"Automated Decision Making for a New Class of AUV Science" presented by Kanna Rajan et al. 2008 Ocean Sciences Meeting.
Autonomous underwater vehicles (AUVs) are an increasingly important tool for oceanographic research. They routinely and cost effectively sample the water column at depths far beyond what humans are capable of visiting. However, control of these platforms has relied on fixed sequences for execution of pre-planned actions limiting their effectiveness for measuring dynamic and episodic ocean phenomenon.
At the Monterey Bay Aquarium Research Institute (MBARI), we are developing an advanced Artificial Intelligence (AI) based control system to enable our AUV's to dynamically adapt to the environment. They do so by deliberating in-situ about mission plans while tracking onboard resource consumption, dealing with plan failures by allowing dynamic re-planning and being cognizant of vehicle health and safety in the course of executing science plans. To date we have tested T-REX (the Teleo-Reactive Executive) on an MBARI Dorado 21feet vehicle with a range of scientific instruments for water-column surveys in Monterey Bay with very promising results in term of adaptivity and robustness.
Click below to access a poster about T-REX (pdf).
Reference: McGann, C., F. Py, K. Rajan, H. Thomas, R. Henthorn, and R. McEwen (2008). Automated decision making for a new class of AUV science. Proceedings of the American Society of Limnology and Oceanography / Ocean Sciences Meeting, Orlando, Florida.