Autonomous Navigation for Underwater Vehicles
Vision-Based Navigation Underwater
This work studies the problem of autonomous navigation for unmanned underwater vehicles, using computer vision for localization. Parallel Tracking and Mapping (PTAM) is employed to locate the vehicle with respect to a visual map, using a single camera, while an Extended Kalman Filter (EKF) is used to fuse the visual information with inertial measurements from an Inertial Measurement Unit (IMU), in order to recover the scale of the map and improve the pose estimation. A PID controller with compensation of the restoring forces is proposed to accomplish trajectory tracking, where a pressure sensor and a magnetometer provide feedback for depth control and yaw, respectively, while the remaining states are provided by the EKF. Real-time experiments are presented to validate the navigation strategy, using a commercial Remotely Operated Vehicle (ROV), the BlueROV2, which was adapte to perform as an Autonomous Underwater Vehicle (AUV) with the help of the Robot Operative System (ROS).
A) AUV in an autonomous mission using vision based localization. B) A frontal camera in the vehicle is used to obtain the feature points for localization. C) Map generated by the PTAM algorithm for localization
Autonomous trajectory tracking using vision-based localization: x, y, z, ψ. Desired (solid red line) vs estimated (dashed blue line) position; x coordinate response on top, y coordinate on the top center, z coordinate on the bottom center and yaw (ψ) on the bottom.
Autonomous trajectory tracking using vision-based localization: aerial view. Desired trajectory (solid red line) vs estimated rajectory (dashed blue line).
Videos
Publications
[J5] A. Manzanilla, S. Reyes, M. Garcia, D. Mercado* and R. Lozano. Autonomous Navigation for Unmanned Underwater Vehicles: Real-Time Experiments using Computer Vision. IEEE Robotics and Automation Letters (RA-L) and ICRA19 presentation, vol. 4, no. 2, pp. 1351-1356, April 2019. doi: 10.1109/LRA.2019.2895272. [download]