Companion Robots Research Articles

THE NIH STAGE MODEL AND STUDY EXAMPLES OF EARLY STAGES IN DEMENTIA CARE INTERVENTION DEVELOPMENT RESEARCH

Abstract The NIH’s Stage Model provides a common language to facilitate discussion of intervention development research. According to NIH Stage Model (2022), “an examination of the mechanisms of behavior change or the principles underlying an intervention is encouraged by the NIH Stage Model in every Stage of behavioral intervention development.” The five papers in this symposium focus on early-stage intervention development by refinement, adaptation and pilot testing (Stage 1) related to dementia and palliative care (PC) clinical trials. The first paper is a cluster trial of a PC education program for nurses (N=23) in 10 assisted living communities that tested the mechanism of staff self-efficacy in increases in advance care planning discussions with family members of residents living with dementia. The second paper is a clinical trial that tested the feasibility of Companion Robots in live-alone Korean-American older adults (N=30) to determine which features help improve health behaviors (e.g. medication adherence, daily exercises). The third paper is a single-site clinical trial pilot study developed with stakeholders which tested the feasibility of a palliative care community health worker support program for hospitalized minoritized persons living with dementia and their caregivers. The fourth paper adapts an evidence-based e-PainSupport intervention for use with dementia caregivers to report patient pain and administration of analgesics. The fifth paper is a protocol to test the feasibility and acceptability of a culturally sensitive caregiver peer support program (Pair2Care) in current (n=15) and trained former (n=15) African-American dementia caregivers. The discussant will highlight ways to improve clinical trial mechanisms.

OLDER ADULTS’ UNDERSTANDING OF SIGNALS COMMUNICATED BY ROBOT COMPANIONS FOR CAREGIVING

Abstract Robotic animal-like companions for older adults are promising technologies to address companionship and new models of care. Our project, Affordable Robotic Intelligence for Elderly Support, aims to design smart communication capabilities in an Ageless Innovation Joy for All™ robotic cat. The cat robot with enhanced capabilities uses intuitive digital cues, including display screen, sound, and LED to create affordances to communicate various interaction intents to engage users into desirable actions. We conducted a study with 315 participants to understand the efficacy of designed affordances. A total of 8 affordances for 8 task scenarios, each with 3 variations of complete or incomplete information, simulating possible experiences were tested with users. Participants were randomly assigned to the conditions “full” (=display+sound+LED), “no_display” (=sound+LED), and “no_sound” (=display+LED) and were asked to provide a response interpretation of the experience signals and rank a list of potential interpretations in order of possibility. Results indicate that participants in the full experience group liked the robot the most (M=6.95 on a scale of 1-10) and gave the highest probability of the robot being a pleasant companion to older adults (M=7.17), compared to the no_display group (M_likability=6.01; M_companionship=6.58) and the no_sound group (M_likability=6.35; M_companionship=6.96). Participants in “no_display” had the greatest difficulty at inferring the robot’s intent. However, the no_sound group had less difficulty understanding the robot than the “full” experience group. Sound (e.g., meowing) appeared to be ambiguous, and removing it improved the communicability of the designed interface of this robot companion.

Generative replay for multi-class modeling of human activities via sensor data from in-home robotic companion pets

Generative replay for multi-class modeling of human activities via sensor data from in-home robotic companion pets

Living Lab-Based Service Interaction Design for a Companion Robot for Seniors in South Korea.

A living lab is a valuable method for designing tangible and intangible service elements, ensuring a comprehensive user experience. Developing a digital companion service, which users may be unfamiliar with, requires observing user behavior in real-world environments and analyzing living and behavioral patterns. A living lab starts with understanding user characteristics and behaviors. Living lab methods have an impact on the accuracy and precision of service design. The number of seniors in South Korea is rapidly increasing, leading to a rise in social issues like solitary deaths and suicide. Addressing these problems has led to a growing demand for companion robots. To design effective companion services, understanding seniors' living environments and their cognitive and behavioral traits is essential. This opinion piece, based on a national R&D project, presents the development of a digital companion for seniors. It offers insights, providing a comprehensive overview of living lab-based service interaction design and proposing methodologies about living lab environment construction and experimentation and considerations when designing robot interaction functions and appearance. The living lab environment includes real living spaces, laboratories, virtual reality settings, and senior welfare centers. Using the research findings, we created service scenarios, analyzed senior language characteristics, and developed the concept and facial expressions of the digital companion. To successfully introduce a novel service, it is crucial to analyze users' real-life behavior and adjust the service accordingly.

