Date of Award

5-2026

Document Type

Thesis

Degree Name

Master of Science (MS)

College/School

College of Science and Mathematics

Department/Program

School of Computing

Thesis Sponsor/Dissertation Chair/Project Chair

Weitian Wang

Committee Member

Junyi Ye

Committee Member

Debapriya Hazra

Abstract

The transition from Industry 4.0’s near-total automation-centric smart factories toward Industry 5.0’s human-centric, adaptive, and resilient collaborative environments has emphasized the need for effective integration between human operators and robot systems. A key challenge in making such systems more human-centric lies in the capability to enable smooth and reliable task handovers between humans and robots. To address this handover problem, we propose a Learning-Finding-Giving framework that utilizes various sensor inputs to dynamically assist human operators in collaborative tasks. Another key challenge lies in how different optimization goals influence system behavior, agent experience, and task efficiency. To mitigate this research gap, we develop a nature-inspired task scheduling optimization approach to validate how different objective functions affect human participants and how they perceive task assignments and interpret the collaborative task process. This enables a comparative understanding of how optimization design impacts collaboration quality beyond commonly used efficiency metrics. This work connects foundational principles of Industry 5.0 with practical real-world implementations of human-robot collaboration, demonstrating how structured frameworks and optimization objectives can jointly contribute to more adaptive, efficient, and human-centered collaborative systems. These findings provide insights toward bridging the gap between theoretical collaboration models and real-world deployment in complex manufacturing environments. Various directions for future work are also discussed.

File Format

PDF

Available for download on Saturday, June 03, 2028

Share

COinS