Towards Versatile Opti-Acoustic Sensor Fusion and Volumetric Mapping

2026-03-15

AI Summary

This work addresses the challenges of underwater 3D mapping in turbid or cluttered environments, where optical sensors fail and sonar suffers from low resolution and elevation ambiguity. The authors propose a multimodal 3D mapping approach that fuses stereo sonar with a monocular camera: overlapping sonar fields of view resolve elevation ambiguity, while visual height cues combined with sonar range measurements generate confidence-weighted 3D point clouds. These are integrated within a Gaussian process voxel mapping framework to prioritize reliable observations. This method represents the first implementation of collaborative mapping using stereo sonar and monocular vision, incorporating a confidence-weighting mechanism that significantly improves reconstruction accuracy of complex structures and enhances navigation safety in both clear and turbid water conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Accurate 3D volumetric mapping is critical for autonomous underwater vehicles operating in obstacle-rich environments. Vision-based perception provides high-resolution data but fails in turbid conditions, while sonar is robust to lighting and turbidity but suffers from low resolution and elevation ambiguity. This paper presents a volumetric mapping framework that fuses a stereo sonar pair with a monocular camera to enable safe navigation under varying visibility conditions. Overlapping sonar fields of view resolve elevation ambiguity, producing fully defined 3D point clouds at each time step. The framework identifies regions of interest in camera images, associates them with corresponding sonar returns, and combines sonar range with camera-derived elevation cues to generate additional 3D points. Each 3D point is assigned a confidence value reflecting its reliability. These confidence-weighted points are fused using a Gaussian Process Volumetric Mapping framework that prioritizes the most reliable measurements. Experimental comparisons with other opti-acoustic and sonar-based approaches, along with field tests in a marina environment, demonstrate the method's effectiveness in capturing complex geometries and preserving critical information for robot navigation in both clear and turbid conditions. Our code is open-source to support community adoption.

Problem

• volumetric mapping
• opti-acoustic sensor fusion
• autonomous underwater vehicles
• elevation ambiguity
• turbid conditions

Innovation

• opti-acoustic fusion
• volumetric mapping
• elevation disambiguation
• confidence-weighted point fusion
• Gaussian Process mapping