A Novel Gait Identity Recognition Method for Personalized Human-robot Collaboration in Industry 5.0

• Introduces a novel gait identity recognition method using IMU data and a two-tower Transformer architecture, enabling personalized human-robot collaboration in Industry 5.0. • Demonstrates superior performance over state-of-the-art methods on two public datasets and a self-collected dataset, with experimental validation in a manufacturing HRC assembly task. • Contributes to the human-centric vision of Industry 5.0 by enhancing productivity, safety, and ergonomics through adaptive robot behavior based on worker identity. • Provides a practical solution for identity recognition in HRC, addressing limitations of vision-based methods such as occlusion and privacy concerns.