Preliminary development of AGLAIA platform: toward integrated sensorimotor and cognitive assessment

Preliminary development of AGLAIA platform: toward integrated sensorimotor and cognitive assessment Aurora Freccero ReWing s.r.l. & DIBRIS (University of Genoa) Genoa, Italy [email protected] Jessica Carloni Pragma Engineering s.r.l. Perugia, Italy [email protected] Stanislao Grazioso University of Naples Federico II & ETA Bioengineering s.r.l. Naples, Italy [email protected] Valentina Massone ReWing s.r.l. & DIBRIS (University of Genoa) Genoa, Italy [email protected] Riccardo Magni Pragma Engineering s.r.l. Perugia, Italy [email protected] Matteo Moro DIBRIS (University of Genoa) Genoa, Italy [email protected] Jacopo Zenzeri ReWing s.r.l. Genoa, Italy [email protected] Giulia A. Albanese ReWing s.r.l. Genoa, Italy [email protected] Teodorico Caporaso University of Naples Federico II & ETA Bioengineering s.r.l. Naples, Italy [email protected] Maura Casadio DIBRIS (University of Genoa) Genoa, Italy [email protected] Abstract— This study presents the preliminary development of AGLAIA, a unified platform for global assessment integrating sensorimotor and cognitive domains. The robotic device EDUSA® PRO-R, GlovETA with EMG sensorized sleeve and the cognitive platform Nu!Reha are integrated into a single Human-Machine Interface. A protocol was developed and tested with 11 unimpaired participants to validate the platform, establishing the foundations for a subsequent phase focused on data driven personalized training. Keywords—assessment, sensorimotor, cognitive, outcome measures I. INTRODUCTION Personalized neurorehabilitation requires a comprehensive, multimodal assessment that integrates both sensorimotor and cognitive functions. In clinical populations, upper limb assessment benefits from validated outcome measures addressing both impairment and activity levels. In this framework, wrist joint perception and motor control are fundamental for effective planning, execution and adaptation of movements. Consequently, quantitative measures of proprioception, wrist kinematics and dynamics are essential to obtain a complete functional profile [1]. At the same time, muscle activation and fatigability provide non-redundant information on motor control and task tolerance. Surface EMG (sEMG) features (e.g., RMS, median frequency) and objective fatigability metrics reflect performance decline and would represent a valuable complement to kinematic outcomes [2]. At the cognitive level, executive functions, attention and visuospatial working memory interact with motor planning and performance. Standardized tools such as Corsi Block Tapping [3] provide indicators suitable for integrated rehabilitation workflows. Systematic reviews highlight the need for reliable tools to support longitudinal monitoring and ensure comparability across studies [2]. It has been demonstrated that robotic devices can provide quantitative and repeatable results when integrated into clinically meaningful protocols. This supports the development of platforms that combine robotic sensors, EMG and cognitive testing into a single process [4]. Motivated by this evidence, the aim of the present study is to advance a unified assessment framework that integrates complementary technologies for sensorimotor and cognitive assessment, ensuring synchronized acquisition across devices and extracting clinically meaningful measures to support user profiling and moving towards future adaptive and personalized training. II. METHODS A. AGLAIA Platform: Devices and Assessment Modalities With the goal of advancing towards a global assessment framework, the study introduces the platform AGLAIA, which integrates three complementary technologies to enable multiple assessment modalities. The platform integrates: • EDUSA® PRO-R [5], an end-effector robotic device developed and commercialized by ReWing s.r.l. (Genoa, Italy) for upper limb sensorimotor training and assessment, providing quantitative outcome measures from kinematic and dynamic indicators, proprioception matching and isometric force tasks. • GlovETA [6], a soft robotic glove with a sensorized forearm sleeve (sEMG) developed by ETA Bioengineering s.r.l. (Naples, Italy), capturing hand-fingers kinematics and muscular activation to characterize fine motor control. • Nu!Reha [7], a software platform developed by Pragma Engineering s.r.l. (Perugia, Italy) that implements validated neuropsychological tasks (e.g., Stroop) in a digital version. Figure 2: bla bla Figure 1: (a) HMI platform interface; (b) Spatio-Temporal Coordination task with EDUSA PRO-R and GlovETA syncronization; (c) Coordination and Attention activity with Nu!Reha and GlovETA syncronization. a. b. c. 2025 I-RIM Conference October 17-19, Rome, Italy ISBN: 9788894580570 10.5281/zenodo.17629886 245 B. AGLAIA Platform: Technologies Integration and Synchronization Technologies integration was achieved through the unified platform AGLAIA, which coordinates all devices within a common Human Machine Interface (HMI), where EDUSA® PRO-R works as the core unit, managing all the activities in a unique protocol. Cross device synchronization is enabled by digital trigger events and APIs start and finish calls: at start, EDUSA® PRO-R delivers both the API command