Data-driven Force Observer for Human-Robot Interaction with Series Elastic Actuators using Gaussian Processes

TL;DR

This paper presents a novel data-driven force observer for human-robot interaction that leverages Gaussian processes to learn unknown dynamics, improving force estimation accuracy and safety in elastic actuator systems.

Contribution

It introduces a Gaussian process-based learning approach integrated into a Bayesian filter for better force estimation with uncertainty quantification in elastic actuators.

Findings

Enhanced force estimation accuracy demonstrated experimentally.

Explicit uncertainty measures improve safety in human-robot interaction.

Guaranteed error bounds facilitate safe deployment in critical applications.

Abstract

Ensuring safety and adapting to the user's behavior are of paramount importance in physical human-robot interaction. Thus, incorporating elastic actuators in the robot's mechanical design has become popular, since it offers intrinsic compliance and additionally provide a coarse estimate for the interaction force by measuring the deformation of the elastic components. While observer-based methods have been shown to improve these estimates, they rely on accurate models of the system, which are challenging to obtain in complex operating environments. In this work, we overcome this issue by learning the unknown dynamics components using Gaussian process (GP) regression. By employing the learned model in a Bayesian filtering framework, we improve the estimation accuracy and additionally obtain an observer that explicitly considers local model uncertainty in the confidence measure of the state estimate. Furthermore, we derive guaranteed estimation error bounds, thus, facilitating the use in safety-critical applications. We demonstrate the effectiveness of the proposed approach experimentally in a human-exoskeleton interaction scenario.