AssuredPNT Intelligent Virtual Sensors for Dynamic Modeling

Shahram Moafipoor, Brad Despres, Jeff A. Fayman, Lydia Bock, Robert Stadel

Peer Reviewed

Abstract: Accurate and reliable Position, Navigation, and Timing (PNT) information is vital in military applications for mission success. The most promising low SWaP-C systems for Assured PNT include relative aiding sensors such as vision (active LiDAR, passive camera), air/wheel speed sensors and other dead-reckoning sensors (magnetometer, barometer). As actual physical devices, they are subject to the usual practical requirements for integration into an Assured PNT system including reconfigurability (plug&play), autonomy-level, deployment feasibility, computational burden, latency and compensation thereof, interdependency, efficiency, and affordability. This paper presents developments of intelligent virtual aiding methods that extend the perceptive space and acuity of physical aiding sensors through the use of knowledge-based systems considering vehicle type, environmental conditions, coverage area, and dynamic range, founded on both programmed models such as non-holonomic constraints and captured knowledge of vehicle dynamics. Our approach utilizes knowledge-based systems and artificial intelligence methods, including artificial neural networks (ANN). Central to this is the concept of a virtual measurement, which is a computationally derived, sensor-fused, knowledge-infused interpretation of an input space that when taken collectively can construct higher-level percepts of the space. The composition and fusion multiply the constituent capabilities allowing extension into higher degree-of-freedom estimation under more tightly guided constraints and lower degradation of certainty. Programmed knowledge of non-holonomic constraints and machine-learning models of vehicle dynamics were developed and tested for 2D land-platforms (wheeled, railroad, robots etc.), 3D sea-platforms (vessels), and 6D air-platforms and tested under degraded GPS quality conditions.
Published in: Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021)
September 20 - 24, 2021
Union Station Hotel
St. Louis, Missouri
Pages: 2578 - 2590
Cite this article: Moafipoor, Shahram, Despres, Brad, Fayman, Jeff A., Bock, Lydia, Stadel, Robert, "AssuredPNT Intelligent Virtual Sensors for Dynamic Modeling," Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), St. Louis, Missouri, September 2021, pp. 2578-2590.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In