In Proceedings of the 20th International Conference on Automated Planning and Scheduling (ICAPS’20). 81–88. http://www.aaai.org/ocs/index.php/ICAPS/ICAPS10/paper/view/1453.Google ScholarGoogle Scholar
  23. [23] Helmert Malte. 2006. The fast downward planning system. Journal of Artificial Intelligence Research 26 (2006), 191246. Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Hoffmann Jörg. 2001. FF: The fast-forward planning system. AI Magazine 22, 3 (2001), 5762. Google ScholarGoogle ScholarDigital LibraryDigital Library
  25. [25] Hoffmann Jörg and Magazzeni Daniele. 2019. Explainable AI planning (XAIP): Overview and the case of contrastive explanation. In Reasoning Web: Explainable Artificial Intelligence. Lecture Notes in Computer Science, Vol. 11810. Springer, 277282.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Hoffmann Jörg and Nebel Bernhard. 2001. The FF planning system: Fast plan generation through heuristic search. Journal of Artificial Intelligence Research 14 (2001), 253302. Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Kautz Henry, Selman Bart, and Hoffmann Joerg. 2006. SatPlan: Planning as Satisfiability. Department of Computer Science and Engineering, University of Washington, Seattle, WA.Google ScholarGoogle Scholar
  28. [28] Krarup Benjamin, Cashmore Michael, Magazzeni Daniele, and Miller Tim. 2019. Model-based contrastive explanations for explainable planning. In Proceedings of the ICAPS 2019 Workshop on Explainable AI Planning (XAIP’19). https://strathprints.strath.ac.uk/69957/.Google ScholarGoogle Scholar
  29. [29] Krarup Benjamin, Krivic Senka, Magazzeni Daniele, Long Derek, Cashmore Michael, and Smith David E.. 2021. Contrastive explanations of plans through model restrictions. CoRR abs/2103.15575 (2021).Google ScholarGoogle Scholar
  30. [30] Lim Brian Y., Dey Anind K., and Avrahami Daniel. 2009. Why and why not explanations improve the intelligibility of context-aware intelligent systems. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI’09). ACM, New York, NY, 21192128. Google ScholarGoogle ScholarDigital LibraryDigital Library
  31. [31] Miller Tim. 2018. Contrastive explanation: A structural-model approach. arXiv E-prints, arXiv:1811.03163 (2018).Google ScholarGoogle Scholar
  32. [32] Pednault Edwin P. D.. 1989. ADL: Exploring the middle ground between STRIPS and the situation calculus. In Proceedings of the 1st International Conference on Principles of Knowledge Representation and Reasoning. 324332. Google ScholarGoogle Scholar
  33. [33] Penna Giuseppe Della, Magazzeni Daniele, and Mercorio Fabio. 2012. A universal planning system for hybrid domains. Applied Intelligence 36, 4 (2012), 932959. Google ScholarGoogle ScholarDigital LibraryDigital Library
  34. [34] Penna Giuseppe Della, Magazzeni Daniele, Mercorio Fabio, and Intrigila Benedetto. 2009. UPMurphi: A tool for universal planning on PDDL+ problems. In Proceedings of the 19th International Conference on Automated Planning and Scheduling (ICAPS’09). 106–113. http://aaai.org/ocs/index.php/ICAPS/ICAPS09/paper/view/707.Google ScholarGoogle Scholar
  35. [35] Percassi Francesco, Scala Enrico, and Vallati Mauro. 2021. Translations from discretised PDDL+ to numeric planning. In Proceedings of the 31st International Conference on Automated Planning and Scheduling (ICAPS’21). 252–261. https://ojs.aaai.org/index.php/ICAPS/article/view/15969.Google ScholarGoogle Scholar
  36. [36] Piotrowski Wiktor Mateusz, Fox Maria, Long Derek, Magazzeni Daniele, and Mercorio Fabio. 2016. Heuristic planning for hybrid systems. In Proceedings of the 30th AAAI Conference on Artificial Intelligence. 4254–4255. http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12394.Google ScholarGoogle Scholar
  37. [37] Sarwar Mir Md Sajid, Ray Rajarshi, and Banerjee Ansuman. 2020. A contrastive plan explanation framework for hybrid system models. In Proceedings of the 2020 18th ACM/IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE’20). 111. Google ScholarGoogle ScholarCross RefCross Ref
  38. [38] Scala Enrico, Haslum Patrik, Thiébaux Sylvie, and Ramírez Miquel. 2016. Interval-based relaxation for general numeric planning. In Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI’16). 655–663. Google ScholarGoogle ScholarDigital LibraryDigital Library
  39. [39] Shin Ji-Ae and Davis Ernest. 2005. Processes and continuous change in a SAT-based planner. Artificial Intelligence 166, 1-2 (2005), 194253. Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Smith David E.. 2012. Planning as an iterative process. In Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI’12). 21802185.Google ScholarGoogle Scholar
  41. [41] Smith David E. and Weld Daniel S.. 1998. Conformant graphplan. In Proceedings of the 15th National/10th Conference on Artificial Intelligence/Innovative Applications of Artificial Intelligence (AAAI’98/IAAI’98). 889896. Google ScholarGoogle Scholar
  42. [42] Sreedharan Sarath, Srivastava Siddharth, Smith David E., and Kambhampati Subbarao. 2019. Why can’t you do that HAL? Explaining unsolvability of planning tasks. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI’19). 1422–1430. Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. A Contrastive Plan Explanation Framework for Hybrid System Models

        Recommendations

        Comments

        Login options

        Check if you have access through your login credentials or your institution to get full access on this article.

        Sign in

        Full Access

        • Published in

          cover image ACM Transactions on Embedded Computing Systems
          ACM Transactions on Embedded Computing Systems  Volume 22, Issue 2
          March 2023
          560 pages
          ISSN:1539-9087
          EISSN:1558-3465
          DOI:10.1145/3572826
          • Editor:
          • Tulika Mitra
          Issue’s Table of Contents

          Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

          Publisher

          Association for Computing Machinery

          New York, NY, United States

          Publication History

          • Published: 24 January 2023
          • Online AM: 15 September 2022
          • Accepted: 23 August 2022
          • Revised: 6 August 2022
          • Received: 1 December 2021
          Published in tecs Volume 22, Issue 2

          Permissions

          Request permissions about this article.

          Request Permissions

          Check for updates

          Qualifiers

          • research-article
          • Refereed
        • Article Metrics

          • Downloads (Last 12 months)113
          • Downloads (Last 6 weeks)6

          Other Metrics

        PDF Format

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Full Text

        View this article in Full Text.

        View Full Text

        HTML Format

        View this article in HTML Format .

        View HTML Format
        About Cookies On This Site

        We use cookies to ensure that we give you the best experience on our website.

        Learn more

        Got it!