ExoNet Database: Wearable Camera Images of Human Locomotion Environments

Laschowski, Brock; McNally, William; Wong, Alexander; McPhee, John

doi:10.1101/2020.10.23.352054

Cited by 2 publications

(1 citation statement)

References 33 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers are working towards the design of controllers that consider user intent, environmental changes, and common transition states in day-to-day activity. Some controllers use body-in-the-loop based controllers during certain states to allow for physiologically meaningful movement during certain states [5], [6].Others added environmental sensing algorithms to determine required trajectory changes based on computer vision [7]- [9]. Some devices have specified movement trajectories for common activities, such a sit-to-stand transitions, stair ascent, stair descent, level walking, and standing which are triggered by specific cues [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Embodiment for Robotic Lower-Limb Exoskeletons: A Narrative Review

Hybart

Ferris

2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Research on embodiment of objects external to the human body has revealed important information about how the human nervous system interacts with robotic lower limb exoskeletons. Typical robotic exoskeleton control approaches view the controllers as an external agent intending to move in coordination with the human. However, principles of embodiment suggest that the exoskeleton controller should ideally coordinate with the human such that the nervous system can adequately model the input-output dynamics of the exoskeleton controller. Measuring embodiment of exoskeletons should be a necessary step in the exoskeleton development and prototyping process. Researchers need to establish high fidelity quantitative measures of embodiment, rather than relying on current qualitative survey measures. Mobile brain imaging techniques, such as high-density electroencephalography, is likely to provide a deeper understanding of embodiment during human-machine interactions and advance exoskeleton research and development. In this review we show why future exoskeleton research should include quantitative measures of embodiment as a metric of success.

show abstract

Section: Introductionmentioning

confidence: 99%

Embodiment for Robotic Lower-Limb Exoskeletons: A Narrative Review

Hybart

Ferris

2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

Sequential Image Classification of Human-Robot Walking Environments using Temporal Neural Networks

Ivanyuk-Skulskiy,

Kurbis,

Mihailidis

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Robotic prosthetic legs and exoskeletons require real-time and accurate estimation of the walking environment for smooth transitions between different locomotion mode controllers. However, previous studies have mainly been limited to static image classification, therein ignoring the temporal dynamics of human-robot locomotion. Motivated by these limitations, here we developed several state-of-the-art temporal convolutional neural networks (CNNs) to compare the performances between static vs. sequential image classification of real-world walking environments (i.e., level-ground terrain, incline stairs, and transitions to and from stairs). Using our large-scale image dataset, we trained a number of encoder networks such as VGG, MobileNetV2, ViT, and MobileViT, each coupled with a temporal long short-term memory (LSTM) backbone. We also trained MoViNet, a new video classification model designed for mobile and embedded devices, to further compare the performances between 2D and 3D temporal deep learning models. Our 3D network outperformed all the hybrid 2D encoders with LSTM backbones and the 2D CNN baseline model in terms of classification accuracy, suggesting that network architecture can play an important role in performance. However, although our 3D neural network achieved the highest classification accuracy, it had disproportionally higher computational and memory storage requirements, which can be disadvantageous for real-time control of robotic leg prostheses and exoskeletons with limited onboard resources.

show abstract

ExoNet Database: Wearable Camera Images of Human Locomotion Environments

Cited by 2 publications

References 33 publications

Embodiment for Robotic Lower-Limb Exoskeletons: A Narrative Review

Embodiment for Robotic Lower-Limb Exoskeletons: A Narrative Review

Sequential Image Classification of Human-Robot Walking Environments using Temporal Neural Networks

Contact Info

Product

Resources

About