In this work, we present a novel approach that allows a robot to improve its own navigation performance through introspection and then targeted data retrieval. It is a step in the direction of life-long learning and adaptation and is motivated by the desire to build robots that have plastic competencies which are not baked in. They should react to and benefit from use. We consider a particular instantiation of this problem in the context of place recognition. Based on a topic-based probabilistic representation for images, we use a measure of perplexity to evaluate how well a working set of background images explain the robot’s online view of the world. Offline, the robot then searches an external resource to seek out additional background images that bolster its ability to localize in its environment when used next. In this way the robot adapts and improves performance through use. We demonstrate this approach using data collected from a mobile robot operating in outdoor workspaces.
AngeliAFilliatDDoncieuxSMeyerJ (2008) Fast and incremental method for loop-closure detection using bags of visual words. IEEE Transactions on Robotics, Special Issue on Visual SLAM24(5): 1027–1037.
2.
BanerjeeABasuS (2007) Topic models over text streams: A study of batch and online unsupervised learning. In: Proceedings of the seventh SIAM International conference on data mining, Minneapolis, MN, 26–28 April 2007, pp. 437–442.
3.
BayHTuytelaarsTVan GoolL (2006) Surf: Speeded up robust features. Computer vision–ECCV 2006, Graz, Austria, 7–13 May 2006, pp. 404–417.
4.
BiberPDuckettT (2005) Dynamic maps for long-term operation of mobile service robots. In: Proceedings of robotics: Science and systems (RSS), Cambridge, MA, 8–11 June 2005, pp. 17–24.
5.
BleiDLaffertyJ (2007) A correlated topic model of science. The Annals of Applied Statistics1(1): 17–35.
6.
BleiDNgAJordanM (2003) Latent Dirichlet allocation. The Journal of Machine Learning Research3: 993–1022.
7.
BoimanOIraniM (2007) Detecting irregularities in images and in video. International Journal of Computer Vision74(1): 17–31.
ChurchillWNewmanP (2012) Practice makes perfect? managing and leveraging visual experiences for lifelong navigation. In: 2012 IEEE International conference on robotics and automation (ICRA), St. Paul, MN, 14–18 May 2012, pp. 4525–4532.
10.
CumminsMNewmanP (2007) Probabilistic appearance based navigation and loop closing. In: 2007 IEEE International conference on robotics and automation, Rome, 10–14 April 2007, pp. 2042–2048.
11.
CumminsMNewmanP (2008) FAB-MAP: Probabilistic localization and mapping in the space of appearance. The International Journal of Robotics Research27(6): 647–665.
12.
CumminsMNewmanP (2011) Appearance-only SLAM at large scale with FAB-MAP 2.0. The International Journal of Robotics Research30(9): 1100–1123.
13.
CussensJ (1993) Bayes and pseudo-Bayes estimates of conditional probabilities and their reliability. In: Machine learning: ECML-93, Vienna, 5–7 April, pp. 136–152.
14.
DayoubFDuckettT (2008) An adaptive appearance-based map for long-term topological localization of mobile robots. In: 2008 IEEE/RSJ International conference on intelligent robots and systems (IROS), Nice, France, 22–26 September 2008, pp. 3364–3369.
15.
EndresFPlagemannCStachnissCBurgardW (2009) Unsupervised discovery of object classes from range data using latent Dirichlet allocation. In: Proceedings of robotics: science and systems, Seattle, USA, p. 34.
16.
Fei-FeiLPeronaP (2005) A Bayesian hierarchical model for learning natural scene categories. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR), San Diego, CA, 20–26 June 2005, Vol. 2, pp. 524–531.
17.
GirdharYDudekG (2010 a) Online navigation summaries. In: 2010 IEEE International conference on robotics and automation (ICRA), Anchorage, AK, 3–8 May 2010, pp. 5035–5040.
18.
GirdharYDudekG (2010 b) Onsum: A system for generating online navigation summaries. In: Proceedings of the IEEE/RSJ International conference on intelligent robots and systems (IROS), Taipei, Taiwan, 18–22 October 2010, pp. 746–751.
19.
GirdharYGiguerePDudekG (2012) Autonomous adaptive underwater exploration using online topic modelling. In: International symposium on experimental robotics, Quebec City, Canada, 17–31 June 2012.
20.
GloverAJMaddernWPMilfordMJWyethGF (2010) FAB-MAP+ RatSLAM: appearance-based SLAM for multiple times of day. In: 2010 IEEE International conference on robotics and automation (ICRA), Anchorage, AK, 3–8 May 2010, pp. 3507–3512.
21.
GriffithsTSteyversM (2004) Finding scientific topics. Proceedings of the National Academy of Sciences of the United States of America101(Suppl 1): 5228.
