Predicting walking response to ankle exoskeletons using data-driven models
Summary (1 min read)
Introduction
- The authors expected the NPV model’s prediction accuracy to meet or exceed that of the 192 LPV model.
- The amount of data required to accurately predict response to exoskeletons will restrict the settings in which 252 phase-varying models are practical, such as in clinical gait analysis where datasets typically contain only a 253 few gait cycles [2, 8].
- To test each model’s generalizability across a range of exoskeleton torque conditions, the authors separately predicted 261 responses to torque in the K1, K2, and K3 datasets, termed held-out conditions, at a 12.5% stride prediction 262 horizon (1/8th of a stride).
VI. DISCUSSION 336
- The authors evaluated the ability of subject-specific phase-varying models to predict kinematic and myoelectric 337 responses to ankle exoskeleton torques during treadmill walking.
- 351 the LPV model’s predictions explained more of the variance in kinematic responses to exoskeletons than the 352 PV model, regardless of whether predictions interpolated (K1 and K2) or extrapolated (K3) relative to the 353 training set.
VII. CONCLUSION 459
- To their knowledge, this is the first study to predict subject-specific responses to ankle exoskeletons using 460 phase-varying models.
- Without making assumptions about individual physiology or motor control, an LPV 461 model predicted short-time kinematic responses to bilateral passive ankle exoskeletons, though predicting 462 myoelectric responses remains challenging.
- Results support the utility of LPV models for studying and 463 predicting response to exoskeleton torque.
Did you find this useful? Give us your feedback
Citations
29 citations
3 citations
2 citations
1 citations
1 citations
References
1,927 citations
"Predicting walking response to ankl..." refers background in this paper
...kinematic or myoelectric) 36 control laws, predicting responses over even 10–20% of a stride may improve tracking performance or 37 transitions between control modes [4, 10-12]....
[...]
...The LPV and NPV models’ accurate predictions over short prediction horizons make 407 them primarily useful for exoskeleton control [10, 11]....
[...]
1,478 citations
1,141 citations
"Predicting walking response to ankl..." refers background in this paper
...At large prediction windows, measurements at an initial phase did not, on average, improve predictions of future posture due to a loss of coherence between inputs at an initial phase and outputs at a final phase [41]....
[...]
...However, as prediction window length increases, coherence between measurements at initial and final phases decreases due to nonlinearities in musculoskeletal dynamics [39-41]....
[...]
932 citations
"Predicting walking response to ankl..." refers background or methods in this paper
...However, 439 when only one training condition or a few strides are collected, as is standard in clinical gait analysis, phase440 varying model predictions will be poor and physiologically-detailed or population-specific models may 441 generate more accurate predictions [8, 19, 44, 45]....
[...]
...Studies predicting muscle 422 activity using physiologically-detailed models accounted for 60-99% of the variance in myoelectric signals, 423 though they evaluated predictions on unperturbed walking conditions only [44, 45]....
[...]
682 citations
"Predicting walking response to ankl..." refers background or methods in this paper
...Ankle exoskeletons are used to improve kinematics and reduce the energetic demands of locomotion in 27 unimpaired adults and individuals with neurologic injuries [1-5]....
[...]
...Inputs and output variables 197 To reflect clinically-relevant measurements and the dynamics of the neuromusculoskeletal system, we 198 selected input variables expected to encode musculoskeletal dynamics and motor control: 3D pelvis 199 orientation and lower-limb and lumbar joint angles, processed EMG signals, and their time derivatives at an 200 initial phase, φ [1, 2, 39]....
[...]
...Since passive exoskeletons typically elicit small changes in joint 111 kinematics and muscle activity, we expected the validity of Floquet Theory for human gait to extend to gait 112 with exoskeletons, indicating that the LPV model should accurately predict responses to passive exoskeleton 113 torque [1, 25-27, 29]....
[...]
...principles to reduce the energetic demand of walking and improve the quality of gait [1, 6, 8, 9]....
[...]
...activity, we found that the average unperturbed gait cycle accounted for only 30-60% of the variance in the 418 K2 data, compared to 60-95% in kinematic signals [1, 9, 12]....
[...]
Related Papers (5)
Frequently Asked Questions (2)
Q2. What are the future works in "Predicting walking response to ankle exoskeletons using data-driven models" ?
Improving data-driven models and experimental protocols to study 464 and predict myoelectric responses to exoskeletons represents an important direction for future research. 465 Modeling responses to exoskeletons or other assistive devices using a phase-varying perspective has the 466 potential to inform exoskeleton design for a range of user groups.