Sparse incremental learning for interactive robot control policy estimation

• Published in: 2008 IEEE International Conference on Robotics and Automation pp. 3315 - 3320
• Main Authors: Grollman, D.H., Jenkins, O.C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2008
• Subjects: Educational robots; Function approximation; Gaussian processes; Ground penetrating radar; Human robot interaction; Machine learning algorithms; Robot control; Robot programming; Robot sensing systems; Robotics and automation
• ISBN: 1424416469; 9781424416462
• ISSN: 1050-4729
• DOI: 10.1109/ROBOT.2008.4543716

We are interested in transferring control policies for arbitrary tasks from a human to a robot. Using interactive demonstration via teleoperation as our transfer scenario, we cast learning as statistical regression over sensor-actuator data pairs. Our desire for interactive learning necessitates algorithms that are incremental and realtime. We examine locally weighted projection regression, a popular robotic learning algorithm, and sparse online Gaussian processes in this domain on one synthetic and several robot-generated data sets. We evaluate each algorithm in terms of function approximation, learned task performance, and scalability to large data sets.