Data-driven Characterization of Human Interaction for Model-based Control of Powered Prostheses

Abstract

This paper proposes a data-driven method for powered prosthesis control that achieves stable walking without the need for additional sensors on the human. The key idea is to extract the nominal gait and the human interaction information from motion capture data, and reconstruct the walking behavior with a dynamic model of the human-prosthesis system. The walking behavior of a human wearing a powered prosthesis is obtained through motion capture, which yields the limb and joint trajectories. Then a nominal trajectory is obtained by solving a gait optimization problem designed to reconstruct the walking behavior observed by motion capture. Moreover, the interaction force profiles between the human and the prosthesis are recovered by simulating the model following the recorded gaits, which are then used to construct a force tube that covers all the interaction force profiles. Finally, a robust Control Lyapunov Function (CLF) Quadratic Programming (QP) controller is designed to guarantee the convergence to the nominal trajectory under all possible interaction forces within the tube. Simulation results show this controller's improved tracking performance with a perturbed force profile compared to other control methods with less model information.

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

“…Previous studies with a similar aim of utilizing sEMG in predicting joint kinematics and kinetics conducted either a feature (e.g., Phinyomark et al, 2011) or a muscle combination selection (e.g., Wang et al, 2021), or report only the utilized feature per muscle (Phinyomark et al, 2011;Li et al, 2021). Note that, taking into account the challenging nature of determining which specific parameter or combination of parameters is responsible for an improved neural network output (Goodfellow et al, 2016), a separate evaluation of the effects of multiple parameters has been suggested (Molnar, 2020). The complexity of the neural networks can consequently be reduced for an efficient training (Kendall et al, 2018).…”

“…The incidence rates of these interventions are high, reaching, e.g., over 11,500 cases alone in the UK each year ( Isaacs-Itua and Sedki, 2018 ) and from 2003 to 2013, about half of those were transtibial amputations ( Ahmad et al, 2016 ). Ascribed to a simple, low economic cost and robust design, energy storing and returning prostheses with elastic and damping characteristics ( Brackx et al, 2013 ) dominate the commercial lower limb prostheses market ( Gehlhar et al, 2020 ). However, because of lack of mechanical power generation and autonomous adaptation they can only provide lower than normal gait speeds with high metabolic energy costs that leads to early fatigue ( Vucina et al, 2005 ; Brackx et al, 2013 ; Xu et al, 2021 ).…”

Powered Prosthesis Locomotion on Varying Terrains: Model-Dependent Control With Real-Time Force Sensing

“…The optimization yields parameters for each domain α v that define Bézier polynomials for the desired trajectories y d s,v (τ (x s ), α v ) parameterized by the state-based phase variable τ (x s ), forward hip position, which goes from 0 to 1 in each domain D v [28]. Details given [29]. The resulting trajectories match the human data well and are shown in [15].…”

“…To design output trajectories for the amputee-prosthesis system that are invariant through impact, we use a hybrid zero dynamics condition [28] in an optimization whose solution must also satisfy the dynamics and feasibility constraints. We design the cost function to minimize the difference between the outputs (the joints) and human joint kinematic walking data obtained through motion capture [29]. The optimization yields parameters for each domain α v that define Bézier polynomials for the desired trajectories y d s,v (τ (x s ), α v ) parameterized by the state-based phase variable τ (x s ), forward hip position, which goes from 0 to 1 in each domain D v [28].…”

Model-Dependent Prosthesis Control with Interaction Force Estimation

“…The optimization solution gives parameters to define the desired trajectories y d s (τ (x s ), α) and the outputs to simulate the human side. See [26] for details. Fig.…”