arXiv subjects

Wendy Ju

Publications and source records attributed to Wendy Ju.

50 records · Page 3Linked to original sources

arXiv2024

A Study on Domain Generalization for Failure Detection through Human Reactions in HRI

Machine learning models are commonly tested in-distribution (same dataset); performance almost always drops in out-of-distribution settings. For HRI research, the goal is often to develop generalized models. This makes domain generalization - retaining performance in different settings - a critical issue. In this study, we present a concise analysis of domain generalization in failure detection models trained on human facial expressions. Using two distinct datasets of humans reacting to videos where error occurs, one from a controlled lab setting and another collected online, we trained deep learning models on each dataset. When testing these models on the alternate dataset, we observed a significant performance drop. We reflect on the causes for the observed model behavior and leave recommendations. This work emphasizes the need for HRI research focusing on improving model robustness and real-life applicability.

cs.RO↗

arXiv2024

Portobello: Extending Driving Simulation from the Lab to the Road

In automotive user interface design, testing often starts with lab-based driving simulators and migrates toward on-road studies to mitigate risks. Mixed reality (XR) helps translate virtual study designs to the real road to increase ecological validity. However, researchers rarely run the same study in both in-lab and on-road simulators due to the challenges of replicating studies in both physical and virtual worlds. To provide a common infrastructure to port in-lab study designs on-road, we built a platform-portable infrastructure, Portobello, to enable us to run twinned physical-virtual studies. As a proof-of-concept, we extended the on-road simulator XR-OOM with Portobello. We ran a within-subjects, autonomous-vehicle crosswalk cooperation study (N=32) both in-lab and on-road to investigate study design portability and platform-driven influences on study outcomes. To our knowledge, this is the first system that enables the twinning of studies originally designed for in-lab simulators to be carried out in an on-road platform.

cs.HC↗

arXiv2024

Fingerprinting New York City's Scaffolding Problem with Longitudinal Dashcam Data

Scaffolds, also called sidewalk sheds, are intended to be temporary structures to protect pedestrians from construction and repair hazards. However, some sidewalk sheds are left up for years. Long-term scaffolding becomes eyesores, creates accessibility issues on sidewalks, and gives cover to illicit activity. Today, there are over 8,000 active permits for scaffolds in NYC; the more problematic scaffolds are likely expired or unpermitted. This research uses computer vision on street-level imagery to develop a longitudinal map of scaffolding throughout the city. Using a dataset of 29,156,833 dashcam images taken between August 2023 and January 2024, we develop an algorithm to track the presence of scaffolding over time. We also design and implement methods to match detected scaffolds to reported locations of active scaffolding permits, enabling the identification of sidewalk sheds without corresponding permits. We identify 850,766 images of scaffolding, tagging 5,156 active sidewalk sheds and estimating 529 unpermitted sheds. We discuss the implications of an in-the-wild scaffolding classifier for urban tech, innovations to governmental inspection processes, and out-of-distribution evaluations outside of New York City.

cs.CV↗

arXiv2024

Adversarial Robots as Creative Collaborators

This research explores whether the interaction between adversarial robots and creative practitioners can push artists to rethink their initial ideas. It also explores how working with these robots may influence artists' views of machines designed for creative tasks or collaboration. Many existing robots developed for creativity and the arts focus on complementing creative practices, but what if robots challenged ideas instead? To begin investigating this, I designed UnsTable, a robot drawing desk that moves the paper while participants (N=19) draw to interfere with the process. This inquiry invites further research into adversarial robots designed to challenge creative practitioners.

cs.RO↗

arXiv2023

A utility belt for an agricultural robot: reflection-in-action for applied design research

Clothing for robots can help expand a robot's functionality and also clarify the robot's purpose to bystanders. In studying how to design clothing for robots, we can shed light on the functional role of aesthetics in interactive system design. We present a case study of designing a utility belt for an agricultural robot. We use reflection-in-action to consider the ways that observation, in situ making, and documentation serve to illuminate how pragmatic, aesthetic, and intellectual inquiry are layered in this applied design research project. Themes explored in this pictorial include 1) contextual discovery of materials, tools, and practices, 2) design space exploration of materials in context, 3) improvising spaces for making, and 4) social processes in design. These themes emerged from the qualitative coding of 25 reflection-in-action videos from the researcher. We conclude with feedback on the utility belt prototypes for an agriculture robot and our learnings about context, materials, and people needed to design successful novel clothing forms for robots.

