Abstract
Automated planning approaches provide robust and efficient methods to automatically find plans for a given problem and a set of possible actions. However, due to the rather high effort required to create planning models, these approaches cannot be used for adaptable manufacturing plants. In this contribution, we present a method to automatically generate a planning problem in the form of PDDL from an existing capability model. This method eliminates the additional effort required to model a planning problem, making planning approaches usable for adaptable manufacturing plants.
Zusammenfassung
Automatisierte Planungsansätze stellen robuste und effiziente Verfahren dar, mit denen für ein gegebenes Problem und mögliche Aktionen ein Plan zum Lösen des Problems ermittelt werden kann. Aufgrund des hohen Aufwands zur Modell-Erstellung lassen sich diese Verfahren jedoch nicht für wandlungsfähige Anlagen nutzen. In diesem Beitrag wird eine Methode zur automatisierten Erstellung eines Planungsproblems aus einem bestehenden Fähigkeitsmodell vorgestellt. Durch diese Methode entfällt der zusätzliche Aufwand für das Modellieren eines Planungsproblems, wodurch Planungsansätze für wandlungsfähige Anlagen nutzbar werden.
Über die Autoren
Luis Miguel Vieira da Silva arbeitet als Wissenschaftlicher Mitarbeiter an der Professur für Automatisierungstechnik der Helmut-Schmidt Universität. In seiner Forschung beschäftigt er sich mit semantischen Technologien in dem Bereich autonomer Fahrzeuge, sein Fokus liegt dabei auf Fähigkeiten und Skills.
René Heesch arbeitet als Wissenschaftlicher Mitarbeiter an der Professur für Informatik im Maschinenbau der Helmut-Schmidt Universität. In seiner Forschung beschäftigt er sich mit KI-basierten Planungsansätzen und fokussiert sich auf die Planung von Produktionsprozessen in modularen Produktionssystemen.
Aljosha Köcher forscht als Wissenschaftlicher Mitarbeiter und Forschungsgruppenleiter für semantische Technologien an der Professur für Automatisierungstechnik der Helmut-Schmidt-Universität. In seiner Forschung beschäftigt er sich mit semantischen Technologien in der Produktion, sein Fokus liegt dabei auf Fähigkeiten und Skills.
Alexander Fay (* 1970) ist Leiter des Instituts für Automatisierungstechnik an der Helmut-Schmidt-Universität / Universität der Bundeswehr Hamburg. Sein Hauptinteresse gilt Beschreibungsmitteln, Methoden und Werkzeugen für ein effizientes Engineering komplexer Automatisierungssysteme. Prof. Fay ist Vorsitzender des Fachbereichs 2 “Methoden der Automatisierung” und des Fachausschusses “Engineering und Betrieb automatisierter Systeme” in der VDI-/VDE-GMA und Mitglied von acatech – Deutsche Akademie der Technikwissenschaften und des Forschungsbeirats der “Plattform Industrie 4.0”.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: The authors ackknowledge dtec.bw – Zentrum für Digitalisierungs- und Technologieforschung der Bundeswehr [Projekte EKI, RIVA] for financial support.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
[1] H. Kagermann, J. Helbig, A. Hellinger, and W. Wahlster, Recommendations for Implementing the Strategic Initiative INDUSTRIE 4.0: Securing the Future of German Manufacturing Industry; Final Report of the Industrie 4.0 Working Group, Forschungsunion, 2013.10.3390/sci4030026Search in Google Scholar
[2] A. Köcher,C. Hildebrandt,L. M. Vieira da Silva, and A Fay, “A formal capability and skill model for use in plug and produce scenarios,” in 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), vol. 1, 2020, pp. 1663–1670.10.1109/ETFA46521.2020.9211874Search in Google Scholar
[3] K. Evers, J. R. Seyler, V. Aravantinos, L. Lucio, and A. Mehdi, “Roadmap to skill based systems engineering,” in 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2019, pp. 1093–1100.10.1109/ETFA.2019.8869534Search in Google Scholar
[4] S. J. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, Pearson, 2021.Search in Google Scholar
[5] A. Rogalla, A. Fay, and O. Niggemann, “Improved domain modeling for realistic automated planning and scheduling in discrete manufacturing,” in 2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA), vol. 1, 2018, pp. 464–471.10.1109/ETFA.2018.8502631Search in Google Scholar
[6] Constructions Aeronautiques, A. Howe, C. Knoblock, et al.., “PDDL— The planning domain definition language,” Tech. Rep., 1998.Search in Google Scholar
[7] A. Anis, W. Schäfer, and O. Niggemann, “A comparison of modeling approaches for planning in Cyber Physical Production Systems,” in Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA), IEEE, 2014, pp. 1–8.10.1109/ETFA.2014.7005189Search in Google Scholar
[8] K. Henry and B. Selman, “Planning as satisfiability,” in Proceedings of the 10th European Conference on Artificial Intelligence (ECAI 92), 1992.Search in Google Scholar
[9] C. Barrett and C. Tinelli, “Satisfiability Modulo theories,” in Handbook of Model Checking, E. M. Clarke, T. A. Henzinger, H. Veith, and R. Bloem, Eds., Cham, Springer International Publishing, 2018, pp. 305–343.10.1007/978-3-319-10575-8_11Search in Google Scholar
