A significant number of aircraft incidents and accidents have been caused, in part,
by flightcrew failure to properly manage cockpit activities, such as failure to initiate
activities at the appropriate time, misprioritization of activities, or the failure to
appropriately monitor activities and terminate them when required. To facilitate the
management of the cockpit activities, a computational aid, the Agenda Manager (AM)
has been developed for use in simulated cockpit environments in an investigation which
was one aspect of a more extensive research project supported by the NASA Ames
Research Center.
The AM is directed at the management of goals and functions, the actors who
perform those functions, and the resources used by these actors. Development of an
earlier AM version, the Cockpit Task Management System (CTMS), demonstrated that it
could be used to assist flightcrews in the improvement of cockpit activity management
under experimental conditions, assuming that the AM determined pilot goals accurately
as well as the functions performed to achieve those goals.
To overcome AM limitations based on that assumption, a pilot goal
communication method (GCM) was developed to facilitate accurate recognition of pilot
goals. Embedded within AM, the GCM was used to recognize pilot goals and to declare
them to the AM. Two approaches to the recognition of pilots goals were considered:
(1) The use of an Automatic Speech Recognition (ASR) system to recognize overtly or
explicitly declared pilot goals, and (2) inference of covertly or implicitly declared pilot
goals via use of an intent inferencing mechanism. These two methods were integrated
into the AM to provide a rich environment for the study of human-machine interactions
in the supervisory control of complex dynamic systems. Through simulated flight
environment experimentation, the proposed GCM has demonstrated its capability to
accurately recognize pilot goals and to handle incorrectly declared goals, and was
validated in terms of subjective workload and pilot flight control performance. / Graduation date: 1997
| Identifer | oai:union.ndltd.org:ORGSU/oai:ir.library.oregonstate.edu:1957/34209 |
| Date | 07 October 1996 |
| Creators | Cha, Woo Chang |
| Contributors | Funk, Kenneth H. |
| Source Sets | Oregon State University |
| Language | en_US |
| Detected Language | English |
| Type | Thesis/Dissertation |
Page generated in 0.002 seconds