Designing for Error Recovery in Human-Robot Interaction

TL;DR

This paper discusses the importance of designing human-robot interaction systems capable of error detection and recovery, emphasizing continuous, interactive decision-making over one-shot approaches.

Contribution

It highlights challenges and proposes initial design ideas for enabling robots to recover from errors, using robotic nuclear gloveboxes as a case study.

Findings

Robots often lack error recovery capabilities in interactive tasks.

Error recovery enhances success rates in human-robot collaboration.

Initial design strategies can improve system robustness.

Abstract

This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the performance of one individual system to beyond so-called human baselines. However, these systems often look at one shot and one-way decisions, whereas the real world is more continuous and interactive. Humans, however, are often able to recover from and learn from errors - enabling a much higher rate of success. We look at the challenges of building a system that can detect/recover from its own errors, using the example of robotic nuclear gloveboxes as a use case to help illustrate examples. We then go on to talk about simple starting designs.