A long-standing challenge in human-automation interaction is adapting automation to the individual characteristics of different humans. As such, "adaptive automation" is intended to be responsive, in real time, to the human. For human-automation interaction scenarios requiring trust calibration, this generally requires adaptations tailored to situational and learned trust factors which change during the human’s interaction. However, given that a human’s dis-positional trust factors also influence their dynamic trust interactions with automation, we aim to answer the question "do different dispositional trust characteristics (toward automation) warrant different types of adaptive automation?" To do this, we build on prior work in which distinct trust dynamics were identified among humans interacting with an intelligent decision aid in a simulated reconnaissance mission. We design a new experiment that enables us to 1) classify participants into one of the two identified trust behaviors based upon a limited set of observations and 2) evaluate each participant’s performance with two different adaptive automation schemes— one customized to their dispositional characteristic and one that is generalized to the broad population based on a single model of trust behavior. Based on data collected from 85 participants, we show that although the customized adaptive automation policies do not produce statistically significant differences in mission performance outcomes than the general one, identifying a participant’s trust behavior using model-based classification is useful for determining which individuals may benefit most from assistance in calibrating their trust.

In this work, we present a methodology for integrating multiple tutoring objectives into model-based control policies for a psychomotor intelligent tutoring system (ITS). While tutoring objectives, like increasing self-efficacy, are well defined in the learning literature, realizing these types of objectives in an algorithmic framework is challenging. Motivated by the role of self-efficacy in psychomotor learning, we employ a Markov Decision Process (MDP) framework to train probabilistic models of self-confidence, workload, and learning stage. A custom reward function combines three key objectives: calibrating self-confidence with learning stage, calibrating workload to learning demands, and advancing learners from novice toward expert. Using this framework, we train two optimal tutoring policies—–one prioritizing cognitive state calibration and the other focusing on learning progression. Using these two policies as test case scenarios, we conduct a between-subjects study and demonstrate how one can leverage the tunability of the multi-objective reward function to achieve desired learning outcomes.

Autonomous systems that can assist humans with increasingly complex tasks are becoming ubiquitous. Moreover, it has been established that a human’s decision to rely on such systems is a function of both their trust in the system and their own self-confidence as it relates to executing the task of interest. Given that both under- and over-reliance on automation can pose significant risks to humans, there is motivation for developing autonomous systems that could appropriately calibrate a human’s trust or self-confidence to achieve proper reliance behavior. In this article, a computational model of coupled human trust and self-confidence dynamics is proposed. The dynamics are modeled as a partially observable Markov decision process without a reward function (POMDP/R) that leverages behavioral and self-report data as observations for estimation of these cognitive states. The model is trained and validated using data collected from 340 participants. Analysis of the transition probabilities shows that the proposed model captures the probabilistic relationship between trust, self-confidence, and reliance for all discrete combinations of high and low trust and self-confidence. The use of the proposed model to design an optimal policy to facilitate trust and self-confidence calibration is a goal of future work.

Properly calibrated human trust is essential for successful interaction between humans and automation. However, while human trust calibration can be improved by increased automation transparency, too much transparency can overwhelm human workload. To address this tradeoff, we present a probabilistic framework using a partially observable Markov decision process (POMDP) for modeling the coupled trust-workload dynamics of human behavior in an action-automation context. We specifically consider hands-off Level 2 driving automation in a city environment involving multiple intersections where the human chooses whether or not to rely on the automation. We consider automation reliability, automation transparency, and scene complexity, along with human reliance and eye-gaze behavior, to model the dynamics of human trust and workload. We demonstrate that our model framework can appropriately vary automation transparency based on real-time human trust and workload belief estimates to achieve trust calibration.

We developed an experiment to elicit human trust dynamics in human-machine interaction contexts and established a quantitative model of human trust behavior with respect to these contexts. The proposed model describes human trust level as a function of experience, cumulative trust, and expectation bias. We estimated the model parameters using human subject data collected from two experiments. Experiment 1 was designed to excite human trust dynamics using multiple transitions in trust level. Five hundred and eighty-one individuals participated in this experiment. Experiment 2 was an augmentation of Experiment 1 designed to study and incorporate the effects of misses and false alarms in the general model. Three hundred and thirty-three individuals participated in Experiment 2. Beyond considering the dynamics of human trust in automation, this model also characterizes the effects of demographic factors on human trust. In particular, our results show that the effects of national culture and gender on trust are significant. For example, U.S. participants showed a lower trust level and were more sensitive to misses as compared with Indian participants. The resulting trust model is intended for the development of autonomous systems that can respond to changes in human trust level in real time.

Today, intelligent machines interact and collaborate with humans in a way that demands a greater level of trust between human and machine. A first step toward building intelligent machines that are capable of building and maintaining trust with humans is the design of a sensor that will enable machines to estimate human trust level in real time. In this article, two approaches for developing classifier-based empirical trust-sensor models are presented that specifically use electroencephalography and galvanic skin response measurements. Human subject data collected from 45 participants is used for feature extraction, feature selection, classifier training, and model validation. The first approach considers a general set of psychophysiological features across all participants as the input variables and trains a classifier-based model for each participant, resulting in a trust-sensor model based on the general feature set (i.e., a “general trust-sensor model”). The second approach considers a customized feature set for each individual and trains a classifier-based model using that feature set, resulting in improved mean accuracy but at the expense of an increase in training time. This work represents the first use of real-time psychophysiological measurements for the development of a human trust sensor. Implications of the work, in the context of trust management algorithm design for intelligent machines, are also discussed.