Tactile communication fault tolerance method and system based on hybrid prediction

Abstract

The invention relates to a tactile communication fault tolerance method and system based on hybrid prediction, and the method comprises the steps: carrying out the prediction compression of to-be-transmitted data during the transmission of data, and only transmitting a data frame with the relative deviation between a prediction value and a real value greater than a dead zone parameter, so as to reduce the amount of data needing to be transmitted; when the data is received, if missing data is encountered, adding 1 to the count, comparing the current count value n with a previously received prediction threshold L, if n is greater than L, predicting the missing data by adopting a zero-order preserving prediction algorithm, and otherwise, predicting the missing data by adopting an LSTM model;and if the data is received, resetting the count value, and obtaining a newly received prediction threshold L while the prediction value is a real value. By setting the continuous prediction threshold, the receiving end can autonomously select a relatively conservative prediction algorithm, the influence brought by accumulated errors caused by continuous prediction is reduced, and the stability ofthe tactile communication system is further improved.

Description

technical field [0001] The invention relates to the technical field of tactile communication, in particular to a fault-tolerant method and system for tactile communication based on hybrid prediction. Background technique [0002] In recent years, with the development of virtual reality (VR) and artificial intelligence, people are gradually unable to satisfy the sense of reality and immersion obtained from vision and hearing, so touch has received more and more attention in the industry. During the transmission of haptic data, transmission errors may be caused by problems such as network jitter, which may lead to instability of the haptic communication system. Traditionally, methods such as zero-order hold and first-order linearity are used to solve this problem, but research has shown that haptic data is not just a simple linear relationship. In recent years, due to its advantages in time series prediction, long short-term memory (LSTM) neural network has been used by resea...

AI Technical Summary

Problems solved by technology

However, this method has the problem of error accumulation in the case of long-term forecasting, and there is still room for improvement in performance

Images