Na Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Na Du has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Yutong Zhang
University of Pittsburgh, PA, USA
6 shared publications - Lesong Jia
School of Computing and Information, University of Pittsburgh
5 shared publications - Xi Jessie Yang
University of Michigan, Ann Arbor, USA
5 shared publications - Lionel Peter Robert
University of Michigan, Ann Arbor, USA
4 shared publications - Shihong Ling
Department of Informatics and Networked Systems, School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
4 shared publications - Yaohan Ding
University of Pittsburgh, PA, USA
4 shared publications
Latest Publications
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 99-112
VRSafe: A Secure Virtual Keyboard to Mitigate Keystroke Inference in Virtual Reality
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 99-112
Open AccessVRSafe: A Secure Virtual Keyboard to Mitigate Keystroke Inference in Virtual Reality
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
When to Explain: Modeling User Need for Explanations in Real-World Autonomous Driving
The integration of artificial intelligence into autonomous vehicles (AVs) raises transparency challenges that can hinder user acceptance and experience. To address when users need AV explanations, we created a large-scale dataset of 3327 diverse driving scenarios, each paired with a user-friendly explanation, and conducted an online study to survey when users need explanations. Using both scenario and user-related factors, our best-performing tree-ensemble models predicted explanation need with great performance (F1=0.72, AUC=0.82). SHAP analyses revealed that while both user- and scenario-related factors matter, factors directly related to driving (AV driving style, AV action, event cause, annual mileage, human driving style) were more contributive than general demographics and environmental factors. Our study delivers a comprehensively annotated dataset that underpins future human-AV interaction research, an explainable model that reliably predicts explanation needs, and valuable insights to inform the design of adaptive AV interfaces for superior user experiences.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessWhen to Explain: Modeling User Need for Explanations in Real-World Autonomous Driving
The integration of artificial intelligence into autonomous vehicles (AVs) raises transparency challenges that can hinder user acceptance and experience. To address when users need AV explanations, we created a large-scale dataset of 3327 diverse driving scenarios, each paired with a user-friendly explanation, and conducted an online study to survey when users need explanations. Using both scenario and user-related factors, our best-performing tree-ensemble models predicted explanation need with great performance (F1=0.72, AUC=0.82). SHAP analyses revealed that while both user- and scenario-related factors matter, factors directly related to driving (AV driving style, AV action, event cause, annual mileage, human driving style) were more contributive than general demographics and environmental factors. Our study delivers a comprehensively annotated dataset that underpins future human-AV interaction research, an explainable model that reliably predicts explanation needs, and valuable insights to inform the design of adaptive AV interfaces for superior user experiences.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
How Humans Naturally Refer to Targets: Understanding Multimodal Instruction Patterns in Human–Robot Interaction
Current multimodal instruction-recognition algorithms in human-robot interaction, developed largely from a purely technical perspective, remain rigid and incomplete in their use of human communicative cues. Therefore, a full understanding of how humans naturally refer to targets in interaction is central to enabling robots to interpret and act on user instructions. To investigate this, we collected multimodal behavior data from 30 participants who naturally instructed a robot for household tasks while we systematically varied target distance, direction, and local referent complexity. Our results show that speech instructions were often vague and lacked explicit target-position information. To resolve this ambiguity, multimodal cues are essential: gaze direction provides an order-of-magnitude improvement in target-localization accuracy, while hand pointing, head turns, and speech onset offer reliable temporal anchors for identifying target-directed gaze. We also found that speech patterns varied with distance and local referent complexity, whereas multimodal behaviors shifted with target direction, underscoring the need for context-adaptive recognition and interface design.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessHow Humans Naturally Refer to Targets: Understanding Multimodal Instruction Patterns in Human–Robot Interaction
Current multimodal instruction-recognition algorithms in human-robot interaction, developed largely from a purely technical perspective, remain rigid and incomplete in their use of human communicative cues. Therefore, a full understanding of how humans naturally refer to targets in interaction is central to enabling robots to interpret and act on user instructions. To investigate this, we collected multimodal behavior data from 30 participants who naturally instructed a robot for household tasks while we systematically varied target distance, direction, and local referent complexity. Our results show that speech instructions were often vague and lacked explicit target-position information. To resolve this ambiguity, multimodal cues are essential: gaze direction provides an order-of-magnitude improvement in target-localization accuracy, while hand pointing, head turns, and speech onset offer reliable temporal anchors for identifying target-directed gaze. We also found that speech patterns varied with distance and local referent complexity, whereas multimodal behaviors shifted with target direction, underscoring the need for context-adaptive recognition and interface design.
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 972-981
Aligning Task Goals before Execution: Insights from Diverse User Groups into Human–Robot Communication in Domestic Settings
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 972-981
Open AccessAligning Task Goals before Execution: Insights from Diverse User Groups into Human–Robot Communication in Domestic Settings
- 27 January 2026
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 18  (1) , 11
Robots with Heart: How Emotion Regulation Shapes Human-Robot Interaction
- 27 January 2026
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 18  (1) , 11
Robots with Heart: How Emotion Regulation Shapes Human-Robot Interaction
- Open Access
- 8 October 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 223, 108254
Human-machine cooperation strategies in game-theoretic scenarios within mixed traffic: A simulator study on driving styles
- 8 October 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 223, 108254
Open AccessHuman-machine cooperation strategies in game-theoretic scenarios within mixed traffic: A simulator study on driving styles
- 11 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69  (1) , 856-858
Game-theoretic Strategies in Mixed Traffic: A Simulator Study on the Impacts of Automated and Human Driving Styles
As human-driven vehicles (HVs) and automated vehicles (AVs) increasingly share roadways, understanding their interactions is essential for traffic safety and efficiency. This driving simulator study using game-theoretic scenarios investigates how AV and human driving styles influence decision-making in mixed traffic. The findings showed that conservative AVs were more likely to be exploited, while aggressive human drivers acted less cooperatively. AV driving styles had a stronger impact in parallel interactions: aggressive AVs led to passive yet riskier human maneuvers, with shorter time-to-collision and higher lateral deceleration. Conservative drivers showed greater maximum counter-steering rate and lateral deceleration to adjust their intentions and avoid risks. In head-on interactions, drivers more often insisted on their right of way. Additionally, trajectory clustering demonstrated the differences in driver strategies in specific scenarios. These findings highlight the need for adaptive AV strategies to foster safe and cooperative mixed-traffic interactions.
- 11 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69  (1) , 856-858
Game-theoretic Strategies in Mixed Traffic: A Simulator Study on the Impacts of Automated and Human Driving Styles
As human-driven vehicles (HVs) and automated vehicles (AVs) increasingly share roadways, understanding their interactions is essential for traffic safety and efficiency. This driving simulator study using game-theoretic scenarios investigates how AV and human driving styles influence decision-making in mixed traffic. The findings showed that conservative AVs were more likely to be exploited, while aggressive human drivers acted less cooperatively. AV driving styles had a stronger impact in parallel interactions: aggressive AVs led to passive yet riskier human maneuvers, with shorter time-to-collision and higher lateral deceleration. Conservative drivers showed greater maximum counter-steering rate and lateral deceleration to adjust their intentions and avoid risks. In head-on interactions, drivers more often insisted on their right of way. Additionally, trajectory clustering demonstrated the differences in driver strategies in specific scenarios. These findings highlight the need for adaptive AV strategies to foster safe and cooperative mixed-traffic interactions.
- 2 September 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 42  (8) , 5762-5780
Modeling Driver Situational Awareness in Takeover Scenarios Using Multimodal Data and Machine Learning
- 2 September 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 42  (8) , 5762-5780
Modeling Driver Situational Awareness in Takeover Scenarios Using Multimodal Data and Machine Learning
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 55  (3) , 450-459
Watch Out for Explanations: Information Type and Error Type Affect Trust and Situational Awareness in Automated Vehicles
Trust and situational awareness (SA) are critical for the acceptance and safety of automated vehicles (AVs). While AV explanations with different information types have been studied to enhance drivers' trust and SA, their effectiveness remains unclear when AVs make errors that do not trigger takeover requests. This study investigated the effects of information type, error type, and their interaction on drivers' trust in AVs, SA, and their relationships. We recruited 300 participants in an online video study with a 3 (information type: why, how, why + how) Ă— 3 (error type: false alarm, miss, correct [no error]) mixed design. How information describes the vehicle's action, while why information refers to the reason for the vehicle's action. Linear mixed models showed that false alarms and misses were associated with lower SA compared with correct scenarios, but possibly due to different reasons. Compared with correct scenarios, both false alarms and misses were associated with lower trust, with misses even lower than false alarms, possibly due to the varying severity of potential consequences. Compared with why and why + how information, how information was generally associated with lower SA and a higher potential of overtrust in false alarms. Trust and SA had a negative linear relationship in misses and false alarms, while no correlations were found in correct scenarios. To mitigate potential overtrust and misinterpretation of situations when AVs make errors, it is crucial to maintain higher SA. We recommend including why information in AV explanations and deploying AV decision systems that are less miss-prone.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 55  (3) , 450-459
Watch Out for Explanations: Information Type and Error Type Affect Trust and Situational Awareness in Automated Vehicles
Trust and situational awareness (SA) are critical for the acceptance and safety of automated vehicles (AVs). While AV explanations with different information types have been studied to enhance drivers' trust and SA, their effectiveness remains unclear when AVs make errors that do not trigger takeover requests. This study investigated the effects of information type, error type, and their interaction on drivers' trust in AVs, SA, and their relationships. We recruited 300 participants in an online video study with a 3 (information type: why, how, why + how) Ă— 3 (error type: false alarm, miss, correct [no error]) mixed design. How information describes the vehicle's action, while why information refers to the reason for the vehicle's action. Linear mixed models showed that false alarms and misses were associated with lower SA compared with correct scenarios, but possibly due to different reasons. Compared with correct scenarios, both false alarms and misses were associated with lower trust, with misses even lower than false alarms, possibly due to the varying severity of potential consequences. Compared with why and why + how information, how information was generally associated with lower SA and a higher potential of overtrust in false alarms. Trust and SA had a negative linear relationship in misses and false alarms, while no correlations were found in correct scenarios. To mitigate potential overtrust and misinterpretation of situations when AVs make errors, it is crucial to maintain higher SA. We recommend including why information in AV explanations and deploying AV decision systems that are less miss-prone.