Reacting on human stubbornness in human-machine trajectory planning

TL;DR

This work addresses adaptive human–automation trajectory planning in unstructured care-like environments by enriching an existing negotiation-based framework with a deterministic, continuous stubbornness state $x_{\text{stubb,H}}$ that is inferred from interaction forces $\boldsymbol{F}_{Int}$ and executed trajectories. The authors introduce an observation model $\boldsymbol{o}=f(x_{\text{stubb,H}})$ and formulate $U_{target}(x_{\text{stubb,H}})$ to drive reciprocal tit-for-tat negotiations, enabling the automation to adapt its movement plan when the human is stubborn. A simulated care corridor demonstrates quantifiable stubbornness estimation and targeted automation accommodation, with $\hat{x}_{\text{stubb,H},\omega}$ correlating with $F_{Int,y}$ and $U_{target}$ modulating automation deviation from its preferred trajectory. The framework offers a generalizable approach to tailor automation behavior to human tendencies in joint trajectory tasks, potentially benefiting Care 4.0 applications. Future work includes validating and refining the stubbornness and movement-change desirability estimators in real-world settings.

Abstract

In this paper, a method for a cooperative trajectory planning between a human and an automation is extended by a behavioral model of the human. This model can characterize the stubbornness of the human, which measures how strong the human adheres to his preferred trajectory. Accordingly, a static model is introduced indicating a link between the force in haptically coupled human-robot interactions and humans's stubbornness. The introduced stubbornness parameter enables an application-independent reaction of the automation for the cooperative trajectory planning. Simulation results in the context of human-machine cooperation in a care application show that the proposed behavioral model can quantitatively estimate the stubbornness of the interacting human, enabling a more targeted adaptation of the automation to the human behavior.

Figures (4)

• Figure 1: The application under consideration: Accompanying a patient in a hospital.
• Figure 2: Flowchart of the further developed automation part of cooperative trajectory planning by inserting an additional subsystem for estimating the human stubbornness that results in the parameter $\hat{\boldsymbol{x}}_\text{stubb,H}$ (marked in blue), which represents human's stubbornness.
• Figure 3: Curves for $U_\text{loss}$ for three different variants of parameters $\bar{I}_\text{min}$ and $\bar{I}_\text{max}$.
• Figure 4: Plot of simulation results