Learning primitive actions through object exploration

The goal of this paper is to investigate how to acquire useful action knowledge by observing the results of exploratory actions on objects. We focus on poking as a representative type of nonprehensile manipulation. Poking can be defined as a short term pushing action. Here we propose an explorative process that allows the robot to learn the relationship between the point of contact on the object boundary and the angle of poke and the actual response of an object. The robot acquires this knowledge without having any prior knowledge about the action. Initially, the robot was only able to move in random directions. Such self emergent processes are essential for the early cognition. The proposed process has been implemented and tested on the humanoid robot Hoap-3.

[1]  Jun Tani,et al.  Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[2]  Kevin M. Lynch,et al.  Stable Pushing: Mechanics, Controllability, and Planning , 1995, Int. J. Robotics Res..

[3]  Tetsuya Ogata,et al.  Predicting Object Dynamics From Visual Images Through Active Sensing Experiences , 2008, Adv. Robotics.

[4]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[5]  Qingguo Li,et al.  Manipulation of Convex Objects via Two-agent Point-contact Push , 2007, Int. J. Robotics Res..

[6]  Giulio Sandini,et al.  Learning about objects through action - initial steps towards artificial cognition , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[7]  Daniel C. Dennett,et al.  Cognitive Wheels: The Frame Problem of AI , 1990, The Philosophy of Artificial Intelligence.