Abstract
Assist-as-needed (AAN) control strategy is applied in robot-aided therapy to promote the subject's engagement with minimal assistance. Current methods are based on physical measurements or employ a model to estimate the subject's engagement, which indirectly reflects the physiology of the subject or needs a complicated modeling process. Besides, manual adjustments are required to tune the parameters of the AAN controller to adapt to the estimated engagement of subjects. Such two drawbacks of previous studies have limited their effectiveness for promoting the subject's engagement during the training. In this paper, we propose an engagement enhancement method based on Bayesian Optimization for the adaptive AAN controller. Firstly, we evaluate the subject's engagement by using sEMG-based muscle activation, which directly relates to the physiology of the subject and eliminates the need for complicated modeling of engagement. Next, Bayesian optimization, which is tolerant of noisy measurements and human adaptation, is used to search for the optimal parameter of the AAN controller for each training trial. Finally, we conduct a study with sixteen healthy human subjects to verify the effectiveness of the proposed method. The experimental results showed that subjects’ engagement in the experiment group improved more significantly and was maintained at a higher level than that in the control group during the training. The performance improvement after the training obtained in the experiment group was higher than that in the control group (45.42% v.s. 30.40%). The experimental results indicate that the proposed method may be promising for transferring to the rehabilitation of post-stroke patients.
Highlights
R EHABILITATION therapy is beneficial to neural plasticity and functional recovery of patients suffering from stroke, cerebral injury, or spinal cord injury
To overcome the aforementioned drawbacks of the existing AAN controller-based robotic training approaches, we propose an engagement enhancement method based on Bayesian optimization for adaptive AAN controllers
The main contributions of this study are twofold: (1) We apply sEMG-based muscle activation to evaluate the subject’s engagement in the AAN controller, which directly relates to the physiology of the subject and eliminates the need for complicated modeling of engagement
Summary
R EHABILITATION therapy is beneficial to neural plasticity and functional recovery of patients suffering from stroke, cerebral injury, or spinal cord injury. One of the most critical areas of research in robot-aided therapy is the development of control strategies [2]. There is evidence that passive movements are insufficient to alter motor recovery but active participation induces neural plasticity [3]. To this end, assist-as-needed (AAN) control strategy has been proposed for promoting the engagement of subjects with minimal assistance in the robot-aided therapy [4]. To maximize engagement during the training and prevent frustration, it is crucial to maintain an individualized and “human-in-the-loop” assistance level for the robotic rehabilitation [5]. One is the estimation of subjects’ engagement level, and the other is the adaptive tunning method for the assistance level, which depends on the hyper-parameters of the AAN controller
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
