Forward models applied in visual servoing for a reaching task in the iCub humanoid robot
College
Gokongwei College of Engineering
Department/Unit
Manufacturing Engineering and Management
Document Type
Article
Source Title
Applied Bionics and Biomechanics
Volume
6
Issue
3
First Page
345
Last Page
354
Publication Date
2009
Abstract
This paper details the application of a forward model to improve a reaching task. The reaching task must be accomplished by a humanoid robot with 53 degrees of freedom (d.o.f.) and a stereo-vision system. We have explored via simulations a new way of constructing and utilizing a forward model that encodes eye–hand relationships. We constructed a forward model using the data obtained from only a single reaching attempt. ANFIS neural networks are used to construct the forward model, but the forward model is updated online with new information that comes from each reaching attempt. Using the obtained forward model, an initial image Jacobian is estimated and is used with a visual servoing controller. Simulation results demonstrate that errors are lower when the initial image Jacobian is derived from the forward model. This paper is one of the few attempts at applying visual servoing in a complete humanoid robot.
html
Recommended Citation
Gamarra, D. T., Pinpin, L. M., Laschi, C., & Dario, P. (2009). Forward models applied in visual servoing for a reaching task in the iCub humanoid robot. Applied Bionics and Biomechanics, 6 (3), 345-354. Retrieved from https://animorepository.dlsu.edu.ph/faculty_research/12789
Disciplines
Artificial Intelligence and Robotics
Keywords
Androids; Robotics; Neural networks (Computer science); Servomechanisms
Upload File
wf_no