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

Abstract The integration of human-robot collaboration (HRC) in manufacturing, particularly within the framework of Human-Cyber-Physical Systems (HCPS) and the emerging paradigm of Industry 5.0, has the potential to significantly enhance productivity, safety, and ergonomics. However, achieving seamless collaboration requires robots to recognize the identity of individual human workers and perform appropriate collaborative operations. This paper presents a novel gait identity recognition method using Inertial Measurement Unit (IMU) data to enable personalized HRC in manufacturing settings, contributing to the human-centric vision of Industry 5.0. The hardware of the entire system consists of the IMU wearable device as the data source and a collaborative robot as the actuator, reflecting the interconnected nature of HCPS. The proposed method leverages wearable IMU sensors to capture motion data, including 3-axis acceleration, 3-axis angular velocity. The two-tower Transformer architecture is employed to extract and analyze gait features. It consists of Temporal and Channel Modules, multi-head Auto-Correlation mechanism, and multi-scale convolutional neural network (CNN) layers. A series of optimization experiments were conducted to improve the performance of the model. The proposed model is compared with other state-of-the-art studies on two public datasets as well as one self-collected dataset. The experimental results demonstrate the better performance of our method in gait identity recognition. It is experimentally verified in the manufacturing environment involving four workers and one collaborative robot in an HRC assembly task, showcasing the practical applicability of this human-centric approach in the context of Industry 5.0.