ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation

arXiv:2604.11386v1 Announce Type: cross Abstract: Recent advancements in foundational models, such as large language models and world models, have greatly enhanced the capabilities of robotics, enabling robots to autonomously perform complex tasks. However, acquiring large-scale, high-quality training data for robotics remains a challenge, as it often requires substantial manual effort and is limited in its coverage of diverse real-world environments. To address this, we propose a novel hybrid approach called Compositional Simulation, which combines classical simulation and neural simulation to generate accurate action-video pairs while maintaining real-world consistency. Our approach utilizes a closed-loop real-sim-real data augmentation pipeline, leveraging a small amount of real-world data to generate diverse, large-scale training datasets that cover a broader spectrum of real-world scenarios. We train a neural simulator to transform classical simulation videos into real-world representations, improving the accuracy of policy models trained in real-world environments. Through extensive experiments, we demonstrate that our method significantly reduces the sim2real domain gap, resulting in higher success rates in real-world policy model training. Our approach offers a scalable solution for generating robust training data and bridging the gap between simulated and real-world robotics.

Related

• VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
• EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
• RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
• ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
• AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Source: arXiv cs.CV | 2026-04-14