An Approach to Elicit Human-Understandable Robot Expressions to Support Human-Robot Interaction

TL;DR

The approach to elicit and design human-understandable robot expressions is described, enabling more natural human-robot interaction and enabling robot expressions that signal curiosity and interest in getting attention.

Abstract

Understanding the intentions of robots is essential for natural and seamless human-robot collaboration. Ensuring that robots have means for non-verbal communication is a basis for intuitive and implicit interaction. For this, we contribute an approach to elicit and design human-understandable robot expressions. We outline the approach in the context of non-humanoid robots. We paired human mimicking and enactment with research from gesture elicitation in two phases: first, to elicit expressions, and second, to ensure they are understandable. We present an example application through two studies (N=16 \& N=260) of our approach to elicit expressions for a simple 6-DoF robotic arm. We show that it enabled us to design robot expressions that signal curiosity and interest in getting attention. Our main contribution is an approach to generate and validate understandable expressions for robots, enabling more natural human-robot interaction.

Figures (6)

• Figure 1: Procedure of creating human-understandable robot expressions, divided into two phases; Expression Elicitation and Expression Verification leading to a final understandable expressions set.
• Figure 2: Distribution of expressions in six taxonomy categories (c.f., \ref{['tab:expressions']}).
• Figure 3: Two example expressions from our setup to demonstrate the 13 expressions to the participants of the verification study in video form.
• Figure 4: Distribution of groups of different interpretations for each expression. We striped non-matching expressions, c.f., \ref{['tab:expressionscores']}.
• Figure 5: Boxplots of the ten questions we asked for every expression. The top row displays the results for the curiosity questions. The bottom row displays the assessment of perception and impact questions. The scales for intrusive and disturbing are reversed such that 100 always means good.