Multi-information fusion human exoskeleton robot control protection system

Abstract

The invention discloses a multi-information fusion human exoskeleton robot control protection system. The system comprises a plurality of inertia measurement assemblies, a plurality of electromyogramsensors, respiration sensors, a depth camera and machine learning processing computers, wherein the inertia measurement assemblies and the electromyogram sensors are installed at arms and legs of a human body, the respiration sensors are installed on a chest, the depth camera is worn on a head, and the machine learning processing computers are installed at any position of the human body; effectivedata acquired by all the sensors at a certain moment are used as input of an LSTM neural network based on a BPTT algorithm, the sum of time consumed by processing a machine learning algorithm throughthe computers and the maximum delay time of receiving control signals by a steering engine at each position of the robot from the moment is used as a time interval, a control signal representing a movement intention of the human body at the moment after the time interval is used as output, a nonlinear function mapping relation which is difficult to express through an analytic expression in engineering is established through neural network training, the movement intention of the human body at the next moment is judged through the action at the moment, so that a function that the correspondingcontrol signal is output is achieved.

Description

technical field [0001] The invention belongs to the technical field of robots, and relates to a control and protection system for a human exoskeleton robot. Background technique [0002] Motor dysfunction such as hemiplegia caused by brain injury has brought a heavy burden to the patient's family and society. Correct and scientific rehabilitation training plays a very important role in the recovery and improvement of limb motor function. Obtaining timely and effective rehabilitation training has become an urgent need for hemiplegic or paraplegic patients, but backward rehabilitation equipment is the main obstacle for patients' rehabilitation. The combination of rehabilitation medicine and robotics improves the effectiveness of rehabilitation training and ensures the intensity of action training, which opens up a new way for the study of new rehabilitation technologies. However, how to identify different motion intentions of the human body and take different measures to prev...

AI Technical Summary

Problems solved by technology

Obtaining timely and effective rehabilitation training has become an urgent need for hemiplegic or paraplegic p

Images