Robots Avoid Potential Failures through Experience-based Probabilistic Planning

Melis Kapotoglu, Cagatay Koc, Sanem Sariel

2015

Abstract

Robots should avoid potential failure situations to safely execute their actions and to improve their performances. For this purpose, they need to build and use their experience online. We propose online learning-guided planning methods to address this problem. Our method includes an experiential learning process using Inductive Logic Programming (ILP) and a probabilistic planning framework that uses the experience gained by learning for improving task execution performance. We analyze our solution on a case study with an autonomous mobile robot in a multi-object manipulation domain where the objective is maximizing the number of collected objects while avoiding potential failures using experience. Our results indicate that the robot using our adaptive planning strategy ensures safety in task execution and reduces the number of potential failures.

References

  1. Du, Y., Hsu, D., Kurniawati, H., Lee, W., Ong, S., and Png, S. (2010). A pomdp approach to robot motion planning under uncertainty. In Int. Conf. on Automated Planning and Scheduling, Workshop on Solving RealWorld POMDP Problems.
  2. Ersen, M., Talay, S. S., and Yalcin, H. (2013). Extracting spatial relations among objects for failure detection. In KIK@ KI, pages 13-20.
  3. Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., and Lepetit, V. (2012). Gradient response maps for real-time detection of textureless objects. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(5):876-888.
  4. Kapotoglu, M., Koc, C., Sariel, S., and Ince, G. (2014). Action monitoring in cognitive robots. In Signal Processing and Communications Applications Conference (SIU), 2014 22nd, pages 2154-2157. IEEE.
  5. Karapinar, S., Altan, D., and Sariel-Talay, S. (2012). A robust planning framework for cognitive robots. In Proceedings of the AAAI-12 Workshop on Cognitive Robotics (CogRob).
  6. Karapinar, S. and Sariel, S. (2015). Cognitive robots learning failure contexts through experimentation. In Proceedings of the 14th International Conference on Autonomous Agents & Multiagent Systems.
  7. Kurniawati, H., Hsu, D., and Lee, W. S. (2008). Sarsop: Efficient point-based pomdp planning by approximating optimally reachable belief spaces. In Robotics: Science and Systems, volume 2008. Zurich, Switzerland.
  8. Lang, T. and Toussaint, M. (2010). Planning with noisy probabilistic relational rules. Journal of Artificial Intelligence Research, 39(1):1-49.
  9. Monsó, P., Alenyà, G., and Torras, C. (2012). Pomdp approach to robotized clothes separation. In Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, pages 1324-1329. IEEE.
  10. Muggleton, S. (1995). Inverse entailment and progol. New generation computing, 13(3-4):245-286.
  11. Ozturk, M. D., Ersen, M., Kapotoglu, M., Koc, C., SarielTalay, S., and Yalcin, H. (2014). Scene interpretation for self-aware cognitive robots. In AAAI-14 Spring Symposium on Qualitative Representations for Robots.
  12. Pajarinen, J. and Kyrki, V. (2014a). Robotic manipulation in object composition space. In Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on, pages 1-6. IEEE.
  13. Pajarinen, J. and Kyrki, V. (2014b). Robotic manipulation of multiple objects as a pomdp. arXiv preprint arXiv:1402.0649.
  14. Pasula, H., Zettlemoyer, L. S., and Kaelbling, L. P. (2004). Learning probabilistic relational planning rules. In ICAPS, pages 73-82.
  15. Png, S. C. O. S. W. and Lee, D. H. W. S. (2009). Pomdps for robotic tasks with mixed observability.
  16. Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., Wheeler, R., and Ng, A. Y. (2009). Ros: an open-source robot operating system. In ICRA workshop on open source software, volume 3, page 5.
  17. Roy, N., Gordon, G., and Thrun, S. (2006). Planning under uncertainty for reliable health care robotics. In Field and Service Robotics, pages 417-426. Springer.
  18. Yildiz, P., Karapinar, S., and Sariel-Talay, S. (2013). Learning guided symbolic planning for cognitive robots. In The IEEE International Conference on Robotics and Automation (ICRA), Autonomous Learning Workshop.
Download


Paper Citation


in Harvard Style

Kapotoglu M., Koc C. and Sariel S. (2015). Robots Avoid Potential Failures through Experience-based Probabilistic Planning . In Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-758-123-6, pages 111-120. DOI: 10.5220/0005548801110120


in Bibtex Style

@conference{icinco15,
author={Melis Kapotoglu and Cagatay Koc and Sanem Sariel},
title={Robots Avoid Potential Failures through Experience-based Probabilistic Planning},
booktitle={Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2015},
pages={111-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005548801110120},
isbn={978-989-758-123-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Robots Avoid Potential Failures through Experience-based Probabilistic Planning
SN - 978-989-758-123-6
AU - Kapotoglu M.
AU - Koc C.
AU - Sariel S.
PY - 2015
SP - 111
EP - 120
DO - 10.5220/0005548801110120