Marine Robotics & Underwater Autonomy
Autonomous Underwater Exploration & Inspection in Visually-degraded EnvironmentsThis work presents the generalization of our exploration path planning stack to the underwater environment using an ROV mapping a submarine bunker.
|
DeepVL: Dynamics and Inertial Measurements-based Deep Velocity Learning for Underwater OdometryThis work presents RNN-based model estimation of underwater robot velocity from proprioceptive data, fused in an EKF for odometry without exteroception. Achieves <4% error in visual blackout and ≈2% with minimal visual input, running in <5 ms on NVIDIA Orin AGX.
|
Online Refractive Camera Model Calibration in Visual Inertial Odometry
This work presents a general refractive camera model and online co-estimation of odometry and the refractive index of unknown media. This enables operation in diverse and varying refractive fluids, given only the camera calibration in air.
|
An Online Self-calibrating Refractive Camera Model with Application to Underwater Odometry
This work presents a camera model for refractive media such as water and its application in underwater visual-inertial odometry. The model is self-calibrating in real-time and is free of known correspondences or calibration targets.
|