arXiv subjects

Wendy Ju

Publications and source records attributed to Wendy Ju.

At least 37 records · Page 2Linked to original sources

arXiv2025

Privacy of Groups in Dense Street Imagery

Spatially and temporally dense street imagery (DSI) datasets have grown unbounded. In 2024, individual companies possessed around 3 trillion unique images of public streets. DSI data streams are only set to grow as companies like Lyft and Waymo use DSI to train autonomous vehicle algorithms and analyze collisions. Academic researchers leverage DSI to explore novel approaches to urban analysis. Despite good-faith efforts by DSI providers to protect individual privacy through blurring faces and license plates, these measures fail to address broader privacy concerns. In this work, we find that increased data density and advancements in artificial intelligence enable harmful group membership inferences from supposedly anonymized data. We perform a penetration test to demonstrate how easily sensitive group affiliations can be inferred from obfuscated pedestrians in 25,232,608 dashcam images taken in New York City. We develop a typology of identifiable groups within DSI and analyze privacy implications through the lens of contextual integrity. Finally, we discuss actionable recommendations for researchers working with data from DSI providers.

cs.CY↗

arXiv2025

Co-Designing with Algorithms: Unpacking the Complex Role of GenAI in Interactive System Design Education

Generative Artificial Intelligence (GenAI) is transforming Human-Computer Interaction (HCI) education and technology design, yet its impact remains poorly understood. This study explores how graduate students in an applied HCI course used GenAI tools during interactive device design. Despite no encouragement, all groups integrated GenAI into their workflows. Through 12 post-class group interviews, we identified how GenAI co-design behaviors present both benefits, such as enhanced creativity and faster design iterations, and risks, including shallow learning and reflection. Benefits were most evident during the execution phases, while the discovery and reflection phases showed limited gains. A taxonomy of usage patterns revealed that students' outcomes depended more on how they used GenAI than the specific tasks performed. These findings highlight the need for HCI education to adapt to GenAI's role and offer recommendations for curricula to better prepare future designers for effective creative co-design.

cs.HC↗

arXiv2025

The Robotability Score: Enabling Harmonious Robot Navigation on Urban Streets

This paper introduces the Robotability Score ($R$), a novel metric that quantifies the suitability of urban environments for autonomous robot navigation. Through expert interviews and surveys, we identify and weigh key features contributing to R for wheeled robots on urban streets. Our findings reveal that pedestrian density, crowd dynamics and pedestrian flow are the most critical factors, collectively accounting for 28% of the total score. Computing robotability across New York City yields significant variation; the area of highest R is 3.0 times more "robotable" than the area of lowest R. Deployments of a physical robot on high and low robotability areas show the adequacy of the score in anticipating the ease of robot navigation. This new framework for evaluating urban landscapes aims to reduce uncertainty in robot deployment while respecting established mobility patterns and urban planning principles, contributing to the discourse on harmonious human-robot environments.

cs.RO↗

arXiv2025

My Precious Crash Data: Barriers and Opportunities in Encouraging Autonomous Driving Companies to Share Safety-Critical Data

Safety-critical data, such as crash and near-crash records, are crucial to improving autonomous vehicle (AV) design and development. Sharing such data across AV companies, academic researchers, regulators, and the public can help make all AVs safer. However, AV companies rarely share safety-critical data externally. This paper aims to pinpoint why AV companies are reluctant to share safety-critical data, with an eye on how these barriers can inform new approaches to promote sharing. We interviewed twelve AV company employees who actively work with such data in their day-to-day work. Findings suggest two key, previously unknown barriers to data sharing: (1) Datasets inherently embed salient knowledge that is key to improving AV safety and are resource-intensive. Therefore, data sharing, even within a company, is fraught with politics. (2) Interviewees believed AV safety knowledge is private knowledge that brings competitive edges to their companies, rather than public knowledge for social good. We discuss the implications of these findings for incentivizing and enabling safety-critical AV data sharing, specifically, implications for new approaches to (1) debating and stratifying public and private AV safety knowledge, (2) innovating data tools and data sharing pipelines that enable easier sharing of public AV safety data and knowledge; (3) offsetting costs of curating safety-critical data and incentivizing data sharing.

