Everyday tasks like hand-washing and tea-making require people to steer their hands to use tools, navigating their hands to reach targets while avoiding hazards. Hand-steering becomes challenging when one cannot visually recognize if their hand is approaching the target and is away from hazards. Currently, no practical technological solutions support blind and low-vision (BLV) individuals’ hand-steering. We designed and developed two auditory hand steering guidance methods: VERBAL and Follow-Your-Finger (FYF). VERBAL uses spoken directional instructions, while FYF uses sonification to guide hand-steering. We conducted a user study with 12 BLV participants to evaluate the feasibility of the methods in supporting hand-steering. VERBAL lacked precision, 24.6% error rate for one of the easiest conditions, but FYF showed promise, achieving 4.17% error rate for the same condition. Among the six participants who preferred FYF, the error rate was 1.39%. The results demonstrate the feasibility of auditory hand steering guidance for BLV individuals.

Robotic guidance systems have shown promise in supporting blind and visually impaired (BVI) individuals with wayfinding and obstacle avoidance. However, most existing systems assume a clear path and do not support a critical aspect of navigation—environmental interactions that require manipulating objects to enable movement. These interactions are challenging for a human–robot pair because they demand (i) precise localization and manipulation of interaction targets (e.g., pressing elevator buttons) and (ii) dynamic coordination between the user’s and robot’s movements (e.g., pulling out a chair to sit). We present a collaborative human–robot approach that combines our robotic guide dog’s precise sensing and localization capabilities with the user’s ability to perform physical manipulation. The system alternates between two modes: lead mode, where the robot detects and guides the user to the target, and adaptation mode, where the robot adjusts its motion as the user interacts with the environment (e.g., opening a door). Evaluation results show that our system enables navigation that is safer, smoother, and more efficient than both a traditional white cane and a non-adaptive guiding system, with the performance gap widening as tasks demand higher precision in locating interaction targets. These findings highlight the promise of human–robot collaboration in advancing assistive technologies toward more generalizable and realistic navigation support.

We present SPASCA - a conversational AI system that promotes psychological and cognitive well-being of persons living with dementia (PLWD). This system features an AI agent that provides social presence and support to PLWD through verbal communications, without physical presence of human caregivers. The system integrates (1) a novel dialogue model that generates dialogue items relevant to the user's experiences and lifestyle, (2) a digital avatar in the form of a talking head with the identity of a caregiver who is familiar to the demented user. We develop prototypes that adopt various interaction modalities and conversational styles and report the pros and cons of different system configurations through expert review. Our system shows the potential of conversational AI for personalized and affordable healthcare services.

Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear—particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, “Put a chair here,” while pointing at a location. If such linguistic and embodied features are common to people’s prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people’s implicit expectations when verbally prompting such programming agents to create interactive VR scenes. Our findings show when people prompted the agent, they had several implicit expectations of these agents: (1) they should have an embodied knowledge of the environment; (2) they should understand embodied prompts by users; (3) they should recall previous states of the scene and the conversation, and that (4) they should have a commonsense understanding of objects in the scene. Further, we found that participants prompted differently when they were prompting in situ (i.e. within the VR environment) versus ex situ (i.e. viewing the VR environment from the outside). To explore how these lessons could be applied, we designed and built Ostaad, a conversational programming agent that allows non-programmers to design interactive VR experiences that they inhabit. Based on these explorations, we outline new opportunities and challenges for conversational programming agents that create VR environments.

In social service centers, practitioners engage in conversations with clients with dementia to facilitate their daily activities and provide support when they are distressed. However, the nature of the care demands the practitioner’s active engagement, which becomes difficult to deliver as the number of people who need care expands. Researchers have been investigating the efficacy of developing agents that assume conversational tasks to alleviate this work. To contribute to the future design of agents for caregiving, we collected and analyzed ten conversations between clients with mild dementia and practitioners who provide care. Our analyses of turn-taking dynamics and dialogue acts with 15k utterances uncovered patterns such as noticeable differences in clients’ and practitioners’ conversational dynamics and the prevalence of neutral-toned, question-oriented utterances by practitioners. We then prototyped a large language model-based script that generates responses to client utterances. We found potential approaches and challenges for making its utterance pattern more similar to that of a practitioner.

