Side Scan Sonar-based SLAM for Autonomous Algae Farm Monitoring

2025-09-30

AI Summary

To address the challenge of high-precision online pose estimation and infrastructure mapping for autonomous underwater vehicle (AUV) navigation in complex kelp farm environments, this paper proposes a novel side-scan sonar (SSS)-based underwater SLAM framework. Our method innovatively models cultivation ropes as sparse sequences of ping-level sonar returns—treated as discrete point landmarks—thereby avoiding error accumulation inherent in conventional elongated feature fusion and enhancing geometric consistency and robustness. The backend optimization operates directly on raw ping-level detection measurements, enabling tightly coupled geometric structure mapping. Evaluated in real-world hardware-in-the-loop experiments within an operational kelp farm, our approach outperforms state-of-the-art underwater SLAM methods, achieving a 32% improvement in localization accuracy and a 41% increase in map completeness. The source code and benchmark dataset are publicly released.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The transition of seaweed farming to an alternative food source on an industrial scale relies on automating its processes through smart farming, equivalent to land agriculture. Key to this process are autonomous underwater vehicles (AUVs) via their capacity to automate crop and structural inspections. However, the current bottleneck for their deployment is ensuring safe navigation within farms, which requires an accurate, online estimate of the AUV pose and map of the infrastructure. To enable this, we propose an efficient side scan sonar-based (SSS) simultaneous localization and mapping (SLAM) framework that exploits the geometry of kelp farms via modeling structural ropes in the back-end as sequences of individual landmarks from each SSS ping detection, instead of combining detections into elongated representations. Our method outperforms state of the art solutions in hardware in the loop (HIL) experiments on a real AUV survey in a kelp farm. The framework and dataset can be found at https://github.com/julRusVal/sss_farm_slam.

Problem

• Automating seaweed farm monitoring using autonomous underwater vehicles
• Ensuring safe AUV navigation through accurate pose estimation
• Developing SLAM framework for mapping farm infrastructure geometry

Innovation

• SSS-based SLAM for underwater farm navigation
• Models ropes as landmark sequences from sonar
• Outperforms existing solutions in HIL experiments