The impact of social robots' presence and roles on children's performance in musical instrument practice

AbstractResearch on the educational applications of social robots has shown how they can motivate children and help improve academic learning outcomes. Here, we examine how robots can support skill learning and, more specifically, musical instrument practice. Drawing from social facilitation theory and evaluation apprehension theory we expected that the robot's mere presence would impact children's performance and that this effect would be contingent upon the children expecting the robot to evaluate their performance. We report an experiment with children (N = 31) aged nine to twelve who practiced a familiar and new piece alone, in the presence of an evaluative robot, and in the presence of a non‐evaluative robot. We found that children performed better in terms of rhythm, pitch, and general impression in the presence of the non‐evaluative robot. These findings offer important insights for designing robot tutors for music learning. Practitioner notesWhat is already known about this topic Social robots have been applied in different educational scenarios (e.g., second language, math, and programming) and were proven to be beneficial for children's motivation. Musical instrument learning requires practice, perseverance, and social support to become successful. Social robots can be used as a provider of social support during musical instrument practice. Children tend to perform better on easy or well‐rehearsed tasks and worse on complex tasks or new ones with the presence of observers, but only when they believe the observer can evaluate them. What this paper adds Social robots are beneficial for children's performance in musical instrument learning. Limited evidence was found to prove that children tend to perform better on old melodies and worse on new melodies in the presence of a social robot. However, the results confirmed that the level of evaluative of the robot matters. Children tend to have better performance with the robot that did not provide evaluative comments when practicing a new melody (a difficult task) than alone and with the robot that offered evaluative comments. This study confirmed that social robots can provide support to children in practicing music, helping to improve their performance. Implications for practice and/or policy Social facilitation and evaluation apprehension effects need to be taken into consideration during the behaviour design of companion robots in learning scenarios. Robots, which were intended to motivate children in learning, should be designed to not provide evaluative comments.

Robot‐Administered Serious Brain Games for Older Adults with Mild Cognitive Impairment or early‐stage Alzheimer’s Disease: A Pilot Study

AbstractBackgroundTraditional methods for disease management have shown limited success treating AD/ADRD or mitigating its symptoms. Innovative technology such as Artificial Intelligence and Socially Robots, have begun to alleviate the growing need for novel solutions for AD/ADRD. While Socially Assistive Robots (SAR) are used to interact with patients with dementia or other mental disorders, to our knowledge, no such cooperative social robots have been studied to co‐play serious brain games with older adults with MCI or early‐stage AD/ADRD.MethodThe study involved 20 older adults (average age: 77.7; std: 6.43; 15 female) living in a care facility who were diagnosed with MCI or Early‐Stage ADRD (SLUMS 10‐25). They participated in 12 different games (e.g., Words, Picture Puzzle, Ryan Runs, Flow Control, Birds, Checkers, Solitaire, Birds Count, etc.) with a social companion robot named Ryan, every day for 8‐10 weeks. These games aimed to improve memory, cognitive function, and physical activity. Each participant had a Ryan device in their apartment and were trained on how to use it. The study collected data on usage time, win/loss rate, difficulty level, average score, and average duration per game, as well as depression screening (PHQ‐9) and SLUMS scores before, during, and after the study.ResultParticipants in the study spent 887 hours using Ryan. They spent 254 hours (28.7%) playing games on Ryan. On average they spent 12 minutes (std = 5 minutes) per day playing serious games with Ryan. Checkers, Flow Game, Picture Puzzle, Solitaire, and Word Puzzle, were the most popular games among all. On average, the SLUMS and PHQ‐9 scores improved by 3.3 and 2.43 points, respectively.ConclusionOur study also shows that on average, participants performed better over time in playing the games. For example, the average Win Rate or Scores of the participants in playing the Flow Game, Word Puzzle, improved over the weeks by about 0.5% and 29 scores, every week, respectively. That means participants were more engaged in playing those games and were able to focus and increase their score or win rate over time.