Blind and low-vision (BLV) people use audio descriptions (ADs) to access videos. However, current ADs are unalterable by end users, thus are incapable of supporting BLV individuals’ potentially diverse needs and preferences. This research investigates if customizing AD could improve how BLV individuals consume videos. We conducted an interview study (Study 1) with fifteen BLV participants, which revealed desires for customizing properties like length, emphasis, speed, voice, format, tone, and language. At the same time, concerns like interruptions and increased interaction load due to customization emerged. To examine AD customization’s effectiveness and tradeoffs, we designed CustomAD, a prototype that enables BLV users to customize AD content and presentation. An evaluation study (Study 2) with twelve BLV participants showed using CustomAD significantly enhanced BLV people’s video understanding, immersion, and information navigation efficiency. Our work illustrates the importance of AD customization and offers a design that enhances video accessibility for BLV individuals.

Blind and Visually Impaired (BVI) people find challenges in navigating unfamiliar environments, even using assistive tools such as white canes or smart devices. Increasingly affordable quadruped robots offer us opportunities to design autonomous guides that could improve how BVI people find ways around unfamiliar environments and maneuver therein. In this work, we designed RDog, a quadruped robot guiding system that supports BVI individuals’ navigation and obstacle avoidance in indoor and outdoor environments. RDog combines an advanced mapping and navigation system to guide users with force feedback and preemptive voice feedback. Using this robot as an evaluation apparatus, we conducted experiments to investigate the difference in BVI people’s ambulatory behaviors using a white cane, a smart cane, and RDog. Results illustrated the benefits of RDog-based ambulation, including faster and smoother navigation with fewer collisions and limitations, and reduced cognitive load. We discuss the implications of our work for multi-terrain assistive guidance systems.

Videos accompanied by documents—document-based videos—enable presenters to share contents beyond videos and audience to use them for detailed content comprehension. However, concurrently exploring multiple channels of information could be taxing. We propose SwapVid, a novel interface for viewing and exploring document-based videos. SwapVid seamlessly integrates a video and a document into a single view and lets the content behaves as both video and a document; it adaptively switches a document-based video to act as a video or a document upon direct manipulation (e.g., scrolling the document, manipulating the video timeline). We conducted a user study with twenty participants, comparing SwapVid to a side-by-side video/document views. Results showed that our interface reduces time and physical workload when exploring slide-based documents based on video referencing. Based on the study findings, we extended SwapVid with additional functionalities and demonstrated that it further extends the practical capabilities.

Audio descriptions (AD) make videos accessible to those who cannot see them. But many videos lack AD and remain inaccessible as traditional approaches involve expensive professional production. We aim to lower production costs by involving novices in this process. We present an AD authoring system that supports novices to write scene descriptions (SD)-textual descriptions of video scenes-and convert them into AD via text-to-speech. The system combines video scene recognition and natural language processing to review novice-written SD and feeds back what to mention automatically. To assess the effectiveness of this automatic feedback in supporting novices, we recruited 60 participants to author SD with no feedback, human feedback, and automatic feedback. Our study shows that automatic feedback improves SD's descriptiveness, objectiveness, and learning quality, without affecting qualities like sufficiency and clarity. Though human feedback remains more effective, automatic feedback can reduce production costs by 45%.

Inaccessible e-commerce websites and mobile applications exclude people with visual impairments (PVI) from online shopping. Customer-to-customer (C2C) marketplaces, a form of e-commerce where trading happens not between businesses and customers but between customers, could pose a unique set of challenges in the interactions that the platform brings about. Through online questionnaire and remote interviews, we investigate problems experienced by people with low vision disabilities in common C2C scenarios. Our study with low vision participants (N = 12) reveal both previously known general accessibility issues (e.g., web and mobile interface accessibility) and C2C specific accessibility issues (e.g., inability to confirm item condition prior to sales).

The majority of online video contents remain inaccessible to people with visual impairments due to the lack of audio descriptions to depict the video scenes. Content creators have traditionally relied on professionals to author audio descriptions, but their service is costly and not readily-available. We investigate the feasibility of creating more cost-effective audio descriptions that are also of high quality by involving novices. Specifically, we designed, developed, and evaluated ViScene, a web-based collaborative audio description authoring tool that enables a sighted novice author and a reviewer either sighted or blind to interact and contribute to scene descriptions (SDs)—text that can be transformed into audio through text-to-speech. Through a mixed-design study with N = 60 participants, we assessed the quality of SDs created by sighted novices with feedback from both sighted and blind reviewers. Our results showed that with ViScene novices could produce content that is Descriptive, Objective, Referable, and Clear at a cost of i.e., US$2.81pvm to US$5.48pvm, which is 54% to 96% lower than the professional service. However, the descriptions lacked in other quality dimensions (e.g., learning, a measure of how well an SD conveys the video’s intended message). While professional audio describers remain the gold standard, for content creators who cannot afford it, ViScene offers a cost-effective alternative, ultimately leading to a more accessible medium.

