Advancing the incremental fusion of robotic sensory features using online multi-kernel extreme learning machine

doi:10.1007/s11704-016-5171-9

Front. Comput. Sci.

2017, Vol. 11

Issue (2) : 276-289 https://doi.org/10.1007/s11704-016-5171-9

RESEARCH ARTICLE

Advancing the incremental fusion of robotic sensory features using online multi-kernel extreme learning machine

Lele CAO^1,^2,³(

),Fuchun SUN^1,²,Hongbo LI^1,²,Wenbing HUANG^1,²

¹. State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
². Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing 100084, China
³. Department of Computing and Information Systems, The University of Melbourne, Parkville 3010 VIC, Australia

Download: PDF(894 KB)
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Robot recognition tasks usually require multiple homogeneous or heterogeneous sensors which intrinsically generate sequential, redundant, and storage demanding data with various noise pollution. Thus, online machine learning algorithms performing efficient sensory feature fusion have become a hot topic in robot recognition domain. This paper proposes an online multi-kernel extreme learning machine (OM-ELM) which assembles multiple ELM classifiers and optimizes the kernel weights with a p-norm formulation of multi-kernel learning (MKL) problem. It can be applied in feature fusion applications that require incremental learning over multiple sequential sensory readings. The performance of OM-ELM is tested towards four different robot recognition tasks. By comparing to several state-of-the-art online models for multi-kernel learning, we claim that our method achieves a superior or equivalent training accuracy and generalization ability with less training time. Practical suggestions are also given to aid effective online fusion of robot sensory features.

Keywords multi-kernel learning online learning extreme learning machine feature fusion robot recognition

Corresponding Author(s): Lele CAO

Just Accepted Date: 17 November 2015 Online First Date: 18 July 2016 Issue Date: 06 April 2017

Cite this article:

Lele CAO,Fuchun SUN,Hongbo LI, et al. Advancing the incremental fusion of robotic sensory features using online multi-kernel extreme learning machine[J]. Front. Comput. Sci., 2017, 11(2): 276-289.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-016-5171-9
https://academic.hep.com.cn/fcs/EN/Y2017/V11/I2/276

