Upper limb exoskeleton robot control method and device based on LSTM neural network

Abstract

The invention provides an upper limb exoskeleton robot control method and device based on an LSTM neural network. A robot arm of an upper limb exoskeleton robot moves along with the upper limb of a human body, and the method comprises the steps: carrying out the processing of the historical movement track data of the human body through a built LSTM neural network prediction model, and predicting to obtain future movement state data of the human body; according to the future movement state data of the human body and a pre-established kinetic model of the upper limb exoskeleton robot, obtaining compensation torque required for controlling the upper limb exoskeleton robot; obtaining human-computer interaction force of the upper limb exoskeleton robot; and processing the compensation torque and the human-computer interaction force, and controlling the upper limb exoskeleton robot according to the processing result. Under the condition that the human-computer interaction force is zero, the upper limb exoskeleton robot can follow the movement of the human body.

Description

technical field [0001] The invention relates to the technical field of exoskeleton robot control, in particular to an upper limb exoskeleton robot control method and device based on an LSTM neural network. Background technique [0002] At present, the main technical directions of research on upper extremity exoskeleton robots at home and abroad are divided into the following categories: one focuses on rehabilitation training, helping patients with upper limb paralysis or muscle damage to recover their functions; the other mainly focuses on lifting and carrying , the fast-growing express logistics field has become an important civilian market for applications, and the shell handling and loading of armored artillery soldiers in plateau anoxic environments has become an important military market for applications. question. [0003] Most of the existing upper limb exoskeleton robot control algorithms are powerful position control algorithm, sensitivity amplification control (SA...

AI Technical Summary

Problems solved by technology

The force position control algorithm has a fast response speed, can detect human interaction force and compensate it in a targeted manner, but has high requirements for modeling accuracy

The Sensitivity Amplified Control (SAC) method follows the user's motion by directly compensating the dynamics of the moving parts, which is essentially an open-loop control method, and it cannot adapt to changing loads due to the lack of feedback about the state information of the human body in the system , and are susceptible to interference

The admittance control

Images