CN114569350A

CN114569350A - Head-mounted type eye-controlled intelligent wheelchair and control method thereof

Info

Publication number: CN114569350A
Application number: CN202210384612.XA
Authority: CN
Inventors: 贺庆; 张云
Original assignee: Beijing Chucai Precision Instrument Technology Co ltd; Beijing Information Science and Technology University
Current assignee: Beijing Chucai Precision Instrument Technology Co ltd; Beijing Information Science and Technology University
Priority date: 2022-04-13
Filing date: 2022-04-13
Publication date: 2022-06-03

Abstract

The application discloses a head-wearing type electro-oculogram controlled intelligent wheelchair and a control method thereof, wherein the intelligent wheelchair comprises head-wearing equipment and wheelchair end equipment, wherein a signal acquisition module in the head-wearing equipment acquires electro-oculogram signals in real time, performs preprocessing operation on the electro-oculogram signals, and converts the electro-oculogram signals into digital signals in an analog-to-digital mode; the feature extraction and identification module is used for extracting and identifying features to obtain eye movement information and sending the eye movement information to the processing control unit; the processing control unit identifies the control intention of a user according to a control discrimination algorithm and sends a control instruction to a motion executing mechanism in the wheelchair end equipment; a motor in the motion executing mechanism drives the wheelchair body to execute corresponding control actions according to the received control instruction; the rechargeable battery supplies power to the head-mounted equipment and the wheelchair-end equipment. According to the invention, through the head-mounted equipment which is convenient for a user to wear, the user can move through eyes to replace fingers to operate the intelligent wheelchair to move in real time, so that the hands are liberated, and the intelligent wheelchair can adapt to more application occasions.

Description

Head-mounted type eye-controlled intelligent wheelchair and control method thereof

Technical Field

The invention relates to the technical field of human-computer interaction, in particular to a head-mounted type eye-controlled intelligent wheelchair and a control method thereof.

Background

With the progress of the society in China, the quality of life of disabled people is more and more generally concerned by various social circles. The investigation shows that the mobility of disabled people and old people is enhanced, the daily convenience is facilitated, and the mental health of the disabled people and the old people can be effectively guaranteed. Wheelchairs are therefore an important tool necessary for life of such disabled persons. The traditional wheelchair needs a user to manually drive or be pushed by others, and is very inconvenient. The electric wheelchair saves manpower and provides convenience for users. However, most electric wheelchairs on the market today are operated by means of a manually controlled joystick, which is not suitable for people with disabled or inconvenient arms.

With the development of technology, the brain-controlled wheelchair and the eye-controlled wheelchair disclosed in recent years can solve the problem to some extent. The brain-controlled wheelchair can send out instructions to control the movement of the wheelchair through brain waves. The mature brain wave signal identification method mainly comprises three paradigms of motor imagery, P300 and SSVEP. Wherein the motor imagery paradigm requires a user to train for a long time, while both the P300 and SSVEP paradigms require an external device to provide the stimulus presentation. The accuracy and reliability of the existing brain control wheelchair are still poor. The eye control wheelchair mainly uses a camera or an eye tracker to shoot eyes of a user at present, and then the eye movement instruction of the user is identified through image processing. The method is easily influenced by a shooting angle and ambient light, the calculation amount of image processing is large, and the real-time performance is difficult to guarantee in practical application. Therefore, it is necessary to develop a more reliable and practical intelligent wheelchair.

Disclosure of Invention

Based on this, this application embodiment provides a wear-type eye electric control's intelligent wheelchair and control method thereof, and user's accessible eye activity control wheelchair is marchd, even the patient that all have disability of hands and feet also can use to it provides convenience to go out for disabled user.

