Key Takeaways & Executive Findings
- •• 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.
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.
1. Introduction
In the era of Industry 5.0, the integration of human-robot collaboration (HRC) in manufacturing environments has become increasingly prevalent [1]. As manufacturing tasks become more complex and customized, the integration of human and robotic capabilities is essential to meet the evolving requirements in the context of Human-Cyber-Physical System (HCPS) [2]. Human-centered philosophy encourages HRC to enhance productivity, improve safety, and reduce the physical strain on human workers [3]. Current research has explored various methods for human motion recognition and posture description, such as using vision-based systems and inertial measurement units (IMUs). These approaches have demonstrated promising results in capturing human movements and recognizing the motion.
Zhang et al. [4] proposed a novel dual-stream convolutional neural network (CNN) based on calculating the optical flow difference in an image sequence, which showed excellent motion recognition and prediction accuracies in the assembly task. Yang et al. [5] predicted human arm motion using Elman neural network (ENN). Kahanowich et al. [6] used an IMU-based system for motion recognition and estimation in HRC. They aim at classifying specific activities, estimating body poses, and even predicting human intentions in collaborative scenarios.
However, to achieve seamless and efficient HRC, it is crucial to develop systems that can adapt to individual human workers’ unique characteristics and behaviors [7]. Identity recognition can be a solution for performing appropriate collaborative operations. Existing research that integrates HRC with identity recognition remains relatively limited. Khalifa et al. [8] proposed a CNN-based face recognition framework for a human-robot interaction system called robot system assistant (RoSA). He et al. [9] proposed a Wasserstein convolutional neural network (WCNN) approach in facial recognition. These studies often use facial recognition, which faces challenges related to occlusion and other limitations.
Loading authentic research manuscript (Pages 1–5)...
Zhangli Lu, Ruohan Wang, Huiying Zhou, Na Dong, Honghao Lyu, Geng Yang (2025). A Novel Gait Identity Recognition Method for Personalized Human-robot Collaboration in Industry 5.0. Chinese Journal of Mechanical Engineering. https://doi.org/10.1186/s10033-025-01348-x
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the main contribution of this paper?
The paper presents a novel gait identity recognition method using IMU data and a two-tower Transformer architecture, enabling personalized human-robot collaboration in Industry 5.0. It demonstrates superior performance over state-of-the-art methods and validates the approach in a real manufacturing HRC assembly task.
How does the proposed method work?
The method uses wearable IMU sensors to capture 3-axis acceleration and angular velocity data. A two-tower Transformer architecture with Temporal and Channel Modules, multi-head Auto-Correlation mechanism, and multi-scale CNN layers extracts and analyzes gait features for identity recognition.
What datasets were used for evaluation?
The model was evaluated on two public datasets and one self-collected dataset, showing better performance compared to other state-of-the-art studies.
What are the practical applications of this research?
The method enables robots to recognize individual workers and adapt their collaborative operations accordingly, enhancing productivity, safety, and ergonomics in manufacturing settings, aligning with the human-centric vision of Industry 5.0.
What are the advantages of using IMU-based gait recognition over vision-based methods?
IMU-based methods are less affected by occlusion and lighting conditions, offer better privacy, and can be integrated into wearable devices, making them suitable for dynamic manufacturing environments.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.