A multi-modal control method for rehabilitation robots based on multi-information fusion

Abstract

The invention provides a rehabilitation robot multimode control method on the basis of multi-information fusion. Biological information and movement information of patients are used as bases for adjusting rehabilitation robot training parameters and control system parameters, and the training parameters are movement instructions of control systems or given signals. The rehabilitation robot multimode control method has the advantages that information of surface electromyogram signals, electroencephalogram signals, electrocardiograph signals, joint angles, joint angular speeds, joint torque, contact force and the like of the patients is acquired, the training parameters and the control system parameters are dynamically adjusted by the aid of information fusion algorithms, training modes areautomatically switched, and accordingly upper and lower limb cooperative intelligent control and flexible control can be carried out on rehabilitation robots; states of the patients can be comprehensively reflected by the acquired biological information and the acquired movement information of the patients, accordingly, the control system parameters can be accurately adjusted, and the rehabilitation robot multimode control method is particularly applicable to the rehabilitation robots with high reliability and safety requirements.

Description

technical field [0001] The invention relates to a multi-modal control method for a rehabilitation robot based on multi-information fusion, which is a multi-modal and collaborative intelligent control strategy based on bio-information and motion information multi-information fusion, such as active and passive, impedance, and power assistance, and is oriented towards personalization. Paradigm's adaptive control strategy belongs to the control field of rehabilitation robots. Background technique [0002] At present, my country has gradually entered an aging society, and the rehabilitation of the elderly and people with limb movement disorders caused by stroke and hemiplegia has become a social problem that needs to be solved urgently. The application and promotion of rehabilitation robots not only improves the efficiency of rehabilitation training for patients, but also solves the problem of insufficient therapists. The current rehabilitation robots have developed various reha...

AI Technical Summary

Problems solved by technology

This method can only be used in a single training mode, and cannot identify the patient's movement intention, and does not take into account the adjustment of the control system parameters when switching between different modes, and the method uses the collected EMG signals to estimate muscle contraction force It is not reliable to adjust the impedance parameters of the control system

The Chinese patent application number 201610243458.9 provides an adaptive control method for lower limb rehabilitation robots that is assisted by the patient's movement needs. By collecting the joint angle and joint angular velocity signals of the patient's lower limbs in real time, the robust variable structure control method is used to achieve the desired trajectory. Adaptive tracking control, although this method can realize continuous and seamless adaptive control of the lower limb rehabilitation robot assisted by the patient's rehabilitation needs, but the information fed back to the control system is only the angle and angular velocity of the joints, and there is no biological information. The adjustment of system parameters may not be accurate

Images