Difference between revisions of "Bootstrapping bilinear models of robotic sensorimotor cascades"

From MurrayWiki
Jump to: navigation, search
(htdb2wiki: creating page for 2010o_cm11-icra.html)
 
(htdb2wiki: creating page for 2010g_cm10-wafr.html)
 
Line 1: Line 1:
 
{{HTDB paper
 
{{HTDB paper
| authors = Andrea Censi and Richard M. Murray
+
| authors = Andrea Censi, Richard M Murray
 
| title = Bootstrapping bilinear models of robotic sensorimotor cascades
 
| title = Bootstrapping bilinear models of robotic sensorimotor cascades
| source = 2011 International Conference on Robotics and Automation (ICRA)
+
| source = Workshop on the Algorithmic Foundations of Robotics (WAFR), 2010 (Submitted)
 
| year = 2010
 
| year = 2010
| type = Conference Paper
+
| type = Preprint
| funding = NSF CPS
+
| funding =  
| url = http://www.cds.caltech.edu/~murray/preprints/cm11-icra.pdf
+
| url = http://www.cds.caltech.edu/~murray/preprints/cm10-wafr_s.pdf
| abstract =  
+
| abstract = We consider the bootstrapping problem, which consists in learning a model of the agent's sensors and actuators starting from zero prior informa- tion, and we take the problem of servoing as a cross-modal task to validate the learned models. We study the class of sensors with bilinear dynamics, for which the derivative of the observations is a bilinear form of the control commands and the observations themselves. This class of models is simple, yet general enough to represent the main phenomena of three representative sensors (field sampler, camera, and range-finder), apparently very different from one another. It also allows a bootstrapping algorithm based on Hebbian learning, and a simple bioplausible control strategy. The convergence proper- ties of learning and control are demonstrated with extensive simulations and by analytical arguments.
We consider the bootstrapping problem, which con- sists in learning a model of the agent’s sensors and actuators starting from zero prior information, and we take the problem of servoing as a cross-modal task to validate the learned models. We study the class of sensors with bilinear dynamics, for which the derivative of the observations is a bilinear form of the control commands and the observations themselves. This class of models is simple, yet general enough to represent the main phenomena of three representative sensors (field sampler, camera, and range- finder), apparently very different from one another. It also allows a bootstrapping algorithm based on Hebbian learning, and a sim- ple bioplausible control strategy. The convergence properties of learning and control are demonstrated with extensive simulations and by analytical arguments.
+
 
| flags =  
 
| flags =  
| tag = cm11-icra
+
| tag = cm10-wafr
| id = 2010o
+
| id = 2010g
 
}}
 
}}

Latest revision as of 06:16, 15 May 2016


Andrea Censi, Richard M Murray
Workshop on the Algorithmic Foundations of Robotics (WAFR), 2010 (Submitted)

We consider the bootstrapping problem, which consists in learning a model of the agent's sensors and actuators starting from zero prior informa- tion, and we take the problem of servoing as a cross-modal task to validate the learned models. We study the class of sensors with bilinear dynamics, for which the derivative of the observations is a bilinear form of the control commands and the observations themselves. This class of models is simple, yet general enough to represent the main phenomena of three representative sensors (field sampler, camera, and range-finder), apparently very different from one another. It also allows a bootstrapping algorithm based on Hebbian learning, and a simple bioplausible control strategy. The convergence proper- ties of learning and control are demonstrated with extensive simulations and by analytical arguments.