CN117908674A - Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system - Google Patents
Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system Download PDFInfo
- Publication number
- CN117908674A CN117908674A CN202410041474.4A CN202410041474A CN117908674A CN 117908674 A CN117908674 A CN 117908674A CN 202410041474 A CN202410041474 A CN 202410041474A CN 117908674 A CN117908674 A CN 117908674A
- Authority
- CN
- China
- Prior art keywords
- brain
- fuzzy logic
- probability
- command
- unmanned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 28
- 230000000638 stimulation Effects 0.000 claims abstract description 17
- 230000001133 acceleration Effects 0.000 claims description 18
- 238000010219 correlation analysis Methods 0.000 claims description 10
- 230000005484 gravity Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 description 21
- 210000003169 central nervous system Anatomy 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000000763 evoking effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010024500 Limb malformation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a brain-computer interface and a brain-computer control method for a brain-controlled air-ground cooperative unmanned system, which comprise the following steps: the acquisition module is used for acquiring a stimulation interface acquired by the unmanned aerial vehicle in real time; the processing module is used for carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface; and the control module is used for carrying out fuzzy logic processing on the processed probabilities to obtain the unmanned parking positions. By adopting the technical scheme of the invention, the command set of the user is converted from a fixed command set to a continuous distribution command set, and simultaneously, the user can operate the unmanned aerial vehicle by both hands to complete air-ground coordination.
Description
Technical Field
The invention belongs to the technical field of man-machine interaction, and particularly relates to a brain-computer interface and a brain-computer control method for a brain-controlled air-ground cooperative unmanned system.
Background
The brain-computer interface (brain-Computer Interface) is a system that detects central nervous system (Central Nervous System, CNS) activity and converts it into an artificial output that can be used to replace, repair, augment, supplement, or improve the normal output of the CNS, thereby altering the constant interaction between the CNS and the internal and external environment. For disabled people with limb defects, the brain-computer interface helps them achieve a life that is close to normal; for normal people, the brain-computer interface can help others to have additional performance capabilities. The brain-computer interface technology has been widely applied to the fields of brain-controlled prostheses, brain-controlled robots, brain-controlled wheelchairs, brain-controlled browsing web pages, brain-controlled vehicles and the like.
Air-ground coordination is a hotspot in the field of multi-agent research at present, and has the characteristics of wide area coverage, strong environmental adaptability, high task execution rate and the like. Compared with a single agent system, the multi-agent cooperation highlights the characteristics of stronger data matching, free cooperation, better system redundancy degree and the like, and is widely applied in more fields. In indoor environment and urban environment, the small unmanned aerial vehicle and the small unmanned aerial vehicle form air-ground cooperation, and can be used for disaster search and rescue, anti-terrorism, riot prevention and the like.
The existing space-ground cooperative system with people in the ring requires operators to complete the operation and control of various devices. The operation mode of single person multi-task can have higher work efficiency and work performance in consideration of the cooperative work of a plurality of operators. Therefore, one task control is completed by using the brain-computer interface, and the other task control is operated in other modes, so that the brain-computer interface has good application prospect.
However, the current brain-computer interface is limited by the performance of the brain-computer interface, and still cannot independently complete a complete control task.
Disclosure of Invention
The invention aims to solve the technical problem of providing a brain-computer interface and a brain-computer control method for a brain-controlled air-ground cooperative unmanned system, which are used for generating the pose of an unmanned vehicle by carrying out probability processing on each command and then processing the probability commands by fuzzy logic by using a reality enhancement technology and a brain-computer interface technology.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A brain-computer interface for a brain-controlled air-ground collaborative unmanned system, comprising:
the acquisition module is used for acquiring a stimulation interface acquired by the unmanned aerial vehicle in real time;
the processing module is used for carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface;
and the control module is used for carrying out fuzzy logic processing on the processed probabilities to obtain the unmanned parking positions.
