ACTIVE SENSING STRATEGIES FOR ROBOTIC PLATFORMS, WITH AN APPLICATION IN VISION-BASED GRIPPING

Benjamin Deutsch, Frank Deinzer, Matthias Zobel, Joachim Denzler

2004

Abstract

We present a vision-based robotic system which uses a combination of several active sensing strategies to grip a free-standing small target object with an initially unknown position and orientation. The object position is determined and maintained with a probabilistic visual tracking system. The cameras on the robot contain a motorized zoom lens, allowing the focal lengths of the cameras to be adjusted during the approach. Our system uses an entropy-based approach to find the optimal zoom levels for reducing the uncertainty in the position estimation in real-time. The object can only be gripped efficiently from a few distinct directions, requiring the robot to first determine the pose of the object in a classification step, and then decide on the correct angle of approach in a grip planning step. The optimal angle is trained and selected using reinforcement learning, requiring no user-supplied knowledge about the object. The system is evaluated by comparing the experimental results to ground-truth information.

References

  1. Bar-Shalom, Y. and Fortmann, T. (1988). Tracking and Data Association. Academic Press, Boston, San Diego, New York.
  2. Bertsekas, D. P. (1995). Dynamic Programming and Optimal Control. Athena Scienti c, Belmont, Massachusetts. Volumes 1 and 2.
  3. Bicchi, A. and Kumar, V. (2000). Robotic grasping and contact: A review. In Proceedings of the 2000 IEEE International Conference on Robotics and Automation, volume 1, pages 348-353, San Francisco.
  4. Borotschnig, H., Paletta, L., Prantl, M., and Pinz, A. (2000). Appearance-based active object recognition. Image and Vision Computing, 18(9):715-727.
  5. Deinzer, F., Denzler, J., and Niemann, H. (2003). Viewpoint Selection - Planning Optimal Sequences of Views for Object Recognition. In Computer Analysis of Images and Patterns - CAIP 2003, LNCS 2756, pages 65-73, Heidelberg. Springer.
  6. Denzler, J. and Brown, C. (2002). Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(2):145-157.
  7. Denzler, J., Zobel, M., and Niemann, H. (2003). Information Theoretic Focal Length Selection for Real-Time Active 3-D Object Tracking. In International Conference on Computer Vision, pages 400-407, Nice, France. IEEE Computer Society Press.
  8. Grzegorzek, M., Deinzer, F., Reinhold, M., Denzler, J., and Niemann, H. (2003). How Fusion of Multiple Views Can Improve Object Recognition in Real-World Environments. In Vision, Modeling, and Visualization 2003, pages 553-560, München. Aka GmbH, Berlin.
  9. Hager, G. and Belhumeur, P. (1998). Ef cient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(10):1025-1039.
  10. Mason, M. (2001). Mechanics of Robotic Manipulation. MIT Press. Intelligent Robotics and Autonomous Agents Series, ISBN 0-262-13396-2.
  11. Paletta, L. and Pinz, A. (2000). Active Object Recognition by View Integration and Reinforcement Learning. Robotics and Autonomous Systems, 31(1-2):71-86.
  12. Puckelsheim, F. (1993). Optimal Design of Experiments. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, New York.
  13. Shannon, C. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27:379- 423,623-656.
  14. Smith, C. and Papanikolopoulos, N. (1996). Vision-guided robotic grasping: Issues and experiments. In Proceedings of the 1996 IEEE International Conference on Robotics and Automation, pages 3203-3208.
  15. Sutton, R. and Barto, A. (1998). Reinforcement Learning. A Bradford Book, Cambridge, London.
  16. Tordoff, B. and Murray, D. (2001). Reactive Zoom Control while Tracking Using an Af ne Camera. In Proceedings of the 12th British Machine Vision Conference, volume 1, pages 53-62.
  17. Zobel, M., Denzler, J., and Niemann, H. (2002). Binocular 3-D Object Tracking with Varying Focal Lengths. In Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition, and Application, Crete, Greece, pages 325-330, Anaheim, Calgary, Zurich. ACTA Press.
Download


Paper Citation


in Harvard Style

Deutsch B., Deinzer F., Zobel M. and Denzler J. (2004). ACTIVE SENSING STRATEGIES FOR ROBOTIC PLATFORMS, WITH AN APPLICATION IN VISION-BASED GRIPPING . In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 972-8865-12-0, pages 169-176. DOI: 10.5220/0001140901690176


in Bibtex Style

@conference{icinco04,
author={Benjamin Deutsch and Frank Deinzer and Matthias Zobel and Joachim Denzler},
title={ACTIVE SENSING STRATEGIES FOR ROBOTIC PLATFORMS, WITH AN APPLICATION IN VISION-BASED GRIPPING},
booktitle={Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2004},
pages={169-176},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001140901690176},
isbn={972-8865-12-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - ACTIVE SENSING STRATEGIES FOR ROBOTIC PLATFORMS, WITH AN APPLICATION IN VISION-BASED GRIPPING
SN - 972-8865-12-0
AU - Deutsch B.
AU - Deinzer F.
AU - Zobel M.
AU - Denzler J.
PY - 2004
SP - 169
EP - 176
DO - 10.5220/0001140901690176