Safety
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
arXiv:2603.12639v2 Announce Type: replace Abstract: Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models
arXiv:2603.12639v2 Announce Type: replace Abstract: 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.
Related
- StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
- VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
- ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation
- Dejavu: Towards Experience Feedback Learning for Embodied Intelligence
- Towards provable probabilistic safety for scalable embodied AI systems
Source: arXiv cs.CV | 2026-04-14