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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jeongeun, Lim, Seungwon, Lee, Joonhyung, Park, Sangbeom, Chang, Minsuk, Yu, Youngjae, Choi, Sungjoon
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913405083844608
author Park, Jeongeun
Lim, Seungwon
Lee, Joonhyung
Park, Sangbeom
Chang, Minsuk
Yu, Youngjae
Choi, Sungjoon
author_facet Park, Jeongeun
Lim, Seungwon
Lee, Joonhyung
Park, Sangbeom
Chang, Minsuk
Yu, Youngjae
Choi, Sungjoon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2306_10376
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents
Park, Jeongeun
Lim, Seungwon
Lee, Joonhyung
Park, Sangbeom
Chang, Minsuk
Yu, Youngjae
Choi, Sungjoon
Robotics
Artificial Intelligence
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.
title CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2306.10376