analiza aiqbench
The paper proposes a learned world model for autonomous driving that jointly predicts future 3D occupancy and ego trajectories using flow matching, with a two-stage scene-to-ego design. Its main claim is that keeping explicit semantic geometry, rather than generating pixels as video-based world-action models do, supports planning. The reported state-of-the-art results on Bench2Drive and nuScenes are benchmark-specific, so readers should check whether the gains hold in real-world closed-loop deployment.
OccWAM: Occupancy World-Action Models with Joint Scene-to-Ego Flow Matching
arXiv:2610.17688v1 Announce Type: new Abstract: Occupancy world models provide a structured, metric representation of future driving scenes, making them a promising basis for end-to-end autonomous driving. However, existing occupancy-aware planners typically couple occupancy prediction and action generation through either hierarchical coupling or parallel multi-task learning. Hierarchical methods use occupancy either as a fully predicted future preceding action generation or as an action-conditioned rollout for trajectory evaluation, whereas parallel multi-task methods predict occupancy alongside planning through a separate branch or auxiliary objective. These interfaces retain either an explicit generation order or a role asymmetry, limiting reciprocal interaction between world prediction and action generation during trajectory formation. We propose OccWAM, an occupancy-native world-action model that jointly generates dense future occupancy and continuous ego trajectories via flow matching conditioned on scene representations. Building on this joint formulation, we introduce scene-to-ego world-action flow matching, a two-stage formulation. The first stage predicts scene-centric occupancy together with an absolute ego trajectory, providing a stable representation of future scene evolution. The same predicted world is then re-indexed into the future ego frames induced by the initial trajectory, where ego motion is represented through adjacent pose increments and a second joint flow refines ego-centric occupancy and motion for action-aligned planning. Unlike video-based world-action models, OccWAM preserves explicit semantic geometry for direct planning reasoning without pixel synthesis. Extensive experiments on Bench2Drive and nuScenes demonstrate state-of-the-art performance in closed-loop driving, open-loop planning, and future occupancy prediction.
Abstract:Occupancy world models provide a structured, metric representation of future driving scenes, making them a promising basis for end-to-end autonomous driving. However, existing occupancy-aware planners typically couple occupancy prediction and action generation through either hierarchical coupling or parallel multi-task learning. Hierarchical methods use occupancy either as a fully predicted future preceding action generation or as an action-conditioned rollout for trajectory evaluation, whereas parallel multi-task methods predict occupancy alongside planning through a separate branch or auxiliary objective. These interfaces retain either an explicit generation order or a role asymmetry, limiting reciprocal interaction between world prediction and action generation during trajectory formation. We propose OccWAM, an occupancy-native world-action model that jointly generates dense future occupancy and continuous ego trajectories via flow matching conditioned on scene representations. Building on this joint formulation, we introduce scene-to-ego world-action flow matching, a two-stage formulation. The first stage predicts scene-centric occupancy together with an absolute ego trajectory, providing a stable representation of future scene evolution. The same predicted world is then re-indexed into the future ego frames induced by the initial trajectory, where ego motion is represented through adjacent pose increments and a second joint flow refines ego-centric occupancy and motion for action-aligned planning. Unlike video-based world-action models, OccWAM preserves explicit semantic geometry for direct planning reasoning without pixel synthesis. Extensive experiments on Bench2Drive and nuScenes demonstrate state-of-the-art performance in closed-loop driving, open-loop planning, and future occupancy prediction.
Robotics (cs.RO)
arXiv:2610.17688 [cs.RO]
(or arXiv:2610.17688v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.17688 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 324 cuvinte
Subiecte conexe
Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous Driving
arXiv · 3 aug. 2026
Perception Beyond the Visible: Incompleteness-Aware Scene Understanding for Robot Autonomy
arXiv · 14 oct. 2026
Beyond VLAs: How World Action Models Reshape Robot Manipulation
NVIDIA · 4 aug. 2026
AffordDrive3D: Affordance-Aware World-Action Modeling with Spatial Understanding
arXiv · 10 oct. 2026