The RACE Project

Robustness by Autonomous Competence Enhancement

Abstract

This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Notes

  1. 1.

    http://gazebosimorg/.

  2. 2.

    http://youtu.be/XvnF2JMfhvc.

References

  1. 1.

    Baader F, Sertkaya B, Turhan A-Y (2007) Computing the least common subsumer wrt a background terminology. J Appl Logic 5(3):392–420

    MathSciNet  Article  MATH  Google Scholar 

  2. 2.

    Bohlken W, Koopmann P, Hotz L, Neumann B (2013) Towards ontology-based realtime behaviour interpretation. In: Guesgen HW, Marsland S (eds) Human behavior recognition technologies: intelligent applications for monitoring and security, IGI Global, pp 33–64

  3. 3.

    Dubba KSR, Cohn AG, Hogg DC, Bhatt M, Dylla F (2014) Learning relational event models from video, submitted for publication

  4. 4.

    Dubba KSR, de Oliveira MR, Lim GH, Kasaei H, Seabra Lopes L, Tomé AM, Cohn AG (2014) Grounding language in perception for scene conceptualization in autonomous robots. In: Proceedings of AAAI 2014 spring symposium on qualitative representations for robots

  5. 5.

    Erol K, Hendler J, Nau DS (1994) HTN planning: complexity and expressivity. In: Proceedings of AAAI

  6. 6.

    Gentner D (1983) Structure-mapping: a theoretical framework for analogy. Cognit Sci 7(2):155–170

    Article  Google Scholar 

  7. 7.

    Kasaei SH, Oliveira M, Lim GH, Seabra Lopes L, Tomé AM (2014) An interactive open-ended learning approach for 3d object recognition. In: Proceedings of ICARSC

  8. 8.

    Konecnỳ Š, Stock S, Pecora F, Saffiotti A (2014) Planning domain+ execution semantics: a way towards robust execution? In: Proceedings of AAAI 2014 spring symposium on qualitative representations for robots

  9. 9.

    Lehmann J, Neumann B, Bohlken W, Hotz L (2014) A robot waiter that predicts events by high-level scene interpretation. In: Proceedings of 6th international conference agents and artificial intelligence

  10. 10.

    Lim GH, Oliveira M, Mokhtari V, Kasaei SH, Seabra Lopes L, Tomé MA (2014) Interactive teaching and experience extraction for learning about objects and robot activities. In: Proceedings of RO-MAN (accepted)

  11. 11.

    Mansouri M, Pecora F (2014) More knowledge on the table: planning with space, time and resources for robots. In: Proceedings of ICRA

  12. 12.

    Mokhtari V, Lim GH, Seabra Lopes L, Pinho AJ (2014) Gathering and conceptualizing plan-based robot activity experiences. In: Proceedings of IAS

  13. 13.

    Nau D, Muñoz-Avila H, Cao Y, Lotem A, Mitchell S (2001) Total-order planning with partially ordered subtasks. In: Proceedings of IJCAI

  14. 14.

    Neumann B, Hotz L, Rost P, Lehmann J (2014) A robot waiter learning from experiences. In: Proceedings of MLDM

  15. 15.

    Newman MEJ (2003) Ego-centered networks and the ripple effect. Soc Netw 25(1):83–95

    Article  Google Scholar 

  16. 16.

    Oliveira M, Lim GH, Seabra Lopes L, Kasaei SH, Tomé AM, Chauhan A (2014) A perceptual memory system for grounding semantic representations in intelligent service robots. In: Proceedings of IROS, (accepted)

  17. 17.

    Quigley M, Conley K, Gerkey BP, Faust J, Foote T, Leibs J, Wheeler R, Ng AY (2009) ROS: an open-source robot operating system. In: Proceedings of ICRA workshop on open source software

  18. 18.

    RACE: robustness by autonomous competence enhancement. http://race.informatik.uni-hamburg.de/

  19. 19.

    Rissanen J (1978) Modeling by shortest data description. Automatica 14(5):465–471

    Article  MATH  Google Scholar 

  20. 20.

    Rockel S et al (2013) An ontology-based multi-level robot architecture for learning from experiences. In: Proceedings of designing intelligent robots, reintegrating AI II, AAAI spring symposium,

  21. 21.

    Rockel S, Klimentjew D, Zhang L, Zhang J (2014) An hyperreality imagination based reasoning and evaluation system (HIRES). In: Proceedings of ICRA

  22. 22.

    Tayyub J, Tavanai A, Gatsoulis Y, Cohn AG, Hogg D (2014) Qualitative and quantitative spatio-temporal relations in daily living activity recognition. University of Leeds, technical report

Download references

Acknowledgments

RACE is funded by the EC FP7-ICT-2011-7, Grant no. 287752, which is greatly appreciated. Comments by the anonymous reviewers have helped improve this paper.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Joachim Hertzberg.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hertzberg, J., Zhang, J., Zhang, L. et al. The RACE Project. Künstl Intell 28, 297–304 (2014). https://doi.org/10.1007/s13218-014-0327-y

Download citation

Keywords

  • Object Category
  • Control Architecture
  • Plan Execution
  • Early Integration
  • Perceptual Memory