Preferably, the processing module converts each command of the electroencephalogram signal into a probability corresponding to each command by filter bank canonical correlation analysis.
Preferably, the control module includes:
The blurring unit is used for blurring the probability of each command;
The first logic reasoning unit is used for carrying out first-order and second-order fuzzy logic reasoning on the membership function according to the fuzzification;
The second logic reasoning unit is used for carrying out longitudinal fuzzy logic reasoning on the brain-controlled vehicle side according to the state feedback;
the defuzzification unit is used for solving the output quantity membership obtained by fuzzy logic reasoning through an average gravity center method to obtain the output quantity, and the output quantity comprises: angular velocity of the drone and acceleration of the drone.
The invention also provides a brain-computer control method for the brain-controlled air-ground cooperative unmanned system, which comprises the following steps:
Step S1, acquiring a stimulation interface acquired by an unmanned aerial vehicle in real time;
S2, carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface;
And S3, performing fuzzy logic processing on each processed probability to obtain the unmanned parking position.
Preferably, step S2 converts each command of the electroencephalogram signal into a probability corresponding to each command by filter bank canonical correlation analysis.
Preferably, step S3 includes:
step S31, blurring the probability of each command;
Step S32, performing first-order and second-order fuzzy logic reasoning according to the membership function obtained through fuzzification;
Step S33, performing fuzzy logic reasoning on the longitudinal direction of the brain-controlled vehicle side according to state feedback;
Step S34, solving the output quantity membership obtained according to fuzzy logic reasoning through an average gravity center method to obtain the output quantity, wherein the output quantity comprises the following components: angular velocity of the drone and acceleration of the drone.
The invention has the beneficial effects that:
The invention projects the induction stimulation of the brain electrical signals into the visual field of the operator, so that the operator can complete other actions at the same time; probability processing is carried out on the electroencephalogram signals and the corresponding commands; the probability corresponding to the command is converted into the pose of the unmanned vehicle by using the fuzzy logic, and meanwhile, the user command is further corrected by introducing state feedback in consideration of the influence of the user history command, so that the problem of excessively fast output change of first-order fuzzy logic reasoning is solved, and the control track is smoother.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a brain-computer structure of a brain-controlled air-ground cooperative unmanned system according to an embodiment of the present invention;
FIG. 2 is a flow chart of a fuzzy logic process according to an embodiment of the present invention;
FIG. 3 is a membership function for fuzzification;
FIG. 4 is a disambiguation membership function.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1:
as shown in fig. 1, an embodiment of the present invention provides a brain-computer interface for a brain-controlled air-ground collaborative unmanned system, including:
the acquisition module is used for acquiring a stimulation interface acquired by the unmanned aerial vehicle in real time;
The processing module is used for carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface, wherein the processing module converts each command of the electroencephalogram signals into the probability corresponding to each command through filter bank typical correlation analysis;
and the control module is used for carrying out fuzzy logic processing on the processed probabilities to obtain the unmanned parking positions.
As an implementation manner of the embodiment of the present invention, the control module includes:
The blurring unit is used for blurring the probability of each command;
The first logic reasoning unit is used for carrying out first-order and second-order fuzzy logic reasoning on the membership function according to the fuzzification;
and the second logic reasoning unit is used for carrying out longitudinal fuzzy logic reasoning on the brain-controlled vehicle side according to the state feedback.
Specifically, the angular acceleration and the acceleration of the current vehicle are detected through a sensor, the angular acceleration and the acceleration are converted into membership of a fuzzy set of the current vehicle state through state feedback fuzzification, and then fuzzy logic reasoning is carried out on the membership of the fuzzy set and the fuzzy set output by the first logic reasoning unit, so that a membership function of the fuzzy set of the output quantity is obtained.
