FR3037498A1 - METHOD FOR CONTROLLING A MOBILE DEVICE - Google Patents

Abstract

The invention relates to the control and control of a wheelchair (a mobile) based on the assimilation of data of visual parameters and brain activity. The control part is to validate a position of the desired look (the Iris) in the environment through brain waves. These feed the control block and are used to evaluate the state of fatigue of the user. From other brain waves, the body temperature as well as the user's heart rate have implemented the emotional state of the user. The assimilation between these two blocks, allows to define a mode of operation, which reflects the emotional state and fatigue of the user as well as the characterization of the environment (the safety of the trajectory, detection of obstacles, and the blocking situation ...). The chair movement instructions are obtained by real-time assimilation of the proximity sensor data and the active mode of travel.

Description

FIELD OF THE INVENTION The present invention relates in particular to the control of a mobile device taking into account at least one cerebral data.

A favorite application is the wheelchair industry for people with disabilities. BACKGROUND The vast majority of today's mobile devices are controlled by partially mechanical controls. Thus, a user must use a joystick, a steering wheel, a bar, or any other means of manual control to navigate a mobile device. Unfortunately, these devices are unusable for some people, including people with quadriplegia. Even for non-quadriplegic people, a means of controlling a mobile device not using manual control is interesting. This can, for example, allow the user's members to perform additional tasks, not related to the control of the mobile device. There is therefore a need for a technical solution for controlling an apparatus without the use of mechanical control.

In the latter field, we know the solution described in CN103263324. This solution allows the control of a wheelchair thanks to the cerebral data type SSVEP (Steady-State Visual-Evoked Potentials) or PEVRP (Visual Evoked Potential of Permanent Diet) in French. This technique allows a control of the wheelchair through the analysis of brain waves emitted by the user during the stimulation of his eyes with a precise frequency (from 5Hz). A continuous or harmonic frequency response is generated at the level of the visual region of the cerebral cortex with the same frequency of appearance of the stimulus. Once the correspondence between a specific light frequency and its response by the brain has been established, it is possible to determine what image the eye has visualized through the analysis of an encephalogram (EEG). In order to increase the safety of the user, sensors detecting obstacles are present on the chair. This solution has some disadvantages. Indeed, the control of a mobile device through a visual control is difficult and tiring. This results in a visual saccade effect, sporadic fixation of the ear and a decrease in the reliability of the command. The movements of the device are thus not very precise, the safety of the user is not optimal, and the great fatigue of the user prevents prolonged use.

Accordingly, there is a need to provide a solution for eliminating or at least reducing at least some of the above disadvantages.

SUMMARY OF THE INVENTION An aspect of the invention relates in particular to a method of controlling the movement of a mobile device by a user in which the motion control is based on a displacement instruction, said displacement instruction including a setpoint trajectory and a target speed, comprising a step of determining said displacement instruction. Advantageously, this method is such that the determination step comprises the following computer-implemented steps using at least one microprocessor: Generating at least one moving instruction (206) based on least on: at least one direction (203) originating from at least one point of view (103) of the user, at least one first cerebral datum of the user, said cerebral datum preferably being derived from a positive cerebral wave of the user, called P300 brain wave (101), appearing 300 ms (millisecond) after stimulation and / or issuing from a brain wave of the user, called brain wave SSVEP (102), appearing in response to predetermined visual stimulation; - Generating at least one control data item (340), at least based on: A second cerebral data of the user resulting from a P300 (101) brain wave and / or from a SSVEP brain wave (102) ) and / or from an alpha and / or beta type brain wave (112) taken at the level of the central and frontal parietal area of the cerebral cortex. physiological data among at least the temperature (105) of the user and / or his heart rate (104); Generating at least one environment data item (412) derived from at least one sensor identifying at least part of the environment of the mobile device; 3037498 3 - Generation of a displacement instruction (500) according to at least: said movement instruction (206), said control data item (340) and said environment data item (412). - Generating a setpoint path (520) and a target speed (510) 5 according to said displacement instruction. This arrangement allows control of a mobile device, taking into account visual, cerebral and physiological data. Thus, said user is helped during the control which greatly reduces the fatigue associated with the use. In addition, taking into account the environment, the security of the user is enhanced. The user's movement instruction is thus first validated by his cerebral data, which makes it possible to avoid involuntary displacements. Moreover this same instruction of displacement is assimilated with a data of control resulting from the cerebral and physiological data. This control data makes it possible to further refine the user's desire to move or not while taking into account data such as stress or fatigue. This results in a general control of the device less tiring, safer and more precise. The invention also relates to a mobile apparatus whose displacement is controlled by the method. Advantageously, this apparatus comprises different types of sensors configured to capture at least one datum according to a point of view of the user, a cerebral data and a physiological data of a user, as well as space data.

