The aim of this paper is to investigate control strategies for functional electrical simulation (FES) cycling, with particular focus on the generation of stimulation intensities for multiple muscles, without any predetermined stimulation pattern. The control system is developed by imitating the biological neuronal control system. Specifically, the control signal on the level of joint torque (quasi-joint torque) is generated from the feedback information of lower extremities. The quasi-joint torque is then distributed to each muscle and the muscle delay is compensated, and finally, the stimulation intensity is determined. Parameters of the control system are optimized by the genetic algorithm with cost function of energy consumption and cadence error. The proposed control system is evaluated by computer simulation. The controller generates efficient stimulation even during the muscle fatigue process and successfully continues cycling without any predetermined stimulation pattern. Moreover, the controller is robust to the parameter error in the muscle delay compensator and also to the disturbances. It is expected that the proposed method would improve the FES cycling performance and relieve patients by eliminating the experimental determination of the stimulation patterns.

Ground reaction force (GRF) is essential for estimating muscle strength and joint torque in inverse dynamic analysis. Typically, it is measured using a force plate. However, force plates have spatial limitations, and studies of gaits involve numerous steps and thus require a large number of force plates, which is disadvantageous. To overcome these challenges, we developed a deep learning model for estimating three-axis GRF utilizing shoes with three uniaxial load cells. GRF data were collected from 81 people as they walked on two force plates while wearing shoes with three load cells. The three-axis GRF was calculated using a seq2seq approach based on long short-term memory (LSTM). To conduct the learning, validation, and testing, random selection was performed based on the subjects. The 60 selected participants were divided as follows: 37 were in the training set, 12 were in the validation set, and 11 were in the test set. The estimated GRF matched the force plate-measured GRF with correlation coefficients of 0.97, 0.96, and 0.90 and root mean square errors of 65.12 N, 15.50 N, and 9.83 N for the vertical, anterior–posterior, and medial–lateral directions, respectively, and there was a mid-stance timing error of 5.61% in the test dataset. A Bland–Altman analysis showed good agreement for the maximum vertical GRF. The proposed shoe with three uniaxial load cells and seq2seq LSTM can be utilized for estimating the 3D GRF in an outdoor environment with level ground and/or for gait research in which the subject takes several steps at their preferred walking speed, and hence can supply crucial data for a basic inverse dynamic analysis.