Informing Real-time Corrections in Corrective Shared Autonomy Through Expert Demonstrations

TL;DR

This paper introduces a Learning from Demonstration approach to improve real-time corrections in Corrective Shared Autonomy, enabling robots to better interpret and apply human corrections during tasks like surface cleaning.

Contribution

It presents an automated method to extract nominal behavior and determine correction strategies, enhancing the flexibility and effectiveness of Corrective Shared Autonomy systems.

Findings

Users successfully completed a surface cleaning task using the method.

The system identified different user correction strategies.

The evaluation suggests potential for future improvements.

Abstract

Corrective Shared Autonomy is a method where human corrections are layered on top of an otherwise autonomous robot behavior. Specifically, a Corrective Shared Autonomy system leverages an external controller to allow corrections across a range of task variables (e.g., spinning speed of a tool, applied force, path) to address the specific needs of a task. However, this inherent flexibility makes the choice of what corrections to allow at any given instant difficult to determine. This choice of corrections includes determining appropriate robot state variables, scaling for these variables, and a way to allow a user to specify the corrections in an intuitive manner. This paper enables efficient Corrective Shared Autonomy by providing an automated solution based on Learning from Demonstration to both extract the nominal behavior and address these core problems. Our evaluation shows that this solution enables users to successfully complete a surface cleaning task, identifies different strategies users employed in applying corrections, and points to future improvements for our solution.