A Curious Vision System for Autonomous and Cumulative Object Learning
We introduce a fully autonomous active vision system that explores its environment and learns visual representations of objects in the scene. The system design is motivated by the fact that infants learn internal representations of the world without much human assistance. Inspired by this, we build a curiosity driven system that is drawn towards locations in the scene that provide the highest potential for learning. In particular, the attention on a stimulus in the scene is related to the improvement in its internal model. This makes the system learn dynamic changes of object appearance in a cumulative fashion. We also introduce a self-correction mechanism in the system that rectifies situations where several distinct models have been learned for the same object or a single model has been learned for adjacent objects. We demonstrate through experiments that the curiosity-driven learning leads to a higher learning speed and improved accuracy.
KeywordsActive vision Unsupervised learning Autonomous vision system Vision for robotics Humanoid robot Icub Object recognition Visual attention Stereo vision Intrinsic motivation
This work was supported by the BMBF Project “Bernstein Fokus: Neurotechnologie Frankfurt, FKZ 01GQ0840” and by the “IM-CLeVeR - Intrinsically Motivated Cumulative Learning Versatile Robots” project, FP7-ICT-IP-231722. We thank Richard Veale, Indiana University for providing the code on saliency.
- 1.Kim, H., Murphy-Chutorian, E., Triesch, J.: Semi-autonomous learning of objects. In: Conference on Computer Vision and Pattern Recognition Workshop, CVPRW ’06, p. 145 (2006)Google Scholar
- 3.Figueira, D., Lopes, M., Ventura, R., Ruesch, J.: From pixels to objects: enabling a spatial model for humanoid social robots. In: IEEE International Conference on Robotics and Automation, ICRA 2009, pp. 3049–3054 (2009)Google Scholar
- 4.Gatsoulis, Y., Burbridge, C., McGinnity, T.: Online unsupervised cumulative learning for life-long robot operation. In: 2011 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 2486–2490 (2011)Google Scholar
- 8.Baldassarre, G.: What are intrinsic motivations? a biological perspective. In: 2011 IEEE International Conference on Development and Learning (ICDL), vol. 2, pp. 1–8 (2011)Google Scholar
- 9.Wang, Q., Chandrashekhariah, P., Spina, G.: Familiarity-to-novelty shift driven by learning: a conceptual and computational model. In: 2011 IEEE International Conference on Development and Learning (ICDL), vol. 2, pp. 1–6 (2011)Google Scholar
- 10.Metta, G., Sandini, G., Vernon, D., Natale, L., Nori, F.: The icub humanoid robot: an open platform for research in embodied cognition. In: Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, PerMIS ’08, pp. 50–56. ACM, New York (2008)Google Scholar
- 12.Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings of Fourth Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
- 14.Jones, J., Palmer, L.: An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. J. Neurophysiol. 58(6), 1233–1258 (1987)Google Scholar
- 16.Murphy-Chutorian, E., Triesch, J.: Shared features for scalable appearance-based object recognition. In: Seventh IEEE Workshops on Application of Computer Vision, WACV/MOTIONS ’05 Volume 1, vol. 1, pp. 16–21 (2005)Google Scholar