# Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping

arXiv: https://arxiv.org/abs/2609.06820 · HTML: https://mlsanity.com/paper/2609.06820/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)

## Builds on (most cited first, 22 of 22)

- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)
- [ActiveNeRF: Learning where to See with Uncertainty Estimation](https://mlsanity.com/paper/2209.08546/) (2022)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [Occupancy Anticipation for Efficient Exploration and Navigation](https://mlsanity.com/paper/2008.09285/) (2020)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [FUEL: Fast UAV Exploration using Incremental Frontier Structure and Hierarchical Planning](https://mlsanity.com/paper/2010.11561/) (2020)
- [EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding](https://mlsanity.com/paper/2412.04380/) (2024)
- [Uncertainty-driven Planner for Exploration and Navigation](https://mlsanity.com/paper/2202.11907/) (2022)
- [Active Neural Mapping](https://mlsanity.com/paper/2308.16246/) (2023)
- [NARUTO: Neural Active Reconstruction from Uncertain Target Observations](https://mlsanity.com/paper/2402.18771/) (2024)
- [MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision](https://mlsanity.com/paper/2303.03315/) (2023)
- [SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration](https://mlsanity.com/paper/2208.10449/) (2022)
- [NextBestPath: Efficient 3D Mapping of Unseen Environments](https://mlsanity.com/paper/2502.05378/) (2025)
- [MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping](https://mlsanity.com/paper/2603.22650/) (2026)
- [Dynamic Feature Alignment for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2110.09641/) (2021)
- [Real-time Mapping of Physical Scene Properties with an Autonomous Robot Experimenter](https://mlsanity.com/paper/2210.17325/) (2022)

## Abstract (arXiv)

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 completion, with learned occupancy, with false positives removed by a ground truth oracle, with false negatives restored by an oracle, and with ground truth occupancy. Our experiments show that correcting false positives or false negatives alone does not consistently improve final coverage. This finding reveals a gap between occupancy accuracy and downstream planning performance. Ground truth occupancy provides a much larger improvement in coverage efficiency than in endpoint coverage, suggesting that planning and reachability remain important bottlenecks even when the geometric world model is accurate. Based on these findings, we introduce a dynamic filtering strategy that preserves predictions in unexplored space while suppressing repeatedly unsupported occupancy using online observations. Preliminary examples show that this strategy can redirect viewpoint selection toward reachable surfaces that would otherwise remain unobserved.