This solution makes it possible to collect the data necessary for the proper operation of the process. Thus, thanks to these sensors, the driving of the mobile device is more fluid and less tiring. BRIEF INTRODUCTION OF THE FIGURES Other features, objects and advantages of the present invention will appear on reading the detailed description which follows, and with reference to the appended drawings given by way of non-limiting examples and in which: FIG. 1 is a flowchart showing the general operation of the mobile device control method - Figure 2 details the method for determining a P300 type cerebral data as a function of a P300 brain wave; FIG. 3 details the method allowing the determination of a SSVEP-type cerebral data as a function of a SSVEP brain wave; FIG. 4 is the process of validation of the direction by the cerebral data P300 and SSVEP; FIG. 5 shows the method for determining the activation thresholds of the gaze point; - Figure 6 details the process of assimilation by fuzzy logic P300 and SSVEP data for the validation of the direction. Figure 7 is a representation of the process of determining the emotional state of the user; - Figure 8 is a representation of the process of determining the state of fatigue of the user. FIG. 9 describes the taking into account of multiple data by the fuzzy logic to determine the environment data; FIG. 10 is a graph of the transcription of speed in degree of membership in fuzzy logic; FIG. 11 is a graph of the transcription of amplitude differences in degree of membership of the fuzzy logic. Figure 12 shows the grid visible to the user to determine the direction; - Figure 13 shows a top view of the mobile device; Fig. 14 shows a side view of the mobile apparatus; DETAILED DESCRIPTION Before going into the details of preferred embodiments of the invention with reference to the drawings in particular, other optional features of the invention, which can be implemented in combination in any combination or in a manner Alternative, are given below: - the movement instruction determines an instruction trajectory among at least one or a combination of directions: advance, reverse, turn right, turn left, stop, the set trajectory being also a function of the instruction trajectory. said step of generating the displacement instruction comprises a validation of the at least one direction coming from at least one point of view of the user by the at least one first cerebral datum, in order to determine the instruction trajectory . The first and / or second cerebral data is derived from a P300 brain wave and comprises a step of generating the first and / or second cerebral data from the P300 brain wave comprising the following steps: - Reading a brain activity of the user with recording of the display time of the commands (TAC), this reading is done by electrodes dispersed on the skull of the user; - Detection of the P300 brain wave from a change in amplitude of brain activity and recording of the change time (TC); - Comparison of TAC with TC; - Generation of the first and / or second cerebral data, called P300 cerebral data, resulting from a P300 brain wave. the displacement instruction determines an instruction trajectory, wherein said step of generating the movement instruction comprises a validation of the at least one direction from at least one user's point of view by the at least a first cerebral data, in order to determine the instruction trajectory, wherein said first cerebral data originates from a P300 brain wave and in which the validation step by the at least one first cerebral data, and comprises the following steps: - If the difference between the TC and the TAC + 300 ms (10-3 seconds) is less than or equal to 100 ms then the instruction trajectory is transmitted to the displacement instruction with a validated status; If the gap between the TC and the TAC + 300 ms is greater than 100 ms, then instruction path is transmitted to the displacement instruction with a suspended status. the first and / or second cerebral data is derived from a SSVEP brain wave and comprises a step of generating the first and / or second cerebral data from the SSVEP brain wave comprising the following steps: - Appearance of the commands with prefixed frequencies (between 10 and 25Hz) (FAC); Detection of the change in amplitude of brain activity and recording of the frequency of change (FC) this reading is done by electrodes dispersed on the skull of the user; - Comparison of the FAC with the CF; 3037498 6 - Generation of the first and / or second cerebral data, called the SSVEP cerebral data, derived from a brain wave SSVEP. the move instruction determines an instruction path, wherein said step of generating the move instruction includes a validation of the at least one direction from at least one user's point of view by the at least one direction of the user. least a first cerebral data, in order to determine the instruction trajectory, wherein said first cerebral data originates from a SSVEP brain wave and in which the validation step by the at least one first cerebral data, and comprises the next steps - If the gap between the FC and the FAC is less than or equal to 10% then the instruction path is transmitted to the displacement instruction with a validated status; 15 - If the gap between the FC and the FAC is greater than 10%, then instruction path is transmitted to the movement instruction with a suspended status. the step of generating the displacement instruction comprises a validation of the at least one direction coming from at least one user's point of view (103) and in which the first and / or second cerebral datum is derived from a P300 brain wave and is called the P300 cerebral data and in which the first and / or second cerebral data is derived from a brain wave SSVEP is called the SSVEP cerebral data, said validation being performed according to the least one P300 cerebral data and at least one SSVEP cerebral data the simultaneous taking into account of the at least two brain data P300 and SSVEP being operated by a fuzzy logic system. a method comprising a step of selecting a control mode from among the following modes: manual, semi-autonomous and autonomous, the displacement instruction being in particular a function of said selected control mode, said selection of the control mode being based on said at least one control data. the generation of at least one control data item comprises the determination of a psychological and / or physiological state of the user, said psychological and / or physiological state of the user being a function of a state of fatigue and / or an emotional state of the user. The generation of the first and / or second cerebral data, called SSVEP cerebral data, is derived from a SSVEP brain wave and / or the generation of the first and / or second cerebral data, called the P300 cerebral data. derived from a P300 brain wave and in which the psychological and / or physiological state of the user is a function of a state of fatigue, said state of fatigue being in particular determined by an interpretation of the second cerebral data, said second cerebral data being the P300 cerebral data and / or the SSVEP cerebral data. the state of fatigue of the user is determined as a function of a predetermination resulting from the at least one P300 and / or SSVEP type cerebral data, of at least one pre-recorded data item in a "fatigue" database And applying the theory of Dempster-Shafer (or theory of evidence) including the application of plausibility rules. - The at least one second cerebral data from a brain wave P300 and / or SSVEP is derived from the same cerebral data P300 and / or SSVEP as the at least one first datum. said second cerebral datum is derived from an alpha and / or beta type brain wave taken at the level of the central and frontal parietal area of the cerebral cortex and in which said generation of at least one control datum also comprises the determination of of a psychological and / or physiological state of the user, said psychological and / or physiological state of the user being a function of an emotional state of said user and in which the emotional state of the user is determined by physiological data function comprising at least one user's temperature and / or a cardiac frequency of the user, and the at least one second cerebral data derived from a beta and / or alpha brain wave called alpha brain wave and / or beta, and at least one prerecorded data in an "emotions" database, said determination being made by a neural network. The psychological and / or physiological state of the user is determined by a fuzzy logic system taking into account the state of fatigue and / or the emotional state of the user. the at least one sensor is configured to allow the detection of the distance between the apparatus and obstacles located near the apparatus and / or to allow the location of the apparatus. said environment datum is derived from several types of sensor and the data of each type of sensor are processed by a fuzzy logic system, the processed data are then interpreted by a neural network allowing the determination of the location and / or the distance from the device to the obstacles, as well as the number of obstacles surrounding said apparatus. Mobile device in which: the at least one first cerebral data is captured by an EEG (electroencephalography) sensor, said EEG sensor being configured to detect and / or record at least one P300 and / or SSVEP brain wave. the at least one second cerebral datum of a user is derived from a positive cerebral wave of the user, called the P300 brain wave, appearing 300 ms (millisecond) after stimulation and / or is derived from a brain wave of the user, called SSVEP brain wave, appearing in response to a predetermined visual stimulation and / or is derived from an alpha wave and / or beta is captured by an EEG sensor (Electroencephalography), said EEG sensor being configured to detect and / or record at least one P300 and / or SSVEP brain wave and / or alpha and / or beta of said user. mobile apparatus comprising a screen configured to display a grid comprising directions and in which each direction present on the grid 20 displays a different light frequency. said at least one point of view of the user is captured by an eye-tracking sensor configured to detect and / or record the at least one point of view of at least one eye of the user when the user is looking at the 'screen. the at least one physiological data of the user is derived from a thermometer and / or a cardio-frequency meter configured to detect and record respectively the temperature and the heart rate of said user. - The environment data are derived from at least one ultrasound sensor and at least one motion sensor configured to locate the mobile device 30 and its distance vis-à-vis objects surrounding it. mobile device having at least one front face, a rear face and two lateral faces comprising ten ultrasonic sensors positioned as follows: two sensors on each of the front and rear faces of the mobile apparatus; three sensors on each of the lateral faces of the mobile device. 35 - Apparatus having at least one front face, a rear face and two side faces comprising four motion sensors positioned on each of the front, rear and side faces of the mobile device.

In order to ensure a complete understanding of the terms of the description, and unless otherwise provided in the description, the term 5-wave brain of type P300 will be understood to mean: Brain activity related to stimulation and manifesting 300 milliseconds (ms) after said stimulation. SSVEP-type brain wave (Steady-State Visueal-Evoked Potential) or PEVRP (Evoked Potential for Permanent Diet) in French: cerebral activity in response to a stimulation of the ear. Depending on the light frequency sensed by the ear, the brain emits a continuous or harmonic frequency response at the level of the visual cortex at the same frequency of appearance of the stimulus. - Dempster-Shafer Theory or Theory of Evidence: The Dempster-Shafer theory is a mathematical theory based on the notion of evidence using belief functions and plausible reasoning. The purpose of this theory is to allow the combination of separate proofs to calculate the probability of an event. Thus it is possible to take into account notions such as uncertainty or reliability. Fuzzy logic system: Fuzzy logic is an extension of the classical logic that allows the modeling of data imperfections based on the concept of fuzzy sets. It can contain elements with only a partial degree of belonging and is to a certain extent close to the flexibility of human reasoning. The fuzzy logic is, for example, described in the following publication: Multisensor data fusion: A review of the state-of-the-art, Bahador Khaleghi, Alaa Khamis, Fakhreddine O. Karray information fusion journal, 2011 - Neural networks: A neural network is a computational model whose design is inspired by the functioning of biological neurons. They are optimized by learning methods. They are placed in the family of artificial intelligence methods to which they provide a perceptive mechanism independent of the implementer's own ideas, and providing input information to formal logical reasoning. Neural networks are described in the following publication: Rifai Chai; Sai Ho Ling; Hunter, G.P .; Tran, Y .; Nguyen, HT, "Neural Network With Fuzzy Particle Swarm Optimization," Biomedical and Health Informatics, IEEE Journal of Vol. 2014. A preferred embodiment of the invention relates to a method of controlling the movement of a wheelchair for a disabled person. Naturally, the invention is not limited to this type of mobile device and an application for the control of a car, an aircraft or a drone is possible for example. More generally, any device controlled by a mobile user can use said method to move.

