Intelligent Assistive Technology and Systems Lab - click to go to homepage
IATSL develops assistive technology that is adaptive, flexible, and intelligent, enabling users to participate fully in their daily lives. Learn more about our research

Visit us:

Room 438

500 University Ave.

Toronto, Canada

P 416.946.8573

F 416.946.8570


Send us mail:

160 - 500 University Ave.

Toronto, ON, M5G 1V7



email us!


Follow IATSL on Twitter


Intelligent Haptic Robotic System for Upper Limb Rehabilitation After Stroke

Keywords: Haptic, stroke, automated, rehabilitation.

In collaboration with: Quanser

Overview of Research

As many as 75% of those with a stroke live with some residual disability. The loss of upper limb movement control, affecting the completion of daily activities, is common after stroke. It is estimated that 65% of stroke survivors are unable to use their affected upper limb in daily activities such as pushing on a chair to stand up, getting into bed, or dressing themselves.

Stroke survivors work with rehabilitation therapists to improve movement control and function in the affected limb and to increase participation in daily activities. In the early stages of recovery, some stroke survivors have very little control of their affected upper limb and require extensive practice and assistance. Consequently, therapists must spend significant amounts of time guiding stroke survivors through repetitive exercises and functional activities, which can be challenging for both and sometimes impossible given the large caseloads of therapists and the lack of outpatient therapy for some stroke survivors.

The goal of this research is to develop an intelligent haptic robotic rehabilitation system to augment treatment of the upper limb after stroke. This system is also aimed to be low cost and portable so that multiple systems can be available for use in a hospital clinic and so that systems can be usable for home-based therapy.

Through three prototype iterations, using a user-centred design approach, we have developed a system ready for further clinical evaluation. The intelligent haptic robotic rehabilitation system has three research and development focus areas:

  1. A robotic device that includes a haptic robotic arm that enables 2 degrees of freedom (2DoF) planar assistive or resistive movements,
  2. An artificial intelligence (AI) controller that automatically adapts exercise parameters according to the stroke survivor’s performance, and
  3. A virtual environment and graphical user interface (GUI) that provides interactive activities and games to motivate stroke survivors to engage and participate in therapy and that provides performance feedback.

Figure 1 shows the intelligent haptic robotic rehabilitation system set up in a hospital-based clinic.

Current Research

    • Improvement of AI controller to include user performance and a stroke survivor model of fatigue
    • Development of a postural monitoring tool to identify and provide feedback on compensatory postures of stroke survivors during exercises
    • Improvement of the therapist GUI and performance report generation tools 
    • Clinical usability evaluation of system with stroke survivors and therapists in a clinic setting

    Picture of haptic robot with components labeled

    Figure 1. Set up of the intelligent haptic robotic rehabilitation system in a hospital-based clinic (click to enlarge).



    1. Huq, R., Wang, R., Lu, E., Lacheray, H., and Mihailidis, A. (2013, in review) Development of a Fuzzy Logic Based Intelligent System for Autonomous Guidance of Poststroke Rehabilitation Exercise.  13th International Conference on Rehabilitation Robotics (ICOR), June 24-26, Seattle, WA.
    2. Grover, L., Arcelus, A., Wang, R., Huq, R., Zabjek, K., Hebert, D. and Mihailidis, A. (2013). Investigation of EMG fatigue patterns while using an upper limb rehabilitation robotic device. RESNA 2013, June 22-24, Bellevue, WA.
    3. Wang, R., Hebert, D., Huq, R., Lu, E. and Mihailidis, A. (2012). Working towards clinical applicability and implementation of a robotic stroke rehabilitation system for the upper limb. 3rd Canadian Stroke Congress, Sep 29-Oct 2, Calgary, AB.
    4. Taati, B., Wang, R., Huq, R., Snoek, J. and Mihailidis, A. (2012). Vision-based posture assessment to detect and categorize compensation during robotic rehabilitation therapy. The 4th IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob 2012), June 24-28, Rome, Italy.
    5. Huq, R., Lu, E., Wang, R., and Mihailidis, A. (2012). Development of a Portable Robot and Graphical User Interface for Haptic Rehabilitation Exercise. The 4th IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob 2012), June 24-28, Rome, Italy.
    6. Lu, E., Wang, R., Huq, R., Gardner, D., Karam, P., Zabjek, K., Hébert, D., Boger, J. and Mihailidis, A. (2012). Development of a robotic device for upper limb stroke rehabilitation: A user-centered design approach. Paladyn. Journal of Behavioral Robotics, 2(4), 176-184.
    7. Kan, P., Huq, R., Hoey, J., Goetschalckx, R. and Mihailidis, A. (2011) The development of an adaptive upper-limb stroke rehabilitation robotic system. Journal of Neuroengineering and Rehabilitation, 8(33). doi:10.1186/1743-0003-8-33.
    8. Huq, R., Kan, P., Goetschalckx, R., Hébert, D., Hoey, J. and Mihailidis, A. (2011). A Decision-Theoretic Approach in the Design of an Adaptive Upper-Limb Stroke Rehabilitation Robot. In the International Conference of Rehabilitation Robotics (ICORR), June 29 - July 1, Zurich, Switzerland, pp. 589-596.
    9. Lu, E., Wang, R., Hebert, D., Boger, J., Galea, M., and Mihailidis, A. (2011). The development of an upper limb stroke rehabilitation robot: Identification of clinical practices and design requirements through a survey of therapists. Disability and Rehabilitation: Assistive Technology, 6(5), 420-431.
    10. Kan, P., Hoey, J. and Mihailidis, A. (2008) Automated upper extremity rehabilitation for stroke patients using a partially observable Markov decision process. In AAAI 2008 Fall Symposium on AI in Eldercare: New Solutions to Old Problems, Arlington, VA.
    11. Kan, P., Boutilier, C., Hebert, D., Hoey, J., Boger, J. and Mihailidis, A. (2007). The preliminary development of a POMDP controller for upper-limb stroke rehabilitation. Festival of Intl Conf on Caregiving, Disability, Aging and Technology (FICCDAT): The 2nd Intl Conf on Technology and Aging (ICTA), Toronto, Canada.
    12. Lam, P., Hebert, D., Boger, J., Lacheray, H., Gardner, D., Apkarian, J. and Mihailidis, A. (2008). A haptic-robotic platform for upper-limb reaching stroke therapy: Preliminary design and evaluation results. Journal of NeuroEngineering and Rehabilitation, 5(15). doi: 10.1186/1743-0003-5-15.

    Funding Sources

    Industrial Partner

    Research Team

    Alex Mihailidis, Ph.D., P.Eng. (University of Toronto)

    Elham Dolatabadi Ph.D., (Toronto Rehabilitation Institute)

    Derek Zhi (Toronto Rehabilitation Institute)

    Michelle Lukasik (Toronto Rehabilitation Institute)

    Rosalie Wang, B.Sc.(OT), PhD (Toronto Rehabilitation Institute)

    Rajibul Huq, Ph.D., P.Eng. (University of Toronto) Rosalie Wang, B.Sc.(OT), PhD (Toronto Rehabilitation Institute)

    Babak Taati, Ph.D., P.Eng. (Toronto Rehabilitation Institute)

    Jacob Apkarian, Ph.D. (Director R&D, Quanser)

    Debbie Hébert, M.Sc. (Occupational Science and Occupational Therapy, University of Toronto)

    Jesse Hoey, Ph. D. (Computer Science, University of Toronto)