Man-machine skill transmission system based on multi-information fusion

Abstract

The invention discloses a man-machine skill transmission system based on multi-information fusion. The man-machine skill transmission system comprises a computer connected with a robot, a sensor mounting bracket, and a somatosensory sensor, a binocular vision camera, a human body electromyographic signal acquisition instrument, a man-machine skill transmission adjusting interface and a monitoring display which are connected with the computer respectively, wherein the somatosensory sensor, the binocular vision camera, the human body electromyographic signal acquisition instrument and the man-machine skill transmission adjusting interface are mounted on the sensor mounting bracket respectively; the human body electromyographic signal acquisition instrument is connected with a human body by a measurement electrode; the somatosensory sensor is arranged on a joint of the human body. According to the system, man-machine interaction of a service robot is sufficient and diversified control policies are provided; a plurality of sensors are convenient to mount and the investment cost is remarkably reduced.

Description

Technical field [0001] The invention relates to the field of robot intelligent learning and control, in particular to a human-machine skill transfer system based on multi-information fusion. Background technique [0002] Service robot technology has developed rapidly in recent years and has received increasing attention. Compared with traditional industrial robots, service robots serve people's daily lives and are therefore closer to humans, requiring safe, stable and reliable human-machine interaction with service robots. At the same time, due to the diversity of human needs, service robots are required to have flexible human-like behavior characteristics. The characteristics of the above-mentioned service robots and people’s expectations for service robots have prompted researchers to find a convenient, simple, stable and low-cost human-computer interaction technology that can realize the stable transfer of human skills to the service robot, making the service robot better Se...

AI Technical Summary

Problems solved by technology

The installation accuracy of these sensors will cause many adverse effects on the service effect, such as the inability to realize human-machine synchronization, distortion of human-computer interaction, etc.; in addition, due to the wide variety of sensors on the market, different sensor installation interfaces are required, and most of them are non-standardized interfaces. Custom-made separately, brings a lot of inconvenience to the experiment debugging, spends considerable time and money

Most of the existing vision sensors are fixed on the wall or the beam of the room, which is time-consuming and laborious to install, and sometimes requires professional technicians to drill holes, etc.

As a fixed experimental platform, these sensors fixed at these positions may not affect the normal experimental tasks. However, once the sensor accuracy drops due to environmental influences such as light, vibration, etc., it is necessary to manually correct the sensor installation error. Obviously, due to improper installation Convenience leads to an increase in the difficulty of adjustment. In addition, when the number or types of sensors need to be increased, the drawbacks of the lack of scalability of the traditional installation method are more obvious

In addition, some experimental occasions are not suitable for wall drilling or hoisting operations, such as relatively open areas or too many indoor wiring, construction may easily cause accidents

Images