Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Saborio, Juan Carlos, Hertzberg, Joachim
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910716602089472
author Saborio, Juan Carlos
Hertzberg, Joachim
author_facet Saborio, Juan Carlos
Hertzberg, Joachim
contents Intention recognition, or the ability to anticipate the actions of another agent, plays a vital role in the design and development of automated assistants that can support humans in their daily tasks. In particular, industrial settings pose interesting challenges that include potential distractions for a decision-maker as well as noisy or incomplete observations. In such a setting, a robotic assistant tasked with helping and supporting a human worker must interleave information gathering actions with proactive tasks of its own, an approach that has been referred to as active goal recognition. In this paper we describe a partially observable model for online intention recognition, show some preliminary experimental results and discuss some of the challenges present in this family of problems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17326
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning
Saborio, Juan Carlos
Hertzberg, Joachim
Artificial Intelligence
Robotics
Intention recognition, or the ability to anticipate the actions of another agent, plays a vital role in the design and development of automated assistants that can support humans in their daily tasks. In particular, industrial settings pose interesting challenges that include potential distractions for a decision-maker as well as noisy or incomplete observations. In such a setting, a robotic assistant tasked with helping and supporting a human worker must interleave information gathering actions with proactive tasks of its own, an approach that has been referred to as active goal recognition. In this paper we describe a partially observable model for online intention recognition, show some preliminary experimental results and discuss some of the challenges present in this family of problems.
title Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2411.17326