Figure 1 provides a general view of the invention. Advantageously, the method for controlling the displacement of the mobile device is based on a displacement instruction 500. The displacement instruction 500 is translated in particular by the generation of a reference trajectory 501 and a reference speed 502 which will influence the trajectory In order to generate said displacement setpoint 500, the method first comprises the acquisition of user data 100 and space data 400. The user data 100 comprises the actual speed and the actual speed of the mobile device. at least one piece of data, and preferably all the following data: a user's point of view 103 or a user's point of view sequence, at least one type of data item P300 110 or SSVEP 120 and preferably according to the two types of brain waves P300 101 and SSVEP 102 as well as physiological data. The physiological data preferably comprises at least one of the following data: cardiac data 104 and temperature data 105. Other types of data may of course be added. The brain waves are picked up by at least one EEG sensor (electroencephalography) 106. The P300 brain data 110 is determined by the deviation of the P300 brain waves 101 during an amplitude change. The SSVEP 120 brain data is determined by the deviation of their SSVEP 102 brain waves upon a change in their power spectral density (CDSP). Advantageously, in order to determine the difference in the amplitude change of a P300 type 101 brain wave, the following steps will be performed: - Reading of a brain activity and recording of the display time of the commands (TAC); - Amplitude change detection in response to stimulation and recording of change time (TC); 3037498 11 - Comparison of TC to TAC + 300ms. - Determination of the gap between the TC and the TAC + 300ms. These steps are illustrated in FIG. 2. Preferably, in order to determine the difference in the CDSP change of the SSVEP waves 102, the following steps will be performed: - Reading of a brain activity and recording of the frequency of appearance orders (FAC); - Detecting the change of CDSP in response to stimulation and recording the change frequency (FC); 10 - CF comparison to CAF; These steps are illustrated in FIG. 2. In a second step, said data of the user 100 and of space 400 will make it possible to generate a displacement instruction 206, a control datum 340 and a datum 412. The displacement instruction 206 includes the analysis and interpretation of said at least one look point 103 or the sequence of a look-point of the user and at least a first and preferably two first P300 type data 110 and / or SSVEP 120 (Figure 3). Said interpretation of these data 20 allows the generation of a validated or non-validated instruction path 220 which will be integrated into the displacement instruction (FIG. 4). This generation is performed by the step of determining the displacement instruction 200. The point of view of the user 103 is acquired by an eye tracking sensor 107 (Eye-tracking in English) preferably arranged below In another embodiment, the sensor is above the screen, or at any other position to capture the view of the user optimally. Advantageously, the eye-tracking sensor 107 makes it possible to detect the point of view of the user on the screen 202. FIG. 5 details an embodiment of the operation of the eye-tracking sensor 107 and the capture of at least one point of view. of the user 103.

Said screen 202 displays at least one grid 201. FIG. 9 details the sequences of viewing points present on the grid 201 (FIG. 12). The grid 201 comprises at least two columns and two lines and preferably three columns and three lines. Each of the boxes of said grid 201 corresponding to a direction. The direction displayed by one box of the grid is at least one of the following directions: forward, backward, right, left and stop. In addition each of the boxes has a specific light frequency. The light frequency of each of the cells of the grid is between 10Hz and 25Hz. In a preferred embodiment of the invention, behind the grid 201 is displayed a representation of the environment facing the mobile device. In order to represent the environment in front of the device, a first camera is present on the front of the mobile device. Advantageously a second camera is present at the rear of mobile device. This second camera can also provide a display of the environment behind the back side of the mobile device. The two cameras are not shown in the figures. The display being performed on the screen 202 during the reverse of the mobile device. Thus, the determination of the moving instruction 206 includes the selection by the user of a direction 203 displayed on a square of the grid 201. The selection of a square of the grid 201 is a stimulation of the brain which will generate a P300-type brain wave 101. In addition, the box having a specific light frequency, a brain wave SSVEP 102 will also be generated. The P300 101 and SSVEP 102 brainwaves will make it possible to determine a first cerebral data P300 110 and SSVEP 120. The simultaneous taking into account of the first two first P300 110 and SSVEP 120 cerebral data for the displacement instruction is performed. by a fuzzy logic system. An example of the assimilation of the first data P300 and SSVEP 204 by the fuzzy logic is given in FIG. 6. The interpretation of said first brain data of the P300 110 and SSVEP 120 type by the fuzzy logic system will make it possible to carry out a validation step 205 of the selected direction 203. Thus, if the difference between the TC and the TAC + 300ms is less than or equal to 100 ms and / or the difference between the FC and the FAC is greater than Y, then the direction is validated by the first cerebral data P300 110 and / or the first data SSVEP 120. If the difference 25 between the TC and the TAC + 300 ms is greater than 100 ms and / or the difference between the FC and the FAC is greater than Y, then the direction is not validated by the first cerebral data SSVEP 120 and / or the first data SSVEP. In case of validation of the direction selected by the user, an instruction path is generated with a validated status.