Audio descriptions (ADs) can increase access to videos for blind people. Researchers have explored different mechanisms for generating ADs, with some of the most recent studies involving paid novices; to improve the quality of their ADs, novices receive feedback from reviewers. However, reviewer feedback is not instantaneous. To explore the potential for real-time feedback through automation, in this paper, we analyze 1,120 comments that 40 sighted novices received from a sighted or a blind reviewer. We find that feedback patterns tend to fall under four themes: (i) Quality; commenting on different AD quality variables, (ii) Speech Act; the utterance or speech action that the reviewers used, (iii) Required Action; the recommended action that the authors should do to improve the AD, and (iv) Guidance; the additional help that the reviewers gave to help the authors. We discuss which of these patterns could be automated within the review process as design implications for future AD collaborative authoring systems.

Presentation slides are widely used in occasions such as academic talks and business meetings. Captions placed on slides support deaf and hard of hearing (DHH) people to understand spoken contents, but simultaneously comprehending and associating visual contents on slides and caption text could be challenging. In this paper, we design and develop a visualization technique to highlight and associate chart on a slide and numerical data in caption. We first conduct a small formative study with people with and without hearing impairments to assess the value of the visualization technique using a lo-fidelity video prototype. We then develop Visionary Caption, a visualization technique that uses natural language processing to automatically highlight visual content and numerical phrases, and show the association between them. We present a scenario and personas to showcase the potential utility of Visionary Caption and guide its future development.

Audio descriptions can make the visual content in videos accessible to people with visual impairments. However, the majority of the online videos lack audio descriptions due in part to the shortage of experts who can create high-quality descriptions. We present ViScene, a web-based authoring tool that taps into the larger pool of sighted non-experts to help them generate high-quality descriptions via two feedback mechanisms—succinct visualizations and comments from an expert. Through a mixed-design study with N = 6 participants, we explore the usability of ViScene and the quality of the descriptions created by sighted non-experts with and without feedback comments. Our results indicate that non-experts can produce better descriptions with feedback comments; preliminary insights also highlight the role that people with visual impairments can play in providing this feedback.

We transform traditional experience writing into in-situ voice-based multimedia authoring. Documenting experiences digitally in blogs and journals is a common activity that allows people to socially connect with others by sharing their experiences (e.g. travelogue). However, documenting such experiences can be time-consuming and cognitively demanding as it is typically done OUT-OF-CONTEXT (after the actual experience). We propose in-situ voice-based multimedia authoring (IVA), an alternative workflow to allow IN-CONTEXT experience documentation. Unlike the traditional approach, IVA encourages in-context content creations using voice-based multimedia input and stores them in multi-modal “snippets”. The snippets can be rearranged to form multimedia articles and can be published with light copy-editing. To improve the output quality from impromptu speech, Q&A scaffolding was introduced to guide the content creation. We implement the IVA workflow in an android application, LiveSnippets - and qualitatively evaluate it under three scenarios (travel writing, recipe creation, product review). Results demonstrated that IVA can effectively lower the barrier of writing with acceptable trade-offs in multitasking.

Existing voice-based interfaces have limited support for text editing, especially when seeing the text is difficult, e.g., while walking or cooking. This research develops voice interaction techniques for eyes-free text editing. First, with a Wizard-of-Oz study, we identified two primary user strategies: using commands, e.g., “ replace go with goes ” and re-dictating over an erroneous portion, e.g., correcting “he go there” by saying “he goes there.” To support these user strategies with an actual system implementation, we developed two eyes-free voice interaction techniques, Commanding and Re-dictation , and evaluated them with a controlled experiment. Results showed that while Re-dictation performs significantly better for more semantically complex edits, Commanding is more suitable for making one-word edits, especially deletions. We developed VoiceRev to combine both the techniques in the same interface and evaluated it with realistic tasks. Results showed improved usability of the combined techniques over either of the two techniques used individually.

