Elsevier

Cognitive Systems Research

Volume 54, May 2019, Pages 258-272
Cognitive Systems Research

Robot-enabled support of daily activities in smart home environments

https://doi.org/10.1016/j.cogsys.2018.10.032Get rights and content

Abstract

Smart environments offer valuable technologies for activity monitoring and health assessment. Here, we describe an integration of robots into smart environments to provide more interactive support of individuals with functional limitations. RAS, our Robot Activity Support system, partners smart environment sensing, object detection and mapping, and robot interaction to detect and assist with activity errors that may occur in everyday settings. We describe the components of the RAS system and demonstrate its use in a smart home testbed. To evaluate the usability of RAS, we also collected and analyzed feedback from participants who received assistance from RAS in a smart home setting as they performed routine activities.

Introduction

The world’s population is aging – the estimated number of individuals age 85+ is expected to triple by 2050 (Alzheimer’s Association, 2017). Currently, an estimated 50% of adults age 85+ need assistance with everyday activities and the annual US cost for this assistance is nearly $2 trillion (Ernst & Hay, 1994). In the case of dementia, cognitively-complex functional activities such as using the phone, preparing meals, taking medications, and managing finances are affected early in the course of the disease (Farias et al., 2006, Perneczky et al., 2006, Schmitter-Edgecombe et al., 2009). Moreover, functional impairment in older adults, or the inability to independently perform these tasks, has been associated with increased health care use, and placement in long-term care facilities (Desai et al., 2004, Marson and Hebert, 2006), number of days in the hospital (Sonn, Grimbyand, & Svanborg, 1996), poorer quality of life (Barberger-Gateau et al., 1993, Peres et al., 2006), morbidity, and mortality (Nourhashemi et al., 2001). According to the National Aging in Place Council (Lerner, 2015), upwards of 90% of older adults prefer to age in place as opposed to moving into a nursing home. Alternative forms of health care are therefore needed to preserve older adults’ independence and quality of life. Technologies that automatically assist with activity of daily living may relieve some of the strain on the health care system as well as caregivers, allowing individuals to remain functionally independent and age in place.

Previous research suggests that smart home technologies, powered by machine learning and automated reasoning, can provide insights into a person’s health status (Cook et al., 2015, Dawadi et al., 2012, Dawadi et al., 2013, Dawadi et al., 2015b, Dawadi et al., 2015a, Dawadi et al., 2016). Information from smart homes can also be harnessed to create reminder systems (Minor, Doppa, & Cook, 2017) as well as automate control of home devices (Mennicken, Vermeulen, & Huang, 2014). What smart homes do not normally bring is a tangible, mobile avatar that partners with the smart home to proactively provide assistance.

In this paper we introduce RAS, a multi-agent robot system that is designed to provide in-home activity support for older adults and others that need assistance to independently perform basic and instrumental activities of daily living (ADLs). RAS represents a collaboration between a smart home and a mobile robot. In this partnership, the smart home tracks activities of daily living and determines when the resident needs assistance. The robot represents an interactive, assistance agent that provides the assistance in the moment, as the need for help is detected. We describe the vision for RAS as well as the details of its design and implementation. We also demonstrate RAS capabilities with a participant performing activities in a smart home testbed.

Section snippets

Related work

Many elder-care robots are already being designed or are in production, representing a wide assortment of appearances and purposes. One such purpose is companionship, exemplified by the robot Paro (Wada, Shibata, Asada, & Musha, 2007). Paro resembles a baby seal and mimics animal-assisted therapy to elicit feelings of joy, happiness, and relaxation from its owner without facing the potential dangers of a real animal such as bites. Pepper is another social companion robot that perceives its

Robot activity support

Memory has a large impact on everyday function, particularly as cognition-affecting diseases progress. RAS represents a technology that aids with everyday function by acting as a cognitive prosthesis. Fig. 1 illustrates the Robot Activity Support (RAS) system components. As shown in the figure, sensors are embedded inside a smart home environment. Based on collected sensor data, models are built of typical activity performance and provide a basis for detecting errors in activity performance.

Evaluation of RAS activity assistance

To demonstrate the ability of RAS to perform activity assistance, we constructed several scenarios in which smart home residents performed activities in a smart apartment testbed. Twenty-six participants were recruited to perform the activities, interact with the robots, and provide feedback on the experience. While each participant performed the activities and interacted with the robot, two experimenters observed from a remote location and a third experimenter stayed on site to assist with the

Discussion and conclusions

A smart environment can use heterogeneous devices to not only monitor and assess resident activities but also intervene to support daily activities. In this project we introduce RAS, a robot activity support system that links smart environment technologies with physical robots to provide aid in completing daily activities. As highlighted in this paper, fully implementing such a system requires synergy between many components including map building, object detection, navigation, user interface,

Acknowledgements

The authors would like to thank Reanne Cunningham and Luke Etherton for their assistance with the initial design of the robot platform and study parameters. We would also like to thank Brian Thomas for his contribution to the website interface. This research is supported in part by the National Institutes of Health under Grant R25EB024327 and by the National Science Foundation under Grant 1734558.

References (59)

  • K.S. Gayathri et al.

