A study on the effects of mixed explicit and implicit communications in human-artificial-agent interactions

TL;DR

Task-related measures, such as time, number of errors, and perceived efficiency of the interaction, as well as the impact of the communication on them, are more sensitive to the type of task and the difficulty level, whereas the combination of explicit and implicit communications more consistently improves human perceptions about artificial agents.

Abstract

Communication between humans and artificial agents is essential for their interaction. This is often inspired by human communication, which uses gestures, facial expressions, gaze direction, and other explicit and implicit means. This work presents interaction experiments where humans and artificial agents interact through explicit and implicit communication to evaluate the effect of mixed explicit-implicit communication against purely explicit communication and the impact of the task difficulty in this evaluation. Results obtained using Bayesian parameter estimation show that the task execution time did not significantly change when mixed explicit and implicit communications were used in neither of our experiments, which varied in the type of artificial agent (virtual agent and humanoid robot) used and task difficulty. The number of errors was affected by the communication only when the human was executing a more difficult task, and an impact on the perceived efficiency of the interaction was only observed in the interaction with the robot, for both easy and difficult tasks. In contrast, acceptance, sociability, and transparency of the artificial agent increased when using mixed communication modalities in both our experiments and task difficulty levels. This suggests that task-related measures, such as time, number of errors, and perceived efficiency of the interaction, as well as the impact of the communication on them, are more sensitive to the type of task and the difficulty level, whereas the combination of explicit and implicit communications more consistently improves human perceptions about artificial agents.

Figures (14)

• Figure 1: Two virtual agents created to interact with people in the experiments.
• Figure 2: Illustrations of the proposed interaction.
• Figure 3: Example of prior and posterior probability distributions for parameter values in the Bayesian estimation. The $95\%$ HDI includes $95\%$ of the posterior distribution and the most credible parameter values.
• Figure 4: Examples of possible relations between the $95\%$ HDI of the posterior distribution and a ROPE around a value of interest, $\alpha_{0}$, for the parameter.
• Figure 5: Examples of t distributions with mean $\mu$, scale $\tau$, and different normality parameters $\nu$. The greater $\nu$ is, the closer the t distribution is to a normal distribution. The scale $\tau$ is related to the spread of the data and covers $50\%$ of the t distribution with $\nu=1$ and $68\%$ of the distribution with $\nu=\infty$.