ARTennis attempts to help low vision players

December 16, 2023

People with low vision (LV) have had fewer options for physical activity, particularly in competitive sports such as tennis and soccer that involve fast, continuously moving elements such as balls and players. A group of researchers from CREATE associate director Jon E. Froehlich‘s Makeability Lab hopes to overcome this challenge by enabling LV individuals to participate in ball-based sports using real-time computer vision (CV) and wearable augmented reality (AR) headsets. Their initial focus has been on tennis.

The team includes Jaewook Lee (Ph.D. student, UW CSE), Devesh P. Sarda (MS/Ph.D. student, University of Wisconsin), Eujean Lee (Research Assistant, UW Makeability Lab), Amy Seunghyun Lee (BS student, UC Davis), Jun Wang (BS student, UW CSE), Adrian Rodriguez (Ph.D. student, UW HCDE), and Jon Froehlich.

Their paper, Towards Real-time Computer Vision and Augmented Reality to Support Low Vision Sports: A Demonstration of ARTennis was published in the 2023 ACM Symposium on User Interface Software and Technology (UIST).

ARTennis is their prototype system capable of tracking and enhancing the visual saliency of tennis balls from a first-person point-of-view (POV). Recent advancements in deep learning have led to models like TrackNet, a neural network capable of tracking tennis balls in third-person recordings of tennis games that is used to improve sports viewing for LV people. To enhance playability, the team first built a dataset of first-person POV images by having the authors wear an AR headset and play tennis. They then streamed video from a pair of AR glasses to a back-end server, analyzed the frames using a custom-trained deep learning model, and sent back the results for real-time overlaid visualization.

After a brainstorming session with an LV research team member, the team added visualization improvements to enhance the ball’s color contrast and add a crosshair in real-time.

Early evaluations have provided feedback that the prototype could help LV people enjoy ball-based sports but there’s plenty of further work to be done. A larger field-of-view (FOV) and audio cues would improve a player’s ability to track the ball. The weight and bulk of the headset, in addition to its expense are also factors the team expects to improve with time, as Lee noted in an interview on Oregon Public Broadcasting.

“Wearable AR devices such as the Microsoft HoloLens 2 hold immense potential in non-intrusively improving accessibility of everyday tasks. I view AR glasses as a technology that can enable continuous computer vision, which can empower BLV individuals to participate in day-to-day tasks, from sports to cooking. The Makeability Lab team and I hope to continue exploring this space to improve the accessibility of popular sports, such as tennis and basketball.”

Jaewook Lee, Ph.D. student and lead author

Ph.D. student Jaewook Lee presents a research poster, Makeability Lab Demos - GazePointAR & ARTennis.

UW News: How an assistive-feeding robot went from picking up fruit salads to whole meals

November, 2023

In tests with this set of actions, the robot picked up the foods more than 80% of the time, which is the user-specified benchmark for in-home use. The small set of actions allows the system to learn to pick up new foods during one meal. UW News talked with Gordon and Nanavati co-lead authors, both doctoral students in the Paul G. Allen School of Computer Science & Engineering, and with co-author Taylor Kessler Faulkner, a UW postdoctoral scholar in the Allen School, about the successes and challenges of robot-assisted feeding.

An assistive-feeding robotic arm attached to a wheelchair uses a fork to stab a piece of fruit on a plate among other fruits.

The team presented its findings Nov. 7 at the 2023 Conference on Robotic Learning in Atlanta.

UW News talked with co-lead authors Gordon and Nanavati, both doctoral students members of CREATE and in the Paul G. Allen School of Computer Science & Engineering, and with co-author Taylor Kessler Faulkner, a UW postdoctoral scholar in the Allen School, about the successes and challenges of robot-assisted feeding for 1.8 million people in the U.S. (according to data from 2010) who can’t eat on their own.

The Personal Robotics Lab has been working on robot-assisted feeding for several years. What is the advance of this paper?

