Artificially intelligent agents are increasingly moving beyond decision-support roles to become teammates, creating novel team configurations beyond traditional human-AI dyads. One such configuration is a hierarchical team, where a human leader directs both human and agent subordinates. This raises key questions about managing mixed-identity subordinates and about how agent traits (ability/integrity) shape trust. We present a lab study with teams of four (one human leader, with one human and two agent subordinates) performing a collaborative block-moving task. Leaders interacted with three types of agents that varied in ability and integrity: High-Integrity-High-Ability (HI-HA), High-Integrity-Low-Ability (HI-LA), and Low-Integrity-High-Ability (LI-HA). Leaders generally preferred and maintained stable trust in humans, whereas trust in agents declined significantly under both low-ability and low-integrity conditions, with stronger sensitivity to integrity. Thematic analysis revealed distinct expectations tied to identity: leaders granted humans an inherent baseline of trust due to humans’ adaptability, while evaluating agents primarily on task efficiency and obedience.

Maintaining adequate situation awareness (SA) is crucial for the safe operation of conditionally automated vehicles (AVs), which requires drivers to regain control during takeover (TOR) events. This study developed a predictive model for real-time assessment of driver SA using multimodal data (e.g., galvanic skin response, heart rate and eye tracking data, and driver characteristics) collected in a simulated driving environment. Sixty-seven participants experienced automated driving scenarios with TORs, with conditions varying in risk perception and the presence of automation errors. Using data from forty-four participants (twenty-three of those had invalid data) a LightGBM (Light Gradient Boosting Machine) model trained on the top 12 predictors identified by SHAP (SHapley Additive exPlanations) achieved promising performance with RMSE = 0.89, M AE = 0.71, and Corr = 0.78. These findings have implications towards context-aware modeling of SA in conditionally automated driving, paving the way for safer and more seamless driver–AV interactions.

Human interaction with autonomous technologies has been extensively studied, mostly focusing on one-to-one dyadic interactions. In contrast, this study examines human altruistic and compliance behaviors in multiple-operator single-agent (MOSA) interaction. We developed a testbed where multiple players perform an evacuation task, assisted by an AI agent that plans the optimal route for everyone. During the evacuation, players could exhibit altruism by reporting additional information, albeit at a personal cost. A lab study with 32 participants, each completing four trials under varying display configurations that manipulated the communication of altruistic actions, yielded 1,012 and 3,865 data points on altruism and compliance, respectively. Using mixed-effects logistic regression, we identified key predictors of altruistic and compliance behaviors and developed prediction models, with accuracies of 73.36% and 91.07%, respectively. These findings offer valuable insights into the role of information transparency, reciprocal altruism, and compliance in MOSA interaction, with implications for designing AI-assisted collaborative systems.

A particular concern with SAE Level 3 automation is the takeover transition from the automated vehicle to the human driver. In response, research has focused on investigating this transition. However, researchers have used a wide range of metrics to measure takeover performance. The lack of consistency in these metrics poses challenges for synthesizing findings. To address this issue, we conducted a systematic literature review of studies published between January 2009 and December 2019, focusing on the takeover performance metrics. Following prior research, we categorize these metrics into two dimensions: timeliness and quality. Additionally, we summarize the scenarios used to elicit takeover requests and analyze the corresponding maneuvers (braking, lane changing, and lane keeping). The results have shown inconsistencies in calculation and naming conventions of takeover performance metrics. Based on these findings, this study proposes several directions for standardizing definitions and terminology, and advancing toward a unified measure of takeover performance.

