Abstract
Robotic leg prostheses and exoskeletons can provide powered locomotor assistance to older adults and/or persons with physical disabilities. However, the current locomotion mode recognition systems being developed for automated high-level control and decision-making rely on mechanical, inertial, and/or neuromuscular sensors, which inherently have limited prediction horizons (i.e., analogous to walking blindfolded). Inspired by the human vision-locomotor control system, we developed an environment classification system powered by computer vision and deep learning to predict the oncoming walking environments prior to physical interaction, therein allowing for more accurate and robust high-level control decisions. In this study, we first reviewed the development of our “ExoNet” database—the largest and most diverse open-source dataset of wearable camera images of indoor and outdoor real-world walking environments, which were annotated using a hierarchical labeling architecture. We then trained and tested over a dozen state-of-the-art deep convolutional neural networks (CNNs) on the ExoNet database for image classification and automatic feature engineering, including: EfficientNetB0, InceptionV3, MobileNet, MobileNetV2, VGG16, VGG19, Xception, ResNet50, ResNet101, ResNet152, DenseNet121, DenseNet169, and DenseNet201. Finally, we quantitatively compared the benchmarked CNN architectures and their environment classification predictions using an operational metric called “NetScore,” which balances the image classification accuracy with the computational and memory storage requirements (i.e., important for onboard real-time inference with mobile computing devices). Our comparative analyses showed that the EfficientNetB0 network achieves the highest test accuracy; VGG16 the fastest inference time; and MobileNetV2 the best NetScore, which can inform the optimal architecture design or selection depending on the desired performance. Overall, this study provides a large-scale benchmark and reference for next-generation environment classification systems for robotic leg prostheses and exoskeletons.
Highlights
There are currently hundreds of millions of individuals worldwide with mobility impairments resulting from aging and/or physical disabilities (Grimmer et al, 2019)
To facilitate onboard real-time inference, the ideal convolutional neural network would achieve high classification accuracy with minimal parameters, computing operations, and inference time. Motivated by these design principles, we quantitatively evaluated and compared the benchmarked convolutional neural networks (CNNs) architectures (N ) and their environment classification predictions on the ExoNet database using an operational metric called “NetScore” (Wong, 2018): (N ) = 20 log a (N )α p (N )β m (N )γ where a (N ) is the image classification accuracy during inference (0–100%), p (N ) is the number of parameters expressed in millions, m (N ) is the number of multiply–accumulates expressed in billions, and α, β, and γ are coefficients that control the effects of the classification accuracy, and the architectural and computational complexities on the NetScore ( ), respectively
EfficientNetB0 network achieved the highest image classification accuracy (Ca) during inference (73.2% accuracy), that being the percentage of true positives (47,265 images) out of the total number of images in the testing set (64,568 images)
Summary
There are currently hundreds of millions of individuals worldwide with mobility impairments resulting from aging and/or physical disabilities (Grimmer et al, 2019). Most robotic leg prostheses and exoskeletons use a hierarchical control architecture, including high, mid, and low-level controllers (Tucker et al, 2015; Young and Ferris, 2017) (Figure 1). The low-level controller uses standard controls engineering algorithms like proportionalintegral-derivative (PID) control to calculate the error between the measured and desired device states and command the robotic actuators to minimize the error via reference tracking and closed-loop feedback control (Tucker et al, 2015; Young and Ferris, 2017; Krausz and Hargrove, 2019)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