cs.RO↗

arXiv2023

Initiative and Materiality: Exploring Mixed-Initiative Calculators with the Tangible Human-A.I. Interaction Framework

How can interactions with A.I. systems be designed? This paper explores the design space for A.I. interaction to develop tools for designers to think about tangible and physical A.I. interactions. Our proposed framework consists of two dimensions: initiative (human, mixed, or machine) and materiality (physical, combined, or digital form). A particularly interesting area of interactions we identify is the quadrant of physical, machine-initiated interactions. With our framework, we examine calculator interactions and attempt to expand these to the tangible, mixed-initiative space. We illustrate each area in our proposed framework with one representative example of a calculator -- a common and well-known example of a computing device. We discuss existing examples of calculators and speculative future interactions with mixed-initiative and physical calculator systems. We reflect on the implications of our framework for the larger task of designing human-A.I. collaborative systems. Designers can also apply this framework as a guideline for analogous solutions to problems in the same domain.

cs.HC↗

arXiv2023

Implicit collaboration with a drawing machine through dance movements

In this demonstration, we exhibit the initial results of an ongoing body of exploratory work, investigating the potential for creative machines to communicate and collaborate with people through movement as a form of implicit interaction. The paper describes a Wizard-of-Oz demo, where a hidden wizard controls an AxiDraw drawing robot while a participant collaborates with it to draw a custom postcard. This demonstration aims to gather perspectives from the computational fabrication community regarding how practitioners of fabrication with machines experience interacting with a mixed-initiative collaborative machine.

cs.HC↗

arXiv2023

Detecting disparities in police deployments using dashcam data

Large-scale policing data is vital for detecting inequity in police behavior and policing algorithms. However, one important type of policing data remains largely unavailable within the United States: aggregated police deployment data capturing which neighborhoods have the heaviest police presences. Here we show that disparities in police deployment levels can be quantified by detecting police vehicles in dashcam images of public street scenes. Using a dataset of 24,803,854 dashcam images from rideshare drivers in New York City, we find that police vehicles can be detected with high accuracy (average precision 0.82, AUC 0.99) and identify 233,596 images which contain police vehicles. There is substantial inequality across neighborhoods in police vehicle deployment levels. The neighborhood with the highest deployment levels has almost 20 times higher levels than the neighborhood with the lowest. Two strikingly different types of areas experience high police vehicle deployments - 1) dense, higher-income, commercial areas and 2) lower-income neighborhoods with higher proportions of Black and Hispanic residents. We discuss the implications of these disparities for policing equity and for algorithms trained on policing data.

cs.CY↗

arXiv2023

Towards Prototyping Driverless Vehicle Behaviors, City Design, and Policies Simultaneously

Autonomous Vehicles (AVs) can potentially improve urban living by reducing accidents, increasing transportation accessibility and equity, and decreasing emissions. Realizing these promises requires the innovations of AV driving behaviors, city plans and infrastructure, and traffic and transportation policies to join forces. However, the complex interdependencies among AV, city, and policy design issues can hinder their innovation. We argue the path towards better AV cities is not a process of matching city designs and policies with AVs' technological innovations, but a process of iterative prototyping of all three simultaneously: Innovations can happen step-wise as the knot of AV, city, and policy design loosens and tightens, unwinds and reties. In this paper, we ask: How can innovators innovate AVs, city environments, and policies simultaneously and productively toward better AV cities? The paper has two parts. First, we map out the interconnections among the many AV, city, and policy design decisions, based on a literature review spanning HCI/HRI, transportation science, urban studies, law and policy, operations research, economy, and philosophy. This map can help innovators identify design constraints and opportunities across the traditional AV/city/policy design disciplinary bounds. Second, we review the respective methods for AV, city, and policy design, and identify key barriers in combining them: (1) Organizational barriers to AV-city-policy design collaboration, (2) computational barriers to multi-granularity AV-city-policy simulation, and (3) different assumptions and goals in joint AV-city-policy optimization. We discuss two broad approaches that can potentially address these challenges, namely, "low-fidelity integrative City-AV-Policy Simulation (iCAPS)" and "participatory design optimization".

