MARVO: Marine-Adaptive Radiance-aware Visual Odometry
By: Sacchin Sundar , Atman Kikani , Aaliya Alam and more
Potential Business Impact:
Helps underwater robots see and navigate better.
Underwater visual localization remains challenging due to wavelength-dependent attenuation, poor texture, and non-Gaussian sensor noise. We introduce MARVO, a physics-aware, learning-integrated odometry framework that fuses underwater image formation modeling, differentiable matching, and reinforcement-learning optimization. At the front-end, we extend transformer-based feature matcher with a Physics Aware Radiance Adapter that compensates for color channel attenuation and contrast loss, yielding geometrically consistent feature correspondences under turbidity. These semi dense matches are combined with inertial and pressure measurements inside a factor-graph backend, where we formulate a keyframe-based visual-inertial-barometric estimator using GTSAM library. Each keyframe introduces (i) Pre-integrated IMU motion factors, (ii) MARVO-derived visual pose factors, and (iii) barometric depth priors, giving a full-state MAP estimate in real time. Lastly, we introduce a Reinforcement-Learningbased Pose-Graph Optimizer that refines global trajectories beyond local minima of classical least-squares solvers by learning optimal retraction actions on SE(2).
Similar Papers
Conceptual Evaluation of Deep Visual Stereo Odometry for the MARWIN Radiation Monitoring Robot in Accelerator Tunnels
CV and Pattern Recognition
Robot sees and moves without help in tunnels.
Enhancing Situational Awareness in Underwater Robotics with Multi-modal Spatial Perception
Robotics
Helps robots see and map underwater clearly.
MANTA: Physics-Informed Generalized Underwater Object Tracking
CV and Pattern Recognition
Tracks underwater things better, even in murky water.