Research output: Thesis › Doctoral Thesis
Research output: Thesis › Doctoral Thesis
}
TY - BOOK
T1 - Optimising Brazing Processes through Learning-Based Visual Servoing and Collaborative Robotics
AU - Fei, Haolin
PY - 2024
Y1 - 2024
N2 - In manufacturing safety-critical components, brazing stands out for itsability to form strong, cost-efficient joints between dissimilar materials.Despite its importance, the brazing process often falls short in efficiencyand precision due to its reliance on manual labour. Simultaneously,full automation, while enhancing certain operational aspects, lacks theadaptability and decision-making prowess inherent to human operators.This thesis addresses these challenges within the brazing process byadvocating for a synergistic integration of robotics and artificial intelligence(AI) in a human-robot collaboration (HRC) framework. It uniquelycombines human expertise with advanced machine capabilities, aiming torefine brazing operations beyond the reach of solely human or automatedendeavours.Central to the thesis is the development of a category-agnostic objectlocalisation strategy. This technique enables robots to recognise andposition brazing filler metal (BFM) across a diverse array of joint configurations without prior specific knowledge of the objects. By leveraging AIdriven insights, this approach significantly enhances operational precisionand adaptability, illustrating its utility in complex assembly tasks wheretraditional methods fall short.Building on this foundation, a learning-based visual servoing methodis introduced. This innovative approach allows robots to dynamicallyadjust their actions in real-time based on visual feedback, navigatingcomplicated environments and performing tasks with heightened accuracy.Such capability is crucial for ensuring the consistent placement of BFMunder varying conditions, demonstrating a marked improvement in theprocess’s reliability and efficiency.Finally, an intuitive human-robot collaboration framework is proposed.This model is designed to seamlessly integrate the strengths of bothhumans and robots, facilitating a partnership that leverages the precisionof automation and the judgement of human operators. Through examplessuch as collaborative adjustment of brazing parameters in response to realtime observations, the framework underscores the importance of human insight in augmenting robotic capabilities.This approach not only advances the brazing process by mitigating thereliance on skilled labour and enhancing safety standards but also laysa foundation for applications beyond brazing, highlighting the transformative potential of integrating human and robotic expertise in industrialprocesses.
AB - In manufacturing safety-critical components, brazing stands out for itsability to form strong, cost-efficient joints between dissimilar materials.Despite its importance, the brazing process often falls short in efficiencyand precision due to its reliance on manual labour. Simultaneously,full automation, while enhancing certain operational aspects, lacks theadaptability and decision-making prowess inherent to human operators.This thesis addresses these challenges within the brazing process byadvocating for a synergistic integration of robotics and artificial intelligence(AI) in a human-robot collaboration (HRC) framework. It uniquelycombines human expertise with advanced machine capabilities, aiming torefine brazing operations beyond the reach of solely human or automatedendeavours.Central to the thesis is the development of a category-agnostic objectlocalisation strategy. This technique enables robots to recognise andposition brazing filler metal (BFM) across a diverse array of joint configurations without prior specific knowledge of the objects. By leveraging AIdriven insights, this approach significantly enhances operational precisionand adaptability, illustrating its utility in complex assembly tasks wheretraditional methods fall short.Building on this foundation, a learning-based visual servoing methodis introduced. This innovative approach allows robots to dynamicallyadjust their actions in real-time based on visual feedback, navigatingcomplicated environments and performing tasks with heightened accuracy.Such capability is crucial for ensuring the consistent placement of BFMunder varying conditions, demonstrating a marked improvement in theprocess’s reliability and efficiency.Finally, an intuitive human-robot collaboration framework is proposed.This model is designed to seamlessly integrate the strengths of bothhumans and robots, facilitating a partnership that leverages the precisionof automation and the judgement of human operators. Through examplessuch as collaborative adjustment of brazing parameters in response to realtime observations, the framework underscores the importance of human insight in augmenting robotic capabilities.This approach not only advances the brazing process by mitigating thereliance on skilled labour and enhancing safety standards but also laysa foundation for applications beyond brazing, highlighting the transformative potential of integrating human and robotic expertise in industrialprocesses.
U2 - 10.17635/lancaster/thesis/2568
DO - 10.17635/lancaster/thesis/2568
M3 - Doctoral Thesis
PB - Lancaster University
ER -