This video does a great job showing how the biological torque prediction works for all sorts of tasks--cyclic, noncyclic, and even unstructured/undefinable movements. First time I've worn an active exoskeleton for hours without ever needing to turn it off!
In our new Nature publication, we present a deep learning-based, task-agnostic exoskeleton controller evaluated on over 30 human activities – a major effort towards real-world viability of exoskeletons.
https://t.co/aqVzAyDsC7
Proud and excited to finally share this awesome project in Nature! We used a real-time data-driven estimate of biological joint moment as a continuous, task-agnostic signal to base our exoskeleton actuator torque around.
https://t.co/vct7rapXHY
Join our team! The Shepherd Lab is recruiting one postdoc (flexible start) and one PhD student (Fall 2025). Project areas include mechatronic design for prosthetics and exos, preference-based optimization, data-driven control, and biomechanics. https://t.co/l1AEApPWAv
My lab is recruiting a postdoc to work on ML-based task-agnostic exoskeleton control and/or lower limb prosthesis design and control. Come join us in Boston!
Shepherd Lab: https://t.co/J9zF1yyjat
Apply here: https://t.co/aaMdUvB80g
We're hiring multiple tenure track positions at Northeastern, with joint appointments possible between Rehab Science and Engineering.
Topics: Sensorimotor rehabilitation, neuromodulation, rehabilitation robotics, and neuroprosthetics.
Come join me!
https://t.co/00MJHwFDeV
New Perspective on #userpreference in prosthetics and exoskeletons. Preference is noisy and tricky to quantify, but contains unique information for researchers trying to develop user-optimal solutions.
https://t.co/sPanfFpGIm
Check out our new publication on the design of a passive prosthetic ankle that lifts the toe during swing phase (to reduce falls) while providing full stance phase energy storage and return!
Excited to share our new research: “Exoskeletons need to react faster than physiological responses to improve standing balance.” w/ @Owen1Beck, @NeuromechanicsL and @GT_PoWeR_Lab.
Paper: https://t.co/7avS6fIcGe
Jargon-free explanation: https://t.co/kpxsgztm0O
1/
Thus, ankle exoskeletons must apply assistance as rapidly as possible to get the center of pressure in front of the center of mass, despite the minor disruption to the natural plantarflexion response. That is, to improve balance, make the human faster not stronger!
I'm recruiting PhD students for Fall 2023; If you are interested in either advanced mechatronic design or machine learning-based control of assistive devices, please reach out! Examples of past projects on my lab site: https://t.co/TkbkDEMJ1M
I am recruiting graduate students to join my lab next year! Opportunities to work on • wearable sensing • human-exoskeleton interaction • pediatric powered mobility & computer interaction • human-in-the-loop optimization for assistive robots, and more! DM me with interest.