Multi-object recognition on the basis of vision and manipulation

Kazunori Ohno, Peter Andersson, Zhong Lei, Eijiro Takeuchi, Satoshi Tadokoro

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The authors aim at recognition of multiple objects by using robot vision and its manipulation. In the case where multiple objects are arranged in a shelf, front objects may conceal some objects behind them. A robot can recognize these objects if it can recognize the front objects using prior knowledge and remove them with its arm. However, it sometimes fails to recognize the objects because of the lack of good features, a bad lighting condition etc. Here, we proposed a new method of the multi-object recognition using the manipulation. Recognized objects are removed using pick-up motion. Unrecognized objects are pushed for changing the angle when the robot cannot recognize them. We show the experimental results of our proposed method. From the results, we can confirm that the manipulation is useful for improving the multi-object recognition.

Original languageEnglish
Title of host publication2010 IEEE/SICE International Symposium on System Integration
Subtitle of host publicationSI International 2010 - The 3rd Symposium on System Integration, SII 2010, Proceedings
Pages19-24
Number of pages6
DOIs
Publication statusPublished - 2010
Event3rd International Symposium on System Integration, SII 2010 - Sendai, Japan
Duration: 2010 Dec 212010 Dec 22

Publication series

Name2010 IEEE/SICE International Symposium on System Integration: SI International 2010 - The 3rd Symposium on System Integration, SII 2010, Proceedings

Conference

Conference3rd International Symposium on System Integration, SII 2010
Country/TerritoryJapan
CitySendai
Period10/12/2110/12/22

Fingerprint

Dive into the research topics of 'Multi-object recognition on the basis of vision and manipulation'. Together they form a unique fingerprint.

Cite this