A Neural Network-Based Gait Phase Classification Method Using Sensors Equipped on Lower Limb Exoskeleton Robots.

An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases.

Brief biomechanical analysis on the walking of spinal cord injury patients with a lower limb exoskeleton robot.

This paper presents a brief biomechanical analysis on the walking behavior of spinal cord injury (SCI) patients. It is known that SCI patients who have serious injuries to their spines cannot walk, and hence, several walking assistance lower limb exoskeleton robots have been proposed whose assistance abilities are shown to be well customized. However, these robots are not yet fully helpful to all SCI patients for several reasons. To overcome these problems, an exact analysis and evaluation of the restored walking function while the exoskeleton is worn is important. In this work, walking behavior of SCI patients wearing the rehabilitation of brain injuries (ROBIN) lower-limb walking assistant exoskeleton was analyzed in comparison to that of normal unassisted walking. The analysis method and results presented herein can be used by other researchers to improve their robots.