Can We Talk through a Robot As if Face-to-Face? Long-Term Fieldwork Using Teleoperated Robot for Seniors with Alzheimer's Disease

Kuwamura, Kaiko; Nishio, S.; Sato, Shinichi

doi:10.3389/fpsyg.2016.01066

Cited by 37 publications

(45 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have recently explored the role of social robots in a variety of domains, including elder care [6,7], shop-keeping [1,2,4,3,55], hotels [8], education [9], travel [10], and as personal 24:2 M. Doering et al companions [11,12]. As the capability of artificial intelligence increases, this trend is likely to continue.…”

Section: Introductionmentioning

confidence: 99%

Neural-network-based Memory for a Social Robot

Doering

Kanda

Ishiguro

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

Many recent studies have shown that behaviors and interaction logic for social robots can be learned automatically from natural examples of human-human interaction by machine learning algorithms, with minimal input from human designers [1-4]. In this work, we exceed the capabilities of the previous approaches by giving the robot memory. In earlier work, the robot's actions were decided based only on a narrow temporal window of the current interaction context. However, human behaviors often depend on more temporally distant events in the interaction history. Thus, we raise the question of whether (and how) an automated behavior learning system can learn a memory representation of interaction history within a simulated camera shop scenario. An analysis of the types of memory-setting and memory-dependent actions that occur in the camera shop scenario is presented. Then, to create more examples of such actions for evaluating a shopkeeper robot behavior learning system, an interaction dataset is simulated. A Gated Recurrent Unit (GRU) neural network architecture is applied in the behavior learning system, which learns a memory representation for performing memory-dependent actions. In an offline evaluation, the GRU system significantly outperformed a without-memory baseline system at generating appropriate memory-dependent actions. Finally, an analysis of the GRU architecture's memory representation is presented. CCS Concepts: • Human-centered computing → Human computer interaction (HCI); • Computing methodologies → Learning from demonstrations; Neural networks;

show abstract

Section: Introductionmentioning

confidence: 99%

Neural-network-based Memory for a Social Robot

Doering

Kanda

Ishiguro

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, there are studies on robots used for older adults in the community, such as using Telenoids for communication support for older adults [9]. Older adults with Alzheimer's disease showed positive reaction to the Telenoid [9]. Another study in Taiwan explored 33 healthy, community-dwelling Taiwanese older adults who responded at a higher level of acceptance toward the more service-oriented robot than the more companion-oriented robot considering attitude, perceived adaptiveness, and perceived usefulness [10].…”

Section: Introductionmentioning

confidence: 99%

“…One example of the intermediary situation between a CR and a community-based elderly is the revitalization of older people through communication exchanges with CRs. There are reports [9] [18] that some older people have become more at peace with themselves by conversing with CRs. It is, therefore, critical that in order to prevent signs and symptoms of possible depression such as withdrawal and isolation, and live an independent life, the focus of using CRs may need to be the provision of life support devices for communication with older people living in the local community.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Intermediary Roles of Public Health Nurses (PHNs) in Utilizing Communication Robots (CRs) in Community Health Care Practice

Kawai¹,

Betriana²,

Tanioka³

et al. 2019

Health

View full text Add to dashboard Cite

Robot technology is expected to reduce the burden of medical professionals, a concern in the super-aged society. The aim of this article is to determine the intermediary roles of Public Health Nurses (PHNs) in using Communication Robots (CRs) in Community Health care. It is necessary to consider who will manage, and how to draw lines of responsibility when a problem occurs when using robots in the future. Regarding the mediator or intermediary role of PHNs in the use of CRs, PHNs are expected to be cognizant of varieties of robots for use with persons of diverse ages and health levels, as well as of robot performances. As one of the community healthcare workers who service the elderly living in the community, the role of PHNs as mediators or intermediaries is to pay attention to ethical and moral issues while working with CRs to manage the health of the community. Lack of understanding of the intermediary role might create possible ethico-moral issues in the future. Therefore, it is critical for PHNs to understand their role as intermediaries. In doing so, it is expected that older people at home will be able to live peaceful lives, as well as be physically and mentally healthy.

show abstract

“…Nevertheless, two issues were realized regarding living with a human-type communication robot as a strategy; to improve cognitive functions and prevent cognitive decline in the elderly [12]. With robot therapy, it was found that only a few aspects of its capabilities, when examined closely, were effects derived from the viewpoints of nursing practices and human care [13] [14]. In this regard, robot therapy has not been generalized, and more descriptions and discussions about its practical utility are required.…”

Section: Introductionmentioning

confidence: 99%

Characteristics of a Transactive Phenomenon in Relationships among Older Adults with Dementia, Nurses as Intermediaries, and Communication Robot

Osaka¹,

Sugimoto²,

Tanioka³

et al. 2017

ICA

View full text Add to dashboard Cite

Healthcare for older adults with dementia is an important healthcare problem in Japan and in other developed countries. Importantly, healthcare workers in Japan are also getting older. In order to address solutions to this problem, using robots is being realized and is starting to assist healthcare and welfare practice needs. The aim of this study was to identify the characteristics of a transactive phenomenon in relationships among older adults with dementia, with nurses as intermediaries and with a cognitive skill-aid robot. Subjects were two institutionalized older adults who were diagnosed with dementia using Hasegawa's Dementia Scale-Revised; a Kabochan (Nodding Kabochan) fixed with a remote-controlled speaker, Pechat (Kabochan with Pechat). Measurements of autonomic nervous activity were done using wearable electrocardiography attached to the subjects for four hours. Heart Rate Variability data were assessed at various frequency bands using a HRV software tool. In a continuously recorded data, interbeat (R-R) intervals were obtained for a 1-min segment using the maximum entropy method. In this study, the two major spectral components of HRV, the variances of the low-frequency (LF: 0.04 -0.15 Hz) band and high-frequency (HF: 0.15 -0.4 Hz) band, were calculated. Activities and behaviors of subjects transacting with Kabochan were observed by the expert nurses and video-recorded. Throughout the transaction period, observations were recorded of patients' behavior, words uttered and over-all contents of the transactive conversation with the Kabochan or Kabochan with Pechat. Identified characteristics were transactive relationship phenomenon; changes in autonomic nervous system activity of persons with How to cite this paper: Osaka, K., Sugimoto, H., Tanioka, T., Yasuhara, Y., Locsin, R., Zhao, Y.R., Okuda, K. and Saito, K. It also showed that autonomic nervous system activity of persons with communication skills is actively changing in older adults with dementia. Conversation of adding Pechat to the Kabochan illustrated that nurses as intermediaries showed emotional conversations as established by effectively manipulating the Pechat. Also, it was revealed that if Kabochan with Pechat uttered words about patient's personal information in a conversation, the patient felt a sense of fear. The researchers suggest that when developing future communication robot for elderly with dementia, it is necessary to consider, for an effective conversation, transactive relationships including nurses as intermediaries. The role functions of these intermediaries have been shown of high versatility, indicating that situations such as these can also be controlled by other healthcare providers such as by occupational therapists.

show abstract

Can We Talk through a Robot As if Face-to-Face? Long-Term Fieldwork Using Teleoperated Robot for Seniors with Alzheimer's Disease

Cited by 37 publications

References 23 publications

Neural-network-based Memory for a Social Robot

Neural-network-based Memory for a Social Robot

The Intermediary Roles of Public Health Nurses (PHNs) in Utilizing Communication Robots (CRs) in Community Health Care Practice

Characteristics of a Transactive Phenomenon in Relationships among Older Adults with Dementia, Nurses as Intermediaries, and Communication Robot

Contact Info

Product

Resources

About