基于行为和信任关系的人机信任预测方法研究

doi:10.11896/jsjkx.250300110

摘要/Abstract

摘要： 随着人工智能(Artificial Intelligence,AI)技术在航空领域的快速发展,人机信任的理解与量化对于飞机的飞行安全、应对突发情况、提高飞行效率等场景变得尤为重要。研究表明,生理和行为特征与信任密切相关,但目前的信任预测研究很少将这些特征纳入考量。为填补这一空白,提出了一种基于深度学习的人机信任预测模型,该模型融合了时序卷积网络(Temporal Convolutional Networks,TCN)和图注意力网络(Graph Attention Network,GAT),并以注视特征和行为特征作为输入。为了更有效地捕捉信任状态及其相关因素(如系统表现和多种行为特征)之间的复杂关系,构建了一个因果图模型。基于MATB任务开展实验,收集了13名被试的信任相关数据。数据分析结果表明,实验设计合理,并成功识别出信任高度相关的特征,可用于信任预测。实验结果显示,相较于现有的信任模型和传统方法,模型在信任预测准确率上至少提升了16%。这一结果不仅验证了所提出方法的有效性,也展现了深度学习技术结合信任相关特征在预测任务中的巨大潜力。此外,由于该模型不受特定领域限制,可为其他领域的信任预测提供有价值的参考。

关键词: 信任预测, 行为特征, 深度学习

Abstract: With the rapid development of AI technologies in the aviation industry,understanding and quantifying human-machine trust have become especially important for flight safety,handling emergencies,and improving flight efficiency.Research has shown that physiological and behavioral features are closely related to trust,but current trust prediction studies seldom consider these features.To address this gap,this research proposes a deep learning-based human-machine trust prediction model,which integrates TCN and GAT,using gaze and behavioral features as inputs.To more effectively capture the complex relationships between trust states and their influencing factors(such as system performance and various behavioral features),a causal graph mo-del is constructed.The study conducts experiments based on the MATB task and collects trust-related data from 13 participants.Data analysis results indicate that the experimental design is sound and successfully identifies features that are highly correlated with trust,which are used for trust prediction.The experimental results demonstrate that,compared to existing trust models and traditional methods,the proposed model improves prediction accuracy by at least 16%.This result not only validates the effectiveness of the proposed approach but also highlights the significant potential of combining deep learning techniques with trust-rela-ted features for prediction tasks.Furthermore,since the model is not limited to a specific domain,this research can provide valuable references for trust prediction in other fields.

Key words: Trust prediction, Behavioral features, Deep learning

中图分类号:

TP18

朱仁泽, 杨宁, 王宝会. 基于行为和信任关系的人机信任预测方法研究[J]. 计算机科学, 2025, 52(11A): 250300110-8. https://doi.org/10.11896/jsjkx.250300110

ZHU Renze, YANG Ning, WANG Baohui. Human-Machine Trust Prediction Using Behavior Measures and Trust Relationships[J]. Computer Science, 2025, 52(11A): 250300110-8. https://doi.org/10.11896/jsjkx.250300110

