RoboStereo: 双塔4D具身世界模型用于统一策略优化
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
AI总结：
本文提出RoboStereo，通过双塔4D具身世界模型实现统一策略优化，解决几何幻觉和缺乏统一优化框架的问题，实验显示在细粒度操作任务中平均相对提升超过97%。
摘要：
可扩展的具身AI面临由于现实世界交互成本和安全风险的根本限制。尽管具身世界模型（EWMs）通过想象的模拟卷出提供希望，但现有方法存在几何幻觉且缺乏统一的优化框架。我们引入RoboStereo，一种对称的双塔4D世界模型，通过双向跨模态增强确保时空几何一致性并缓解物理幻觉。基于此高保真4D模拟器，我们提出首个基于世界模型的策略优化统一框架：（1）测试时策略增强（TTPA）用于预执行验证，（2）模仿-进化策略学习（IEPL）利用视觉感知奖励学习专家示范，（3）开放探索策略学习（OEPL）实现自主技能发现和自我修正。全面实验表明RoboStereo在生成质量上达到最先进的水平，我们的统一框架在细粒度操作任务中实现平均相对提升超过97%。
英文摘要：
Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models (EWMs) offer promise through imagined rollouts, existing approaches suffer from geometric hallucinations and lack unified optimization frameworks for practical policy improvement. We introduce RoboStereo, a symmetric dual-tower 4D world model that employs bidirectional cross-modal enhancement to ensure spatiotemporal geometric consistency and alleviate physics hallucinations. Building upon this high-fidelity 4D simulator, we present the first unified framework for world-model-based policy optimization: (1) Test-Time Policy Augmentation (TTPA) for pre-execution verification, (2) Imitative-Evolutionary Policy Learning (IEPL) leveraging visual perceptual rewards to learn from expert demonstrations, and (3) Open-Exploration Policy Learning (OEPL) enabling autonomous skill discovery and self-correction. Comprehensive experiments demonstrate RoboStereo achieves state-of-the-art generation quality, with our unified framework delivering >97% average relative improvement on fine-grained manipulation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