We introduce Project Sidewalk, a new web-based tool that enables online crowdworkers to remotely label pedestrian-related accessibility problems by virtually walking through city streets in Google Street View. To train, engage, and sustain users, we apply basic game design principles such as interactive onboarding, mission-based tasks, and progress dashboards. In an 18-month deployment study, 797 online users contributed 205,385 labels and audited 2,941 miles of Washington DC streets. We compare behavioral and labeling quality differences between paid crowdworkers and volunteers, investigate the effects of label type, label severity, and majority vote on accuracy, and analyze common labeling errors. To complement these findings, we report on an interview study with three key stakeholder groups (N=14) soliciting reactions to our tool and methods. Our findings demonstrate the potential of virtually auditing urban accessibility and highlight tradeoffs between scalability and quality compared to traditional approaches.

A growing number of people are working as part of on-line crowd work. Crowd work is often thought to be low wage work. However, we know little about the wage distribution in practice and what causes low/high earnings in this setting. We recorded 2,676 workers performing 3.8 million tasks on Amazon Mechanical Turk. Our task-level analysis revealed that workers earned a median hourly wage of only ~$2/h, and only 4% earned more than $7.25/h. While the average requester pays more than $11/h, lower-paying requesters post much more work. Our wage calculations are influenced by how unpaid work is accounted for, e.g., time spent searching for tasks, working on tasks that are rejected, and working on tasks that are ultimately not submitted. We further explore the characteristics of tasks and working patterns that yield higher hourly wages. Our analysis informs platform design and worker tools to create a more positive future for crowd work.

Earning money is a primary motivation for workers on Amazon Mechanical Turk, but earning a good wage is difficult because work that pays well is not easily identified and can be time-consuming to find. We explored the strategies that both low- and high-earning workers use to find and complete tasks via a survey of 360 workers. Nearly all workers surveyed had earning money as their primary goal, and workers used many of the same tools (browser extensions and scripts) and strategies in an attempt to earn more money, regardless of earning level. However, high-earning workers used more tools, were more involved in worker communities, and more heavily used batch completion strategies. A natural next step is to use automated systems to assist workers with finding and completing tasks. Workers found this idea interesting, but expressed concerns about impact on the quality of their work and whether using automated tools to support them would violate platform rules. We conclude with ideas for future work in supporting workers to earn more and design considerations for such tools.

Adults with Autism Spectrum Disorders (ASD) are unemployed at a high rate, in part because the constraints and expectations of traditional employment can be difficult for them. In this paper, we report on our work in introducing people with ASD to remote work on a crowdsourcing platform and a prototype tool we developed by working with participants. We conducted a six-week long user-centered design study with three participants with ASD. The early stage of the study focused on assessing the abilities of our participants to search and work on micro-tasks available on the crowdsourcing market. Based on our preliminary findings, we designed, developed, and evaluated a prototype tool to facilitate image transcription tasks that are increasingly popular on crowd labor markets. Our findings suggest that people with ASD have varying levels of ability to work on micro-tasks, but are likely to be able to work on tasks like image transcription. The tool we introduce, Assistive Task Queue (ATQ), facilitated our participants' completion of image transcription tasks by removing ambiguity in finding the next task to work on and in simplifying tasks into discrete steps. ATQ may serve as a general platform for finding and delivering appropriate tasks to workers with autism.

We present Project Sidewalk, a new online tool that allows anyone-from motivated citizens to government workers-to remotely label accessibility problems by virtually walking through city streets. Basic game design principles such as interactive onboarding, mission-based tasks, and stats dashboards are used to train, engage, and sustain users. We describe the current Project Sidewalk system, present results of a pilot public deployment with 581 users, and discuss open questions and future work.

In this paper, we investigate how people with mobility impairments assess and evaluate accessibility in the built environment and the role of current and emerging location-based technologies therein. We conducted a three-part formative study with 20 mobility impaired participants: a semi-structured interview (Part 1), a participatory design activity (Part 2), and a design probe activity (Part 3). Part 2 and 3 actively engaged our participants in exploring and designing the future of what we call assistive location-based technologies (ALTs) location-based technologies that specifically incorporate accessibility features to support navigating, searching, and exploring the physical world. Our Part 1 findings highlight how existing mapping tools provide accessibility benefits even though often not explicitly designed for such uses. Findings in Part 2 and 3 help identify and uncover useful features of future ALTs. In particular, we synthesize 10 key features and 6 key data qualities. We conclude with ALT design recommendations.

