cs.HCOct 22, 2026

Navigating human-robot interaction challenges in private and residential aged care homes

Authors: David Ahmedt-Aristizabal, Mohammad Ali Armin, Akila Pemasiri, Harshala Gammulle, Tharindu Fernando, David Silvera-Tawil, Simon Denman

Organizations: CSIRO, Imaging and Computer Vision Group, Canberra, Australia · Queensland University of Technology, School of Electrical Engineering and Robotics, Signal Processing, Artificial Intelligence and Vision Technologies (SAIVT Lab), Brisbane, Australia · CSIRO, Australian e-Health Research Centre, Sydney, Australia · UNSW Medicine & Health, International Centre for Future Health Systems, Sydney, Australia

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

This chapter explores how robotic systems and ambient intelligence can enhance care for older adults in residential aged care (RAC) homes and private homes. Although these settings differ, we frame both as extreme and challenging environments for human-robot interaction (HRI), characterised by cluttered and dynamic layouts, diverse resident needs, and limited on-site technical support. We review embodied and non-embodied systems that assist with daily living, safety monitoring, and social engagement, highlighting hybrid deployments where robots complement fixed and wearable sensors. To ensure these technologies are usable and effective, design considerations consider the cognitive, physical, and social needs of older adults. Interaction design prioritises accessibility for older adults with low digital literacy, using robust but simple voice interfaces, small sets of non-verbal cues, accessible screen-based companions, and safe object handovers. Privacy, trust, and acceptability are addressed via practical strategies such as on-device inference, data minimisation, visible consent controls, and transparent data handling aligned with emerging artificial intelligence (AI) and privacy regulation. Evaluation emphasises real-world metrics including false alarms per day, time to recover from faults, staff workload, and long-term system reliability. We close by outlining open research challenges and future directions for scalable, regulation-ready deployments that support aging with dignity, safety, and independence.

Figures & tables

Figure 1: Example aged care environments illustrating clutter, mobility aids, and variable lighting that shape sensing and interaction: a private home living room (left) and a residential aged care corridor (right).
Figure 2: Concept map of the chapter. Boxes summarise core sections; arrows show the primary reading flow, key cross-section design influences, and how future directions feed back into background assumptions as the field evolves.
DimensionResidential care homesPrivate homes
Supervision and presence of staffStaff are usually on-site, with scheduled rounds and defined escalation pathways. Monitoring can be continuous in some areas and intermittent in others.No formal on-site staff. Support is typically provided by family, visiting carers, or community services, often with long gaps between visits.
Policy and governance contextOperate under aged care regulations, clinical governance, infection prevention policies, and facility-level procedures. Technology must fit accreditation and audit requirements.Governed mainly by consumer protection, tenancy or home ownership arrangements, and general privacy and safety laws. Policies and record-keeping practices vary widely by household.
Environmental variabilityLayouts are somewhat standardised within a facility, with repeated room types and shared areas, although furniture and equipment may still move.Highly heterogeneous and personalised. Floor plans, furniture, lighting, and clutter vary from home to home and change over time.
Available technical and care supportSome access to internal information technology and maintenance teams, plus nursing and care staff who can help reset or reposition devices when trained.Very limited technical support on site. Households rely on remote support, ad hoc local help, or do it themselves, often with low digital literacy.
Mobility aids and assistive equipmentHigh prevalence of walkers, wheelchairs, hoists, oxygen stands, and shared medical equipment in corridors and rooms, with associated trip and collision risks.Mobility aids may be present but are more idiosyncratic and less standardised. Distribution across homes is uneven, and storage locations can change frequently.
Table 1: Contrasting residential care homes and private homes as deployment contexts for HRI.
Figure 3: Example interaction scenario in a residential aged care lounge, showing a mobile social robot engaging an older adult via speech and on-screen prompts, alongside ambient devices such as a smart speaker, wall-mounted tablet, television, and ceiling and wall sensors. The scene illustrates how multimodal interaction, distributed sensing, clutter, mobility aids, and uneven lighting jointly shape design choices.
Figure 4: System architecture: robot and ambient sensors feed a local hub for edge processing and policy enforcement, while clinical summaries flow to cloud/Electronic Health Record (EHR) systems via standard interfaces built on Fast Healthcare Interoperability Resources (FHIR).
Figure 5: Examples of robot form factors used in residential aged care and private homes. Top left: humanoid service robot similar to Pepper. Top right: pet-like therapeutic robot similar to PARO. Bottom left: tabletop social companion similar to ElliQ. Bottom right: mobile telepresence/assistant robot similar to Temi.
Figure 6: Taxonomy of sensors and devices across robotic systems in aged care.
Figure 7: Overview of the practical challenges of HRI in home and aged care, and how existing learning paradigms address these challenges.
Figure 8: Integrative acceptability framework for social robots in RAC and private homes. The four domains perceived effectiveness, burden and usability, ethical and relational fit, and affective engagement represent recurring constructs shared across the TFA, Almere, and TAM/UTAUT model families ( Zhao et al., 2025 ; Felber et al., 2024 ; Felding et al., 2023 ) .
Figure 9: A staged evaluation timeline for assistive and social robots and ambient AI in private and care homes. The emphasis shifts from dataset and simulator metrics to safety, workflow, privacy, and long-term reliability measures as systems progress toward sustained deployment.
Figure 10: Simulation testbeds for assistive robots in aged care. Left: 3D simulation of a residential aged care apartment, with a mobile robot navigating around furniture, mobility aids, and narrow corridors. Middle: top-down occupancy grid and planned trajectory, with marked fall zones, bed areas, and no-go regions. Right: offline evaluation dashboard showing replay of robot–resident interactions alongside safety and performance metrics (distance to residents, detected events, and alert statistics) used to refine policies before real-world deployment.
Figure 11: Schematic overview of five open research challenges in assistive human–robot interaction for private and residential aged care homes: robust multimodal perception, personalisation without privacy loss, governance and evidence, operational and economic sustainability, and equity and cultural competence.
More in this topic

Human-Robot Interaction

Human-robot interaction studies how people and robots communicate, coordinate, and safely work or live together.

See all 452 papers

Explore similar work

CardsList

  1. Towards Equitable Robotic Furnishing Agents for Aging-in-Place: ADL-Grounded Design Exploration

    Mar 15, 2026Hansoo Lee, Changhee Seo, Subin Park +1Assistive RoboticsHuman-Robot Interaction

    Imperial College London, United Kingdom · KIST, Republic of Korea

  2. Perception of Social Robots as Communication Partners in Healthcare for Older Adults

    May 20, 2026Hana Yamamoto, Carlotta Julia Mayer, Charlotte Raithel +5Healthcare RoboticsRobotics

    Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Adenauerring 12, Karlsruhe, 76131, Baden-Württemberg, Germany. · Department of Robotics, Tohoku University, Aramaki Aza Aoba, Aoba-ku, Sendai, 980-8579, Miyagi, Japan. · Institute of Medical Psychology, Heidelberg University, Bergheimer Str. 20, Heidelberg, 69115, Baden-Württemberg, Germany. +2

  3. Effects of Robotic Touch on Older Users During Walking Guidance by a Humanoid Robot

    Jul 10, 2026Leonie Leven, Marko Ackermann, Christian Werner +4Assistive RoboticsHuman-Robot Interaction

    Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany. · Geriatric Center, Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany. · Institute of Medical Psychology, University Hospital Heidelberg, and Ruprecht-Karls University Heidelberg, Heidelberg, Germany. +1