In a first aspect, a head-mounted eye-controlled intelligent wheelchair is provided, which comprises a head-mounted device and a wheelchair end device, wherein the head-mounted device comprises a signal acquisition module and a feature extraction and identification module, the wheelchair end device comprises a processing and control unit, a motion execution mechanism, a wheelchair body and a rechargeable battery, specifically:

the signal acquisition module is used for acquiring an electro-ocular signal in real time, carrying out preprocessing operation on the electro-ocular signal and converting the electro-ocular signal into a digital signal through an analog-to-digital converter;

the characteristic extraction and identification module is electrically connected with the signal acquisition module and is used for acquiring the digital signals, carrying out signal identification on the digital signals, carrying out characteristic extraction and classification on the identified eye control signals to obtain eye movement information, and sending the eye movement information to the processing control unit, wherein the characteristic extraction and identification module is communicated with the processing control unit in a wired and/or wireless mode;

the processing control unit is electrically connected with the motion executing mechanism and used for receiving the eye movement information, identifying the control intention of the user according to a control discrimination algorithm and sending a control instruction to the motion executing mechanism;

the motion executing mechanism comprises a motor and a transmission device which are arranged on the wheelchair body, and the motor drives the wheelchair body to execute corresponding control actions according to the received control instructions;

the rechargeable battery is respectively arranged in the head-wearing equipment and the wheelchair end equipment and used for supplying power to the head-wearing equipment and the wheelchair end equipment.

Optionally, the system further comprises an obstacle detection module: the obstacle detection module is electrically connected with the processing control unit and used for detecting obstacles or hollow parts around the wheelchair and preventing the wheelchair from colliding or falling.

Optionally, the wheelchair further comprises a manual operating device, wherein the manual operating device is connected with the processing control unit and is used for replacing an electro-oculogram control mode to operate the wheelchair to move when signals of the signal acquisition module are interfered;

the manual control device also comprises a braking device, and the wheelchair can be braked and fixed by pulling the braking device.

Optionally, the signal acquisition module includes a connection detection circuit and a driving excitation circuit:

the connection detection circuit is used for detecting whether each electro-oculogram electrode is well connected with the corresponding position around the eyes of the user;

the driving excitation circuit is used for improving the common mode rejection capability of the electro-oculogram signal acquisition, eliminating external interference and ensuring the quality of the acquired signal.

Optionally, the signal acquisition module is connected with the eyes of the user in an eye electric lead mode, and the eye electrode lead can be an Ag/AgCI electrode patch assembly and comprises a single-pole lead mode and a double-pole lead mode.

Optionally, the signal acquisition module further includes: a protection device, an amplifier, a filter and a baseline adjustment circuit;

the protection device is connected with the eye conductor and is used for protecting the post-stage circuit, protecting the breakdown and/or interference of human body static electricity on the post-stage circuit and preventing the electric leakage in the circuit from damaging the human body;

the amplifier is used for controllably amplifying the input eye electrical signal so as to enhance the effect of the common mode rejection ratio of the system; wherein, the amplifier is an instrument amplifier with high input impedance, and adopts a shielding layer driving technology to enhance the shielding capability to the external electromagnetic interference;

the filter is used for filtering irrelevant interference signals mixed in the eye electrical signals; the irrelevant interference signals at least comprise power frequency interference signals, environmental radio signals, electrocardiosignals and electromyographic signals;

the baseline adjusting circuit is used for adjusting the center of the electro-oculogram analog signal to an amplitude convenient for the analog-to-digital converter to collect.

In a second aspect, a method for controlling a head-mounted electro-ocularly controlled intelligent wheelchair is provided, which is applied to the intelligent wheelchair of the first aspect, and includes:

s1, acquiring an eye electric signal of a user through a signal acquisition module, preprocessing the eye electric signal, and converting the eye electric signal into a digital signal through an analog-to-digital converter;

s2, carrying out digital signal processing on the digital signal, carrying out signal identification on the digital signal, and carrying out feature extraction and classification on the identified eye electric control signal to obtain eye movement information;

s3, identifying the control intention of the user according to the eye movement information and a control discrimination algorithm, and sending a control instruction;

and S4, controlling the wheelchair motion executing mechanism according to the control command, and driving the wheelchair to execute corresponding control action.

Optionally, in S2, the processing the digital signal, performing signal recognition on the digital signal, and performing feature extraction and classification on the recognized eye electrical control signal to obtain eye movement information further includes:

denoising and end point detection are carried out on the digital signal of the electro-oculogram, a preset electro-oculogram processing algorithm is executed, the electro-oculogram signal characteristics are extracted, and the electro-oculogram signals are classified to obtain eye movement information.

