A Care Robot with Ethical Sensing System for Older Adults at Home
This academic paper presents the development of an older adult-guided and caregiver-monitored care robot named Dori, designed for prefrail and frail older adults living at home. The study utilizes a human-centered artificial intelligence (HCAI) framework and focus group interviews with caregivers and medical staff to establish ethical sensing services that balance health monitoring needs with human dignity, privacy, and autonomy. Specifically, the robot uses MediaPipe Pose to extract joint coordinate information rather than storing raw camera images, protecting user privacy during activities such as fall detection and medication management.
Summary and content fields are drawn from the document text and are pending editorial review.
Who issued it
Who it governs
Researchers, developers, and healthcare practitioners interested in the ethical design and implementation of socially assistive robots for older adults.
What the document contains
The document covers the design, ethical considerations, software architecture, and hardware implementation of an elder care robot utilizing human pose recognition and human-centered AI principles for home-based monitoring and assistance.
It does not provide commercial manufacturing standards, national regulatory mandates, or legal enforcement mechanisms for care robots.
- The study develops an older adult-guided and caregiver-monitored care robot named Dori for prefrail and frail older adults living at home.
- Focus group interviews with caregivers and medical staff informed the design of five key service areas: cognitive support, emotional support, physical activity support, medication management, and caregiver management.
- Ethical judgments regarding dignity, privacy, and autonomy differed between caregivers and medical staff, leading to a user-controlled design where continuous personal video data is not stored.
- The robot utilizes Google's MediaPipe Pose to extract joint coordinate information from camera images, protecting personal privacy while successfully detecting movements and falls.
- When users refuse medication or monitoring, the robot is programmed to confirm intentions up to three times before logging and notifying guardians or medical staff.
· Introduction · Related Work · Designing of a Care Robot with Ethical Sensing of Human Poses · Development · Conclusions
How it scores
Each score is backed by a quote verified against the document text. Editorial review has not yet confirmed them.
Accountability
3/5Clear responsibility for AI outcomes
The AI research community is moving toward HCAI to calm fears of out-of-control robots, clarify responsibility for failures, and reduce biased decisions that lead to unfair treatment of minorities.
3. Designing of a Care Robot with Ethical Sensing of Human Poses
screening score · 2026-10-24
Fairness
1/5Non-discrimination and equitable treatment
reduce biased decisions that lead to unfair treatment of minorities.
3. Designing of a Care Robot with Ethical Sensing of Human Poses
screening score · 2026-10-24
Human Dignity
4/5Respect for the inherent worth of persons
Therefore, the pose recognition technology adopted in the present work uses only joint coordinate information extracted from camera images and thus is advantageous for protecting human dignity and personal information.
Abstract
screening score · 2026-10-24
Human Oversight
4/5Humans remain in control of consequential decisions
In this study, we develop an older adult-guided and caregiver-monitored robot using sensors and machine learning (ML) for use at home in the near future.
1. Introduction
screening score · 2026-10-24
Privacy
4/5Protection of personal data and private life
In the service setting unit, users can enter their own settings and receive real-time video processing without having their video data stored separately through the service providing unit.
5. Conclusions
screening score · 2026-10-24
Transparency
1/5Openness about how AI systems work and are used
transparency, controllability, value adjustment, responsibility, and human dignity
2. Related Work
screening score · 2026-10-24
Enforcement
0/5Consequences and compliance mechanisms with real force
screening score · 2026-10-24
Impact Assessment
3/5Required assessment of an AI system's risks/impacts before or during use
In this study, we develop an older adult-guided, caregiver-monitored robot, Dori, which can detect and recognize movement by sensing human poses in accordance with two factors from the human-centered artificial intelligence (HCAI) framework.
Abstract
screening score · 2026-10-24