Predictive Modeling of Periodic Behavior for Human-Robot Symbiotic Walking
This work addresses the need for efficient and accurate predictive modeling in human-robot symbiotic walking, specifically for robotic prosthetics, representing an incremental improvement by extending existing Interaction Primitives to periodic regimes.
The paper tackles the problem of modeling periodic human walking for human-robot symbiotic applications by proposing Periodic Interaction Primitives, a probabilistic framework that learns compact models to generate predictions and control signals for a robotic prosthetic ankle, achieving a MAE of 2.21 degrees in 0.0008s per inference and outperforming alternatives by being 20 times faster and 4.5 times more accurate.
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.