VERIFICATION AND VALIDATION OF CAMERA-BASED ROBOTIC INSPECTION SYSTEM WITH CAMERA FAULT INJECTION TOOL

Alim Kerem Erdoğmuş; Uğur Yayan

Article Details

VERIFICATION AND VALIDATION OF CAMERA-BASED ROBOTIC INSPECTION SYSTEM WITH CAMERA FAULT INJECTION TOOL

Authors:

Alim Kerem Erdoğmuş | Uğur Yayan

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 1, pp.1159-1168

Document Type:

Article

Publication Date:

4/2024

Document Language:

Turkish

Document ID (Org No.):

2001315502

pISSN:

2630-5712

Keywords:

Abstract:

 Nowadays, camera-based robotic inspection systems have gained popularity with the developing image processing techniques. Such systems are used extensively in many sectors from food to military. The verification and validation processes required during the development of these systems are quite long and costly. This study was developed to perform and improve verification and validation activities on camera-based industrial robotic systems. The tests and results are explained with the Camera Fault Injection Tool CamFITool, which enables the use of different types of fault injection methods Open, Close, Dilation, Erosion, Gradient, Motionblur, Salt  Pepper, Gaussian and Poisson to RGB and TOF cameras. Within the scope of the VALU3S project, the study focussed on OTOKARs ROKOS robotic system by injecting faults in various configurations into libraries consisting of camera images taken from the real environment with CamFITool and analysing the effects of this injection on the system. In this context, fault injection was performed in 49 different test configurations. As a result, CamFITool, an open-source fault injection tool that tests the fault tolerance of camera-based industrial robotic systems, is proposed to ensure safer and more stable operation of these systems.

 Nowadays, camera-based robotic inspection systems have gained popularity with the developing image processing techniques. Such systems are used extensively in many sectors from food to military. The verification and validation processes required during the development of these systems are quite long and costly. This study was developed to perform and improve verification and validation activities on camera-based industrial robotic systems. The tests and results are explained with the Camera Fault Injection Tool CamFITool, which enables the use of different types of fault injection methods Open, Close, Dilation, Erosion, Gradient, Motionblur, Salt  Pepper, Gaussian and Poisson to RGB and TOF cameras. Within the scope of the VALU3S project, the study focussed on OTOKARs ROKOS robotic system by injecting faults in various configurations into libraries consisting of camera images taken from the real environment with CamFITool and analysing the effects of this injection on the system. In this context, fault injection was performed in 49 different test configurations. As a result, CamFITool, an open-source fault injection tool that tests the fault tolerance of camera-based industrial robotic systems, is proposed to ensure safer and more stable operation of these systems.

 Nowadays, camera-based robotic inspection systems have gained popularity with the developing image processing techniques. Such systems are used extensively in many sectors from food to military. The verification and validation processes required during the development of these systems are quite long and costly. This study was developed to perform and improve verification and validation activities on camera-based industrial robotic systems. The tests and results are explained with the Camera Fault Injection Tool CamFITool, which enables the use of different types of fault injection methods Open, Close, Dilation, Erosion, Gradient, Motionblur, Salt  Pepper, Gaussian and Poisson to RGB and TOF cameras. Within the scope of the VALU3S project, the study focussed on OTOKARs ROKOS robotic system by injecting faults in various configurations into libraries consisting of camera images taken from the real environment with CamFITool and analysing the effects of this injection on the system. In this context, fault injection was performed in 49 different test configurations. As a result, CamFITool, an open-source fault injection tool that tests the fault tolerance of camera-based industrial robotic systems, is proposed to ensure safer and more stable operation of these systems.

 Günümüzde, gelişen görüntü işleme teknikleri ile birlikte kamera tabanlı robotik inceleme sistemleri oldukça popülerlik kazanmıştır. Bu tür sistemler gıdadan, askeriyeye birçok sektörde yoğun olarak kullanılmaktadır. Bu sistemler geliştirilirken gerekli olan doğrulama ve onaylama süreçleri oldukça uzun ve maliyetli olmaktadır. Bu çalışma, kamera tabanlı endüstriyel robotik sistemler üzerinde doğrulama ve onaylama faaliyetlerini gerçekleştirmek ve iyileştirmek amacıyla geliştirilmiştir. RGB ve TOF kameralara farklı türlerde Open, Close, Dilation, Erosion, Gradient, Motionblur, TuzBiber, Gaussian ve Poisson hata enjeksiyon yöntemleri kullanılmasını mümkün Kamera Hata Enjeksiyon Aracı CamFITool ile gerçekleştirilmiş testler ve sonuçlar açıklanmıştır. Yapılan çalışma, VALU3S projesi kapsamında, OTOKARın ROKOS robotik sistemine, CamFITool ile gerçek ortamdan alınmış kamera görüntülerinden oluşan kitaplıklara, çeşitli konfigürasyonlarda hatalar enjekte edilip, bu enjeksiyonun sisteme etkilerinin incelenmesine odaklanmıştır. Bu kapsamda 49 farklı test komfigürasyonunda hata enjeksiyonu gerçekleştirilmiştir. Sonuç olarak, kamera tabanlı endüstriyel robotik sistemlerin daha güvenli ve stabil çalışmalarının sağlanması için, bu sistemlerin hataya dayanıklı olup olmadıklarını test eden açık kaynaklı bir hata enjeksiyon aracı olan CamFITool önerilmiştir.

Article Details

VERIFICATION AND VALIDATION OF CAMERA-BASED ROBOTIC INSPECTION SYSTEM WITH CAMERA FAULT INJECTION TOOL

Authors:

Alim Kerem Erdoğmuş | Uğur Yayan

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 1, pp.1159-1168

Document Type:

Article

Publication Date:

4/2024

Document Language:

Turkish

Document ID (Org No.):

2001315502

pISSN:

2630-5712

Robotics

Verification&Validation

Fault injection

Robot operating system

Camera-based perceptionRobotik

Doğrulama&Onaylama

Hata enjeksiyonu

Robot işletim sistemi

Kamera-tabanlı görü

Issues

Article Details

Authors: Alim Kerem Erdoğmuş | Uğur Yayan

Publisher: Eskişehir Osmangazi University

Main Topics: Bilgisayar Yazılımı

Journal: Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 1, pp.1159-1168

Document Type: Article

Publication Date: 4/2024

Document Language: Turkish

Document ID (Org No.): 2001315502

pISSN: 2630-5712

Issues

Authors:

Alim Kerem Erdoğmuş | Uğur Yayan

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.32 Issue 1, pp.1159-1168

Document Type:

Article

Publication Date:

4/2024

Document Language:

Turkish

Document ID (Org No.):

2001315502

pISSN:

2630-5712