Optionally, the control discrimination algorithm may include:

the two eyes blink twice continuously or the eyes are closed for more than 2s, and the wheelchair is controlled to brake or stop;

blinking once in both eyes, and then continuously glancing upwards twice to control the wheelchair to move forwards;

blinking once in both eyes, and then continuously glancing downwards twice to control the wheelchair to move backwards;

blinking once for both eyes, and then continuously seeing to the left to control the wheelchair to turn left until the eyes return to the right;

blinking once by two eyes, and then continuously looking rightwards to control the wheelchair to rotate rightwards until the eyes return to the right;

blinking once in both eyes, and then continuously glancing twice leftwards to control the left movement of the wheelchair;

blinking once by two eyes, and then continuously glancing to the right twice to control the wheelchair to move to the right;

the eye movement behavior that does not conform to the preset eye movement pattern is considered as unintentional eye movement of the user and no action is performed.

Optionally, the control method further includes:

when the signal acquisition module fails to acquire the eye electric signals of the user, the wheelchair is controlled to move through the manual control device.

According to the technical scheme provided by the embodiment of the application, the intelligent wheelchair comprises the head-mounted equipment and the wheelchair end equipment, wherein the head-mounted equipment comprises the signal acquisition module and the feature extraction and identification module, the wheelchair end equipment comprises the processing and control unit, the motion execution mechanism, the wheelchair body and the rechargeable battery, and through the head-mounted equipment which is convenient for a user to wear, the user can operate the intelligent wheelchair to act in real time through eye movement instead of fingers, and hands are liberated, so that the intelligent wheelchair can adapt to more application occasions.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.

The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.

Fig. 1 is a schematic structural diagram illustrating a structure of a head-mounted electro-ocularly controlled intelligent wheelchair according to an embodiment of the present invention;

FIG. 2 is a diagram of the electrical eye potential distribution;

FIG. 3 is a schematic structural diagram of a single-pole lead embodiment of a head-mounted electro-ocularly controlled smart wheelchair according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an embodiment of bipolar leads of a head-mounted electro-ocularly operated smart wheelchair according to an embodiment of the present invention;

fig. 5 is a flowchart of a method for controlling a head-mounted electro-ocularly controlled intelligent wheelchair according to an embodiment of the present invention.

Detailed Description

The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In particular, please refer to fig. 1, which shows a schematic structural diagram of a head-mounted electro-ocularly controlled intelligent wheelchair according to an embodiment of the present invention,

including head-mounted apparatus and wheelchair end equipment, wherein head-mounted apparatus includes signal acquisition module and feature extraction identification module, and wheelchair end equipment includes processing control unit, motion actuating mechanism, wheelchair body and rechargeable battery, specifically:

the signal acquisition module is used for acquiring the electro-ocular signals in real time, carrying out preprocessing operation on the electro-ocular signals and converting the electro-ocular signals into digital signals through the analog-to-digital converter;

in an alternative embodiment of the present application, the signal acquisition module comprises: the system comprises an ocular electrical lead, a protective device, a filter, a baseline correction circuit, an amplifier and an analog-to-digital converter. Receiving an eye electrical signal acquired by an eye electrode arranged at a preset position around the eye by adopting an eye electrical lead connected with the eye electrode; filtering, baseline correction, amplification and the like are carried out on the electro-oculogram signals to obtain electro-oculogram analog signals; the analog-to-digital converter carries out parallel synchronous acquisition on the multi-channel electrooculogram analog signals to obtain quantized electrooculogram digital signals.

And the characteristic extraction and identification module is electrically connected with the signal acquisition module and is used for acquiring the digital signals, carrying out signal identification on the digital signals, carrying out characteristic extraction and classification on the identified eye movement control signals to obtain eye movement information, and sending the eye movement information to the processing control unit, wherein the characteristic extraction and identification module is communicated with the processing control unit in a wired and/or wireless mode.

