OccWAM: Occupancy World-Action Models with Joint Scene-to-Ego Flow Matching
Overview
OccWAM is a new world-action model for autonomous driving that jointly generates dense future occupancy and continuous ego trajectories via flow matching. It improves closed-loop driving, open-loop planning, and future occupancy prediction performance on Bench2Drive and nuScenes.,
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsOccWAM: Occupancy World-Action Models with Joint Scene-to-Ego Flow Matching
OccWAM is a new world-action model for autonomous driving that jointly generates dense future occupancy and continuous ego trajectories via flow matching conditioned on scene representations. It introduces a two-stage scene-to-ego world-action flow matching formulation, improving closed-loop driving, open-loop planning, and future occupancy prediction performance.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).