Intelligent computing for demonstration-based robot learning

Robot learning is an efficient strategy to achieve control task without explicit programming. In this work, we present a learning framework in which the robot is taught how to perform desired behaviors through a demonstration procedure. During the demonstration, the behavior sequences are recorded and transferred to time series data, and intelligent computing methods are proposed to learn the behaviors from the data. To assess the performance of the proposed framework, different sets of experiments have been conducted and the results show that our framework can be used to learn robot behaviors efficiently and successfully.

[1]  Thomas R. Zentall,et al.  Imitation: definitions, evidence, and mechanisms , 2006, Animal Cognition.

[2]  G. Rizzolatti,et al.  The mirror-neuron system. , 2004, Annual review of neuroscience.

[3]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[4]  Sebastian Thrun,et al.  Toward a Framework for Human-Robot Interaction , 2004, Hum. Comput. Interact..

[5]  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).

[6]  Magdalena D. Bugajska,et al.  Building a Multimodal Human-Robot Interface , 2001, IEEE Intell. Syst..

[7]  Toshiharu Taura,et al.  A Study on Acquiring Underlying Behavioral Criteria for Manipulator Motion by Focusing on Learning Efficiency , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[8]  J. Vohradský.  Neural network model of gene expression , 2001, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[9]  Atsushi Nakazawa,et al.  Learning from Observation Paradigm: Leg Task Models for Enabling a Biped Humanoid Robot to Imitate Human Dances , 2007, Int. J. Robotics Res..

[10]  Rajesh P. N. Rao,et al.  Robotic imitation from human motion capture using Gaussian processes , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[11]  Auke Jan Ijspeert,et al.  Central pattern generators for locomotion control in animals and robots: A review , 2008, Neural Networks.

[12]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[13]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[14]  Helge J. Ritter,et al.  Situated robot learning for multi-modal instruction and imitation of grasping , 2004, Robotics Auton. Syst..