RoboDream: Compositional World Models for Scalable Robot Data Synthesis

• URL: http://arxiv.org/abs/2606.02577v1
• Date: Mon, 01 Jun 2026 17:59:38 GMT
• Title: RoboDream: Compositional World Models for Scalable Robot Data Synthesis
• Abstract summary: Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming.<n>We present a generalizable embodiment-centric world model that achieves scalable data generation by synthesizing demonstrations with novel objects.<n>We demonstrate with real-world experiments that our generated data consistently improves downstream policy performance and significantly reduces real-world data requirements across diverse manipulation tasks.
• Score: 31.864551794584667
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming. While video diffusion models offer a promising avenue for data scaling, existing generative approaches are often limited to superficial visual augmentation, or suffer from embodiment hallucinations that yield physically infeasible motions. We present a generalizable embodiment-centric world model that achieves scalable data generation by synthesizing photorealistic demonstrations with novel objects, in novel scenes, and from novel viewpoints. Our approach anchors generation to rendered robot motion while conditioning on explicit scene and object priors, effectively decoupling trajectory execution from environment synthesis. This formulation has the potential to unlock two powerful data scaling capabilities: (1) retrieval and rebirth, which repurposes existing trajectories into entirely new contexts without new motion data; and (2) prop-free teleoperation, where operators manipulate empty air and the model hallucinates the target objects and scene afterwards, eliminating reset time. We demonstrate with real-world experiments that our generated data consistently improves downstream policy performance and significantly reduces real-world data requirements across diverse manipulation tasks.

Related papers

• Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation [55.42006264038458]
  Action-conditioned world models have emerged as a promising paradigm for robot learning.<n>Mem-World is a memory-augmented multi-view action-conditioned world model.<n>We present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements.
  arXiv  Detail & Related papers  (2026-06-17T11:42:00Z)
• OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation [51.37436817948304]
  OASIS is a simulation-data-driven framework for humanoid loco-manipulation.<n>It reconstructs realistic object assets from real-world images using a 3D generative model.<n>Under zero-shot deployment, it achieves higher success rates on most tasks than that trained on real-robot teleoperation data.
  arXiv  Detail & Related papers  (2026-06-07T10:01:53Z)
• Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation [9.875136212706165]
  Controllable human video generation aims to produce realistic videos of humans with explicitly guided motions and appearances.<n>Synthetic data provides a scalable and controllable alternative.<n>Our study offers the first comprehensive exploration of synthetic data's role in human-centric video synthesis.
  arXiv  Detail & Related papers  (2026-04-23T05:10:15Z)
• SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation [45.71119158785489]
  We introduce SoftMimicGen, an automated data generation pipeline for deformable object manipulation tasks.<n>We introduce a suite of high-fidelity simulation environments that encompasses a wide range of deformable objects.<n>We apply SoftMimicGen to generate datasets across the task suite, train high-performing policies from the data, and systematically analyze the data generation system.
  arXiv  Detail & Related papers  (2026-03-26T17:58:40Z)
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos [110.98100817695307]
  We introduce DreamDojo, a foundation world model that learns diverse interactions and dexterous controls from 44k hours of egocentric human videos.<n>Our work enables several important applications based on generative world models, including live teleoperation, policy evaluation, and model-based planning.
  arXiv  Detail & Related papers  (2026-02-06T18:49:43Z)
• Mirage2Matter: A Physically Grounded Gaussian World Model from Video [87.9732484393686]
  We present Simulate Anything, a graphics-driven world modeling and simulation framework.<n>Our approach reconstructs real-world environments into a photorealistic scene representation using 3D Gaussian Splatting (3DGS)<n>We then leverage generative models to recover a physically realistic representation and integrate it into a simulation environment via a precision calibration target.
  arXiv  Detail & Related papers  (2026-01-24T07:43:57Z)
• AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis [33.90053396451562]
  We introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis.<n>Our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling.<n>Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies.
  arXiv  Detail & Related papers  (2025-12-12T18:59:45Z)
• Synthetic Dataset Generation for Autonomous Mobile Robots Using 3D Gaussian Splatting for Vision Training [0.708987965338602]
  We propose a novel method for automatically generating annotated synthetic data in Unreal Engine.<n>We demonstrate that synthetic datasets can achieve performance comparable to that of real-world datasets.<n>This is the first application of synthetic data for training object detection algorithms in robot soccer.
  arXiv  Detail & Related papers  (2025-06-05T14:37:40Z)
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models [120.25799361925387]
  DreamGen is a pipeline for training robot policies that generalize across behaviors and environments through neural trajectories.<n>Our work establishes a promising new axis for scaling robot learning well beyond manual data collection.
  arXiv  Detail & Related papers  (2025-05-19T04:55:39Z)
• Scaling Up Dynamic Human-Scene Interaction Modeling [58.032368564071895]
  TRUMANS is the most comprehensive motion-captured HSI dataset currently available. It intricately captures whole-body human motions and part-level object dynamics. We devise a diffusion-based autoregressive model that efficiently generates HSI sequences of any length.
  arXiv  Detail & Related papers  (2024-03-13T15:45:04Z)
• Future Urban Scenes Generation Through Vehicles Synthesis [90.1731992199415]
  We propose a deep learning pipeline to predict the visual future appearance of an urban scene. We follow a two stages approach, where interpretable information is included in the loop and each actor is modelled independently. We show the superiority of this approach over traditional end-to-end scene-generation methods on CityFlow.
  arXiv  Detail & Related papers  (2020-07-01T08:40:16Z)

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.