Learn More
There has been considerable work in AI on decision-theoretic planning and planning under uncertainty. Unfortunately, all of this work suffers from one or more of the following limitations: 1) it relies on very simple models of actions and time, 2) it assumes that uncertainty is manifested in discrete action outcomes, and 3) it is only practical for very(More)
Executive Summary The world's climate is continuing to change at rates that are projected to be unprecedented in recent human history. Some models are now indicating that the temperature increases to 2100 may be larger than previously estimated in 2001. The impacts of climate change are likely to be considerable in tropical regions. Developing countries are(More)
We present regional model simulations of the dust emission events during the Bodélé Dust Experiment (BoDEx) that was carried out in February and March 2005 in Chad. A box model version of the dust emission model is used to test different input parameters for the emission model, and to compare the dust emissions computed with observed wind speeds to those(More)
[1] Mineral dust aerosols play an important role in the climate system. Coupled climate-aerosol models are an important tool with which to quantify dust fluxes and the associated climate impact. Over the last decade or more, numerous models have been developed, both global and regional, but to date, there have been few attempts to compare the performance of(More)
—The Pathfinder mission demonstrated the potential for robotic Mars exploration but at the same time indicated the need for more robust rover autonomy. Future planned missions call for long traverses over unknown terrain, robust navigation and instrument placement, and reliable operations for extended periods of time. Ultimately, missions may visit multiple(More)
We describe an approach for exploiting structure in Markov Decision Processes with continuous state variables. At each step of the dynamic programming , the state space is dynamically partitioned into regions where the value function is the same throughout the region. We first describe the algorithm for piecewise constant representations. We then extend it(More)
In this paper, we propose a new method based on Hidden Markov Models to interpret temporal sequences of sensor data from mobile robots to automatically detect features. Hidden Markov Models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (such as neural networks) are their(More)
A surgical intensive care unit (ICU) is a challenging monitoring environment. The multitude of monitored variables, the high frequency of alarms, and the severity of likely complications and emergencies can overload the cognitive skills of even experienced clinicians. ICU monitoring is also complicated by changes in clinical context. Over the course of a(More)
Intelligent monitoring and control involves observing and guiding the behavior of a physical system toward some objective, with real-time constraints on the utility of particular actions. Generic functional requirements for this task include: integration of perception, reasoning , and action; integration of multiple reasoning activities; reasoning about(More)