Orbis 2: A Hierarchical World Model for Driving
Researchers introduce Orbis 2, a hierarchical world model for autonomous driving that separates future prediction into two levels: a high-level predictor for coarse scene structure over long time horizons and a low-level generator for detailed predictions. The model is trained in two stages, first with diffusion forcing pretraining to enhance internal representations, followed by teacher forcing fine-tuning for stable rollouts. Orbis 2 achieves state-of-the-art results on standard driving world model benchmarks, including long-horizon generation fidelity and steering responsiveness.
Why it matters: This work demonstrates a significant advance in autonomous driving world models by combining long-horizon spatial reasoning with high perceptual fidelity, leading to improved performance and internal representations.
Full story at: arXiv Robotics ↗