DIVO: Continuous-time DVL-Inertial-Visual Odometry for Unmanned Underwater Vehicles
2026-07-06 • Robotics
Robotics
AI summaryⓘ
The authors developed a new method to help underwater robots understand their position using sound, cameras, and motion sensors together. They created a system that combines these different data types continuously over time, which helps the robot keep track of where it is even in tricky underwater conditions like poor lighting and cloudy water. Their system includes a new way for the robot to pick out important visual details using machine learning, making it better at working underwater. Tests with real underwater data showed their approach is more accurate and reliable than existing methods.
acoustic-visual-inertial odometrycontinuous-time trajectory estimationGaussian processesDoppler velocity logstereo camerainertial measurement unitvisual trackingfeature extractionsimultaneous localization and mapping (SLAM)underwater robotics
Authors
Kyungmin Jung, Angad Bajwa, Junha Yoo, Arturo Del Castillo Bernal, James Richard Forbes
Abstract
This paper presents a novel acoustic-visual-inertial odometry solution leveraging a continuous-time trajectory estimation framework for unmanned underwater vehicles. Underwater environments present unique challenges for visual localization and mapping, such as light attenuation, illumination variance, and the presence of particulate matter. This motivates the use of additional sensing modalities and a visual tracking pipeline that is robust to diverse subsea conditions. The proposed system is the first continuous-time trajectory estimation framework based on Gaussian processes to fuse asynchronous measurements from a Doppler velocity log, a stereo camera, and an inertial measurement unit. Additionally, a novel visual frontend is proposed, incorporating learning-based feature extraction and matching that is robust to the specific challenges that subsea environments present. The proposed framework enables seamless integration of additional sensor modalities in continuous-time and is adaptable to different environments without reconfiguration. The proposed system is extensively tested on real-world underwater inspection datasets, where it outperforms state-of-the-art visual-inertial and acoustic-visual-inertial SLAM algorithms in accuracy, robustness, and trajectory coverage. Notably, the proposed system outperforms the state-of-the-art despite only forming short-term visual data associations.