Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kawaharazuka, Kento, Kanazawa, Naoaki, Obinata, Yoshiki, Okada, Kei, Inaba, Masayuki
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914715718909952
author Kawaharazuka, Kento
Kanazawa, Naoaki
Obinata, Yoshiki
Okada, Kei
Inaba, Masayuki
author_facet Kawaharazuka, Kento
Kanazawa, Naoaki
Obinata, Yoshiki
Okada, Kei
Inaba, Masayuki
contents In this study, we develop a simple daily assistive robot that controls its own vision according to linguistic instructions. The robot performs several daily tasks such as recording a user's face, hands, or screen, and remotely capturing images of desired locations. To construct such a robot, we combine a pre-trained large-scale vision-language model with a low-cost low-rigidity robot arm. The correlation between the robot's physical and visual information is learned probabilistically using a neural network, and changes in the probability distribution based on changes in time and environment are considered by parametric bias, which is a learnable network input variable. We demonstrate the effectiveness of this learning method by open-vocabulary view control experiments with an actual robot arm, MyCobot.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07451
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model
Kawaharazuka, Kento
Kanazawa, Naoaki
Obinata, Yoshiki
Okada, Kei
Inaba, Masayuki
Robotics
In this study, we develop a simple daily assistive robot that controls its own vision according to linguistic instructions. The robot performs several daily tasks such as recording a user's face, hands, or screen, and remotely capturing images of desired locations. To construct such a robot, we combine a pre-trained large-scale vision-language model with a low-cost low-rigidity robot arm. The correlation between the robot's physical and visual information is learned probabilistically using a neural network, and changes in the probability distribution based on changes in time and environment are considered by parametric bias, which is a learnable network input variable. We demonstrate the effectiveness of this learning method by open-vocabulary view control experiments with an actual robot arm, MyCobot.
title Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model
topic Robotics
url https://arxiv.org/abs/2312.07451