Motion Analysis Lab

Overview

The Motion Analysis Lab (MAL) at Spaulding Rehabilitation Hospital combines state-of-the-art technology with internationally recognized expertise to treat mobility-limiting conditions like cerebral palsy, Parkinson’s, spinal cord injuries, stroke, and TBI. As a national leader in robotics and wearable technology, our mission is simple: to help patients regain their independence. By studying the biomechanics of human movement, we develop ground-breaking solutions to get people moving again.

Research Projects

A vision-based compensatory-posture-detection tool to enhance performance of the BURT® upper-extremity stroke-therapy device

While rehabilitation robotics allows for high-intensity intervention, it is typically limited to one-on-one sessions. This NIH-funded project leverages deep learning and video tracking to enable a single therapist to oversee multiple patients simultaneously during robot-assisted upper-limb therapy. By increasing efficiency, this technology aims to expand access to the high-dose motor practice essential for improved recovery outcomes.

Achieving optimal motor function in stroke survivors via the development and deployment of a sensorized ring

In this NIH-funded collaboration with UMass Amherst, we are developing a sensorized ring designed to monitor and improve hand dexterity in stroke survivors. The device encourages patients to actively use their affected limb during daily activities, bridging the gap between clinical therapy and home life. By fostering consistent, real-world practice, our goal is to significantly enhance functional independence and overall quality of life.

Assessment of a physio-neuro platform (SynPhNe) for home-based retraining of hand function in stroke survivors

Through a collaboration with the Singapore-based company SynPhNe, the MAL is developing innovative solutions for home-based upper-limb rehabilitation. Our team is evaluating the efficacy of technology-assisted training for stroke survivors, focusing on repetitive arm and hand movements. By providing real-time feedback, this approach aims to enhance movement quality and accelerate the recovery of motor function.

Relying on pharmacotherapy to improve motor gains of robot-assisted upper-extremity rehabilitation in chronic stroke survivors

Patients with severe motor impairments often display limited progress in response to traditional stroke rehabilitation. In this collaboration with Neuro-Innovators, we are investigating how pharmacotherapies can improve the results of upper-limb motor retraining. By combining robot-assisted therapy with medications that prime the motor system, we aim to accelerate recovery and help stroke survivors regain the ability to perform activities of daily living.

SmartAssist™: adaptive robotic assistance to maximize patient engagement with the Barrett upper-extremity robotic trainer (BURT)

Robotic therapy has gained significant attention for its ability to deliver the high-intensity, repetitive practice essential for recovery after a stroke. However, the most effective way to control these robots to maximize patients’ motor gains remains a key research question. In this NIH-funded collaboration with Barrett Technology, the MAL is testing advanced control strategies. By refining how robots interact with and assist patients, we aim to identify the optimal "ingredients" for rehabilitation and ensure every survivor achieves their best possible outcome.

StrokeWear: a novel wrist wearable sensor system to promote hemiparetic upper extremity use in home daily life

Stroke survivors often struggle to use their affected arm during daily tasks, which can hinder long-term recovery. In this NIH-funded collaboration with BioSensics, the MAL is utilizing wearable sensors (worn like a wristwatch) to monitor and encourage the use of the stroke-affected limb throughout the day. By increasing both the quantity and quality of arm movement in real-world settings, we aim to drive therapeutic gains that enhance functional independence and overall quality of life.

Markerless technology for clinical gait evaluations in children with cerebral palsy

Evaluating gait abnormalities is a critical step in planning surgeries to improve mobility for children with cerebral palsy. However, traditional motion-capture technology is cumbersome to use, limiting patient access to these evaluations. In this BIRD Foundation-supported collaboration with Newton Tech, the MAL is pioneering the use of markerless technology to streamline gait assessments. We aim to make these evaluations more accessible, ultimately leading to better surgical planning and improved clinical outcomes.

RERC on recreation, sport, and exercise technologies for people with disabilities (RecTech)

Despite their motor impairments, many children with cerebral palsy share a common desire: the ability to run and participate in sports. In this NIDILRR-supported collaboration with the University of Alabama, we are exploring the use of the “frame runner”, a specialized, bicycle-like support system designed to make running accessible. By analyzing the biomechanics of movement, our research identifies the optimal equipment configurations to maximize efficiency and performance. Our goal is to harness this technology to help children achieve their athletic potential and experience the joy of running.

AI-driven earpiece wearable to enhance symptom management, self-care, and caregiver support in patients with neurodegenerative diseases

Patients with neurodegenerative diseases like Parkinson’s and Alzheimer’s often struggle with blood pressure regulation when standing, a condition known as orthostatic hypotension. This sudden drop in pressure can cause dizziness and lead to dangerous, injurious falls. In this collaboration with Lumia and UMass Amherst, we are testing an earpiece sensor that monitors proxy measures of cerebral blood flow. By providing real-time data, this technology allows clinicians to precisely titrate medications, stabilizing blood pressure and significantly reducing fall risks.