1	Sonnenburg S, Rätsch G, Schäfer C, Schölkopf B. Large scale multiple kernel learning. The Journal of Machine Learning Research, 2006, 7: 1531–1565
2	Lanckriet G R, Cristianini N, Bartlett P, Ghaoui L E, Jordan M I. Learning the kernel matrix with semidefinite programming. The Journal of Machine Learning Research, 2004, 5: 27–72
3	Zien A, Ong C S. Multiclass multiple kernel learning. In: Proceedings of International Conference on Machine Learning. 2007, 1191–1198 https://doi.org/10.1145/1273496.1273646
4	Rakotomamonjy A, Bach F, Canu S, Grandvalet Y. Simplemkl. Journal of Machine Learning Research, 2008, 9: 2491–2521
5	Shalev-Shwartz S. Online learning and online convex optimization. Foundations and Trends in Machine Learning, 2011, 4(2): 107–194 https://doi.org/10.1561/2200000018
6	Cesa-Bianchi N, Lugosi G. Prediction, Learning, and Games. Cambridge: Cambridge University Press, 2006 https://doi.org/10.1017/CBO9780511546921
7	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications. Neurocomputing, 2006, 70(1): 489–501 https://doi.org/10.1016/j.neucom.2005.12.126
8	Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks, 2006, 17(4): 879–892 https://doi.org/10.1109/TNN.2006.875977
9	Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110 https://doi.org/10.1023/B:VISI.0000029664.99615.94
10	Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2005, 886–893 https://doi.org/10.1109/cvpr.2005.177
11	Van De Weijer J, Schmid C. Coloring local feature extraction. In: Proceedings of European Conference on Computer Vision. 2006, 334–348 https://doi.org/10.1007/11744047_26
12	Wang H, Ullah M M, Klaser A, Laptev I, Schmid C. Evaluation of local spatio-temporal features for action recognition. In: Proceedings of British Machine Vision Conference. 2009, 1–11 https://doi.org/10.5244/c.23.124
13	Taylor G W, Fergus R, LeCun Y, Bregler C. Convolutional learning of spatio-temporal features. In: Proceedings of European Conference on Computer Vision. 2010, 140–153 https://doi.org/10.1007/978-3-642-15567-3_11
14	Li Z, Liu J, Yang Y, Zhou X, Lu H. Clustering-guided sparse structural learning for unsupervised feature selection. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(9): 2138–2150 https://doi.org/10.1109/TKDE.2013.65
15	Li Z, Liu J, Tang J, Lu H. Robust structured subspace learning for data representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(1): 2085–2098 https://doi.org/10.1109/TPAMI.2015.2400461
16	Kokar M M, Tomasik J A, Weyman J. Formalizing classes of information fusion systems. Information Fusion, 2004, 5(3): 189–202 https://doi.org/10.1016/j.inffus.2003.11.001
17	Khaleghi B, Khamis A, Karray F O, Razavi S N. Multisensor data fusion: a review of the state-of-the-art. Information Fusion, 2011, 14(1): 28–44 https://doi.org/10.1016/j.inffus.2011.08.001
18	Waske B, Benediktsson J A. Fusion of support vector machines for classification of multisensor data. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 3858–3866 https://doi.org/10.1109/TGRS.2007.898446
19	Reiter A, Allen P K, Zhao T. Learning features on robotic surgical tools. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2012, 38–43 https://doi.org/10.1109/cvprw.2012.6239245
20	Campos F M, Correia L, Calado J. Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches. Journal of Intelligent and Robotic Systems, 2015, 77(2): 377–390 https://doi.org/10.1007/s10846-013-0016-3
21	Jie L, Orabona F, Fornoni M, Caputo B, Cesa-Bianchi N. OM-2: an online multi-class multi-kernel learning algorithm. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2010, 43–50
22	Gijsberts A, Metta G. Incremental learning of robot dynamics using random features. In: Proceedings of IEEE International Conference on Robotics and Automation. 2011, 951–956 https://doi.org/10.1109/icra.2011.5980191
23	Nguyen-Tuong D, Peters J. Incremental online sparsification for model learning in real-time robot control. Neurocomputing, 2011, 74(11): 1859–1867 https://doi.org/10.1016/j.neucom.2010.06.033
24	Cho S, Jo S. Incremental online learning of robot behaviors from selected multiple kinesthetic teaching trials. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2013, 43(3): 730–740 https://doi.org/10.1109/TSMCA.2012.2207108
25	Jamone L, Natale L, Nori F, Metta G, Sandini G. Autonomous online learning of reaching behavior in a humanoid robot. International Journal of Humanoid Robotics, 2012, 9(10): 6–8 https://doi.org/10.1142/s021984361250017x
26	Luo J, Pronobis A, Caputo B, Jensfelt P. Incremental learning for place recognition in dynamic environments. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2007, 721–728 https://doi.org/10.1109/iros.2007.4398986
27	Ciliberto C, Smeraldi F, Natale L, Metta G. Online multiple instance learning applied to hand detection in a humanoid robot. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2011, 1526–1532 https://doi.org/10.1109/iros.2011.6095002
28	Araki T, Nakamura T, Nagai T, Funakoshi K, Nakano M, Iwahashi N. Online object categorization using multimodal information autonomously acquired by robots. Advanced Robotics, 2012, 26(17): 1995–2020 https://doi.org/10.1080/01691864.2012.728693
29	Su L j, Yao M. Extreme learning machine with multiple kernels. In: Proceedings of IEEE International Conference on Control and Automation. 2013, 424–429
30	Liu X, Wang L, Huang G B, Zhang J, Yin J. Multiple kernel extreme learning machine. Neurocomputing, 2015, 149: 253–264 https://doi.org/10.1016/j.neucom.2013.09.072
