|
Abstract:
The increase in the size of the Air Force's Unmanned Aerial Vehicle (UAV) fleet, and the desire to reduce operational manning requirements, has led to an interest in Multiple Aircraft Control (MAC) technology. The MAC concept is highly prone to operator overload, as it requires operators to maintain awareness for multiple aircraft. To attempt to mitigate the potential of operator overload, this research introduces an agent into the system interface to assume responsibility for managing automation mode selection. The agent uses a novel dynamic scheme for determining how and when to introduce automation assistance to the operator. By using a reinforcement learning approach, the interface agent is able to correlate an operator's workload and performance levels. This allows the agent to determine the most appropriate times to introduce automation assistance. By automating tasks at appropriate times, the agent helps the system balance the operator's workload level, striking the best possible balance between operator awareness and overall performance, while reducing the potential for operator overload.
| Limitations: |
 APPROVED FOR PUBLIC RELEASE |
| Description: |
Master's thesis |
| Pages: |
120 |
| Report Date: |
22 Mar 2012 |
| Report Number: |
A630955 |
|
|
|
|
|
Keywords relating to this report:
Email This Abstract
