Developmental action perception for manipulative interaction

The paper describes a developmental framework of action-driven perception in anthropomorphic robots. The key idea of the framework is that action develops the agent's perception of the own body and its action. In this framework, a robot voluntarily generates movements, and then develops the ability to perceive its own body and the effects of action primitives. The robot, moreover, demonstrates manipulative actions composed of the learned primitives, and characterizes the actions based on their sensory effects. After learning, the robot can predictively recognize humans' manipulative actions with cross-modal recovery of unavailable sensory information and reproduce the recognized actions. We evaluated the proposed framework in experiments with a real robot. In the experiments, we achieved developmental recognition of human actions as well as their reproduction.

[1]  E. Reed.  The Ecological Approach to Visual Perception , 1989 .

[2]  A. Needham,et al.  Shared challenges in object perception for robots and infants , 2008 .

[3]  G. Rizzolatti,et al.  Parietal Lobe: From Action Organization to Intention Understanding , 2005, Science.

[4]  Michael I. Jordan,et al.  An internal model for sensorimotor integration. , 1995, Science.

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

[6]  Emre Ugur,et al.  Goal emulation and planning in perceptual space using learned affordances , 2011, Robotics Auton. Syst..

[7]  Barbara Caputo,et al.  Using Object Affordances to Improve Object Recognition , 2011, IEEE Transactions on Autonomous Mental Development.

[8]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[9]  Jivko Sinapov,et al.  A Behavior-Grounded Approach to Forming Object Categories: Separating Containers From Noncontainers , 2012, IEEE Transactions on Autonomous Mental Development.

[10]  Lorenzo Natale,et al.  Linking Action to Perception in a Humanoid Robot: a Developmental Approach to Grasping , 2004 .

[11]  Michael A. Arbib,et al.  Schema design and implementation of the grasp-related mirror neuron system , 2002, Biological Cybernetics.

[12]  Giulio Sandini,et al.  Body Definition Based on Visuomotor Correlation , 2012, IEEE Transactions on Industrial Electronics.

[13]  G. Rizzolatti,et al.  Premotor cortex and the recognition of motor actions. , 1996, Brain research. Cognitive brain research.

[14]  G. Rizzolatti,et al.  Action recognition in the premotor cortex. , 1996, Brain : a journal of neurology.

[15]  Manuel Lopes,et al.  Learning Object Affordances: From Sensory--Motor Coordination to Imitation , 2008, IEEE Transactions on Robotics.

[16]  Michael A. Arbib,et al.  Mirror neurons and imitation: A computationally guided review , 2006, Neural Networks.

[17]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[18]  G. Sandini,et al.  Understanding mirror neurons. , 2006 .

[19]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[20]  Giorgio Metta,et al.  Grounding vision through experimental manipulation , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[21]  G. Metta,et al.  Action learning based on developmental body perception , 2013, 2013 IEEE International Conference on Industrial Technology (ICIT).

[22]  Mitsuo Kawato,et al.  Internal models for motor control and trajectory planning , 1999, Current Opinion in Neurobiology.

[23]  Masaki Tomonaga,et al.  The perception of self-agency in chimpanzees (Pan troglodytes) , 2011, Proceedings of the Royal Society B: Biological Sciences.