Advanced Autopilot System => Human-Automation Issues
The operation of aircraft has become increasingly automated
The complexity of the advanced flight deck
Mode Confusion have gained increasing attention as a core area for aviation safety
“pilots become confused about the current and future status (i.e., operating mode) of the automation and interact with it incorrectly”
Many incidents and accidents have been caused by mode confusion.
reported in NASA’s Aviation Safety Reporting System (ASRS)
Boeing Incident: B-737 (1989)
Memphis Center incident: “Kill the Capture”
Automatic mode transition from Vertical Speed (V/S) to Capture mode when “capturing” the newly set target altitude on the MCP (the “capture altitude” which is unknown (or not displayed) could create confusion).
Airbus Incident A-310 (1994)
Paris: Tarom incident “Speed Protection”
Automatic mode transition from V/S to OP CLB (Open Climb) mode
Flash Airlines B-737 (2004)
Egypt accident
Automatic mode-transition from HDG SEL (Heading Select) mode to CWS-R (Control Wheel Steering-Roll) mode and vertigo
Asiana 214 (2013)
San Francisco accident
"The captain selected an inappropriate autopilot mode, which, without the captain's awareness, resulted in the autothrottle no longer controlling airspeed. The aircraft then descended below the desired glide path with the crew unaware of the decreasing airspeed. The attempted go-around was conducted below 100 feet, by which time it was too late. Over-reliance on automation and lack of systems understanding by the pilots were cited as major factors contributing to the accident."
Mode confusion can cause unexpected changes in the aircraft’s altitude and airspeed
It is important to detect the mode confusion in a timely manner to prevent undesirable accidents
In this regard, our group develops a range of mode confusion detection algorithms:
Intent Inference Based Flight Deck Human-Automation Mode Confusion Detection
Data-Driven Modeling and Analysis Framework for Cockpit Human–Machine Interaction Issues
Formal Verification for Mode Confusion in the Flight Deck using Intent-based Abstraction
Automation Intent Inference Using the GFHMM for Flight Deck Mode Confusion Detection