Predictive Modeling of Periodic Behavior for Human-Robot Symbiotic Walking

TL;DR

This paper introduces Periodic Interaction Primitives, a probabilistic framework for modeling and predicting periodic human walking behavior, which improves prediction speed and accuracy for robotic prosthesis control.

Contribution

The paper extends Interaction Primitives to handle periodic movements, enabling efficient, data-driven modeling and control of human walking and robotic prostheses.

Findings

Achieved 2.21° MAE in ankle angle prediction

Inference time of 0.0008 seconds per prediction

20 times faster and 4.5 times more accurate than alternatives

Abstract

We propose in this paper Periodic Interaction Primitives - a probabilistic framework that can be used to learn compact models of periodic behavior. Our approach extends existing formulations of Interaction Primitives to periodic movement regimes, i.e., walking. We show that this model is particularly well-suited for learning data-driven, customized models of human walking, which can then be used for generating predictions over future states or for inferring latent, biomechanical variables. We also demonstrate how the same framework can be used to learn controllers for a robotic prosthesis using an imitation learning approach. Results in experiments with human participants indicate that Periodic Interaction Primitives efficiently generate predictions and ankle angle control signals for a robotic prosthetic ankle, with MAE of 2.21 degrees in 0.0008s per inference. Performance degrades gracefully in the presence of noise or sensor fall outs. Compared to alternatives, this algorithm functions 20 times faster and performed 4.5 times more accurately on test subjects.