Back to Publications

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

Authors: Marios Xanthidis, Michail Kalaitzakis, Nare Karapetyan, James Johnson, Nikolaos Vitzilaios, Jason O'Kane, Ioannis Rekleitis

Abstract: Visual monitoring operations underwater require both observing in close-proximity the objects of interest, 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.

PDF Video
@inproceedings{XanthidisIROS2021, author = {Marios Xanthidis and Michail Kalaitzakis and Nare Karapetyan and James Johnson and Nikolaos Vitzilaios and Jason O'Kane and Ioannis Rekleitis}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, title = {AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles}, year = {2021}, volume = {}, number = {}, pages = {5387-5394}, keywords = {}, doi = {10.1109/IROS51168.2021.9636124} }