HendelAWeinshallDPelegS (2011) Identifying surprising events in videos using Bayesian topic models. Computer vision–ACCV 2010, Queenstown, New Zealand, 8–12 November 2010, pp. 448–459.
24.
HoKNewmanP (2007) Detecting loop closure with scene sequences. International Journal of Computer Vision74(3): 261–286.
25.
HoffmanMBleiDBachF (2010) Online learning for latent Dirichlet allocation. Advances in Neural Information Processing Systems23: 856–864.
26.
HoiSJinRZhuJLyuM (2006) Batch mode active learning and its application to medical image classification. In: Proceedings of the 23rd International conference on machine learning, Pittsburgh, PA, 25–29 June, pp. 417–424.
27.
HolubAPeronaPBurlM (2008) Entropy-based active learning for object recognition. In: 2008 IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW), Anchorage AK, 23–28 June 2008, pp. 1–8.
28.
HorsterELienhartRSlaneyM (2007) Image retrieval on large-scale image databases. In: Proceedings of the 6th ACM International conference on image and video retrieval, Amsterdam, 9–11 July 2007, pp. 17–24.
29.
HospedalesTGongSXiangT (2011) Finding rare classes: Active learning with generative and discriminative models. IEEE Transactions on Knowledge and Data Engineering (99): 1–1.
30.
IttiLBaldiP (2005) A principled approach to detecting surprising events in video. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR), San Diego, CA, 20–26 June 2005, Vol. 1, pp. 631–637.
31.
JohoDTipaldiGDEngelhardNStachnissCBurgardW (2012) Nonparametric Bayesian models for unsupervised scene analysis and reconstruction. In: Proceedings of robotics: science and systems (RSS), Sydney, Australia, 9–13 July 2012.
32.
JoshiAPorikliFPapanikolopoulosN (2009) Multi-class active learning for image classification. In: 2009 IEEE conference on computer vision and pattern recognition (CVPR), Miami, FL, 20–25 June 2009, pp. 2372–2379.
33.
KapoorAGraumanKUrtasunRDarrellT (2010) Gaussian processes for object categorization. International Journal of Computer Vision88(2): 169–188.
34.
KonoligeKBowmanJ (2009) Towards lifelong visual maps. In: 2009 IEEE/RSJ International conference on intelligent robots and systems (IROS), St. Louis, MO, 10–15 October 2009, pp. 1156–1163.
35.
KonoligeKBowmanJChenJMihelichPCalonderMLepetitVFuaP (2010) View-based maps. The International Journal of Robotics Research29(8): 941–957.
36.
LavrenkoV (2009) A generative theory of relevance, Vol. 26. New York: Springer-Verlag.
37.
LawrenceNSeegerMHerbrichR (2002) Fast sparse Gaussian process methods: The informative vector machine. In: Advances in neural information processing systems, pp. 609–616.
38.
LevinASzeliskiR (2004) Visual odometry and map correlation. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition (CVPR), Washington DC, 27 June–2 July 2004, pp. I–611.
39.
LiuXCroftW (2004) Cluster-based retrieval using language models. In: Proceedings of the 27th annual international ACM SIGIR conference on research and development in information retrieval, Sheffield, UK, 25–29 July 2004, pp. 186–193.
40.
LoweD (2004) Distinctive image features from scale-invariant keypoints. International journal of computer vision60(2): 91–110.
41.
MacKayDPetoL (1995) A hierarchical Dirichlet language model. Natural language engineering1(3): 1–19.
42.
MaddernWMilfordMWyethG (2012) CAT-SLAM: probabilistic localisation and mapping using a continuous appearance-based trajectory. The International Journal of Robotics Research31(4): 429–451.
43.
ManningCRaghavanPSchutzeH (2008) Introduction to information retrieval, Vol. 1. Cambridge: Cambridge University Press.
44.
MeiCSibleyGNewmanP (2010) Closing loops without places. In: 2010 IEEE/RSJ International conference on intelligent robots and systems (IROS), Taipei, Taiwan, 18–22 October 2010, pp. 3738–3744.
45.
MilfordMWyethG (2010) Persistent navigation and mapping using a biologically inspired SLAM system. The International Journal of Robotics Research29(9): 1131–1153.
46.
MurilloACKoseckaJ (2009) Experiments in place recognition using gist panoramas. In: 2009 IEEE 12th International conference on computer vision workshops (ICCV Workshops), Kyoto, Japan, 27 September–4 October 2009, pp. 2196–2203.
47.
PaulRNewmanP (2010) FAB-MAP 3D: Topological mapping with spatial and visual appearance. In: 2010 IEEE International conference on robotics and automation (ICRA), Anchorage, AK, 3–8 May 2010, pp. 2649–2656.
48.
PaulRNewmanP (2011) Self help: Seeking out perplexing images for ever improving navigation. In: 2011 IEEE International conference on robotics and automation (ICRA), Shanghai, China, 9–13 May 2013, pp. 445–451.
