Abstract
In upper limb rehabilitation training by exploiting robotic devices, the qualitative or quantitative assessment of human active effort is conducive to altering the robot control parameters to offer the patients appropriate assistance, which is considered an effective rehabilitation strategy termed as assist-as-needed. Since active effort of a patient is changeable for the conscious or unconscious behavior, it is considered to be more feasible to determine the distributions of the passive resistance of the patient's joints versus the joint angle in advance, which can be adopted to assess the active behavior of patients combined with the measurement of robotic sensors. However, the overintensive measurements can impose a burden on patients. Accordingly, a prediction method of shoulder joint passive torque based on a Backpropagation neural network (BPANN) was proposed in the present study to expand the passive torque distribution of the shoulder joint of a patient with less measurement data. The experiments recruiting three adult male subjects were conducted, and the results revealed that the BPANN exhibits high prediction accurate for each direction shoulder passive torque. The results revealed that the BPANN can learn the nonlinear relationship between the passive torque and the position of the shoulder joint and can make an accurate prediction without the need to build a force distribution function in advance, making it possible to draw up an assist-as-needed strategy with high accuracy while reducing the measurement burden of patients and physiotherapists.
Highlights
For patients suffering impaired upper limb function after stroke, adopting rehabilitation robots for rehabilitation exercise can reduce labor burden of therapists, with more accurate measurement of the position and force information in the rehabilitation training
A shoulder passive torque prediction method based on Backpropagation neural network (BPANN) was proposed to expand the shoulder passive torque-angle relationship
Experiments were carried out to measure the kinematics and torques on the shoulder joint of 3 healthy subjects, and the measurement data was used as training set and testing set of a three-layer BPANN to test the prediction effect
Summary
For patients suffering impaired upper limb function after stroke, adopting rehabilitation robots for rehabilitation exercise can reduce labor burden of therapists, with more accurate measurement of the position and force information in the rehabilitation training. Not all patients lost all their active motion abilities; patients retaining part of the motion abilities can achieve significantly improved training effect of their active participation in the rehabilitation training [3]. As revealed from existing studies, overdose robotic assistance will reduce the patient’s active force output and energy consumption in rehabilitation training, and the patient’s limbs appear to be “slacking,” probably reducing the efficiency of rehabilitation [4]. Compared with the stiff control strategy that moves the patient’s limbs along a desired trajectory in the training process given the patient’s active motion ability, the socalled “assist-as-needed” strategy that provides only the minimum assistance required to maximize the patient’s active participation can enhance the efficiency of rehabilitation [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
