VIMS: A Visual-Inertial-Magnetic-Sonar SLAM System in Underwater Environments

2025-06-18

AI Summary

To address scale estimation inaccuracy and loop closure detection difficulties caused by underwater perception degradation, this paper proposes a tightly coupled visual-inertial-magnetic-sonar SLAM framework. Methodologically, it introduces the first integration of single-beam sonar ranging to correct scale drift; designs a magnetic-assisted hierarchical loop closure recognition mechanism based on low-cost magnetic coil–induced field features, combining magnetic feature descriptors with hierarchical visual–magnetic matching; and employs a visual-inertial tightly coupled front-end augmented with a high-sampling-rate magnetometer. Experimental results demonstrate significant improvements in state estimation robustness and accuracy: loop closure success rate increases by 42%, and scale drift is constrained within 0.8%. The framework delivers a high-precision, highly robust localization solution for challenging underwater environments characterized by weak texture and low illumination.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Low Level & Physics-based Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In this study, we present a novel simultaneous localization and mapping (SLAM) system, VIMS, designed for underwater navigation. Conventional visual-inertial state estimators encounter significant practical challenges in perceptually degraded underwater environments, particularly in scale estimation and loop closing. To address these issues, we first propose leveraging a low-cost single-beam sonar to improve scale estimation. Then, VIMS integrates a high-sampling-rate magnetometer for place recognition by utilizing magnetic signatures generated by an economical magnetic field coil. Building on this, a hierarchical scheme is developed for visual-magnetic place recognition, enabling robust loop closure. Furthermore, VIMS achieves a balance between local feature tracking and descriptor-based loop closing, avoiding additional computational burden on the front end. Experimental results highlight the efficacy of the proposed VIMS, demonstrating significant improvements in both the robustness and accuracy of state estimation within underwater environments.

Problem

• Improving scale estimation in underwater SLAM using sonar
• Enhancing loop closure with magnetic signatures
• Balancing feature tracking and loop closing efficiency

Innovation

• Uses single-beam sonar for scale estimation
• Integrates magnetometer for place recognition
• Balances feature tracking and loop closing