In an optional embodiment of the present application, the feature extraction and identification unit is connected to the analog-to-digital converter, and is configured to receive the eye electrical digital signal output by the signal acquisition module, and perform noise cancellation and end point detection; and executing a preset electro-oculogram processing algorithm, extracting the electro-oculogram signal characteristics, classifying the electro-oculogram signals, and sending the eye movement state result to the processing control unit in a wired or wireless mode.

In this embodiment, the preset electro-oculography algorithm may include recognizing eye movement information according to a BP neural network and performing a training process. Specifically, training and classifying are carried out through a BP neural network according to received electro-oculogram digital signals, coefficients in a target function back propagation correction model are utilized to obtain the trained BP neural network, and the trained BP neural network is utilized to classify the electro-oculogram signals.

And the processing control unit is electrically connected with the motion executing mechanism and used for receiving the eye movement information, identifying the control intention of the user according to the control discrimination algorithm and sending a control instruction to the motion executing mechanism.

And the motion executing mechanism comprises a motor and a transmission device which are arranged on the wheelchair body, and the motor drives the wheelchair body to execute corresponding control actions according to the received control instructions.

Two little front wheels of wheelchair body have the steering motor in this application, through the different rotational speed of steering motor, turn to and rotate amplitude control wheelchair and rotate to different directions.

The rechargeable battery is respectively arranged in the head-wearing device and the wheelchair end device and used for supplying power to the head-wearing device and the wheelchair end device.

The embodiment of the invention provides a head-mounted type intelligent wheelchair controlled by an electro-oculogram. The intelligent wheelchair is controlled by the rotation and blinking of eyeballs. The human eye is a charged body, the corneal end of the eyeball is positively charged, and the retinal end is negatively charged, as shown in fig. 2. When the eyeball rotates, a slight change in the electric quantity is measured by the cortex near the eyeball. The level fluctuation of each electrode can be measured when the eyeball rotates by using the electrodes distributed around the eye, so that the rotation direction of the eyeball is analyzed. When the eyes of a person are closed, the alpha wave signal is greatly increased, so that the blinking action is easily distinguished.

Specifically, the signal acquisition module is connected with the eyes of a user by adopting an eye electric lead, and the eye electrode lead can be an Ag/AgCI electrode patch component. Has two connection modes of a unipolar lead and a bipolar lead, and the two lead embodiments are respectively shown in figures 3 and 4.

The electro-ocular leads are used for being connected with the ocular electrodes and receiving the electro-ocular signals acquired by the ocular electrodes at all positions; the electro-oculogram is divided into a unipolar lead and a bipolar lead. In fig. 3, a first electrode is denoted by a, a second electrode by B, a third electrode by C, a fourth electrode by D, a fifth electrode by E, a sixth electrode by F, and a seventh electrode by G, and in the unipolar lead method, one electrode a is attached to the center of the forehead as a ground electrode, and four electrodes B, C, D, E are measurement electrodes, where B is placed above the lateral eyebrow and C is placed about 20mm below the orbit of the eye and is on a vertical line with B. D. E, two electrodes are respectively placed at the outer side of two eyes and at the position which is about 10mm away from the outer canthus. The other two electrodes F, G are used as reference electrodes and attached to the mastoid process or the ear lobe. During detection, four measuring electrodes are fed via the leads to the positive inputs of the four amplifiers, respectively, while the reference electrode F, G with equal potential is fed via the leads to the negative inputs of the four amplifiers simultaneously, and the ground electrode A is connected to the power supply ground of the amplifiers. After amplification and filtering, the four signals are respectively collected to obtain the absolute electric potentials of the four measuring electrodes relative to the reference electrode, so that the eye movement condition is judged.

In the bipolar lead method, as shown in fig. 4, the eighth electrode is marked with a, the ninth electrode is marked with B, the tenth electrode is marked with C, the eleventh electrode is marked with D, and the twelfth electrode is marked with E, electrode a is attached to the center of the forehead and serves as the ground electrode, and four electrodes B, C, D, E serve as the measuring electrodes, wherein electrode B, C is paired to serve as the vertical measuring electrode, B is placed above the lateral eyebrow center, and C is placed about 20mm below the orbit and is on the same vertical line with B. D. The pair E was used as horizontal measuring electrodes and placed approximately 10mm from the outer canthus outside both eyes. During detection, B, C are respectively connected to the positive and negative input ends of one amplifier, and D, E are respectively connected to the positive and negative input ends of the other amplifier. Resulting in a relative potential difference of BC and DE, respectively. B. The potential difference between C is the vertical movement of the eyeball. D. The potential difference between E is the horizontal movement of the eyeball.