cs.HC↗

arXiv2025

Making Sense of Robots in Public Spaces: A Study of Trash Barrel Robots

In this work, we analyze video data and interviews from a public deployment of two trash barrel robots in a large public space to better understand the sensemaking activities people perform when they encounter robots in public spaces. Based on an analysis of 274 human-robot interactions and interviews with N=65 individuals or groups, we discovered that people were responding not only to the robots or their behavior, but also to the general idea of deploying robots as trashcans, and the larger social implications of that idea. They wanted to understand details about the deployment because having that knowledge would change how they interact with the robot. Based on our data and analysis, we have provided implications for design that may be topics for future human-robot design researchers who are exploring robots for public space deployment. Furthermore, our work offers a practical example of analyzing field data to make sense of robots in public spaces.

cs.RO↗

arXiv2025

Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection

Street scene datasets, collected from Street View or dashboard cameras, offer a promising means of detecting urban objects and incidents like street flooding. However, a major challenge in using these datasets is their lack of reliable labels: there are myriad types of incidents, many types occur rarely, and ground-truth measures of where incidents occur are lacking. Here, we propose BayFlood, a two-stage approach which circumvents this difficulty. First, we perform zero-shot classification of where incidents occur using a pretrained vision-language model (VLM). Second, we fit a spatial Bayesian model on the VLM classifications. The zero-shot approach avoids the need to annotate large training sets, and the Bayesian model provides frequent desiderata in urban settings - principled measures of uncertainty, smoothing across locations, and incorporation of external data like stormwater accumulation zones. We comprehensively validate this two-stage approach, showing that VLMs provide strong zero-shot signal for floods across multiple cities and time periods, the Bayesian model improves out-of-sample prediction relative to baseline methods, and our inferred flood risk correlates with known external predictors of risk. Having validated our approach, we show it can be used to improve urban flood detection: our analysis reveals 113,738 people who are at high risk of flooding overlooked by current methods, identifies demographic biases in existing methods, and suggests locations for new flood sensors. More broadly, our results showcase how Bayesian modeling of zero-shot LM annotations represents a promising paradigm because it avoids the need to collect large labeled datasets and leverages the power of foundation models while providing the expressiveness and uncertainty quantification of Bayesian models.

cs.LG↗

arXiv2025

Towards Sustainable Research Data Management in Human-Computer Interaction

We discuss important aspects of HCI research regarding Research Data Management (RDM) to achieve better publication processes and higher reuse of HCI research results. Various context elements of RDM for HCI are discussed, including examples of existing and emerging infrastructures for RDM. We briefly discuss existing approaches and come up with additional aspects which need to be addressed. This is to apply the so-called FAIR principle fully, which -- besides being findable and accessible -- also includes interoperability and reusability. We also discuss briefly the kind of research data types that play a role here and propose to build on existing work and involve the HCI scientific community to improve current practices.

cs.HC↗

arXiv2024

ReStory: VLM-augmentation of Social Human-Robot Interaction Datasets

Internet-scaled datasets are a luxury for human-robot interaction (HRI) researchers, as collecting natural interaction data in the wild is time-consuming and logistically challenging. The problem is exacerbated by robots' different form factors and interaction modalities. Inspired by recent work on ethnomethodological and conversation analysis (EMCA) in the domain of HRI, we propose ReStory, a method that has the potential to augment existing in-the-wild human-robot interaction datasets leveraging Vision Language Models. While still requiring human supervision, ReStory is capable of synthesizing human-interpretable interaction scenarios in the form of storyboards. We hope our proposed approach provides HRI researchers and interaction designers with a new angle to utilizing their valuable and scarce data.

cs.RO↗

arXiv2024

Nudge: Haptic Pre-Cueing to Communicate Automotive Intent

To increase driver awareness in a fully autonomous vehicle, we developed several haptic interaction prototypes that signal what the car is planning to do next. The goal was to use haptic cues so that the driver could be situation aware but not distracted from the non-driving tasks they may be engaged in. This paper discusses the three prototypes tested and the guiding metaphor behind each concept. We also highlight the Wizard of Oz protocol adopted to test the haptic interaction prototypes and some key findings from the pilot study.

