A comparison of learning strategies for biologically constrained development of gaze control on an iCub robot
- 836 Downloads
Gaze control requires the coordination of movements of both eyes and head to fixate on a target. We present a biologically constrained architecture for gaze control and show how the relationships between the coupled sensorimotor systems can be learnt autonomously from scratch, allowing for adaptation as the system grows or changes. Infant studies suggest developmental learning strategies, which can be applied to sensorimotor learning in humanoid robots. We examine two strategies (sequential and synchronous) for the learning of eye and head coupled mappings, and give results from implementations on an iCub robot. The results show that the developmental approach can give fast, cumulative, on-line learning of coupled sensorimotor systems.
KeywordsDevelopmental robotics Gaze control Sensorimotor learning Eye-head coordination Humanoid robotics
This research has received funds from the European Community 7th Framework Programme (FP7/2007-2013), “Challenge 2—Cognitive Systems, Interaction, Robotics”, Grant Agreement No. ICT-IP-231722, project “IM-CLeVeR—Intrinsically Motivated Cumulative Learning Versatile Robots”.
- Angulo-Kinzler, R. M., Ulrich, B., & Thelen, E. (2002). Three-month-old infants can select specific leg motor solutions. Motor Control, 6(1), 52–68.Google Scholar
- Gallahue, D. L. (1982). Understanding motor development in children. New York: Wiley.Google Scholar
- Hülse, M., & Lee, M. (2010). Adaptation of coupled sensorimotor mappings: An investigation towards developmental learning of humanoids. In S. Doncieux (Ed.), SAB 2010, LNAI 6226 (pp. 468–477). Springer.Google Scholar
- Law, J., Lee, M., & Huelse, M. (2010). Infant development sequences for shaping sensorimotor learning in humanoid robots. In Proceedings of the 10th international conference on epigenetic robotics (pp 65–72)Google Scholar
- Metta, G., Sandini, G., Vernon, D., Natale, L., & Nori, F. (2008). The icub humanoid robot: An open platform for research in embodied cognition. In Proceedings of the 8th workshop on performance metrics for intelligent systems (pp. 50–56). Washington, DC: ACM.Google Scholar
- Piaget, J. (1973). The child’s conception of the world. London: Paladin.Google Scholar
- Wang, X., & Jin, J. (2001). A quantitive analysis for decomposing visual signal of the gaze displacement. In D. D. Feng, J. Jin, P. Eades, & H. Yan (Eds.), Proceedings of the Pan-Sydney area workshop on visual information processing—Volume 11 (VIP ’01) (Vol. 11, pp. 153–159). Darlinghurst, Australia: Australian Computer Society Inc.Google Scholar