Abstract
The limited nature of robot sensors make many important robotics problems partially observable. These problems may require the system to perform complex information-gathering operations. One approach to solving these problems is to create plans in belief-space, the space of probability distributions over the under-lying state of the system. The belief-space plan encodes a strategy for performing a task while gaining information as necessary. Most approaches to belief-space planning rely upon representing belief state in a particular way (typically as a Gaussian). Unfortunately, this can lead to large errors between the assumed density representation of belief state and the true belief state. This paper proposes a new sample-based approach to belief-space planning that has fixed computational complexity while allowing arbitrary implementations of Bayes filtering to be used to track belief state. The approach is illustrated in the context of a simple example and compared to a prior approach. Then, we propose an application of the technique to an instance of the grasp synthesis problem where a robot must simultaneously localize and grasp an object given initially uncertain object parameters by planning information-gathering behavior. Experimental results are presented that demonstrate the approach to be capable of actively localizing and grasping boxes that are presented to the robot in uncertain and hard-to-localize configurations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Although we have formally limited ourselves to the case of zero process noise, we find in Sect. 4 that empirically, our algorithm performs well in environments with bounded process noise.
References
C. Papadimitriou, J. Tsitsiklis, Math. Oper. Res. 12(3), 441 (1987)
T. Smith, R. Simmons, in Proceedings Uncertainty in Artificial Intelligence (2005)
H. Kurniawati, D. Hsu, W.S. Lee, in Proceedings of Robotics: Science and Systems (RSS)
S. Ross, J. Pineau, S. Paquet, B. Chaib-draa, J. Mach. Learn. Res. 32, 663 (2008)
H. Bai, W. Hsu, D. Lee, A. Ngo, in Workshop on the Algorithmic Foundations of Robotics (WAFR) (2010)
J. Porta, N. Vlassis, M. Spaan, P. Poupart, J. Mach. Learn. Res. 7, 2329 (2006)
J. Van der Berg, P. Abbeel, K. Goldberg, in Proceedings of Robotics: Science and Systems (RSS) (2010)
S. Prentice, N. Roy, in 12th International Symposium of Robotics Research (2008)
N. Du Toit, J. Burdick, in IEEE International Conference on Robotics and Automation (ICRA) (2010)
R. Platt, R. Tedrake, L. Kaelbling, T. Lozano-Perez, in Proceedings of Robotics: Science and Systems (RSS) (2010)
T. Erez, W. Smart, in Proceedings of the International Conference on Uncertainty in Artificial Intelligence (2010)
K. Hauser, in Workshop on the Algorithmic Foundations of Robotics (WAFR) (2010)
R. Platt, L. Kaelbling, T. Lozano-Perez, R. Tedrake, A hypothesis-based algorithm for planning and control in non-gaussian belief spaces. Technical Report CSAIL-TR-2011-039, Massachusetts Institute of Technology (2011)
A. Doucet, N. Freitas, N. Gordon (eds.), Sequential Monte Carlo Methods in Practice (Springer, 2001)
S. LaValle, J. Kuffner, Int. J. Robot. Res. 20(5), 378 (2001)
D. Jacobson, D. Mayne, Differential Dynamic Programming (Elsevier, 1970)
J. Betts, Practical Methods for Optimal Control Using Nonlinear Programming (Siam, 2001)
M. Fischler, R. Bolles, Commun. ACM 24, 381 (1981)
L. Sciavicco, B. Siciliano, Modelling and Control of Robot Manipulators (Springer, 2000)
L. Blackmore, M. Ono, in Proceedings of the AIAA Guidance, Navigation, and Control Conference (2009)
Acknowledgments
This work was supported in part by in part by the NSF under Grant No. 0712012, in part by ONR MURI under grant N00014-09-1-1051 and in part by AFOSR grant AOARD- 104135.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Platt, R., Kaelbling, L., Lozano-Perez, T., Tedrake, R. (2017). Efficient Planning in Non-Gaussian Belief Spaces and Its Application to Robot Grasping. In: Christensen, H., Khatib, O. (eds) Robotics Research . Springer Tracts in Advanced Robotics, vol 100. Springer, Cham. https://doi.org/10.1007/978-3-319-29363-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-29363-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-29362-2
Online ISBN: 978-3-319-29363-9
eBook Packages: EngineeringEngineering (R0)