Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot

Mohan Sridharan, Peter Stone

2008

Abstract

A major challenge to the deployment of mobile robots in a wide range of tasks is the ability to function autonomously, learning appropriate models for environmental features and adapting these models in response to environmental changes. Such autonomous operation is feasible iff the robot is able to plan an appropriate action sequence. In this paper, we focus on the task of color modeling/learning, and present two algorithms that enable a mobile robot to plan action sequences that facilitate color learning. We propose a long-term action-selection approach that maximizes color learning opportunities while minimizing localization errors over an entire action sequence, and compare it with a greedy/heuristic action-selection approach that plans incrementally, to maximize the utility based on the current state information. We show that long-term action-selection provides a more principled solution that requires minimal human supervision. All algorithms are fully implemented and tested on the Sony AIBO robots.

References

  1. Pineau, J., Montemerlo, M., Pollack, M., Roy, N., Thrun, S.: Towards Robotic Assistants in Nursing Homes: Challenges and results. RAS Special Issue on Socially Interactive Robots (2003)
  2. Minten, B.W., Murphy, R.R., Hyams, J., Micire, M.: Low-order Complexity Vision-based Docking. IEEE Transactions on Robotics and Automation 17 (2001) 922-930
  3. Thrun, S.: Stanley: The Robot that Won the DARPA Grand Challenge. Journal of Field Robotics 23 (2006) 661-692
  4. Sridharan, M., Stone, P.: Color Learning on a Mobile Robot: Towards Full Autonomy under Changing Illumination. In: The International Joint Conference on Artificial Intelligence. (2007)
  5. Brooks, R.A.: A Robust Layered Control System for a Mobile Robot. Robotics and Automation 2 (1986) 14-23
  6. Boutillier, C., Dean, T., S.Hanks: Decision Theoretic Planning: Structural Assumptions and Computational Leverage. Journal of AI Research 11 (1999) 1-94
  7. Ghallab, M., Nau, D., Traverso, P.: Automated Planning: Theory and Practice. Morgan Kaufmann, San Francisco, CA 94111 (2004)
  8. Comaniciu, D., Meer, P.: Mean shift: A Robust Approach Toward Feature Space Analysis. PAMI (2002)
  9. Shi, J., Malik, J.: Normalized Cuts and Image Segmentation. In IEEE Transactions on PAMI (2000)
  10. Maloney, L.T., Wandell, B.A.: Color Constancy: A Method for Recovering Surface Spectral Reflectance. Journal of Optical Soceity of America A 3 (1986) 29-33
  11. Rosenberg, C., Hebert, M., Thrun, S.: Color Constancy using KL-divergence. In: The IEEE International Conference on Computer Vision (ICCV). (2001)
  12. Cohen, D., Ooi, Y.H., Vernaza, P., Lee, D.D.: UPenn TDP, RoboCup-2003: RoboCup Competitions and Conferences. (2004)
  13. Cameron, D., Barnes, N.: Knowledge-based Autonomous Dynamic Color Calibration. In: The International RoboCup Symposium. (2003)
  14. Jungel, M.: Using Layered Color Precision for a Self-calibrating Vision System. In: The International RoboCup Symposium. (2004)
  15. Schulz, D., Fox, D.: Bayesian Color Estimation for Adaptive Vision-based Robot Localization. In: IROS. (2004)
  16. Anzani, F., Bosisio, D., Matteucci, M., Sorrenti, D.: On-line Color Calibration in Nonstationary Environments. In: RoboCup Symposium. (2005)
  17. Four Legged: The RoboSoccer Four-Legged League (2007) http://www.tzi.de/ 4legged/.
  18. Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press (1995)
  19. NN-Toolbox: Matlab Neural Network Toolbox (2007) http://www.mathworks.com/ access/helpdesk/help/toolbox/nnet/.
  20. Jensfelt, P., Folkesson, J., Kragic, D., Christensen, H.I.: Exploiting distinguishable image features in robotic mapping and localization. In: The European Robotics Symposium (EUROS). (2006)
Download


Paper Citation


in Harvard Style

Sridharan M. and Stone P. (2008). Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot . In VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008) ISBN 978-989-8111-23-4, pages 43-52. DOI: 10.5220/0002337300430052


in Bibtex Style

@conference{visapp-roboperc08,
author={Mohan Sridharan and Peter Stone},
title={Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot},
booktitle={VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)},
year={2008},
pages={43-52},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002337300430052},
isbn={978-989-8111-23-4},
}


in EndNote Style

TY - CONF
JO - VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)
TI - Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot
SN - 978-989-8111-23-4
AU - Sridharan M.
AU - Stone P.
PY - 2008
SP - 43
EP - 52
DO - 10.5220/0002337300430052