31	Cao L L, Huang W B, Sun F C. Optimization-based extreme learning machine with multi-kernel learning approach for classification. In: Proceedings of International Conference on Pattern Recognition. 2014, 3564–3569 https://doi.org/10.1109/icpr.2014.613
32	Liang N Y, Huang G B, Saratchandran P, Sundararajan N. A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Transaction on Neural Networks, 2006, 17(6): 1411–1423 https://doi.org/10.1109/TNN.2006.880583
33	Hoang M T T, Huynh H T, Vo N H, Won Y. A robust online sequential extreme learning machine. Lecture Notes in Computer Science, 2007, 4491: 1077–1086 https://doi.org/10.1007/978-3-540-72383-7_126
34	Lan Y, Soh Y C, Huang G B. Ensemble of online sequential extreme learning machine. Neurocomputing, 2009, 72(13): 3391–3395 https://doi.org/10.1016/j.neucom.2009.02.013
35	Hush D, Kelly P, Scovel C, Steinwart I. QP algorithms with guaranteed accuracy and run time for support vector machines. The Journal of Machine Learning Research, 2006, 7: 733–769
36	Jie L, Orabona F, Caputo B. An online framework for learning novel concepts over multiple cues. In: Proceedings of Asian Conference on Computer Vision. 2010, 269–280 https://doi.org/10.1007/978-3-642-12307-8_25
37	Hoi S C, Jin R, Zhao P, Yang T. Online multiple kernel classification. Machine Learning, 2013, 90(2): 289–316 https://doi.org/10.1007/s10994-012-5319-2
38	Huang G B, Ding X, Zhou H. Optimization-based extreme learning machine for classification. Neurocomputing, 2010, 74(1): 155–163 https://doi.org/10.1016/j.neucom.2010.02.019
39	Huang G B, Zhou H, Ding X, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics: Cybernetics, 2012, 42(2): 513–529
40	Huang G B. What are extreme learning machines? filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle. Cognitive Computation, 2015, 7(3): 263–278 https://doi.org/10.1007/s12559-015-9333-0
41	Orabona F, Jie L, Caputo B. Multi kernel learning with online-batch optimization. The Journal of Machine Learning Research, 2012, 13(1): 227–253
42	Orabona F, Jie L, Caputo B. Online-batch strongly convex multi kernel learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2010, 787–794 https://doi.org/10.1109/cvpr.2010.5540137
43	Fink M, Shalev-Shwartz S, Singer Y, Ullman S. Online multiclass learning by interclass hypothesis sharing. In: Proceedings of International Conference on Machine Learning. 2006, 313–320 https://doi.org/10.1145/1143844.1143884
44	Huang G B, Wang D H, Lan Y. Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107–122 https://doi.org/10.1007/s13042-011-0019-y
45	Bach F R, Lanckriet G R, Jordan M I. Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of International Conference on Machine Learning. 2004, 6 https://doi.org/10.1145/1015330.1015424
46	Jin R, Hoi S C, Yang T. Online multiple kernel learning: algorithms and mistake bounds. Lecture Notes in Computer Science, 2010, 6331(4): 390–404 https://doi.org/10.1007/978-3-642-16108-7_31
47	Xiao W, Sun F C, Liu H P, He C. Dexterous robotic-hand grasp learning using piecewise linear dynamic systems model. In: Proceedings of International Conference on Cognitive Systems and Information Processing. 2014, 845–855 https://doi.org/10.1007/978-3-642-37835-5_73
48	Xiao W, Sun F C, Liu H P, Huang C. Manipulation techniques of dexterous robotic hand based on cyber-physical fusion. Journal of Tsinghua University (Science and Technology), 2013, 11: 1601–1608
49	Bekiroglu Y, Kragic D, Kyrki V. Learning grasp stability based on tactile data and hmms. In: Proceedings of IEEE International Symposium on Robot and Human Interactive Communication. 2010, 132–137 https://doi.org/10.1109/ROMAN.2010.5598659
50	Bekiroglu Y, Laaksonen J, Jorgensen J A, Kyrki V, Kragic D. Assessing grasp stability based on learning and haptic data. IEEE Transactions on Robotics, 2011, 27(3): 616–629 https://doi.org/10.1109/TRO.2011.2132870
51	Yang J, Liu H, Sun F, Gao M. Tactile sequence classification using joint kernel sparse coding. In: Proceedings of International Joint Conference on Neural Networks. 2015, 1–6 https://doi.org/10.1109/ijcnn.2015.7280512
52	Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2006, 2169–2178 https://doi.org/10.1109/cvpr.2006.68
53	Madry M, Bo L, Kragic D, Fox D. ST-HMP: Unsupervised spatiotemporal feature learning for tactile data. In: Proceedings of IEEE International Conference on Robotics and Automation. 2014, 2262–2269
54	Orabona F. DOGMA: a Matlab toolbox for online learning, 2009
55	Bo L, Ren X, Fox D. Hierarchical matching pursuit for image classification: architecture and fast algorithms. In: Proceedings of Conference on Neural Information Processing Systems. 2011, 2115–2123
56	Hinton G. A practical guide to training restricted boltzmann machines. Momentum, 2010, 9(1): 926

[1]

Supplementary Material

Download

[1]	Hui ZHONG, Zaiyi CHEN, Chuan QIN, Zai HUANG, Vincent W. ZHENG, Tong XU, Enhong CHEN. Adam revisited: a weighted past gradients perspective[J]. Front. Comput. Sci., 2020, 14(5): 145309-.
[2]	Jia ZHU, Xingcheng WU, Jing XIAO, Changqin HUANG, Yong TANG, Ke Deng. Improved expert selection model for forex trading[J]. Front. Comput. Sci., 2018, 12(3): 518-527.
[3]	Zhaoxiang ZHANG, Yunhong WANG. Automatic object classification using motion blob based local feature fusion for traffic scene surveillance[J]. Front Comput Sci, 2012, 6(5): 537-546.

Viewed

Full text

Abstract

Cited

Shared

Discussed