Automatic identification of mechanical parts for robotic disassembly using the PointNet deep neural network. (15th March 2022)

• Record Type: Journal Article
• Authors: Zheng, Senjing; Lan, Feiying; Baronti, Luca; Pham, Duc Truong; Castellani, Marco
• Is Part Of: International journal of manufacturing research. Volume 17:Number 1(2022)
• Page Start: 1
• Page End: 21
• Publication Date: 2022-03-15
• Subjects: remanufacturing -- disassembly -- automotive -- machine vision -- point clouds -- deep neural networks -- DNNs; Manufacturing processes -- Periodicals; Manufacturing processes -- Automation -- Periodicals; Production engineering -- Periodicals; Factory management -- Periodicals; 670.5
• Languages: English
• ISSNs: 1750-0591

Abstract

Identification is the first step towards the manipulation of parts for robotic disassembly and remanufacturing. PointNet is a recently developed deep neural network capable of identifying objects from 3D scenes (point clouds) irrespective of their position and orientation. PointNet was used to recognise 12 instances of components of turbochargers for automotive engines. These instances included different mechanical parts, as well as different models of the same part. Point clouds of partial views of the parts were created from CAD models using a purpose-developed depth-camera simulator, reproducing various levels of sensor imprecision. Experimental evidence indicated PointNet can be consistently trained to recognise with accuracy the objects. In the presence of sensor imprecision, the accuracy in the recall phase can be increased adding stochastic error to the training examples. Training 12 independent classifiers, one for each part, did not yield significant improvements in accuracy compared to using one classifier for all the parts. [Submitted 13 September 2019; Accepted 27 March 2020]