MURI - Opportunistic sensing

Recent developments in sensor technology, robotics, communications, signal, and semantic processing and computation have enabled the conception of opportunistic sensing (OS) systems that accomplish automatic target recognition (ATR) tasks using a potentially large network of coordinated stationary and mobile platforms carrying sensors of diverse modalities. The promise of OS systems lies in their ability to continuously optimize their performance by intelligently exploiting massive amounts of sensor data in addition to their ability to navigate and coordinate their sensing assets.

However, this great promise is offset by a number of critical challenges, which include:

• Growing volumes of sensor data: Teams of multiple mobile sensors operating continuously over increasingly large and complicated environments produce prodigious volumes of data that must be communicated, fused, organized, and processed in (near) real-time without collapsing the communications fabric.
• Increasingly diverse data: The apparent lack of correlation among images and other data taken from different viewpoints and with different sensor modalities and resolutions thwarts naïve approaches to data fusion and processing. Moreover, important contextual and operational information is often non-numeric, which further complicates matters.
• Diverse and changing operating conditions: Targets may be cluttered, camouflaged, occluded and imaged under different illuminations with miscalibrated or noisy sensors. Novel targets can appear, greatly complicating online operation.
• Increasing mobility: Multiple mobile sensing platforms must be remotely or autonomously maneuvered and coordinated to optimize ATR performance.

To date, the core issues underlying OS have been studied largely in isolation. It is our belief that real progress on OS requires a coordinated effort based on a unified mathematical and algorithmic foundation that supports not only efficient sensing, processing, data fusion, and decision making, but also direct performance analysis and prediction.

This MURI project is developing a principled theory of OS that provides predictable, optimal performance for a range of different ATR problems through the effective utilization of the available network of resources.

The project aims to train 11 graduate students and 1 postdoc per year in OS theory and practice in an interdisciplinary and collaborative research environment. Educational materials resulting from the project will be disseminated free of charge through the Connexions project (cnx.org).