cs.HC↗

arXiv2024

Mutual Benefit: The Case for Sharing Autonomous Vehicle Data with the Public

Autonomous driving is a widely researched technology that is frequently tested on public roads. The data generated from these tests represent an essential competitive element for the respective companies moving this technology forward. In this paper, we argue for the normative idea that a part of this data should more explicitly benefit the general public by sharing it through a trusted entity as a form of compensation and control for the communities that are being experimented upon. To support this argument, we highlight what data is available to be shared, make the ethical case for sharing autonomous vehicle data, present case studies in how AV data is currently shared, draw from existing data-sharing platforms from similar transportation industries to make recommendations on how data should be shared and conclude with arguments as to why such data-sharing should be encouraged.

cs.CY↗

arXiv2024

Regaining Trust: Impact of Transparent User Interface Design on Acceptance of Camera-Based In-Car Health Monitoring Systems

Introducing in-car health monitoring systems offers substantial potential to improve driver safety. However, camera-based sensing technologies introduce significant privacy concerns. This study investigates the impact of transparent user interface design on user acceptance of these systems. We conducted an online study with 42 participants using prototypes varying in transparency, choice, and deception levels. The prototypes included three onboarding designs: (1) a traditional Terms and Conditions text, (2) a Business Nudge design that subtly encouraged users to accept default data-sharing options, and (3) a Transparent Walk-Through that provided clear, step-by-step explanations of data use and privacy policies. Our findings indicate that transparent design significantly affects user experience measures, including perceived creepiness, trust in data use, and trustworthiness of content. Transparent onboarding processes enhanced user experience and trust without significantly increasing onboarding time. These findings offer practical guidance for designing user-friendly and privacy-respecting in-car health monitoring systems.

cs.HC↗

arXiv2024

ERR@HRI 2024 Challenge: Multimodal Detection of Errors and Failures in Human-Robot Interactions

Despite the recent advancements in robotics and machine learning (ML), the deployment of autonomous robots in our everyday lives is still an open challenge. This is due to multiple reasons among which are their frequent mistakes, such as interrupting people or having delayed responses, as well as their limited ability to understand human speech, i.e., failure in tasks like transcribing speech to text. These mistakes may disrupt interactions and negatively influence human perception of these robots. To address this problem, robots need to have the ability to detect human-robot interaction (HRI) failures. The ERR@HRI 2024 challenge tackles this by offering a benchmark multimodal dataset of robot failures during human-robot interactions (HRI), encouraging researchers to develop and benchmark multimodal machine learning models to detect these failures. We created a dataset featuring multimodal non-verbal interaction data, including facial, speech, and pose features from video clips of interactions with a robotic coach, annotated with labels indicating the presence or absence of robot mistakes, user awkwardness, and interaction ruptures, allowing for the training and evaluation of predictive models. Challenge participants have been invited to submit their multimodal ML models for detection of robot errors and to be evaluated against various performance metrics such as accuracy, precision, recall, F1 score, with and without a margin of error reflecting the time-sensitivity of these metrics. The results of this challenge will help the research field in better understanding the robot failures in human-robot interactions and designing autonomous robots that can mitigate their own errors after successfully detecting them.

cs.RO↗

arXiv2024

Using Social Cues to Recognize Task Failures for HRI: Overview, State-of-the-Art, and Future Directions

Robots that carry out tasks and interact in complex environments will inevitably commit errors. Error detection is thus an essential ability for robots to master to work efficiently and productively. People can leverage social feedback to get an indication of whether an action was successful or not. With advances in computing and artificial intelligence (AI), it is increasingly possible for robots to achieve a similar capability of collecting social feedback. In this work, we take this one step further and propose a framework for how social cues can be used as feedback signals to recognize task failures for human-robot interaction (HRI). Our proposed framework sets out a research agenda based on insights from the literature on behavioral science, human-robot interaction, and machine learning to focus on three areas: 1) social cues as feedback (from behavioral science), 2) recognizing task failures in robots (from HRI), and 3) approaches for autonomous detection of HRI task failures based on social cues (from machine learning). We propose a taxonomy of error detection based on self-awareness and social feedback. Finally, we provide recommendations for HRI researchers and practitioners interested in developing robots that detect task errors using human social cues. This article is intended for interdisciplinary HRI researchers and practitioners, where the third theme of our analysis provides more technical details aiming toward the practical implementation of these systems.

