Coordinated Movement For Prosthesis Reference Trajectory Generation: Temporal Factors And Attention

Data-driven gait prediction can provide a reference trajectory for a wide variety of simple and complex movements captured in the training data. Coordinated Movement (CM) is a data-driven approach that maps movements of the body to movements of target joints, such as the ankle and knee. We have previously shown that the performance of CM for complex activities can be improved by adding more training data. In this paper we demonstrate that performance can also be improved by 1) including a history of the target joint angles as inputs to the model and 2) dynamic reallocation of the importance of the inputs over time using a neural network technique called Attention. These modifications are applicable when additional training data is limited. We also observe that Attention can follow important events in gait over time, adding interpretability to the system.