AUTOMATED PACKING SYSTEMS - A SYSTEMS-ENGINEERING APPROACH

Citation
Pf. Whelan et Bg. Batchelor, AUTOMATED PACKING SYSTEMS - A SYSTEMS-ENGINEERING APPROACH, IEEE transactions on systems, man and cybernetics. Part A. Systems and humans, 26(5), 1996, pp. 533-544
Citations number
75
Categorie Soggetti
System Science",Ergonomics,"Computer Science Cybernetics
ISSN journal
10834427
Volume
26
Issue
5
Year of publication
1996
Pages
533 - 544
Database
ISI
SICI code
1083-4427(1996)26:5<533:APS-AS>2.0.ZU;2-L
Abstract
The ability to manipulate previously unseen objects under visual contr ol is one of the key tasks in the successful implementation of robotic , automated assembly and adaptive material handling systems, The autom ation of such complex industrial environments will require the develop ment of machine vision systems that are highly adaptable and capable o f dealing with a wide range of variable products. An important group o f applications of this type is found in the automated packing and nest ing of arbitrary shapes, The aim of this work has been to produce an e fficient packing strategy that is flexible enough for a wide variety o f industrial uses and which can be implemented using fast moderately p riced hardware, A systems approach, as distinct from a purely algorith mic one, has been deliberately adopted since the work is concerned wit h industrial vision applications in which significant problem constrai nts exist, This paper also outlines the background to this research, a nd reviews a selection of industrial packing applications. The packing procedure that has been devised, consists of two major components, Th e first is a geometric packing technique that is based on morphologica l image processing operations, This is used in conjunction with a Prol og based heuristic packing procedure. Some of the factors considered a t the heuristic level include shape ordering and shape orientation, bo th of which must be carried out prior to the implementation of the geo metric packer. The heuristic procedures deal with problem constraints that are specific to a given application.