cs.RO↗

arXiv2024

(Social) Trouble on the Road: Understanding and Addressing Social Discomfort in Shared Car Trips

Unpleasant social interactions on the road can negatively affect driving safety. At the same time, researchers have attempted to address social discomfort by exploring Conversational User Interfaces (CUIs) as social mediators. Before knowing whether CUIs could reduce social discomfort in a car, it is necessary to understand the nature of social discomfort in shared rides. To this end, we recorded nine families going on drives and performed interaction analysis on this data. We define three strategies to address social discomfort: contextual mediation, social mediation, and social support. We discuss considerations for engineering and design, and explore the limitations of current large language models in addressing social discomfort on the road.

cs.HC↗

arXiv2024

Student Reflections on Self-Initiated GenAI Use in HCI Education

This study explores students' self-initiated use of Generative Artificial Intelligence (GenAI) tools in an interactive systems design class. Through 12 group interviews, students revealed the dual nature of GenAI in (1) stimulating creativity and (2) speeding up design iterations, alongside concerns over its potential to cause shallow learning and reliance. GenAI's benefits were pronounced in the execution phase of design, aiding rapid prototyping and ideation, while its use in initial insight generation posed risks to depth and reflective practice. This reflection highlights the complex role of GenAI in Human-Computer Interaction education, emphasizing the need for balanced integration to leverage its advantages without compromising fundamental learning outcomes.

cs.HC↗

arXiv2024

Field Notes on Deploying Research Robots in Public Spaces

Human-robot interaction requires to be studied in the wild. In the summers of 2022 and 2023, we deployed two trash barrel service robots through the wizard-of-oz protocol in public spaces to study human-robot interactions in urban settings. We deployed the robots at two different public plazas in downtown Manhattan and Brooklyn for a collective of 20 hours of field time. To date, relatively few long-term human-robot interaction studies have been conducted in shared public spaces. To support researchers aiming to fill this gap, we would like to share some of our insights and learned lessons that would benefit both researchers and practitioners on how to deploy robots in public spaces. We share best practices and lessons learned with the HRI research community to encourage more in-the-wild research of robots in public spaces and call for the community to share their lessons learned to a GitHub repository.

cs.RO↗

arXiv2024

Designing a User-centric Framework for Information Quality Ranking of Large-scale Street View Images

Street view imagery (SVI), largely captured via outfitted fleets or mounted dashcams in consumer vehicles is a rapidly growing source of geospatial data used in urban sensing and development. These datasets are often collected opportunistically, are massive in size, and vary in quality which limits the scope and extent of their use in urban planning. Thus far there has not been much work to identify the obstacles experienced and tools needed by the users of such datasets. This severely limits the opportunities of using emerging street view images in supporting novel research questions that can improve the quality of urban life. This work includes a formative interview study with 5 expert users of large-scale street view datasets from academia, urban planning, and related professions which identifies novel use cases, challenges, and opportunities to increase the utility of these datasets. Based on the user findings, we present a framework to evaluate the quality of information for street images across three attributes (spatial, temporal, and content) that stakeholders can utilize for estimating the value of a dataset, and to improve it over time for their respective use case. We then present a case study using novel street view images where we evaluate our framework and present practical use cases for users. We discuss the implications for designing future systems to support the collection and use of street view data to assist in sensing and planning the urban environment.

cs.HC↗

arXiv2024

SSUP-HRI: Social Signaling in Urban Public Human-Robot Interaction dataset

This paper introduces our dataset featuring human-robot interactions (HRI) in urban public environments. This dataset is rich with social signals that we believe can be modeled to help understand naturalistic human-robot interaction. Our dataset currently comprises approximately 15 hours of video footage recorded from the robots' perspectives, within which we annotated a total of 274 observable interactions featuring a wide range of naturalistic human-robot interactions. The data was collected by two mobile trash barrel robots deployed in Astor Place, New York City, over the course of a week. We invite the HRI community to access and utilize our dataset. To the best of our knowledge, this is the first dataset showcasing robot deployments in a complete public, non-controlled setting involving urban residents.

cs.RO↗