In case of non-validation of the direction selected by the user, an instruction trajectory is generated with a suspended status. Said validated instruction trajectory 210 or suspended 220 is then integrated with the displacement instruction. The validation method 205 of the selected direction 203 by at least one first P300 data item 110 110 and SSVEP 120 is illustrated in FIG. 4.

Advantageously, the control data 340 will make it possible, thanks to the determination step 300, to select a control mode 350 of the mobile device from at least one of the following modes: manual, semi-autonomous and autonomous. In another embodiment of the invention control modes 350 may be deleted or added. This is the selected control mode 350 which will be integrated in the displacement instruction. Said control data 340 comprises at least one physiological and / or physiological data item 331, at least one second cerebral data item of the P300 110 or SSVEP 120 type and / or alpha and / or beta frequency band 130, at least one pre-recorded data item derived from a "fatigue" database 310 and another data item from an "emotion" database 320. Preferably, the control data item 340 comprises two second cerebral data of the P300 110 and / or SSVEP 120 and / or band type. frequency alpha and / or beta 130 and physiological and / or psychological data 331 a function of the heart rate (cardiac data 104) and the temperature (temperature data 105) of the user. These data combined or not between them allow the determination of a state of fatigue 312 and an emotional state 322 of the user. The fatigue database contains the alpha and beta brain waves as well as the maximum amplitudes and the period of appearance of the P300 at the EEG sensors.

Advantageously, the first cerebral data P300 110 and / or SSVEP 120 and the second cerebral data P300 110 and / or SSVEP 120 are derived from the same brain waves P300 101 and / or SSVEP 102. "Emotion" data, contains the normalized variations of the asymmetries of the alpha and beta frequency bands at the parietal, central and frontal portion of the cerebral cortex. In addition, it incorporates changes in heart rates that are correlated with different states of emotion as well as body temperature data. Advantageously, the fatigue state 312 of the user is a function of a second cerebral data P300 110 and / or SSVEP 120 and at least one pre-recorded data 30 in a "fatigue" database 310. Said second cerebral data P300 110 and / or SSVEP 120 is preferably the same as the first cerebral data previously used by the displacement instruction 206. Nevertheless, the interpretation of the difference between the TC and the TAC + 300ms and / or between the CF and the FAC are different. In addition, the simultaneous consideration 311 of the P300 101 and / or SSVEP 32 brain waves by the control data 340 to determine the fatigue state 312 is performed by the Dempster-Shafer theory or theory of evidence. In this configuration, the difference between these values makes it possible to determine the fatigue state 312 of the user. Indeed, a correlation exists between the state of fatigue of the user the deviation of the maximum amplitude as well as the duration of appearance of the P300, and the observed difference of the maximum amplitude of FC. Thus, if the difference between the normalized amplitudes of the P300 is less than 10% and / or the difference in amplitudes of the predominant frequency of the SSVEP is less than 15% then an average fatigue state is determined. In a preferred but nonlimiting embodiment of the invention, four levels of fatigue can be determined (high, medium, low and nonexistent fatigue). In other embodiments of the invention, the number of fatigue levels may vary positively or negatively. The correspondence between the deviations of the P300 110 and / or SSVEP 120 brain data and the fatigue state 312 is possible by comparing these deviations with the fatigue database 310 and the incorporation of plausibility rules. The method for determining the state of fatigue 312 is illustrated in FIG. 8. Advantageously, an emotional state 322 is also generated as a function of the physiological data and the at least one second cerebral data P300 110 and / or SSVEP 120 and / or alpha and / or beta data 130 and at least one prerecorded data in an "emotion" database 320. " The evolution of alpha waves and / or beta 112 over time, is correlated with the emotional state expressed. Once again, the deviation of the normalized amplitudes of these waves is calculated. If this latter increases by 15%, a state of stress is detected. Associated with the user's cardiac data 104 and temperature data 105, it is possible to determine the emotional state 322 of the user. The logic allowing the interpretation and the assimilation 321 of these multiple data is in particular the networks of neurons. Other theories can of course be used for the interpretation of these data.

Advantageously and in a general manner, the first cerebral data P300 110 and / or SSVEP 120 and the second cerebral data P300 110 and / or SSVEP 120 are derived from the same brain waves P300 101 and / or SSVEP 102. Advantageously, the emotional state 322 is determined among the following four states: stress, nervousness, relaxation, excitation. The number of emotional states 322 present 30 is not limiting, and the addition or deletion of emotional states is possible. The simultaneous consideration 321 of the brain data, physiological data (temperature and heart rate) and at least one datum from the "emotion" database 322 is produced by a neuron network. This method of determining the emotional state 322 of the user is illustrated in FIG.

Once the fatigue state 312 and the emotional state 322 of the user have been determined, the combination of these states 330 by a fuzzy logic system allows the determination of a psychological state 331 of the user. It is according to the user's psychological state 331 that the control mode 350 will be selected. Once the control mode 350 has been selected, said selection is integrated in the displacement instruction.

