Sage Journals: Discover world-class research

Abstract

In this paper we address the problem of closing the loop from perception to action selection for unmanned ground vehicles, with a focus on navigating slopes. A new non-parametric learning technique is presented to generate a mobility representation where the maximum feasible speed is used as a criterion to classify the world. The inputs to the algorithm are terrain gradients derived from an elevation map and past observations of wheel slip. It is argued that such a representation can aid in path planning with improved selection of vehicle heading and velocity in off-road slopes. In addition, an information theoretic test is proposed to validate a chosen proprioceptive representation (such as slip) for mobility map generation. Results of mobility map generation and its benefits to path planning are shown.

Keywords

off-road ground vehicles scene interpretation mobility maps proprioception vehicle-terrain interaction Gaussian processes

Get full access to this article

View all access options for this article.

References

Abbeel, P. and Ng, A.Y. ( 2004). Apprenticeship learning via inverse reinforcement learning . 21st International Conference on Machine Learning , Banff, Canada.

Angelova, A. , Matthies, L. , Helmick, D. and Perona, P. ( 2006). Slip prediction using visual information. Proceedings of Robotics: Science and Systems (RSS).

Angelova, A. , Matthies, L. , Helmick, D. and Perona, P. ( 2007). Learning and prediction of slip using visual information . Journal of Field Robotics, 24(3): 206-231.

Bishop, C.M. ( 2006). Pattern Recognition And Machine Learning. Berlin, Springer.

Csató, L. ( 2002). Gaussian Processes-Iterative Sparse Approximations. Aston University, PhD Thesis.

Goldberg, P. , Williams, C. and Bishop, C. ( 1998). Regression with input-dependent noise: a Gaussian process treatment. Advances in Neural Information Processing Systems (NIPS). Cambridge, MA, The MIT Press, Volume 10. pp. 493-499.

Gonzalez, R.C. and Woods, R.E. ( 2008). Digital Image Processing (3rd edn). Englewood Cliffs, NJ, Prentice Hall.

Green, A.R. and Rye, D. ( 2007). Sensible planning for vehicles operating over difficult unstructured terrains. IEEE Aerospace Conference , pp. 1-8.

Hadsell, R. , Sermanet, P. , Erkan, A.N. , Ben, J. , Han, J. , Flepp, B. , Muller, U. , and LeCun, Y. ( 2007). Online learning for offroad robots: Using spatial label propagation to learn by long-range traversability. Proceedings of Robotics: Science and Systems.

10.

Jackel, L.D. , Krotkov, E. , Perschbacher, M. , Pippine, J. and Sullivan, C. ( 2006). The DARPA LAGR program: Goals, challenges, methodology, and phase I results. Journal of Field Robotics, 23(11-12): 945-973.

11.

Julier, S.J. ( 1996). Process Models for the Navigation of High-Speed Land Vehicles. PhD Thesis, The University of Oxford.

12.

Julier, S.J. , Uhlmann, J.K. and Durrant-Whyte, H.F. ( 2000). A new method for the nonlinear transformation of means and covariances in filters and estimators. IEEE Transactions on Automatic Control, 45(3): 477-482.

13.

Karumanchi, S. , Allen, T. , Bailey, T. and Scheding, S. ( 2009). Non-parametric learning to aid path planning over slopes . Proceedings of Robotics: Science and Systems , Seattle, WA.

14.

Kersting, K. , Plagemann, C. , Pfaff, P. and Burgard, W. ( 2007). Most likely heteroschedastic gaussian process regression . Proceedings of 24th Internatinal Conference on Machine Learning, Corvallis, OR.

15.

Lacroix, S. , Mallet, A. , Bonnafous, D. , Bauzil, G. , Fleury, S. , Herrb, M. and Chatila., R. ( 2002). Autonomous rover navigation on unknown terrains: functions and integration. The International Journal of Robotics Research , 21(10-11): 917-942.

16.