This study aims to explore the associations between individuals’ trust dynamics in automated/autonomous technologies and their personal characteristics, and to further examine whether personal characteristics can be used to predict a user’s trust dynamics type. The experimental data involved 130 participants who performed a simulated surveillance task that consisted of a compensatory tracking task and a threat detection task. An imperfect automated threat detector assisted participants in the detection task. Using a pre-experimental survey covering 12 constructs and 28 dimensions, we collected data on participants’ personal characteristics. Based on the experimental data, we performed k-means clustering and identified three trust dynamics types. Subsequently, we conducted one-way analyses of variance to evaluate differences among the three trust dynamics types in terms of personal characteristics, behaviors, performance, and postexperimental ratings. Participants were clustered into three groups, namely Bayesian decision makers, disbelievers, and oscillators. Results showed that the clusters differ significantly in seven personal characteristics: masculinity, positive affect, extraversion, neuroticism, intellect, performance expectancy, and high expectations. The disbelievers tend to have highneuroticismand lowperformance expectancy. The oscillators tend to have higher scores inmasculinity,positive affect,extraversion, andintellect. We also found significant differences in behaviors, performance, and postexperimental ratings across the three groups. The disbelievers are the least likely to blindly follow the recommendations made by the automated threat detector. Based on the significant personal characteristics, we developed a decision tree model to predict the trust dynamics type with an accuracy of 70% . This model offers promising implications for identifying individuals whose trust dynamics may deviate from a Bayesian pattern.

Explainable AI (XAI) aims to provide insights into the decisions made by AI models. To date, most XAI approaches provide only one-time, static explanations, which cannot cater to users' diverse knowledge levels and information needs. Conversational explanations have been proposed as an effective method to customize XAI explanations. However, building conversational explanation systems is hindered by the scarcity of training data. Training with synthetic data faces two main challenges: lack of data diversity and hallucination in the generated data. To alleviate these issues, we introduce a repetition penalty to promote data diversity and exploit a hallucination detector to filter out untruthful synthetic conversation turns. We conducted both automatic and human evaluations on the proposed system, fEw-shot Multi-round ConvErsational Explanation (EMCEE). For automatic evaluation, EMCEE achieves relative improvements of 81.6% in BLEU and 80.5% in ROUGE compared to the baselines. EMCEE also mitigates the degeneration of data quality caused by training on synthetic data. In human evaluations (N = 60), EMCEE outperforms baseline models and the control group in improving users' comprehension, acceptance, trust, and collaboration with static explanations by large margins. Through a fine-grained analysis of model responses, we further demonstrate that training on self-generated synthetic data improves the model's ability to generate more truthful and understandable answers, leading to better user interactions. To the best of our knowledge, this is the first conversational explanation method that can answer free-form user questions following static explanations.

Research in explainable AI (XAI) aims to provide insights into the decision-making process of opaque AI models. To date, most XAI methods offer one-off and static explanations, which cannot cater to the diverse backgrounds and understanding levels of users. With this paper, we investigate if free-form conversations can enhance users’ comprehension of static explanations in image classification, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. We conduct a human-subject experiment with 120 participants. Half serve as the experimental group and engage in a conversation with a human expert regarding the static explanations, while the other half are in the control group and read the materials regarding static explanations independently. We measure the participants’ objective and self-reported comprehension, acceptance, and trust of static explanations. Results show that conversations significantly improve participants’ comprehension, acceptance , trust, and collaboration with static explanations, while reading the explanations independently does not have these effects and even decreases users’ acceptance of explanations. Our findings highlight the importance of customized model explanations in the format of free-form conversations and provide insights for the future design of conversational explanations.

In mixed traffic environments that involve conventional vehicles (CVs) and autonomous vehicles (AVs), it is essential for CV drivers to maintain an appropriate level of situation awareness (SA) to ensure safe and efficient interactions with AVs. While previous research has established the benefits of external human–machine interfaces (HMIs) for communicating AV intent, this study extended this knowledge by focusing on the vital but underexplored interaction with CV drivers. Specifically, we investigated how AV communication through HMIs affected CV drivers by systematically comparing internal (iHMI) and external (eHMI) interfaces, and examined their impact on CV driver awareness, cognitive load, and behavior. Initially, we designed eight HMI concepts through a human-centered design process. The two highest-rated concepts were selected for implementation as eHMIs and iHMIs. Subsequently, we designed a within-subjects experiment with three conditions: a control condition without any communication HMI, and two treatment conditions using eHMIs and iHMIs as communication means. We investigated the effects of these conditions on 50 participants in a virtual environment (VR) driving simulator. Self-reported assessments and eye-tracking measures were employed to evaluate participants’ SA, trust, acceptance, and mental workload. Results indicated that the iHMI condition resulted in superior SA among participants and improved trust in the AV compared to the control and eHMI conditions. Additionally, iHMI led to a comparatively lower increase in mental workload compared to the other two conditions. Our study contributes to the development of effective AV-CV communications and has the potential to inform the design of future AV systems.

This paper examines the effect of real-time, personalized alignment of a robot's reward function to the human's values on trust and team performance. We present and compare three distinct robot interaction strategies: a non-learner strategy where the robot presumes the human's reward function mirrors its own; a non-adaptive-learner strategy in which the robot learns the human's reward function for trust estimation and human behavior modeling, but still optimizes its own reward function; and an adaptive-learner strategy in which the robot learns the human's reward function and adopts it as its own. Two human-subject experiments with a total number of N=54 participants were conducted. In both experiments, the human-robot team searches for potential threats in a town. The team sequentially goes through search sites to look for threats. We model the interaction between the human and the robot as a trust-aware Markov Decision Process (trust-aware MDP) and use Bayesian Inverse Reinforcement Learning (IRL) to estimate the reward weights of the human as they interact with the robot. In Experiment 1, we start our learning algorithm with an informed prior of the human's values/goals. In Experiment 2, we start the learning algorithm with an uninformed prior. Results indicate that when starting with a good informed prior, personalized value alignment does not seem to benefit trust or team performance. On the other hand, when an informed prior is unavailable, alignment to the human's values leads to high trust and higher perceived performance while maintaining the same objective team performance.

Autonomous Guided Vehicles (AGVs) are becoming increasingly common in industrial environments to transport heavy equipment around warehouses. Within the idea of Industry 5.0, these AGVs are expected to work alongside humans in the same shared workspace. To enable smooth and trustworthy interaction between workers and AGVs, the AGVs must be able to model the workers’ behavior and plan their trajectories around it. In this paper, we introduce a Finite Automaton Model (FAM) to model worker motion in such a context. We conduct a human subject experiment using a Virtual Reality (VR) environment and an omnidirectional treadmill to collect data about worker trajectories to tune our model. We show that not only is our model more interpretable, but also outperforms machine learning models at classifying worker motion behavior with limited training data. Future research can use our model to modify AGV behavior to promote trustworthy human-AGV interaction.

Workload management is a critical concern in shared control of unmanned ground vehicles. In response to this challenge, prior studies have developed methods to estimate human operators’ workload by analyzing their physiological data. However, these studies have primarily adopted a single-model-single-feature or a single-model-multiple-feature approach. The present study proposes a Bayesian inference model to estimate workload, which leverages different machine learning models for different features. We conducted a human subject experiment with 24 participants, in which a human operator teleoperated a simulated High Mobility Multipurpose Wheeled Vehicle (HMMWV) with the help from an autonomy while performing a surveillance task simultaneously. Participants’ eye-related features, including gaze trajectory and pupil size change, were used as the physiological input to the proposed Bayesian inference model. Results show that the Bayesian inference model achieves a 0.823 F1 score, 0.824 precision, and 0.821 recall, outperforming the single models.

Trust is crucial for ensuring the safety, security, and widespread adoption of automated vehicles (AVs), and if trust is lacking, drivers and the general public may hesitate to embrace this technology. This research seeks to investigate contextualized trust profiles in order to create personalized experiences for drivers in AVs with varying levels of reliability. A driving simulator experiment involving 70 participants revealed three distinct contextualized trust profiles (i.e.,confident copilots,myopic pragmatists, andreluctant automators) identified through K-means clustering, and analyzed in relation to drivers' dynamic trust, dispositional trust, initial learned trust, personality traits, and emotions. The experiment encompassed eight scenarios where participants were requested to take over control from the AV in three conditions: a control condition, a false alarm condition, and a miss condition. To validate the models, a multinomial logistic regression model was constructed using the shapley additive explanations explainer to determine the most influential features in predicting contextualized trust profiles, achieving an F1-score of 0.90 and an accuracy of 0.89. In addition, an examination of how individual factors impact contextualized trust profiles provided valuable insights into trust dynamics from a user-centric perspective. The outcomes of this research hold significant implications for the development of personalized in-vehicle trust monitoring and calibration systems to modulate drivers' trust levels, thereby enhancing safety and user experience in automated driving.

Trust-aware human-robot interaction (HRI) has received increasing research attention, as trust has been shown to be a crucial factor for effective HRI. Research in trust-aware HRI discovered a dilemma - maximizing task rewards often leads to decreased human trust, while maximizing human trust would compromise task performance. In this work, we address this dilemma by formulating the HRI process as a two-player Markov game and utilizing the reward-shaping technique to improve human trust while limiting performance loss. Specifically, we show that when the shaping reward is potential-based, the performance loss can be bounded by the potential functions evaluated at the final states of the Markov game. We apply the proposed framework to the experience-based trust model, resulting in a linear program that can be efficiently solved and deployed in real-world applications. We evaluate the proposed framework in a simulation scenario where a human-robot team performs a search-and-rescue mission. The results demonstrate that the proposed framework successfully modifies the robot's optimal policy, enabling it to increase human trust at a minimal task performance cost.

Trust calibration poses a significant challenge in the interaction between drivers and automated vehicles (AVs) in the context of human-automation collaboration. To effectively calibrate trust, it becomes crucial to accurately measure drivers’ trust levels in real time, allowing for timely interventions or adjustments in the automated driving. One viable approach involves employing machine learning models and physiological measures to model the dynamic changes in trust. This study introduces a technique that leverages machine learning models to predict drivers’ real-time dynamic trust in conditional AVs using physiological measurements. We conducted the study in a driving simulator where participants were requested to take over control from automated driving in three conditions that included a control condition, a false alarm condition, and a miss condition. Each condition had eight takeover requests (TORs) in different scenarios. Drivers’ physiological measures were recorded during the experiment, including galvanic skin response (GSR), heart rate (HR) indices, and eye-tracking metrics. Using five machine learning models, we found that eXtreme Gradient Boosting (XGBoost) performed the best and was able to predict drivers’ trust in real time with an f1-score of 89.1% compared to a baseline model of$K$-nearest neighbor classifier of 84.5%. Our findings provide good implications on how to design an in-vehicle trust monitoring system to calibrate drivers’ trust to facilitate interaction between the driver and the AV in real time.

This paper develops a novel framework called Providers-Clients-Robots (PCR), applicable to socially assistive robots that support research on shared understanding in human-robot interactions. Providers, Clients, and Robots share an actionable and intuitive representation of the environment to create plans that best satisfy the combined needs of all parties. The plans are formed via interaction between the Client and the Robot based on a previously built multi-modal navigation graph. The explainable environmental representation in the form of a navigation graph is constructed collaboratively between Providers and Robots prior to interaction with Clients. We develop a realization of the proposed framework to create a spatial-semantic representation of an indoor environment autonomously. Moreover, we develop a planner that takes in constraints from Providers and Clients of the establishment and dynamically plans a sequence of visits to each area of interest. Evaluations show that the proposed realization of the PCR framework can successfully make plans while satisfying the specified time budget and sequence constraints and outperforming the greedy baseline.

