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

• URL: http://arxiv.org/abs/2605.17522v1
• Date: Sun, 17 May 2026 16:11:22 GMT
• Title: RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
• Abstract summary: Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world.<n>We introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space.
• Score: 29.85979864354417
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation [18.092834753587454]
  FlowPilot is a compact world-action model for real-time onboard UAV navigation from depth.<n>A dual-stream mixture-of-transformers couples video and action experts through shared attention, allowing future-scene prediction and trajectory generation to inform each other.
  arXiv  Detail & Related papers  (2026-08-01T12:43:31Z)
• WAM4D: Fast 4D World Action Model via Spatial Register Tokens [52.16661403052964]
  We present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts.<n>We show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.
  arXiv  Detail & Related papers  (2026-06-12T02:49:34Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• An Efficient and Multi-Modal Navigation System with One-Step World Model [11.582535121562247]
  Current navigation world models rely on multi-step diffusion processes and autoregressive frame-by-frame generation.<n>We propose a one-step generation paradigm and a 3D U-Net backbone equipped with efficient spatial-temporal attention.<n>This design drastically reduces inference latency, enabling high-frequency control while achieving superior predictive performance.
  arXiv  Detail & Related papers  (2026-01-18T06:29:56Z)
• FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation [34.045199714747596]
  FlowRAM is a novel framework that leverages generative models to achieve region-aware perception.<n>FlowRAM is able to generate physically plausible actions for a variety of real-world tasks in less than 4 time steps.
  arXiv  Detail & Related papers  (2025-06-19T10:30:02Z)
• SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining [62.433137130087445]
  SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs.<n>We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions.<n>With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
  arXiv  Detail & Related papers  (2025-03-25T17:59:57Z)
• An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training [50.71892161377806]
  DFIT-OccWorld is an efficient 3D occupancy world model that leverages decoupled dynamic flow and image-assisted training strategy.<n>Our model forecasts future dynamic voxels by warping existing observations using voxel flow, whereas static voxels are easily obtained through pose transformation.
  arXiv  Detail & Related papers  (2024-12-18T12:10:33Z)
• G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation [65.86819811007157]
  We present G3Flow, a novel framework that constructs real-time semantic flow, a dynamic, object-centric 3D representation by leveraging foundation models.<n>Our approach uniquely combines 3D generative models for digital twin creation, vision foundation models for semantic feature extraction, and robust pose tracking for continuous semantic flow updates.<n>Our results demonstrate the effectiveness of G3Flow in enhancing real-time dynamic semantic feature understanding for robotic manipulation policies.
  arXiv  Detail & Related papers  (2024-11-27T14:17:43Z)
• Dynamic Tube MPC: Learning Tube Dynamics with Massively Parallel Simulation for Robust Safety in Practice [28.37162791852146]
  Inevitable tracking error necessitates robustification of the nominal plan to ensure safety. In this work, we present a novel method leveraging massively parallel simulation to learn a dynamic tube representation. The resulting Dynamic MPC Tube is applied to the 3D hopping robot ARCHER.
  arXiv  Detail & Related papers  (2024-11-22T21:22:51Z)
• Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction [14.866463843514156]
  Let Occ Flow is the first self-supervised work for joint 3D occupancy and occupancy flow prediction using only camera inputs. Our approach incorporates a novel attention-based temporal fusion module to capture dynamic object dependencies. Our method extends differentiable rendering to 3D volumetric flow fields.
  arXiv  Detail & Related papers  (2024-07-10T12:20:11Z)
• FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation [87.74617110803189]
  Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision. We present a recurrent architecture that learns a single step of an unrolled iterative alignment procedure for refining scene flow predictions.
  arXiv  Detail & Related papers  (2020-11-19T23:23:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.