[10] C. Barrett, L. de Moura, S. Ranise, A. Stump, and C. Tinelli, “The SMT-LIB initiative and the rise of SMT,” in Hardware and Software: Verification and Testing, Lecture Notes in Computer Science, S. Barner, I. Harris, D. Kroening, and O. Raz, Eds., Berlin, Heidelberg, Springer, 2011, p. 3.10.1007/978-3-642-19583-9_2Search in Google Scholar
[11] W. Shen, F. Trevizan, and S. Thiébaux, “Learning domain-independent planning heuristics with hypergraph networks,” in Proceedings of the International Conference on Automated Planning and Scheduling, vol. 30, 2020, pp. 574–584.10.1609/icaps.v30i1.6754Search in Google Scholar
[12] Y. Li,D. Tarlow,M. Brockschmidt, and R. Zemel, “Gated graph sequence neural networks,” 2016. Available at: http://arxiv.org/pdf/1511.05493v4 [accessed Nov 17, 2015].Search in Google Scholar
[13] G. Francès, A. B. Corrêa, C. Geissmann, and F. Pommerening, “Generalized potential heuristics for classical planning,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), S. Kraus, Ed., California, International Joint Conferences on Artificial Intelligence, 2019, pp. 5554–5561.10.24963/ijcai.2019/771Search in Google Scholar
[14] J. Segovia-Aguas, S. Jiménez, and A. Jonsson, “Unsupervised classification of planning instances,” in Proceedings of the International Conference on Automated Planning and Scheduling, vol. 27, 2017, pp. 452–460.10.1609/icaps.v27i1.13851Search in Google Scholar
[15] A. Kuhnle, J.-P. Kaiser, F. Theiß, N. Stricker, and G. Lanza, “Designing an adaptive production control system using reinforcement learning,” J. Intell. Manuf., vol. 32, no. 3, pp. 855–876, 2021. https://doi.org/10.1007/s10845-020-01612-y.Search in Google Scholar
[16] A. Köcher,R. Heesch,N. Widulle, et al.., “A research agenda for AI planning in the field of flexible production systems,” in 2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS), IEEE, 2022, pp. 1–8.10.1109/ICPS51978.2022.9816866Search in Google Scholar
[17] E. Järvenpää,N. Siltala,O. Hylli, and M. Lanz, “Capability matchmaking procedure to support rapid configuration and Re-configuration of production systems,” Procedia Manuf., vol. 11, pp. 1053–1060, 2017. https://doi.org/10.1016/j.promfg.2017.07.216.Search in Google Scholar
[18] M. M. Mabkhot, A. M. Al-Samhan, and L. Hidri, “An ontology-enabled case-based reasoning decision support system for manufacturing process selection,” Adv. Mater. Sci. Eng., vol. 2019, pp. 1–18, 2019. https://doi.org/10.1155/2019/2505183.Search in Google Scholar
[19] N. Keddis, G. Kainz, and A. Zoitl, “Capability-based planning and scheduling for adaptable manufacturing systems,” in IEEE [International Conference on] Emerging Technologies and Factory Automation (ETFA), 2014, Piscataway, NJ, IEEE, 2014, pp. 1–8.10.1109/ETFA.2014.7005213Search in Google Scholar
[20] I. Gocev, S. Grimm, and T. A. Runkler, “Explanation of action plans through ontologies,” in On the move to meaningful internet systems, Lecture Notes in Computer Science Programming and Software Engineering, vol. 11230, H. Panetto, C. Debruyne, E. Proper, C. A. Ardagna, D. Roman, and R. Meersman, Eds. Cham, Springer, 2018, pp. 386–403.10.1007/978-3-030-02671-4_24Search in Google Scholar
[21] Z. Kootbally, C. Schlenoff, C. Lawler, T. Kramer, and S. K. Gupta, “Towards robust assembly with knowledge representation for the planning domain definition language (PDDL),” Robot. Comput.-Integr. Manuf., vol. 33, pp. 42–55, 2015. https://doi.org/10.1016/j.rcim.2014.08.006.Search in Google Scholar
[22] J. Pfrommer,D. Stogl,K. Aleksandrov,S. Escaida Navarro, B. Hein, and J. Beyerer, “Plug & produce by modelling skills and service-oriented orchestration of reconfigurable manufacturing systems,” At – Automatisierungstechnik, vol. 63, no. 10, pp. 790–800, 2015.10.1515/auto-2014-1157Search in Google Scholar
[23] A. Köcher, T. Jeleniewski, and A. Fay, “A method to automatically generate semantic Skill models from PLC Code,” in IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, IEEE, 2021, pp. 1–6.10.1109/IECON48115.2021.9589674Search in Google Scholar
[24] A. Köcher, C. Hildebrandt, B. Caesar, et al.., “Automating the development of machine skills and their semantic description,” in 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2020, pp. 1013–1018.10.1109/ETFA46521.2020.9211933Search in Google Scholar
[25] C. Hildebrandt,A. Köcher,C. Küstner,et al.., “Ontology building for cyber-physical systems: application in the manufacturing domain,” in IEEE Transactions on Automation Science and Engineering, 2020, pp. 1–17.10.1109/TASE.2020.2991777Search in Google Scholar
[26] P. Haslum, N. Lipovetzky, D. Magazzeni, and C. Muise, “An introduction to the planning domain definition language,” in Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 13, no. 2, pp. 1–187, 2019.10.1007/978-3-031-01584-7Search in Google Scholar
[27] M. Fox and D. Long, “PDDL2.1: an extension to PDDL for expressing temporal planning domains,” J. Artif. Intell. Res., vol. 20, pp. 61–124, 2003. https://doi.org/10.1613/jair.1129.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
