skip to main content

Title: Predicting 3-D Lower Back Joint Load in Lifting: A Deep Pose Estimation Approach
Goal: Lifting is a common manual material handling task performed in the workplaces. It is considered as one of the main risk factors for work-related musculoskeletal disorders. An important criterion to identify the unsafe lifting task is the values of the net force and moment at L5/S1 joint. These values are mainly calculated in a laboratory environment, which utilizes marker-based sensors to collect three-dimensional (3-D) information and force plates to measure the external forces and moments. However, this method is usually expensive to set up, time-consuming in process, and sensitive to the surrounding environment. In this study, we propose a deep neural network (DNN)-based framework for 3-D pose estimation, which addresses the aforementioned limitations, and we employ the results for L5/S1 moment and force calculation. Methods: At the first step of the proposed framework, full body 3-D pose is captured using a DNN, then at the second step, estimated 3-D body pose along with the subject's anthropometric information is utilized to calculate L5/S1 join's kinetic by a top-down inverse dynamic algorithm. Results: To fully evaluate our approach, we conducted experiments using a lifting dataset consisting of 12 subjects performing various types of lifting tasks. The results are validated against a marker-based motion capture system as a reference. The grand mean ± SD of the total moment/force absolute errors across all the dataset was 9.06 ± 7.60 N·m/4.85 ± 4.85 N. Conclusion: The proposed method provides a reliable tool for assessment of the lower back kinetics during lifting and can be an alternative when the use of marker-based motion capture systems is not possible.  more » « less
Award ID(s):
1703883 1555408 1451292
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
IEEE Transactions on Human-Machine Systems
Page Range / eLocation ID:
1 to 10
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Excessive low back joint loading during material handling tasks is considered a critical risk factor of musculoskeletal disorders (MSD). Therefore, it is necessary to understand the low-back joint loading during manual material handling to prevent low-back injuries. Recently, computer vision-based pose reconstruction methods have shown the potential in human kinematics and kinetics analysis. This study performed L5/S1 joint moment estimation by combining VideoPose3D, an open-source pose reconstruction library, and a biomechanical model. Twelve participants lifting a 10 kg plastic crate from the floor to a knuckle-height shelf were captured by a camera and a laboratory-based motion tracking system. The L5/S1 joint moments obtained from the camera video were compared with those obtained from the motion tracking system. The comparison results indicate that estimated total peak L5/S1 moments during lifting tasks were positively correlated to the reference L5/S1 joint moment, and the percentage error is 7.7%. 
    more » « less
  2. This article presents an optimization formulation and experimental validation of a dynamic-joint-strength-based two-dimensional symmetric maximum weight-lifting simulation. Dynamic joint strength (the net moment capacity as a function of joint angle and angular velocity), as presented in the literature, is adopted in the optimization formulation to predict the symmetric maximum lifting weight and corresponding motion. Nineteen participants were recruited to perform a maximum-weight-box-lifting task in the laboratory, and kinetic and kinematic data including motion and ground reaction forces were collected using a motion capture system and force plates, respectively. For each individual, the predicted spine, shoulder, elbow, hip, knee, and ankle joint angles, as well as vertical and horizontal ground reaction force and box weight, were compared with the experimental data. Both root-mean-square error and Pearson’s correlation coefficient ( r) were used for the validation. The results show that the proposed two-dimensional optimization-based motion prediction formulation is able to accurately predict all joint angles, box weights, and vertical ground reaction forces, but not horizontal ground reaction forces. 
    more » « less
  3. Abstract

    Marker‐based motion capture techniques are commonly used to measure human body kinematics. These techniques require an accurate mapping from physical marker position to model marker position. Traditional methods utilize a manual process to achieve marker positions that result in accurate tracking. In this work, we present an optimization algorithm for model marker placement to minimize marker tracking error during inverse kinematics analysis of dynamic human motion. The algorithm sequentially adjusts model marker locations in 3‐D relative to the underlying rigid segment. Inverse kinematics is performed for a dynamic motion capture trial to calculate the tracking error each time a marker position is changed. The increase or decrease of the tracking error determines the search direction and number of increments for each marker coordinate. A final marker placement for the model is reached when the total search interval size for every coordinate falls below a user‐defined threshold. Individual marker coordinates can be locked in place to prevent the algorithm from overcorrecting for data artifacts such as soft tissue artifact. This approach was used to refine model marker placements for eight able‐bodied subjects performing walking trials at three stride frequencies. Across all subjects and stride frequencies, root mean square (RMS) tracking error decreased by 38.4% and RMS tracking error variance decreased by 53.7% on average. The resulting joint kinematics were in agreement with expected values from the literature. This approach results in realistic kinematics with marker tracking errors well below accepted thresholds while removing variance in the model‐building procedure introduced by individual human tendencies.

    more » « less
  4. Tensegrity robots, which are composed of compressive elements (rods) and flexible tensile elements (e.g., cables), have a variety of advantages, including flexibility, low weight, and resistance to mechanical impact. Nevertheless, the hybrid soft-rigid nature of these robots also complicates the ability to localize and track their state. This work aims to address what has been recognized as a grand challenge in this domain, i.e., the state estimation of tensegrity robots through a markerless, vision-based method, as well as novel, onboard sensors that can measure the length of the robot's cables. In particular, an iterative optimization process is proposed to track the 6-DoF pose of each rigid element of a tensegrity robot from an RGB-D video as well as endcap distance measurements from the cable sensors. To ensure that the pose estimates of rigid elements are physically feasible, i.e., they are not resulting in collisions between rods or with the environment, physical constraints are introduced during the optimization. Real-world experiments are performed with a 3-bar tensegrity robot, which performs locomotion gaits. Given ground truth data from a motion capture system, the proposed method achieves less than 1~cm translation error and 3 degrees rotation error, which significantly outperforms alternatives. At the same time, the approach can provide accurate pose estimation throughout the robot's motion, while motion capture often fails due to occlusions. 
    more » « less
  5. The human sensorimotor system can adapt to various changes in the environmental dynamics by updating motor commands to improve performance after repeated exposure to the same task. However, the characteristics and mechanisms of the adaptation process remain unknown for dexterous manipulation, a unique motor task in which the body physically interacts with the environment with multiple effectors, i.e., digits, in parallel. We addressed this gap by using robotic manipulanda to investigate the changes in the digit force coordination following mechanical perturbation of an object held by tripod grasps. As the participants gradually adapted to lifting the object under perturbations, we quantified two components of digit force coordination. One is the direction-specific manipulation moment that directly counteracts the perturbation, whereas the other one is the direction-independent internal moment that supports the stability and stiffness of the grasp. We found that trial-to-trial improvement of task performance was associated with increased manipulation moment and a gradual decrease of the internal moment. These two moments were characterized by different rates of adaptation. We also examined how these two force coordination components respond to changes in perturbation directions. Importantly, we found that the manipulation moment was sensitive to the extent of repetitive exposure to the previous context that has an opposite perturbation direction, whereas the internal moment did not. However, the internal moment was sensitive to whether the postchange perturbation direction was previously experienced. Our results reveal, for the first time, that two distinct processes underlie the adaptation of multidigit force coordination for dexterous manipulation. NEW & NOTEWORTHY Changes in digit force coordination in multidigit object manipulation were quantified with a novel experimental design in which human participants adapted to mechanical perturbations applied to the object. Our results show that the adaptation of digit force coordination can be characterized by two distinct components that operate at different timescales. We further show that these two components respond to changes in perturbation direction differently. 
    more » « less