CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents

TL;DR

This paper introduces a method for classifying and disambiguating user commands in robotic systems using large language models, improving reliability by accurately identifying command clarity and handling ambiguity or infeasibility.

Contribution

The paper presents a novel uncertainty estimation approach and a zero-shot disambiguation method for user commands in robotic interactions, along with a new dataset and real-world validation.

Findings

Effective classification of command certainty improves robot reliability.

Zero-shot disambiguation reduces misunderstandings in human-robot interactions.

Validated approach in simulation and real-world scenarios.

Abstract

In this paper, we focus on inferring whether the given user command is clear, ambiguous, or infeasible in the context of interactive robotic agents utilizing large language models (LLMs). To tackle this problem, we first present an uncertainty estimation method for LLMs to classify whether the command is certain (i.e., clear) or not (i.e., ambiguous or infeasible). Once the command is classified as uncertain, we further distinguish it between ambiguous or infeasible commands leveraging LLMs with situational aware context in a zero-shot manner. For ambiguous commands, we disambiguate the command by interacting with users via question generation with LLMs. We believe that proper recognition of the given commands could lead to a decrease in malfunction and undesired actions of the robot, enhancing the reliability of interactive robot agents. We present a dataset for robotic situational awareness, consisting pair of high-level commands, scene descriptions, and labels of command type (i.e., clear, ambiguous, or infeasible). We validate the proposed method on the collected dataset, pick-and-place tabletop simulation. Finally, we demonstrate the proposed approach in real-world human-robot interaction experiments, i.e., handover scenarios.