TY - GEN
T1 - Applying intrinsic motivation for visuomotor learning of robot arm motion
AU - Nishide, Shun
AU - Nobuta, Harumitsu
AU - Okuno, Hiroshi G.
AU - Ogata, Tetsuya
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014
Y1 - 2014
N2 - In this paper, we present a method to apply intrinsic motivation for improving visuomotor learning of robot's arm with external object in view. Multiple Timescales Recurrent Neural Network (MTRNN) is utilized for learning the robot arm/external object dynamics. Training of MTRNN is done using the Back Propagation Through Time (BPTT) algorithm. BPTT algorithm is modified as follows. 1. Evaluate predictability of robot arm/objects using training error of MTRNN. 2. Assign a preference ratio to each object based on predictability. The preference ratio represents the weight of each object to training. Experiments were conducted using an actual robot moving the arm while a human moves his arm in the robot's camera view. The result of the experiment showed that the proposed method presents better training result of robot arm visuomotor dynamics compared to general training with BPTT.
AB - In this paper, we present a method to apply intrinsic motivation for improving visuomotor learning of robot's arm with external object in view. Multiple Timescales Recurrent Neural Network (MTRNN) is utilized for learning the robot arm/external object dynamics. Training of MTRNN is done using the Back Propagation Through Time (BPTT) algorithm. BPTT algorithm is modified as follows. 1. Evaluate predictability of robot arm/objects using training error of MTRNN. 2. Assign a preference ratio to each object based on predictability. The preference ratio represents the weight of each object to training. Experiments were conducted using an actual robot moving the arm while a human moves his arm in the robot's camera view. The result of the experiment showed that the proposed method presents better training result of robot arm visuomotor dynamics compared to general training with BPTT.
KW - Cognitive Developmental Robotics
KW - Intrinsic Motivation
KW - Recurrent Neural Network
UR - http://www.scopus.com/inward/record.url?scp=84988239793&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84988239793&partnerID=8YFLogxK
U2 - 10.1109/URAI.2014.7057370
DO - 10.1109/URAI.2014.7057370
M3 - Conference contribution
AN - SCOPUS:84988239793
T3 - 2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014
SP - 364
EP - 367
BT - 2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014
Y2 - 12 November 2014 through 15 November 2014
ER -