Control, Modeling, and Perception of Autonomous Systems (CoMPAS) Laboratory seeks to build scalable marine robotics foundations — from creating the basic tools to enabling the main research lines for future developments. We aim to enable exploration without previous knowledge of the environment (such as seafloor maps) in complex terrain with multiple platforms. Based on addressing the fundamental technology challenges will allow getting closer to achieve persistence presence, ocean visualization, adaptive targeted sampling, environmental change detection, and repeated monitoring of the ocean, from benthic to midwater.

The major efforts expected over the next three years in marine robotics include:

  • Scalable Navigation: Enabling Simultaneous localization and mapping (SLAM) approach for known and unknown environments based on visual and acoustic information.
  • Scalable Control: Enabling advanced control in complex environments.
  • Scalable Platforms: Enabling multi-vehicle solutions with homogeneous/heterogeneous platforms.

Those are key elements for the autonomy of marine robotics platforms to enable multi-vehicle operations.

Team

Directory

CoMPAS Lab is directed by Giancarlo Troni, Assistant Professor at Pontificia Universidad Católica de Chile

Projects

All Projects

Publications

All Publications

Supplemental resources

Magnetometer and Gyroscope Calibration

Fuentes-Guíñez, J., G. Troni, and H. Lobel. 2025. SPLASH-SegFormer Pipeline: A Transformer-Based Approach for High-Resolution and Low-Cost Laser Scanner Seafloor Mapping. IEEE Robotics and Automation Letters, 10(8):7995–8002. https://doi.org/10.1109/LRA.2025.3577520

Bhat, S., G. Troni, and I. Stenius. 2026. Online learning for agile underwater maneuvering: Gaussian processes and sparse regression for data-driven model predictive control. Robotics and Autonomous Systems, 195(105211). https://doi.org/10.1016/j.robot.2025.105211

Correa, A., S. Rodríguez-Martínez, and G. Troni. 2024. Deep Reinforcement Learning Trajectory Control of Nonholonomic Autonomous Surface Vehicles in Challenging Wave Conditions: Theory and Preliminary Evaluation. IEEE/OES Autonomous Underwater Vehicles Symposium (AUV), Boston, MA, USA, 2024,1–6. https://doi.org/10.1109/AUV61864.2024.11030777

Sufán, V. and G. Troni. 2025. Swim4Real: Deep Reinforcement Learning-Based Energy-Efficient and Agile 6-DOF Control for Underwater Vehicles. IEEE Robotics and Automation Letters, 10(7): 7326-7333. https://doi.org/10.1109/LRA.2025.3575650

Rodríguez-Martínez, S., and G. Troni. 2025. Full magnetometer and gyroscope bias estimation using angular rates: Theory and experimental evaluation of a factor graph-based approach. IEEE Journal of Oceanic Engineering, 1–10. https://doi.org/10.1109/JOE.2024.3523701. Learn more.

Latest News

All News

Technologies

All Technologies

Data

All Data