The defuzzification unit is used for solving the output quantity membership obtained by fuzzy logic reasoning through an average gravity center method to obtain the output quantity, and the output quantity comprises: angular velocity of the unmanned vehicle and acceleration of the unmanned vehicle;
By adopting the technical scheme of the embodiment of the invention, a driver makes a decision according to the current road vehicle information and sends out corresponding electroencephalogram signals; the probability output calculates a corresponding probability value according to the quality of the electroencephalogram signals; and outputting a signal with the minimum error cost according to the fuzzy logic reasoning, and performing fine adjustment according to the environment information, so that the control precision is finer.
The experimental paradigm of the brain electrical signal selected by the invention is steady-state visual evoked potential (STEADY STATE Visually Evoked Potential, SSVEP). Five selected instructions correspond to five different stimulation frequencies, namely acceleration, deceleration, start-stop, left turn and right turn respectively.
In order to reduce the workload of the driver, embodiments of the present invention introduce commands in an uncontrolled state. This command does not pertain to the evoked stimulation of SSVEP, so training is required to collect experimental data from the subject prior to testing.
The classification with the largest correlation coefficient is directly selected as output after the typical correlation analysis processing of the traditional filter bank, and the embodiment of the invention is used for converting the correlation coefficient after the typical correlation analysis processing of the filter bank into the probability corresponding to each command instead.
The correlation coefficient obtained after the acquired electroencephalogram signal is subjected to the filter bank typical correlation analysis processing at a certain moment is rho= [ rho 1 ρ2 ρ3 ρ4 ρ5 ], wherein rho i represents the filter bank typical correlation analysis processing result of the ith instruction corresponding to the current moment.
The fitting probability output model adopts a logistic regression method, and the expression is as follows:
wherein A and B are parameters to be fitted, and ρ is a corresponding correlation coefficient. P is the probability of the final output.
The fitting process employs minimization of the cross entropy loss function:
Wherein t i is the tag therein. t i =1 means that the ith sample belongs to such instruction; t i =0 means that the ith sample does not belong to such an instruction.
The start-stop command output by the SSVEP can affect the start-stop function and the stop function of the unmanned vehicle, namely, the start-stop command corresponds to a bool type variable, the priority is higher than other commands, and a built-in counter count is designed. Wherein count satisfies the condition: and 0.ltoreq.count.ltoreq.k. And when the start-stop command is activated, the count is increased by 1, otherwise, the count is reduced by 1, the count is cleared when k is reached each time, and the unmanned vehicle stop state is changed.
As shown in fig. 2, the fuzzy logic process includes: fuzzification, first order fuzzy logic reasoning, second order fuzzy logic reasoning and defuzzification. Blurring consists of five inputs: left turn, right turn, acceleration, deceleration, uncontrolled; comprising two outputs: the change amount delta theta of steering wheel angle, acceleration a. The membership function of the input is shown in fig. 3.
The membership functions of the five input quantities are the same, each instruction comprises two membership functions of H and L, and after blurring, the probability of each instruction is converted into the membership of two corresponding H and L fuzzy sets. The membership functions use both an S-type function and a Z-type function.
The membership function of each input quantity carries out logic reasoning, and the following principles are satisfied: logic or taking the maximum value of membership degrees of the logic; logic AND takes the minimum value of the membership degree of the logic AND and the logic AND; logic no takes 1 and the membership is bad. The fuzzy logic reasoning in the embodiment of the invention adopts AND logic, and a specific reasoning process is made into a table to display as shown in table 1 and table 2.
TABLE 1
TABLE 2
The contents of the table represent fuzzy sets of the output of the first order fuzzy logic reasoning. According to the first order inference rules, zero ambiguity sets represent straight going and no acceleration, speedUp and SlowDown acceleration and deceleration, and TurningLeft and TurningRight left and right turns.
And then performing second-order fuzzy logic reasoning. The method has the core thought that the state of the unmanned vehicle is fed back to the control interface, and the intention of the user is corrected for the second time. The specific reasoning formats are shown in tables 3 and 4.
