Browsing by Author "Wang, Manhua"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
- Am I Really Angry? The Influence of Anger Intensities on Young Drivers' BehaviorsWang, Manhua; Jeon, Myounghoon (ACM, 2023-09-18)Anger can lead to aggressive driving and other negative behaviors. While previous studies treated anger as a single dimension, the present research proposed that anger has distinct intensities and aimed to understand the effects of different anger intensities on driver behaviors. After developing the anger induction materials, we conducted a driving simulator study with 30 participants and assigned them to low, medium, and high anger intensity groups. We found that drivers with low anger intensity were not able to recognize their emotions and exhibited speeding behaviors, while drivers with medium and high anger intensities might be aware of their anger along with its adverse effects and then adjusted their longitudinal control. However, angry drivers generally exhibited compromised lateral control indicated by steering and lane-keeping behaviors. Our findings shed light on the potentially different influences of anger intensities on young drivers’ behaviors, especially the importance of anger recognition for intervention solutions.
- Jarvis in the car: Report on characterizing and designing in-vehicle intelligent agents workshopWang, Manhua; Hock, Phillip; Chan Lee, Seul; Baumann, Martin; Jeon, Myounghoon (SAGE, 2022-10-27)As intelligent agents have become more popular at home, they have been progressively introduced into driving environments. Although previous research has discussed agent features and their effects on driver perception and performance, attributes that define in-vehicle agents and distinguish them from other intelligent agents have not been discussed clearly. Thus, we organized a workshop on characterizing and designing in-vehicle intelligent agents at the 13th International Conference on Automotive User Interfaces (AutoUI 2021). In this report, we integrated ideas generated during the workshop and identified user-centered action and autonomy as two attributes that define an agent, with functions and features as specific characteristics that vary agent design. The outcomes of this workshop can facilitate in-vehicle intelligent agent design and deliver optimal user experience, while providing insights on manipulating variables in controlled studies.
- Physiological Linkage Between Autistic and Non-autistic Adult Dyads During Collaborative TasksKim, Sun Wook; Fok, Megan; Wang, Manhua; Theodat, Anabelle; Baker, Brian; Jeon, Myounghoon; Scarpa, Angela (2022-09-28)
- Reliable and transparent in-vehicle agents lead to higher behavioral trust in conditionally automated driving systemsTaylor, Skye; Wang, Manhua; Jeon, Myounghoon (Frontiers, 2023-05)Trust is critical for human-automation collaboration, especially under safety-critical tasks such as driving. Providing explainable information on how the automation system reaches decisions and predictions can improve system transparency, which is believed to further facilitate driver trust and user evaluation of the automated vehicles. However, what the optimal level of transparency is and how the system communicates it to calibrate drivers' trust and improve their driving performance remain uncertain. Such uncertainty becomes even more unpredictable given that the system reliability remains dynamic due to current technological limitations. To address this issue in conditionally automated vehicles, a total of 30 participants were recruited in a driving simulator study and assigned to either a low or a high system reliability condition. They experienced two driving scenarios accompanied by two types of in-vehicle agents delivering information with different transparency types: "what"-then-wait (on-demand) and "what + why" (proactive). The on-demand agent provided some information about the upcoming event and delivered more information if prompted by the driver, whereas the proactive agent provided all information at once. Results indicated that the on-demand agent was more habitable, or naturalistic, to drivers and was perceived with faster system response speed compared to the proactive agent. Drivers under the high-reliability condition complied with the takeover request (TOR) more (if the agent was on-demand) and had shorter takeover times (in both agent conditions) compared to those under the low-reliability condition. These findings inspire how the automation system can deliver information to improve system transparency while adapting to system reliability and user evaluation, which further contributes to driver trust calibration and performance correction in future automated vehicles.
- Using Multilevel Hidden Markov Models to Understand Driver Hazard Avoidance during the Takeover Process in Conditionally Automated VehiclesWang, Manhua; Parikh, Ravi; Jeon, Myounghoon (SAGE, 2023-10-25)Ensuring a safe transition between the automation system and human operators is critical in conditionally automated vehicles. During the automation-to-human transition process, hazard avoidance plays an important role after human drivers regain the vehicle control. This study applies the multilevel Hidden Markov Model to understand the hazard avoidance processes in response to static road hazards as continuous processes. The three-state model—Approaching, Negotiating, and Recovering—had the best model fitness, compared to the four-state and five-state models. The trained model reaches an average of 66% accuracy rate on predicting hazard avoidance states on the testing data. The prediction performance reveals the possibility to use the hazard avoidance pattern to recognize driving behaviors. We further propose several improvements at the end to generalize our models into other scenarios, including the potential to model hazard avoidance as a basic driving skill across different levels of automation conditions.
- What Do You Want for In-Vehicle Agents? One Fits All vs. Multiple Specialized AgentsPark, Se Hyeon; Lee, Seul Chan; Wang, Manhua; Hock, Philipp; Baumann, Martin; Jeon, Myounghoon (ACM, 2022-09-17)It is expected that in-vehicle intelligent agents (IVIAs) become an important user interface in automated driving, and much research on how to design IVIAs considering user needs and scenarios has been conducted. The question arising here is whether people want to have one almighty agent connecting to all user's data sources and dealing with all situations, including driving contexts. Another plausible form is multiple specialized agents that play the role only in each task context. As a first step in answering the question, we developed two plausible scenarios of interacting with IVIAs and presented the video. In both scenarios, a user of IVIAs experiences embarrassing situations because of the connectivity of IVIAs. We expect that this effort can be a starting point to understand users' needs and requirements to develop and design IVIAs in terms of connectivity.