Optionally, the ocular electrode lead may specifically include a dry and/or wet electrode, an ocular electrode feed, and an electrical interface (e.g., a BNC interface).

Because the ocular electrical signals collected by the ocular electrodes are weak, the ocular electrical signals can be amplified for subsequent processing, and specifically, the ocular electrical signals received by the ocular electrical conductance connection can be amplified, filtered and the like in a preprocessing channel to obtain ocular electrical analog signals; the pretreatment channel comprises: a protection device, a filter, a baseline adjustment circuit and an amplifier.

A protective device in electrical communication with the eye. The protection circuit is used for protecting a post-stage circuit, and mainly prevents breakdown and/or interference of human body static electricity to the post-stage circuit or prevents electric leakage in the circuit from causing damage to a human body. The device can be realized by TVS tube, Zener diode, gas discharge tube and other devices.

The filter filters common interference signals and comprises: power frequency interference, environmental radio signals, electrocardiosignals, electromyographic signals and the like.

The baseline adjusting circuit adjusts the center of the electro-oculogram analog signal to the amplitude convenient for the analog-to-digital converter to collect, and avoids the electro-oculogram analog signal from deviating too much and exceeding the measurement range of the analog-to-digital converter.

The amplifier can be realized by an instrumentation amplifier with high input impedance. Optionally, a shielding layer driving technology is adopted, that is, the reference end of the amplifier is connected with the eye electrode feeder line and the shielding layer of the head-mounted device, so that the shielding capability of the external electromagnetic interference is enhanced.

The analog-to-digital conversion module may specifically be a bioelectricity collection analog-to-digital converter represented by ADS 1299. The device is used for synchronously acquiring the plurality of paths of electro-oculogram analog signals in parallel and converting the electro-oculogram analog signals into electro-oculogram digital signals. The ADS1299 chip integrates a baseline adjusting circuit and an amplifier, and can realize the functions of exciting a driving signal and connecting and detecting;

the characteristic extraction and identification unit is used for receiving the electro-oculogram digital signals output by the signal acquisition module, and performing noise elimination and end point detection on the electro-oculogram digital signals; executing a preset electro-oculogram processing algorithm, extracting electro-oculogram signal characteristics, classifying the electro-oculogram signals, and sending the eye movement state result to a processing control unit in a wired or wireless mode to control the intelligent wheelchair to carry out preset operation; the characteristic extraction and identification unit can be realized by processor chips such as an ARM processor, a DSP, an FPGA and the like; for the convenience of wearing by the user, a processor with a wireless communication function, such as NRF52840, is preferable.

One possible feature classification method in the present application is: when the user uses the wheelchair for the first time, the user can complete the actions of blinking for a plurality of times, looking up, looking down, looking left and looking right in sequence under the prompt of the intelligent wheelchair. The waveform and the electro-oculogram feature corresponding to the above actions are recorded by the feature extraction unit. When the user normally uses the device, if the electro-oculogram signal exceeds the amplitude of the silent state signal, the feature analysis is carried out on the electro-oculogram signal. And if the consistency of the waveform of the electro-ocular signal and a certain pre-stored action reaches 80% and the amplitude exceeds 60% of the pre-stored amplitude peak value of the action, the user is considered to execute the action of the eye movement. If neither the electro-ocular signal is consistent with any pre-stored motion waveform or the amplitude does not reach 60% of any pre-stored motion amplitude peak, the user is considered not to perform a valid eye motion. The preset electro-oculogram processing algorithm provides the method for recognizing the eye movement information according to the BP neural network and carrying out training processing, which is easy to understand, in other optional embodiments, wavelet transformation, linear discriminant analysis, correlation analysis and other methods can be adopted for extracting the features of the electro-oculogram signals, a support vector machine, a hidden Markov chain, a neural network and other methods can be adopted for classifying the electro-oculogram signals, and whatever technology is finally adopted, the technical scheme of carrying out electro-oculogram control by adopting the idea of the invention is regarded as being realized based on the invention.