Ethan K. Gordon: I joined the Personal Robotics Lab at the end of 2018 when Siddhartha Srinivasa, a professor in the Allen School and senior author of our new study, and his team had created the first iteration of its robot system for assistive applications. The system was mounted on a wheelchair and could pick up a variety of fruits and vegetables on a plate. It was designed to identify how a person was sitting and take the food straight to their mouth. Since then, there have been quite a few iterations, mostly involving identifying a wide variety of food items on the plate. Now, the user with their assistive device can click on an image in the app, a grape for example, and the system can identify and pick that up.

Taylor Kessler Faulkner: Also, we’ve expanded the interface. Whatever accessibility systems people use to interact with their phones — mostly voice or mouth control navigation — they can use to control the app.

EKG: In this paper we just presented, we’ve gotten to the point where we can pick up nearly everything a fork can handle. So we can’t pick up soup, for example. But the robot can handle everything from mashed potatoes or noodles to a fruit salad to an actual vegetable salad, as well as pre-cut pizza or a sandwich or pieces of meat.

In previous work with the fruit salad, we looked at which trajectory the robot should take if it’s given an image of the food, but the set of trajectories we gave it was pretty limited. We were just changing the pitch of the fork. If you want to pick up a grape, for example, the fork’s tines need to go straight down, but for a banana they need to be at an angle, otherwise it will slide off. Then we worked on how much force we needed to apply for different foods.

In this new paper, we looked at how people pick up food, and used that data to generate a set of trajectories. We found a small number of motions that people actually use to eat and settled on 11 trajectories. So rather than just the simple up-down or coming in at an angle, it’s using scooping motions, or it’s wiggling inside of the food item to increase the strength of the contact. This small number still had the coverage to pick up a much greater array of foods.

We think the system is now at a point where it can be deployed for testing on people outside the research group. We can invite a user to the UW, and put the robot either on a wheelchair, if they have the mounting apparatus ready, or a tripod next to their wheelchair, and run through an entire meal.

For you as researchers, what are the vital challenges ahead to make this something people could use in their homes every day?

EKG: We’ve so far been talking about the problem of picking up the food, and there are more improvements that can be made here. Then there’s the whole other problem of getting the food to a person’s mouth, as well as how the person interfaces with the robot, and how much control the person has over this at least partially autonomous system.

TKF: Over the next couple of years, we’re hoping to personalize the robot to different people. Everyone eats a little bit differently. Amal did some really cool work on social dining that highlighted how people’s preferences are based on many factors, such as their social and physical situations. So we’re asking: How can we get input from the people who are eating? And how can the robot use that input to better adapt to the way each person wants to eat?

Amal Nanavati: There are several different dimensions that we might want to personalize. One is the user’s needs: How far the user can move their neck impacts how close the fork has to get to them. Some people have differential strength on different sides of their mouth, so the robot might need to feed them from a particular side of their mouth. There’s also an aspect of the physical environment. Users already have a bunch of assistive technologies, often mounted around their face if that’s the main part of their body that’s mobile. These technologies might be used to control their wheelchair, to interact with their phone, etc. Of course, we don’t want the robot interfering with any of those assistive technologies as it approaches their mouth.

There are also social considerations. For example, if I’m having a conversation with someone or at home watching TV, I don’t want the robot arm to come right in front of my face. Finally, there are personal preferences. For example, among users who can turn their head a little bit, some prefer to have the robot come from the front so they can keep an eye on the robot as it’s coming in. Others feel like that’s scary or distracting and prefer to have the bite come at them from the side.

A key research direction is understanding how we can create intuitive and transparent ways for the user to customize the robot to their own needs. We’re considering trade-offs between customization methods where the user is doing the customization, versus more robot-centered forms where, for example, the robot tries something and says, “Did you like it? Yes or no.” The goal is to understand how users feel about these different customization methods and which ones result in more customized trajectories.