Le, A.T. , Rye, D. and Durrant-Whyte, H. ( 1997). Estimation of track-soil interactions for autonomous tracked vehicles. IEEE International Conference on Robotics and Automation, Vol. 2, pp. 1388-1393.

17.

Meeds, E. and Osindero, S. ( 2006). An Alternative Infinite Mixture of Gaussian Process Experts (Advances in Neural Information Processing Systems, Vol. 18). Cambridge, MA, The MIT Press, pp. 883-890.

18.

Noë, A. ( 2005). Action in Perception. Cambridge, MA , The MIT Press.

19.

Ojeda, L. , Borenstein, J. , Witus, G. and Karlsen, R. ( 2006). Terrain characterization and classification with a mobile robot. Journal of Field Robotics, 23(2): 103-122.

20.

Quiñonero Candela, J. and Rasmussen, C.E. ( 2005). A unifying view of sparse approximate Gaussian process regression. Journal of Machine Learning Research, 6(12): 1935- 1959.

21.

Rasmussen, C.E. ( 2000). The Infinite Gaussian Mixture Model (Advances in Neural Information Processing Systems, Vol. XXX). Cambridge, MA , The MIT Press.

22.

Rasmussen, C.E. and Ghahramani, Z. ( 2002). Infinite Mixtures of Gaussian Process Experts (Advances in Neural Information Processing Systems, Vol. 14). Cambridge, MA, The MIT Press, pp. 881-888.

23.

Rasmussen, C.E. and Williams, C.K.I. ( 2006). Gaussian Processes for Machine Learning. Cambridge, MA, The MIT Press, Volume 12. pp. 554-560.

24.

Ratliff, N. ( 2009). Learning to Search: Structured Prediction Techniques for Imitation Learning. Carnegie Mellon University, PhD Thesis.

25.

Seeger, M. , William, C. and Lawrence, N. ( 2003). Fast forward selection to speed up sparse Gaussian process regression. Proceedings of the 9th Workshop on Artificial Intelligence and Statistics.

26.

Shneier, M. , Chang, T. , Hong, T. , Shackleford, W. , Bostelman, R. and Albus, J.S. ( 2008). Learning traversability models for autonomous mobile vehicles. Autonomous Robots, 24(1): 69-86.

27.

Silver, D. , Bagnell, J. and Stentz, A. ( 2008). High performance outdoor navigation from overhead data using imitation learning. Proceedings of Robotics: Science and Systems IV, Zurich, Switzerland.

28.

Silver, D. , Sofman, B. , Vandapel, N. , Bagnell, J. and Stentz, A. ( 2006). Experimental analysis of overhead data processing to support long range navigation. IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 2443-2450.

29.

Sofman, B. , Ratliff, E.L. , Bagnell, J. , Cole, J. , Vandapel, N. and Stentz, A. ( 2006). Improving robot navigation through self-supervised online learning. Journal of Field Robotics, 23(12).

30.

Stavens, D. , Hoffmann, G. and Thrun, S. ( 2007). Online speed adaptation using supervised learning for high-speed, offroad autonomous driving. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

31.

Sutton, R.S. and Barto, A.G. ( 1998). Reinforcement Learning: An Introduction. Cambridge, MA, The MIT Press.

32.

Tipping, M.E. ( 2001). Sparse Bayesian learning and the relevance vector machine . Journal of Machine Learning Research, 1: 211-244.

33.

Tipping, M.E. and Faul, A.C. ( 2003). Fast marginal likelihood maximisation for sparse Bayesian models. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, Key West, FL.

34.

Wong, J.Y. ( 2001). Theory Of Ground Vehicles (3rd edn). New York, Wiley.

35.

Wood, F. , Grollman, D.H. , Heller, K.A. , Jenkins, O.C. and Black, M.J. ( 2008). Incremental Nonparametric Bayesian Regression. Technical Report CS-08-07, Department of Computer Science, Brown University.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB