Sensorimotor Models of Space and Object Geometry
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2850-2850.
Abstract
A baby experiencing the world for the first time faces a considerable challenging sorting through what William James called the blooming, buzzing confusion of the senses. With the increasing capacity of modern sensors and the complexity of modern robot bodies, a robot in an unknown or unfamiliar body faces a similar and equally daunting challenge. Addressing this challenge directly by designing robot agents capable of resolving the confusion of sensory experience in an autonomous manner would substantially reduce the engineering required to program robots and the improve the robustness of resulting robot capabilities. Working towards a general solution to this problem, this work uses distinctive state abstractions and sensorimotor embedding to generate basic knowledge of sensor structure, local geometry, and object geometry starting with uninterpreted sensors and effectors.
@inproceedings{ijcai2011p497,
title = {Sensorimotor Models of Space and Object Geometry},
author = {Stober, Jeremy},
booktitle = {Proceedings of the Twenty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-11}},
publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
editor = {Toby Walsh},
pages = {2850--2850},
year = {2011},
month = {7},
doi = {10.5591/978-1-57735-516-8/IJCAI11-497},
url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-497},
}
TY - CPAPER TI - Sensorimotor Models of Space and Object Geometry AU - Stober, Jeremy T2 - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11 PB - AAAI Press/International Joint Conferences on Artificial Intelligence PY - 2011 SP - 2850 EP - 2850 DO - 10.5591/978-1-57735-516-8/IJCAI11-497 UR - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-497 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
