Computerized compliance of Personal Protective Equipment (PPE) is an emerging topic in academic literature that aims to enhance workplace safety through the automation of compliance and prevention of PPE misuse (which currently relies on manual employee supervision and reporting). Although trends in the scientific literature indicate a high potential for solving the compliance problem by employing computer vision (CV) techniques, the practice has revealed a series of barriers that limit their wider applications. This article aims to contribute to the advancement of CV-based PPE compliance by providing a comparative review of high-level approaches, algorithms, datasets, and technologies used in the literature. The systematic review highlights industry-specific challenges, environmental variations, and computational costs related to the real-time management of PPE compliance. The issues of employee identification and identity management are also discussed, along with ethical and cybersecurity concerns. Through the concept of CV-based PPE Compliance 4.0, which encapsulates PPE, human, and company spatio-temporal variabilities, this study provides guidelines for future research directions for addressing the identified barriers. The further advancements and adoption of CV-based solutions for PPE compliance will require simultaneously addressing human identification, pose estimation, object recognition and tracking, necessitating the development of corresponding public datasets.
Despite technological progress and the tendency for automation, the majority of manufacturing workplaces still rely on human labor. Although industrial tasks are frequently composed of simple operator actions, non-ergonomic execution of such repetitive tasks has been reported as the primary cause of musculoskeletal disorders (which have a significant negative impact on public health and the economy). Considering the sizes of manufacturing halls and large numbers of employees, there is an increasing need for tools that can improve the recognition of unsafe acts. Herein, a deep learning-based procedure for pose safety assessment is proposed and validated using monocular videos captured with a conventional IP camera. The two key composing components of the proposed pipeline are the three-dimensional (3D) pose estimator and mesh classifier. The proposed method was validated experimentally by considering three different methodologically selected industrial tasks: a laborious task that requires all-body effort (pushing and pulling), a task that requires an upper-limb action comprising intensive interaction and motion control (drilling), and a typical collaborative task (polishing with a collaborative robot with variable mechanical impedance). Accuracies of 84.67%, 92%, and 98%, respectively, were achieved. Besides higher accuracy, the proposed method has shown practical advantages over existing alternatives based on analyzing the parameters derived from the human poses. Particularly, we report that the proposed procedure is generic, and it works directly with 3D human body poses, which significantly increases applicability while reducing the complexity and effort needed for data annotation and output interpretation by non-experts. The further research steps will be directed towards additional experimenting and improving the inference time of the composed deep learning architectures, with the end goal of enabling real-time solutions on edge AI devices.
Non-ergonomic execution of repetitive physical tasks represents a major cause of work-related musculoskeletal disorders (WMSD). This study was focused on the pushing and pulling (P&P) of an industrial handcart (which is a generic physical task present across many industries), with the aim to investigate the dependence of P&P execution on the operators’ psychological status and the presence of pain syndromes of the upper limbs and spine. The developed acquisition system integrated two three-axis force sensors (placed on the left and right arm) and six electromyography (EMG) electrodes (placed on the chest, back, and hand flexor muscles). The conducted experiment involved two groups of participants (with and without increased psychological scores and pain syndromes). Ten force parameters (for both left and right side), one EMG parameter (for three different muscles, both left and right side), and two time-domain parameters were extracted from the acquired signals. Data analysis showed intergroup differences in the examined parameters, especially in force integral values and EMG mean absolute values. To the best of our knowledge, this is the first study that evaluated the composite effects of pain syndromes, spine mobility, and psychological status of the participants on the execution of P&P tasks—concluding that they have a significant impact on the P&P task execution and potentially on the risk of WMSD. The future work will be directed towards the development of a personalized risk assessment system by considering more muscle groups, supplementary data derived from operators’ poses (extracted with computer vision algorithms), and cognitive parameters (extracted with EEG sensors).
Emerging robotic systems with compliant characteristics, incorporating nonrigid links and/or elastic actuators, are opening new applications with advanced safety features, as well as improved performance and energy efficiency in contact tasks. However, the complexity of such systems poses challenges in modeling and control due to their nonlinear nature and model variations over time. To address these challenges, the paper introduces Locally Weighted Projection Regression (LWPR) and its online learning capabilities to keep the model of compliant actuators accurate and enable the model-based controls to be more robust. The approach is experimentally validated in Cartesian position and stiffness control for a 4 DoF planar robot driven by Variable Stiffness Actuators (VSA), whose real-time implementation is supported by the Sequential Least Squares Programming (SLSQP) optimization approach.