Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Feng, Yao, Xiang, Chendong, Mao, Xinyi, Tan, Hengkai, Zhang, Zuyue, Huang, Shuhe, Zheng, Kaiwen, Liu, Haitian, Su, Hang, Zhu, Jun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.17661
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918256275619840
author Feng, Yao
Xiang, Chendong
Mao, Xinyi
Tan, Hengkai
Zhang, Zuyue
Huang, Shuhe
Zheng, Kaiwen
Liu, Haitian
Su, Hang
Zhu, Jun
author_facet Feng, Yao
Xiang, Chendong
Mao, Xinyi
Tan, Hengkai
Zhang, Zuyue
Huang, Shuhe
Zheng, Kaiwen
Liu, Haitian
Su, Hang
Zhu, Jun
contents Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent video-based approaches have shown great promise in capturing and transferring the temporal and physical interactions by pre-training on Internet-scale video data. However, such methods are often not optimized for the embodiment-specific closed-loop control, typically suffering from high latency and insufficient grounding. In this paper, we present Vidarc (Video Diffusion for Action Reasoning and Closed-loop Control), a novel autoregressive embodied video diffusion approach augmented by a masked inverse dynamics model. By grounding video predictions with action-relevant masks and incorporating real-time feedback through cached autoregressive generation, Vidarc achieves fast, accurate closed-loop control. Pre-trained on one million cross-embodiment episodes, Vidarc surpasses state-of-the-art baselines, achieving at least a 15% higher success rate in real-world deployment and a 91% reduction in latency. We also highlight its robust generalization and error correction capabilities across previously unseen robotic platforms.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17661
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vidarc: Embodied Video Diffusion Model for Closed-loop Control
Feng, Yao
Xiang, Chendong
Mao, Xinyi
Tan, Hengkai
Zhang, Zuyue
Huang, Shuhe
Zheng, Kaiwen
Liu, Haitian
Su, Hang
Zhu, Jun
Robotics
Machine Learning
Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent video-based approaches have shown great promise in capturing and transferring the temporal and physical interactions by pre-training on Internet-scale video data. However, such methods are often not optimized for the embodiment-specific closed-loop control, typically suffering from high latency and insufficient grounding. In this paper, we present Vidarc (Video Diffusion for Action Reasoning and Closed-loop Control), a novel autoregressive embodied video diffusion approach augmented by a masked inverse dynamics model. By grounding video predictions with action-relevant masks and incorporating real-time feedback through cached autoregressive generation, Vidarc achieves fast, accurate closed-loop control. Pre-trained on one million cross-embodiment episodes, Vidarc surpasses state-of-the-art baselines, achieving at least a 15% higher success rate in real-world deployment and a 91% reduction in latency. We also highlight its robust generalization and error correction capabilities across previously unseen robotic platforms.
title Vidarc: Embodied Video Diffusion Model for Closed-loop Control
topic Robotics
Machine Learning
url https://arxiv.org/abs/2512.17661