Reflex or Reflection? The Oculomotor Behavior of the Companion Robot, Creating the Impression of Communicating with an Emotional Being

Reflex or Reflection? The Oculomotor Behavior of the Companion Robot, Creating the Impression of Communicating with an Emotional Being

Understanding Dog Behavior through Visual and Auditory Sensing Using Machine Learning

This work aims to understand a dog’s behavior towards environmental stimuli. Different from previous works, we collect multi-modality data including both video and audio data observed from the dog’s egocentric perspective. We propose to model the association between a dog’s reaction and the visual and auditory stimuli perceived by the dog using machine learning, in particular through an extended Convolutional Neural Network (eCNN). The eCNN model takes colored images, Short Time Fourier Transform (STFT) of audio, and motion fields extracted from image sequences as input, and outputs a prediction of the dog’s reaction, classified as Sit, Stand, Walk, or Smell. Our proposed model achieves promising prediction results, with an average accuracy of 79.02% over all four classes. We also evaluate model performance by separately using one of image, audio, and motion information. Our results show that the dog responds strongly to low-frequency sounds and various color differences in its field of view. These research findings provide valuable insights to understanding animal behavior and intelligence as well as insights for building robotic companion dogs.

Higher oxytocin concentrations occur in subjects who build affiliative relationships with companion robots

Building affiliative relationships with others is important for mental health. Recently, robots have been expected to play a role in improving mental health, but there is little scientific evidence as to whether they can build affiliative relationships with humans. To investigate that, we conducted studies combining behavior, physiology and questionnaires for companion robot Owners and Non-Owners. The results reveal that the steady-state concentration of oxytocin, a hormone related to affiliative relationships, was significantly higher in Owners than in Non-Owners. In addition, the Owners showed more behaviors indicative of intimacy than the Non-Owners. These results suggest that humans can build affiliative relationships with robots. Fifteen minutes of contact with the robot decreased the concentration of cortisol in both groups, suggesting that even a brief contact can contribute to improving mental health. Therefore, relationships between humans and robots may be one option to improve mental health and enhance well-being.

Research Hotspots and Trends of Social Robot Interaction Design: A Bibliometric Analysis

(1) Background: Social robot interaction design is crucial for determining user acceptance and experience. However, few studies have systematically discussed the current focus and future research directions of social robot interaction design from a bibliometric perspective. Therefore, we conducted this study in order to identify the latest research progress and evolution trajectory of research hotspots in social robot interaction design over the last decade. (2) Methods: We conducted a comprehensive review based on 2416 papers related to social robot interaction design obtained from the Web of Science (WOS) database. Our review utilized bibliometric techniques and integrated VOSviewer and CiteSpace to construct a knowledge map. (3) Conclusions: The current research hotspots of social robot interaction design mainly focus on #1 the study of human–robot relationships in social robots, #2 research on the emotional design of social robots, #3 research on social robots for children’s psychotherapy, #4 research on companion robots for elderly rehabilitation, and #5 research on educational social robots. The reference co-citation analysis identifies the classic literature that forms the basis of the current research, which provides theoretical guidance and methods for the current research. Finally, we discuss several future research directions and challenges in this field.

Medication adherence management for in-home geriatric care with a companion robot and a wearable device

Older adults are prone to forgetfulness and varying degrees of cognitive impairment, which can lead to not taking medication on time, taking the wrong medication or the wrong dose, all of which can negatively affect a person’s health and recovery from illness. Existing medication reminders, like mobile apps and pill boxes, are neither age-friendly nor designed to minimize the burden of documenting medication adherence. In this paper, we present a Medication Adherence Management System (MAMS) for elders, which is based on a companion robot and a wearable device. The MAMS addresses the key issues of safe medication management: medication reminders, medication confirmation, and medication history recording. Human subject tests were conducted to evaluate the performance, acceptability and usability of the MAMS. Results from 35 human subjects showed that the average scores of the convenience, usefulness, and adoptability of the proposed MAMS were 8.17, 8.49, and 8.23 out of 10, respectively. The System Usability Scale (SUS) scores for the MAMS, the robot, and the wearable device are 75.29, 78.60 and 76.40, respectively. We believe the MAMS has potential use in future in-home geriatric care.

