Wellness Robots and the Path to Full Autonomy
Wellness Robots and the Path to Full Autonomy
This paper defines autonomous wellness robots using a six-level Care Robot Autonomy Scale (CRAS) modeled on SAE J3016. It presents Ryan, developed at the University of Denver and commercialized by DreamFace Technologies, as a case study. NIH/NIA-funded data (N=18; 887 hours) reports statistically significant cognitive improvement (SLUMS +2.61, p = 0.015) and a trend toward reduced depressive symptoms (PHQ-9 -2.50, p = 0.073).
The authors introduce a new taxonomy (CRAS) and present longitudinal data from an NIH-funded study on the Ryan robot, while explicitly distinguishing current capabilities (CRAS Level 1-2) from future autonomy goals.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported duration
887 hours
View original evidence
across four wellness-aligned dimensions. We present Ryan, developed initially at the University of Denver and commercialized by DreamFace Technologies, as a case study. NIH/NIA-funded longitudinal evidence (N = 18; 887 hours) shows statistically significant cognitive improvement (SLUMS +2.61, p = 0.015) and a clinically meaningful directional reduction in depressive symptoms (PHQ-9 -2.50, p = 0.073), with no novelty
Open source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
across four wellness-aligned dimensions. We present Ryan, developed initially at the University of Denver and commercialized by DreamFace Technologies, as a case study. NIH/NIA-funded longitudinal evidence (N = 18; 887 hours) shows statistically significant cognitive improvement (SLUMS +2.61, p = 0.015) and a clinically meaningful directional reduction in depressive symptoms (PHQ-9 -2.50, p = 0.073), with no novelty
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org