报告题目：

Finding the Proverbial Needle in the Coastal Ocean: Automated Reasoning for Sampling and Control in Marine Robotics

报告人：

Kanna Rajan博士

Principal Researcher for Autonomy

Monterey Bay Aquarium Research Institute (MBARI)

Kanna.Rajan@mbari.org

http://www.mbari.org/staff/kanna/

报告时间：

2011年5月26日　09:30-10:45

报告地点：

R楼二楼会议室

报告摘要：

The coastal ocean is a dynamic and complex environment with interacting physical, biological and chemical processes where many of the complex multi-disciplinary phenomena that scientists seek to understand, such as blooms, riverine and estuarine plumes, and sediment transport processes, have unpredictable spatial and temporal expressions. Recently, novel approaches to sampling are being explored using cost-effective and capable robotic platforms such as autonomous underwater vehicles (AUVs). These vehicles can support a diverse array of sensors to resolve interacting physical, chemical, biological phenomena. At the Monterey Bay Aquarium Research Institute (MBARI) we have designed, developed and deployed an on-board adaptive control software system that integrates automated planning and probabilistic state estimation within a hybrid executive. The Teleo-Reactive Executive (T-REX) is built around the paradigm of sense-plan-act and is used on-board MBARIs Dorado AUV for science missions. Such a system has removed the need to use pre-scripted plans allowing the AUV to adapt to changing mission objectives. State estimation is undertaken using a Hidden Markov Model (HMM) built using statistical Machine Learning techniques to learn a model of a targeted scientific feature. Onboard dynamic replanning using the HMM results in actuation of discrete water samplers, resulting in a novel opportunistic science capability.

To date we have focused on intermediate nepheloid layers (INLs), episodic features that are believed to play a role in the transport of zooplankton in the dynamic coastal waters of Monterey Bay, California. T-REX has recognized, mapped and sampled INLs during multiple surveys and collected invertebrate larvae contained in the water samples which were subsequently characterized with molecular probes on shore. Preliminary results obtained during these surveys support the hypothesis that INLs function as vehicles for episodic larval transport. This inter-disciplinary effort has led us towards a more ambitious goal of building a shore/ship based Decision Support System (DSS) to enable the science user to target multiple assets for sampling meso-scale features like blooms and anoxic zones. We envision a capability which captures data from a diverse set of sources to target platform deployment, multi-vehicle coordination and provide situational awareness. AUVs and other robotic assets will have on-board decisional level capability to synthesize and execute plans and reconfigure in the event of failure or in response to emergent science opportunities. In this talk we will describe the importance of automated inference capabilities that our experience has shown to be valuable to exploration of coastal waters. And we will project where automated inference capabilities can truly impact the study of a domain that has had little to poor exposure to techniques in Artificial Intelligence.

报告人简介：

Dr. Kanna Rajan is the Principal Researcher in Autonomy at the Monterey Bay Aquarium Research Institute (http://www.mbari.org), a privately funded non-profit Oceanographic institute which he joined in October 2005. Prior to that he was a Senior Research Scientist for the Autonomous Systems and Robotics Area at NASA Ames Research Center Moffett Field, California.

At Ames, he balanced programmatic and technical responsibilities. He was the Principal Investigator of the MAPGEN Mixed-Initiative Planning effort to command and control the Spirit and Opportunity rovers on the surface of the Red Planet. MAPGEN continues to be used to this day, twice daily in the mission-critical uplink process at the Jet Propulsion Laboratory in Pasadena.

Kanna was one of the six principals of the Remote Agent Experiment (RAX) team, which designed, built, tested and flew the first closed-loop AI based control system on a spacecraft 65 Million miles from Earth. The RA was the co-winner of NASA's 1999 Software of the Year, the agency's highest technical award (http://ic.arc.nasa.gov/projects/remote-agent/).

His interests are in automated Planning/Scheduling, modeling and representation for real world planners and agent architectures for Distributed Control applications. Prior to joining NASA Ames, he was in the doctoral program at the Courant Institute of Math Sciences at New York University. And prior to that he was at the Knowledge Systems group at American Airlines, helping build a Maintenance Routing scheduler (MOCA), which continues to be used by the airline 365 days of the year.

Kanna is the recipient of two NASA medals; a 2002 NASA Public Service Medal from NASA Ames for his efforts on the Remote Agent. In 2004, JPL awarded him the NASA Exceptional Service Medal for his role on the Mars Exploration Rovers mission. MAPGEN has been awarded NASA's 2004 Turning Goals into Reality award under the Administrators Award category, a NASA Space Act Award, a NASA Group Achievement Award and a NASA Ames Honor Award. He is also the recipient of the First NASA Ames Information Directorate Infusion Award in 2002.

He was the Co-chair of the 2005 International Conference on Automated Planning and Scheduling (ICAPS), Monterey California and till 2005 the chair of the Executive Board of the International Workshop on Planning and Scheduling for Space. He continues to serve on review panels for NASA, the Italian Space Agency and European Space Agency.

欢迎广大职工、研究生参加。

　　　　　　　　　　　　　　　　　　　　　　　二室　综合办
　　　　　　　　　　　　　　　　　　　　　　　　 2011年5月24日