Incremental supervised learning for mobile robot reactive control Export

@article{citeulike:2160392, abstract = {Reactive control for a mobile robot can be defined as a mapping from a perceptual space to a command space. This mapping can be hard-coded by the user (potential fields, fuzzy logic), and can also be learnt. This paper is concerned with supervised learning for perception to action mapping for a mobile robot. Among the existing neural approaches for supervised learning of a function, we have selected the grow and learn network for its properties adapted to robotic problems: incrementality and flexible structure. We will present the results we have obtained with this network using first raw sensor data and then pre-processed measures with the automatic construction of virtual sensors.}, author = {Reignier, Patrick and Hansen, Volker and Crowley, James L.}, booktitle = {Robotics and Autonomous Systems}, citeulike-article-id = {2160392}, citeulike-linkout-0 = {http://www.ingentaconnect.com/content/els/09218890/1997/00000019/00000003/art00054}, journal = {Intelligent Robotic Systems SIRS'95}, month = {March}, number = {3-4}, pages = {247--257}, posted-at = {2007-12-23 01:55:53}, priority = {2}, title = {Incremental supervised learning for mobile robot reactive control}, url = {http://www.ingentaconnect.com/content/els/09218890/1997/00000019/00000003/art00054}, volume = {19}, year = {1997} }

TY - JOUR ID - citeulike:2160392 L3 - citeulike-article-id:2160392 N2 - Reactive control for a mobile robot can be defined as a mapping from a perceptual space to a command space. This mapping can be hard-coded by the user (potential fields, fuzzy logic), and can also be learnt. This paper is concerned with supervised learning for perception to action mapping for a mobile robot. Among the existing neural approaches for supervised learning of a function, we have selected the grow and learn network for its properties adapted to robotic problems: incrementality and flexible structure. We will present the results we have obtained with this network using first raw sensor data and then pre-processed measures with the automatic construction of virtual sensors. IS - 3-4 JF - Intelligent Robotic Systems SIRS'95 EP - 257 TI - Incremental supervised learning for mobile robot reactive control VL - 19 T2 - Robotics and Autonomous Systems SP - 247 AU - Reignier, Patrick AU - Hansen, Volker AU - Crowley, James PY - 1997/03// UR - http://www.ingentaconnect.com/content/els/09218890/1997/00000019/00000003/art00054 ER -