Man-machine co-driving system based on hybrid brain-computer interface and control method thereof

Abstract

The invention discloses a man-machine co-driving system based on a hybrid brain-computer interface and a control method thereof, which can realize two modes of robot complete brain control and man-machine co-driving control, highlights a human core effect in robot control, makes full use of human experience intelligence and intelligent robot accurate perception to carry out decision making, and assists a user to carry out safety control, a user can receive feedback information, the system can continuously learn a user operation mode, continuously accumulate operation data and data during VR scene training can be used for improving system performance, man-machine interaction is safer and more efficient, man-machine interaction coupling is enhanced, and the method has important application value in man-machine co-driving and intelligent robots. Compared with a single-mode BCI system, the hybrid BCI system has multiple control instructions, better operability and robustness and more diversified operation control, the man-machine interaction mode better conforms to practical application, and the problems that a brain-controlled robot is single in operation mode and control instructionsare too simple are solved.

Description

technical field [0001] The invention relates to the technical field of intelligent robots, in particular to a human-machine co-driving system based on a hybrid brain-computer interface and a control method thereof. Background technique [0002] Brain-Computer Interface (BCI) is a multidisciplinary technology that extracts specific bioelectrical signals directly from the brain and effectively decodes them based on theories of cognitive neuroscience and pattern recognition. Direct communication between the brain and the external environment enables manipulation of external devices such as computers and robots, and feedback of external information to the brain through stimulation. In recent years, brain science and brain-inspired intelligence technology have gradually attracted people's attention and become a research hotspot in the development of artificial intelligence. Developed countries such as the United States, Germany, and the United Kingdom have successively promoted b...

AI Technical Summary

Problems solved by technology

[0004] The number of commands output by the BCI system based on a single mode is small, the control function is limited, the recognition accuracy of multi-classification tasks is low and the user operation fault tolerance is poor, the coupling degree of human-computer interaction is not high, and the control of complete artificial brain control There are potential safety hazards in the method, and control errors are prone to cause serious consequences. The operation function and safety cannot meet the actual control requirements of the robot.

The patent with the application number 201710542674.8 discloses that the motor imagery (Motor Imagery, MI) signal of the left and right hands is used to realize the intelligent rehabilitation robot for upper limb rehabilitation training. This MI-based single-mode BCI system can be classified due to its signal generation principle. The number of control commands is small and the recognition accuracy is low

The patent application number 201410103602.X discloses a Steady State Visual Evoked Potential (SSVEP) signal to realize four control commands for the robot to move forward, backward, turn left, and turn right. The BCI system The disadvantage is that it completely relies on the user to focus on the visual stimulation target that flickers at a specific frequency to achieve the control purpose. The user is prone to visual fatigue, and the system does not have start-stop, acceleration at all levels, deceleration at all levels, back and steering functions of different magnitudes. In the shared driving mode, it is impossible to evaluate and optimize the user's operation safety, and it is prone to operating errors

In the traditional BCI-based mobile robot control system, the user can only output a fixed corresponding speed or direction angle change amount for one control intention. If there is an operation error, the next control adjustment can only be made through the BCI system, and it cannot be corrected in time. it's very dangerous

Images