Distill: Uncovering the True Intent behind Human-Robot Communication

TL;DR

The paper introduces Distill, a novel human-robot communication interface that refines user intent by simplifying, generalizing, and relaxing task specifications to improve robot understanding.

Contribution

It presents a new approach called Distill that enhances human-robot communication by better capturing true user intent from initial task inputs.

Findings

Distill effectively removes unnecessary steps from user specifications.

It generalizes the meaning behind individual steps to improve flexibility.

Crowdsourcing studies show Distill improves understanding of user intent.

Abstract

As robots become increasingly integrated into everyday environments, intuitive communication paradigms such as natural language and end-user programming have become indispensable for specifying autonomous robot behavior. However, these mechanisms are ineffective at fully capturing user intent: natural language is imprecise and ambiguous, whereas end-user programming can be overly specific. As a result, understanding what users truly mean when they interact with robots remains a central challenge for human-AI communication systems. To address this issue, we propose the Distill approach for human-robot communication interfaces. Given a task specification provided by the user, Distill (1) removes unnecessary steps; (2) generalizes the meaning behind individual steps; and (3) relaxes ordering constraints between steps. We implemented Distill on a web interface and, through a crowdsourcing study, demonstrated its ability to elicit and refine user intent from initial task specifications.