A gait phase prediction model trained on benchmark datasets for evaluating a controller for prosthetic legs

Abstract

Powered lower-limb assistive devices, such as prostheses and exoskeletons, are a promising option for helping mobility-impaired individuals regain functional gait. Gait phase prediction plays an important role in controlling these devices and evaluating whether the device generates a gait similar to that of individuals with intact limbs. This study proposes a gait phase prediction method based on a deep neural network (DNN). The long short-term memory (LSTM)-based model predicts a continuous gait phase from the 250 ms history of the vertical load, thigh angle, knee angle, and ankle angle, commonly available on powered lower-limb assistive devices. One unified model was trained using publicly available benchmark datasets containing intact limb gaits for level-ground walking (LGW) and ascending stairs (SA). A phase prediction error of 1.28% for all benchmark datasets was obtained. The model was subsequently applied to a state machine-controlled powered prosthetic leg dataset collected from four individuals with unilateral transfemoral amputation. The gait phase prediction results (a phase prediction error of 5.70%) indicate that the model trained on benchmark data can be used for a system not included in the training dataset with no post-processing, such as model adaptation. Furthermore, it provided information regarding evaluation of the controller: whether the prosthetic leg generated normal gait. In conclusion, the proposed gait phase prediction model will facilitate efficient gait prediction and evaluation of controllers for powered lower-limb assistive devices.

Implementing Gait Kinematic Trajectory Forecasting Models on an Embedded System

“…Moreover, problems can arise in situations where the motion capture markers used for gait are obscured by arm swinging or hand rails that may be needed for safety in certain clinical populations [ 51 ]. Unlike fixed-motion capture systems, embedded systems have numerous practical and important applications in many areas of rehabilitation science and biomedical engineering [ 1 , 6 , 9 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 28 , 29 ]. For example, as previously noted [ 37 ], the accurate sensor-aided prediction of gait kinematic trajectories can serve as a feedforward mechanism to powered devices instead of predominantly relying on feedback sensors, effectively serving to improve device performance by avoiding alterations in the user’s natural gait trajectories [ 37 ].…”

“…Walking is an essential activity in daily life. Mobility augmentation through the use of wearable assistive ambulatory devices can provide vertical support, assist in lower-limb motion, and improve the quality of life for users [ 4 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ]. In addition to the medical applications of wearable assistive ambulatory devices, the impact of various non-medical applications of these devices is also being realized, as they may be able to help healthy individuals perform important activities in daily life [ 4 , 5 , 16 ].…”

“…While there are intricate complexities related to safety regulatory requirements, user acceptance, as well as device reliability and adaptability that need to be considered, assistive ambulatory devices have the potential to help in such situations and may even reduce the burden on healthcare resources [ 4 ]. Nevertheless, given the importance of mobility assistance for both medical and non-medical end-user applications, there has been increasing interest in designing more effective and intelligent assistive ambulatory technologies [ 1 , 4 , 5 , 6 , 8 , 9 , 11 , 12 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ].…”

Generating synthetic gait patterns based on benchmark datasets for controlling prosthetic legs

“…A total of 2145 and 100 gait cycles were obtained from [ 19 ] and [ 12 ], respectively. More details on this peak detection-based pattern extraction can be found in our previous work [ 21 ].…”

“…The dataset contained goniometer data as well as motion capture data (used to train the GAN) for the joint angles. Because of the differences in sensor characteristics, the goniometer and motion capture data show different joint angle values [ 21 ]. In conclusion, the subset containing goniometer data differs from the data included in the training dataset.…”