Navigating new indoor spaces and interacting with the environment presents many challenges for people who are blind or have low vision (BLV). To address these challenges, we prototyped a smartphone-based conversational assistant that helps BLV people navigate and interact with their environment. The prototype utilizes a cognitive architecture to integrate three different technologies: (i) augmented-reality spatial anchors for high-precision localization and access to static information about the environment; (ii) real-time object/people detection for information about the environment and obstacle avoidance; and (iii) a conversational agent}that uses large language models (LLMs) for information extraction, conversational interaction, and turn-by-turn navigation. We assess the impact of different technologies on human performance by measuring user task time and errors. We found that conversational interaction holistically integrates the different technologies to deliver a better user experience while significantly reducing task completion time.

On-demand, last-mile delivery -- the transportation of goods from a local distribution center to the customer's door within a specified time window -- is used by people with disabilities (PwDs) for a variety of reasons. While delivery robots have potential in this space, they often widen disparities in access for PwDs. Inspired by the concept of pluriversality, which embraces the diversity of worldviews, we facilitated participatory design workshops with PwDs to co-design accessible and equitable delivery robots. Our findings support the importance of delivery robots with varied form factors that are robust and customizable to support diverse PwDs and their respective needs and preferences. We also provide broader considerations for automation in delivery ecosystems.

Guide robots have the potential to improve the experience of independent travel for people who are blind or have low vision. While many technical challenges for robot guides have been studied, open questions about robot behaviors and features remain. We conducted a two-phase user study with 16 blind and low-vision participants. First, we tested whether robot path planners that account for specific orientation cues affect users’ comfort and spatial awareness. Then, we elicited user preferences for guide robots through semi-structured interviews and scenario-based design sessions. We provide insights regarding desired robot behaviors and features that impact robot usability, human agency vs. autonomy, and perceived safety.

Exercise supports healthy aging, but motivation often declines with age, increasing demand on therapists and coaches. We present a conversational robotic exercise coach that promotes engagement and assesses motivation through dialogue. In a WoZ study with ten adults aged 59 and above, participants showed varied interaction styles; even those with low motivation rated sessions positively, suggesting such agents can enhance exercise enjoyment. We identify three design needs for autonomous coaches: rephrasing for clarity, conversation beyond exercise, and adaptable speech delivery.

Different people respond to feedback and guidance in different ways, and their preferences may change based on their mood, tiredness, etc. We present a robot exercise coach that provides verbal and nonverbal feedback in two different styles: firm and encouraging. We collect a dataset of people experiencing both feedback styles and show that the style that someone performs best with may not be the one they have the best subjective experience with or be the one that they state they prefer. To account for this, we present a contextual bandit approach that enables the robot coach to learn the best style to use over time to improve the human's performance, and show that this approach performs quite well in expectation on the real human data.

Interpersonal synchrony (IS), the behavioral and physiological coordination across time and space, plays a crucial role in social interactions by fostering empathy, closeness, and prosocial behaviors. However, there is a need for more examination of human-robot interaction (HRI) research focused on interactions where the temporal alignment of body movements and the spatial coordination of the content produced by those movements is vital to the quality of the interaction, such as in joint visual art-making. In this work, we investigated the impact of IS on human raters’ perceptions of a human-robot (HR) dyad engaged in a joint painting activity. We conducted two online studies (n = 70, total) in which participants watched 4 videos (1 repeated synchronous video and 3 asynchronous videos). We varied the degree of IS displayed by an HR dyad on two axes: (a) temporal alignment (e.g., speed of producing brush strokes) and (b) spatial similarity (i.e., similarity in the visual content produced). Our results indicate that some temporal and spatial dimensions of IS displayed by an HR dyad during joint painting have significant positive impacts on external observers’ perceptions of the robot, including prosocial tendencies (i.e., empathy, synchrony, and closeness) and acceptance. These findings are significant for emergent research on collaborative robots.

As the population of older adults increases, there is a growing need for support for them to age in place. This is exacerbated by the growing number of individuals struggling with cognitive decline and shrinking number of youth who provide care for them. Artificially intelligent agents could provide cognitive support to older adults experiencing memory problems, and they could help informal caregivers with coordination tasks. To better understand this possible future, we conducted a speed dating with storyboards study to reveal invisible social boundaries that might keep older adults and their caregivers from accepting and using agents. We found that healthy older adults worry that accepting agents into their homes might increase their chances of developing dementia. At the same time, they want immediate access to agents that know them well if they should experience cognitive decline. Older adults in the early stages of cognitive decline expressed a desire for agents that can ease the burden they saw themselves becoming for their caregivers. They also speculated that an agent who really knew them well might be an effective advocate for their needs when they were less able to advocate for themselves. That is, the agent may need to transition from being unremarkable to remarkable. Based on these findings, we present design opportunities and considerations for agents and articulate directions of future research.

The population of older adults experiencing cognitive decline is growing faster than the number of workers who can care for them. Artificially intelligent (AI) agents could assist these older adults, keeping them in their homes longer. For this to happen, older adults must be willing to adopt and rely on agents. Would they trust an agent that might need to report their decline to others? We conducted a speed dating study exploring the impact of agent affiliation (i.e., who the agent should work for). Our healthy and declining participants reacted positively to the idea of agents supporting them. They particularly recognized how the agent would reduce the burden placed on their family caregivers. They viewed affiliation to be dynamic, shifting from the declining older adult and orienting more to their caregivers over the course of cognitive decline. They envisioned the agent modifying its decision-making process to be like their caregivers’.

A long-standing challenge in accessible computing has been to get developers to produce the accessible UI code necessary for assistive technologies to work properly. AI coding assistants (e.g., Github Copilot) potentially offer a new opportunity to make UI code more accessible automatically, but it is unclear how their use impacts code accessibility and what developers need to know in order to use them effectively. In this paper, we report on a study where developers untrained in accessibility were tasked with building web UI components with and without an AI coding assistant. Our findings suggest that while current AI coding assistants show potential for creating more accessible UIs, they currently require accessibility awareness and expertise, limiting their expected impact.

Social navigation and pedestrian behavior research has shifted towards machine learning-based methods and converged on the topic of modeling inter-pedestrian interactions and pedestrian-robot interactions. For this, large-scale datasets that contain rich information are needed. We describe a portable data collection system, coupled with a semi-autonomous labeling pipeline. As part of the pipeline, we designed a label correction web application that facilitates human verification of automated pedestrian tracking outcomes. Our system enables large-scale data collection in diverse environments and fast trajectory label production. Compared with existing pedestrian data collection methods, our system contains three components: a combination of top-down and ego-centric views, natural human behavior in the presence of a socially appropriate "robot", and human-verified labels grounded in the metric space. To the best of our knowledge, no prior data collection system has a combination of all three components. We further introduce our ever-expanding dataset from the ongoing data collection effort – the TBD Pedestrian Dataset and show that our collected data is larger in scale, contains richer information when compared to prior datasets with human-verified labels, and supports new research opportunities.

In this work, we aim to improve transparency and efficacy in human-robot collaboration by developing machine teaching algorithms suitable for groups with varied learning capabilities. While previous approaches focused on tailored approaches for teaching individuals, our method teaches teams with various compositions of diverse learners using team belief representations. We investigate various group teaching strategies, such as focusing on individual beliefs or the group’s collective beliefs, and assess their impact on learning robot policies for different team compositions. Our findings reveal that team belief strategies produce less variation in learning duration and better accommodate diverse teams compared to individual belief strategies, suggesting their suitability in mixed proficiency settings with limited resources. In contrast, individual belief strategies provide a more uniform knowledge level, particularly effective for homogeneously inexperienced groups. Our study indicates that the effectiveness of the teaching strategy is significantly influenced by team composition and learner proficiency, highlighting the importance of real-time assessment of learner proficiency and adapting teaching approaches based on learner proficiency for optimal teaching outcomes.

Traditionally, potential fields and vector fields have been extensively used for motion planning, especially in finding paths to a goal position while avoiding obstacles along the way. However, such methods have only been applied to the problem of finding the shortest path to only one goal position. In human-centered environments with multiple goals, the shortest path (e.g., most predictable) is often not the most intent-expressive path (e.g., most legible) to one of the goals. We devised a method for robot planning and navigation in human-centered environments that uses potential fields to plan intent-expressive motion to a specific goal among many, while utilizing adaptive vector fields to avoid obstacles without sacrificing the legibility property of the motion. We found that our method can produce motions that are of comparable legibility and shorter path length compared to a legible motion planner baseline, as well as more legible paths compared to a traditional potential field method. Our method was evaluated in several scenarios where legibility is useful, namely maps with and without obstacles and goal switching.

This paper investigates how conversational agents that are embedded in smart environments should present themselves socially. In an online study, we simulate a future space habitat in which "astronauts" (participants) interact with one or more agents to complete several tasks related to science, maintenance, and inventory. We examine effects of agent affiliation (affiliation with a user, affiliation with a domain, or affiliation with all users and all domains) and narrative perspective (first-vs. third-person references to parts of the environment) on mental models of the smart environment as one or multiple entities, trust, performance, and social variables. Our findings suggest that in this type of setting, interacting with a single agent may increase mental demand, and that agents that speak about embodied interaction in third person are perceived as more trustworthy and competent than agents that speak in first person.

With more robots being deployed in the world, users will likely interact with multiple robots sequentially when receiving services. In this paper, we describe an exploratory field study in which unsuspecting participants experienced a "person transfer" – a scenario in which they first interacted with one stationary robot before another mobile robot joined to complete the interaction. In our 7-hour study spanning 4 days, we recorded 18 instances of person transfers with 40+ individuals. We also interviewed 11 participants after the interaction to further understand their experience. We used the recorded video and interview data to extract interesting insights about in-the-field sequential human-robot interaction, such as mobile robot handovers, trust in person transfer, and the importance of the robots’ positions. Our findings expose pitfalls and present important factors to consider when designing sequential human-robot interaction.

Many academic subjects are inaccessible for students who are blind or have low vision (BLV) due to the prevalence of visual aids to represent concepts. Interactive devices offer promise as creative tools for teachers of the visually impaired (TVIs) as they can support real-time iteration of adapted learning materials, display changing information, and provide embodied learning experiences for BLV students. We conducted semi-structured interviews with 5 educators (all have TVI experience) and identified their considerations when creating adaptations, attitudes towards technology, and perspectives on existing barriers to access. Our findings reveal and reaffirm unresolved challenges in the adaptation process as well as offer insights into key factors that must be considered when selecting the type of adaptation. From these findings, we formulate design recommendations for interactive tools that support TVIs in creating effective adaptations for BLV students.

Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions based on pairwise user preferences. SortCMA efficiently and robustly leverages user input to find parameter sets without directly modeling a reward. We apply this method to tuning a commercial depth sensor without ground truth, and to robot social navigation, which involves highly complex preferences over robot behavior. We show that our method succeeds in optimizing for the user's goals and perform a user study to evaluate social navigation results.

Virtual assistants, vacuum robots, security systems, and other smart home technologies are rapidly advancing, evolving, and gaining popularity. This raises questions of how people envision future interactions with smart home systems and how they imagine the future roles of such technologies in society. We deployed an online study that collected fictional short stories from 60 participants about smart home interactions. We identified themes regarding the roles of smart home technologies, social interactions with AI, and concerns about data privacy in the context of the home. We describe our method, discuss insights from the stories that explicitly reflect possible futures and implicitly reflect the present, and make design recommendations based on our findings.

Robot navigation in crowded public spaces is a complex task that requires addressing a variety of engineering and human factors challenges. These challenges have motivated a great amount of research resulting in important developments for the fields of robotics and human-robot interaction over the past three decades. Despite the significant progress and the massive recent interest, we observe a number of significant remaining challenges that prohibit the seamless deployment of autonomous robots in crowded environments. In this survey article, we organize existing challenges into a set of categories related to broader open problems in robot planning, behavior design, and evaluation methodologies. Within these categories, we review past work and offer directions for future research. Our work builds upon and extends earlier survey efforts by (a) taking a critical perspective and diagnosing fundamental limitations of adopted practices in the field and (b) offering constructive feedback and ideas that could inspire research in the field over the coming decade.

Design produces valuable knowledge by offering new perspectives that reframe problematic situations. Research through Design (RtD) contributes new frames along with design work demonstrating a frame's value. Interestingly, RtD papers rarely describe how reframing happens. This gap in documentation unintentionally implies a romantic account of design, it implies that the first step of an RtD project is to have a brilliant idea. This is especially problematic in cases where the reframing causes a pivot that leads to a new research program. To help address this gap, we describe a case where through a series of three design experiments we experienced a research pivot. We describe how our work to improve web-table navigation for screen-reader users broke our frame. The break led to a new research program focused on constructing a conversational internet. This paper offers our case along with reflection on reporting design work that drives reframing.

Designers of smart-home systems must make decisions about the perceived identities and interconnectedness of their various devices. To inform these decisions, we performed an online study to examine whether people perceive multiple devices in a smart home as different interfaces for the same system, devices that talk to each other, or independent devices. We manipulated the types of devices in the system (hetero-geneous!homogeneous), how the devices relayed commands to each other (implicit/explicit), and the task requested. Participants were flexible in how they interpreted the devices, presenting an opportunity for designers to select a suitable model.

In this paper, we explored how a mobile robot should join an existing multimodal interaction between a person and a stationary robot. We developed three different strategies (Circular, Line, and Improper) and an interactive system to put the strategies in practice. Circular (all interactants stand in a circle) and Line (two robots stand in a line facing a person) were based on existing human group spatial arrangements, whereas Improper (second robot stands far from the person and stationary robot) explored how a bad arrangement might change a user’s position and perception. We also investigated how scenarios with different tasks influenced human positions at different stages of the interaction. We conducted a 3x4 mixed design, in-person user study and found that participants in the Improper condition repositioned themselves to decrease the distance differences between interactants. We also conducted an exploratory analysis on the spatial data to better understand how user actions and social cues, such as gaze and vocalizations, changed spatial behaviors.

With the infusion of computation into workplaces and homes, various service settings, and everyday objects, scholars in human–computer interaction (HCI) and related domains have begun to consider the research and design implications not only of smart “things,” but ofsmart environments. Much of the work on smart environments to date has focused on smart homes; related work in HCI explores user values for smart homes, means of interacting with computation in smart homes (e.g., interfaces and agents), how to balance the needs of multiple stakeholders, and how to preserve user trust and autonomy. However, the smart environments of the future will not always fit the smart home mold of a coalescence of products that exist to automate and ease everyday tasks for the end users. They will be both user-focused and goal-focused, public and private, large and small, and ephemeral and long-lasting. It will benefit the field to look atsmart environmentsas a unit of analysis—including what these different types of environments have in common and what they do not—from a systemic, user experience design-oriented view. In this survey article, we review prior research on smart environments and various related bodies of literature. Informed by our literature review, we articulate fivelensesthat distinguish different types of smart environments from one another. We then propose research directions for future work on this topic.

The human-robot interaction community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures to evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult to compare the performance of such methods across the literature. To bridge this gap, we introduce SocNavBench , a simulation framework for evaluating social navigation algorithms. SocNavBench comprises a simulator with photo-realistic capabilities and curated social navigation scenarios grounded in real-world pedestrian data. We also provide an implementation of a suite of metrics to quantify the performance of navigation algorithms on these scenarios. Altogether, SocNavBench provides a test framework for evaluating disparate social navigation methods in a consistent and interpretable manner. To illustrate its use, we demonstrate testing three existing social navigation methods and a baseline method on SocNavBench , showing how the suite of metrics helps infer their performance trade-offs. Our code is open-source, allowing the addition of new scenarios and metrics by the community to help evolve SocNavBench to reflect advancements in our understanding of social navigation.

As development of robots with the ability to self-assess their proficiency for accomplishing tasks continues to grow, metrics are needed to evaluate the characteristics and performance of these robot systems and their interactions with humans. This proficiency-based human-robot interaction (HRI) use case can occur before, during, or after the performance of a task. This article presents a set of metrics for this use case, driven by a four-stage cyclical interaction flow: (1) robot self-assessment of proficiency (RSA), (2) robot communication of proficiency to the human (RCP), (3) human understanding of proficiency (HUP), and (4) robot perception of the human’s intentions, values, and assessments (RPH). This effort leverages work from related fields including explainability, transparency, and introspection, by repurposing metrics under the context of proficiency self-assessment. Considerations for temporal level (a priori, in situ, and post hoc) on the metrics are reviewed, as are the connections between metrics within or across stages in the proficiency-based interaction flow. This article provides a common framework and language for metrics to enhance the development and measurement of HRI in the field of proficiency self-assessment.

Social agents and robots are moving into front-line positions in brick and mortar services, taking on roles where they directly interact with customers. These agents could potentially recognize customers to personalize service. Will customers like this, or might they feel monitored and profiled? Robots could also re-embody (move their “personality” between one body and another) in order to take on multiple roles that are typically performed by different people. Will this make customers feel more taken care of, or will it raise concerns about the robot’s competence and expertise? Our work investigates when robots should and should not recognize customers and re-embody. Our online study used storyboards to present possible future interactions between robots and customers across several different service contexts. Our findings suggest that people generally accept robots identifying customers and taking on vastly different roles. However, in some contexts, these robot behaviors seem creepy and untrustworthy.

Mobile robots have been shown to be helpful in guiding users in complex indoor spaces. While these robots can assist all types of users, current implementations often rely on users visually rendezvousing with the robot, which may be a challenge for people with visual impairments. This paper describes a proof of concept for a robotic system that addresses this kind of short-range rendezvous for users with visual impairments. We propose to use a lattice graph-based Anytime Repairing A* (ARA*) planner as a global planner to discourage the robot from turning in place at its goal position, making its path more human-like and safer. We also interviewed an Orientation & Mobility (O&M) Specialist for their thoughts on our planner. They observed that our planner produces less obtrusive trajectories to the user than the ROS default global planner and recommended that our system should allow the robot to approach the person from the side as opposed to the front as it currently does. In the future, we plan to test our system with users in-person to better validate our assumptions and find additional pain points.

There is considerable effort within the HCI community to explore, document, and advocate for the lived experiences of persons with disabilities (PWDs). However, PWDs from the Global South, particularly Africa, are underrepresented in this scholarship. We contribute to closing this gap by investigating the unmet transit needs and characterization of technology within the disability community in Kampala, Uganda. We investigated transportation due to the increase in ride-share solutions created by widespread mobile computing and the resulting disruption of transportation worldwide. We hosted co-design sessions with disability advocates and adapted the stakeholder tokens method from the value-sensitive design framework to map the stakeholder ecosystem. Our key insight is the identification of a new group of non-traditional core stakeholders who highlight the values of inclusion, mobility, and safety within the ecosystem. Finally, we discuss how our findings engage with concepts of disability justice and perceptions of power.

How are people using current smart home technologies, and how do they conceptualize future ones that are more interconnected and more capable than those available today? We deployed an online survey study to 150 participants to investigate use of and opinions about smart speakers, home robots, virtual assistants, and other smart home devices. We also gauged how impressions of connected smart home devices are shaped by the way the devices interact with one another. Through a mixed-methods qualitative and quantitative approach, we found that people mostly use single devices for single functions, and have simple and brief interactions with virtual assistants. However, they imagine their future devices to have more control over the physical environment (i.e., interact with each other) and envision them interacting with people in more socially complex ways. These findings motivate design considerations and research directions for connected smart home technologies.

We explored different ways in which a multi-robot system might recover after one robot experiences a failure. We compared four recovery conditions: Update (a robot fixes its error and continues the task), Re-embody (a robot transfers its intelligence to a different body), Call (the failed robot summons a second robot to take its place), and Sense (a second robot detects the failure and proactively takes the place of the first robot). We found that trust in the system and perceived competence of the system were higher when a single robot recovered from a failure on its own (by updating or re-embodying) than when a second robot took over the task. We also found evidence that two robots that used the same socially interactive intelligence were perceived more similarly than two robots with different intelligences. Finally, our study revealed a relationship between how people perceive the agency of a robot and how they perceive the performance of the system.

In the not-so-distant future, people in service experiences are likely to interact with more than a single intelligent system, often sequentially, including different robots and devices. However, there has been sparse work exploring the characteristics of transferring people from one intelligent system to another. This paper aims to create a context-independent taxonomy to differentiate and categorize the transfer of users across robots, devices, and human staff in service interactions. We conducted two sets of design workshops where participants generated scenarios of human-multi-robot interactions and existing person transfers. Using the outcomes of both workshops, we analyzed scenarios and constructed a taxonomy for person transfers with 4-dimensions: Rationale, Type, Design, and Information Shared. We showcase different ways to utilize the taxonomy, and, through it, we discuss the trade-offs and design considerations in the implementation of person transfers.

Human-in-the-loop Machine Learning (HIL-ML) is a widely adopted paradigm for instilling human knowledge in autonomous agents. Many design choices influence the efficiency and effectiveness of such interactive learning processes, particularly the interaction type through which the human teacher may provide feedback. While different interaction types (demonstrations, preferences, etc.) have been proposed and evaluated in the HIL-ML literature, there has been little discussion of how these compare or how they should be selected to best address a particular learning problem. In this survey, we propose an organizing principle for HIL-ML that provides a way to analyze the effects of interaction types on human performance and training data. We also identify open problems in understanding the effects of interaction types.

Recently, transformer language models have been applied to build both task-and non-taskoriented dialogue systems.Although transformers perform well on most of the NLP tasks, they perform poorly on context retrieval and symbolic reasoning.Our work aims to address this limitation by embedding the model in an operational loop that blends both natural language generation and symbolic injection.We evaluated our system on the multi-domain DSTC8 data set and reported joint goal accuracy of 75.8% (ranked among the first half positions), intent accuracy of 97.4% (which is higher than the reported literature), and a 15% improvement for success rate compared to a baseline with no symbolic injection.These promising results suggest that transformer language models can not only generate proper system responses but also symbolic representations that can further be used to enhance the overall quality of the dialogue management as well as serving as scaffolding for complex conversational reasoning.

Artificial Intelligence (AI) plays an increasingly important role in improving HCI and user experience. Yet many challenges persist in designing and innovating valuable human-AI interactions. For example, AI systems can make unpredictable errors, and these errors damage UX and even lead to undesired societal impact. However, HCI routinely grapples with complex technologies and mitigates their unintended consequences. What makes AI different? What makes human-AI interaction appear particularly difficult to design? This paper investigates these questions. We synthesize prior research, our own design and research experience, and our observations when teaching human-AI interaction. We identify two sources of AI's distinctive design challenges: 1) uncertainty surrounding AI's capabilities, 2) AI's output complexity, spanning from simple to adaptive complex. We identify four levels of AI systems. On each level, designers encounter a different subset of the design challenges. We demonstrate how these findings reveal new insights for designers, researchers, and design tool makers in productively addressing the challenges of human-AI interaction going forward.

Smart technologies have recently come under scrutiny for automating inequality. Given the current push towards developing and implementing smart cities policies that affect transportation systems in places like Kampala and Kigali, it is important to examine how the different modes of transportation meet the needs of diverse passengers and identify opportunities for technology to address any inequities. Prior studies have focused on the impact of informal public transportation on government policy and examined drivers' perspectives, but they largely overlooked the experiences of passengers and other industry stakeholders. In this study, we conducted interviews and surveys with public transportation riders with different disabilities as well as other stakeholders, including transport and financial technology creators. Our findings illuminate inequities in the transportation system surrounding discrimination and harassment, influence of ability on preferred transportation modes despite inaccessible interfaces, and influence of perceived social hierarchical structures on innovation. We present insights into how passengers appropriate technology to overcome challenges, and we uncover opportunities for technology to fill additional gaps. Lastly, we discuss how these findings support emergent frameworks such as aspiration-based design, and we present potential envisioned futures of technology for informal public transportation.

People take to social media to share their thoughts, joys, and sorrows. A recent popular trend has been to support and mourn people and pets that have died as well as other objects that have suffered catastrophic damage. As several popular robots have been discontinued, including the Opportunity Rover, Jibo, and Kuri, we are interested in how language used to mourn these robots compares to that to mourn people, animals, and other objects. We performed a study in which we asked participants to categorize deidentified Twitter reactions as referencing the death of a person, an animal, a robot, or another object. Most reactions were labeled as being about humans, which suggests that people use similar language to describe feelings for animate and inanimate entities. We used a natural language toolkit to analyze language from a larger set of tweets. A majority of tweets about Opportunity included second-person ("you") and gendered third-person pronouns (she/he versus it), but terms like "R.I.P" were reserved almost exclusively for humans and animals. Our findings suggest that people verbally mourn robots similarly to living things, but reserve some language for people.

Service robots often perform their main functions in public settings, interacting with more than one person at a time. How these robots should handle the affairs of individual users while also behaving appropriately when others are present is an open question. One option is to design for flexible agent embodiment: letting agents take control of different robots as people move between contexts. Through structured User Enactments, we explored how agents embodied within a single robot might interact with multiple people. Participants interacted with a robot embodied by a singular service agent, agents that re-embody in different robots and devices, and agents that co-embody within the same robot. Findings reveal key insights about the promise of re-embodiment and co-embodiment as design paradigms as well as what people value during interactions with service robots that use personalization.

Robots operating in human environments must be careful, when executing their manipulation skills, not to disturb nearby objects. This requires robots to reason about the effect of their manipulation choices by accounting for the support relationships among objects in the scene. Humans do this in part by visually assessing their surroundings and using physics intuition for how likely it is that a particular object can be safely manipulated (i.e., cause no disruption in the rest of the scene). Existing work has shown that deep convolutional neural networks can learn intuitive physics over images generated in simulation and determine the stability of a scene in the real world. In this paper, we extend these physics intuition models to the task of assessing safe object extraction by conditioning the visual images on specific objects in the scene. Our results, in both simulation and real-world settings, show that with our proposed method, physics intuition models can be used to inform a robot of which objects can be safely extracted and from which direction to extract them.

Personalization of user experience has a long history of success in the HCI community. More recently the community has focused on adaptive user interfaces, supported by machine learning, that reduce interaction efforts and improves user experience by collapsing transactions and pre-filtering results. However, generally, these more recent results have only been demonstrated in the laboratory environment. In this paper, we share the case of a deployed mobile transit app that adapts based on users’ previous usage. We examine the impact of adaptation, both good and bad, and user abandonment rates. We conducted an 18-month assessment where 2,616 participants (with and without vision impairments) were recruited and participated in an A/B study. Finally, we draw some insights on some unusual effects that appear over the long term.

Interactions with multiple conversational agents and social robots are becoming increasingly common. This raises new design challenges: Should agents and robots be modeled after humans, presenting their entity (i.e., social presence) as bound to a single body, or should they take advantage of non-human capabilities, such as moving their social presence from body to body across service touchpoints and contexts? We conducted a User Enactments study in which participants interacted with agents that had one social presence per body, that could re-embody (move their social presence from body to body), and that could co-embody (move their social presence into a body that already contains another). Reactions showed that participants felt comfortable with re-embodying agents, who created more seamless and efficient experiences. Yet situations that required expertise or concentration raised concerns about non-human behaviors. We report on our insights regarding collaboration and coordination with several agents in multi-step interactions.

The inevitable increase in real-world robot applications will, consequently, lead to more opportunities for robots to have observable failures. Although previous work has explored interaction during robot failure and discussed hypothetical danger, little is known about human reactions to actual robot behaviors involving property damage or bodily harm. An additional, largely unexplored complication is the possible influence of social characteristics in robot design. In this work, we sought to explore these issues through an in-person study with a real robot capable of inducing perceived property damage and personal harm. Participants observed a robot packing groceries and had opportunities to react to and assist the robot in multiple failure cases. Prior exposure to damage and threat failures decreased assistance rates from approximately 81% to 60%, with variations due to robot facial expressions and other factors. Qualitative data was then analyzed to identify interaction design needs and opportunities for failing robots.

We describe an exploration of how kiosk-type stationary robots might provide navigation instructions for blind people. Inspired by a technique used by Orientation & Mobility experts in which a route is traced out on a person's palm, we developed five methods that supplement verbal instructions with physical movements. We explored the usability, strengths, and limitations of each of our methods in two exploratory studies with blind participants. One method, in which the robot used its entire arm to create path gestures while participants held its gripper, was preferred by 5 out of 8 blind participants and performed comparably on a recall task as a verbal-only instruction method. A closer approximation of the original palm method failed. We analyzed interview data to understand the reasons behind the failures and successes. We discuss the lessons learned from our studies about instruction methods, how robots in public settings can be useful for blind people, and the challenges of deploying such systems in public.

Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed in practice. Empirical research diagnosed poor contextual fit as the cause. This paper describes the design and field evaluation of a radically new form of DST. It automatically generates slides for clinicians' decision meetings with subtly embedded machine prognostics. This design took inspiration from the notion of Unremarkable Computing, that by augmenting the users' routines technology/AI can have significant importance for the users yet remain unobtrusive. Our field evaluation suggests clinicians are more likely to encounter and embrace such a DST. Drawing on their responses, we discuss the importance and intricacies of finding the right level of unremarkableness in DST design, and share lessons learned in prototyping critical AI systems as a situated experience.

Interactions with social robots in public and private spaces are becoming more and more common and varied. As this trend continues, it is important to understand how a robot's embodiment influences its ability to calibrate trust and comfort with its users and behave in accordance with social norms. This is especially true when one social intelligence embodies multiple physical robots (re-embodiment). We have conducted two studies-one quantitative and and one qualitative-which shed light on the way robots should be embodied and re-embodied by intelligences during different types of social interactions. This paper outlines our previous work on elucidating the role of embodiment in social interactions and experimenting with re-embodiment as a design paradigm, and it describes the directions in which we plan to take this research in the near future.

Human-robot interactions that involve multiple robots are becoming common. It is crucial to understand how multiple robots should transfer information and transition users between them. To investigate this, we designed a 3 × 3 mixed-design study in which participants took part in a navigation task. Participants interacted with a stationary robot who summoned a functional (not explicitly social) mobile robot to guide them. Each participant experienced the three types of robot-robot interaction: representative (the stationary robot spoke to the participant on behalf of the mobile robot), direct (the stationary robot delivered the request to the mobile robot in a straightforward manner), and social (the stationary robot delivered the request to the mobile robot in a social manner). Each participant witnessed only one type of robot-robot communication: silent (the robots covertly communicated), explicit (the robots acknowledged that they were communicating), or reciting (the stationary robot said the request aloud). Our results show that it is possible to instill socialness in and improve likability of a functional robot by having a social robot interact socially with it. We also found that covertly exchanging information is less desirable than reciting information aloud.

Many robot applications being explored involve robots leading humans during navigation. Developing effective robots for this task requires a way for robots to understand and model a human's following behavior. In this paper, we present results from a user study of how humans follow a guide robot in the halls of an office building. We then present a data-driven Markovian model of this following behavior, and demonstrate its generalizability across time interval and trajectory length. Finally, we integrate the model into a global planner and run a simulation experiment to investigate the benefits of coupled human-robot planning. Our results suggest that the proposed model effectively predicts how humans follow a robot, and that the coupled planner, while taking longer, leads the human significantly closer to the target position.

Machine learning (ML) plays an increasingly important role in improving a user's experience. However, most UX practitioners face challenges in understanding ML's capabilities or envisioning what it might be. We interviewed 13 designers who had many years of experience designing the UX of ML-enhanced products and services. We probed them to characterize their practices. They shared they do not view themselves as ML experts, nor do they think learning more about ML would make them better designers. Instead, our participants appeared to be the most successful when they engaged in ongoing collaboration with data scientists to help envision what to make and when they embraced a data-centric culture. We discuss the implications of these findings in terms of UX education and as opportunities for additional design research in support of UX designers working with ML.

Autonomous vehicles have been in development for nearly thirty years and recently have begun to operate in real-world, uncontrolled settings. With such advances, more widespread research and evaluation of human interaction with autonomous vehicles (AV) is necessary. Here, we present an interview study of 32 pedestrians who have interacted with Uber AVs. Our findings are focused on understanding and trust of AVs, perceptions of AVs and artificial intelligence, and how the perception of a brand affects these constructs. We found an inherent relationship between favorable perceptions of technology and feelings of trust toward AVs. Trust in AVs was also influenced by a favorable interpretation of the company's brand and facilitated by knowledge about what AV technology is and how it might fit into everyday life. To our knowledge, this paper is the first to surface AV-related interview data from pedestrians in a natural, real-world setting.

The ability to communicate is crucial to leading an independent life. Unfortunately, individuals from developing communities who are deaf and hard of hearing tend to encounter difficulty communicating, due to a lack of educational resources. We present findings from a two-year deployment of Speak Up, a suite of voice-powered games to motivate speech therapy, at a school for the deaf in India. Using ethnographic methods, we investigated the interplay between Speak Up and local educational practices. We found that teachers' speech therapy goals had evolved to differ from those encoded in the games, that the games influenced classroom dynamics, and that teachers had improved their computer literacy and developed creative uses for the games. We used these insights to further enhance Speak Up by creating an explicit teacher role in the games, making changes that encouraged teachers to build their computer literacy, and adding an embodied agent.

We explored whether a robot can leverage social influences to motivate nearby bystanders to intervene and defend them from human abuse. We designed a between-subjects study where 48 participants took part in a memorization task and observed a confederate mistreating a robot both verbally and physically. The robot was either empathetic towards the participant»s performance in the task or indifferent. When the robot was mistreated, it ignored the abuse, shut down in response to it, or reacted emotionally. We found that the majority of the participants intervened to help the robot after it was abused. Interventions happened for a wide range of reasons. Interestingly, the empathetic robot increased the proportion of participants that self-reported intervening in comparison to the indifferent robot, but more participants moved the robot as a response to abuse in the latter case. The participants also perceived the robot being verbally mistreated more and reported higher levels of personal distress when the robot briefly shut down after abuse in comparison to when it reacted emotionally or did not react at all.

We demonstrate a system of adding an additional human-robot communication channel using a spherical robot through kinesthetic haptic signals. While not designed for this type of interaction, we show that the robot could be used to generate kinesthetic haptic signals through asymmetric rotations. These rotations generate pseudo-rotations that are detectable in a user's palm and can convey both rotational and directional information with proper training. We present two user studies that explore potential types of distinguishable haptic signals. While some participants were able to rapidly identify the different signals, other participants expressed the need for more training. We also describe use cases we believe would benefit from such interaction and general guidelines for spherical haptic devices.

We conducted a 2x2 between-subjects experiment to examine the effects of two orientation and two gaze behaviors during group conversations for a mobile, low degree-of-freedom robot. For this experiment, we designed a novel protocol to induce changes in the robot's group and study different social contexts. In addition, we implemented a perception system to track participants and control the robot's orientation and gaze with little human intervention. The results showed that the gaze behaviors under consideration affected the participants' perception of the robot's motion and that its motion affected human perception of its gaze. This mutual dependency implies that robot gaze and body motion must be designed and controlled jointly, rather than independently of each other. Moreover, the orientation behaviors that we studied led to similar feelings of inclusion and sense of belonging to the robot's group, suggesting that both can be primitives for more complex orientation behaviors.

Machine learning improves mobile user experience. Interestingly, envisioning apps with adaptive interfaces that reduce navigation and selection effort is not standard UX practice. When implementing an adaptive UI for our mobile transit app, we encountered a number of problems. Our original design did not log necessary information nor did it induce users to provide good labels. On reflection, we realized UX designers should identify and refine UI adaptions when sketching wireframes. To advance on this insight, we reviewed the interfaces of popular apps and extracted six design patterns where UI adaptation can improve in-app navigation. Next, we designed an exemplar set of wireframes, illustrating how UX designers might annotate their interaction flows to communicate planned adaptation and note the information (logs and labels) needed to make the desired inferences.

Clinical decision support tools (DSTs) are computational systems that aid healthcare decision-making. While effective in labs, almost all these systems failed when they moved into clinical practice. Healthcare researchers speculated it is most likely due to a lack of user-centered HCI considerations in the design of these systems. This paper describes a field study investigating how clinicians make a heart pump implant decision with a focus on how to best integrate an intelligent DST into their work process. Our findings reveal a lack of perceived need for and trust of machine intelligence, as well as many barriers to computer use at the point of clinical decision-making. These findings suggest an alternative perspective to the traditional use models, in which clinicians engage with DSTs at the point of making a decision. We identify situations across patients' healthcare trajectories when decision supports would help, and we discuss new forms it might take in these situations.

Research in assistive systems for travelers who are blind/low vision (B/LV) has been largely focused on basic map information. We present NavCue, an intelligent system module for providing rich, multi-sensory, context-based information using speech guidance and robot physical gestures. This approach is motivated by our previous user studies with people who are blind or low vision. This rich information should enhance user location awareness and confidence when traveling through unfamiliar locations.

In this paper, we describe the process of making a robot useful as a guide robot for people who are blind or visually impaired. For this group, the interactive audio feature of a robot assumes a very high level of importance. We have introduced some features that will help to make the robot sound natural and be more comfortable. We first addressed the question of the speaker placement to help the user determine the size and distance of the robot. After the initial meeting, user data will be retained by the robot so that their communication evolves with every interaction. The robot will also ask the users if they need to take a rest after a specified interval depending upon the user's age and the distance they need to cover. The next time they visit, all this information will be used to make the interaction more natural and customized for each individual user.

Participatory sensing systems use people and their smartphones as a sensing infrastructure, and getting people to make contributions remains a critical challenge. Little work details how system designers should combine different interactions to increase coverage of service location. Tiramisu, a participatory sensing system, invites transit riders to crowdsource real-time arrival information by sharing location traces when they commute. We extended this system with a new feature that allows riders at stops to "spot" buses passing by. To better understand the impact of this new feature, we conducted an observational log analysis, examining changes in coverage and user behavior before and after the new feature. Following the addition of the spotting feature, participants' contributions increased coverage (the number of trips with real-time data) by 98%, and they used the app more than twice as much. The addition of the spotting feature was also followed by a significant increase of trace contributions.

We describe a method for low-cost awareness of characteristics of dense, moving crowds such as group formation, personal space approximation, and occlusion compensation for use in navigating through crowds. It incorporates social expectations and is inspired by human perceptual processes. The approach uses a single Kinect to cluster all moving objects into groups, applies a 2D polygon projection in obscured regions, and a group personal space modeled using asymmetric Gaussians in order to inhibit certain socially inappropriate robot paths. This approach trades off detection of individual people for higher coverage and lower cost, while preserving high speed processing. A real-world evaluation of this approach showed good performance in comparison to an existing people detection approach. The projected polygon step captures significantly more people in the scene (77% vs. 80%) and supports group clustering in dense, complex scenarios. Examples are provided for group splitting and merging, dense crowds with obstructions, and cases where other approaches typically encounter difficulty.

We explore online reinforcement learning techniques to find good policies to control the orientation of a mobile robot during social group conversations. In this scenario, we assume that the correct behavior for the robot should convey attentiveness to the focus of attention of the conversation. Thus, the robot should turn towards the speaker. Our results from tests in a simulated environment show that a new state representation that we designed for this problem can be used to find good policies for the robot. These policies can generalize across interactions with different numbers of people and can handle various levels of sensing noise.

Robots are predicted to serve in environments in which human honesty is important, such as the workplace, schools, and public institutions. Can the presence of a robot facilitate honest behavior? In this paper, we describe an experimental study evaluating the effects of robot social presence on people's honesty. Participants completed a perceptual task, which is structured so as to allow them to earn more money by not complying with the experiment instructions. We compare three conditions between subjects: Completing the task alone in a room; completing it with a non-monitoring human present; and completing it with a non-monitoring robot present. The robot is a new expressive social head capable of 4-DoF head movement and screen-based eye animation, specifically designed and built for this research. It was designed to convey social presence, but not monitoring. We find that people cheat in all three conditions, but cheat equally less when there is a human or a robot in the room, compared to when they are alone. We did not find differences in the perceived authority of the human and the robot, but did find that people felt significantly less guilty after cheating in the presence of a robot as compared to a human. This has implications for the use of robots in monitoring and supervising tasks in environments in which honesty is key.

Dynamic changes can present significant challenges for visually impaired travelers to safely and independently navigate urban environments. To address these challenges, we are developing the NavPal suite of technology tools [1]. NavPal includes a dynamic guidance tool [2] in the form of a smartphone app that can provide real-time instructions based on available map information to guide navigation in indoor environments. In this paper we enhance our past work by introducing a framework for blind travelers to add map/navigation information to the tool, and to invite trusted sources to do the same. The user input is realized through audio breadcrumb annotations that could be useful for future trips. The trusted sources mechanism provides invited trusted individuals or organizations an interface to contribute real-time information about the surrounding environment. We demonstrate the feasibility of our solution through a prototype Android smartphone-based outdoor navigation aid for blind travelers. An initial usability study with visually impaired adults informed the design and implementation of this prototype.

Appropriate robot behavior in public, open spaces cannot occur without the ability to automatically detect conversational groups of free-standing people. To this end, we propose an alternating optimization procedure that estimates lower body orientations and detects groups of interacting people. The first task is achieved by tracking the direction of the lower body of the people in the scene based on their position, their head orientation, the location of objects of interest in their vicinity, and their groups. For the second task, we propose a new group detection algorithm based on F-formation detection. This method can reason about lower body orientation distributions, and generates soft group assignments for the orientation trackers. We evaluate the proposed approach on a publicly available dataset, and show that it can improve state-of-the-art detection of non-interacting people without sacrificing group detection accuracy. This is particularly useful for robots since it provides more opportunities for starting interactions and can help estimate disengagement.

Participatory sensing systems (PSS) require frequent injection of information that has a short shelf-life. The use of crowds to gather information for PSS is therefore particularly challenging. In this study, we explore the impact of two policies on user contributions. A quid-pro-quo policy exchanges contributions from users for access to critical information in the system. A request policy simply reminds the user that information is needed to make the system function well. Prior research has shown that request for help in crowdsourced system is an effective mechanism to increase contributions. During a large-scale experimental study within a publicly deployed, crowdsourced, transit information system, we analyzed metrics associated with frequency of contribution and commitment to long-term use over a 10-month period. Our results confirmed that quid-pro-quo led to more contribution, but at a cost of faster departure from the study. When a participant was simply requested to contribute, but could still access community-generated data if they ignored a request, was largely ineffective and was statistically similar to the control condition where no request for contribution occurred. Thus crowdsource system designers should consider imposing quid-pro-quo type policies for PSS that concentrate on fewer users, but makes them more productive.

In this study, we explored the impact of a co-located sidekick on child-robot interaction. We examined child behaviors while interacting with an expressive furniture robot and his robot lamp sidekick. The results showed that the presence of a sidekick did not alter child proximity, but did increase attention to spoken elements of the interaction. This suggests the addition of a co-located sidekick has potential to increase engagement but may not alter subtle physical interactions associated with personal space and group spatial arrangements. The findings also reinforce existing research by the community on proxemics and anthropomorphism.

Trust in automation is a crucial ingredient for successful human robot interaction. Both human related and robot related factors influence the user's trust on the robot and it is challenging to characterize each of these factors and study how they affect human trust. In this study we try to understand how blame attribution after an error impacts user trust. Three different robot personalities were implemented, each assigning blame to either of the user, the robot itself, or the human-robot team. Our study results confirm that blame attribution impacts human trust in robots.

We propose an assisted photography framework to help visually impaired users properly aim a camera and evaluate our implementation in the context of documenting public transportation accessibility. Our framework integrates user interaction during the image capturing process to help users take better pictures in real time. We use an image composition model to evaluate picture quality and suggest providing audiovisual feedback to improve users’ aiming position. With our particular framework implementation, blind participants were able to take pictures of similar quality to those taken by low vision participants without assistance. Likewise, our system helped low vision participants take pictures as good as those taken by fully sighted users. Our results also show a positive trend in favor of spoken directions to assist visually impaired users in comparison to tone and silent feedback. Positive usefulness ratings provided by full vision users further suggest that assisted photography has universal appeal.

Many mobile applications rely on location information gained from location services on mobile devices. However, continuously tracking the device location with high accuracy drains the battery quickly. Furthermore, sensing the same location can be redundant when multiple devices are co-located. In this paper, we develop a crowdsourcing-based location service, E2A2 (energy efficient and accuracy aware), which places colo-cated devices into groups, and uses group location to represent individual device location. The E2A2 location service aims to reduce individual device battery consumption associated with location services while simultaneously maintaining high location accuracy for each device. Our experimental results from a prototype system show the effectiveness of our proposed solution with different mobility patterns. We also present results on the impact of different system parameters and the number of users in a group. Compared to running GPS location services on individual devices separately, our E2A2 service saves on average 33% battery consumption rate when 4 devices are co-located at walking speed and 26% battery consumption rate when 4 devices are colocated on the same bus while meeting the same accuracy requirements.

We evaluate three interaction modes to assist visually impaired users during the camera aiming process: speech, tone, and silent feedback. Our main assumption is that users are able to spatially localize what they want to photograph, and roughly aim the camera in the appropriate direction. Thus, small camera motions are sufficient for obtaining a good composition. Results in the context of documenting accessibility barriers related to public transportation show that audio feedback is valuable. Visually impaired users were not affected by audio feedback in terms of social comfort. Furthermore, we observed trends in favor of speech over tone, including higher ratings for ease of use. This study reinforces earlier work that suggests users who are blind or low vision find assisted photography appealing and useful.

Prior work in human-autonomy interaction has focused on plant systems that operate in highly structured environments. In contrast, many human-robot interaction (HRI) tasks are dynamic and unstructured, occurring in the open world. It is our belief that methods developed for the measurement and modeling of trust in traditional automation need alteration in order to be useful for HRI. Therefore, it is important to characterize the factors in HRI that influence trust. This study focused on the influence of changing autonomy reliability. Participants experienced a set of challenging robot handling scenarios that forced autonomy use and kept them focused on autonomy performance. The counterbalanced experiment included scenarios with different low reliability windows so that we could examine how drops in reliability altered trust and use of autonomy. Drops in reliability were shown to affect trust, the frequency and timing of autonomy mode switching, as well as participants' self-assessments of performance. A regression analysis on a number of robot, personal, and scenario factors revealed that participants tie trust more strongly to their own actions rather than robot performance.

It is challenging to quantitatively measure a user's trust in a robot system using traditional survey methods due to their invasiveness and tendency to disrupt the flow of operation. Therefore, we analyzed data from an existing experiment to identify measures which (1) have face validity for measuring trust and (2) align with the collected post-run trust measures. Two measures are promising as real-time indications of a drop in trust. The first is the time between the most recent warning and when the participant reduces the robot's autonomy level. The second is the number of warnings prior to the reduction of the autonomy level.

Crowd-sourcing social computing systems represent a new material for HCI designers. However, these systems are difficult to work with and to prototype, because they require a critical mass of participants to investigate social behavior. Service design is an emerging research area that focuses on how customers co-produce the services that they use, and thus it appears to be a great domain to apply this new material. To investigate this relationship, we developed Tiramisu, a transit information system where commuters share GPS traces and submit problem reports. Tiramisu processes incoming traces and generates real-time arrival time predictions for buses. We conducted a field trial with 28 participants. In this paper we report on the results and reflect on the use of field trials to evaluate crowd-sourcing prototypes and on how crowd sourcing can generate co-production between citizens and public services.

We explore deception in the context of a multi-player robotic game. The robot does not participate as a competitor, but is in charge of declaring who wins or loses every round. The robot was designed to deceive game players by imperceptibly balancing how much they won, with the hope this behavior would make them play longer and with more interest. Inducing false belief about who wins the game was accomplished by leveraging paradigms about robot behavior and their better perceptual abilities. Results include the finding that participants were more accepting of lying by our robot than for robots in general. Some participants found the balancing strategy favorable after being debriefed, while others showed less interest due to a perceived level of unfairness.

We present an interactive, computational approach for assisting users with visual impairments during photographic documentation of transit problems. Our technique can be described as a method to improve picture composition, while retaining visual information that is expected to be most relevant. Our system considers the position of the estimated region of interest (ROI) of a photo, and camera orientation. Saliency maps and Gestalt theory are used for guiding the user towards a more balanced picture. Our current implementation for mobile phones uses optic flow to update the internal knowledge of the position of the ROI and tilt sensor readings to correct non horizontal or vertical camera orientations. Using ground truth labels, we confirmed our method proposes valid strategies for improving image composition. Future work includes an optimized implementation and user studies.

Despite regulations specifying parking spots that support wheelchair vans, it is not uncommon for end users to encounter problems with clearance for van ramps. Even if a driver elects to park in the far reaches of a parking lot as a precautionary measure, there is no guarantee that the spot next to their van will be empty when they return. Likewise, the prevalence of older drivers who experience significant difficulty with ingress and egress from vehicles is nontrivial and the ability to fully open a car door is important. This work describes a method and user interaction for low cost, short-range parking without a driver in car. This will enable ingress/egress without the doors being blocked by neighboring cars.

The recent advances in web 2.0 technologies and the rapid adoption of smart phones raises many opportunities for public services to improve their services by engaging their users (who are also owners of the service) in co-design: a dialog where users help design the services they use. To investigate this opportunity, we began a service design project investigating how to create repeated information exchanges between riders and a transit agency in order to create a virtual "place" from which the dialog on services could take place. Through interviews with riders, a workshop with a transit agency, and speed dating of design concepts, we have developed a design direction. Specifically, we propose a service that combines vehicle location and "fullness" ratings provided by riders with dynamic route change information from the transit agency as a foundation for a dialog around riders conveying input for continuous service improvement.

RADAR is a multiagent system with a mixed-initiative user interface designed to help office workers cope with email overload. RADAR agents observe experts to learn models of their strategies and then use the models to assist other people who are working on similar tasks. The agents' assistance helps a person to transition from the normal email-centric workflow to a more efficient task-centric workflow. The Email Classifier learns to identify tasks contained within emails and then inspects new emails for similar tasks. A novel task-management user interface displays the found tasks in a to-do list, which has integrated support for performing the tasks. The Multitask Coordination Assistant learns a model of the order in which experts perform tasks and then suggests a schedule to other people who are working on similar tasks. A novel Progress Bar displays the suggested schedule of incomplete tasks as well as the completed tasks. A large evaluation demonstrated that novice users confronted with an email overload test performed significantly better (a 37% better overall score with a factor of four fewer errors) when assisted by the RADAR agents.

The Wizard of Oz experiment method has a long tradition of acceptance and use within the field of human-robot interaction. The community has traditionally downplayed the importance of interaction evaluations run with the inverse model: the human simulated to evaluate robot behavior, or Oz of Wizard. We argue that such studies play an important role in the field of human-robot interaction. We differentiate between methodologically rigorous human modeling and placeholder simulations using simplified human models. Guidelines are proposed for when Oz of Wizard results should be considered acceptable. This paper also describes a framework for describing the various permutations of Wizard and Oz states.

This paper describes an effort to identify common metrics for task-oriented human-robot interaction (HRI). We begin by discussing the need for a toolkit of HRI metrics. We then describe the framework of our work and identify important biasing factors that must be taken into consideration. Finally, we present suggested common metrics for standardization and a case study. Preparation of a larger, more detailed toolkit is in progress.

Experts from the Robotics Institute were individually interviewed for their insight on interface lessons for fully and semi-autonomous mobile robots. Information was collected on four main themes: challenges, things that seem to work well, things that do not work well, and interface wisdom. The comments were then condensed and pooled into seven high-level categories: safety, remote awareness, control, command inputs, status and state, recovery, and interface design. Classification of expert comments was relatively straightforward in that many interviewees identified consistent material. This suggests that those producing interfaces for fully and semi-autonomous mobile robots should, at the minimum, ensure that they have addressed these broad topics.

This paper describes a robotic walker designed as an assistive device for frail elderly people with cognitive impairment. Locomotion is most often the primary form of exercise for the elderly, and devices that provide mobility assistance are critical for the health and well being of such individuals. Previous work on walkers focused primarily on safety but offered little or no assistance with navigation and global orientation. Our system provides these features in addition to the stability and support provided by conventional walkers. A software suite of robot localization and navigation combined with a shared-control haptic interface achieves this capability. The system has been tested in a retirement facility near Pittsburgh, PA, USA.