Advertisement

Using AI-Planning to Solve a Kinodynamic Path Planning Problem and Its Application for HAPS

  • Jane Jean Kiam
  • Axel Schulte
  • Enrico Scala
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 903)

Abstract

This work emphasizes on the ability of a domain-independent AI-planner to solve a kinodynamic path planning problem by recapitulating the encoding in the PDDL+ modelling language and by showing the easy extension for multiple HAPS. The advantage of the approach is highlighted with the concept of an implementation framework that incorporates tools to validate the problem model and to explain the plans to the operator. Some flight path plans are illustrated as well as the validation of plans are described.

Keywords

Kinodynamic Path planning AI planning HAPS Wind field Explainable AI 

References

  1. 1.
    Fox, M., Long, D., Magazzeni, D.: Explainable Planning. International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Explainable AI, Melbourne (2017)Google Scholar
  2. 2.
    Bogomolov, S., Magazzeni, D., Minopoli, S., Wehrle, M.: PDDL+ planning with hybrid automata: Foundations of translating must behavior. In: Proceedings of International Conference on Automated Planning and Scheduling (ICAPS) (2015)Google Scholar
  3. 3.
    Fox, M., Howey, R., Long, D.: Validating plans in the context of processes and exogenous events. In: Proceedings of AAAI Conference on AI. Pittsburgh, Pennsylvania (2005)Google Scholar
  4. 4.
    Long, D., Fox, M.: Modelling mixed discrete-continuous domains for planning. J. Artif. Intell. Res. 27, 235–297 (2006)CrossRefGoogle Scholar
  5. 5.
    LaValle, S.M., Kuffner, J.J.: Randomized kinodynamic planning. Int. J. Rob. Res. 20(5), 378–400 (2001)CrossRefGoogle Scholar
  6. 6.
    Kiam, J.J., Gerdts, M., Schulte, A.: Fast subset path planning/replanning to avoid obstacles with time-varying probabilistic motion patterns. In: 8th European Starter AI Researcher Symposium, The Hague, The Netherlands (2016)Google Scholar
  7. 7.
    Kiam, J.J., Scala, E., Ramirez, M., Schulte, A.: Using a hybrid AI-Planner to plan feasible flight paths for HAPS-Like UAVs. In: ICAPS Proceedings of the 6th Workshop on Planning and Robotics (PlanRob), Delft, The Netherlands (2018)Google Scholar
  8. 8.
    Kiam, J.J., Schulte, A.: multilateral mission planning in a time-varying vector field with dynamic constraints. In: IEEE Systems, Man, and Cybernetics, Miyazaki, Japan (2018)Google Scholar
  9. 9.
    Steinmetz, M., Hoffmann, J.: Towards clause-learning state space search: learning to recognize dead-ends. In Proceedings of AAAI Conference on AI (2016)Google Scholar
  10. 10.
    Seegebarth, B., Müller, F., Schattenberg, B., Biundo, S.: Making hybrid plans more clear to human users - A formal approach for generating sound explanations. In: Proceedings of International Conference on Automated Planning and Scheduling (ICAPS) (2012)Google Scholar
  11. 11.
    Müller, R., Kiam, J.J., Mothes, F.: Multiphysical simulation of a semi-autonomous solar powered high altitude pseudo-satellite. In: IEEE Aerospace Conference, Montana (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute of Flight Systems, University of the BundeswehrMunichGermany
  2. 2.Fondazione Bruno KesslerTrentoItaly

Personalised recommendations