Date: January 13, 2008 11:24:52 PM EST
Subject: [ICAPS] Underwater Robotics/Planning & Execution
Summer Internship, Monterey Bay California

The Monterey Bay Aquarium Research Institute (MBARI
http://www.mbari.org) is a private non-profit oceanographic
research institute which has engaged in inter-disciplinary
research in the ocean sciences and technology for 20 years. The
institute does advanced work in Robotics, Genetics,
Micro-Biology and Ocean Exploration and Observing with 3 ocean
going ships, 2 Remotely Operated Vehicles (ROV's) and 3 deep
ocean Autonomous Underwater Vehicles (AUV's) in addition to
state-of-the-art science and technology facilities. MBARI's
2008 Internship applications are now open with details at:

http://www.mbari.org/education/internship/08interns/08announce.htm

At MBARI the Autonomous Systems group is engaged in research
efforts to use Artificial Intelligence (AI) techniques to
enable Autonomous Underwater Vehicles (AUV) to be more adaptive
and self aware of their resource and goal commitments. Our
onboard deliberative system T-REX
(http://www.mbari.org/autonomy/TREX/) being used on  our AUV
platform (http://www.mbari.org/auv/), is based on
the sense-deliberate-act paradigm synthesizing new mission
plans in-situ in response to environmental conditions. T-REX
uses a state-of-the-art temporal constraint-based planner
(EUROPA) developed originally at NASA and deployed on a number
of space missions including the ongoing Mars Exploration Rovers
(MER) mission. 

Potential internship opportunities include working on:

1. PlanWorks debugging tool for EUROPA which allows us to
leverage work done in visualization of constraint networks,
token networks and timelines. The internship primarily be
focused on developing PlanWorks to provide diagnostic
information for T-REX. 

2. Expanding the simulation capability currently available
within T-REX, including monte-carlo simulation for model and
and agent validation. The internship will focus on augmenting
and adding new features for shore-side T-REX validation.

3. Extend the NDDL domain modeling language within the EUROPA
planner to natively support arithmetic constraints and
propagate them efficiently. 

Highly motivated graduate or undergraduate students with substantial 

+ Java programming skills
+ Limited C or C++ programming skills
+ AI Planning and a background in Constraint Satisfaction would
be a plus

are encouraged to apply. Women and Minorities are particularly
encouraged to apply.