Papers for

hobbyist underwater vehicle builders

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Visual inertial slam enables low cost underwater autonomous navigation

Towards Effective Visual-Inertial SLAM with Passive-Only Sensors for Low-Cost Autonomous Underwater Vehicles

Abstract: Improvements to Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) for low-cost autonomous underwater vehicles (AUVs) are critical for transitioning advanced marine robotics from specialized labs to broader research and hobbyist applications. While high-end AUVs typically rely on expensive sensor suites - such as Doppler Velocity Logs (DVLs) and Ultra-Short Baseline (USBL) systems - this work demonstrates that robust, high-quality navigation is achievable using a sub-$10, 000(USD) platform equipped only with inexpensive consumer-grade sensors. By leveraging a similarly priced, open-source AUV, we evaluate the performance of stereo cameras, Micro-electromechanical System (MEMS)-based IMUs, and depth sensors in a fully unconstrained 6-degree-of-freedom (6-DOF) underwater environment. We analyze the efficacy of off-the-shelf SLAM packages and propose optimizations for sensor fusion to mitigate the visual and physical challenges of untethered underwater operation. Our results prove that a usable SLAM solution can be accessible to the masses, providing a benchmark for expectations in demanding, real-time maritime missions without the financial barrier of industrial-grade hardware.

Thu 17 SeptRobotics
The gist
Navigating underwater with robots is usually expensive because it needs special sensors. This paper shows that good navigation can be done using simple and cheap cameras and motion sensors instead. The researchers tested their approach on a low-cost underwater robot and improved how these sensors work together to handle challenges underwater. Their work makes underwater mapping and navigation more accessible for hobbyists and small labs.
Open → 2609.21015v1