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

2026-09-26

AI Summary

This study addresses the unreliability of monocular depth estimation caused by underwater visual degradation, which compromises autonomous navigation safety. To overcome this limitation, we propose AquaBEV, a model that bypasses explicit depth dependency by directly predicting bird's-eye-view (BEV) occupancy through a polar-coordinate causal reasoning architecture. By integrating the CORAL hierarchical exploration framework with vision-language models (VLMs), our approach enables high-level semantic planning and dynamic trajectory generation. Experimental evaluations in simulated reef environments demonstrate that the proposed method achieves a structural IoU of 37.48% and a closed-loop coverage rate of 88.95%, while maintaining a zero-collision record. These results indicate that AquaBEV provides a highly robust spatial perception and safe navigation solution for underwater robots operating in complex aquatic environments.

Abstract

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.

Problem

• underwater navigation
• underwater exploration
• bird's-eye-view occupancy
• monocular depth estimation
• visual degradation

Innovation

• Bird's-Eye-View Occupancy
• Underwater Navigation
• Monocular Depth Bypass
• Causal Reasoning
• Vision-Language Model Planning