Improving the health status of dysvascular amputees by deploying digital prosthetic interface technology in combination with exercise intervention

Individuals with lower-limb amputations due to diabetes often struggle with prosthetic use, as traditional designs can cause skin irritation, blisters, and infections on the residual limb. To address this problem, the MAL is collaborating on an NIH-funded project with Bionic Skins, an MIT spinoff. Together, we are evaluating innovative liner and socket technology designed to maximize residuum health. By prioritizing skin integrity and comfort, this project aims to enhance mobility and quality of life for dysvascular amputees.

Publications

1. Tejwani, R., Payne, J., Velazquez, K., Bonato, P. and Asada, H., 2026. Adaptive robot guidance through real-time compliance estimation and dual-modal control. Communications Engineering
2. Liu, Y., Vergara-Diaz, G., Pugliese, B.L., Black-Schaffer, R., Kim, G., Bonato, P. and Lee, S.I., 2026. Beyond the Wrist: Finger-Worn Accelerometers Enhance Assessment of Post-Stroke Motor Performance. Neurorehabilitation and neural repair, 40(1), pp.16-24.
3. Liu, Y., Pugliese, B.L., Vergara-Diaz, G., O’Brien, A., Black-Schaffer, R., Bonato, P. and Lee, S.I., 2025. Advancing Wearable-Based Upper-Limb Stroke Recovery Assessment to the Clinic: A Comparison of Movement Segmentation Strategies. IEEE Transactions on Neural Systems and Rehabilitation Engineering.
4. Pugliese, B.L., Civeriati, V., Tenforde, A.S., Demarchi, D. and Bonato, P., 2025. Detecting exercise-induced temperature distribution changes at the knee using a wearable array of thermistors. IEEE Access.
5. Corniani, G., Sapienza, S., Vergara-Diaz, G., Valerio, A., Vaziri, A., Bonato, P. and Wayne, P.M., 2025. Remote monitoring of Tai Chi balance training interventions in older adults using wearable sensors and machine learning. Scientific Reports, 15(1), p.10444.
6. Bonato, P., Reinkensmeyer, D. and Manto, M., 2025. Two decades of breakthroughs: charting the future of NeuroEngineering and Rehabilitation. Journal of NeuroEngineering and Rehabilitation, 22(1), p.59.
7. Pugliese, B.L., Angelucci, A., Parisi, F., Sapienza, S., Fabara, E., Corniani, G., Tenforde, A.S., Aliverti, A., Demarchi, D. and Bonato, P., 2025. Development of a wearable sleeve-based system combining polymer optical fiber sensors and an lstm network for estimating knee kinematics. IEEE Transactions on Neural Systems and Rehabilitation Engineering.
8. Vergara-Diaz, G.P., Sapienza, S., Daneault, J.F., Fabara, E., Adans-Dester, C., Severini, G., Cheung, V.C., de Vargas, C.E.R., Nimec, D. and Bonato, P., 2025. Can muscle synergies shed light on the mechanisms underlying motor gains in response to robot-assisted gait training in children with cerebral palsy?. Journal of neuroengineering and rehabilitation, 22(1), p.23.
9. Zandigohar, M., Han, M., Sharif, M., Günay, S.Y., Furmanek, M.P., Yarossi, M., Bonato, P., Onal, C., Padır, T., Erdoğmuş, D. and Schirner, G., 2024. Multimodal fusion of EMG and vision for human grasp intent inference in prosthetic hand control. Frontiers in Robotics and AI, 11, p.1312554.
10. Lee, S.I., Liu, Y., Vergara-Díaz, G., Pugliese, B.L., Black-Schaffer, R., Stoykov, M.E. and Bonato, P., 2024. Wearable-based kinematic analysis of upper-limb movements during daily activities could provide insights into stroke survivors’ motor ability. Neurorehabilitation and neural repair, 38(9), pp.659-669.
11. Bonato, P., Feipel, V., Corniani, G., Arin-Bal, G. and Leardini, A., 2024. Position paper on how technology for human motion analysis and relevant clinical applications have evolved over the past decades: striking a balance between accuracy and convenience. Gait & posture, 113, pp.191-203.
12. Parisi, F., Corniani, G., Bonato, P., Balkwill, D., Acuna, P., Go, C., Sharma, N. and Stephen, C.D., 2024. Motor assessment of x-linked dystonia parkinsonism via machine-learning-based analysis of wearable sensor data. Scientific Reports, 14(1), p.13229.
13. Subramaniam, S., Akay, M., Anastasio, M.A., Bailey, V., Boas, D., Bonato, P., Chilkoti, A., Cochran, J.R., Colvin, V., Desai, T.A. and Duncan, J.S., 2024. Grand challenges at the interface of engineering and medicine. IEEE open journal of engineering in medicine and biology, 5, pp.1-13.
14. Awad, L.N., Jayaraman, A., Nolan, K.J., Lewek, M.D., Bonato, P., Newman, M., Putrino, D., Raghavan, P., Pohlig, R.T., Harris, B.A. and Parker, D.A., 2024. Efficacy and safety of using auditory-motor entrainment to improve walking after stroke: a multi-site randomized controlled trial of InTandemTM. Nature communications, 15(1), p.1081.
15. Nunes, A.S., Yildiz Potter, İ., Mishra, R.K., Bonato, P. and Vaziri, A., 2024. A deep learning wearable-based solution for continuous at-home monitoring of upper limb goal-directed movements. Frontiers in Neurology, 14, p.1295132.