Search for: All records

This study presents a mobile app that facilitates undergraduate students to learn data science through their own full body motions. Leveraging the built-in camera of a mobile device, the proposed app captures the user and feeds their images into an open-source computer-vision algorithm that localizes the key joint points of human body. As students can participate in the entire data collection process, the obtained motion data is context-rich and personally relevant to them. The app utilizes the collected motion data to explain various concepts and methods in data science under the context of human movements. The app also visualizes the geometric interpretation of data through various visual aids, such as interactive graphs and figures. In this study, we use principal component analysis, a commonly used dimensionality reduction method, as an example to demonstrate the proposed learning framework. Strategies to encompass other learning modules are also discussed for further improvement. 

In recent years, there has been a trend to adopt human-robot collaboration (HRC) in the industry. In previous studies, computer vision-aided human pose reconstruction is applied to find the optimal position of point of operation in HRC that can reduce workers’ musculoskeletal disorder (MSD) risks due to awkward working postures. However, the reconstruction of human pose through computer-vision may fail due to the complexity of the workplace environment. In this study, we propose a data-driven method for optimizing the position of point of operation during HRC. A conditional variational auto-encoder (cVAE) model-based approach is adopted, which includes three steps. First, a cVAE model was trained using an open-access multimodal human posture dataset. After training, this model can output a simulated worker posture of which the hand position can reach a given position of point of operation. Next, an awkward posture score is calculated to evaluate MSD risks associated with the generated postures with a variety of positions of point of operation. The position of point of operation that is associated with a minimum awkward posture score is then selected for an HRC task. An experiment was conducted to validate the effectiveness of this method. According to the findings, the proposed method produced a point of operation position that was similar to the one chosen by participants through subjective selection, with an average difference of 4.5 cm. 

Biomechanics examines different physical characteristics of the human body movement by applying principles of Newtonian mechanics to physical activities. Therefore, undergraduate biomechanics courses are highly demanding in mathematics and physics. While the inclusion of laboratory experiences can augment student comprehension of biomechanics concepts, the cost and the required expertise associated with motion tracking systems can be a burden of offering laboratory sessions. In this study, we developed a mobile platform app to facilitate learning human kinematics in biomechanics courses. An optimized computer-vision model that is based on convolutional pose machine (CPM), MobileNet V2 and TensorFlow Lite frameworks is adopted to reconstruct human pose first. A real-time human kinematics analysis then allows students to conduct human motion experiments. The proposed app can serve as a potential instructional tool in biomechanics courses. 

Work-related musculoskeletal disorders (MSDs) are often observed in human-robot collaboration (HRC), a common work configuration in modern factories. In this study, we aim to reduce the risk of MSDs in HRC scenarios by developing a novel model-free reinforcement learning (RL) method to improve workers’ postures. Our approach follows two steps: first, we adopt a 3D human skeleton reconstruction method to calculate workers’ Rapid Upper Limb Assessment (RULA) scores; next, we devise an online gradient-based RL algorithm to dynamically improve the RULA score. Compared with previous model-based studies, the key appeals of the proposed RL algorithm are two-fold: (i) the model-free structure allows it to “learn” the optimal worker postures without need any specific biomechanical models of tasks or workers, and (ii) the data-driven nature makes it accustomed to arbitrary users by providing personalized work configurations. Results of our experiments confirm that the proposed method can significantly improve the workers’ postures. 

Human-robot collaboration (HRC) is an emerging research area that has gained tremendous attention from both academia and industry. Since some robot-related factors can elicit mental stress or have negative psychological effects on human workers, it is essential to understand these factors and maintain workers’ mental stress at a low level. Galvanic Skin Response (GSR) measures skin conductance and is known to be a physiological measurement that reflects short-term mental stress. Typically, skin conductance increases in response to greater mental stress. In this study, the mental stress caused by the hand-over activities of a collaborative robot was investigated using both GSR as an objective measurement and NASA-Task Load Index (TLX) as a subjective assessment. Several robot-related factors that may lead to mental stress were experimentally examined. GSR outcomes indicated that end effector approaching within workers’ view, low end effector speed, and constrained end effector trajectory led to a significantly lower skin conductance. Some aspects of the NASA-TLX also indicated that speed and trajectory significantly affected the scores. Yet, no significant differences were found between approaching directions regarding NASA-TLX scores.