Yaohan Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yaohan Ding has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Na Du
School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
4 shared publications Na Du
University of Pittsburgh, PA, USA
3 shared publications- Lesong Jia
School of Computing and Information, University of Pittsburgh
2 shared publications Balaji Palanisamy
University of Pittsburgh, PA, USA
1 shared publication- Beining Yang
University of Pittsburgh, PA, USA
1 shared publication Bowen Ye
University of Pittsburgh, PA, USA
1 shared publication
Latest Publications
- Open Access
- 29 October 2026
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
Designing Backup-Supporting Information Displays for Multi-Human Multi-Agent Teams in Drone Swarm Supervision
Search-and-rescue (SAR) drone swarms increasingly require multi-operator supervision, in which backup behaviors redistribute cognitive load to improve performance but introduce trade-offs in situational awareness (SA) and task engagement. Existing human-autonomy teaming interfaces present symmetric displays across all roles, ignoring the asymmetric information needs of backup providers and recipients. We developed a two-human, eight-drone Unity SAR testbed that operationalizes three team structures (independent, Operator A-busy, Operator B-busy) via event-allocation manipulation, with a SPAM (Situation Present Assessment Method)-derived in-task SA probe. Three iterative focus groups with eight human-centered design researchers and professionals yielded four display conditions: no-display baseline, effort display, urgency display, and combined. Semi-structured interviews with three SAR practitioners confirmed high realism ratings for the overall testbed and the viability of dynamic backup. A feasibility pilot study ( N = 4) revealed a significant main effect of team structure on backup count, confirming that the manipulation elicits backup behaviors as designed.
- 29 October 2026
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
Open AccessDesigning Backup-Supporting Information Displays for Multi-Human Multi-Agent Teams in Drone Swarm Supervision
Search-and-rescue (SAR) drone swarms increasingly require multi-operator supervision, in which backup behaviors redistribute cognitive load to improve performance but introduce trade-offs in situational awareness (SA) and task engagement. Existing human-autonomy teaming interfaces present symmetric displays across all roles, ignoring the asymmetric information needs of backup providers and recipients. We developed a two-human, eight-drone Unity SAR testbed that operationalizes three team structures (independent, Operator A-busy, Operator B-busy) via event-allocation manipulation, with a SPAM (Situation Present Assessment Method)-derived in-task SA probe. Three iterative focus groups with eight human-centered design researchers and professionals yielded four display conditions: no-display baseline, effort display, urgency display, and combined. Semi-structured interviews with three SAR practitioners confirmed high realism ratings for the overall testbed and the viability of dynamic backup. A feasibility pilot study ( N = 4) revealed a significant main effect of team structure on backup count, confirming that the manipulation elicits backup behaviors as designed.
- 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.
- 13 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69 (1) , 1052-1054
Understanding User Privacy and Disclosure Decisions in Virtual Reality
Understanding the thought process behind users’ disclosure of sensitive personal information in the Virtual Reality (VR) context is essential for addressing the unique privacy issues posed by the extensive and distinctive data collection of VR. Our research focuses on understanding VR users’ underlying motivations for disclosing personal information or withholding it while they access VR services. We designed twelve game-based scenarios to simulate real-life privacy challenges encountered during VR usage and recruited participants to engage with these scenarios. Our proposed structural equation model suggests that disclosure decisions are influenced by anticipated outcomes, trust, and perceived risks, contingent upon the type of data being collected. In addition, the semantic analysis revealed VR users’ disclosure decisions were shaped by their perceptions of data sensitivity, expectations of potential outcomes, and past experiences with data collection. Our study offers insights into privacy-centric designs and guide the development of responsible interactions in the VR environment.
- 13 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69 (1) , 1052-1054
Understanding User Privacy and Disclosure Decisions in Virtual Reality
Understanding the thought process behind users’ disclosure of sensitive personal information in the Virtual Reality (VR) context is essential for addressing the unique privacy issues posed by the extensive and distinctive data collection of VR. Our research focuses on understanding VR users’ underlying motivations for disclosing personal information or withholding it while they access VR services. We designed twelve game-based scenarios to simulate real-life privacy challenges encountered during VR usage and recruited participants to engage with these scenarios. Our proposed structural equation model suggests that disclosure decisions are influenced by anticipated outcomes, trust, and perceived risks, contingent upon the type of data being collected. In addition, the semantic analysis revealed VR users’ disclosure decisions were shaped by their perceptions of data sensitivity, expectations of potential outcomes, and past experiences with data collection. Our study offers insights into privacy-centric designs and guide the development of responsible interactions in the VR environment.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Explanations Help: Leveraging Human Capabilities to Detect Cyberattacks on Automated Vehicles
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessExplanations Help: Leveraging Human Capabilities to Detect Cyberattacks on Automated Vehicles
- Open Access
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 226-230
Investigating Effects of Drivers' Self-Confidence and Confidence in Automated Vehicles on Trust and Takeover Intention
To maximize the benefits of driving automated vehicles (AVs), humans can allow the more capable party to drive in certain scenarios, which requires proper trust and takeover intention from humans. We conducted an online survey study with 136 participants to examine how drivers’ self-confidence and confidence in AV, as indicators of perceived driving capability, influence their trust and takeover intention in AVs. Results suggested that confidence in AV had a larger effect than self-confidence. Generally, low confidence in AV predicted lower trust and higher takeover intention, while low self-confidence predicted lower takeover intention. Specifically, low self-confidence predicted higher trust only when confidence in AV was low. Furthermore, we observed similar levels of trust across different self-confidence levels when confidence in AV was high, suggesting a potential ceiling effect of trust on imperfect AVs. Our findings provide a better understanding of human-AV teaming patterns from the perspective of human factors.