Advantageously, the space data 400 is a function of at least one environment sensor. In a preferred embodiment of the invention, at least one environmental sensor comprises at least one motion sensor 402 and at least one ultrasonic sensor 401, and preferably four motion sensors 402 and ten ultrasound sensors 401 (FIGS. 14). Preferably, the mobile apparatus comprises three ultrasonic sensors 401 and a motion sensor 402 on each of these side faces. Two ultrasonic sensors 401 and a motion sensor 402 are positioned on each of the front and rear faces of the mobile device. When the mobile device is a wheelchair for a disabled person, then the ultrasound sensors 401 are positioned on the chassis of said wheelchair.

In this embodiment the positioning of the ultrasonic sensors 401 on the frame is preferably as close to the ground as possible. The motion sensors 402 are preferably positioned above the ultrasound sensors 401. Advantageously, the ultrasonic sensors 401 enable the generation of an ultrasound data 403. Said ultrasound data 403 comprises the detection of the number of ultrasounds. obstacles and their positions. Thus, according to a specific algorithm, the data from the ultrasonic sensors 401 allow the calculation of the location of the mobile device in an inner room. In external environment, the location of the device can be achieved by any other means, such as with a geolocation chip of satellite type. Ultrasonic sensors 401 advantageously have a maximum range of at least 3 meters and preferably 6 meters. This advantageous configuration allows a detection of the number of obstacles surrounding the mobile device, as well as their distances vis-à-vis said mobile device. The motion sensors 402 enable generation of motion data 404. Said motion data 404 allows detection of any activity around the mobile device. Said motion sensors 402 advantageously have a maximum range of 2 meters and preferably a range of 4 meters. The ultrasound data 403 and the movement data 404 allow the location of the device, as well as its distance from the obstacles and the number of obstacles. All these elements define the environment data item 412. Said environment data item 412 is then integrated with the displacement instruction. Finally, the data from the different types of ultrasonic sensors 401 and movements 402 are assimilated by a fuzzy logic system 411 described in FIG. 9. This step of assimilating the ultrasound data 403 and the movement 404 to determine the environment datum is the block 410 of FIG. 9. The displacement instruction then processes and analyzes the validated or non validated instruction path 220, the control mode 350 as well as the environment datum 412. To carry out this information processing, it advantageously comprises a computer (preferably a microprocessor and / or a programmable logic circuit (FGPA in English)) and an internal memory. In another embodiment of the invention, the computer is remote and only the displacement instruction 500 is sent to the mobile device for its application. The processing of these data is carried out according to a fuzzy logic system in order to determine a displacement speed 501 as well as a displacement path 502 (FIGS. 11 and 12). Advantageously, the speed can be determined by two methods: either at 15 using encoders mounted on the chair or through data from motion sensors 402 of ultrasonic sensors 401. Thus, in a preferred embodiment of the invention, the mobile device moves at a maximum speed by default. Then, a speed reduction coefficient is applied according to the data received. The sensor for detecting the speed of the apparatus is preferably an odometer. Other speed sensors can of course be added. In another embodiment of the invention, there is no default speed. In this case, the speed is determined by the position of the at least one look point or visual sequence 103 on the grid 201. The taking into account of all these data allows a refinement of the displacement instruction 500. For example, if the user is tired, the mobile device will determine a control mode 350 autonomous, and allow validation of the "suspended" directions 210. Taking into account the fatigue state 312 allows to correct this data and to allow an easy move. Similarly, in the event of an obstacle, the ultrasonic sensor 401 allows an automatic bypass, or a half-turn of the mobile device. Thus, the user does not remain stuck in front of the obstacle. From the foregoing description it is clear that the invention offers a particularly effective solution for controlling a mobile device accurately, reliably and particularly comfortable for the user. The mobile device can therefore be driven during the time intervals much wider than with other known solutions.

The invention is not limited to the previously described embodiments but extends to all embodiments within the scope of the claims.

3037498 REFERENCES 100. User data; 101. P300 brainwave; 5 102. Brain wave SSVEP; 103. Point of view of the user; 104. Cardiac data; 105. Temperature data; 106. Encephalography sensor 107. Eye-tracking sensor; 108. Cardio-frequency meter; 109. Thermometer; 110. P300 brain data; 111. Determination of a P300 cerebral data; 112. Brain wave Alpha and / or Beta 120. Brain data SSVEP; 121. Determination of a cerebral data SSVEP; 130. Alpha and / or Beta 200 brain data. Determining displacement instruction data; 201. Grid; 202. Screen 203. Selection of a direction by the user; 204. Assimilation of P300 30 and SSVEP data; 205. Validation of the direction selected by the cerebral data 206. Movement instruction 210. Determination of a valided instruction trajectory; 220. determination of a suspended instruction trajectory; 300. Step of determining the control data; 310. Fatigue database 311. Assimilation by the theory of evidence 45 312. State of fatigue 320. Database "emotion"; 321. Assimilation by the theory of evidence; 322. Emotional state; 50 330. Fuzzy logic assimilation 331 Psychological and / or physiological state 340. Control data 350. Control mode; 55 400. Space data 401. Ultrasonic sensor; 402. Motion sensor; 403. Ultrasound data; 60 404. Data of movements; 410. Determination of the environmental data; 411. Assimilation of the environment by fuzzy logic; 65 412. Environmental data; 3037498 19 500. Setpoint displacement, 510. Setpoint speed; 520. Trajectory setpoint.

