Abstract
In aiming for advanced robotic systems that autonomously and permanently readapt to changing and uncertain environments, we introduce a scheme of fast learning and readaptation of robotic sensorimotor mappings based on biological mechanisms underpinning the development and maintenance of accurate human reaching. The study presents a range of experiments, using two distinct computational architectures, on both learning and realignment of robotic hand–eye coordination. Analysis of the results provide insights into the putative parameters and mechanisms required for fast readaptation and generalization from both a robotic and biological perspective.
Similar content being viewed by others
References
Aslin RN, Salapatek P. Saccadic localization of visual targets by very young human infant. Percept Psychophys. 1975;17:293–302.
Bedford FL. Keeping perception accurate. Trends Cogn Sci. 1999;3:4–11.
Berthier NE, Keen R. Development of reaching in infancy. Exp Brain Res. 2006;169:507–18.
Buneo CA, Jarvis MR, Batista AP, Andersen RA. Direct visuomotor transformations for reaching. Nature. 2002;416:632–6.
Chao F, Lee MH, Lee JJ. A developmental algorithm for oculomotor coordination. Edinburgh: TAROS. 2008. p. 72–8.
Clifton RK, Muir DW, Ashmead DH, Clarkson MG. Is visually guided reaching in early infancy a myth. Child Dev. 1993;64:1099–110
Fraiberg S, Siegel BL, Gibson R. The role of sound in the search behavior of a blind infant. Psychoanal Study Child. 1966;21:327–57.
Guerin F, McKenzie D. A piagetian model of early sensrimotor development.Brighton. UK Epigenetic: Robotics; 2008.
Hoffmann H, Schenk W, Möller R. Learning visuomotor transformations for gaze-control and grasping. Biol Cybern. 2005;93:119130.
Hülse M, McBride S, Lee M. Robotic hand–eye coordination without global reference: a biologically inspired learning scheme. In: Proc. Int. Conf. on Developmental Learning, ICDL 2009, Shanghai, China; 2009
Lee MH, Meng Q, Chao F. Developmental learning for autonomous robots. Rob Auton Syst. 2007; 55(9):750–9
Redding GM, Wallace B. Generalization of prism adaptation. J Exp Psychol Hum Percept Perform. 2006;32:1006–22
Robinson SR, Kleven GA. Learning to move before birth. In: Hopkins B, Johnson SP, editors. Prenatal development of postnatal functions. Westport: Praeger Publishers. p. 131–75
Spencer JP, Clearfield M, Corbetta D, Ulrich B, Buchanan P, Schöner G. Moving toward a grand theory of development: in memory of Esther Thelen. Child Dev. 2006;77:1521–38
Thelen E, Corbetta D, Kamm K, Spencer JP, Schneider K, Zernicke RF. The transition to reaching-mapping intention and intrinsic dynamics. Child Dev. 1993;64:1058–98
Von Hofsten C. Developmental changes in the organization of prereaching movements. Devl Psychol. 1984;20:378–88
Wallace MT (2003) Cross-modal neural development. In: Quinlan PT, editors. Connectionist models of development. Guildford: Biddles Ltd. p. 312–43
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by EU-FP7 projects IM-CLeVeR and ROSSI and by EPSRC, UK through grant EP/C516303/1.
Appendices
Appendix 1: Uncertainty of the Active Vision System
In order to evaluate these results in relation to the uncertainty of the active vision system, the average tilt–verge values for specific object locations were also derived (Table 7). One can see that the vision system has a uncertainty of ≈0.002 rad in average for tilt and verge motors. The complete vision domain, however, is approximately 0.2 rad3. Therefore, out of 2.5 × 107 distinguishable samples in the vision space, our method requires only 300 examples to achieve the given performance in robotic hand–eye coordination.
Appendix 2: Approximation of \({\mathcal{S}}\) in \(A_{\mathcal{S}}\)
The parameters for approximating the shifts in visual space via quadratic and linear regression as well as the simple mean value are summarized in Table 8. The quadratic functions provide the best match, which are plotted in Fig. 14 overlaid by the actual offset values derived from the mappings \({\mathcal{R}}_C\) and \({\mathcal{R}}_S\)
Rights and permissions
About this article
Cite this article
Hülse, M., McBride, S. & Lee, M. Fast Learning Mapping Schemes for Robotic Hand–Eye Coordination. Cogn Comput 2, 1–16 (2010). https://doi.org/10.1007/s12559-009-9030-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-009-9030-y