Gait trajectory generation model training method, method for generating trajectory by using model, and equipment

Abstract

The invention provides a gait trajectory generation model training method, a method for generating a trajectory by using a model, and equipment. The gait trajectory generation model training method comprises the steps: acquiring human body parameters of each testee, normal gait trajectories at different speeds and gait unit trajectories of multiple testees at the same speed, wherein the normal gait track comprises a normal gait length and a normal joint track, and the gait unit track comprises a gait unit length and a joint unit track; training an encoder and a decoder by using the normal gaittrajectory; inputting the normal gait track into the trained encoder to obtain normal gait features; inputting the gait unit track into the trained encoder to obtain gait unit features; constructinga gait training set according to the human body parameters, the normal gait length, the normal gait features, the gait unit length and the gait unit features; and training an extreme learning machineby using the gait training set. The application is used for obtaining a model beneficial to recovery of normal gait of a patient with lower limb disorder.

Description

technical field [0001] The present application relates to the field of robot technology, in particular to a training method for gait trajectory generation model, a method and equipment for generating trajectory by using the model. Background technique [0002] Aging has gradually become a common trend in today's society. The elderly are at greater risk of stroke or spinal cord injury, which will lead to loss of walking ability. The survey of patients with stroke or spinal cord injury shows that patients generally worry about their walking ability. The most important of the mobility needs are the ability to walk and stand. Therefore, rehabilitation to help patients walk and stand is particularly important. [0003] At present, the training methods used in rehabilitation therapy are mainly based on parameterized mathematical models, zero-moment points and other methods, but this increases the amount of calculation and complexity of rehabilitation training methods. Contents ...

AI Technical Summary

Problems solved by technology

[0003] At present, the training methods used in rehabilitation therapy are mainly based on parameterized mathematical models, zero moment points and other methods, but this increases the amount of calculation and complexity of rehabilitation training methods.

Images