Claims (24)

REVENDICATIONS1. A method of controlling the movement of a mobile device by a user in which the displacement control is based on a displacement instruction (500), comprising a step of determining said displacement instruction (500) characterized, in that this step method comprises the following computer-implemented steps using at least one microprocessor: - Generating at least one moving instruction (206) based on at least: at least one direction (203) issued from at least one point of view (103) of the user, at least one first cerebral data of the user, said cerebral data being derived from a positive cerebral wave of the user, called the P300 brain wave (101) , appearing 300 ms (millisecond) after stimulation and / or from a user's brain wave, called SSVEP brain wave (102), appearing in response to a predetermined visual stimulation; - Generation (300) of at least one control data item (340), at least based on: A second cerebral data of the user resulting from a P300 (101) brain wave and / or from a brain wave SSVEP (102) and / or from an alpha and / or beta (112) brain wave at the level of the central and frontal parietal area of the cerebral cortex. physiological data among at least the temperature (105) of the user and / or his heart rate (104); - Generation of at least one environment data (412) from at least one sensor identifying at least part of the environment of the mobile device; - Generation of a displacement instruction (500) according to at least: said movement instruction (206), said control data (340) and said environment data (412). - Generating a setpoint path (520) and a target speed (510) as a function in particular of said displacement instruction. 3037498 20 2. Method according to the preceding claim wherein the displacement instruction (206) determines an instruction trajectory among at least one or a combination of directions: advance, reverse, turn right, turn left, stop, the trajectory setpoint (500) also being a function of the instruction trajectory. 3. Method according to the preceding claim, wherein said step of generating the displacement instruction comprises a validation (205) of the at least one direction (203) coming from at least one point of view of the user ( 103) by the at least one first cerebral data, in order to determine the instruction trajectory. 4. A method according to any one of the preceding claims wherein the first and / or second cerebral data originates from a P300 brain wave (101) and comprises a step of generating (111) the first and / or the second cerebral data (111) derived from the P300 brain wave (101) comprising the following steps: - Reading of a brain activity of the user with recording of the display time of the commands (TAC); - Detection of the P300 (101) brain wave from a change in amplitude of brain activity and recording of the change time (TC); - Comparison of TAC with TC; 25 - Generation of the first and / or second cerebral data, called the P300 cerebral data (110), resulting from a P300 (101) brain wave. The method of the preceding claim, wherein the move instruction (206) determines an instruction path, wherein said step of generating the move instruction comprises a validation (205) of the at least one direction. (203) derived from at least one point of view of the user (103) by the at least one first cerebral datum, in order to determine the instruction trajectory, in which said first cerebral data originates from a brain wave P300 (101) and wherein the validation step (205) by the at least one first cerebral data, and comprises the following steps: - If the gap between the TC and the TAC + 300 ms (10- 3 seconds) is less than or equal to 100 ms then the instruction path is transmitted to the movement instruction with a validated status (220); If the difference between the TC and the TAC + 300 ms is greater than 100 ms, then instruction path is transmitted to the movement instruction with a suspended status (210). 6. Method according to any one of the preceding claims wherein the first and / or second cerebral data originates from a brain wave SSVEP (102) and comprises a step of generating (121) the first and / or second cerebral data from the SSVEP brain wave (102) comprising the following steps: - Appearance of commands with prefixed frequencies (between 10 and 25Hz) (FAC); Detecting the change in amplitude of brain activity and recording the change frequency (FC); - Comparison of the FAC with the CF; Generation of the first and / or second cerebral data, called the cerebral data SSVEP (120), issued from a brain wave SSVEP (102). 20 7. The method according to the preceding claim, wherein the displacement instruction (206) determines an instruction trajectory, wherein said step of generating the displacement instruction comprises a validation (205) of the at least one direction ( 203) derived from at least one point of view of the user (103) by the at least one first cerebral datum, in order to determine the instruction trajectory, wherein said first cerebral datum is derived from a brain wave SSVEP (102) and wherein the validation step (205) by the at least one first cerebral data, and comprises the following steps 30 - If the gap between the FC and the FAC is less than or equal to 10% then the instruction path is transmitted to the movement instruction with a validated status (220); If the gap between the FC and the FAC is greater than 10%, then instruction path is transmitted to the movement instruction with a suspended status (210). 3037498 22 The method of claim 3, wherein the step of generating the move instruction comprises enabling (205) the at least one direction (203) from at least one user's look-up point (203). 103) and wherein the first and / or second cerebral data originate from a P300 brain wave (101) and are referred to as P300 cerebral data (110) and wherein the first and / or second cerebral data are derived from a SSVEP brain wave (102) is called the SSVEP cerebral data (120), said validation (205) being performed as a function of the at least one P300 cerebral data (110) and the at least one SSVEP cerebral data (120) simultaneously taking into account the at least two brain data P300 (110) and SSVEP (120) being operated by a fuzzy logic system (204). A method according to any one of the preceding claims comprising a step of selecting (300) a control mode (350) from among the following modes: manual, semi-autonomous and autonomous, the displacement instruction (500) being in particular a function of said control mode (350) selected, said selection of the control mode being based on said at least one control data (340). 20 10. Method according to the preceding claim wherein the generation (300) of at least one control data (340) comprises the determination of a psychological and / or physiological state (331) of the user, said psychological state and / or physiological (331) of the user depending on a state of fatigue (312) and / or an emotional state (322) of the user. 25 11. Method according to the preceding claim wherein the generation of the first and / or second cerebral data, called SSVEP cerebral data (120), is derived from a brain wave SSVEP (102) and / or the generation of the first and / or the second cerebral data, called the P300 cerebral data (110), originates from a P300 (101) brain wave and in which the user's psychological and / or physiological state (331) is a function of a fatigue state (312), said fatigue state being determined in particular by an interpretation of the second cerebral data, said second cerebral data being the P300 cerebral data (110) and / or the cerebral data SSVEP (120). 3037498 23 12. Method according to the preceding claim wherein the fatigue state (312) of the user is determined according to a predetermination from the at least one type of data P300 (110) and / or SSVEP (120). ), at least one prerecorded data in a database "fatigue" (310), and applying the theory of evidence (311) including the application of plausibility rules. 13. The method as claimed in claim 1, in which said second cerebral datum is derived from an alpha and / or beta type brain wave (112) taken at the level of the central and frontal parietal zone of the cerebral cortex and in which said generation (300) of at least one control data item (340) also comprises the determination of a psychological and / or physiological state (331) of the user, said psychological and / or physiological state (331) of the user being a function of an emotional state (322) of said user and wherein the emotional state (322) of the user is determined based on physiological data including at least one user's temperature (105) and / or a heart rate of the user (104), and the at least one second cerebral data derived from a beta and / or alpha brain wave (112) called alpha and / or beta brain wave, and at least one data prerecorded in an "emotions" database (320), said determination being performed by a neural network (321). 25 14. The method of claim 10 wherein the psychological and / or physiological state of the user is determined by a fuzzy logic system (330) taking into account the state of fatigue (312) and / or the emotional state. (322) of the user. 30 15. The method of claim 1 wherein the at least one sensor is configured to allow the detection of the distance between the device and obstacles located near the device and / or to allow the location of the device. 35 16. Method according to the preceding claim wherein said environment data (412) is derived from several types of sensor and the data 3037498 24 of each type of sensor are processed by a fuzzy logic system (411), the processed data is then interpreted by a neural network for determining the location and / or distance of the apparatus from the obstacles, as well as the number of obstacles surrounding said apparatus. Mobile apparatus the movement of which is controlled by the method according to any one of the preceding claims comprising different types of sensors configured to capture at least one user's viewing point (103), brain data and physiological data. of the user, as well as space data (400) relating to an environment of the mobile device. 18. Mobile device according to the preceding claim comprising at least one electroencephalographic (EEG) sensor (106) configured to capture at least one of the following brain waves: a user's cerebral-positive wave called the P300 brain wave (101) appearing 300 ms (millisecond) after stimulation, a brain wave of the user called SSVEP brain wave (102) appearing in response to a predetermined visual stimulation, an alpha brain wave of the user, a beta brain wave of the user. Mobile apparatus according to any one of the two preceding claims comprising a screen (202) configured to display a grid (201) comprising directions and wherein each direction present on the grid (201) displays a different light frequency. Mobile device according to the preceding claim, comprising an eye-tracking sensor (107) configured to detect and / or record at least one viewing point (103) of at least one iris of the user when the user is looking at the camera. screen (202). Mobile apparatus according to one of the four preceding claims comprising a thermometer (109) and / or a cardio-frequency meter (108) configured to detect and record respectively a temperature and a heart rate of the user, the apparatus The mobile device is configured such that the at least one physiological data of the user is derived from the thermometer (109) and / or the cardio frequency meter (108). Mobile apparatus according to any one of the five preceding claims comprising at least one ultrasound sensor (401) and at least one motion sensor (402) configured to locate the mobile device and its distance from each other. to surrounding objects, the mobile apparatus being configured to generate environment data (412) from the at least one ultrasound sensor (401) and the at least one motion sensor (402). . 10 23. Mobile device according to the preceding claim, having at least one front face, a rear face and two side faces and comprising ten ultrasonic sensors (401) positioned as follows: - two sensors on each of the front and rear faces of the mobile apparatus; three sensors on each of the lateral faces of the mobile device. 24. Mobile device according to one of the two preceding claims having at least one front face, a rear face and two side faces and comprising four movement sensors (402) positioned on each of the front, rear and side faces of the apparatus. mobile.