Abstract
This paper explores the suitability of commonly employed classification methods to action-selection tasks in robotics, and argues that a classifier’s introspective capacity is a vital but as yet largely under-appreciated attribute. As illustration we propose an active learning framework for semantic mapping in mobile robotics and demonstrate it in the context of autonomous driving. In this framework, data are selected for label disambiguation by a human supervisor using uncertainty sampling. Intuitively, an introspective classification framework—i.e. one which moderates its predictions by an estimate of how well it is placed to make a call in a particular situation—is particularly well suited to this task. To achieve an efficient implementation we extend the notion of introspection to a particular sparse Gaussian Process Classifier, the Informative Vector Machine (IVM). Furthermore, we leverage the information-theoretic nature of the IVM to formulate a principled mechanism for forgetting stale data, thereby bounding memory use and resulting in a truly life-long learning system. Our evaluation on a publicly available dataset shows that an introspective active learner asks more informative questions compared to a more traditional non-introspective approach like a Support Vector Machine (SVM) and in so doing, outperforms the SVM in terms of learning rate while retaining efficiency for practical use.
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 subscriptionsReferences
Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121–167 (1998)
Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)
DARPA. Urban challenge route network definition file (RNDF) and mission data file (MDF) formats, March 2007
Dima, C., Hebert, M., Stentz. A.: Enabling learning from large datasets: applying active learning to mobile robotics. In: IEEE International Confreence on Robotics and Automation (ICRA), vol. 1, pp. 108–114. IEEE (2004)
Fairfield, N., Urmson, C.: Traffic light mapping and detection. In: IEEE International Conference on Robotics and Automation (ICRA) (2011)
Freund, Y., Seung, H.S., Shamir, E., Tishby, N.: Selective sampling using the query by committee algorithm. Mach. Learn. 28(2), 133–168 (1997)
Grimmett, H., Paul, R., Triebel, R., Posner, I.: Knowing when we don’t know: introspective classification for mission-critical decision making. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (2013)
Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: Computer Vision and Pattern Recognition (CVPR), pp. 2372–2379 (2009)
Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Gaussian processes for object categorization. Int. J. Comput. Vis. 88(2), 169–188 (2010)
Lawrence, N.D., Seeger, M., Herbrich, R.: Fast sparse gaussian process methods: the informative vector machine. Adv. Neural Inf. Process. Syst. 15, 609–616 (2002)
Lawrence, N.D., Platt, J.C., Jordan, M.I.: Extensions of the informative vector machine. In: Proceedings of the First international conference on Deterministic and Statistical Methods in Machine Learning, pp. 56–87. Springer (2005)
McCallum, A., Nigam, K.: Employing em in pool-based active learning for text classification. In: Proceedings of ICML-98, 15th International Conference on Machine Learning, pp. 350–358 (1998)
Paul, R., Newman, P.: Self help: Seeking out perplexing images for ever improving navigation. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 445–451. IEEE (2011)
Platt, J.: Probabilistic outputs for support vector machines and comparison to regularize likelihood methods. In: Smola, A.J., Bartlett, P., Schoelkopf, B., Schuurmans, D. (eds.) Advances in Large Margin Classifiers, pp. 61–74 (2000)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Robotics Centre of Mines ParisTech. Traffic lights recognition (TLR) data set
Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin-Madison (2010)
Tellex, S., Thaker, P., Deits, R., Kollar, T., Roy, N.: Toward information theoretic human-robot dialog. In: Robotics: Science and Systems (2012)
Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2, 45–66 (2002)
Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. IEEE Trans. Pattern Anal. Mach. Intell., 29(5):854–869 (2007). ISSN 0162–8828
Triebel, R., Grimmett, H., Paul, R., Posner, I.: Introspective active learning for scalable semantic mapping. In: Workshop. Robotics Science and Systems (RSS) (2013)
Urmson, C., et al.: Autonomous driving in urban environments: boss and the Urban Challenge. J. Field Robot., 25(8):425–466 (2008). ISSN 1556–4967
Acknowledgments
This work is funded under the European Community’s Seventh Framework Programme (FP7/2007–2013) under Grant Agreement Number 269916 (V-CHARGE) and by the UK EPSRC Grant Number EP/J012017/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Triebel, R., Grimmett, H., Paul, R., Posner, I. (2016). Driven Learning for Driving: How Introspection Improves Semantic Mapping. In: Inaba, M., Corke, P. (eds) Robotics Research. Springer Tracts in Advanced Robotics, vol 114. Springer, Cham. https://doi.org/10.1007/978-3-319-28872-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-28872-7_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28870-3
Online ISBN: 978-3-319-28872-7
eBook Packages: EngineeringEngineering (R0)