Bioinspired SLAM Approach for Unmanned Surface Vehicle

2025-09-23

AI Summary

Unmanned surface vehicles (USVs) operating in GPS-denied waterways require lightweight, computationally efficient visual-inertial SLAM for robust navigation. Method: Inspired by hippocampal navigation mechanisms, this work adapts the RatSLAM framework to USVs—reimplementing OpenRatSLAM2 on ROS2 and tightly fusing monocular vision with IMU measurements to achieve a resource-efficient visual-inertial SLAM system. A scene-specific parameter tuning strategy is introduced to ensure stable pose estimation and semi-metric map construction in constrained waterway environments. Contribution/Results: Evaluated on a custom waterway dataset, the approach achieves mean orientation error <0.5° and position error <2% of total traveled distance—meeting typical robotic application accuracy requirements and significantly outperforming pure visual SLAM. This work establishes a deployable, interpretable, biologically inspired navigation paradigm for resource-constrained USVs.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Biometrics, Face, Gesture & Pose
• 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: Efficiency and scalability of Web search engines
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

This paper presents OpenRatSLAM2, a new version of OpenRatSLAM - a bioinspired SLAM framework based on computational models of the rodent hippocampus. OpenRatSLAM2 delivers low-computation-cost visual-inertial based SLAM, suitable for GPS-denied environments. Our contributions include a ROS2-based architecture, experimental results on new waterway datasets, and insights into system parameter tuning. This work represents the first known application of RatSLAM on USVs. The estimated trajectory was compared with ground truth data using the Hausdorff distance. The results show that the algorithm can generate a semimetric map with an error margin acceptable for most robotic applications.

Problem

• Develops bioinspired SLAM for unmanned surface vehicles in GPS-denied environments
• Creates low-computation visual-inertial SLAM suitable for waterway navigation
• Validates algorithm accuracy using ground truth comparison metrics

Innovation

• Bioinspired SLAM based on rodent hippocampus models
• Low-computation visual-inertial SLAM for GPS-denied environments
• ROS2-based architecture with parameter tuning insights