Advertisement

Paladyn

, 2:1 | Cite as

Learning grasp affordance densities

  • R. DetryEmail author
  • D. Kraft
  • O. Kroemer
  • L. Bodenhagen
  • J. Peters
  • N. Krüger
  • J. Piater
Research Article

Abstract

We address the issue of learning and representing object grasp affordance models. We model grasp affordances with continuous probability density functions (grasp densities) which link object-relative grasp poses to their success probability. The underlying function representation is nonparametric and relies on kernel density estimation to provide a continuous model. Grasp densities are learned and refined from exploration, by letting a robot “play” with an object in a sequence of grasp-and-drop actions: the robot uses visual cues to generate a set of grasp hypotheses, which it then executes and records their outcomes. When a satisfactory amount of grasp data is available, an importance-sampling algorithm turns it into a grasp density. We evaluate our method in a largely autonomous learning experiment, run on three objects with distinct shapes. The experiment shows how learning increases success rates. It also measures the success rate of grasps chosen to maximize the probability of success, given reaching constraints.

Keywords

robot learning grasping probabilistic models cognitive robotics 

References

  1. [1]
    A. Bicchi and V. Kumar. Robotic grasping and contact: a review. In IEEE International Conference on Robotics and Automation, 2000.Google Scholar
  2. [2]
    G. E. P. Box and M. E. Muller. A note on the generation of random normal deviates. The Annals of Mathematical Statistics, 29(2):610–611, 1958.zbMATHCrossRefGoogle Scholar
  3. [3]
    M. T. Ciocarlie and P. K. Allen. Hand posture subspaces for dexterous robotic grasping. Int. J. Rob. Res., 28(7):851–867, 2009.CrossRefGoogle Scholar
  4. [4]
    C. de Granville, J. Southerland, and A. H. Fagg. Learning grasp affordances through human demonstration. In IEEE International Conference on Development and Learning, 2006.Google Scholar
  5. [5]
    R. Detry, E. Başeski, N. Krüger, M. Popović, Y. Touati, O. Kroemer, J. Peters, and J. Piater. Learning object-specific grasp affordance densities. In IEEE International Conference on Development and Learning, pages 1–7, 2009.Google Scholar
  6. [6]
    R. Detry, E. Başeski, M. Popović, Y. Touati, N. Krüger, O. Kroemer, J. Peters, and J. Piater. Learning continuous grasp affordances by sensorimotor exploration. In O. Sigaud and J. Peters, editors, From Motor Learning to Interaction Learning in Robots, pages 451–465. Springer-Verlag, 2010.Google Scholar
  7. [7]
    R. Detry, D. Kraft, A. G. Buch, N. Krüger, and J. Piater. Refining grasp affordance models by experience. In IEEE International Conference on Robotics and Automation, pages 2287–2293, 2010.Google Scholar
  8. [8]
    R. Detry, N. Pugeault, and J. Piater. A probabilistic framework for 3D visual object representation. IEEE Trans. Pattern Anal. Mach. Intell., 31(10):1790–1803, 2009.CrossRefGoogle Scholar
  9. [9]
    A. Doucet, N. de Freitas, and N. Gordon. Sequential Monte Carlo Methods in Practice. Springer, 2001.Google Scholar
  10. [10]
    S. Ekvall and D. Kragic. Interactive grasp learning based on human demonstration. In IEEE International Conference on Robotics and Automation, 2004.Google Scholar
  11. [11]
    R. A. Fisher. Dispersion on a sphere. In Proc. Roy. Soc. London Ser. A, 1953.Google Scholar
  12. [12]
    J. J. Gibson. The Ecological Approach to Visual Perception. Lawrence Erlbaum Associates, 1979.Google Scholar
  13. [13]
    K. Huebner, K. Welke, M. Przybylski, N. Vahrenkamp, T. Asfour, D. Kragic, and R. Dillmann. Grasping known objects with humanoid robots: A box-based approach. In International Conference on Advanced Robotics, 2009.Google Scholar
  14. [14]
    J. A. J rgensen, L.-P. Ellekilde, and H. G. Petersen. Robworksim —an open simulator for sensor based grasping. In Proceedings for the joint conference of ISR 2010 (41st International Symposium on Robotics) and ROBOTIK 2010 (6th German Conference on Robotics), 2010.Google Scholar
  15. [15]
    D. Kraft, R. Detry, N. Pugeault, E. Ba3eski, F Guerin, J. Piater, and N. Krüger. Development of object and grasping knowledge by robot exploration. IEEE Transactions on Autonomous Mental Development, 2(4):368–383, 2010.CrossRefGoogle Scholar