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 226-230
Open AccessInvestigating Effects of Drivers' Self-Confidence and Confidence in Automated Vehicles on Trust and Takeover Intention
To maximize the benefits of driving automated vehicles (AVs), humans can allow the more capable party to drive in certain scenarios, which requires proper trust and takeover intention from humans. We conducted an online survey study with 136 participants to examine how drivers’ self-confidence and confidence in AV, as indicators of perceived driving capability, influence their trust and takeover intention in AVs. Results suggested that confidence in AV had a larger effect than self-confidence. Generally, low confidence in AV predicted lower trust and higher takeover intention, while low self-confidence predicted lower takeover intention. Specifically, low self-confidence predicted higher trust only when confidence in AV was low. Furthermore, we observed similar levels of trust across different self-confidence levels when confidence in AV was high, suggesting a potential ceiling effect of trust on imperfect AVs. Our findings provide a better understanding of human-AV teaming patterns from the perspective of human factors.
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
One Size Does Not Fit All: Designing and Evaluating Criticality-Adaptive Displays in Highly Automated Vehicles
To promote drivers’ overall experiences in highly automated vehicles, we designed three objective criticality-adaptive displays: IO display highlighting Influential Objects, CO display highlighting Critical Objects, and ICO display highlighting Influential and Critical Objects differently. We conducted an online video-based survey study with 295 participants to evaluate them in varying traffic conditions. Results showed that low-trust propensity participants found ICO display more useful while high-trust propensity participants found CO displays more useful. When interacting with vulnerable road users (VRUs), participants had higher situational awareness (SA) but worse non-driving related task (NDRT) performance. Aging and CO displays also led to slower NDRT reactions. Nonetheless, older participants found displays more useful. We recommend providing different criticality-adaptive displays based on drivers’ trust propensity, age, and NDRT choice to enhance driving and NDRT performance and suggest carefully treating objects of different categories in traffic.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessOne Size Does Not Fit All: Designing and Evaluating Criticality-Adaptive Displays in Highly Automated Vehicles
To promote drivers’ overall experiences in highly automated vehicles, we designed three objective criticality-adaptive displays: IO display highlighting Influential Objects, CO display highlighting Critical Objects, and ICO display highlighting Influential and Critical Objects differently. We conducted an online video-based survey study with 295 participants to evaluate them in varying traffic conditions. Results showed that low-trust propensity participants found ICO display more useful while high-trust propensity participants found CO displays more useful. When interacting with vulnerable road users (VRUs), participants had higher situational awareness (SA) but worse non-driving related task (NDRT) performance. Aging and CO displays also led to slower NDRT reactions. Nonetheless, older participants found displays more useful. We recommend providing different criticality-adaptive displays based on drivers’ trust propensity, age, and NDRT choice to enhance driving and NDRT performance and suggest carefully treating objects of different categories in traffic.
- 1 September 2023
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 67 (1) , 1176-1177
Designing for Trust and Situational Awareness in Automated Vehicles: Effects of Information Type and Error Type
Trust and situational awareness (SA) are crucial to the adoption and safety of automated vehicles (AVs). Appropriate design of AV explanations could promote drivers’ acceptance, trust, and SA, enabling drivers to get more benefits from the technology. This study investigated the effects of error type and information type of AV explanations on drivers’ trust and SA. We recruited 300 participants for an online video study with a 3 (information type) × 2 (error type) mixed design. Linear mixed model analyses showed that compared with false alarms, misses were associated with more trust decrease after the error and more trust decrease after the post-error recovery. Compared with why information, how information was associated with lower SA generally and risked potential over-trust in false alarms. Therefore, we recommend deploying AV decision systems that are less miss-prone and including why information in AV explanations.
- 1 September 2023
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 67 (1) , 1176-1177
Designing for Trust and Situational Awareness in Automated Vehicles: Effects of Information Type and Error Type
Trust and situational awareness (SA) are crucial to the adoption and safety of automated vehicles (AVs). Appropriate design of AV explanations could promote drivers’ acceptance, trust, and SA, enabling drivers to get more benefits from the technology. This study investigated the effects of error type and information type of AV explanations on drivers’ trust and SA. We recruited 300 participants for an online video study with a 3 (information type) × 2 (error type) mixed design. Linear mixed model analyses showed that compared with false alarms, misses were associated with more trust decrease after the error and more trust decrease after the post-error recovery. Compared with why information, how information was associated with lower SA generally and risked potential over-trust in false alarms. Therefore, we recommend deploying AV decision systems that are less miss-prone and including why information in AV explanations.