The Japanese Pursuit of Human–Robot Companionship

Building on global advances in artificial emotional intelligence, Japanese companies have increasingly invested in developing social robots with capacities to express and evoke emotion. In some cases, they can even read the emotional expressions of human users. These efforts parallel a broader trend in state support for developing technological solutions to socioeconomic problems, such as social isolation and a deficit in care workers. The rise of companion robots has elicited excitement about potential futures of human–robot existence as well as concerns over data privacy and the loss of inter-human connection, embodying the dynamic emotional dimensions of Japan’s social transformation.

Home-Based Intelligent Exercise System for Seniors' Healthcare: The Example of Golf Croquet.

In 2020, the world experienced the threat of the COVID-19 epidemic, and seniors and chronic disease patients generally reduced their exercise and social activities to avoid increasing the risk of infection, which could lead to increased loneliness and even many diseases. Combining golf croquet games with a mobile application (App) and AIoT companion robots, this research constructs a home-based intelligent exercise system, uses the technology acceptance model (TAM), deduces users' intention to use this system based on perceived usefulness and perceived ease of use, and adds the needs of love and belonging, esteem, cognitive, aesthetic, and self-actualization in Maslow's hierarchy of needs theory (HNT) to conduct an analysis of system needs. This study collected empirical data, totaling 320 participants including seniors and their caregivers, from elderly care centers in northern Taiwan using a cross-sectional survey and purposive sampling. Based on regression and variance analysis, the results show that participants have a high level of acceptance of this system, believing that it is easy to learn and operate and can increase interaction with others, improve self-confirmation, satisfy the thirst for knowledge, increase the feeling of happiness, and fulfill self-actualization needs. In the future, by collecting and recording the process of seniors using the App, so as to find out their health problems as soon as possible, expand their daily life through this exercise, and achieve the goal of happy living and better healthcare.

A Study of Objective Evaluation Indicator Based on Robot Activity Logs for Owner Attachment to Companion Robot

A Study of Objective Evaluation Indicator Based on Robot Activity Logs for Owner Attachment to Companion Robot

Technology Acceptance Models from Different Viewpoints of Caregiver, Receiver, and Care Facility Administrator: Lessons from Long-Term Implementation Using Baby-Like Interactive Robot for Nursing Home Residents with Dementia

The introduction of companion robots into nursing homes has positive effects on older people with dementia (PwD) but increases the physical and psychological burden on the nursing staff, such as learning how to use them, fear of breakdowns, and concern about hygiene, and the concerns of the nursing home administrator, such as increased turnover and reduced quality of care due to this. To solve this problem, it is necessary to investigate the acceptability of robots from the viewpoints of all stakeholders: PwD as receivers, nursing staff as caregivers, and nursing home administrator as a care facility administrator. However, there is still missing hypothesis about how their acceptability is structured and involved with each other. This study proposes three technology acceptance model (TAMs) from the perspectives of PwD, nursing staff, and nursing home administrator. The models are conceptualized based on the qualitative and quantitative analysis of the results of our two experiments involving a baby-like interactive robot to stimulate PwD in the same nursing home (one with low acceptance of all stakeholders and the other with their high acceptance) in addition to the comparison with other companion robots. Based on the proposed models, we discuss an integrated TAM for the acceptance of companion robots in long-term care facilities. We also discuss the possibility of applying our approach, which examines the perspectives of various stakeholders on technology acceptance, to other areas such as health care and education, the ethical consideration of introducing a baby-like robot and some limitations.

