Causal Robot Communication Inspired by Observational Learning Insights

TL;DR

This paper explores how robots can effectively communicate their intentions by identifying and explaining the causal actions within their behavior, drawing inspiration from observational learning in psychology.

Contribution

It introduces the first application of behavior learning insights to enable robots to selectively explain causal actions for improved human-robot interaction.

Findings

Robots can identify key causal actions in their behavior sequences.

Selective explanations improve human understanding of robot intentions.

The approach enhances trust and acceptance in HRI.

Abstract

Autonomous robots must communicate about their decisions to gain trust and acceptance. When doing so, robots must determine which actions are causal, i.e., which directly give rise to the desired outcome, so that these actions can be included in explanations. In behavior learning in psychology, this sort of reasoning during an action sequence has been studied extensively in the context of imitation learning. And yet, these techniques and empirical insights are rarely applied to human-robot interaction (HRI). In this work, we discuss the relevance of behavior learning insights for robot intent communication, and present the first application of these insights for a robot to efficiently communicate its intent by selectively explaining the causal actions in an action sequence.