Search

Motion prediction based on kinematic information such as body segment displacement and joint angle has been widely studied. Because motions originate from forces, it is beneficial to estimate dynamic information, such as the ground reaction force (GRF), in addition to kinematic information for advanced motion prediction. In this study, we proposed a method to estimate GRF and ground reaction moment (GRM) from electromyography (EMG) in combination with and without an inertial measurement unit (IMU) sensor using a machine learning technique. A long short-term memory network, which is suitable for processing long time-span data, was constructed with EMG and IMU as input data to estimate GRF during posture control and stepping motion. The results demonstrate that the proposed method can provide the GRF estimation with a root mean square error (RMSE) of 8.22 ± 0.97% (mean ± SE) for the posture control motion and 11.17 ± 2.16% (mean ± SE) for the stepping motion. We could confirm that EMG input is essential especially when we need to predict both GRF and GRM with limited numbers of sensors attached under knees. In addition, we developed a GRF visualization system integrated with ongoing motion in a Unity environment. This system enabled the visualization of the GRF vector in 3-dimensional space and provides predictive motion direction based on the estimated GRF, which can be useful for human motion prediction with portable sensors.

Multiple tasks are simultaneously performed during walking in our daily life. Distracted walk by smartphone usage is recently getting a social problem. The term dual-task gait refers to the secondary task added to the walking. Attention demanding tasks may influence how a person walks. Since in-lab measurement may not accurately reflect the daily living gait, wearable sensors approach have been proposed for gait analysis in an out-of-lab setting. This study addresses the potential of using only two inertial measurement units (IMUs) attached to the shoes for the assessment of cognitive dual-task gait and how it differs from single-task gait. We found that the proposed system is sensitive to recognizing a tiny change in gait features such as on the double support time and gait indices when subject performing dual-task gait compared to the single-task gait experiment.

In this study, we proposed a framework for extracting gait events and extensive temporal features, seamlessly, during walking and running on a treadmill by constructing a finite state machine (FSM) transition rules based on two IMU sensors attached to the back of the shoes. Detailed innerclass states were defined to recognize the double support phase on walking gait and the double flight phase on running gait. Further, an in-depth speed-based analysis of temporal gait features can be performed for each tested speed with an automatic speed change detection algorithm based on the moving average filter applied to motion intensity data. The results have demonstrated that the FSM can accurately distinguish walking gait and running gait while also extract a detailed gait phase, respectively. This finding may contribute to a more flexible gait analysis where a change in speed or transition from walk to run can be anticipated and recognized accordingly.

In this study, we investigated a control algorithm for a semi-active prosthetic knee based on reinforcement learning (RL). Model-free reinforcement Q-learning control with a reward shaping function was proposed as the voltage controller of a magnetorheological damper based on the prosthetic knee. The reward function was designed as a function of the performance index that accounts for the trajectory of the subject-specific knee angle. We compared our proposed reward function to a conventional single reward function under the same random initialization of a Q -matrix. We trained this control algorithm to adapt to several walking speed datasets under one control policy and subsequently compared its performance with that of other control algorithms. The results showed that our proposed reward function performed better than the conventional single reward function in terms of the normalized root mean squared error and also showed a faster convergence trend. Furthermore, our control strategy converged within our desired performance index and could adapt to several walking speeds. Our proposed control structure has also an overall better performance compared to user-adaptive control, while some of its walking speeds performed better than the neural network predictive control from existing studies., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 Hutabarat, Ekkachai, Hayashibe and Kongprawechnon.)