SOURCE-LINKED INTELLIGENCE

Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, recent systems use pretrained occupancy networks as world models that complete missing geometry. The predicted structure contributes to expected coverage gain and constrains feasible robot motion. Consequently, occupancy errors can change both what the robot chooses to explore and where it is able to move. We diagnose these effects by holding the planner fixed and varying only the occupancy representation provided to it. We consider planning without

Read original source ↗ Open in workspace

recordType

paper

region

Global