Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults

Aniol Civit, Antonio Andriella, Alba Martínez, Joan Ars, Aida Ribera, Cristian Barrué, Guillem Alenyà · N/A · 2026

Summary

Abstract Summary

Frailty assessments are crucial to evaluate the risk of adverse events and the health and social care needs of older adults, yet their administration remains resource-intensive and typically relies on coarse clinical outcomes, such as task completion times, which may overlook biomechanical indicators of functional decline. To address this, we present a robotic framework that guides older adults through standardised frailty and fall-risk tests while capturing clinical scores and additional frailty-related metrics, offering a deeper insight into a user's condition. The system uses a Behaviour Tree architecture that coordinates perception, decision-making, interaction, and measurement modules. Using vision-based skeleton tracking, the robot evaluates established clinical tests, including the Short Physical Performance Battery (SPPB) and the Timed Up and Go (TUG). The framework was co-designed with healthcare professionals and evaluated in situ during six months in a rehabilitation centre's research lab with N=81 older adults. Robot-derived measurements were compared against therapist assessments and clinical reference instruments, including a gait analysis walkway and an inertial measurement unit (IMU). Results showed excellent agreement for most test completion times and gait-related parameters ($ICC > 0.9$). And, substantial agreement for the overall SPPB score comparing the robot and the therapist ($k = 0.67$) and moderate agreement comparing the robot and the IMU ($k=0.55$). The findings highlight that social robots can provide reliable and objective frailty assessments in healthcare settings while enabling the collection of relevant mobility indicators beyond conventional outcomes.

Key Points

Frailty assessments are crucial to evaluate the risk of adverse events and the health and social care needs of older adults, yet their administration remains resource-intensive and typically relies on coarse clinical outcomes, such as task completion times, which may overlook biomechanical indicators of functional decline.
To address this, we present a robotic framework that guides older adults through standardised frailty and fall-risk tests while capturing clinical scores and additional frailty-related metrics, offering a deeper insight into a user's condition.
The system uses a Behaviour Tree architecture that coordinates perception, decision-making, interaction, and measurement modules.
Using vision-based skeleton tracking, the robot evaluates established clinical tests, including the Short Physical Performance Battery (SPPB) and the Timed Up and Go (TUG).
The framework was co-designed with healthcare professionals and evaluated in situ during six months in a rehabilitation centre's research lab with N=81 older adults.

User-Centred Design of Robotic Framework

The development of the proposed robotic framework followed a user-centred design process carried out in collaboration with healthcare professionals from the Intermediate Care Hospital Parc Sanitari Pere Virgili.

Rather than defining the system from a technological perspective, the objective was to understand current clinical practice, identify the main limitations of existing frailty assessment procedures, and derive the functional requirements that the robotic system should satisfy.

User-Centred Design of Robotic Framework — Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults — Fig. 2 : On the left, the answers of a group in the workshop session. On the right, all groups are discussing their answers.

Robotic Framework for Autonomous Frailty Assessments

In this section, we present the complete design of the robotic framework used to autonomously conduct frailty and fall-risk assessments. The framework integrates all refinements derived from the co-design process and pilot iterations described in Section III . The architecture of the system is illustrated in Fig. 1 . The framework is composed of four main modules.

First, the Perception Module processes the sensory input and estimates the participant’s skeletal pose using a vision-based tracking system (see Sec. IV-A ).

Robotic Framework for Autonomous Frailty Assessments — Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults — Fig. 3 : Behaviour Tree (BT) for the Frailty Assessment, the blue octagons are selector nodes, the orange rectangles are sequential nodes, the grey circles are action nodes, the green circles are condition nodes, and the white circle is a decorator of type “Failure is Success”, called “Standing Balance Success”, to guarantee that when the participant fails in one of the balance tests, the rest of the balance tests are skipped and the robot moves to the Gait Speed test. Each test is a robot action of the BT.

Experimental Design

This section describes the experimental methodology used to evaluate the proposed robotic framework. The objective of the study is to assess whether the robot can autonomously guide older adults through frailty assessments and obtain measurements comparable to those obtained by a therapist and clinical reference instruments.

As already mentioned, an occupational therapist supervised the experiment for safety and to intervene if something unexpected occurred.

Experimental Design — Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults — Fig. 4 : Experimental setting of the frailty assessment experiment.

Sources and Demonstrations

Figures are reproduced from Civit et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.