  16. [16]
    D. Kraft, N. Pugeault, E. Ba3eski, M. Popovi¢, D. Kragic, S. Kalkan, F. Wörgötter, and N. Krüger. Birth of the object: Detection of objectness and extraction of object shape through object action complexes. International Journal of Humanoid Robotics, 5:247–265, 2009.CrossRefGoogle Scholar
  17. [17]
    D. Kragic, A. T. Miller, and P. K. Allen. Real-time tracking meets online grasp planning. In IEEE International Conference on Robotics and Automation, pages 2460–2465, 2001.Google Scholar
  18. [18]
    O. Kroemer, R. Detry, J. Piater, and J. Peters. Combining active learning and reactive control for robot grasping. Robotics and Autonomous Systems, 58(9):1105–1116, 2010.CrossRefGoogle Scholar
  19. [19]
    J. J. Kuffner and S. M. Lavalle. RRT-Connect: An efficient approach to single-query path planning. In IEEE International Conference on Robotics and Automation, 2000.Google Scholar
  20. [20]
    J. Lee and M. Verleysen. Nonlinear dimensionality reduction. Springer Verlag, 2007.Google Scholar
  21. [21]
    A. T. Miller, S. Knoop, H. Christensen, and P. K. Allen. Automatic grasp planning using shape primitives. In IEEE International Conference on Robotics and Automation, volume 2, pages 1824–1829, 2003.Google Scholar
  22. [22]
    L. Montesano and M. Lopes. Learning grasping affordances from local visual descriptors. In IEEE International Conference on Development and Learning, 2009.Google Scholar
  23. [23]
    J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, 1988.Google Scholar
  24. [24]
    M. Popović, D. Kraft, L. Bodenhagen, E. Başeski, N. Pugeault, D. Kragic, T. Asfour, and N. Krüger. A strategy for grasping unknown objects based on co-planarity and colour information. Robotics and Autonomous Systems, 2010.Google Scholar
  25. [25]
    N. Pugeault, F. Wörgötter, and N. Krüger. Visual primitives: Local, condensed, and semantically rich visual descriptors and their applications in robotics. International Journal of Humanoid Robotics, 2010. (to appear).Google Scholar
  26. [26]
    N. Pugeault, F. Wörgötter, and N. Krüger. Visual primitives: Local, condensed, and semantically rich visual descriptors and their applications in robotics. International Journal of Humanoid Robotics, 2010.Google Scholar
  27. [27]
    E. Sahin, M. Cakmak, M. R. Dogar, E. Ugur, and G. Ucoluk. To afford or not to afford: A new formalization of affordances towards affordance-based robot control. Adaptive Behavior, 2007.Google Scholar
  28. [28]
    M. Salganicoff, L. H. Ungar, and R. Bajcsy. Active learning for vision-based robot grasping. Mach. Learn., 23:251–278, May 1996.Google Scholar
  29. [29]
    A. Saxena, J. Driemeyer, and A. Y Ng. Robotic Grasping of Novel Objects using Vision. International Journal of Robotics Research, 27(2):157, 2008.CrossRefGoogle Scholar
  30. [30]
    K. Shimoga. Robot grasp synthesis algorithms: A survey. The International Journal of Robotics Research, 15(3):230, 1996.CrossRefGoogle Scholar
  31. [31]
    B. W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman & Hall/CRC, 1986.Google Scholar
  32. [32]
    E. B. Sudderth. Graphical models for visual object recognition and tracking. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, USA, 2006.Google Scholar
  33. [33]
    J. D. Sweeney and R. Grupen. A model of shared grasp affordances from demonstration. In International Conference on-Simulation and Computa-Humanoid Robots, 2007.Google Scholar
  34. [34]
    A. T. A. Wood. Simulation of the von Mises-Fisher distribution. Communications in Statistics tion, 23(1):157–164, 1994.zbMATHCrossRefGoogle Scholar

Copyright information

© © Versita Warsaw and Springer-Verlag Wien 2011

Authors and Affiliations

  • R. Detry
    • 1
    Email author
  • D. Kraft
    • 2
  • O. Kroemer
    • 3
  • L. Bodenhagen
    • 2
  • J. Peters
    • 3
    • 4
  • N. Krüger
    • 2
  • J. Piater
    • 5
  1. 1.Centre for Autonomous SystemsKungliga Tekniska högskolan (KTH)StockholmSweden
  2. 2.Maersk Mc-Kinney Moller InstituteUniversity of Southern DenmarkCopenhagenDenmark
  3. 3.MPI for Biological CyberneticsTübingenGermany
  4. 4.Darmstadt University of TechnologyDarmstadtGermany
  5. 5.University of InnsbruckInnsbruckAustria

Personalised recommendations