As autonomous systems become more complicated, humans may have difficulty deciphering autonomy-generated solutions and increasingly perceive autonomy as a mysterious black box. The lack of transparency contributes to the lack of trust in autonomy and suboptimal team performance. In response to this concern, researchers have proposed various methods to enhance autonomy transparency and evaluated how enhanced transparency could affect the people’s trust and the human-autonomy team performance. However, the majority of prior studies measured trust at the end of the experiment and averaged behavioral and performance measures across all trials in an experiment, yet overlooked the temporal dynamics of those variables. We have little understanding of how autonomy transparency affects trust, dependence, and performance over time. The present study, therefore, aims to fill the gap and examine such temporal dynamics. We develop a game Treasure Hunter wherein a human uncovers a map for treasures with the help from an intelligent assistant. The intelligent assistant recommends where the human should go next. The rationale behind each recommendation could be conveyed in a display that explicitly lists the option space (i.e., all the possible actions) and the reason why a particular action is the most appropriate in a given context. Results from a human-in-the-loop experiment with 28 participants indicate that by conveying the intelligent assistant’s decision-making rationale via the display, participants’ trust increases significantly and becomes more calibrated over time. Using the display also leads to a higher acceptance of recommendations from the intelligent agent.

Despite the benefits of automated vehicles (AVs), there are still barriers to their widespread adoption. Expectations about AVs have been identified as one of the most important factors in understanding AV adoption. Therefore, by understanding the public's expectations of AVs, we can better understand whether or when AVs are likely to be adopted on a wide scale. Individual differences, including demographics and personality, have been identified as factors that impact technology expectations and adoption. However, it is not clear whether and how individual differences can influence expectations of AVs. To examine this, we conducted an online survey with 443 U.S. drivers who were recruited and divided into subpopulations by age, gender, ethnicity, census region, educational level, marital status, income, driving frequency, driving experience, and personality traits. Results revealed that drivers' expectations of AVs differ significantly by age, gender, ethnicity, education levels, marital status, drive frequency, drive experience, and personality. More specifically, higher expectations are more often generated by drivers who are younger, men, White non-Hispanic, more highly educated, never married, with a higher frequency of driving, with less driving experience, and who are high in extraversion, agreeableness, conscientiousness, and emotional stability. The results of this study provide a foundation for future research related to expectations and have important implications on future design and development of AVs.

It is extremely important to ensure a safe takeover transition in conditionally automated driving. One of the critical factors that quantifies the safe takeover transition is takeover time. Previous studies identified the effects of many factors on takeover time, such as takeover lead time, non-driving tasks, modalities of the takeover requests, and scenario urgency. However, there is a lack of research to predict takeover time by considering these factors all at the same time. Toward this end, we used eXtreme Gradient Boosting (XGBoost) to predict the takeover time using a dataset from a meta-analysis study [Zhanget al.(2019)]. In addition, we used SHAP (SHapley Additive exPlanation) to analyze and explain the effects of the predictors on takeover time. We identified seven most critical predictors that resulted in the best prediction performance. Their main effects and interaction effects on takeover time were examined. The results showed that the proposed approach provided both good performance and explainability. Our findings have implications on the design of in-vehicle monitoring and alert systems to facilitate the interaction between the drivers and the automated vehicle.

The advancement in machine learning and artificial intelligence promotes the testing and deployment of autonomous vehicles (AVs) on public roads. The California Department of Motor Vehicles (CA DMV) has launched the Autonomous Vehicle Tester Program, which collects and releases reports related to Autonomous Vehicle Disengagement (AVD) from autonomous driving. Understanding the causes of AVD is critical to improving the AV system’s safety and stability and providing guidance for AV testing and deployment. In this work, we built a scalable end-to-end pipeline to collect, process, model, and analyze the disengagement reports released from 2014 to 2020 using natural language processing and deep transfer learning. The analysis of disengagement data using taxonomy, visualization, and statistical tests revealed the trends of AV testing, cause frequency, and significant relationships between causes and effects of AVD. We found that (1) manufacturers tested AVs intensively during the Spring and/or Winter, (2) test drivers initiated more than 80% of the disengagement while more than 75% of the disengagement were because of errors in perception, localization & mapping, planning and control of the AV system, and (3) there was a significant relationship between the initiator of AVD and the cause category. This study serves as a successful practice of deep transfer learning using pre-trained models and generates a consolidated disengagement database allowing further investigation for other researchers. The related code and data are available on github.1

