Active learning of probabilistic forward models in visuo-motor development

Forward models enable both robots and humans to predict the sensory consequences of their motor actions. To learn its own forward models a robot needs to experiment with its own motor system, in the same way that human infants need to babble as a part of their motor development. In this paper we investigate how this babbling with the motor system can be influenced by the forward models’ own knowledge of their predictive ability. By spending more time babbling in regions of motor space that require more accuracy in the forward model, the learning time can be reduced. The key to guiding this exploration is the use of probabilistic forward models, which are capable of learning and predicting not just the sensory consequence of a motor command, but also an estimate of how accurate this prediction is. An experiment was carried out to test this theory on a robotic pan tilt camera.

[1]  Yiannis Demiris,et al.  Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition , 2005, IJCAI.

[2]  D. Wolpert,et al.  Motor prediction , 2001, Current Biology.

[3]  A. Meltzoff,et al.  Explaining Facial Imitation: A Theoretical Model. , 1997, Early development & parenting.

[4]  K. Doya,et al.  A unifying computational framework for motor control and social interaction. , 2003, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[5]  Yiannis Demiris,et al.  Hierarchical attentive multiple models for execution and recognition of actions , 2006, Robotics Auton. Syst..

[6]  Hod Lipson,et al.  AN EXPLORATION-ESTIMATION ALGORITHM FOR SYNTHESIS AND ANALYSIS OF ENGINEERING SYSTEMS USING MINIMAL PHYSICAL TESTING , 2004, DAC 2004.

[7]  Yiannis Demiris,et al.  Distributed, predictive perception of actions: a biologically inspired robotics architecture for imitation and learning , 2003, Connect. Sci..

[8]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[9]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[10]  Gary R. Bradski,et al.  Real time face and object tracking as a component of a perceptual user interface , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[11]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[12]  M. Hasenjäger,et al.  Active learning in neural networks , 2002 .

[13]  Holger Schoener,et al.  Active Learning with Neural Networks , 2007 .

[14]  Pierre-Yves Oudeyer,et al.  The Playground Experiment: Task-Independent Development of a Curious Robot , 2005 .

[15]  Yiannis Demiris,et al.  Learning Forward Models for Robots , 2005, IJCAI.

[16]  David M. Sobel,et al.  A theory of causal learning in children: causal maps and Bayes nets. , 2004, Psychological review.

[17]  Daphne Koller,et al.  Active Learning for Parameter Estimation in Bayesian Networks , 2000, NIPS.