| Title: | OS13-1 Object Status Detection in Cluttered Environment for Robot Grasping Using Mask-RCNN |
|---|---|
| Publication: | ICAROB2023 |
| Volume: | 28 |
| Pages: | 297-300 |
| ISSN: | 2188-7829 |
| DOI: | 10.5954/ICAROB.2023.OS13-1 |
| Author(s): | Kasman , Eiji Hayashi |
| Publication Date: | February 9, 2023 |
| Keywords: | object detection, Mask RCNN, cluttered environment |
| Abstract: | Detecting object status in cluttered manipulator's robot environment before grasping is quite challenging to recognize the target because of unstructured and uncertainty scenes. Using Mask R-CNN for detecting the status of the object i.e. free for picking, close, overlapping and piling to the other objects is very useful as computer vision before the manipulator doing next procedures to complete its task. This paper provides a systematic summary and analysis target detecting and recognizing object status using Mask R-CNN. Unlike related solution methods that use machine vision and deep learning directly and combine together for doing robot controlling, pushing and grasping, we are doing image processing separately and simply for detecting the object's status before performing like pushing the object for making free and easy grasping. Experiment with this method shows that it has good accuracy, easy to implement for detecting and classification using the algorithm. |
| PDF File: | https://alife-robotics.co.jp/members2023/icarob/data/html/data/OS/OS13/OS13-1.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/ |
(c)2008 Copyright The Regents of ALife Robotics Corporation Ltd. All Rights Reserved.