An official website of the United States government
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.
more »
« less
A deep learning-based RULA method for working posture
Musculoskeletal disorders (MSDs) represent one of the leading cause of injuries from modern industries. Previous research has identified a causal relation between MSDs and awkward working postures. Therefore, a robust tool for estimating and monitoring workers’ working posture is crucial to MSDs prevention. The Rapid Upper Limb Assessment (RULA) is one of the most adopted observational methods for assessing working posture and the associated MSDs risks in industrial practice. The manual application of RULA, however, can be time consuming. This research proposed a deep learning-based method for realtime estimating RULA from 2-D articulated pose using deep neural network. The method was trained and evaluated by 3-D pose data from Human 3.6, an open 3-D pose dataset, and achieved overall Marginal Average Error (MAE) of 0.15 in terms of RULA grand score (or 3.33% in terms of percentage error). All the data and code can be found at the first author’s GitHub (https://github.com/LLDavid/RULA_machine)
more »
« less
- Award ID(s):
- 1822477
- PAR ID:
- 10184812
- Date Published:
- Journal Name:
- Proceedings of the Human Factors and Ergonomics Society 2019 Annual Meeting
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Fall prevention has always been a crucial topic for injury prevention. Research shows that real-time posture monitoring and subsequent fall prevention are important for the prevention of fall-related injuries. In this research, we determine a real-time posture classifier by comparing classical and deep machine learning classifiers in terms of their accuracy and robustness for posture classification. For this, multiple classical classifiers, including classical machine learning, support vector machine, random forest, neural network, and Adaboost methods, were used. Deep learning methods, including LSTM and transformer, were used for posture classification. In the experiment, joint data were obtained using an RGBD camera. The results show that classical machine learning posture classifier accuracy was between 75% and 99%, demonstrating that the use of classical machine learning classification alone is sufficient for real-time posture classification even with missing joints or added noise. The deep learning method LSTM was also effective in classifying the postures with high accuracy, despite incurring a significant computational overhead cost, thus compromising the real-time posture classification performance. The research thus shows that classical machine learning methods are worthy of our attention, at least, to consider for reuse or reinvention, especially for real-time posture classification tasks. The insight of using a classical posture classifier for large-scale human posture classification is also given through this research.more » « less
-
The objective of this research is to evaluate vision-based pose estimation methods for on-site construction robots. The prospect of human-robot collaborative work on construction sites introduces new workplace hazards that must be mitigated to ensure safety. Human workers working on tasks alongside construction robots must perceive the interaction to be safe to ensure team identification and trust. Detecting the robot pose in real-time is thus a key requirement in order to inform the workers and to enable autonomous operation. Vision-based (marker-less, marker-based) and sensor-based (IMU, UWB) are two of the main methods for estimating robot pose. The marker-based and sensor-based methods require some additional preinstalled sensors or markers, whereas the marker-less method only requires an on-site camera system, which is common on modern construction sites. In this research, we develop a marker-less pose estimation system, which is based on a convolutional neural network (CNN) human pose estimation algorithm: stacked hourglass networks. The system is trained with image data collected from a factory setup environment and labels of excavator pose. We use a KUKA robot arm with a bucket mounted on the end-effector to represent a robotic excavator in our experiment. We evaluate the marker-less method and compare the result with the robot’s ground truth pose. The preliminary results show that the marker-less method is capable of estimating the pose of the excavator based on a state-of-the-art human pose estimation algorithm.more » « less
-
Estimation and inference in statistics pose significant challenges when data are collected adaptively. Even in linear models, the Ordinary Least Squares (OLS) estimator may fail to exhibit asymptotic normality for single coordinate estimation and have inflated error. This issue is highlighted by a recent minimax lower bound, which shows that the error of estimating a single coordinate can be enlarged by a multiple of $$\sqrt{d}$$ when data are allowed to be arbitrarily adaptive, compared with the case when they are i.i.d. Our work explores this striking difference in estimation performance between utilizing i.i.d. and adaptive data. We investigate how the degree of adaptivity in data collection impacts the performance of estimating a low-dimensional parameter component in high-dimensional linear models. We identify conditions on the data collection mechanism under which the estimation error for a low-dimensional parameter component matches its counterpart in the i.i.d. setting, up to a factor that depends on the degree of adaptivity. We show that OLS or OLS on centered data can achieve this matching error. In addition, we propose a novel estimator for single coordinate inference via solving a Two-stage Adaptive Linear Estimating equation (TALE). Under a weaker form of adaptivity in data collection, we establish an asymptotic normality property of the proposed estimator.more » « less
-
Advancements in robot-assisted surgery have been rapidly growing since two decades ago. More recently, the automation of robotic surgical tasks has become the focus of research. In this area, the detection and tracking of a surgical tool are crucial for an autonomous system to plan and perform a procedure. For example, knowing the position and posture of a needle is a prerequisite for an automatic suturing system to grasp it and perform suturing tasks. In this paper, we proposed a novel method, based on Deep Learning and Point-to-point Registration, to track the 6 degrees of freedom (DOF) pose of a metal suture needle from a robotic endoscope (an Endoscopic Camera Manipulator from the da Vinci Robotic Surgical Systems), without the help of any marker. The proposed approach was implemented and evaluated in a standard simulated surgical environment provided by the 2021–2022 AccelNet Surgical Robotics Challenge, thus demonstrates the potential to be translated into a real-world scenario. A customized dataset containing 836 images collected from the simulated scene with ground truth of poses and key points information was constructed to train the neural network model. The best pipeline achieved an average position error of 1.76 mm while the average orientation error is 8.55 degrees, and it can run up to 10 Hz on a PC.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1177/1071181319631174
