eduzhai > Applied Sciences > Engineering >

Human Trust-based Feedback Control Dynamically varying automation transparency to optimize human-machine interactions

  • Save

... pages left unread,continue reading

Document pages: 21 pages

Abstract: Human trust in automation plays an essential role in interactions betweenhumans and automation. While a lack of trust can lead to a human s disuse ofautomation, over-trust can result in a human trusting a faulty autonomoussystem which could have negative consequences for the human. Therefore, humantrust should be calibrated to optimize human-machine interactions with respectto context-specific performance objectives. In this article, we present aprobabilistic framework to model and calibrate a human s trust and workloaddynamics during his her interaction with an intelligent decision-aid system.This calibration is achieved by varying the automation s transparency---theamount and utility of information provided to the human. The parameterizationof the model is conducted using behavioral data collected through human-subjectexperiments, and three feedback control policies are experimentally validatedand compared against a non-adaptive decision-aid system. The results show thathuman-automation team performance can be optimized when the transparency isdynamically updated based on the proposed control policy. This framework is afirst step toward widespread design and implementation of real-time adaptiveautomation for use in human-machine interactions.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...