Model-based and model-free reinforcement learning for visual servoing

To address the difficulty of designing a controller for complex visual-servoing tasks, two learning-based uncalibrated approaches are introduced. The first method starts by building an estimated model for the visual-motor forward kinematic of the vision-robot system by a locally linear regression me...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE International Conference on Robotics and Automation pp. 2917 - 2924
Main Authors Farahmand, A.M., Shademan, A., Jagersand, M., Szepesvari, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2009
Subjects
Calibration
Cameras
Control systems
Jacobian matrices
Kinematics
Learning
Linear regression
Manipulators
Robot vision systems
Visual servoing
Online AccessGet full text
ISBN1424427886
9781424427888
ISSN1050-4729
DOI10.1109/ROBOT.2009.5152834

Cover

More Information
Summary:To address the difficulty of designing a controller for complex visual-servoing tasks, two learning-based uncalibrated approaches are introduced. The first method starts by building an estimated model for the visual-motor forward kinematic of the vision-robot system by a locally linear regression method. Afterwards, it uses a reinforcement learning method named Regularized Fitted Q-Iteration to find a controller (i.e. policy) for the system (model-based RL). The second method directly uses samples coming from the robot without building any intermediate model (model-free RL). The simulation results show that both methods perform comparably well despite not having any a priori knowledge about the robot.
ISBN:1424427886
9781424427888
ISSN:1050-4729
DOI:10.1109/ROBOT.2009.5152834