cs.HC↗

arXiv2023

Frankenstein's Toolkit: Prototyping Electronics Using Consumer Products

In our practice as educators, researchers and designers we have found that centering reverse engineering and reuse has pedagogical, environmental, and economic benefits. Design decisions in the development of new hardware tool-kits should consider how we can use e-waste at hand as integral components of electronics prototyping. Dissection, extraction and modification can give insights into how things are made at scale. Simultaneously, it can enable prototypes that have greater fidelity or functionality than would otherwise be cost-effective to produce.

cs.HC↗

arXiv2023

The Bystander Affect Detection (BAD) Dataset for Failure Detection in HRI

For a robot to repair its own error, it must first know it has made a mistake. One way that people detect errors is from the implicit reactions from bystanders -- their confusion, smirks, or giggles clue us in that something unexpected occurred. To enable robots to detect and act on bystander responses to task failures, we developed a novel method to elicit bystander responses to human and robot errors. Using 46 different stimulus videos featuring a variety of human and machine task failures, we collected a total of 2452 webcam videos of human reactions from 54 participants. To test the viability of the collected data, we used the bystander reaction dataset as input to a deep-learning model, BADNet, to predict failure occurrence. We tested different data labeling methods and learned how they affect model performance, achieving precisions above 90%. We discuss strategies to model bystander reactions and predict failure and how this approach can be used in real-world robotic deployments to detect errors and improve robot performance. As part of this work, we also contribute with the "Bystander Affect Detection" (BAD) dataset of bystander reactions, supporting the development of better prediction models.

cs.RO↗

arXiv2021

The PUEVA Inventory: A Toolkit to Evaluate the Personality, Usability and Enjoyability of Voice Agents

The proliferation of voice agents in consumer devices requires new tools for evaluating these systems beyond their technical functionality. This paper presents a toolkit for the evaluation of Voice User Interfaces (VUIs) with the intention of measuring the crucial factors of subjective enjoyment in the user experience. The PUEVA toolkit was constructed using a meta-analysis of existing literature, structured N=20 and semi-structured N=18 interviews and a within subjects lab study. The resulting questionnaire contains 35 items that represent 12 scales in three categories: (1) Personality (2) Usablity and (3) Enjoyability. The PUEVA Toolkit moves us towards the capacity to evaluate and compare subjective, joyful experiences in between-subject as well as within-subject research designs.

cs.HC↗

arXiv2021

Look at Me When I Talk to You: A Video Dataset to Enable Voice Assistants to Recognize Errors

People interacting with voice assistants are often frustrated by voice assistants' frequent errors and inability to respond to backchannel cues. We introduce an open-source video dataset of 21 participants' interactions with a voice assistant, and explore the possibility of using this dataset to enable automatic error recognition to inform self-repair. The dataset includes clipped and labeled videos of participants' faces during free-form interactions with the voice assistant from the smart speaker's perspective. To validate our dataset, we emulated a machine learning classifier by asking crowdsourced workers to recognize voice assistant errors from watching soundless video clips of participants' reactions. We found trends suggesting it is possible to determine the voice assistant's performance from a participant's facial reaction alone. This work posits elicited datasets of interactive responses as a key step towards improving error recognition for repair for voice assistants in a wide variety of applications.

cs.HC↗

arXiv2021

Remote Observation of Field Work on the Farm

Travel restrictions and social distancing measures make it difficult to observe, monitor or manage physical fieldwork. We describe research in progress that applies technologies for real-time remote observation and conversation in on-road vehicles to observe field work on a farm. We collaborated on a pilot deployment of this project at Kreher Eggs in upstate New York. We instrumented a tractor with equipment to remotely observe and interview farm workers performing vehicle-related work. This work was initially undertaken to allow sustained observation of field work over longer periods of time from geographically distant locales; given our current situation, this work provides a case study in how to perform observational research when geographic and bodily distance have become the norm. We discuss our experiences and provide some preliminary insights for others looking to conduct remote observational research in the field.

cs.CY↗