# AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Exploration

arXiv: https://arxiv.org/abs/2609.32156 · HTML: https://mlsanity.com/paper/2609.32156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction](https://mlsanity.com/paper/2412.04384/) (2024)
- [Navigation in the Presence of Obstacles for an Agile Autonomous Underwater Vehicle](https://mlsanity.com/paper/1903.11750/) (2019)
- [High-Speed Robot Navigation using Predicted Occupancy Maps](https://mlsanity.com/paper/2012.12142/) (2020)
- [AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles](https://mlsanity.com/paper/2110.01646/) (2021)
- [OceanPlan: Hierarchical Planning and Replanning for Natural Language AUV Piloting in Large-scale Unexplored Ocean Environments](https://mlsanity.com/paper/2403.15369/) (2024)
- [UIVNAV: Underwater Information-driven Vision-based Navigation via Imitation Learning](https://mlsanity.com/paper/2309.08806/) (2023)
- [Demonstrating CavePI: Autonomous Exploration of Underwater Caves by Semantic Guidance](https://mlsanity.com/paper/2502.05384/) (2025)
- [Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection](https://mlsanity.com/paper/2603.05623/) (2026)
- [PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2412.07616/) (2024)
- [AquaChat++: LLM-Assisted Multi-ROV Inspection for Aquaculture Net Pens with Integrated Battery Management and Thruster Fault Tolerance](https://mlsanity.com/paper/2508.06554/) (2025)
- [DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring](https://mlsanity.com/paper/2509.13666/) (2025)
- [CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater Monitoring](https://mlsanity.com/paper/2603.14786/) (2026)
- [uScenes: A Multimodal RGB and 3D Sonar Dataset for Underwater Robot Perception](https://mlsanity.com/paper/2608.27795/) (2026)
- [A Novel Occupancy Mapping Framework for Risk-Aware Path Planning in Unstructured Environments](https://mlsanity.com/paper/2011.08045/) (2020)
- [AquaBEV: Monocular Underwater BEV Occupancy with 3D Sonar Supervision](https://mlsanity.com/paper/2609.04411/) (2026)

## Abstract (arXiv)

Safe underwater exploration requires a robot to understand where surrounding structures are located and which regions are available for motion. Existing vision-based underwater exploration systems commonly obtain this information indirectly by estimating monocular depth, unprojecting the geometry into 3D space, and accumulating it into a 2D bird's-eye-view occupancy map. This reliance on intermediate depth estimation is particularly problematic underwater, where scattering and wavelength-dependent attenuation degrade visual cues and limit the reliability of monocular depth estimates. We introduce AquaBEV-Nav, an underwater exploration framework that bypasses explicit monocular depth estimation through direct bird's-eye-view occupancy prediction. Built upon the CORAL hierarchical exploration framework, AquaBEV-Nav replaces its depth-based perception front end with AquaBEV. Given a single RGB frame, AquaBEV maps visual features into a learned polar representation, performs causal reasoning along the range dimension, and reconstructs local Cartesian occupancy without relying on intermediate depth prediction. The resulting occupancy map is accumulated into CORAL's persistent spatial memory, providing spatial context for VLM-based high-level planning and collision constraints for dynamics-aware local trajectory generation. Across ten simulated reef environments and six occupancy backbones evaluated under a single protocol, AquaBEV-Nav reaches 37.48 structure IoU and 53.2 target IoU, 88.95% closed-loop coverage with zero collisions.