Close-Proximity Underwater Terrain Mapping Using Learning-based Coarse Range Estimation

TL;DR

This paper introduces a learning-based monocular vision method for close-proximity underwater terrain mapping, enabling autonomous underwater vehicles to create accurate elevation maps for obstacle avoidance in complex 3D environments.

Contribution

It presents a novel probabilistic mapping approach that integrates a scene range estimator with uncertainty modeling for improved underwater terrain mapping.

Findings

Effective in filtering transient objects like fish and lighting variations.

Accurate terrain reconstruction demonstrated in simulated and real reef environments.

Feasible for obstacle detection and range estimation using monocular cameras.

Abstract

This paper presents a novel approach to underwater terrain mapping for Autonomous Underwater Vehicles (AUVs) operating in close proximity to complex 3D environments. The proposed methodology creates a probabilistic elevation map of the terrain using a monocular image learning-based scene range estimator as a sensor. This scene range estimator can filter transient objects such as fish and lighting variations. The mapping approach considers uncertainty in both the estimated scene range and robot pose as the AUV moves through the environment. The resulting elevation map can be used for reactive path planning and obstacle avoidance to allow robotic systems to approach the underwater terrain as closely as possible. The performance of our approach is evaluated in a simulated underwater environment by comparing the reconstructed terrain to ground truth reference maps, as well as demonstrated using AUV field data collected within in a coral reef environment. The simulations and field results show that the proposed approach is feasible for obstacle detection and range estimation using a monocular camera in reef environments.