49.
PhilbinJSivicJZissermanA (2008) Geometric LDA: A generative model for particular object discovery. In: Proceedings of the British machine vision conference (BMVC), Leeds, UK, 1–4 September 2008.
50.
RanganathanADellaertF (2009) Bayesian surprise and landmark detection. In: 2009 IEEE International conference on robotics and automation (ICRA), Kobe, Japan, 12–17 May 2009, pp. 2017–2023.
51.
SeegerMWilliamsCLawrenceN (2003) Fast forward selection to speed up sparse Gaussian process regression. In: Ninth International workshop on AI and statistics, Key West, FL, 3–6 January 2003.
52.
SettlesB (2010) Active learning literature survey. Computer Sciences Technical Report 1648. University of Wisconsin, Madison, USA.
53.
Silpa-AnanCHartleyR (2004) Localisation using an image-map. In: Proceedings of the Australian conference on robotics and automation, Canberra, Australia.
54.
Silpa-AnanCHartleyR (2008) Optimised kd-trees for fast image descriptor matching. In: 2008 IEEE conference on computer vision and pattern recognition (CVPR), Anchorage, AK, 24–26 June 2008, pp. 1–8.
55.
SinghGKoseckaJ (2010) Visual loop closing using gist descriptors in manhattan world. In: Omnidirectional robot vision workshop, with IEEE International Conference on Robotics and Automation (ICRA), Anchorage, Alaska, 3–8 May 2010.
56.
SivicJRussellBZissermanAFreemanWEfrosA (2008) Unsupervised discovery of visual object class hierarchies. In: 2008 IEEE conference on computer vision and pattern recognition (CVPR), Anchorage, AK, 24–26 June 2008, pp. 1–8.
57.
SivicJZissermanA (2003) Video google: A text retrieval approach to object matching in videos. In: Proceedings of ninth IEEE International conference on computer vision, Nice, France, 13–16 October 2003, pp. 1470–1477.
58.
TellexSThakerPRoyN (2012) Toward information theoretic human–robot dialog. In: Proceedings of robotics: Science and systems, Sydney, Australia, 9–13 July 2012.
59.
TehYJordanMBealMBleiD (2006) Hierarchical Dirichlet processes. Journal of the American Statistical Association101(476): 1566–1581.
60.
ValgrenCLilienthalA (2007) Sift, surf and seasons: Long-term outdoor localization using local features. In: Proceedings of the European conference on mobile robots (ECMR), Freiburg, 19–21 September 2007, pp. 253–258.
61.
VaradarajanJOdobezJ (2009) Topic models for scene analysis and abnormality detection. In: IEEE 12th International conference on computer vision workshops (ICCV Workshops), Kyoto, Japan, 27 September–4 October 2009, pp. 1338–1345.
62.
WallachH (2006) Topic modeling: Beyond bag-of-words. In: Proceedings of the 23rd International conference on machine learning, Pittsburgh, PA, 25–29 June 2006, pp. 977–984.
63.
WangCBleiDLiF (2009 a) Simultaneous image classification and annotation. In: IEEE conference on computer vision and pattern recognition (CVPR), Miami, FL, 20–25 June 2009, pp. 1903–1910.
64.
WangCPaisleyJBleiD (2011) Online variational inference for the hierarchical Dirichlet process. In: Proceedings of fourteenth International conference on artificial intelligence and statistics (AISTATS), Ft Lauderdale, FL, 11–13 April 2011.
65.
WangXGrimsonE (2007) Spatial latent Dirichlet allocation. Advances in Neural Information Processing Systems20: 1577–1584.
66.
WangXMaXGrimsonW (2009 b) Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models. IEEE Transactions on Pattern Analysis and Machine Intelligence31(3): 539–555.
67.
WeiXCroftW (2006) LDA-based document models for ad-hoc retrieval. In: Proceedings of the 29th annual International ACM SIGIR conference on research and development in information retrieval, Seattle, WA, 6–11 August 2006, pp. 178–185.
68.
ZhaiCLaffertyJ (2001) A study of smoothing methods for language models applied to ad hoc information retrieval. In: Proceedings of the 24th annual International ACM SIGIR conference on research and development in information retrieval, New Orleans, LA, 9–13 September 2001, pp. 334–342.
69.
ZhangYCallanJMinkaT (2002) Novelty and redundancy detection in adaptive filtering. In: Proceedings of the 25th annual International ACM SIGIR conference on research and development in Information retrieval, Tampere, Finland, 11–15 August 2002, pp. 81–88.
70.
ZhuJXingEP (2010) Conditional topic random fields. In: International conference on machine learning (ICML), Haifa, Israel, 21–24 June 2010, pp. 1239–1246.
