Predicting Human Behavior in Autonomous Systems: A Collaborative Machine Teaching Approach for Reducing Transfer of Control Events

TL;DR

This paper presents a data-driven, human-behavior-based machine teaching method using LSTM models to predict user actions, reducing unnecessary control transfers in autonomous systems, thereby improving reliability and human-AI collaboration.

Contribution

It introduces a novel approach that leverages human interaction data to train AI models for proactive fault handling in autonomous systems, reducing unnecessary interventions.

Findings

Non-expert data effectively trains models to predict user behavior.

Predicted behaviors can reduce unnecessary transfer of control events.

Approach enhances system robustness and human-AI collaboration.

Abstract

As autonomous systems become integral to various industries, effective strategies for fault handling are essential to ensure reliability and efficiency. Transfer of Control (ToC), a traditional approach for interrupting automated processes during faults, is often triggered unnecessarily in non-critical situations. To address this, we propose a data-driven method that uses human interaction data to train AI models capable of preemptively identifying and addressing issues or assisting users in resolution. Using an interactive tool simulating an industrial vacuum cleaner, we collected data and developed an LSTM-based model to predict user behavior. Our findings reveal that even data from non-experts can effectively train models to reduce unnecessary ToC events, enhancing the system's robustness. This approach highlights the potential of AI to learn directly from human problem-solving behaviors, complementing sensor data to improve industrial automation and human-AI collaboration.