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

Artificial Intelligence (AI) plays an increasingly important role in improving HCI and user experience. Yet many challenges persist designing innovating valuable human-AI interactions. For example, AI systems can make unpredictable errors, these errors damage UX even lead to undesired societal impact. However, routinely grapples with complex technologies mitigates their unintended consequences. What makes different? interaction appear particularly difficult design? This paper investigates...

Machine learning (ML) plays an increasingly important role in improving a user's experience. However, most UX practitioners face challenges understanding ML's capabilities or envisioning what it might be. We interviewed 13 designers who had many years of experience designing the ML-enhanced products and services. probed them to characterize their practices. They shared they do not view themselves as ML experts, nor think more about would make better designers. Instead, our participants...

Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed practice. Empirical research diagnosed poor contextual fit as the cause. This paper describes design and field evaluation of a radically new form DST. It automatically generates slides for clinicians' meetings with subtly embedded machine prognostics. took inspiration from notion "Unremarkable Computing", that augmenting...

Robot navigation in crowded public spaces is a complex task that requires addressing variety of engineering and human factors challenges. These challenges have motivated great amount research resulting important developments for the fields robotics human-robot interaction over past three decades. Despite significant progress massive recent interest, we observe number remaining prohibit seamless deployment autonomous robots environments. In this survey article, organize existing into set...

Prior work in human trust of autonomous robots suggests the timing reliability drops impact and control allocation strategies. However, is traditionally measured post-run, thereby masking real-time changes trust, reducing sensitivity to factors like inertia, subjecting measure biases primacy-recency effect. Likewise, little known on how feedback robot confidence interacts with An experiment examine these issues showed loss due early masked traditional post-run measures, demonstrates alters...

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 elderly, and devices that provide mobility assistance are critical health well being such individuals. Previous work on walkers focused primarily safety but offered little or no navigation global orientation. Our system provides these features in addition to stability support provided by conventional walkers. A...

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

Crowd-sourcing social computing systems represent a new material for HCI designers. However, these are difficult to work with and prototype, because they require critical mass of participants investigate behavior. Service design is an emerging research area that focuses on how customers co-produce the services use, thus it appears be great domain apply this material. To relationship, we developed Tiramisu, transit information system where commuters share GPS traces submit problem reports....

Prior work in human-autonomy interaction has focused on plant systems that operate highly structured environments. In contrast, many human-robot (HRI) tasks are dynamic and unstructured, occurring the open world. It is our belief methods developed for measurement modeling of trust traditional automation need alteration order to be useful HRI. Therefore, it important characterize factors HRI influence trust. This study changing autonomy reliability. Participants experienced a set challenging...

Prior work in human trust of autonomous robots suggests the timing reliability drops impact and control allocation strategies. However, is traditionally measured post-run, thereby masking real-time changes trust, reducing sensitivity to factors like inertia, subjecting measure biases primacy-recency effect. Likewise, little known on how feedback robot confidence interacts with An experiment examine these issues showed loss due early masked traditional post-run measures, demonstrates alters...

The detection and tracking of moving objects is an essential task in robotics. CMU‐RI Navlab group has developed such a system that uses laser scanner as its primary sensor. We will describe our algorithm use several applications. Our worked successfully on indoor outdoor platforms with different kinds configurations two‐dimensional three‐dimensional scanners. applications vary from collision warning systems, people classification, observing human tracks, input to dynamic planner. Several...

Clinical decision support tools (DSTs) are computational systems that aid healthcare decision-making. While effective in labs, almost all these failed when they moved into clinical practice. Healthcare researchers speculated it is most likely due to a lack of user-centered HCI considerations the design systems. This paper describes field study investigating how clinicians make heart pump implant with focus on best integrate an intelligent DST their work process. Our findings reveal perceived...

Interactions with multiple conversational agents and social robots are becoming increasingly common. This raises new design challenges: Should be modeled after humans, presenting their entity (i.e., presence) as bound to a single body, or should they take advantage of non-human capabilities, such moving presence from body across service touchpoints contexts? We conducted User Enactments study in which participants interacted that had one per could re-embody (move body), co-embody into...

The human-robot interaction community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult compare the performance of such across literature. To bridge this gap, we introduce SocNavBench , simulation framework evaluating social navigation algorithms. comprises simulator with photo-realistic capabilities curated...

We explored whether a robot can leverage social influences to motivate nearby bystanders intervene and defend them from human abuse. designed between-subjects study where 48 participants took part in memorization task observed confederate mistreating both verbally physically. The was either empathetic towards the participant»s performance or indifferent. When mistreated, it ignored abuse, shut down response it, reacted emotionally. found that majority of intervened help after abused....

Autonomous vehicles have been in development for nearly thirty years and recently begun to operate real-world, uncontrolled settings. With such advances, more widespread research evaluation of human interaction with autonomous (AV) is necessary. Here, we present an interview study 32 pedestrians who interacted Uber AVs. Our findings are focused on understanding trust AVs, perceptions AVs artificial intelligence, how the perception a brand affects these constructs. We found inherent...

Robots are predicted to serve in environments which human honesty is important, such as the workplace, schools, and public institutions. Can presence of a robot facilitate honest behavior? In this paper, we describe an experimental study evaluating effects social on people's honesty. Participants completed perceptual task, structured so allow them earn more money by not complying with experiment instructions. We compare three conditions between subjects: Completing task alone room;...

We conducted a 2x2 between-subjects experiment to examine the effects of two orientation and gaze behaviors during group conversations for mobile, low degree-of-freedom robot. For this experiment, we designed novel protocol induce changes in robot's study different social contexts. In addition, implemented perception system track participants control with little human intervention. The results showed that under consideration affected participants' motion its gaze. This mutual dependency...

This paper explores the integration of two AI subdisciplines employed in development artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs). We present three approaches, each grounded theoretical models supported by preliminary empirical evidence. The modular approach, which introduces four with varying degrees integration, makes use chain-of-thought prompting, draws inspiration from augmented LLMs, Common Model Cognition,...

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 are able spatially localize what they want photograph, roughly aim in appropriate direction. Thus, small motions sufficient for obtaining a good composition. Results context of documenting accessibility barriers related public transportation show audio feedback valuable. Visually were not affected by terms social comfort....

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 UI for our transit app, we encountered a number of problems. Our original design did log necessary information nor it induce users to provide good labels. On reflection, realized designers should identify refine adaptions when sketching wireframes. To advance on this insight, reviewed the...

Robot navigation in crowded public spaces is a complex task that requires addressing variety of engineering and human factors challenges. These challenges have motivated great amount research resulting important developments for the fields robotics human-robot interaction over past three decades. Despite significant progress massive recent interest, we observe number remaining prohibit seamless deployment autonomous robots pedestrian environments. In this survey article, organize existing...