Open AccessViewpoint Planning for Object Identification Using Visual Experience According to Long-Term Activity
Author(s) -
Kimitoshi Yamazaki,
Kazuki Nogami,
Kotaro Nagahama
Publication year - 2022
Publication title -
international journal of automation technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.513
H-Index - 18
eISSN - 1883-8022
pISSN - 1881-7629
DOI - 10.20965/ijat.2022.p0197
Subject(s) - identification (biology) , object (grammar) , orientation (vector space) , computer science , selection (genetic algorithm) , artificial intelligence , term (time) , computer vision , motion planning , robot , mathematics , botany , geometry , physics , quantum mechanics , biology
In this paper, we propose a viewpoint planning method for object identification. We introduce the policy of maximizing the posterior probability of the orientation of an object observed after a robot moves its viewpoint and show a novel formulation of viewpoint planning. In addition, we propose criteria for viewpoint selection based on past sensing experience. Finally, we confirm the effectiveness of the proposed method via simulations using a mobile manipulator.