Integrated Data Registration for Networked Aircraft Navy SBIR FY2011.2 Sol No.: Navy SBIR FY2011.2 Topic No.: N112-101 Topic Title: Integrated Data Registration for Networked Aircraft Proposal No.: N112-101-0110 Firm: Heron Systems Incorporated 20945 Great Mills Road Suite 201 Lexington Park, Maryland 20653 Contact: Jason Summers Phone: (301) 866-0330 Web Site: www.heronsystems.com Abstract: An integrated data registration solution using neural networks is proposed.� Previous data registration solutions typically involve a fixed model of biases and noise.� The biases are then estimated and the estimates used to offset future sensor measurements.� These models are unable to solve more complex situations where the errors do not fit into a given model.� Given a changed operating environment, a new model would need to be developed.� A new approach is needed that can respond flexibly to highly variable operating environments.� Neural networks are a solution that can offer this flexibility. We propose to extend the work of Haim Karniely's "Sensor Registration using Neural Networks" to include sensor navigation and clock synchronization.� The solution is algorithmic in nature, requiring the identification of a method for training the NN to remove sensor, navigation and clock biases. Customized error and learning rate functions will be developed to train the neural net.� Existing Heron Systems products will be leveraged to create a test environment for training and evaluating the neural network.� The test environment will include a scenario generator for developing training and test cases and an unclassified E-2 radar model. Benefits: For commercial use, the neural network architecture and algorithms will be packaged as a software library. The library is foreseen to function as a data driven application, capable of adapting to specific data registration parameters and requirements during the learning phase of the neural network algorithm. This adaptability will be a key component of the product, allowing for maximal applicability in both government and private industry. The expected market for this product is large. Within government, specifically the Department of Defense, the registration of sensor data and the elimination of time and navigation biases is a fundamental need for platforms involved in the surveillance mission. This product will be marketed to those platforms through their associated PMAs. Platforms of interest operate on land, sea, and air, and include AWACS, AEGIS, E-2, E-3, P-8, and Patriot Missile Systems. Command and Control systems will also benefit from the data registration capabilities provided by this product. Demand from the Coast Guard, Homeland Security, and NASA could also be identified in applications where disparate sensors are viewing a common frame of reference. Private sector interest in the product is anticipated from companies in the aerospace and defense industries. Similar data registration problems exist in these industries. This product can provide these companies with capabilities to create larger data fusion solutions. Potential demand exists in the space industry as well. Tracking objects in orbit requires significant sensor networks spread across large distances. A data registration product can provide significant capability to companies operating in this area by providing closely aligned sensor data to tracking algorithms. Return