Member Login

Project

Project 4.3: Quality Assurance Framework for Human-Robot Collaborative Manufacturing

PhD researcher

Project based at

UTS

Lead Partner Organisation

Monitoring and automated documentation of outcomes of collaborative robot activity

Start date: January 2023
Expected end date: July 2026

 

The project provides manufacturers with a structured approach to quality control that effectively combines human judgment with cobot capabilities in defect management and rework reduction. This systematic framework helps industries move towards more efficient and reliable quality assurance processes.

Project Overview

This research project develops an innovative quality control framework that optimizes collaboration between humans and collaborative robots (cobots) in manufacturing environments. A key focus is systematic defect detection, categorization, and reduction through intelligent human-robot collaboration.

The framework addresses critical industry challenges in defect management and rework processes by introducing a structured approach to quality control. It implements a comprehensive defect classification system that covers material, dimensional, functional, visual, and packaging defects. By combining human expertise in complex defect assessment with cobot consistency in repetitive inspections, the system enables thorough quality control while reducing rework requirements.

The research delivers a systematic procedure model that guides manufacturers in implementing effective quality control through human-robot collaboration. This includes innovative approaches to defect identification, rework analysis, and waste reduction strategies. The framework emphasizes root cause analysis and preventive measures, enabling manufacturers to not just detect defects but prevent their recurrence.

Industry Impact

  • Comprehensive defect management through optimized human-robot collaboration
  • Systematic approach to defect categorization and analysis
  • Reduced rework through early detection and prevention
  • Efficient root cause analysis and corrective action implementation
  • Enhanced tracking and documentation of quality issues
  • Data-driven quality improvement strategies
  • Waste reduction through optimized quality control processes

Research Significance

This research addresses key manufacturing challenges:

  • Need for systematic defect identification and categorization
  • Reduction of rework and associated costs
  • Integration of human expertise in defect assessment
  • Optimization of inspection processes
  • Development of preventive quality control measures

Innovation Elements

  • Multi-category defect classification system
  • Intelligent task allocation between humans and cobots
  • Rework analysis and reduction protocols
  • Quality control optimization methods
  • Performance monitoring systems

Supervisory Team

Publications

  • Ahamed, M., Sick, N., ‘Integrating human and robot expertise for improved R&D management: A conceptual framework’. R&D Management Workshop 2024.
  • Ahamed, M., Sick, N., Guertler, M., (CIE51, 2024), “”Bridging the gap: Barriers to and requirements for human robot knowledge transfer.

Associated Researchers

Nathalie Sick

Chief Investigator, Research Program Co-lead (Quality Assurance and Compliance)
University of Technology Sydney
View Bio

Lee Clemon

Associate Investigator
University of Technology Sydney / University of Illinois Urbana-Champaign
View Bio

Mariadas Roshan

Postdoctoral Research Fellow, (Quality Assurance and Compliance program)
Swinburne University of Technology
View Bio

Michelle Dunn

Research Program Co-lead (Quality Assurance and Compliance)
Swinburne University of Technology
View Bio

Chris McCarthy

Chief Investigator
Swinburne University of Technology
View Bio