skip to main content


Title: Trust and Pediatric Exoskeletons: A Comparative Study of Clinician and Parental Perspectives
The purpose of this study was to survey the perspectives of clinicians regarding pediatric robotic exoskeletons and compare their views with the views of parents of children with disabilities. A total of 78 clinicians completed the survey; they were contacted through Children’s Healthcare of Atlanta, the American Academy for Cerebral Palsy and Developmental Medicine, and group pages on Facebook. Most of the clinicians were somewhat concerned to very concerned that a child might not use the device safely outside of the clinical setting. Most clinicians reported that the child would try to walk, run, and climb using the exoskeleton. The parents reported higher trust (i.e., lower concern) in the child using an exoskeleton outside of the clinical setting, compared to the clinician group. Prior experience with robotic exoskeletons can have an important impact on each group’s expectations and self-reported level of trust in the technology.  more » « less
Award ID(s):
1849101
NSF-PAR ID:
10139609
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
IEEE Transactions on Technology and Society
ISSN:
2637-6415
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. However, EMG signals change as a result of supplemental torque from an exoskeleton, resulting in unreliable estimates of the user's joint torque during active exoskeleton assistance. Here, we present an EMG control framework for robotic exoskeletons that provides consistent joint torque predictions across varying levels of assistance. Experiments with three healthy human participants showed that using diverse training data (from different levels of assistance) enables robust torque predictions, and that a convolutional neural network (CNN), but not a Kalman filter (KF), can capture the non-linear transformations in EMG due to exoskeleton assistance. With diverse training, the CNN could reliably predict joint torque from EMG during zero, low, medium, and high levels of exoskeleton assistance [root mean squared error (RMSE) below 0.096 N-m/kg]. In contrast, without diverse training, RMSE of the CNN ranged from 0.106 to 0.144 N-m/kg. RMSE of the KF ranged from 0.137 to 0.182 N-m/kg without diverse training, and did not improve with diverse training. When participant time is limited, training data should emphasize the highest levels of assistance first and utilize at least 35 full gait cycles for the CNN. The results presented here constitute an important step toward adaptive and robust human augmentation via robotic exoskeletons. This work also highlights the non-linear reorganization of locomotor output when using assistive exoskeletons; significant reductions in EMG activity were observed for the soleus and gastrocnemius, and a significant increase in EMG activity was observed for the erector spinae. Control algorithms that can accommodate spatiotemporal changes in muscle activity have broad implications for exoskeleton-based assistance and rehabilitation following neuromuscular injury. 
    more » « less
  2. Detection of the user’s walking is a critical part of exoskeleton technology for the full automation of smooth and seamless assistance during movement transitions. Researchers have taken several approaches in developing a walk detection system by using different kinds of sensors; however, only a few solutions currently exist which can detect these transitions using only the sensors embedded on a robotic hip exoskeleton (i.e., hip encoders and a trunk IMU), which is a critical consideration for implementing these systems in-the-loop of a hip exoskeleton controller. As a solution, we explored and developed two walk detection models that implemented a finite state machine as the models switched between walking and standing states using two transition conditions: stand-to-walk and walk-to-stand. One of our models dynamically detected the user’s gait cycle using two hip encoders and an IMU; the other model only used the two hip encoders. Our models were developed using a publicly available dataset and were validated online using a wearable sensor suite that contains sensors commonly embedded on robotic hip exoskeletons. The two models were then compared with a foot contact estimation method, which served as a baseline for evaluating our models. The results of our online experiments validated the performance of our models, resulting in 274 ms and 507 ms delay time when using the HIP+IMU and HIP ONLY model, respectively. Therefore, the walk detection models established in our study achieve reliable performance under multiple locomotive contexts without the need for manual tuning or sensors additional to those commonly implemented on robotic hip exoskeletons. 
    more » « less
  3. Autonomous lower-limb exoskeletons must modulate assistance based on locomotion mode (e.g., ramp or stair ascent) to adapt to the corresponding changes in human biological joint dynamics. However, current mode classification strategies for exoskeletons often require user-specific tuning, have a slow update rate, and rely on additional sensors outside of the exoskeleton sensor suite. In this study, we introduce a deep convolutional neural network-based locomotion mode classifier for hip exoskeleton applications using an open-source gait biomechanics dataset with various wearable sensors. Our approach removed the limitations of previous systems as it is 1) subject-independent (i.e., no user-specific data), 2) capable of continuously classifying for smooth and seamless mode transitions, and 3) only utilizes minimal wearable sensors native to a conventional hip exoskeleton. We optimized our model, based on several important factors contributing to overall performance, such as transition label timing, model architecture, and sensor placement, which provides a holistic understanding of mode classifier design. Our optimized DL model showed a 3.13% classification error (steady-state: 0.80 ± 0.38% and transitional: 6.49 ± 1.42%), outperforming other machine learning-based benchmarks commonly practiced in the field (p<0.05). Furthermore, our multi-modal analysis indicated that our model can maintain high performance in different settings such as unseen slopes on stairs or ramps. Thus, our study presents a novel locomotion mode framework, capable of advancing robotic exoskeleton applications toward assisting community ambulation. 
    more » « less
  4. Abstract

    Genomic tests such as exome sequencing have recently become an option for diagnosing patients. The tests allow clinical geneticists to sequence the majority of patients’ disease causing genetic variants. As a new technology, exome sequencing confronts the question of what the benefit is of this increased genetic information. Against a narrow perspective of clinical utility that emphasises tangible improvements in a patient's disease management, professional organisations have argued that genomic sequencing should be considered beneficial if it helps families and society. Based on video‐recorded observations of the return of exome sequencing results to parents of a child with disabilities in the clinic and in‐depth interviews with these parents, we examine how genomic test results become actionable in the clinical encounter. We find that parents and clinicians marshal exome results beyond biomedical diagnostic and management goals to address questions about guilt for causing the disabilities and to secure access to disability‐related services. We argue that genomic actionability rests on the interaction between the biological characteristics of genetic results and the predicaments facing parents of children with disabilities.

     
    more » « less
  5. Introduction

    This study is aimed at developing a task-based methodology for the design of robotic exoskeletons. This is in contrast to prevailing research efforts, which attempt to mimic the human limb, where each human joint is given an exoskeleton counter-joint. Rather, we present an alternative systematic design approach for the design of exoskeletons that can follow the complex three-dimensional motions of the human body independent of anatomical measures and landmarks. With this approach, it is not necessary to know the geometry of the targeted limb but rather to have a description of its motion at the point of attachment.

    Methods

    The desired trajectory of the targeted limb has been collected through a motion capture system from a healthy subject. Then, an approximate dimensional synthesis has been employed to specify the size of the mechanism and its location with respect to the limb, while generating the desired trajectory. The procedure for this method, from motion capture to kinematic synthesis to mechanism selection and optimization, is validated with an illustrative example.

    Results

    The proposed method resulted an exoskeleton which follows the desired trajectory of the human limb without any need of aligning its joint to the corresponding human joints.

    Conclusion

    A method to design lower mobility exoskeletons for specific sets of human motion is presented; the approach result an exoskeleton with lesser actuation system while generating complex 3D limb motions, which in turn results a lighter exoskeletons. It also avoids a need to align each robotic joint axis with its human counterpart.

     
    more » « less