Language barrier is the primary challenge for effective cross-lingual conversations. Spoken language translation (SLT) is perceived as a cost-effective alternative to less affordable human interpreters, but little research has studied how people interact with such technology. Using a prototype translator application, we performed a formative evaluation to elicit how people interact with the technology and adapt their conversation style. We conducted two sets of studies with a total of 23 pairs (46 participants). Participants worked on storytelling tasks to simulate natural conversations with 3 different interface settings. Our findings show that collocutors naturally adapt their style of speech production and comprehension to compensate for inadequacies in SLT. We conclude the paper with design guidelines that emerged from the analysis.

Crowdsourcing systems leverage short bursts of focused attention from many contributors to achieve a goal. By requiring people’s full attention, existing crowdsourcing systems fail to leverage people’s cognitive surplus in the many settings for which they may be distracted, performing or waiting to perform another task, or barely paying attention. In this paper, we study opportunities for low-effort crowdsourcing that enable people to contribute to problem solving in such settings. We discuss the design space for low-effort crowdsourcing, and through a series of prototypes, demonstrate interaction techniques, mechanisms, and emerging principles for enabling low-effort crowdsourcing.

Building on recent prior work that combines Google Street View (GSV) and crowdsourcing to remotely collect information on physical world accessibility, we present the first 'smart' system, Tohme, that combines machine learning, computer vision (CV), and custom crowd interfaces to find curb ramps remotely in GSV scenes. Tohme consists of two workflows, a human labeling pipeline and a CV pipeline with human verification, which are scheduled dynamically based on predicted performance. Using 1,086 GSV scenes (street intersections) from four North American cities and data from 403 crowd workers, we show that Tohme performs similarly in detecting curb ramps compared to a manual labeling approach alone (F- measure: 84% vs. 86% baseline) but at a 13% reduction in time cost. Our work contributes the first CV-based curb ramp detection system, a custom machine-learning based workflow controller, a validation of GSV as a viable curb ramp data source, and a detailed examination of why curb ramp detection is a hard problem along with steps forward.

Low-vision and blind bus riders often rely on known physical landmarks to help locate and verify bus stop locations (e.g., by searching for a shelter, bench, newspaper bin). However, there are currently few, if any, methods to determine this information a priori via computational tools or services. In this paper, we introduce and evaluate a new scalable method for collecting bus stop location and landmark descriptions by combining online crowdsourcing and Google Street View (GSV). We conduct and report on three studies in particular: (i) a formative interview study of 18 people with visual impairments to inform the design of our crowdsourcing tool; (ii) a comparative study examining differences between physical bus stop audit data and audits conducted virtually with GSV; and (iii) an online study of 153 crowd workers on Amazon Mechanical Turk to examine the feasibility of crowdsourcing bus stop audits using our custom tool with GSV. Our findings reemphasize the importance of landmarks in non-visual navigation, demonstrate that GSV is a viable bus stop audit dataset, and show that minimally trained crowd workers can find and identify bus stop landmarks with 82.5% accuracy across 150 bus stop locations (87.3% with simple quality control).

Poorly maintained sidewalks, missing curb ramps, and other obstacles pose considerable accessibility challenges; however, there are currently few, if any, mechanisms to determine accessible areas of a city a priori. In this paper, we investigate the feasibility of using untrained crowd workers from Amazon Mechanical Turk (turkers) to find, label, and assess sidewalk accessibility problems in Google Street View imagery. We report on two studies: Study 1 examines the feasibility of this labeling task with six dedicated labelers including three wheelchair users; Study 2 investigates the comparative performance of turkers. In all, we collected 13,379 labels and 19,189 verification labels from a total of 402 turkers. We show that turkers are capable of determining the presence of an accessibility problem with 81% accuracy. With simple quality control methods, this number increases to 93%. Our work demonstrates a promising new, highly scalable method for acquiring knowledge about sidewalk accessibility.

We explore the feasibility of using crowd workers from Amazon Mechanical Turk to identify and rank sidewalk accessibility issues from a manually curated database of 100 Google Street View images. We examine the effect of three different interactive labeling interfaces (Point, Rectangle, and Outline) on task accuracy and duration. We close the paper by discussing limitations and opportunities for future work.