RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Sixu, Chen, Junliang, Xu, Huaiyuan, Li, Zhuohao, Wang, Guangming, Jing, Yixiong, Xu, Sheng, Zhao, Runyi, Sheil, Brian, Chau, Lap-Pui, Liu, Guiliang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911692132188160
author Lin, Sixu
Chen, Junliang
Xu, Huaiyuan
Li, Zhuohao
Wang, Guangming
Jing, Yixiong
Xu, Sheng
Zhao, Runyi
Sheil, Brian
Chau, Lap-Pui
Liu, Guiliang
author_facet Lin, Sixu
Chen, Junliang
Xu, Huaiyuan
Li, Zhuohao
Wang, Guangming
Jing, Yixiong
Xu, Sheng
Zhao, Runyi
Sheil, Brian
Chau, Lap-Pui
Liu, Guiliang
contents Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular pipelines stacking multiple submodels, resulting in high computational overhead and limited real-time performance. To address these challenges, we introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space. As an end-to-end framework, RoboFlow4D directly predicts multi-frame 3D flows from visual observations and textual instructions, providing explicit flow-based planning to guide action generation. This design allows seamless integration with general action policies, forming an efficient observation-planning-execution closed loop. Through slow-fast collaboration between flow prediction and action control, RoboFlow4D enables real-time and resource-efficient manipulation. Extensive experiments in both simulation and real-world settings demonstrate that RoboFlow4D consistently improves manipulation success rates and computational efficiency, advancing flow-guided planning for embodied intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17522
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
Lin, Sixu
Chen, Junliang
Xu, Huaiyuan
Li, Zhuohao
Wang, Guangming
Jing, Yixiong
Xu, Sheng
Zhao, Runyi
Sheil, Brian
Chau, Lap-Pui
Liu, Guiliang
Robotics
Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular pipelines stacking multiple submodels, resulting in high computational overhead and limited real-time performance. To address these challenges, we introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space. As an end-to-end framework, RoboFlow4D directly predicts multi-frame 3D flows from visual observations and textual instructions, providing explicit flow-based planning to guide action generation. This design allows seamless integration with general action policies, forming an efficient observation-planning-execution closed loop. Through slow-fast collaboration between flow prediction and action control, RoboFlow4D enables real-time and resource-efficient manipulation. Extensive experiments in both simulation and real-world settings demonstrate that RoboFlow4D consistently improves manipulation success rates and computational efficiency, advancing flow-guided planning for embodied intelligence.
title RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2605.17522