Event
SVIn+: A Multimodal Underwater State Estimation Framework
1 reports · 1 sources
Chinmay Burgul and other authors propose SVIn+, a multi-sensor state estimation framework for autonomous underwater vehicles (AUVs). Building on the open-source visual-inertial SLAM system SVIn, it incorporates water pressure and DVL measurements into tightly coupled nonlinear optimization, and uses KISS-ICP to decouple the front end to generate relative pose factors, incorporating 3D sonar structural information into the factor graph. The authors report that in field deployments in shipwreck and coral reef scenarios, the framework suppresses drift and maintains global consistency. The paper has been accepted to IROS 2026, and the code and dataset have been made publicly available on the project website.
Report timeline
- SVIn+: An Underwater State Estimation Framework Integrating 3D Sonar, Visual-Inertial, Water Pressure, and DVL
SVIn+ is a multi-sensor state estimation framework for autonomous underwater vehicles (AUVs). Building on the open-source visual-inertial SLAM system SVIn, it integrates water-pressure and DVL measurements into tightly coupled nonlinear optimization and uses a KISS-ICP decoupled front end to generate relative pose factors, incorporating 3D sonar structural information into the factor graph. The authors conducted field deployments in shipwreck and coral reef scenarios, validating drift suppression and global consistency. The paper was accepted to IROS 2026, and the code and datasets have been released on the project website.
arXiv cs.RO ·