Interactive Perception for Deformable Object Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Weng, Zehang, Zhou, Peng, Yin, Hang, Kravberg, Alexander, Varava, Anastasiia, Navarro-Alarcon, David, Kragic, Danica
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916452015013888
author Weng, Zehang
Zhou, Peng
Yin, Hang
Kravberg, Alexander
Varava, Anastasiia
Navarro-Alarcon, David
Kragic, Danica
author_facet Weng, Zehang
Zhou, Peng
Yin, Hang
Kravberg, Alexander
Varava, Anastasiia
Navarro-Alarcon, David
Kragic, Danica
contents Interactive perception enables robots to manipulate the environment and objects to bring them into states that benefit the perception process. Deformable objects pose challenges to this due to significant manipulation difficulty and occlusion in vision-based perception. In this work, we address such a problem with a setup involving both an active camera and an object manipulator. Our approach is based on a sequential decision-making framework and explicitly considers the motion regularity and structure in coupling the camera and manipulator. We contribute a method for constructing and computing a subspace, called Dynamic Active Vision Space (DAVS), for effectively utilizing the regularity in motion exploration. The effectiveness of the framework and approach are validated in both a simulation and a real dual-arm robot setup. Our results confirm the necessity of an active camera and coordinative motion in interactive perception for deformable objects.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive Perception for Deformable Object Manipulation
Weng, Zehang
Zhou, Peng
Yin, Hang
Kravberg, Alexander
Varava, Anastasiia
Navarro-Alarcon, David
Kragic, Danica
Robotics
Interactive perception enables robots to manipulate the environment and objects to bring them into states that benefit the perception process. Deformable objects pose challenges to this due to significant manipulation difficulty and occlusion in vision-based perception. In this work, we address such a problem with a setup involving both an active camera and an object manipulator. Our approach is based on a sequential decision-making framework and explicitly considers the motion regularity and structure in coupling the camera and manipulator. We contribute a method for constructing and computing a subspace, called Dynamic Active Vision Space (DAVS), for effectively utilizing the regularity in motion exploration. The effectiveness of the framework and approach are validated in both a simulation and a real dual-arm robot setup. Our results confirm the necessity of an active camera and coordinative motion in interactive perception for deformable objects.
title Interactive Perception for Deformable Object Manipulation
topic Robotics
url https://arxiv.org/abs/2403.05177