What should the public understand about robot-assisted feeding, both in general and specifically the work your lab is doing?

EKG: It’s important to look not just at the technical challenges, but at the emotional scale of the problem. It’s not a small number of people who need help eating. There are various figures out there, but it’s over a million people in the U.S. Eating has to happen every single day. And to require someone else every single time you need to do that intimate and very necessary act can make people feel like a burden or self-conscious. So the whole community working towards assistive devices is really trying to help foster a sense of independence for people who have these kinds of physical mobility limitations.

AN: Even these seven-digit numbers don’t capture everyone. There are permanent disabilities, such as a spinal cord injury, but there are also temporary disabilities such as breaking your arm. All of us might face disability at some time as we age and we want to make sure that we have the tools necessary to ensure that we can all live dignified lives and independent lives. Also, unfortunately, even though technologies like this greatly improve people’s quality of life, it’s incredibly difficult to get them covered by U.S. insurance companies. I think more people knowing about the potential quality of life improvement will hopefully open up greater access.

Additional co-authors on the paper were Ramya Challa, who completed this research as an undergraduate student in the Allen School and is now at Oregon State University, and Bernie Zhu, a UW doctoral student in the Allen School. This research was partially funded by the National Science Foundation, the Office of Naval Research and Amazon.

For more information, contact Gordon at, Nanavati at and Faulkner at

Excerpted and adapted from the UW News story by Stefan Milne.

UW News: Can AI help boost accessibility? CREATE researchers tested it for themselves

November 2, 2023 | UW News

Generative artificial intelligence tools like ChatGPT, an AI-powered language tool, and Midjourney, an AI-powered image generator, can potentially assist people with various disabilities. They could summarize content, compose messages, or describe images. Yet they also regularly spout inaccuracies and fail at basic reasoningperpetuating ableist biases.

This year, seven CREATE researchers conducted a three-month autoethnographic study — drawing on their own experiences as people with and without disabilities — to test AI tools’ utility for accessibility. Though researchers found cases in which the tools were helpful, they also found significant problems with AI tools in most use cases, whether they were generating images, writing Slack messages, summarizing writing or trying to improve the accessibility of documents.

Four AI-generated images show different interpretations of a doll-sized “crocheted lavender husky wearing ski goggles,” including two pictured outdoors and one against a white background.

The team presented its findings Oct. 22 at the ASSETS 2023 conference in New York.

“When technology changes rapidly, there’s always a risk that disabled people get left behind,” said senior author Jennifer Mankoff, CREATE’s director and a professor in the Paul G. Allen School of Computer Science & Engineering. “I’m a really strong believer in the value of first-person accounts to help us understand things. Because our group had a large number of folks who could experience AI as disabled people and see what worked and what didn’t, we thought we had a unique opportunity to tell a story and learn about this.”

The group presented its research in seven vignettes, often amalgamating experiences into single accounts to preserve anonymity. For instance, in the first account, “Mia,” who has intermittent brain fog, deployed, which summarizes PDFs, to help with work. While the tool was occasionally accurate, it often gave “completely incorrect answers.” In one case, the tool was both inaccurate and ableist, changing a paper’s argument to sound like researchers should talk to caregivers instead of to chronically ill people. “Mia” was able to catch this, since the researcher knew the paper well, but Mankoff said such subtle errors are some of the “most insidious” problems with using AI, since they can easily go unnoticed.

Yet in the same vignette, “Mia” used chatbots to create and format references for a paper they were working on while experiencing brain fog. The AI models still made mistakes, but the technology proved useful in this case.

“When technology changes rapidly, there’s always a risk that disabled people get left behind.”

Jennifer Mankoff, CREATE Director, professor in the Allen School

Mankoff, who’s spoken publicly about having Lyme disease, contributed to this account. “Using AI for this task still required work, but it lessened the cognitive load. By switching from a ‘generation’ task to a ‘verification’ task, I was able to avoid some of the accessibility issues I was facing,” Mankoff said.

