Lower limb motion intention prediction method based on attention mechanism

Abstract

The invention relates to a lower limb motion intention prediction method based on an attention mechanism, which comprises the following steps of: 1, acquiring a gait signal in a lower limb motion process, performing normalization processing on the gait signal, and dividing training set data and test set data; step 2, constructing a prediction model, wherein the prediction model comprises an input module, a convolutional neural network module, a long-short term memory neural network module and an attention mechanism, and when the input module, the convolutional neural network module, the long-short term memory neural network module and the attention mechanism are connected in sequence, an output result of the attention mechanism passes through a full connection layer; 3, pre-training the prediction model by using the training set data, and determining a time step length; then training the pre-trained prediction model; and 4, applying the trained prediction model to prediction of the motion intention of the lower limbs. According to the method, the position with obvious change of the joint angle is amplified through the attention mechanism, and the prediction error of the joint angle can be effectively reduced.

Description

technical field [0001] The invention belongs to the technical field of gait pattern recognition, and in particular relates to a lower limb movement intention prediction method based on an attention mechanism. Background technique [0002] Motion intention is the key part to realize the precise tracking of human body motion by exoskeleton, and finally realize the synchronous motion of human and machine. Although research on motion intentions in the field of exoskeletons has achieved certain results in recent years, the technology is still immature. The key to motion intention recognition is to accurately predict the gait signals of the subsequent time series based on the gait signals of the current time series, so as to guide the human-machine synchronous movement. [0003] Machine learning methods based on gait signals are widely used in the field of gait recognition. Generally, various sensors such as acceleration, angular velocity, and pressure are worn on the human body ...

AI Technical Summary

Problems solved by technology

[0006] The gait signal changes periodically, and the change of the gait signal is more obvious at the alternation of the previous phase and the next phase of the gait cycle. Since the network structure of the above method is relatively simple, for the gait signal where the change is obvious The feature extraction effect is poor, so the prediction accuracy is generally low

Images