The absence of tactile cues such as keys and buttons makes touchscreens difficult to navigate for people with visual impairments. Increasing tactile feedback and tangible interaction on touchscreens can improve their accessibility. However, prior solutions have either required hardware customization or provided limited functionality with static overlays. In addition, the investigation of tactile solutions for large touchscreens may not address the challenges on mobile devices. We therefore present Interactiles, a low-cost, portable, and unpowered system that enhances tactile interaction on Android touchscreen phones. Interactiles consists of 3D-printed hardware interfaces and software that maps interaction with that hardware to manipulation of a mobile app. The system is compatible with the built-in screen reader without requiring modification of existing mobile apps. We describe the design and implementation of Interactiles, and we evaluate its improvement in task performance and the user experience it enables with people who are blind or have low vision.

XiaoyiZhang, TracyTran, YuqianSun, IanCulhane, ShobhitJain, JamesFogarty, JenniferMankoff: Interactiles: 3D Printed Tactile Interfaces to Enhance Mobile Touchscreen Accessibility. ASSETS 2018: To Appear [PDF]

Figure 2. Floating windows created for number pad (left), scrollbar (right) and control button (right bottom). The windows can be transparent; we use colors for demonstration.
Figure 4. Average task completion times of all tasks in the study.


eDigs logoJennifer MankoffDimeji OnafuwaKirstin EarlyNidhi VyasVikram Kamath:
Understanding the Needs of Prospective Tenants. COMPASS 2018: 36:1-36:10

EDigs is a research project group in Carnegie Mellon University working on sustainability. Our research is focused on helping people find a perfect rental through machine learning and user research.

We sometimes study how our members use EDigs in order to learn how to build software support for successful social communities.

eDigs websiteScreenshot of showing a mobile app, facebook and twitter feeds, and information about it.

Nonvisual Interaction Techniques at the Keyboard Surface

Rushil Khurana,Duncan McIsaac, Elliot Lockerman,Jennifer Mankoff Nonvisual Interaction Techniques at the Keyboard Surface, CHI 2018, To Appear

A table (shown on screen). Columns are mapped to the number row of the keyboard and rows to the leftmost column of keys, and (1) By default the top left cell is selected. (2) The right hand presses the ‘2’ key, selecting the second column (3) The left hand selects the next row (4) The left hand selects the third row. In each case, the position of the cell and its content are read out aloud.

Web user interfaces today leverage many common GUI design patterns, including navigation bars and menus (hierarchical structure), tabular content presentation, and scrolling. These visual-spatial cues enhance the interaction experience of sighted users. However, the linear nature of screen translation tools currently available to blind users make it difficult to understand or navigate these structures. We introduce Spatial Region Interaction Techniques (SPRITEs) for nonvisual access: a novel method for navigating two-dimensional structures using the keyboard surface. SPRITEs 1) preserve spatial layout, 2) enable bimanual interaction, and 3) improve the end user experience. We used a series of design probes to explore different methods for keyboard surface interaction. Our evaluation of SPRITEs shows that three times as many participants were able to complete spatial tasks with SPRITEs than with their preferred current technology.

Talk [Slides]:

Sample Press:

KOMO Radio | New screen reader method helps blind, low-vision users browse complex web pages

Device helps blind, low-vision users better browse web pages. Allen Cone

Graph showing task completion rates for different kinds of tasks in our user study
A user is searching a table (shown on screen) for the word ‘Jill’. Columns are mapped to the number row of the keyboard and rows to the leftmost column of keys. (1) By default the top left cell is selected. (2) The right hand presses the ‘2’ key, selecting the second column (3) The left hand selects the next row (4) The left hand selects the third row. In each case, the number of occurrences of the search query in the respective column or row are read aloud. When the query is found, the position and content of the cell are read out aloud.

Expressing and Reusing Design Intent in 3D Models

Picture of 3D models and a printout

Megan K Hofmann, Gabriella Han, Scott E Hudson, Jennifer Mankoff. Greater Than the Sum of Its PARTs: Expressing and Reusing Design Intent in 3D Models CHI 2018, To Appear.

With the increasing popularity of consumer-grade 3D printing, many people are creating, and even more using, objects shared on sites such as Thingiverse. However, our formative study of 962 Thingiverse models shows a lack of re-use of models, perhaps due to the advanced skills needed for 3D modeling. An end user program perspective on 3D modeling is needed. Our framework (PARTs) empowers amateur modelers to graphically specify design intent through geometry. PARTs includes a GUI, scripting API and exemplar library of assertions which test design expectations and integrators which act on intent to create geometry. PARTs lets modelers integrate advanced, model specific functionality into designs, so that they can be re-used and extended, without programming. In two workshops, we show that PARTs helps to create 3D printable models, and modify existing models more easily than with a standard tool.

Picture of 3D models and a printout

Volunteer AT Fabricators

Perry-Hill, J., Shi, P., Mankoff, J. & Ashbrook, D. Understanding Volunteer AT Fabricators: Opportunities and Challenges in DIY-AT for Others in e-NABLE. Accepted to CHI 2017

We present the results of a study of e-NABLE, a distributed, collaborative volunteer effort to design and fabricate upper-limb assistive technology devices for limb-different users. Informed by interviews with 14 stakeholders in e-NABLE, including volunteers and clinicians, we discuss differences and synergies among each group with respect to motivations, skills, and perceptions of risks inherent in the project. We found that both groups are motivated to be involved in e-NABLE by the ability to use their skills to help others, and that their skill sets are complementary, but that their different perceptions of risk may result in uneven outcomes or missed expectations for end users. We offer four opportunities for design and technology to enhance the stakeholders’ abilities to work together.

Screen Shot 2017-03-14 at 1.09.13 PMA variety of 3D-printed upper-limb assistive technology devices designed and produced by volunteers in the e-NABLE community. Photos were taken by the fourth author in the e-NABLE lab on RIT’s campus.

Tactile Interfaces to Appliances

Anhong Guo, Jeeeun Kim, Xiang ‘Anthony’ Chen, Tom Yeh, Scott E. Hudson, Jennifer Mankoff, & Jeffrey P. Bigham, Facade: Auto-generating Tactile Interfaces to Appliances, In Proceedings of the 35th Annual ACM Conference on Human Factors in Computing Systems (CHI’17), Denver, CO (To appear)

Common appliances have shifted toward flat interface panels, making them inaccessible to blind people. Although blind people can label appliances with Braille stickers, doing so generally requires sighted assistance to identify the original functions and apply the labels. We introduce Facade – a crowdsourced fabrication pipeline to help blind people independently make physical interfaces accessible by adding a 3D printed augmentation of tactile buttons overlaying the original panel. Facade users capture a photo of the appliance with a readily available fiducial marker (a dollar bill) for recovering size information. This image is sent to multiple crowd workers, who work in parallel to quickly label and describe elements of the interface. Facade then generates a 3D model for a layer of tactile and pressable buttons that fits over the original controls. Finally, a home 3D printer or commercial service fabricates the layer, which is then aligned and attached to the interface by the blind person. We demonstrate the viability of Facade in a study with 11 blind participants.


Aversion to Typing Errors

Quantifying Aversion to Costly Typing Errors in Expert Mobile Text Entry

Text entry is an increasingly important activity for mobile device users. As a result, increasing text entry speed of expert typists is an important design goal for physical and soft keyboards. Mathematical models that predict text entry speed can help with keyboard design and optimization. Making typing errors when entering text is inevitable. However, current models do not consider how typists themselves reduce the risk of making typing errors (and lower error frequency) by typing more slowly. We demonstrate that users respond to costly typing errors by reducing their typing speed to minimize typing errors. We present a model that estimates the effects of risk aversion to errors on typing speed. We estimate the magnitude of this speed change, and show that disregarding the adjustments to typing speed that expert typists use to reduce typing errors leads to overly optimistic estimates of maximum errorless expert typing speeds.

promoNikola Banovic, Varun Rao, Abinaya Saravanan, Anind K. Dey, and Jennifer Mankoff. 2017. Quantifying Aversion to Costly Typing Errors in Expert Mobile Text Entry. (To appear) In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI ’17). ACM, New York, NY, USA.

Modeling & Generating Routines

Leveraging Human Routine Models to Detect and Generate Human Behaviors

An ability to detect behaviors that negatively impact people’s wellbeing and show people how they can correct those behaviors could enable technology that improves people’s lives. Existing supervised machine learning approaches to detect and generate such behaviors require lengthy and expensive data labeling by domain experts. In this work, we focus on the domain of routine behaviors, where we model routines as a series of frequent actions that people perform in specific situations. We present an approach that bypasses labeling each behavior instance that a person exhibits. Instead, we weakly label instances using people’s demonstrated routine. We classify and generate new instances based on the probability that they belong to the routine model. We illustrate our approach on an example system that helps drivers become aware of and understand their aggressive driving behaviors. Our work enables technology that can trigger interventions and help people reflect on their behaviors when those behaviors are likely to negatively impact them.

drivingsimulator_no_labelNikola Banovic, Anqi Wang, Yanfeng Jin, Christie Chang, Julian Ramos, Anind K. Dey, and Jennifer Mankoff. 2017. Leveraging Human Routine Models to Detect and Generate Human Behaviors. (To appear) In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI ’17). ACM, New York, NY, USA.

3D Printing with Embedded Textiles


Stretching the Bounds of 3D Printing with Embedded Textiles

Textiles are an old and well developed technology that have many desirable characteristics. They can be easily folded, twisted, deformed, or cut; some can be stretched; many are soft. Textiles can maintain their shape when placed under tension and can even be engineered with variable stretching ability.

When combined, textiles and 3D printing open up new opportunities for rapidly creating rigid objects with embedded flexibility as well as soft materials imbued with additional functionality. We introduce a suite of techniques for integrating the two and demonstrate how the malleability, stretchability and aesthetic qualities of textiles can enhance rigid printed objects, and how textiles can be augmented with functional properties enabled by 3D printing.

Click images below to see more detail:


Rivera, M.L., Moukperian, M., Ashbrook, D., Mankoff, J., Hudson, S.E. 2017. Stretching the Bounds of 3D Printing with Embedded Textiles. To appear in to the annual ACM conference on Human Factors in Computing Systems. CHI ‘17. [Paper]


Watch-ya-doin is an innovative experienced based sampling framework for longitudinal data collection and analysis. Our system consists of a smartwatch and an android device working unobtrusively to track data. Our goal is to train on and recognize a specific activity over time. We use a simple wrist-worn accelerometer to predict eating behavior and other activities. These are inexpensive to deploy and easy to maintain, since battery life is a whole week using our application.
     Our primary application area is AT abandonment. About 700,000 people in the United States have an upper limb amputation, and about 6.8 million face fine motor and/or arm dexterity limitations[1]. Assistive technology (AT), ranging from myo-electric prosthetics to passive prosthetics to a variety of orthotics can help in the rehabilitation and improve independence and ability to perform everyday tasks. Yet AT is not used to its full potential, with abandonment rates ranging from 23% to 90% for prosthetics users, and high abandonment of orthotics as well. Given the cost of these devices, this is an enormous waste of a significant financial investment in developing, fabricating, and providing the device, as well as potentially leading to frustration, insufficient rehabilitation, increased risk of limb-loss associated co-morbidities, and overall a reduced quality of life for the recipient.
       To address this, we need objective and accurate information about AT use. Current data is limited primarily to questionnaires, or skill testing during office visits. Apart from being limited by subjectivity and evaluator bias, survey tools are also not appropriate to estimate quality of use. A patient may – more or less accurately – report his or her AT use for a certain number of hours a day, but this does not indicate which tasks it was used for, which makes it difficult to evaluate how appropriate or helpful they were. In addition, neither reported use time nor skill testing can be sufficiently used to predict abandonment once AT is deployed.

      Our next steps include generalizing our approach to AT (such as upper limb prosthetics), and expanding it to include a wider variety of tracked activities. In addition, we will develop a longitudinal data set that includes examples of abandonment. This will allow the creation algorithms that can characterize the type and quality of use over the lifecycle of AT and predict abandonment.

[1] U.S. Census 2001