And the memory is connected with the feature extraction and identification unit. For storing the user's electro-oculogram information. In particular, the flash memory or the EEPROM memory can be used for realizing the data transmission.

The wheelchair-end apparatus includes: the wheelchair comprises a processing control unit, a motion executing mechanism, a wheelchair body and a rechargeable battery.

And the processing control unit is a control core of the wheelchair end. The control method comprises the steps of operating a preset control discrimination algorithm according to a received eye movement state signal, judging whether a user performs eye movement intentionally or unintentionally, and identifying the control intention of the user, so as to control a motion execution module to execute corresponding actions and drive the wheelchair to move. The processing control unit can be realized by processor chips such as an ARM processor, a DSP, an FPGA and the like. For corresponding wireless communication with the head-mounted device, a processor with wireless communication function, such as NRF52840, is preferred.

In the embodiment of the present application, the preset control discrimination algorithm is as follows:

(a) and (5) blinking two times continuously or closing the eyes for more than 2s, and controlling the wheelchair to brake or stop.

(b) The eyes blink once and then pan upwards twice in succession to control the wheelchair to advance.

(c) The two eyes blink once and then continuously scan downwards twice, and the wheelchair is controlled to retreat and is in a stop state before retreating.

(d) The eyes blink once, then the left eye is continuously looked at, and the wheelchair is controlled to turn left until the eyes return to the right.

(e) The eyes blink once, then the right eye is continuously looked at, and the wheelchair is controlled to rotate right until the eyes return to the right.

(f) The two eyes blink once and then scan twice to the left continuously to control the left movement of the wheelchair.

(h) The two eyes blink once and then pan twice to the right continuously to control the wheelchair to move to the right.

(g) The eye movement behavior that does not conform to the preset eye movement pattern is considered as unintentional eye movement of the user and no action is performed.

The preset control discrimination algorithm can be adjusted according to the requirements of users. Of course, there may be other mapping manners, and the embodiment of the present invention is only illustrative and not limiting.

The motion execution module consists of a motor driver, a motor and a transmission device. The motor driver receives the instruction sent by the processing control unit, the motor is controlled to rotate, and the transmission device transmits kinetic energy to the wheel of the wheelchair to drive the wheel to rotate.

The wheelchair body comprises two large rear wheels and two small front wheels. The four wheels are driven by a motor respectively. The two small front wheels are also provided with steering motors, and the wheelchair is controlled to rotate in different directions through different rotating speeds, steering and rotating amplitudes of the steering motors.

Preferably, the wheelchair-end equipment is provided with an obstacle detection module, and the front obstacles or hollow parts are detected through the sensors, so that the risks of collision or falling of the wheelchair and the like are prevented, and the personal safety of a user is guaranteed. The obstacle detection module can be realized by adopting an infrared obstacle detector or an ultrasonic probe,

the wheelchair-end equipment is provided with a manual control device, and when a user has physical discomfort or sudden conditions, the user or family members can manually control the wheelchair to stop or return to a safe area.

The processing control unit also has a voice prompt function. The user can perform pre-calibration of the electro-ocular signal according to the prompt. The wheelchair can inform the user through voice when the electric quantity is insufficient or an obstacle is met.

And the rechargeable battery is used for providing electric energy for all parts of the intelligent wheelchair device. The power supply module consists of a battery and a level conversion circuit. In order to improve the wearability of the system, the head-mounted equipment does not need an external power line for power supply when in use.

