IEEE SCV Robotics & Automation Society

Date and Time

Wednesday, June 4, 7:00PM Pacific
at 7:00, 5-minute business meeting
at 7:05, speaker presentation

Location

Carnegie Mellon University West Coast (directions https://west.cmu.edu/who_we_are/visitor)

Title

Adaptive Control for Autonomous Underwater Vehicles

Speaker

Conor McGann, Monterey Bay Aquarium Research Institute (MBARI) / Willow Garage

Abstract

This talk describes the application of AI planning to adaptively control an Autonomous Underwater Vehicle in pursuit of greater understanding of dynamic ocean processes

Autonomous Underwater Vehicles (AUV) are mobile robotic platforms used
by the oceanographic community for exploration in diverse environments
from the seafloor to the ocean surface. The extensive payload capacity
and operational versatility of AUV's offer a cost-effective alternative
to traditional ship-based oceanographic measurements for advancing ocean
research. Existing mission control practices rely on manually scripted
plans produced prior to mission execution. Mission scripts are prone to
error and do not afford adaptability of the vehicle to unanticipated
events. Such adaptability is critical to maximize science utility from
the limited time, energy and sampling opportunities available for a
mission. To address these issues, we have developed and deployed an
Adaptive Control System that integrates Planning and Probabilistic State
Estimation in a goal-directed hybrid executive, enabling scientists to
detect, survey and sample events of an unpredictable nature. The system
developed for ocean science is general purpose and adaptable to other
ocean going and terrestrial platforms.

Biographies

Conor McGann:

Conor McGann hails from Dublin, Ireland. He received his Bachelors in Computer Engineering from Trinity College, Dublin in 1990 and his Phd in Computer Science from that same institution in 1995. Subsequently, he co-founded Cunav Technologies, a Dublin based software company which he lead as CEO for 3 years. In 1998 Conor married a Texan and emigrated to the US where he joined the supply-chain company, i2 Technologies, and became the Chief Architect for their Customer Management Product Group.

In 2002 Conor joined the Planning and Scheduling Group at the NASA Ames Research Center where he lead the development of the EUROPA-2 constraint-based temporal planning library which has been used for ground based and onboard planning in a wide range of applications. In November 2006 Conor turned to inner space when he joined the embryonic Autonomous Systems Group of the Monterey Bay Aquarium Research Institute.

In May, 2008, Conor returned to the Bay Area to join Willow Garage, a robotics company located in Menlo Park. He continues to collaborate with NASA and MBARI and pursue his interests in autonomous systems.

URLS:
www.willowgarage.com
https://www.mbari.org/autonomy/TREX/index.htm

SLIDES:
Conor-presentation