Back to SAS Lab

Event Summary

RSS 2014 Workshop on
Autonomous Control, Adaptation, and Learning for Underwater Vehicles
1-Day Workshop
Berkeley, CA
Date: July 12, 2014
Location: Wheeler 130

Web Address:
http://drexelsaslab.appspot.com/workshops/rss2014/index.html

Point of Contact:

Ryan N. Smith
Fort Lewis College
Email: rnsmith _at_ fortlewis _dot_ edu
Web: http://www.ryannealsmith.com/


Call for Extended Abstracts

Start of page

Event Abstract

There has been a steady increase in the deployment of autonomous underwater and surface vehicles (AUVs and ASVs) for applications such as hazardous waste mitigation, inspection and recovery of marine structures, environmental monitoring, and tracking of various biological, chemical, and physical processes. These emerging applications require solving unique challenges that arise when working in the underwater environment. The lack of reliable wireless communications between robots and a base station or with other robots makes remote control difficult; underwater vehicle dynamics are tightly coupled with the environmental dynamics making controls hard; and wellunderstood perception technologies do not always apply to the underwater environment. These challenges, in addition to our limited understanding of the complexities of the fluidic environment, make closed-loop control, online learning, and adaptive decision making challenging at best.

The purpose of this workshop is to bring together experts in the highly interdisciplinary field of autonomous underwater robotics to bridge the gap between (1) modeling and prediction for closed-loop control and (2) online learning and adaptation in highly dynamic and uncertain environments. Specifically we would like to highlight new work that lies at the intersection of robotics, control theory, artificial intelligence, machine learning, ocean science, and transport theory that addresses issues in modeling and prediction of the underwater environment. The techniques developed in this workshop will lead to improvements in control, learning, and adaptation for underwater systems that are paramount to achieving prolonged persistent autonomy in these environments.

Start of page

Intended Audience

This workshop is targeted at researchers in the general robotics communities interested in underwater robotics applications. Researchers in machine learning, artificial intelligence, and oceanography will also find the topics of interest. Specifically, we are targeting audiences in the aquatic robotics community who are interested in topics related to:

  • Motion planning and Control
  • Environmentally constrained Path Planning
  • Single and Multi-Agent Control
  • Modeling and Prediction of Dynamic and Uncertain Environments
  • Online Learning
  • Distributed Control
  • Coordination of Heterogeneous Systems
  • Applications in Field Robotics
  • Cloud Robotics
  • Novel Testbeds, Actuators and Sensors

The proposed workshop will continue to expand on progress made in prior RSS workshops run by the coorganizers. The RSS 2013 workshop on Robotic Exploration, Monitoring, and Information worked towards developing learning and planning techniques necessary for longterm autonomy. However, the focus of this prior workshop was on general algorithmic techniques, and the specific requirements for underwater systems were not addressed.

We additionally propose to extend the reach of previous workshops at RSS (2011, 2012, 2013), IROS (2011, 2012) on Robotics for Environmental Monitoring, and ICRA (2012, 2013) on Many Robot Systems: Crossing the Reality Gap that were all run and/or attended by all of the coorganizers. Through this workshop series we have noticed a recurring need in the community for a dissemination and discussion venue focused primarily on the control and autonomy of underwater vehicles and vehicles operating in communication and localizationlimited environments. The robotics for environmental monitoring community addresses a broad range of application-driven problems, however many researchers face the fundamental problems of navigation, communication and data acquisition; this is the primary focus of the proposed workshop.

Start of page

Invited Speakers

Christopher Clark, Harvey Mudd College, Confirmed
Geoff Hollinger, Oregon State University, Confirmed
Franz Hover, MIT, Confirmed
M. Ani Hsieh, Drexel University, Confirmed
Ryan Smith, Fort Lewis College, Confirmed
Fumin Zhang, GA Tech, Confirmed
Ryan Eustice, University of Michigan, Confirmed
David P. Williams, NATO CMRE, Confirmed
Doug Horner, Naval Postgraduate School, Confirmed
Noel DuToit, Naval Postgraduate School, Confirmed


Start of page

List of Panel Speakers

S.K. Gupta, NSF, Confirmed
Jason Stack, ONR, Confirmed but Tentative
Marc Steinberg, ONR, Confirmed but Tentative


Start of page

Workshop Program

This proposed workshop will be a full day workshop consisting of a combination of invited keynote talks, oral and/or poster presentations, and a panel discussion. Invited keynote speakers will include leading academic and government representatives and experts in the various areas of underwater robotic systems. We will solicit submissions in the form of extended abstracts (2 pages) to select additional oral and/or poster presentations. The workshop will conclude with a two panel discussions on key technical challenges.

Detailed program is available here.

09:00-09:15 Welcome & Introduction by the Organizers
09:15-09:30 Geoff Hollinger (OSU)
Human-robot Underwater Data Collection
09:30-09:45 Ryan Eustice (U Mich)
An Adaptive Active Visual SLAM Framework for Real-Time Area Coverage
09:45-10:00 David P. Williams (NATO CMRE)
Adaptive Mine Countermeasures Using Intelligent Autonomous Underwater Vehicles
10:00-10:15 Christopher Clark (Harvey Mudd)
Underwater Robot Control and Estimation Developments Driven by Marine Science and Archeology
10:15-10:30 Doug Horner (NPS)
Undersea Autonomy in Extreme Environments, Part I
10:30-11:00 Coffee Break
11:00-11:15 Noel DuToit (NPS)
Undersea Autonomy in Extreme Environments, Part II
11:15-11:30 Poster Spotlights
11:30-12:30 Poster Session
12:30-14:00 Lunch Break
14:00-14:15 Franz Hover (MIT)
Oceanographic Pursuit: Networked Control of Multiple Vehicles Tracking Dynamic Ocean Features
14:15-14:30 Ani Hsieh (Drexel)
Controlling Basin Breakout for Autonomous Vehicles in Geophysical Flows
14:30-14:45 Fumin Zhang (GA Tech)
Glider CT: Reconstructing Flow Field Through Guided Motion
14:45-13:00 Ryan Smith (Fort Lewis)
Priors and Persistence in Aquatic Monitoring with Autonomous Robots
15:00-15:30 Coffee Break
15:30-16:45 Government Panel Discussion
Panelists: SK Gupta (NSF), Jason Stack (ONR), Marc Steinberg (ONR)
16:45-17:30 Open Panel Discussion Conducted by the Workshop Organizers


Start of page

Event Organizers

Geoff Hollinger
Oregon State University
Email: geoff _dot_ hollinger _at_ oregonstate _dot_ edu
Web: http://research.engr.oregonstate.edu/rdml/

M. Ani Hsieh
Drexel University
Email: mhsieh1 _at_ drexel _dot_ edu
Web: http://drexelsaslab.appspot.com/

Franz Hover
Massachusetts Institute of Technology
Email: hover _at_ mit _dot_ edu
Web: http://web.mit.edu/hovergroup/

Ryan N. Smith (Contact)
Fort Lewis College
Email: rnsmith _at_ fortlewis _dot_ edu
Web: http://www.ryannealsmith.com/


Start of page