Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks

Trust is a crucial human factor in automated supervisory control tasks. To attain appropriate reliance, the operator’s trust should be calibrated to reflect the system’s capabilities. This study utilized eye-tracking technology to explore novel approaches, given the intrusive, subjective, and sporad...

Full description

Saved in:
Bibliographic Details
Main Authors: Keran Wang, Wenjun Hou, Huiwen Ma, Leyi Hong
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/7946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037268246429696
author Keran Wang
Wenjun Hou
Huiwen Ma
Leyi Hong
author_facet Keran Wang
Wenjun Hou
Huiwen Ma
Leyi Hong
author_sort Keran Wang
collection DOAJ
description Trust is a crucial human factor in automated supervisory control tasks. To attain appropriate reliance, the operator’s trust should be calibrated to reflect the system’s capabilities. This study utilized eye-tracking technology to explore novel approaches, given the intrusive, subjective, and sporadic characteristics of existing trust measurement methods. A real-world scenario of alarm state discrimination was simulated and used to collect eye-tracking data, real-time interaction data, system log data, and subjective trust scale values. In the data processing phase, a dynamic prediction model was hypothesized and verified to deduce and complete the absent scale data in the time series. Ultimately, through eye tracking, a discriminative regression model for trust calibration was developed using a two-layer Random Forest approach, showing effective performance. The findings indicate that this method may evaluate the trust calibration state of operators in human–agent collaborative teams within real-world settings, offering a novel approach to measuring trust calibration. Eye-tracking features, including saccade duration, fixation duration, and the saccade–fixation ratio, significantly impact the assessment of trust calibration status.
format Article
id doaj-art-47d5168d31bc4be289e81da4e6b5cef1
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-47d5168d31bc4be289e81da4e6b5cef12025-08-20T02:56:55ZengMDPI AGSensors1424-82202024-12-012424794610.3390/s24247946Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control TasksKeran Wang0Wenjun Hou1Huiwen Ma2Leyi Hong3School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, No. 1 Nanfeng Road, Shahe Higher Education Park, Shahe Area, Changping District, Beijing 102206, ChinaSchool of Digital Media & Design Arts, Beijing University of Posts and Telecommunications, No. 10 Xitucheng Road, Beijing 100876, ChinaSchool of Digital Media & Design Arts, Beijing University of Posts and Telecommunications, No. 10 Xitucheng Road, Beijing 100876, ChinaSchool of Digital Media & Design Arts, Beijing University of Posts and Telecommunications, No. 10 Xitucheng Road, Beijing 100876, ChinaTrust is a crucial human factor in automated supervisory control tasks. To attain appropriate reliance, the operator’s trust should be calibrated to reflect the system’s capabilities. This study utilized eye-tracking technology to explore novel approaches, given the intrusive, subjective, and sporadic characteristics of existing trust measurement methods. A real-world scenario of alarm state discrimination was simulated and used to collect eye-tracking data, real-time interaction data, system log data, and subjective trust scale values. In the data processing phase, a dynamic prediction model was hypothesized and verified to deduce and complete the absent scale data in the time series. Ultimately, through eye tracking, a discriminative regression model for trust calibration was developed using a two-layer Random Forest approach, showing effective performance. The findings indicate that this method may evaluate the trust calibration state of operators in human–agent collaborative teams within real-world settings, offering a novel approach to measuring trust calibration. Eye-tracking features, including saccade duration, fixation duration, and the saccade–fixation ratio, significantly impact the assessment of trust calibration status.https://www.mdpi.com/1424-8220/24/24/7946automated supervisory controltrust measurementtrust calibrationeye trackingRandom Forest
spellingShingle Keran Wang
Wenjun Hou
Huiwen Ma
Leyi Hong
Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
Sensors
automated supervisory control
trust measurement
trust calibration
eye tracking
Random Forest
title Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
title_full Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
title_fullStr Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
title_full_unstemmed Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
title_short Eye-Tracking Characteristics: Unveiling Trust Calibration States in Automated Supervisory Control Tasks
title_sort eye tracking characteristics unveiling trust calibration states in automated supervisory control tasks
topic automated supervisory control
trust measurement
trust calibration
eye tracking
Random Forest
url https://www.mdpi.com/1424-8220/24/24/7946
work_keys_str_mv AT keranwang eyetrackingcharacteristicsunveilingtrustcalibrationstatesinautomatedsupervisorycontroltasks
AT wenjunhou eyetrackingcharacteristicsunveilingtrustcalibrationstatesinautomatedsupervisorycontroltasks
AT huiwenma eyetrackingcharacteristicsunveilingtrustcalibrationstatesinautomatedsupervisorycontroltasks
AT leyihong eyetrackingcharacteristicsunveilingtrustcalibrationstatesinautomatedsupervisorycontroltasks