and the digital trigger to reset clocks; at finish, devices compute their respective outcomes and send them to the AGLAIA platform where they are stored anonymously in a unified database. III. RESULTS A. Assessment Protocol and Outcome Measures The designed assessment protocol, described in Tab.1, has a total duration of 60 minutes and includes 13 activities, chosen to evaluate upper limb functions across sensorimotor and cognitive domains, while remaining feasible within a single session. For each activity, the most appropriate outcome measures were selected to be computed and extracted to quantify participant’s performance. On the sensorimotor side, EDUSA® PRO-R is used to assess wrist range of motion, position sense, motor coordination and force generation. During coordination and force tasks, GlovETA is integrated to capture forearm muscle activations via sEMG, but it is also used alone to assess fingers range of motion. For the cognitive domain, we selected tests correlated to planning and motor execution implemented on Nu!Reha to assess visuospatial working memory, selective attention, cognitive flexibility, hand-eye coordination, sustained and selective attention, and interference control. Three cognitive tasks are performed by integrating GlovETA to also acquire hand kinematics and forearm muscular activations. TABLE 1: ASSESSMENT ACTIVITIES AND SELECTED OUTCOME MEASURES Activity Outcome Measure Domain Wrist Active Range of Motion Active RoM [deg] Sensorimotor Wrist Passive Range of Motion Passive RoM [deg] Sensorimotor Proprioceptive Evaluation Matching Error [deg] Sensorimotor Spatio-Temporal Coordination Tracking Error [deg] Path Rate [%] Co-Contraction Index [/] Sensorimotor Isometric Force Min Max Force [N] Co-Contraction Index [/] Sensorimotor Finger Active Range of Motion Active RoM [deg] Sensorimotor Finger Passive Range of Motion Passive RoM [deg] Sensorimotor DigiCorsi Span [/] Reaction Time [s] Cognitive Coordination and Attention Total Score [/] Cognitive Digital Agnosia Reaction Time [s] Cognitive Trail Making Execution Time A [s] Execution Time B [s] Cognitive Auditory Attention Total Score [/] Cognitive DigiStroop Total Score [/] Cognitive B. Pilot Validation with Unimpaired Participants A pilot study was conducted on eleven unimpaired participants (33.1±10.2 y.o., 6 males, 5 females) to verify platform robustness. Tests were executed following the multidomain (sensorimotor and cognitive) protocol previously described. AGLAIA platform enables protocol execution across different technologies, which were fully managed and synchronized via dedicated APIs and triggers. The synchronization was successful, providing reliable time alignment (less than 10 ms) essential for computing reliable outcome measures from the three devices. Outcomes from sensorimotor and cognitive activities were stored anonymously in a unified database, with all results accessible through the EDUSA PRO-R dashboard. Multi device execution, timing alignment and outcome extraction were feasible and robust across the entire assessment protocol. All subjects successfully executed the entire assessment (zero activities not completed), tasks were correctly proposed and the stored outcome measures were reliable. IV. DISCUSSIONS The development of AGLAIA platform and the first validation tests establish a reliable multidomain pipeline, laying the foundation for introducing data driven personalization without altering the clinical workflow. Next steps include the use of stored outcome measures as input of an algorithm used to compute the optimal parameters of a training task, implemented as a tracking activity performed with EDUSA® PRO-R, in which different challenges can be introduced based on the performance achieved during the assessment. ACKNOWLEDGMENT This work was supported by the European Union - NextGenerationEU project ‘‘RAISE - Robotics and AI for Socio-economic Empowerment’’ (ECS00000035). REFERENCES [1] U. Proske and S. C. Gandevia, “The proprioceptive senses: their roles in signaling body shape, body position and movement, and muscle force,” Physiol. Rev., vol. 92, no. 4, pp. 1651–1697, Oct. 2012, doi: 10.1152/physrev.00048.2011. [2] G. Albanese, V. Falzarano, M. Holmes, P. Morasso, and J. Zenzeri, “A Dynamic Submaximal Fatigue Protocol Alters Wrist Biomechanical Properties and Proprioception,” Front. Hum. Neurosci., vol. 16, p. 887270, May 2022, doi: 10.3389/fnhum.2022.887270. [3] R. P. Kessels, M. J. van Zandvoort, A. Postma, L. J. Kappelle, and E. H. de Haan, “The Corsi Block-Tapping Task: standardization and normative data,” Appl. Neuropsychol., vol. 7, no. 4, pp. 252–258, 2000, doi: 10.1207/S15324826AN0704_8. [4] G. A. Albanese et al., “Efficacy of wrist robot-aided orthopedic rehabilitation: a randomized controlled trial,” J. Neuroengineering Rehabil., vol. 18, no. 1, p. 130, Aug. 2021, doi: 10.1186/s12984-02100925-0. [5] I. Pippo et al., “Existing Devices in Wrist Rehabilitation Robotics: Mechanical Design, Control Systems, and User Requirements for Commercialization,” p. 8, Sept. 2024, doi: 10.1109/MESA61532.2024.10704903. [6] “GLOVETA,” ETA Bioengineering. [Online]. Available: https://www.etabioengineering.com/gloveta/ [7] “Pragma Engineering - Nu!Reha.” [Online]. Available: http://www.pragmaeng.it/ 246