Coordinated Movement for Prosthesis Reference Trajectory Generation: Temporal Factors and Attention

Rai, Vijeth; Sharma, Abhishek; Preechayasomboon, Pornthep

doi:10.1109/biorob49111.2020.9224435

“…One explanation is that their shallow neural network architecture did not take the dynamic spatialtemporal relationships of human-robot system into account. More recently, studies have successfully used more advanced neural network classes such as recurrent neural networks (RNNs) [19] and attention-based long short-term memory networks (LSTMs) [20], [21] to generate reference trajectories for prosthesis controllers based on able-bodied data. Others have used wearable sensors and machine learning models to predict joint moments for exoskeleton control, also using ablebodied data [22].…”

Section: B Current Data-driven Approaches In Prosthetic Controlmentioning

confidence: 99%

Using Deep Learning Models to Predict Prosthetic Ankle Torque

Prasanna¹,

Realmuto²,

Anderson³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Inverse dynamics from motion capture is the most common technique for acquiring biomechanical kinetic data. However, this method is time-intensive, limited to a gait laboratory setting, and requires a large array of reflective markers to be attached to the body. A practical alternative must be developed to provide biomechanical information to high-bandwidth prosthesis control systems to enable predictive controllers. In this study, we applied deep learning to build dynamical system models capable of accurately estimating and predicting prosthetic ankle torque from inverse dynamics using only six input signals. We performed a hyperparameter optimization protocol that automatically selected the model architectures and learning parameters that resulted in the most accurate predictions. We show that the trained deep neural networks predict ankle torques one sample into the future with an average RMSE of 0.04±0.02 Nm/kg, corresponding to 2.9±1.6% of the ankle torque’s dynamic range. Comparatively, a manually-derived analytical regression model predicted ankle torques with a RMSE of 0.35±0.53 Nm/kg, corresponding to 26.6±40.9% of the ankle torque’s dynamic range. In addition, the deep neural networks predicted ankle torque values half a gait cycle into the future with an average drop in performance of 1.7% of the ankle torque’s dynamic range. This application of deep learning provides an avenue towards the development of predictive control systems for powered limbs aimed at optimizing prosthetic ankle torque. </p>

show abstract

“…One explanation is that their shallow neural network architecture did not take the dynamic spatialtemporal relationships of human-robot system into account. More recently, studies have successfully used more advanced neural network classes such as recurrent neural networks (RNNs) [17] and attention-based long short-term memory networks (LSTMs) [18], [19] to generate reference trajectories for prosthesis controllers based on able-bodied data. In the context of exoskeleton control, Camargo et al combined the use of machine learning models with wearable sensors to predict joint moments from able-bodied subjects [20].…”

Section: B Current Data-driven Approaches In Prosthetic Controlmentioning

confidence: 99%

Using Deep Learning Models to Predict Prosthetic Ankle Torque

Prasanna¹,

Realmuto²,

Anderson³

et al. 2022

Preprint

Self Cite

0

View full text Add to dashboard Cite

<p>Inverse dynamics from motion capture is the most common technique for acquiring biomechanical kinetic data. However, this method is time-intensive, limited to a gait laboratory setting, and requires a large array of reflective markers to be attached to the body. A practical alternative must be developed to provide biomechanical information to high-bandwidth prosthesis control systems to enable predictive controllers. In this study, we applied deep learning to build dynamical system models capable of accurately estimating and predicting prosthetic ankle torque from inverse dynamics using only six input signals. We performed a hyperparameter optimization protocol that automatically selected the model architectures and learning parameters that resulted in the most accurate predictions. We show that the trained deep neural networks predict ankle torques one sample into the future with an average RMSE of 0.04±0.02 Nm/kg, corresponding to 2.9±1.6% of the ankle torque’s dynamic range. Comparatively, a manually-derived analytical regression model predicted ankle torques with a RMSE of 0.35±0.53 Nm/kg, corresponding to 26.6±40.9% of the ankle torque’s dynamic range. In addition, the deep neural networks predicted ankle torque values half a gait cycle into the future with an average drop in performance of 1.7% of the ankle torque’s dynamic range. This application of deep learning provides an avenue towards the development of predictive control systems for powered limbs aimed at optimizing prosthetic ankle torque. </p>

show abstract

“…of Mechanical Engineering, University of Washington Seattle, WA 98195 USA (e-mail: as711@uw.edu) Eric Rombokas is with the Dept. of Mechanical Engineering, University of Washington, Seattle, WA 98195 USA (e-mail: rombokas@uw.edu) using distinct controllers for different gait phases [4]- [7] or even activities [8]- [10], by estimating joint angles directly from residual limb motions. Using a history of the kinematic state of the user, predictions of normative movements are generated that could serve as appropriate prosthesis commands.…”

Section: Introductionmentioning

confidence: 99%

Improving IMU-Based Prediction of Lower Limb Kinematics in Natural Environments Using Egocentric Optical Flow

Sharma

¹

2022

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

We seek to predict knee and ankle motion using wearable sensors. These predictions could serve as target trajectories for a lower limb prosthesis. In this manuscript, we investigate the use of egocentric vision for improving performance over kinematic wearable motion capture. We present an out-of-thelab dataset of 23 healthy subjects navigating public classrooms, a large atrium, and stairs for a total of almost 12 hours of recording. The prediction task is difficult because the movements include avoiding obstacles, other people, idiosyncratic movements such as traversing doors, and individual choices in selecting the future path. We demonstrate that using vision improves the quality of the predicted knee and ankle trajectories, especially in congested spaces and when the visual environment provides information that does not appear simply in the movements of the body. Overall, including vision results in 7.9% and 7.0% improvement in root mean squared error of knee and ankle angle predictions respectively. The improvement in Pearson Correlation Coefficient for knee and ankle predictions is 1.5% and 12.3% respectively. We discuss particular moments where vision greatly improved, or failed to improve, the prediction performance. We also find that the benefits of vision can be enhanced with more data. Lastly, we discuss challenges of continuous estimation of gait in natural, out-of-the-lab datasets.

show abstract

Coordinated Movement for Prosthesis Reference Trajectory Generation: Temporal Factors and Attention

Cited by 11 publications

References 21 publications

Using Deep Learning Models to Predict Prosthetic Ankle Torque

Using Deep Learning Models to Predict Prosthetic Ankle Torque

Using Deep Learning Models to Predict Prosthetic Ankle Torque

Improving IMU-Based Prediction of Lower Limb Kinematics in Natural Environments Using Egocentric Optical Flow

Contact Info

Product

Resources

About