Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks.

This study determined whether the kinematics of lower limb trajectories during walking could be extrapolated using Long Short Term Memory (LSTM) neural networks. It was hypothesised that LSTM autoencoders could reliably forecast multiple time-step trajectories of the lower limb kinematics, specifically Linear Acceleration (LA) and Angular Velocity (AV). Using 3D motion capture, lower limb position-time coordinates were sampled (100 Hz) from 6 male participants (age 22 ± 2 years, height 1.77 ± 0.02 m, body mass 82 ± 4 kg) who walked for 10 minutes at 5km/h on a 0% gradient motor driven treadmill. This data was fed into a LSTM model with a sliding window of 4 kinematic variables with 25 samples or time-steps; LA and AV for thigh and shank. The LSTM was tested to forecast 5 samples (i.e. time-steps) of the 4 kinematic input variables. To attain generalisation, the model was trained on a dataset of 2,665 strides from 5 participants and evaluated on a test-set of 1 stride from a sixth participant. The LSTM model learned the lower limb kinematic trajectories using the training samples and tested for generalisation across participants. The forecasting horizon suggested higher model reliability in predicting earlier future trajectories. The Mean Absolute Error (MAE) was evaluated on each variable across the single tested stride and for the 5 sample forecast it obtained 0.047 m/s2 thigh LA, 0.047 m/s2 shank LA, 0.028 deg/s thigh AV and 0.024 deg/s shank AV. All predicted trajectories were highly correlated with the measured trajectories, with correlation coefficients greater than 0.98. The motion prediction model may have a wide range of applications, such as mitigating the risk of falls or balance loss and improving the human-machine interface for wearable assistive devices.