LAUSR

Emerging variable-stiffness ankle prostheses can modulate their stiffness to meet differing biomechanical demands. To this end, knowledge of the optimal ankle stiffness is required for each user and activity. One approach to is to match the stiffness of prosthesis to the users preference, but this requires a tuning process to determine each users preferences. In this work, we seek to reduce this time by estimating user-preferred ankle stiffness using biomechanical data collected from seven subjects during walking at stiffness settings around their preferred stiffness. We investigated different machine learning algorithms, sensor subsets, and the impact of user-specific training data on estimation accuracy. We found that a long short term memory (LSTM) algorithm trained on user-specific data from the affected side only were able to predict user preferred ankle stiffness with an RMSE of 5.2% 0.3%. The prediction error was less than prosthesis users ability to reliably sense stiffness changes (7.7%), which highlights the significance of the performance of our proposed method. This study provides the foundation for an automated approach for predicting user-preferred prosthesis mechanics that would ease the burden of tuning these systems in a clinical setting.