Painted vision and robot planning

Author

Andreae, John H.

Author_Institution

Dept. of Electr. & Electron. Eng., Canterbury Univ., Christchurch, New Zealand

fYear

1994

fDate

29 Nov-2 Dec 1994

Firstpage

387

Lastpage

391

Abstract

Learning to cooperate in a bunpie microworld of 3×3 squares, each of two robots (robot A makes pies and consumes buns, while robot B makes buns and consumes pies) is rewarded if it sees the other robot “smile” (it “smiles” when it makes or consumes food). To help the robots predict and make plans in this world, their vision is augmented by a spatially structured, short-term memory of what they have seen during the past few steps. This “painted vision” is an economical, domain-specific way to improve prediction, and it is suggested that it is a step towards providing robots with that sense of “being in the world”, which we enjoy

Keywords

cellular automata; cognitive systems; intelligent control; planning (artificial intelligence); prediction theory; robots; cooperation; learning; microworld; painted vision; prediction; reward; robot planning; sense of being; spatially structured short-term memory; squares; Animals; Economic forecasting; Eyes; Head; Layout; Orbital robotics; Painting; Retina; Robot sensing systems; Robot vision systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on

Conference_Location

Brisbane, Qld.

Print_ISBN

0-7803-2404-8

Type

conf

DOI

10.1109/ANZIIS.1994.396994

Filename

396994