In this paper we describe a project undertaken for the Office of Force Transformation (OFT) to investigate alternative resource allocation strategies for America's armed forces. In particular, OFT is interested in understanding how resource allocation strategies can be used in the context of distributed, network-centric units. To address this problem we have developed a simulation tool using agent-based modeling to explore the emergent properties of a distributed sensor network. We focus on the task of using distributed sensors with varying characteristics and capabilities trying to detect and track the movement of enemy units in an urban environment. The goal of the project is to identify the impact of different resource allocation strategies on the performance of the sensor network.

Compiler writers have crafted many heuristics over the years to approximately solve NP-hard problems efficiently. Finding a heuristic that performs well on a broad range of applications is a tedious and difficult process. This paper introduces Meta Optimization, a methodology for automatically fine-tuning compiler heuristics. Meta Optimization uses machine-learning techniques to automatically search the space of compiler heuristics. Our techniques reduce compiler design complexity by relieving compiler writers of the tedium of heuristic tuning. Our machine-learning system uses an evolutionary algorithm to automatically find effective compiler heuristics. We present promising experimental results. In one mode of operation Meta Optimization creates application-specific heuristics which often result in impressive speedups. For hyperblock formation, one optimization we present in this paper, we obtain an average speedup of 23% (up to 73%) for the applications in our suite. Furthermore, by evolving a compiler's heuristic over several benchmarks, we can create effective, general-purpose heuristics. The best general-purpose heuristic our system found for hyperblock formation improved performance by an average of 25% on our training set, and 9% on a completely unrelated test set. We demonstrate the efficacy of our techniques on three different optimizations in this paper: hyperblock formation, register allocation, and data prefetching.

The vision subsystem of an autonomous mobile robot was created using a form of evolutionary computation known as genetic programming. In this form, individuals are algorithms represented as parse trees. The primitives of the representation were specifically chosen to capture the spirit of existing vision algorithms. Thus, the evolutionary computation can be viewed as searching roughly the same space that researchers search when developing their system using trial and error. Traditional image operators such as the Sobel magnitude and a median filter were combined in arbitrary ways, and images from an unmodified office environment were used as training data. A hand written obstacle avoidance algorithm used the output of the best vision algorithm to avoid obstacles in real time. It performed as well as the existing hand written combined navigation and vision systems.

We present a method for representing, communicating and fusing distributed, noisy and uncertain observations of an object by multiple robots. The approach relies on re-parameterization of the canonical two-dimensional Gaussian distribution that corresponds more naturally to the observation space of a robot. The approach enables two or more observers to achieve greater effective sensor coverage of the environment and improved accuracy in object position estimation. We demonstrate empirically that, when using our approach, more observers achieve more accurate estimations of an object's position. The method is tested in three application areas, including object location, object tracking, and ball position estimation for robotic soccer. Quantitative evaluations of the technique in use on mobile robots are provided.