Article: Automatic identification of mechanical parts for robotic disassembly using the PointNet deep neural network Journal: International Journal of Manufacturing Research (IJMR) 2022 Vol.17 No.1 pp.1 - 21 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] Inderscience Publishers - linking academia, business and industry through research

Title: Automatic identification of mechanical parts for robotic disassembly using the PointNet deep neural network

Authors: Senjing Zheng; Feiying Lan; Luca Baronti; Duc Truong Pham; Marco Castellani

Addresses: Department of Mechanical Engineering, University of Birmingham, Birmingham, UK ' Department of Mechanical Engineering, University of Birmingham, Birmingham, UK ' School of Computer Science, University of Birmingham, Birmingham, UK ' Department of Mechanical Engineering, University of Birmingham, Birmingham, UK ' Department of Mechanical Engineering, University of Birmingham, Birmingham, UK

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]

Keywords: remanufacturing; disassembly; automotive; machine vision; point clouds; deep neural networks; DNNs.

DOI: 10.1504/IJMR.2022.121591

International Journal of Manufacturing Research, 2022 Vol.17 No.1, pp.1 - 21

Received: 13 Sep 2019
Accepted: 27 Mar 2020
Published online: 21 Mar 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Automatic identification of mechanical parts for robotic disassembly using the PointNet deep neural network

Keep up-to-date