The results of the other tests researchers selected were equally mixed:

  • One author, who is autistic, found AI helped to write Slack messages at work without spending too much time troubling over the wording. Peers found the messages “robotic,” yet the tool still made the author feel more confident in these interactions.
  • Three authors tried using AI tools to increase the accessibility of content such as tables for a research paper or a slideshow for a class. The AI programs were able to state accessibility rules but couldn’t apply them consistently when creating content.
  • Image-generating AI tools helped an author with aphantasia (an inability to visualize) interpret imagery from books. Yet when they used the AI tool to create an illustration of “people with a variety of disabilities looking happy but not at a party,” the program could conjure only fraught images of people at a party that included ableist incongruities, such as a disembodied hand resting on a disembodied prosthetic leg.

“I was surprised at just how dramatically the results and outcomes varied, depending on the task,” said lead author Kate Glazko, a UW doctoral student in the Allen School. “”n some cases, such as creating a picture of people with disabilities looking happy, even with specific prompting — can you make it this way? — the results didn’t achieve what the authors wanted.”

The researchers note that more work is needed to develop solutions to problems the study revealed. One particularly complex problem involves developing new ways for people with disabilities to validate the products of AI tools, because in many cases when AI is used for accessibility, either the source document or the AI-generated result is inaccessible. This happened in the ableist summary ChatPDF gave “Mia” and when “Jay,” who is legally blind, used an AI tool to generate code for a data visualization. He could not verify the result himself, but a colleague said it “didn’t make any sense at all.”  The frequency of AI-caused errors, Mankoff said, “makes research into accessible validation especially important.”

Mankoff also plans to research ways to document the kinds of ableism and inaccessibility present in AI-generated content, as well as investigate problems in other areas, such as AI-written code.

“Whenever software engineering practices change, there is a risk that apps and websites become less accessible if good defaults are not in place,” Glazko said. “For example, if AI-generated code were accessible by default, this could help developers to learn about and improve the accessibility of their apps and websites.”

Co-authors on this paper are Momona Yamagami, who completed this research as a UW postdoctoral scholar in the Allen School and is now at Rice University; Aashaka DesaiKelly Avery Mack and Venkatesh Potluri, all UW doctoral students in the Allen School; and Xuhai Xu, who completed this work as a UW doctoral student in the Information School and is now at the Massachusetts Institute of Technology. This research was funded by Meta, Center for Research and Education on Accessible Technology and Experiences (CREATE), Google, an NIDILRR ARRT grant and the National Science Foundation.

For more information, contact Glazko at and Mankoff at

This article was adapted from the UW News article by Stefan Milne.

UW News: A11yBoard accessible presentation software

October 30, 2023 | UW News

A team led by CREATE researchers has created A11yBoard for Google Slides, a browser extension and phone or tablet app that allows blind users to navigate through complex slide layouts, objects, images, and text. Here, a user demonstrates the touchscreen interface. Team members Zhuohao (Jerry) Zhang, Jacob O. Wobbrock, and Gene S-H Kim presented the research at ASSETS 2023.

A user demonstrates creating a presentation slide with A11yBoard on a touchscreen tablet and computer screen.

Screen readers, which convert digital text to audio, can make computers more accessible to many disabled users — including those who are blind, low vision or dyslexic. Yet slideshow software, such as Microsoft PowerPoint and Google Slides, isn’t designed to make screen reader output coherent. Such programs typically rely on Z-order — which follows the way objects are layered on a slide — when a screen reader navigates through the contents. Since the Z-order doesn’t adequately convey how a slide is laid out in two-dimensional space, slideshow software can be inaccessible to people with disabilities.

Combining a desktop computer with a mobile device, A11yBoard lets users work with audio, touch, gesture, speech recognition and search to understand where different objects are located on a slide and move these objects around to create rich layouts. For instance, a user can touch a textbox on the screen, and the screen reader will describe its color and position. Then, using a voice command, the user can shrink that textbox and left-align it with the slide’s title.

“We want to empower people to create their own content, beyond a PowerPoint slide that’s just a title and a text box.”

Jacob O. Wobbrock, CREATE associate director and professor in the UW Information School

“For a long time and even now, accessibility has often been thought of as, ‘We’re doing a good job if we enable blind folks to use modern products.’ Absolutely, that’s a priority,” said senior author Jacob O. Wobbrock, a UW professor in the Information School. “But that is only half of our aim, because that’s only letting blind folks use what others create. We want to empower people to create their own content, beyond a PowerPoint slide that’s just a title and a text box.”

A11yBoard for Google Slides builds on a line of research in Wobbrock’s lab exploring how blind users interact with “artboards” — digital canvases on which users work with objects such as textboxes, shapes, images and diagrams. Slideshow software relies on a series of these artboards. When lead author Zhuohao (Jerry) Zhang, a UW doctoral student in the iSchool, joined Wobbrock’s lab, the two sought a solution to the accessibility flaws in creativity tools, like slideshow software. Drawing on earlier research from Wobbrock’s lab on the problems blind people have using artboards, Wobbrock and Zhang presented a prototype of A11yBoard in April. They then worked to create a solution that’s deployable through existing software, settling on a Google Slides extension.

For the current paper, the researchers worked with co-author Gene S-H Kim, an undergraduate at Stanford University, who is blind, to improve the interface. The team tested it with two other blind users, having them recreate slides. The testers both noted that A11yBoard greatly improved their ability to understand visual content and to create slides themselves without constant back-and-forth iterations with collaborators; they needed to involve a sighted assistant only at the end of the process.

The testers also highlighted spots for improvement: Remaining continuously aware of objects’ positions while trying to edit them still presented a challenge, and users were forced to do each action individually, such as aligning several visual groups from left to right, instead completing these repeated actions in batches. Because of how Google Slides functions, the app’s current version also does not allow users to undo or redo edits across different devices.

Ultimately, the researchers plan to release the app to the public. But first they plan to integrate a large language model, such as GPT, into the program.

“That will potentially help blind people author slides more efficiently, using natural language commands like, ‘Align these five boxes using their left edge,’” Zhang said. “Even as an accessibility researcher, I’m always amazed at how inaccessible these commonplace tools can be. So with A11yBoard we’ve set out to change that.”

This research was funded in part by the University of Washington’s Center for Research and Education on Accessible Technology and Experiences (UW CREATE). For more information, contact Zhang at and Wobbrock at

This article was adapted from the UW News article by Stefan Milne.

Forbes’ Mindset Matters highlights CREATE as the innovation industry needs

Jonathan Kaufman, in Forbes magazine’s Mindset Matters column, calls for innovation to make workplaces inclusive and accessible. In his May 31, 2020 column, An Object Lesson For Business, And Innovation In The Age Of A Pandemic, he highlights the partnership between CREATE and Microsoft as a prime example of how we can “redefine the very nature of work and develop the tools needed to create a culture of innovation.”

“It is at this moment that offers organizational leadership a means to reframe the status that disability plays in how we redefine the very nature of work and develop the tools needed to create a culture of innovation and cultivate a management strategy that embraces the needs of individual employees to be more productive and in turn give back to the collective goals of the company.”

Jonathan Kaufman, Forbes magazine

Designing for the fullness of human experience

Anat Caspi and Taskar Center featured on King 5’s New Day Northwest

A familiar face joined Margaret Larson on New Day NW this morning. Anat Caspi, Director of the Taskar Center and Director of Translation for the UW Accessibility Center, shared recent innovations from robotics to smart, sensing environments.

Technology design has taken this stance about designing for the “average” person. And in many cases that is a big design mismatch to the needs and preferences of people who are not the “average” …

Anat Caspi

View the full interview on the King 5 website.