AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles

TL;DR

AquaVis is a real-time, perception-aware navigation framework enabling underwater robots to efficiently track multiple visual targets and avoid obstacles, optimizing visibility in complex 3D underwater environments.

Contribution

It introduces the first real-time, visibility-aware motion planning framework for AUVs with arbitrary camera setups, enhancing tracking and obstacle avoidance capabilities.

Findings

Significant improvement in tracking multiple points of interest.

Low computational overhead and fast re-planning times.

Effective in real-time for single or multiple camera configurations.

Abstract

Visual monitoring operations underwater require both observing the objects of interest in close-proximity, and tracking the few feature-rich areas necessary for state estimation.This paper introduces the first navigation framework, called AquaVis, that produces on-line visibility-aware motion plans that enable Autonomous Underwater Vehicles (AUVs) to track multiple visual objectives with an arbitrary camera configuration in real-time. Using the proposed pipeline, AUVs can efficiently move in 3D, reach their goals while avoiding obstacles safely, and maximizing the visibility of multiple objectives along the path within a specified proximity. The method is sufficiently fast to be executed in real-time and is suitable for single or multiple camera configurations. Experimental results show the significant improvement on tracking multiple automatically-extracted points of interest, with low computational overhead and fast re-planning times