Modeling Human Temporal Uncertainty in Human-Agent Teams

TL;DR

This paper investigates how to model human timing uncertainty in human-robot collaboration, proposing that heavy-tailed distributions, especially Log-Normal, best represent human temporal variability to improve scheduling and fluency.

Contribution

It introduces an online collaborative game to collect data and demonstrates that heavy-tailed distributions effectively model human timing uncertainty, informing future scheduling methods.

Findings

Heavy-tailed distributions fit human timing data well

Log-Normal distribution provides the best fit

Online game facilitates data collection for modeling

Abstract

Automated scheduling is potentially a very useful tool for facilitating efficient, intuitive interactions between a robot and a human teammate. However, a current gapin automated scheduling is that it is not well understood how to best represent the timing uncertainty that human teammates introduce. This paper attempts to address this gap by designing an online human-robot collaborative packaging game that we use to build a model of human timing uncertainty from a population of crowd-workers. We conclude that heavy-tailed distributions are the best models of human temporal uncertainty, with a Log-Normal distribution achieving the best fit to our experimental data. We discuss how these results along with our collaborative online game will inform and facilitate future explorations into scheduling for improved human-robot fluency.