TABLE 3 Table 3
TABLE 4 Table 4
The content of the table head is the result of first-order fuzzy logic reasoning, and the second-order reasoning is continued according to the result of the first-order to obtain the output result of the table seed. The membership function of its output is shown in figure 4.
The defuzzification adopts an average gravity center method. The output membership obtained by reasoning is solved through an average gravity center method to obtain the output.
u(t)＝u(t-1)+Δu(t) (6)
Where x θ is the abscissa of the angular velocity portion of the ground vehicle and x a is the abscissa of the acceleration portion. f (·) is a membership function of the output, as shown in FIG. 4.
The left side represents the membership function of the angular velocity of the ground unmanned vehicle, and the right side represents the membership function of the acceleration of the unmanned vehicle.
The obtained steering wheel angle and acceleration of the vehicle can be used as input quantities of other auxiliary controllers.
At the same time, an operator can operate the unmanned aerial vehicle to complete another task under the ground environment, and simultaneously perform multitasking activities.
According to the embodiment of the invention, on the premise that an operator can output a real intention through a brain-computer interface by an augmented reality method, a steering wheel corner with lower error cost is output through a probabilistic output port and fuzzy logic, and a state feedback correction command is used for maintaining control stability in the whole control process, so that the multitasking air-ground collaborative operation method is completed. In one aspect, the present invention is directed to improving the steering stability of a brain-controlled vehicle; in another aspect, the present invention is directed to reducing human workload
Example 2:
the embodiment of the invention also provides a brain-computer control method for the brain-controlled air-ground cooperative unmanned system, which comprises the following steps:
Step S1, acquiring a stimulation interface acquired by an unmanned aerial vehicle in real time;
S2, carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface;
And S3, performing fuzzy logic processing on each processed probability to obtain the unmanned parking position.
As an implementation manner of the embodiment of the present invention, step S2 converts each command of the electroencephalogram signal into a probability corresponding to each command through filter bank typical correlation analysis.
As one implementation of the embodiment of the present invention, step S3 includes:
step S31, blurring the probability of each command;
Step S32, performing first-order and second-order fuzzy logic reasoning according to the membership function obtained through fuzzification;
Step S33, performing fuzzy logic reasoning on the longitudinal direction of the brain-controlled vehicle side according to state feedback;
Step S34, solving the output quantity membership obtained according to fuzzy logic reasoning through an average gravity center method to obtain the output quantity, wherein the output quantity comprises the following components: angular velocity of the drone and acceleration of the drone.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present invention pertains are made without departing from the spirit of the present invention, and all modifications and improvements fall within the scope of the present invention as defined in the appended claims.
Claims (6)
1. A brain-computer interface for a brain-controlled air-ground collaborative unmanned system, comprising:
the acquisition module is used for acquiring a stimulation interface acquired by the unmanned aerial vehicle in real time;
the processing module is used for carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface;
and the control module is used for carrying out fuzzy logic processing on the processed probabilities to obtain the unmanned parking positions.
2. The brain-computer interface for a brain-controlled air-ground collaborative unmanned system according to claim 1, wherein the processing module converts each command of the electroencephalogram signal into a probability corresponding to each command by filter bank canonical correlation analysis.
3. The brain-computer interface for a brain-controlled air-ground collaborative unmanned system according to claim 2, wherein the control module comprises:
The blurring unit is used for blurring the probability of each command;
The first logic reasoning unit is used for carrying out first-order and second-order fuzzy logic reasoning on the membership function according to the fuzzification;
The second logic reasoning unit is used for carrying out longitudinal fuzzy logic reasoning on the brain-controlled vehicle side according to the state feedback;
the defuzzification unit is used for solving the output quantity membership obtained by fuzzy logic reasoning through an average gravity center method to obtain the output quantity, and the output quantity comprises: angular velocity of the drone and acceleration of the drone.
