Summary
International Conference on Machine Vision Applications
2023
Session Number:P1
Session:
Number:P1-05
Safe height estimation of deformable objects for picking robots by detecting multiple potential contact points
Yang Jaesung, Hagihara Daisuke, Ito Kiyoto, Chihara Nobuhiro,
pp.-
Publication Date:2023/07/23
Online ISSN:2188-5079
DOI:10.34385/proc.78.P1-05
PDF download
Summary:
Object sorting in logistics warehouses is still carried out manually, and there is a great need for automation with arm robots. It is desirable that target objects be carefully placed in situations where careful handling of products is important. We propose a method for esti-mating the height of picked object with a single depth camera to achieve precise placing of items such as stacking, espe-cially for objects that are deformable, e.g., bags. The proposed method detects multiple potential contact points of a picked object to estimate the appropriate height to place the object using the point-cloud differ-ence before and after picking. The validity of the pro-posed method was verified using 26 cases in which de-formable objects were placed inside a container, and it was confirmed that object-height estimation is possible with an average error of 3.2 mm.