Monterey Bay Aquarium Research Institute
CANON Initiative
Decision support system (DSS)

A decision support system is necessary for CANON because of the growing complexity of multi-disciplinary experiments requires integration of data synthesis and inference. DSS brings together existing MBARI technology within a framework that is current and scalable for technology transfer. It is a new effort for bringing together separate elements within MBARI, while also leveraging contributions from participating researchers outside MBARI.

Conventional ways of sampling and observing the ocean have relied on ship-based observations, which often require on-station presence and provide limited spatio-temporal coverage. Fixed observing infrastructure based on moorings cannot capture the dynamic scales of processes that extend over large horizontal scales (kilometers), vary in depth, or evolve in space with typical advection rates of up to 1 m/s. Satellite observations, although capable of capturing the spatial evolution of biological events, are limited to the sea surface when there is no adverse weather. Autonomous underwater vehicles (AUVs) in this context provide a valuable platform for coverage and cost-effective operation. They provide two-way capability for data return and shore-side control.

One principal problem continues to be where to position the AUVs and where they should sample to resolve key ecological questions. This also involves deriving an optimal path for sampling at the right place and time based on science requirements. To solve this problem the team envisions the capability to capture data from diverse sources to target AUV deployment as well as to provide situational awareness to the scientist on shore. Current efforts take a number of complementary approaches.

satellite image of the position of the AUV in the Pacific Ocean
Click on the image above to see a representative asset map of the positioning of the AUV near Monterey Bay using the decision support system live interface.
© MBARI 2010

The decision support system is a tool to aid decision making by processing data that augments human cognitive capabilities for problem solving. With artificial intelligence (AI) perspective, it involves the use of inference, event notification and exploration of alternative scenarios. It is interactive since humans and computers use their best traits to bring about a solution. It is more than a standard informational display.

DSS is a tool that will augment situational awareness, inform asset deployment, integrate data management, and enhance collaboration targeted for ocean science field experiments.

One approach will use a wide range of data sources including satellite observations, mooring data, and high-frequency radar to statistically project patch advection.

Another will build decision-making capability using artificial intelligence techniques onboard AUVs to adaptively sample dynamic coastal phenomenon. CANON proposes to systematically use these capabilities to provide a shore-side decision support system tool (Figure 30) for scientists to target the placement of AUVs close to and within bloom patches.


Proposed Architecture of the shore-side decision support system for coordination and adpation of mobile platforms for CANON

Proposed architecture of the shore-side decision support system for coordination and adaptation of mobile platforms for CANON. © MBARI 2009.

Such a tool will enable scientists on shore to generate “what if” scenarios for potential changes to AUV transects, changes to environmental conditions, or alternative sample sites for hypothesis testing. The aim will be to encapsulate predictive capabilities in one tool that generates advice for scientists on shore. In doing so we leverage our experience of providing similar functionalities as a DSS for scientists on NASA’s Mars Exploration Rovers mission.

The information above is from the following references:
  • J. Das, K. Rajan, S. Frolov, J. Ryan, F. Py, D. Caron, and G. Sukhatme, "Towards Marine Bloom Trajectory Prediction for AUV Mission Planning", Submitted to IEEE International Conference on Robotics and Automation, 2010.

  • K. Rajan, F. Py, C. McGann, J. Ryan, T. O'Reilly, T. Maughan and B. Roman, “Onboard Adaptive Control of AUVs using Automated Planning and Execution”, International Symposium on Unmanned Untethered Submersible Technology (UUST) August 2009. Durham, NH.

  • F. Py, K. Rajan and C. McGann “A Systematic Agent Framework for Situated Autonomous Systems”, to be published, Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010), Toronto, Canada, May 2010

  • J. Bresina, A.K. Jonsson, P.H. Morris and K. Rajan “Activity Planning for the Mars Exploration Rovers”, Intnl. Conf. on Automated Planning and Scheduling, June 2005, Monterey, CA.
Last updated: Aug. 20, 2010