Learning Predictive Models for Ergonomic Control of Prosthetic Devices

TL;DR

This paper introduces a novel robot learning framework that predicts and optimizes the biomechanical impact of assistive robot actions on humans, aiming to reduce physical strain during human-robot collaboration.

Contribution

It extends Interaction Primitives to enable predictive biomechanics and integrates this into a model-predictive control strategy for ergonomic assistance.

Findings

Minimizes knee and muscle forces in prosthetic control

Demonstrates effectiveness in synthetic and real-world experiments

Optimizes robot actions for ergonomic safety

Abstract

We present Model-Predictive Interaction Primitives -- a robot learning framework for assistive motion in human-machine collaboration tasks which explicitly accounts for biomechanical impact on the human musculoskeletal system. First, we extend Interaction Primitives to enable predictive biomechanics: the prediction of future biomechanical states of a human partner conditioned on current observations and intended robot control signals. In turn, we leverage this capability within a model-predictive control strategy to identify the future ergonomic and biomechanical ramifications of potential robot actions. Optimal control trajectories are selected so as to minimize future physical impact on the human musculoskeletal system. We empirically demonstrate that our approach minimizes knee or muscle forces via generated control actions selected according to biomechanical cost functions. Experiments are performed in synthetic and real-world experiments involving powered prosthetic devices.