Sliding prediction method and device based on force sensor, electronic equipment and storage medium

Abstract

The invention discloses a sliding prediction method and device based on a force sensor, electronic equipment and a storage medium. The method comprises the following steps of collecting a force sensordata signal; serving the force sensor data signal as an input of a long-short-term memory network LSTM, and obtaining an output result after testing the force sensor data signal through an LSTM network training model; and predicting the sliding of the force sensor according to the output result. Through the prediction method disclosed by the invention, the sliding prediction is realized through adata driving learning way for performing training model testing and judgment on the force sensor data signal by combining the LSTM network without performing thread modification and adjusting on a specific object, the better adaptability is provided, and the result accuracy rate is improved; and the judgment is performed according to the force change of the force sensor and before the occurrenceof the relative movement.

Description

technical field [0001] The invention relates to the field of sensors, in particular to a sliding prediction method, device, electronic equipment and storage medium based on a force sensor. Background technique [0002] At present, sliding prediction is the key technology for robots to achieve stable grasping. Predicting the current grasping state through sensor feedback can help control robots to achieve more stable and reliable grasping actions. [0003] At present, sliding prediction can be divided into force, tactile perception and visual perception according to different perception methods. Force and tactile perception Through the force and tactile feedback, since there will be force changes and relative displacements between the object and the sensor when relative sliding occurs, it can be judged according to the time domain and frequency domain information of the data, and can be determined by force, displacement, vibration and other characteristics. determination. V...

AI Technical Summary

Problems solved by technology

[0007] The above technical solutions need to modify and adjust the threshold for specific items, poor adaptability, and the accuracy of prediction results is not high

Images