Online User Assessment for Minimal Intervention During Task-Based Robotic Assistance

TL;DR

This paper introduces a new human-robot interface evaluation method using the mode insertion gradient (MIG), which assesses user input impact in real-time, enabling minimal intervention and adaptable assistance during task execution.

Contribution

The paper presents a novel MIG-based filtering criterion for human-robot interaction that is minimally invasive, skill-sensitive, and applicable for training and safety assurance.

Findings

MIG correlates negatively with user skill level.

MIG-based assistance improves training outcomes.

Simulation shows MIG ensures task completion and safety.

Abstract

We propose a novel criterion for evaluating user input for human-robot interfaces for known tasks. We use the mode insertion gradient (MIG)---a tool from hybrid control theory---as a filtering criterion that instantaneously assesses the impact of user actions on a dynamic system over a time window into the future. As a result, the filter is permissive to many chosen strategies, minimally engaging, and skill-sensitive---qualities desired when evaluating human actions. Through a human study with 28 healthy volunteers, we show that the criterion exhibits a low, but significant, negative correlation between skill level, as estimated from task-specific measures in unassisted trials, and the rate of controller intervention during assistance. Moreover, a MIG-based filter can be utilized to create a shared control scheme for training or assistance. In the human study, we observe a substantial training effect when using a MIG-based filter to perform cart-pendulum inversion, particularly when comparing improvement via the RMS error measure. Using simulation of a controlled spring-loaded inverted pendulum (SLIP) as a test case, we observe that the MIG criterion could be used for assistance to guarantee either task completion or safety of a joint human-robot system, while maintaining the system's flexibility with respect to user-chosen strategies.