Autonomous adaptive environmental assessment and feature tracking via autonomous underwater vehicles
Name
Schmidt_Autonomous adaptive.pdf
Size
1.87 MB
Format
Adobe PDF
Checksum (MD5)
f673afd27de5a2a2eddefa295a7e375f
Author(s)
Petillo, Stephanie Marie
Balasuriya, Arjuna Prabhath
Schmidt, Henrik
Date Issued
May 2010
Journal
OCEANS 2010 IEEE - Sydney
Publisher
Institute of Electrical and Electronics Engineers
Citation
Petillo, Stephanie, Arjuna Balasuriya, and Henrik Schmidt. Autonomous Adaptive Environmental Assessment and Feature Tracking via Autonomous Underwater Vehicles. In OCEANS 10 IEEE SYDNEY, 1-9. Institute of Electrical and Electronics Engineers. © 2010 IEEE.
Version
Final published version
Abstract
In the underwater environment, spatiotemporally dynamic environmental conditions pose challenges to the detection and tracking of hydrographic features. A useful tool in combating these challenge is Autonomous Adaptive Environmental Assessment (AAEA) employed on board Autonomous Underwater Vehicles (AUVs). AAEA is a process by which an AUV autonomously assesses the hydrographic environment it is swimming through in real-time, effectively detecting hydro-graphic features in the area. This feature detection process leads naturally to the subsequent active/adaptive tracking of a selected feature. Due to certain restrictions in operating AUVs this detection-tracking feedback loop setup with AAEA can only rely on having an AUV's self-collected hydrographic data (e.g., temperature, conductivity, and/or pressure readings) available. With a basic quantitative definition of an underwater feature of interest, an algorithm can be developed (with which a data set is evaluated) to detect said feature. One example of feature tracking with AAEA explored in this paper is tracking the marine thermocline. The AAEA process for thermocline tracking is outlined here from quantitatively defining the thermocline region and calculating thermal gradients, all the way through simulation and implementation of the process on AUVs. Adaptation to varying feature properties, scales, and other challenges in bringing the concept of feature tracking with AAEA into implementation in field experiments is addressed, and results from two recent field experiments are presented.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Department of Ocean Engineering
Massachusetts Institute of Technology. Laboratory for Autonomous Marine Sensing Systems
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/OCEANSSYD.2010.5603513