Deep learning-based companion robot on senile dementia patients

BackgroundThere are currently at least 50 million dementia patients worldwide, and this number is expected to reach 152 million by 2050, of which about 60-70% will be Alzheimer’s patients. The companion robot based on deep learning is a product of the development of artificial intelligence technology, which is of great significance to the physical and mental health of the elderly, so it is used in the research on the treatment of Alzheimer’s patients.Subjects and Methods100 patients with Alzheimer’s disease in a hospital were selected for the study, and 50 patients were randomly divided into experimental group and control group. In the experiment, 50 patients with Alzheimer in the experimental group used a companion robot based on deep learning for auxiliary treatment while carrying out daily treatment. The control group of 50 patients did not receive any adjuvant therapy in addition to daily treatment. After three months of treatment, the study used the 3D-CAM and the mini–mental state examination (MMSE) to collect the treatment status of all patients, and used the SPSS23.0 statistical software to statistically analyze the collected data.ResultsAfter statistical analysis, the results of the two groups were obtained. The scores of 3D-CAM and MMSE in the experimental group were significantly higher than those in the control group and the difference was statistically significant.ConclusionsCompanion robots based on deep learning are helpful in the treatment of Alzheimer’s patients. They can improve the therapeutic effect and have certain social value.AcknowledgementThe Fundamental Research Funds in Heilongjiang Provincial Universities (No.135309356); Qiqihar University Young Teachers’ Scientific Research Initiation Support Program (No.2012k-M17).

"Enjoy, but Moderately!": Designing a Social Companion Robot for Social Engagement and Behavior Moderation in Solitary Drinking Context

Socially assistive robots can support people in making behavior changes by socially engaging in or moderating certain behaviors, such as physical exercise and snacking. However, there has not been much work on designing social robots that aim to support both social engagement and behavior moderation, i.e., offering social interactions for engaging in behaviors without over-engagement. This work explores how social robots can moderate alcohol consumption while socially engaging them in a solitary drinking context. As alcohol consumption can have benefits when done in moderation, this companion robot aims to guide the user toward moderate drinking by using social engagement (i.e., creating an enjoyable atmosphere) and drinking moderation (i.e., regulating the drinking pace). Our preliminary user study (n=20) reveals that the robot is perceived as a friendly companion, and its human-likeness is partly attributed to the robot's intervention. Most participants followed the robot's guidance and perceived it as an intelligent friend due to its social interactions and behavior tracking features. We discuss the benefit of physical interactions for social engagement, utilizing interaction rituals for enjoyable but moderate commensality, and ethical considerations in solitary drinking contexts.

How I want technology used in my care: Learning from documented choices of people living with dementia using a dyadic decision making tool

ABSTRACTWhile technologies for aging in place are promoted to support care partners and people living with dementia, perspectives of people living with dementia are underrepresented in both use decisions among families and discussions within academia and industry. This mixed-methods study examined the use preferences of twenty-nine people living with mild Alzheimer’s disease (AD) for four categories of technologies: location tracking, in-home sensors, web-cameras, and virtual companion robots. Participants completed a novel dyadic intervention, Let’s Talk Tech, where they documented their preferences of the four technology categories for care planning purposes. Post-test interviews were thematically analyzed and provide insight into selection processes. Technology preferences varied considerably by and within participant living with mild AD. Excepting location tracking, non-technology and low-technology options were more desirable than the featured technologies. Control over technology use was of great importance to people living with AD. Considerations given to technology preference selection imperfectly fit within the new Health Technology Acceptance Model (H-TAM) developed for older adults. These findings underscore the importance of including people living with dementia in decision making about technologies to support care at home and the need for further personalization and tailorable technological devices to accommodate and align with their preferences.

Social Robots to Fend Off Loneliness?

Social robots are increasingly being deployed to address social isolation and loneliness, particularly among older adults. Clips on social media attest that individuals availing themselves of this option are pleased with their robot companions. Yet, some people find the use of social robots to meet fundamental human emotional needs disturbing. This article clarifies and critically evaluates this response. It sets forth a framework for loneliness, which characterizes one kind of loneliness as involving an affective experience of lacking human relations that provide certain social goods. Next, the article discusses social robots and critically reviews the literature on the ethics of using them in light of this loneliness characterization. Third, we present a normative argument connecting the philosophical critique of loneliness-as-absence with the design and deployment of social robots. Finally, we draw out the implications of our analysis for public health and for interrogating the aims of commercial companies who make social robots.

Living With Robotic Companions for Better Psychological Well-Being

We live in a world where interactive devices are always around. But can these technologies become more than just useful tools for us? What if there was a social robot that could act as a helpful companion and help people improve their psychological well-being in their homes?