{"title":"Trust and Cognitive Load in semi-automated UAV operation","authors":"Martin Lochner, Andreas Duenser, Shouvojit Sarker","doi":"10.1145/3369457.3369509","DOIUrl":null,"url":null,"abstract":"Trust in automation is an essential precursor to system adoption and use. Given the emerging wave of autonomous systems available for public consumption and the resources devoted to this trend, it's important to understand trust, and how to measure it. Further, the level of performance demonstrated by a system can affect trust in that system. As such, proper design of an autonomous system can be facilitated by measuring trust in such systems. Rather than relying only on traditional methods of measuring trust, such as pen and paper, or behavioural markers, this work extends previous research by investigating psycho-physiological markers for trust, using Galvanic Skin Response (GSR) and machine learning. We induced high vs. low trust states in amateur unmanned aerial vehicle (UAV) operators, and manipulated the automation level of the UAV. We collected workload and trust ratings during and after flying a UAV. Despite moderate results with traditional metrics (NASA TLX, and the System Trust Scale), we were able to classify trust states based on the GSR data with 80% accuracy. This research forms part of our ongoing work on developing a model for the relation between automation, and user trust and cognitive load.","PeriodicalId":258766,"journal":{"name":"Proceedings of the 31st Australian Conference on Human-Computer-Interaction","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 31st Australian Conference on Human-Computer-Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3369457.3369509","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Trust in automation is an essential precursor to system adoption and use. Given the emerging wave of autonomous systems available for public consumption and the resources devoted to this trend, it's important to understand trust, and how to measure it. Further, the level of performance demonstrated by a system can affect trust in that system. As such, proper design of an autonomous system can be facilitated by measuring trust in such systems. Rather than relying only on traditional methods of measuring trust, such as pen and paper, or behavioural markers, this work extends previous research by investigating psycho-physiological markers for trust, using Galvanic Skin Response (GSR) and machine learning. We induced high vs. low trust states in amateur unmanned aerial vehicle (UAV) operators, and manipulated the automation level of the UAV. We collected workload and trust ratings during and after flying a UAV. Despite moderate results with traditional metrics (NASA TLX, and the System Trust Scale), we were able to classify trust states based on the GSR data with 80% accuracy. This research forms part of our ongoing work on developing a model for the relation between automation, and user trust and cognitive load.