AQUA-SLAM: Tightly-Coupled Underwater Acoustic-Visual-Inertial SLAM with Sensor Calibration

2025-03-14

AI Summary

Underwater environments severely degrade visual SLAM performance due to low illumination, weak texture, and limited visibility. To address this, we propose AQUA-SLAM—the first tightly coupled acoustic–visual–inertial SLAM framework integrating a Doppler Velocity Log (DVL), stereo camera, and IMU. Our contributions include: (1) a multi-sensor tightly coupled state estimation model formulated as a graph optimization problem using GTSAM; (2) an online-capable, linear calibration method for DVL transducer misalignment and extrinsic parameters; and (3) underwater-adapted stereo feature extraction, DVL velocity observation modeling, and robust tracking strategies. Extensive evaluation on real-world datasets—including a controlled pool environment with ground-truth trajectories and challenging offshore sea trials in the Bohai Sea—demonstrates that AQUA-SLAM achieves significantly higher localization accuracy and robustness compared to state-of-the-art underwater SLAM and VI-SLAM systems. The source code will be made publicly available.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Biometrics, Face, Gesture & Pose
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Underwater environments pose significant challenges for visual Simultaneous Localization and Mapping (SLAM) systems due to limited visibility, inadequate illumination, and sporadic loss of structural features in images. Addressing these challenges, this paper introduces a novel, tightly-coupled Acoustic-Visual-Inertial SLAM approach, termed AQUA-SLAM, to fuse a Doppler Velocity Log (DVL), a stereo camera, and an Inertial Measurement Unit (IMU) within a graph optimization framework. Moreover, we propose an efficient sensor calibration technique, encompassing multi-sensor extrinsic calibration (among the DVL, camera and IMU) and DVL transducer misalignment calibration, with a fast linear approximation procedure for real-time online execution. The proposed methods are extensively evaluated in a tank environment with ground truth, and validated for offshore applications in the North Sea. The results demonstrate that our method surpasses current state-of-the-art underwater and visual-inertial SLAM systems in terms of localization accuracy and robustness. The proposed system will be made open-source for the community.

Problem

• Enhance underwater SLAM accuracy using multi-sensor fusion.
• Address visibility and feature loss in underwater environments.
• Develop real-time sensor calibration for underwater SLAM systems.

Innovation

• Tightly-coupled Acoustic-Visual-Inertial SLAM system
• Efficient multi-sensor extrinsic calibration technique
• Real-time online DVL misalignment calibration