Situation awareness (SA) is critical to improving takeover performance during the transition period from automated driving to manual driving. Although many studies measured SA during or after the driving task, few studies have attempted to predict SA in real time in automated driving. In this work, we propose to predict SA during the takeover transition period in conditionally automated driving using eye-tracking and self-reported data. First, a tree ensemble machine learning model, named LightGBM (Light Gradient Boosting Machine), was used to predict SA. Second, in order to understand what factors influenced SA and how, SHAP (SHapley Additive exPlanations) values of individual predictor variables in the LightGBM model were calculated. These SHAP values explained the prediction model by identifying the most important factors and their effects on SA, which further improved the model performance of LightGBM through feature selection. We standardized SA between 0 and 1 by aggregating three performance measures (i.e., placement, distance, and speed estimation of vehicles with regard to the ego-vehicle) of SA in recreating simulated driving scenarios, after 33 participants viewed 32 videos with six lengths between 1 and 20 s. Using only eye-tracking data, our proposed model outperformed other selected machine learning models, having a root-mean-squared error (RMSE) of 0.121, a mean absolute error (MAE) of 0.096, and a 0.719 correlation coefficient between the predicted SA and the ground truth. The code is available athttps://github.com/refengchou/Situation-awareness-prediction. Our proposed model provided important implications on how to monitor and predict SA in real time in automated driving using eye-tracking data.

In conditionally automated driving, in-vehicle alert systems can provide drivers with information to assist their takeovers from automated driving. This study investigated how display modality and information influenced drivers’ acceptance of the in-vehicle alert systems under different event criticality situations. We conducted an online video study with a 3 (information type) × 3 (display modality) × 2 (event criticality) mixed design involving 60 participants. The results showed that considering drivers’ perceived usefulness and ease of use, presenting why only information was not sufficient for takeovers as compared to what will only information and why + what will information. Participants reported higher ease of use in the combination of speech and augmented reality condition when compared to the speech only condition. High event criticality led to drivers’ lower perceived usefulness and more negative opinions of the displays. The findings have implications for the design of in-vehicle alert systems during takeover transitions.

Automated Vehicle (AV) buses hold great potential, yet it is not clear if Americans will choose to ride them. Trust and attitudes, often influenced by individual differences, are vital predictors of technology acceptance and AVs are no exception. To deepen our understanding of individual differences as they pertain to AV buses, this paper presents the results of a national survey of 401 participants located in the United States of America. Findings from this survey indicate that individual differences influenced trust, attitude, and intention to ride AV buses. Specifically, trust in AV buses differed by individual's age and bus riding frequency while attitudes toward AV buses differed by individual's age, ethnicity, and bus riding frequency. Finally, intention to ride an AV bus differed by age, gender, ethnicity, and bus riding frequency. Based on these results, we propose a research agenda that seeks to inform future research on acceptance of AV buses.

In conditionally automated driving, drivers engaged in non-driving related tasks (NDRTs) have difficulty taking over control of the vehicle when requested. This study aimed to examine the relationships between takeover performance and drivers’ cognitive load, takeover request (TOR) lead time, and traffic density. We conducted a driving simulation experiment with 80 participants, where they experienced 8 takeover events. For each takeover event, drivers’ subjective ratings of takeover readiness, objective measures of takeover timing and quality, and NDRT performance were collected. Results showed that drivers had lower takeover readiness and worse performance when they were in high cognitive load, short TOR lead time, and heavy oncoming traffic density conditions. Interestingly, if drivers had low cognitive load, they paid more attention to driving environments and responded more quickly to takeover requests in high oncoming traffic conditions. The results have implications for the design of in-vehicle alert systems to help improve takeover performance.

