Developing Signal-Pattern-Recognition Programs
- Thursday, 16 November 2006
Software system aids development of application programs that analyze signals.
An automated system to assist a General Aviation (GA) pilot in improving situational awareness of weather in flight is now undergoing development. This development is prompted by the observation that most fatal GA accidents are attributable to loss of weather awareness. Loss of weather awareness, in turn, has been attributed to the difficulty of interpreting traditional pre-flight weather briefings and the difficulty of both obtaining and interpreting traditional in-flight weather briefings. The developmental automated system not only improves weather awareness but also substantially reduces the time a pilot must spend in acquiring and maintaining weather awareness.
The automated system includes computer hardware and software, a speech-based hardware/software user interface, and hardware interfaces between the computer and aircraft radio-communication equipment. The heart of the system consists of artificial intelligence software, called Aviation Weather Environment (AWE), that implements a human-centered methodology oriented towards providing the weather information (1) that the pilot needs and/or wants, (2) at the appropriate time, and (3) in the appropriate format.
AWE can be characterized as a context-aware, domain-and-task knowledgeable, personalized, adaptive assistant. AWE automatically monitors weather reports for the pilot’s flight route and warns the pilot of any weather conditions outside the limits of acceptable weather conditions that the pilot has specified in advance. AWE provides textual and/or graphical representations of important weather elements overlaid on a navigation map (see figure). The representations depict current and forecast conditions in an easy-to-interpret manner and are geographically positioned next to each applicable airport to enable the pilot to visualize conditions along the route. In addition to automatic warnings, the system enables the pilot to verbally request (via the speech-based user interface) weather and airport information.
AWE is context-aware in the following sense: From the location of the aircraft (as determined by a Global Positioning System receiver) and the route as specified by the pilot, AWE determines the phase of flight. In determining the timing of warnings and the manner in which warnings are issued, AWE takes account of the phase of flight, the pilot’s definition of acceptable weather conditions, and the pilot’s preferences for automatic notification. By noting the pilot’s verbal requests for information during the various phases of flight, the system learns to provide the information, without explicit requests, at the corresponding times on subsequent flights under similar conditions.
This work was done by Lilly Spirkovska of Ames Research Center and Suresh K. Lodha of the University of California. For further information, access the Technical Support Package (TSP) free on-line at www.techbriefs.com/tsp under the Information Sciences category.
Inquiries concerning rights for the commercial use of this invention should be addressed to the Patent Counsel, Ames Research Center, (650) 604-5104. Refer to ARC-14970-1.
This Brief includes a Technical Support Package (TSP).
Using Artificial Intelligence To Inform Pilots of Weather (reference ARC-14970-1) is currently available for download from the TSP library.
Please Login at the top of the page to download.