4. A brain-computer control method for a brain-controlled air-ground cooperative unmanned system is characterized by comprising the following steps:
Step S1, acquiring a stimulation interface acquired by an unmanned aerial vehicle in real time;
S2, carrying out probability processing on the electroencephalogram signals generated based on the stimulation interface;
And S3, performing fuzzy logic processing on each processed probability to obtain the unmanned parking position.
5. The brain-computer control method for brain-controlled air-ground cooperative unmanned system according to claim 4, wherein step S2 converts each command of the electroencephalogram signal into a probability corresponding to each command through a filter bank canonical correlation analysis.
6. The brain-computer control method for brain-controlled air-ground cooperative unmanned system according to claim 5, wherein step S3 comprises:
step S31, blurring the probability of each command;
Step S32, performing first-order and second-order fuzzy logic reasoning according to the membership function obtained through fuzzification;
s33, performing fuzzy logic reasoning on the longitudinal direction of the brain-controlled vehicle side according to state feedback;
Step S34, solving the output quantity membership obtained according to fuzzy logic reasoning through an average gravity center method to obtain the output quantity, wherein the output quantity comprises the following components: angular velocity of the drone and acceleration of the drone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410041474.4A CN117908674A (en) | 2024-01-11 | 2024-01-11 | Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410041474.4A CN117908674A (en) | 2024-01-11 | 2024-01-11 | Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117908674A true CN117908674A (en) | 2024-04-19 |
Family
ID=90690493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410041474.4A Pending CN117908674A (en) | 2024-01-11 | 2024-01-11 | Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117908674A (en) |
-
2024
- 2024-01-11 CN CN202410041474.4A patent/CN117908674A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105825241B (en) | Operator brake based on fuzzy neural network is intended to discrimination method | |
| CN112000087A (en) | Intent priority fuzzy fusion control method for brain-controlled vehicle | |
| CN110059593B (en) | Facial expression recognition method based on feedback convolutional neural network | |
| Chen et al. | Research on deep learning in the field of mechanical equipment fault diagnosis image quality | |
| Xiong et al. | A new synchronous control method for dual motor electric vehicle based on cognitive-inspired and intelligent interaction | |
| CN114103974B (en) | Brain-computer interface method for vehicle continuous control | |
| CN117908674A (en) | Brain-computer interface and brain-computer control method for brain-controlled air-ground cooperative unmanned system | |
| Yu et al. | Social vision for intelligent vehicles: from computer vision to foundation vision | |
| CN110329277A (en) | A kind of intelligent automobile man-machine coordination control Weight Value Distributed Methods | |
| Yuan et al. | VRDriving: A virtual-to-real autonomous driving framework based on adversarial learning | |
| Wang et al. | An adaptive control approach for intelligent wheelchair based on bci combining with qoo | |
| CN114675539A (en) | Door and window intelligent control system of independently studying | |
| Chen et al. | Deep Learning-Based Fatigue Detection for Online Learners | |
| Zhang et al. | Robust H∞ Fuzzy Logic Control of Intelligent Electrically Powered Wheelchair | |
| CN117697769B (en) | Robot control system and method based on deep learning | |
| Kehtarnavaz et al. | Autonomous vehicle following by a fuzzy logic controller | |
| CN113708692B (en) | Permanent magnet synchronous motor control method of brain emotion controller based on experience information | |
| Baoquan et al. | The nonlinear control using fuzzy logic for spinning underwater vehicle | |
| Zhiqi | Application of Improved PID Control Algorithm in Intelligent Vehicle | |
| CN101673355A (en) | Cognition associative memory model | |
| Zhou et al. | Study of braking strategy considering comfort | |
| Dong et al. | Shared control schematic for brain controlled vehicle based on fuzzy logic | |
| Zhu et al. | Sensor Fusion in Machining System Monitoring | |
| CN116198521A (en) | Hybrid electric vehicle working condition identification method and system | |
| CN114021608A (en) | Electroencephalogram recognition method fusing structure information between brain regions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |