Title:

OS7-2 POMDP-based action planning for the recognition of occluded objects with Humanoid robots

Publication: ICAROB2020
Volume: 25
Pages: 281-284
ISSN: 2188-7829
DOI: 10.5954/ICAROB.2020.OS7-2
Author(s): Masato Tsuru, Pierre Gergondet, Tomohiro Motoda, Adrien Escande, Eiichi Yoshida, Ixchel G. Ramirez-Alpizar, Weiwei Wan, Kensuke Harada
Publication Date: January 13, 2020
Keywords: humanoid robot, POMDP, planning, point cloud, occlusion, 6DoF registration
Abstract: In this paper, we present a high-layer motion planner which plans humanoid robot actions to search for object models in the robot workspace. To overcome the occlusion problem, our proposed method plans to get different perspectives of the object. POMDP (Partially Observable Markov Decision Process) is used to determine the observation pose of a robot. The planner then builds a comprehensive point cloud of by merging the point clouds gathered from different positions. The point cloud is compared to a 3D model of the object to estimate the pose of the real object.
PDF File: https://alife-robotics.co.jp/members2020/icarob/data/html/data/OS/OS7/OS7-2.pdf
Copyright: © The authors.
This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
See for details: https://creativecommons.org/licenses/by-nc/4.0/

ALife Robotics Corporation Ltd.

HOME

 

 

(c)2008 Copyright The Regents of ALife Robotics Corporation Ltd. All Rights Reserved.