TY - JOUR
T1 - Learning tasks from observation and practice
AU - Bentivegna, Darrin C.
AU - Atkeson, Christopher G.
AU - Cheng, Gordon
N1 - Funding Information:
Support for all authors was provided by ATR Computational Neuroscience Laboratories, Department of Humanoid Robotics and Computational Neuroscience, and the Communications Research Laboratory (CRL). It was also supported in part by the National Science Foundation Award IIS-9711770.
PY - 2004/6/30
Y1 - 2004/6/30
N2 - This paper presents a framework that gives robots the ability to initially learn a task behavior from observing others. The framework includes a method for the robots to increase performance while operating in the task environment. We demonstrate this approach applied to air hockey and the marble maze task. Our robots initially learn to perform the tasks using learning from observation, and then increase their performance through practice.
AB - This paper presents a framework that gives robots the ability to initially learn a task behavior from observing others. The framework includes a method for the robots to increase performance while operating in the task environment. We demonstrate this approach applied to air hockey and the marble maze task. Our robots initially learn to perform the tasks using learning from observation, and then increase their performance through practice.
KW - Action recognition
KW - Imitation
KW - Learning from observation
KW - Locally weighted learning
KW - Movement primitives
UR - http://www.scopus.com/inward/record.url?scp=2942511955&partnerID=8YFLogxK
U2 - 10.1016/j.robot.2004.03.010
DO - 10.1016/j.robot.2004.03.010
M3 - Article
AN - SCOPUS:2942511955
SN - 0921-8890
VL - 47
SP - 163
EP - 169
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
IS - 2-3
ER -