Transportation and AI/ML

会議の名前
CHI 2023
Passenger Perceptions, Information Preferences, and Usability of Crowding Visualizations on Public Displays in Transit Stations and Vehicle
要旨

Large crowds in public transit stations and vehicles introduce obstacles for wayfinding, hygiene, and physical distancing. Public displays that currently provide on-site transit information could also provide critical crowdedness information. Therefore, we examined people's crowd perceptions and information preferences before and during the pandemic, and designs for visualizing crowdedness to passengers. We first report survey results with public transit users (n = 303), including the usability results of three crowdedness visualization concepts. Then, we present two animated crowd simulations on public displays that we evaluated in a field study (n = 44). We found that passengers react very positively to crowding information, especially before boarding a vehicle. Visualizing the exact physical spaces occupied on transit vehicles was most useful for avoiding crowded areas. However, visualizing the overall fullness of vehicles was the easiest to understand. We discuss design implications for communicating crowding information to support decision-making and promote a sense of safety.

著者
Leah Zhang-Kennedy
University of Waterloo, Waterloo, Ontario, Canada
Saira Aziz
University of Waterloo, Waterloo, Ontario, Canada
Oluwafunminitemi (Temi) Oluwadare
University of Waterloo, Waterloo, Ontario, Canada
Lyndon Pan
University of Waterloo, Waterloo, Ontario, Canada
Zeyu Wu
University of Waterloo, Waterloo, Ontario, Canada
Sydney E.C.. Lamorea
University of Waterloo, Waterloo, Ontario, Canada
Soda Li
University of Waterloo, Waterloo, Ontario, Canada
Michael Sun
University of Waterloo, University of Waterloo, Ontario, Canada
Ville Mäkelä
University of Waterloo, Waterloo, Ontario, Canada
論文URL

https://doi.org/10.1145/3544548.3581241

動画
Cleared for Safe Take-off? Improving the Usability of Mission Preparation to Mitigate the Safety Risks of Drone Operations
要旨

Drone operations such as power line inspection, automated deliveries, or crowd control are becoming more widespread. For flights that present serious risks to human safety, operators must conduct safety assessments and get authorizations from the regulators. These preparation tasks are complex and time-consuming but few previous works addressed them. We interviewed 14 professional drone operators, safety study consultants, and 2 regulators to better understand the needs for these tasks. The result is a workable model of the tasks which includes defining the concept of operation, assessing operational risks, and negotiating for authorization. We devised 9 recommendations to inform the design of future mission preparation tools, and consolidated them with a follow-up questionnaire. The recommendations include systematically describing a mission with operational parameters, showing their estimated impact on mission safety, or enabling awareness of the application's status among all stakeholders. We conclude with design concerns and opportunities to inform future research.

著者
Balita Heriniaina RAKOTONARIVO
ENAC - Université de Toulouse , Toulouse, France
Nicolas Drougard
ISAE-SUPAERO, Toulouse, France
Stéphane Conversy
ENAC, Toulouse, France
Jérémie Garcia
ENAC - Université de Toulouse, Toulouse, France
論文URL

https://doi.org/10.1145/3544548.3581003

動画
Aspirations and Practice of ML Model Documentation: Moving the Needle with Nudging and Traceability
要旨

The documentation practice for machine-learned (ML) models often falls short of established practices for traditional software, which impedes model accountability and inadvertently abets inappropriate or misuse of models. Recently, model cards, a proposal for model documentation, have attracted notable attention, but their impact on the actual practice is unclear. In this work, we systematically study the model documentation in the field and investigate how to encourage more responsible and accountable documentation practice. Our analysis of publicly available model cards reveals a substantial gap between the proposal and the practice. We then design a tool named DocML aiming to (1) nudge the data scientists to comply with the model cards proposal during the model development, especially the sections related to ethics, and (2) assess and manage the documentation quality. A lab study reveals the benefit of our tool towards long-term documentation quality and accountability.

著者
Avinash Bhat
McGill University, Montreal, Quebec, Canada
Austin Coursey
Vanderbilt University, Nashville, Tennessee, United States
Grace Hu
McGill University, Montreal, Quebec, Canada
Sixian Li
McGill University, Montreal, Quebec, Canada
Nadia Nahar
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Shurui Zhou
University of Toronto, Toronto, Ontario, Canada
Christian Kästner
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Jin L.C. Guo
McGill University, Montreal, Quebec, Canada
論文URL

https://doi.org/10.1145/3544548.3581518

動画
Get Distracted or Missed the Stop? Investigating Public Transit Passengers’ Travel-Based Multitasking Behaviors, Motives, and Challenges
要旨

Mobile users commonly multitask during travel, but doing so on public transit can be challenging due to the dynamic nature of the environment as well as long-standing lack of infrastructural support. Nevertheless, HCI scholars and practitioners have devoted relatively little attention to developing technology for enhancing travel multitasking. To facilitate such development, we sought to understand travel multitaskers’ practices and challenges while on public transit, and to that end, conducted a multi-methods study that involved shadowing and interviewing 30 of them. We identified four travel-multitasking patterns, characterized by distinct motives that affected these travelers’ multitasking practices, receptivity to environmental stimuli, and task persistence. The two main challenges they encountered during travel multitasking resulted from mutual interference from their tasks and from the dynamic nature of transit environments. Based on these findings, design recommendations for public-transit agencies and mobile services are also provided.

著者
Hsinju Lee
National Tsing Hua University, Hsinchu City, Taiwan
Fang-Hsin Hsu
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Wei-Ko Li
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Jie Tsai
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Ying-Yu Chen
National Yang Ming Chiao Tung University, Hsinchu City, (none), Taiwan
Yung-Ju Chang
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
論文URL

https://doi.org/10.1145/3544548.3581391

動画
Work with AI and Work for AI: Autonomous Vehicle Safety Drivers’ Lived Experiences
要旨

The development of Autonomous Vehicle (AV) has created a novel job, the safety driver, recruited from experienced drivers to supervise and operate AV in numerous driving missions. Safety drivers usually work with non-perfect AV in high-risk real-world traffic environments for road testing tasks. However, this group of workers is under-explored in the HCI community. To fill this gap, we conducted semi-structured interviews with 26 safety drivers. Our results present how safety drivers cope with defective algorithms and shape and calibrate their perceptions while working with AV. We found that, as front-line workers, safety drivers are forced to take risks accumulated from the AV industry upstream and are also confronting restricted self-development in working for AV development. We contribute the first empirical evidence of the lived experience of safety drivers, the first passengers in the development of AV, and also the grassroots workers for AV, which can shed light on future human-AI interaction research.

著者
Mengdi Chu
Tsinghua University, Beijing, China
Keyu Zong
Tsinghua University, Beijing, China
Xin Shu
Tsinghua Huniversity, Beijing, Beijing, China
Jiangtao Gong
Tsinghua University, Beijing, China
Zhicong Lu
City University of Hong Kong, Hong Kong, China
Kaimin Guo
Tsinghua university, Beijing, China
Xinyi Dai
Tsinghua University, Beijing, China
Guyue Zhou
Tsinghua University, Beijing, China
論文URL

https://doi.org/10.1145/3544548.3581564

動画