Referring to fig. 5, fig. 5 is a flowchart illustrating a method for controlling a head-mounted electro-ocularly controlled intelligent wheelchair according to an embodiment of the present invention. The embodiment of the invention provides a control method of a head-mounted type eye-controlled intelligent wheelchair, which is applied to the head-mounted type eye-controlled intelligent wheelchair in any one of the embodiments and comprises the following steps:

s2, carrying out digital signal processing on the digital signals, carrying out signal identification on the digital signals, and carrying out feature extraction and classification on the identified eye electric control signals to obtain eye movement information;

s3, identifying the control intention of the user according to the eye movement information and the control discrimination algorithm, and sending a control instruction;

and S4, controlling the wheelchair motion actuating mechanism according to the control command, and driving the wheelchair to execute the corresponding control action.

Wherein, carry out digital signal processing to digital signal carries out signal identification, carries out feature extraction and classification with the eye electric control signal who recognizes and obtains eye movement information, still includes: denoising and end point detection are carried out on the digital signal of the electro-oculogram, a preset electro-oculogram processing algorithm is executed, the electro-oculogram signal characteristics are extracted, and the electro-oculogram signals are classified to obtain eye movement information. When the signal acquisition module fails to acquire the eye electric signals of the user, the wheelchair is controlled to move through the manual control device.

It is worth mentioning that the head-mounted type eye-controlled intelligent wheelchair and the control method thereof provided by the embodiment of the invention are convenient for a user to wear, and the user can operate the intelligent wheelchair to move in real time by eye movement instead of fingers to liberate both hands. The intelligent wheelchair can adapt to more application occasions and has the same beneficial effects, and the details are not repeated.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the claims. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. The utility model provides a wear-type eye electric intelligent wheelchair of controlling, a serial communication port, intelligent wheelchair includes head-mounted device and wheelchair end equipment, wherein head-mounted device includes signal acquisition module and feature extraction identification module, wheelchair end equipment includes processing control unit, motion actuating mechanism, wheelchair body and rechargeable battery, specifically:

2. The smart wheelchair of claim 1 further comprising an obstacle detection module:

the obstacle detection module is electrically connected with the processing control unit and used for detecting obstacles or hollow parts around the wheelchair and preventing the wheelchair from colliding or falling.

3. The intelligent wheelchair as claimed in claim 1, further comprising a manual operating device, wherein the manual operating device is connected with the processing control unit and is used for operating the wheelchair to act in an alternative eye-to-eye electrical control mode when the signal of the signal acquisition module is interfered;

4. The intelligent wheelchair of claim 1, wherein the signal acquisition module comprises a connection detection circuit and a drive excitation circuit:

5. The intelligent wheelchair of claim 1, wherein the signal acquisition module is connected with the eyes of the user by means of an eye electrode lead, and the eye electrode lead can be an Ag/AgCI electrode patch assembly and comprises two connection modes of a single-pole lead and a double-pole lead.

6. The smart wheelchair as claimed in claim 1, wherein the signal acquisition module further comprises: a protection device, an amplifier, a filter and a baseline adjustment circuit;

the amplifier is used for carrying out controllable amplification on an input eye electrical signal so as to enhance the effect of a system common mode rejection ratio, wherein the amplifier selects an instrument amplifier with high input impedance and adopts a shielding layer driving technology so as to enhance the shielding capability on external electromagnetic interference;

7. A control method of a head-mounted type eye-controlled intelligent wheelchair, which is applied to the intelligent wheelchair of any one of claims 1 to 6, and is characterized by comprising the following steps:

s2, carrying out digital signal processing on the digital signal, carrying out signal identification on the digital signal, and carrying out feature extraction and classification on the identified eye electrical control signal to obtain eye movement information;

and S4, controlling the wheelchair motion actuating mechanism according to the control command, and driving the wheelchair to execute corresponding control action.

8. The control method according to claim 7, wherein in S2, the digital signal is subjected to digital signal processing, the digital signal is subjected to signal recognition, and the recognized eye electric control signal is subjected to feature extraction and classification to obtain eye movement information, and the method further comprises:

9. The control method according to claim 7, wherein the control discrimination algorithm may include:

blinking for two times continuously or closing eyes for more than 2s continuously, and controlling the wheelchair to brake or stop;

blinking once by eyes, and then continuously glancing twice to the right to control the right movement of the wheelchair;

10. The control method according to claim 7, characterized in that the method further comprises: