Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Wei, Li, Gongsheng, Gong, Zhefei, Ding, Pengxiang, Zhao, Han, Wang, Donglin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909612743065600
author Zhao, Wei
Li, Gongsheng
Gong, Zhefei
Ding, Pengxiang
Zhao, Han
Wang, Donglin
author_facet Zhao, Wei
Li, Gongsheng
Gong, Zhefei
Ding, Pengxiang
Zhao, Han
Wang, Donglin
contents Vision-Language-Action (VLA) models have recently become highly prominent in the field of robotics. Leveraging vision-language foundation models trained on large-scale internet data, the VLA model can generate robotic actions directly from visual observations and human instructions through a single end-to-end neural network. Despite their effectiveness, current VLA models usually accept only one form of human prompting, language instructions, which may constrain their applicability in open-ended human-robot interactions. For example, a user might expect the robot to retrieve an object shown in an image, follow an instruction written on the whiteboard, or imitate a behavior demonstrated in a video, rather than relying solely on language-based descriptions. To address this gap, we introduce OE-VLA, which explores the potential of VLA models for open-ended multimodal instructions. Extensive results demonstrate that our OE-VLA not only achieves comparable performance to traditional VLA models with linguistic input but also delivers impressive results across four additional categories of open-ended tasks. The proposed methodology could significantly expand the applications of VLA models across various everyday scenarios and facilitate human-robot interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11214
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
Zhao, Wei
Li, Gongsheng
Gong, Zhefei
Ding, Pengxiang
Zhao, Han
Wang, Donglin
Robotics
Vision-Language-Action (VLA) models have recently become highly prominent in the field of robotics. Leveraging vision-language foundation models trained on large-scale internet data, the VLA model can generate robotic actions directly from visual observations and human instructions through a single end-to-end neural network. Despite their effectiveness, current VLA models usually accept only one form of human prompting, language instructions, which may constrain their applicability in open-ended human-robot interactions. For example, a user might expect the robot to retrieve an object shown in an image, follow an instruction written on the whiteboard, or imitate a behavior demonstrated in a video, rather than relying solely on language-based descriptions. To address this gap, we introduce OE-VLA, which explores the potential of VLA models for open-ended multimodal instructions. Extensive results demonstrate that our OE-VLA not only achieves comparable performance to traditional VLA models with linguistic input but also delivers impressive results across four additional categories of open-ended tasks. The proposed methodology could significantly expand the applications of VLA models across various everyday scenarios and facilitate human-robot interaction.
title Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
topic Robotics
url https://arxiv.org/abs/2505.11214