参考文献

[1]ISO/IEC.2011 Systems and software engineering-Systems and software Quality Requirements and Evaluation(SQuaRE)-System and software quality models:ISO/IEC 25010[S].2011.
[2]ZHANG P,CHEN N,SHEN S,et al.AI-enabled space-air-ground integrated networks:Management and optimization[J].IEEE Network,2024,38(2):186-192.
[3]SUN L,CHENG Z,KONG D,et al.Modeling and analysis of human-machine mixed traffic flow considering the influence of the trust level toward autonomous vehicles[J].Simulation Mo-delling Practice and Theory,2023,125:102741.
[4]HOPKO S K,MEHTA R K,PAGILLA P R.Physiological and perceptual consequences of trust in collaborative robots:An Empirical Investigation of Human and Robot Factors[J].Applied Ergonomics,2023,106:103863.
[5]STUCK R E,TOMLINSONB J,WALKER B N.The impor-tance of incorporating risk into human-automation trust[J].Theoretical Issues in Ergonomics Science,2022,23(4):500-516.
[6]AKASH K,MCMAHON G,REID T,et al.Human trust-based feedback control:Dynamically varying automationtransparency to optimize human-machine interactions[J].IEEE Control Systems Magazine,2020,40(6):98-116.
[7]DE VISSER E J,MONFORT S S,MCKENDRICK R,et al.Almost human:Anthropomorphism increases trust resilience in cognitive agents[J].Journal of Experimental Psychology:Applied,2016,22(3):331.
[8]LUSTER M S,PITTS B J.Trust in automation:the effects of system certainty on decision-making[C]//Proceedings of the Human Factors and Ergonomics Society Annual Meeting.Los Angeles,CA:SAGE Publications,2021:32-36.
[9]YUKSEL B F,COLLISSON P,CZERWINSKI M.Brains orbeauty:How to engender trust in user-agent interactions[J].ACM Transactions on Internet Technology,2017,17(1):1-20.
[10]TENHUNDFELD N L,DE VISSER E J,HARING K S,et al.Calibrating trust in automation through familiarity with the autoparking feature of a Tesla Model X[J].Journal of Cognitive Engineering and Decision Making,2019,13(4):279-294.
[11]WALLISER J C,DE VISSER E J,SHAW T H.Application of a system-wide trust strategy when supervising multiple autonomous agents[C]//Proceedings of the Human Factors and Ergonomics Society Annual Meeting.Los Angeles,CA:SAGE Publications,2016:133-137.
[12]JESSUP S A,SCHNEIDER T R,ALARCON G M,et al.Themeasurement of the propensity to trust automation[C]//Virtual,Augmented and Mixed Reality.Applications and Case Studies:11th International Conference,VAMR 2019,Held as Part of the 21st HCI International Conference(HCII 2019).Springer,2019:476-489.
[13]GLIKSON E,WOOLLEY A W.Human trust in artificial intelligence:Review of empirical research[J].Academy of Management Annals,2020,14(2):627-660.
[14]JIAN J Y,BISANTZ A M,DRURY C G.Foundations for anempirically determined scale of trust in automated systems[J].International Journal of Cognitive Ergonomics,2000,4(1):53-71.
[15]ULLMAN D,MALLE B F.What does it mean to trust a robot? Steps toward a multidimensional measure of trust[C]//Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction.2018:263-264.
[16]WOJTON H M,PORTER D,LANE S T,et al.Initial validationof the trust of automated systems test(TOAST)[J].The Journal of Social Psychology,2020,160(6):735-750.
[17]LU Y,SARTER N.Eye tracking:a process-oriented method for inferring trust in automation as a function of priming and system reliability[J].IEEE Transactions on Human-Machine Systems,2019,49(6):560-568.
[18]AYOUB J,AVETISIAN L,YANG X J,et al.Real-time trust prediction in conditionally automated driving using physiological measures[J].IEEE Transactions on Intelligent Transportation Systems,2023,24(12):14642-14650.
[19]PERELLO-MARCH J R,BURNS C ,WOODMAN R,et al.Using fNIRS to verify trust in highly automated driving[J].IEEE Transactions on Intelligent Transportation Systems,2022,24(1):739-751.
[20]OH S,SEONG Y,YI S,et al.Neurological measurement of hu-man trust in automation using electroencephalogram[J].International Journal of Fuzzy Logic and Intelligent Systems,2020,20(4):261-271.
[21]WESTPHAL M,VÖSSING M,SATZGER G,et al.Decisioncontrol and explanations in human-AI collaboration:Improving user perceptions and compliance[J].Computers in Human Behavior,2023,144:107714.
[22]REZAEI KHAVAS Z,KOTTURU M R,AHMADZADEH SR,et al.Do humans trust robots that violate moral trust?[J].ACM Transactions on Human-Robot Interaction,2024,13(2):1-30.
[23]REMPEL J K,HOLMES J G,ZANNA M P.Trust in close rela-tionships[J].Journal of Personality and Social Psychology,1985,49(1):95.
[24]LEE J,MORAY N.Trust,control strategies and allocation of function in human-machine systems[J].Ergonomics,1992,35(10):1243-1270.
[25]HU W L,AKASH K,REID T,et al.Computational modelingof the dynamics of human trust during human-machine interactions[J].IEEE Transactions on Human-Machine Systems,2018,49(6):485-497.
[26]CHEN S,ZHAO Y B,WANG Y,et al.A human-machine trust model integrating machine estimated performance[C]//2023 6th International Symposium on Autonomous Systems(ISAS).IEEE,2023:1-6.
[27]RABBY M K M,KHAN M A,KARIMODDINI A,et al.Modeling of trust within a human-robot collaboration framework[C]//2020 IEEE International Conference on Systems,Man,and Cybernetics(SMC).IEEE,2020:4267-4272.
[28]GUO Y,YANG X J.Modeling and predicting trust dynamics in human-robot teaming:A Bayesian inference approach[J].International Journal of Social Robotics,2021,13(8):1899-1909.
[29]VELICˇKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[30]LIU Y,DONG H,WANG X,et al.Time series prediction based on temporal convolutional network[C]//2019 IEEE/ACIS 18th International Conference on Computer and Information Science(ICIS).IEEE,2019:300-305.
[31]BI J,XU K,YUAN H,et al.Network attack prediction with hybrid temporal convolutional network and bi-directional GRU[J].IEEE Internet of Things Journal,2024,11(7):12619-12630.
[32]CEGARRA J,VALÉRY B,AVRIL E,et al.OpenMATB:Amulti-attribute task battery promoting task customization,software extensibility and experiment replicability[J].Behavior Research Methods,2020,52:1980-1990.
[33]PASZKE A,GROSS S,MASSA F,et al.PyTorch:An imperative style,high-performance deep learning library[C]//Advances in Neural Information Processing Systems.2019.
[34]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed