Explore the vast range of titles available.

We present a real-time motion-synthesis method for robot manipulators, called RelaxedIK, that is able to not only accurately match end-effector pose goals as done by traditional IK solvers, but also create smooth, feasible motions that avoid joint-space discontinuities, self-collisions, and kinematic singularities. To achieve these objectives on-the-fly, we cast the standard IK formulation as a weighted-sum non-linear optimization problem, such that motion goals in addition to end-effector pose matching can be encoded as terms in the sum. We present a normalization procedure such that our method is able to effectively make trade-offs to simultaneously reconcile many, and potentially competing, objectives. Using these trade-offs, our formulation allows features to be relaxed when in conflict with other features deemed more important at a given time. We compare performance against a state-of-the-art IK solver and a real-time motion-planning approach in several geometric and real-world tasks on seven robot platforms ranging from 5-DOF to 8-DOF. We show that our method achieves motions that effectively follow position and orientation end-effector goals without sacrificing motion feasibility, resulting in more successful execution of tasks compared to the baseline approaches. We also empirically evaluate how our solver performs with different optimization solvers, gradient calculation methods, and choice of loss function in the objective function.

While a growing number of machine learning (ML) systems have been deployed in clinical settings with the promise of improving patient care, many have struggled to gain adoption and realize this promise. Based on a qualitative analysis of coded interviews with clinicians who use an ML-based system for sepsis, we found that, rather than viewing the system as a surrogate for their clinical judgment, clinicians perceived themselves as partnering with the technology. Our findings suggest that, even without a deep understanding of machine learning, clinicians can build trust with an ML system through experience, expert endorsement and validation, and systems designed to accommodate clinicians’ autonomy and support them across their entire workflow.

Theory of Mind (ToM) has received significant research attention. Traditional ToM research has provided important understanding of how humans reason about mental states by utilizing shared world knowledge, social cues, and the interpretation of actions; however, many current behavioral paradigms are limited to static, \"third-person\" protocols. Emerging experimental approaches such as cognitive simulation and simulated social interaction offer opportunities to investigate ToM in interactive, \"first-person\" and \"second-person\" scenarios while affording greater experimental control. The advantages and limitations of traditional and emerging ToM methodologies are discussed with the intent of advancing the understanding of ToM in socially mediated situations.

A critical gap in our knowledge about social media is whether we can alleviate accessibility barriers and challenges for individuals with traumatic brain injury (TBI), to improve their social participation and health. To do this, we need real-time information about these barriers and challenges, to design appropriate aids. The aim of this study was to characterize the ways people with TBI accessed and used social media websites and understand unique challenges they faced. We invited 8 adults with moderate to severe TBI to log onto their own Facebook page and use it as they regularly would while thinking aloud. Their comments were recorded and transcribed for qualitative analysis. We first analyzed participants' utterances using a priori coding based on a framework proposed by Meshi et al to classify adults' motives for accessing social media. We next used an open coding method to understand the challenges that people with TBI faced while using Facebook. In other words, we analyzed participants' needs for using Facebook and then identified Facebook features that made it challenging for them to meet those needs. Participants used all categories of codes in the framework by Meshi et al and provided detailed feedback about the Facebook user interface. A priori coding revealed 2 dimensions that characterized participants' Facebook use: whether they were active or passive about posting and self-disclosure on Facebook and their familiarity and fluency in using Facebook. The open coding analysis revealed 6 types of challenges reported by participants with TBI, including difficulty with language production and interpretation, attention and information overload, perceptions of negativity and emotional contagion, insufficient guidance to use Facebook, concerns about web-based scams and frauds, and general accessibility concerns. Results showed that individuals with TBI used Facebook for the same reasons typical adults do, suggesting that it can help increase social communication and reduce isolation and loneliness. Participants also identified barriers, and we propose modifications that could improve access for individuals with brain injury. On the basis of identified functions and challenges, we conclude by proposing design ideas for social media support tools that can promote more active use of social media sites by adults with TBI.

Adults with traumatic brain injury (TBI) report significant barriers to using current social media platforms, including cognitive overload and challenges in interpreting social cues. Rehabilitation providers may be tasked with helping to address these barriers. To develop technological supports to increase social media accessibility for people with TBI-related cognitive impairments and to obtain preliminary data on the perceived acceptability, ease of use, and utility of proposed technology aids. We identified four major barriers to social media use among individuals with TBI: sensory overload, memory impairments, misreading of social cues, and a lack of confidence to actively engage on social media platforms. We describe the process of developing prototypes of support aids aimed at reducing these specific social media barriers. We created mock-ups of these prototypes and asked 46 community-dwelling adults with TBI (24 females) to rate the proposed aids in terms of their acceptability, ease of use, and utility. Across all aids, nearly one-third of respondents agreed they would use the proposed aids frequently, and the majority of respondents rated the proposed aids as easy to use. Respondents indicated that they would be more likely to use the memory and post-writing aids than the attention and social cue interpretation aids. Findings provide initial support for social-media-specific technology aids to support social media access and social participation for adults with TBI. Results from this study have design implications for future development of evidence-based social media support aids. Future work should develop and deploy such aids and investigate user experience.

Individuals with a history of traumatic brain injury (TBI) report fewer social contacts, less social participation, and more social isolation than noninjured peers. Cognitive-communication disabilities may prevent individuals with TBI from accessing the opportunities for social connection afforded by computer-mediated communication, as individuals with TBI report lower overall usage of social media than noninjured peers and substantial challenges with accessibility and usability. Although adaptations for individuals with motor and sensory impairments exist to support social media use, there have been no parallel advances to support individuals with cognitive disabilities, such as those exhibited by some people with TBI. In this study, we take a preliminary step in the development process by learning more about patterns of social media use in individuals with TBI as well as their input and priorities for developing social media adaptations. This study aims to characterize how and why adults with TBI use social media and computer-mediated communication platforms, to evaluate changes in computer-mediated communication after brain injury, and to elicit suggestions from individuals with TBI to improve access to social media after injury. We conducted a web-based survey of 53 individuals with a chronic history of moderate-to-severe TBI and a demographically matched group of 51 noninjured comparison peers. More than 90% of participants in both groups had an account on at least one computer-mediated communication platform, with Facebook and Facebook Messenger being the most popular platforms in both groups. Participants with and without a history of TBI reported that they use Facebook more passively than actively and reported that they most frequently maintain web-based relationships with close friends and family members. However, participants with TBI reported less frequently than noninjured comparison participants that they use synchronous videoconferencing platforms, are connected with acquaintances on the web, or use social media as a gateway for offline social connection (eg, to find events). Of the participants with TBI, 23% (12/53) reported a change in their patterns of social media use caused by brain injury and listed concerns about accessibility, safety, and usability as major barriers. Although individuals with TBI maintain social media accounts to the same extent as healthy comparisons, some may not use them in a way that promotes social connection. Thus, it is important to design social media adaptations that address the needs and priorities of individuals with TBI, so they can also reap the benefits of social connectedness offered by these platforms. By considering computer-mediated communication as part of individuals' broader social health, we may be able to increase web-based participation in a way that is meaningful, positive, and beneficial to broader social life.

Of all computational systems, robots are unique in their ability to afford embodied interaction using the wider range of human communicative cues. Research on human communication provides strong evidence that embodied cues, when used effectively, elicit social, cognitive, and task outcomes such as improved learning, rapport, motivation, persuasion, and collaborative task performance. While this connection between embodied cues and key outcomes provides a unique opportunity for design, taking advantage of it requires a deeper understanding of how robots might use these cues effectively and the limitations in the extent to which they might achieve such outcomes through embodied interaction. This article aims to underline this opportunity by providing an overview of key embodied cues and outcomes in human communication and describing a research program that explores how robots might generate high‐level social, cognitive, and task outcomes such as learning, rapport, and persuasion using embodied cues such as verbal, vocal, and nonverbal cues.

Voice-controlled smart speakers and displays have a unique but unproven potential for delivering eHealth interventions. Many laptop- and smartphone-based interventions have been shown to improve multiple outcomes, but voice-controlled platforms have not been tested in large-scale rigorous trials. Older adults with multiple chronic health conditions, who need tools to help with their daily management, may be especially good candidates for interventions on voice-controlled devices because these patients often have physical limitations, such as tremors or vision problems, that make the use of laptops and smartphones challenging. The aim of this study is to assess whether participants using an evidence-based intervention (ElderTree) on a smart display will experience decreased pain interference and improved quality of life and related measures in comparison with participants using ElderTree on a laptop and control participants who are given no device or access to ElderTree. A total of 291 adults aged ≥60 years with chronic pain and ≥3 additional chronic conditions will be recruited from primary care clinics and community organizations and randomized 1:1:1 to ElderTree access on a smart display along with their usual care, ElderTree access on a touch screen laptop along with usual care, or usual care alone. All patients will be followed for 8 months. The primary outcomes are differences between groups in measures of pain interference and psychosocial quality of life. The secondary outcomes are between-group differences in system use at 8 months, physical quality of life, pain intensity, hospital readmissions, communication with medical providers, health distress, well-being, loneliness, and irritability. We will also examine mediators and moderators of the effects of ElderTree on both platforms. At baseline, 4 months, and 8 months, patients will complete written surveys comprising validated scales selected for good psychometric properties with similar populations. ElderTree use data will be collected continuously in system logs. We will use linear mixed-effects models to evaluate outcomes over time, with treatment condition and time acting as between-participant factors. Separate analyses will be conducted for each outcome. Recruitment began in August 2021 and will run through April 2023. The intervention period will end in December 2023. The findings will be disseminated via peer-reviewed publications. To our knowledge, this is the first study with a large sample and long time frame to examine whether a voice-controlled smart device can perform as well as or better than a laptop in implementing a health intervention for older patients with multiple chronic health conditions. As patients with multiple conditions are such a large cohort, the implications for cost as well as patient well-being are significant. Making the best use of current and developing technologies is a critical part of this effort. ClinicalTrials.gov NCT04798196; https://clinicaltrials.gov/ct2/show/NCT04798196. PRR1-10.2196/37522.

Although moderate to severe traumatic brain injury (TBI) leads to facial affect recognition impairments in up to 39% of individuals, protective and risk factors for these deficits are unknown. The aim of the current study was to examine the effect of sex on emotion recognition abilities following TBI. We administered two separate emotion recognition tests (one static and one dynamic) to 53 individuals with moderate to severe TBI (females = 28) and 49 demographically matched comparisons (females = 22). We then investigated the presence of a sex-by-group interaction in emotion recognition accuracy. In the comparison group, there were no sex differences. In the TBI group, however, females significantly outperformed males in the dynamic (but not the static) task. Moreover, males (but not females) with TBI performed significantly worse than comparison participants in the dynamic task. Further analysis revealed that sex differences in emotion recognition abilities within the TBI group could not be explained by lesion location, TBI severity, or other neuropsychological variables. These findings suggest that sex may serve as a protective factor for social impairment following TBI and inform clinicians working with TBI as well as research on the neurophysiological correlates of sex differences in social functioning.

From teaching in labs to training for assembly, a role that robots are expected to play is to instruct their users in completing physical tasks. While instruction requires a range of capabilities, such as use of verbal and nonverbal language, a fundamental requirement for an instructional robot is to provide its students with instructions in a way that maximizes their task performance. In this paper, we present an autonomous instructional robot and investigate how different instructional strategies affect user performance and experience. Our analysis of human instructor–trainee interactions identified two key instructional strategies: (1) grouping instructions together and (2) summarizing the outcome of subsequent instructions. We implemented these strategies into a humanlike robot that autonomously instructed its users in a pipe-assembly task. To achieve autonomous instruction, we also developed a repair mechanism that enabled the robot to correct mistakes and misunderstandings. An evaluation of the instructional strategies in a human–robot interaction study showed that employing the grouping strategy resulted in faster task completion and increased rapport with the robot, although it also increased the number of task breakdowns. A comparison of our results with the human instructor–trainee interactions revealed many similarities, areas where our model for robot instructors could be improved, and the nuanced ways in which human instructors use training strategies such as summarization. Our findings offer strong implications for the design of instructional robots and directions of future research.