    Probabilistic ontology based activity recognition in smart homes using Markov Logic Network

    Knowledge-Based Systems

    (2017)
  • Alzheimer’s Association

    Alzheimer’s disease: Facts and figures

    Alzheimer’s Dement

    (2017)
  • P. Barberger-Gateau et al.

    Four instrumental activities of daily living score as a predictor of one-year incident dementia

    Age and Ageing

    (1993)
  • M. Begum et al.

    Collaboration of an assistive robot and older adults with dementia

    Gerontechnology

    (2015)
  • A. Bisio et al.

    Motor contagion during human-human and human-robot interaction

    PLoS ONE

    (2014)
  • J. Boren et al.

    The SMACH high-level executive

    IEEE Robotics and Automation Magazine

    (2010)
  • P. Bovbel et al.

    Casper: An assistive kitchen robot to promote aging in place

    Journal of Medical Devices

    (2014)
  • Brenon, A., Portet, F., & Vacher, M. (2015.) Using statistico-relational model for activity recognition in smart home....
  • E. Broadbent et al.

    Acceptance of healthcare robots for the older population: Review and future directions

    International Journal of Socical Robotics

    (2009)
  • L. Chen et al.

    Guest editorial: Special issue on situation, activity, and goal awareness in cyber-physical human-machine systems

    IEEE Transactions on Human-Machine Systems

    (2017)
  • Chin, K., Diehl, J., & Norman, V. (1988). Development of an instrument measuring user satisfaction of the...
  • COCO (2018). Overview. Common objects in context. [Online]. Available:...
  • D.J. Cook

    Learning setting-generalized activity models for smart spaces

    IEEE Intelligent Systems

    (2012)
  • D.J. Cook et al.

    CASAS: A smart home in a box

    Computer (Long. Beach. Calif)

    (2013)
  • D.J. Cook et al.

    Analyzing activity behavior and movement in a naturalistic environment using smart home techniques

    IEEE Journal of Biomedical and Health Informatics

    (2015)
  • B. Das et al.

    “One-class classification-based real-time activity error detection in smart homes

    IEEE Journal of Selected Topics in Signal Processing

    (2016)
  • B. Das et al.

    One-class classification-based real-time activity error detection in smart homes

    IEEE Journal of Selected Topics in Signal Processing

    (2016)
  • P. Dawadi et al.

    Automated cognitive health assessment using smart home monitoring of complex tasks

    IEEE Transactions on Systems Man, Cybernetics Part B

    (2012)
  • P. Dawadi et al.

    Longitudinal functional assessment of older adults using smart home sensor data

    IEEE Journal of Biomedical and Health Informatics

    (2015)
  • P. Dawadi et al.

    Modeling patterns of activities using activity curves

    Pervasive and Mobile Computing

    (2015)
  • P. Dawadi et al.

    Automated clinical assessment from smart home-based behavior data

    IEEE Journal of Biomedical and Health Informatics

    (2016)
  • P. Dawadi et al.

    Automated assessment of cognitive health using smart home technologies

    Technology and Health Care

    (2013)
  • A. Desai et al.

    Activities of daily living in patients with dementia: Clinical relevance, methods of assessment and effects of treatment

    CNS Drugs

    (2004)
  • M. Destephe et al.

    Improving the human-robot interaction through emotive movements A special case: Walking

    ACM/IEEE International Conference Human-Robot Interaction

    (2013)
  • Eaton, E., Mucchiani, C., Mohan, M., Isele, D., Luna, J. M., & Clingerman, C. (2016). Design of a low-cost platform for...
  • R.L. Ernst et al.

    The US economic and social costs of Alzheimer’s disease revisited

    American Journal of Public Health

    (1994)
  • Estimote (2018). The physical world. Software-defined [Online]. Available:...
  • Fang, H., Si, H., Chen, L. (2013.) Recurrent neural network for human activity recognition in smart home. In Chinese...
  • S. Farias et al.

    MCI is associated with deficits in everyday functioning

    Alzheimer Disease and Associated Disorders

    (2006)
  • Cited by (86)

    • Gait rehabilitation training robot: A motion-intention recognition approach with safety and convenience

      2022, Robotics and Autonomous Systems
      Citation Excerpt :

      The recent years have witnessed a rapid increase in aged people [1,2]. Meanwhile, along with large amounts of handicapped individuals, there is an increasing need for assisted walking and gait rehabilitation training both in hospitals and at homes [3,4]. Therefore, various kinds of rehabilitation robots have been developed for the elderly and disabled people in hospitals, rehabilitation centers, and other large places.

    • A survey on blockchain, SDN and NFV for the smart-home security

      2022, Internet of Things (Netherlands)
      Citation Excerpt :

      Robots can also support the daily activities of users. For instance, Wilson et al. [27] emphasize the contribution of physical robots to aid in completing daily activities of users, such as senior citizens. Automation is an essential part of the smart home.

    • A comprehensive bibliometric analysis and visualization of smart home research

      2022, Technological Forecasting and Social Change
      Citation Excerpt :

      Most of the scholars in this group are from the same country, and many of them are affiliated with the same institute. For example, Wilson et al. (2019). “Robot-enabled support of daily activities in smart home environments”, published in Cognitive Systems Research, is one of his two highly collaborative (N: 10) articles.

    View all citing articles on Scopus
    View full text