Abstract
To efficiently identify properties from its environment is an essential ability of a mobile robot who needs to interact with humans. Successful approaches to provide robots with such ability are based on ad-hoc perceptual representation provided by AI designers. Instead, our goal is to endow autonomous mobile robots (in our experiments a Pioneer 2DX) with a perceptual system that can efficiently adapt itself to ease the learning task required to anchor symbols. Our approach is in the line of meta-learning algorithms that iteratively change representations so as to discover one that is well fitted for the task. The architecture we propose may be seen as a combination of the two widely used approach in feature selection: the Wrapper-model and the Filter-model. Experiments using the PLIC system to identify the presence of Humans and Fire Extinguishers show the interest of such an approach, which dynamically abstracts a well fitted image description depending on the concept to learn.
This work has been partially supported by a grant to the CNRS Jeune équipe ”Découverte” (UMR 7606)
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Coradeschi, S., Saffiotti, A.: Anchoring symbols to sensor data: preliminary report. In: Proceedings of AAAI-2000, Austin, Texas (July 2000)
Steels, L.: The talking heads experiment. volume 1. words and meanings. In: Antwerpen. (1999)
Thrun, S., Bennewitz, M., Burgard, W., Cremers, A., Dellaert, F., Fox, D., Hihnel, D., Rosenberg, C., Roy, N., Schulte, J., Schulz, D.: Minerva: A second generation mobile tour-guide robot. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). (1999)
Stone, J.: Computer vision: What is the object? In: Prospects for AI, Proc. Artificial Intelligence and Simulation of Behaviour. Birmingham, England., IOS Press, Amsterdam. pages 199–208(1993)
Klingspor, V., Morik, K., Rieger, A.D.: Learning concepts from sensor data of a mobile robot. Machine Learning 23 (1996) 305–332
Saitta, L., Zucker, J.D.: A model of abstraction in visual perception. In: Applied Artificial Intelligence. 15(8): 761–776. (2001)
Picault, S., Drogoul, A.: The microbes project, an experimental approach towards open collective robotics. In: Proc. of the 5th International Symposium on Distributed Autonomous Robotic Systems, Springer-Verlag Tokyo Inc. (2000)
Giordana, A., Saitta, L.: Phase transitions in relational learning. Machine Learning Journal 41 (2000) 217-
Stricker, M., Swain, M.: The capacity and the sensitivity of color histogram indexing. In: Technical Report 94-05, Communications Technology Lab, ETH-Zentrum. (1994)
Saitta, L., Zucker, J.D.: Semantic abstraction for concept representation and learning. In AAAI), S.i.P.b., ed.: Symposium on Abstraction, Reformulation and Approximation (SARA98), Asilomar Conference Center, Pacific Grove, California (1998)
Drury, S.: A Guide to Remote Sensing. The Kluwer International Series on Information Retrieval, 11, Oxford (1990)
Saitta, L., Zucker, J.D.: A model of abstraction in visual perception. Applied Artificial Intelligence 15 (2001) 761–776
Giordana, A., Saitta, L.: Abstraction: a general framework for learning. In: Working notes of the AAAI Workshop on Automated Generation of Approximations and Abstraction, Boston, MA (1990) 245–256
Sacerdoti, E.: Planning in a hierarchy of abstraction spaces. Artificial Intelligence 5 (1974) 115–135
Chevaleyre, Y., Zucker, J.D.: A framework for learning rules from multiple instance data. In: Proc. European Conference on Machine Learning (ECML2001). (ECML2001)
Steels, L.: The origin of syntax in visually grounded robotic agents. In: Proceedings of IJCAI97, Morgan Kaufman Pub. Los Angeles. (1997)
Beymer, D., Konolige K.: Real-time tracking of multiple people using continous detection. In: Proceedings of the International Conference on Computer Vision (ICCV’99). (1999)
Wang, J.Z.: Integrated Region-based Image Retrieval. The Kluwer International Series on Information Retrieval, 11, Oxford (2001)
Hsieh, I., Fan, K.: Color image retrieval using shape and spatial properties. In: ICPR00, Vol. I: pp 1023–1026. (2000)
Brooks, R.: Intelligence without representation. Artificial Intelligence 47 (1991) 139–159
Marr, D.: Vision. Freeman and Co., Oxford(1982)
Goldstone, R.L.: Perceptual learning. In: Annual Reviews of Psychology. 49:585–612. (1998)
Kohavi, R., John, G.: The wrapper approach. In: Feature Selection for Knowledge Discovery and Data Mining, H. Liu and H. Motoda (eds.), Kluwer Academic Publishers, pp33–50. (1998)
Kohavi, R., Sommerfield, D.: Feature subset selection using the wrapper method: Overfitting and dynamic search space In: International Conference on Knowledge Discovery and Data Mining. (1995)
Giunchiglia, F.: Using abstrips abstractions where do we stand ? Artificial Intelligence Review 13 (1996) 201–213
Rehrmann, V., Priese, L.: Fast and robust segmentation of natural color scenes. In: Asian Conference on Computer Vision, Hongkong, China. (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zucker, JD., Bredeche, N., Saitta, L. (2002). Abstracting Visual Percepts to Learn Concepts. In: Koenig, S., Holte, R.C. (eds) Abstraction, Reformulation, and Approximation. SARA 2002. Lecture Notes in Computer Science(), vol 2371. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45622-8_19
Download citation
DOI: https://doi.org/10.1007/3-540-45622-8_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43941-7
Online ISBN: 978-3-540-45622-3
eBook Packages: Springer Book Archive