For safe navigation around pedestrians, automated vehicles (AVs) need to plan their motion by accurately predicting pedestrians' trajectories over long time horizons. Current approaches to AV motion planning around crosswalks predict only for short time horizons (1-2 s) and are based on data from pedestrian interactions with human-driven vehicles (HDVs). In this paper, we develop a hybrid systems model that uses pedestrians' gap acceptance behavior and constant velocity dynamics for long-term pedestrian trajectory prediction when interacting with AVs. Results demonstrate the applicability of the model for long-term (> 5 s) pedestrian trajectory prediction at crosswalks. Further, we compared measures of pedestrian crossing behaviors in the immersive virtual environment (when interacting with AVs) to that in the real world (results of published studies of pedestrians interacting with HDVs), and found similarities between the two. These similarities demonstrate the applicability of the hybrid model of AV interactions developed from an immersive virtual environment (IVE) for real-world scenarios for both AVs and HDVs.

Automated driving has many potential benefits, such as improving driving safety and reducing drivers’ workload. However, from a human factors’ perspective, one concern is that drivers become increasingly out of the control loop once they start to engage in non-driving-related tasks, which makes it difficult for the drivers to take over control in some situations. In the present study, we examined reviewers’ comments of YouTube videos featuring takeover transitions on commercially available autonomous vehicles and categorized the comments into four topics: Non-driving related tasks, automation capability awareness, situation awareness, and warning effectiveness. Then we investigated people’ opinions on the design of the takeover mechanism of commercially available autonomous vehicles using topic mining and sentiment analysis, and we found that 1) the topic of automation capability awareness received many more positive comments than both negative and neutral comments while the distributions of positive, negative, and neutral comments were fairly even in other topics and 2) people had extreme positive and negative opinions in non-driving related tasks than other topics. Finally, we discussed possible design recommendations in order to facilitate takeover transitions.

This paper gives an overview of the ten-year development of the papers presented at the International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI) from 2009 to 2018. We categorize the topics into two main groups, namely, manual driving-related research and automated driving-related research. Within manual driving, we mainly focus on studies on user interfaces (UIs), driver states, augmented reality and head-up displays, and methodology; Within automated driving, we discuss topics, such as takeover, acceptance and trust, interacting with road users, UIs, and methodology. We also discuss the main challenges and future directions for AutoUI and offer a roadmap for the research in this area.

Workload management is of critical concern in the teleoperation of unmanned vehicles because teleoperation is often employed in high-risk industries wherein high workload can lead to sub-optimal task performance and can harm human operators’ long-term well-being. This study aimed to assess the detrimental effects of time delays in teleoperation on operators’ workload and performance, and how a delay compensation aid mitigated such effects. We conducted a human-in-the-loop experiment with 36 participants using a dual-task teleoperation platform, where participants drove a simulated High Mobility Multipurpose Wheeled Vehicle (HMMWV) and performed a one-back memory task under three conditions: the delay condition, the delay with compensation aid condition, and the ideal no delay condition. A model-free predictor was used as the compensation aid. Results indicate that with a time delay of 0.8-s participants’ workload increased and performance degraded significantly. Moreover, the model-free predictor mitigated the detrimental effects of time delay on workload and task performance. Our findings suggest that participants are more sensitive in their perceived workload compared to the objective and physiological measures of workload. In addition, without any delay compensation algorithms, continuous teleoperation may not be ideal for operations with long time delays.

Existing research assessing human operators' trust in automation and robots has primarily examined trust as a steady-state variable, with little emphasis on the evolution of trust over time. With the goal of addressing this research gap, we present a study exploring the dynamic nature of trust. We defined trust of entirety as a measure that accounts for trust across a human's entire interactive experience with automation, and first identified alternatives to quantify it using real-time measurements of trust. Second, we provided a novel model that attempts to explain how trust of entirety evolves as a user interacts repeatedly with automation. Lastly, we investigated the effects of automation transparency on momentary changes of trust. Our results indicated that trust of entirety is better quantified by the average measure of "area under the trust curve" than the traditional post-experiment trust measure. In addition, we found that trust of entirety evolves and eventually stabilizes as an operator repeatedly interacts with a technology. Finally, we observed that a higher level of automation transparency may mitigate the "cry wolf" effect -- wherein human operators begin to reject an automated system due to repeated false alarms.