Primitive Manipulation Learning with Connectionism
Abstract
Infants' manipulative exploratory behavior within the environment is a vehicle of cognitive stimulation[McCall 1974]. During this time, infants practice and perfect sensorimotor patterns that become be(cid:173) havioral modules which will be seriated and imbedded in more com(cid:173) plex actions. This paper explores the development of such primitive learning systems using an embodied light-weight hand which will be used for a humanoid being developed at the MIT Artificial In(cid:173) telligence Laboratory[Brooks and Stein 1993]. Primitive grasping procedures are learned from sensory inputs using a connectionist reinforcement algorithm while two submodules preprocess sensory data to recognize the hardness of objects and detect shear using competitive learning and back-propagation algorithm strategies, respectively. This system is not only consistent and quick dur(cid:173) ing the initial learning stage, but also adaptable to new situations after training is completed.
Cite
Text
Matsuoka. "Primitive Manipulation Learning with Connectionism." Neural Information Processing Systems, 1995.Markdown
[Matsuoka. "Primitive Manipulation Learning with Connectionism." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/matsuoka1995neurips-primitive/)BibTeX
@inproceedings{matsuoka1995neurips-primitive,
title = {{Primitive Manipulation Learning with Connectionism}},
author = {Matsuoka, Yoky},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {889-895},
url = {https://mlanthology.org/neurips/1995/matsuoka1995neurips-primitive/}
}