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

TL;DR

RoboFlow4D introduces a lightweight, end-to-end 3D flow prediction model that enhances real-time robotic manipulation by unifying perception and planning, significantly improving efficiency and success rates.

Contribution

It presents RoboFlow4D, a novel unified flow world model that directly predicts multi-frame 3D flows from visual and textual inputs for real-time robotic manipulation.

Findings

Improves manipulation success rates in simulation and real-world tests.

Achieves real-time performance with lower computational overhead.

Enhances flow-guided planning efficiency for embodied intelligence.

Abstract

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.