A control method and device of a suspended multifunctional vehicle interactive robot

Abstract

The application relates to a control method and device of a suspended multifunctional vehicle-mounted interactive robot, which comprises the following steps: when an intelligent networked vehicle starts, the vehicle-mounted interactive robot is suspended in the air, it is judged whether the current driver is the vehicle owner, the vehicle owner's facial expression is recognized, and friendly interaction is carried out; a voice instruction is issued by the vehicle owner, voice interaction is carried out between the vehicle-mounted interactive robot and the vehicle owner, the vehicle-mounted interactive robot is made to face the vehicle owner according to the direction in which the vehicle owner is located; vehicle speed information is acquired, the magnetic suspension force field of the vehicle-mounted interactive robot is adjusted according to the vehicle speed information, and the vehicle-mounted interactive robot is prevented from flying out from above the magnetic suspension dynamic control module to cause accidental injury.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent networked vehicles, in particular to a control method and device of a suspended multifunctional vehicle-mounted interactive robot. BACKGROUND

[0002] With the development trend of intelligentization, networking, experience, and personalization driving the rapid transformation of vehicles into the largest intelligent terminal, users' acceptance of device intelligence is continuously improving, and in the context of the Internet of Things era, users' demand for personalized human-vehicle interaction is increasingly strong. In order to meet the above requirements of users and build the core channel of human-vehicle interaction, the current personalized human-computer interaction mainly adopts screen interaction and holographic form interaction as the main mode, supplemented by screen interaction.

[0003] Screen interaction, as a relatively traditional human-computer interaction method, directly interacts with the driver through touch, graphics, and text on the vehicle display screen. With the continuous increase in the size and number of in-vehicle display screens, the degree of information interaction fragmentation is enhanced, and there are many potential risks in terms of interaction integrity and driving safety. Therefore, to solve the above problems, the current method proposes to use holographic technology as the main interaction method, supplemented by vehicle screens, to improve driving safety, reduce interaction fragmentation, and further improve interaction experience. However, this method does not fundamentally solve the problems of driving safety and interaction fragmentation, and the use of holographic technology is affected by light, which leads to new obstacles in the transmission of interactive information, thereby causing new problems.

[0004] Therefore, to solve the problem that traditional automobile human-computer interaction devices are mainly composed of instrument panels, central controls, and vehicle information entertainment (IVI) terminals, which use functional partitioning to cause fragmentation of interactive functions, on the other hand, the automobile interaction accelerates the transition to artificial intelligence, requiring new automobile human-computer interaction methods to be more humanized, stereoscopic, and real, and to focus on interactivity, and on the third aspect, to ensure that the driver's line of sight is always in front of the vehicle during driving, reduce the time away from the forward line of sight, and enhance driving safety. SUMMARY

[0005] To solve the above problems, the present application provides a control method and device of a suspended multifunctional vehicle-mounted interactive robot, which can ensure the integrity of interactive information, has good interaction experience, and can enhance driving safety.

[0006] To achieve the above object, in the first aspect, the application adopts the following technical scheme: a control method of a suspended multifunctional vehicle-mounted interactive robot, comprising: when an intelligent connected vehicle starts, suspending the vehicle-mounted interactive robot in the air, determining whether the current driver is the vehicle owner, performing vehicle owner facial expression recognition, and performing friendly interaction; issuing a voice command by the vehicle owner, performing voice interaction with the vehicle-mounted interactive robot, making the vehicle-mounted interactive robot face the vehicle owner according to the direction in which the vehicle owner is located; obtaining vehicle speed information, adjusting the magnetic suspension force field of the vehicle-mounted interactive robot according to the vehicle speed information, and avoiding the vehicle-mounted interactive robot from flying out from above the magnetic suspension dynamic force control module to cause accidental injury.

[0007] Further, the determination of whether the current driver is the vehicle owner comprises: determining whether the current driver is the vehicle owner through image recognition, and uploading the driver information through interaction with the Internet of Things service background through a 5G network, notifying the vehicle owner of the vehicle start condition if the driver information does not match the information in the Internet of Things service background, and performing facial expression recognition if the information matches.

[0008] Further, the voice interaction comprises:

[0009] The vehicle owner sends a voice command to the vehicle-mounted interactive robot to perform voice interaction.

[0010] The vehicle-mounted interactive robot analyzes the voice command, sends corresponding control commands to other vehicle controllers, controls other vehicle controllers to complete the command requirements, and determines the direction in which the vehicle owner is located according to a sound field positioning method.

[0011] Further, the facial expression recognition of the vehicle owner and the sound field positioning method comprise:

[0012] The driver issues a voice command to the suspended multifunctional vehicle-mounted interactive robot.

[0013] It is determined whether the command information includes voice and image information of the driver, image processing is performed if the image information is included, and sound field positioning is performed if the voice information is included.

[0014] The driver's face image and the part of the sound reflecting the emotion are packaged and sent to the Internet of Things service background through a 5G network for face recognition big data processing to check whether the driver is the vehicle owner.

[0015] The human emotion big data processing of the Internet of Things service background will intelligently match the facial emotion gallery of the Internet of Things service background to determine the emotional state of the interactive driver, and will also use the part of the driver's voice and tone reflecting the emotion to comprehensively determine the current driver's emotion, and will return the current driver's emotional result to the robot.

[0016] The robot communicates with the driver by using corresponding interactive expressions and tone to improve the interactive friendliness.

[0017] The owner of the vehicle is informed by short message that the vehicle is currently driven by a non-owner, and whether to authorize service;

[0018] The current unauthorized result is sent back to the robot, and the robot gives a voice prompt to the driver that the authorization is not authorized, and the interaction action is completed.

[0019] Further, the image processing includes:

[0020] The driver image is filtered by an image filtering algorithm, the background of the image recognition is removed according to the pre-calibration of the camera of the vehicle interactive robot, and the face image distortion caused by the camera is corrected. The face image is determined to be complete, and in the case of incomplete or insufficient completeness, the recognition of half of the face image is completed first, and the complete face image is completed based on the data, and the driver face image area is obtained;

[0021] The driver face image is extracted, and the part reflecting the driver's emotion is extracted.

[0022] Further, the sound field positioning includes:

[0023] The noise of the driver's voice is filtered by an audio filtering algorithm, and the background noise interference source is removed;

[0024] The time difference of the driver's voice reaching the two microphones of the robot is amplified by an audio amplification algorithm, the sound source direction of the sound is determined to be on the left, right or front of the robot, and the robot is instructed to rotate towards the sound source direction. The display screen of the robot will rotate according to the instruction;

[0025] The driver's voice is extracted, and the part reflecting the driver's emotion is extracted.

[0026] Further, the vehicle interactive robot is directly faced to the owner according to the direction of the owner, including: according to the direction of the owner, the vehicle interactive robot is directly faced to the user through the steering control processing.

[0027] Further, the magnetic suspension force field of the vehicle interactive robot is adjusted, including: if the vehicle speed reaches the pre-set speed preset, the magnetic suspension force is reduced, the suspension height of the interactive controller is reduced, and the vehicle interactive robot is reset.

[0028] In the second aspect, the present application adopts the following technical scheme: a control device of a suspended multifunctional vehicle interactive robot, the control device is used to realize the above control method, and the control device includes:

[0029] The magnetic suspension power control module is connected with the artificial intelligence controller, receives the control instruction transmitted by the artificial intelligence controller, controls the magnetic suspension force field of the vehicle-mounted interactive robot, and suspends the vehicle-mounted interactive robot in the air or resets the vehicle-mounted interactive robot;

[0030] The voice recognition module is used for recognizing the voice instruction of the driver, transmitting to the artificial intelligence controller, and performing voice interaction with the driver;

[0031] The image recognition module is used for recognizing the facial expression of the driver, transmitting to the artificial intelligence controller, and performing friendly interaction with the driver according to the recognized expression;

[0032] The steering control module is connected with the artificial intelligence controller, controls the vehicle-mounted interactive robot suspended in the air to steer according to the control instruction transmitted by the artificial intelligence controller, and makes the vehicle-mounted interactive robot face the driver;

[0033] The vehicle body data module is used for acquiring the current state information of the vehicle and transmitting to the artificial intelligence controller;

[0034] The artificial intelligence controller is connected with the Internet of Things service background through the 5G communication module, and interacts with the Internet of Things service background by the current device, vehicle, and owner identity recognition information.

[0035] In a third aspect, the present application adopts the following technical solution: a computer readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the above methods.

[0036] The present application has the following advantages due to the above technical solutions:

[0037] 1、The present application fuses GPS positioning technology, electromagnetic suspension technology, CAN bus collection technology, 5G communication technology, voice recognition technology, directional sound field technology, image recognition technology, emotion recognition technology and Internet of Things technology to provide a more personalized new intelligent man-machine interaction for intelligent networked vehicles.

[0038] 2、The present application is based on electromagnetic suspension technology, controls the size of the suspension magnetic force generated by the current, and controls the magnetic field by combining the position sensor and the controller, so that the suspended multifunctional vehicle-mounted interactive robot can be stably suspended in the air, thereby solving the problem of reducing the suspension height of the suspended multifunctional vehicle-mounted interactive robot during vehicle driving, avoiding the robot flying out due to inertia caused by sudden change of vehicle speed, and causing driving danger, and solving the problem of self-rotation of the suspended multifunctional vehicle-mounted interactive robot during vehicle driving.

[0039] 3、The application is based on directional sound field technology, can determine the sound source of voice instruction, and thus controls the display screen of the robot to turn by the turning control module, so as to achieve face-to-face interaction and improve interaction interactivity.

[0040] 4、The application is based on image recognition technology and emotion recognition technology, recognizes the emotion of the driver and other interactive personnel, especially intelligently matches according to the tens of thousands of Asian race face emotion databases of the Internet of Things service background, so as to accurately judge the emotional state of the interactive personnel, especially the driver, and improve the interaction experience.

[0041] In summary, the device solves the problems of integrated interaction information and ensures the integrity of the interaction information; makes the car human-computer interaction mode more humanized, stereoscopic and real, focuses on interactivity, gives the driver a good interaction experience; ensures that the driver's line of sight is always in front of the vehicle during driving, reduces the time of deviating from the forward line of sight, and enhances the driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 is a control method flow chart of the suspension type multifunctional vehicle-mounted interactive robot in an embodiment of the application;

[0043] Figure 2 is a control device structure schematic diagram of the suspension type multifunctional vehicle-mounted interactive robot in an embodiment of the application;

[0044] Figure 3 is an artificial intelligence fusion algorithm flow of the suspension type multifunctional vehicle-mounted interactive robot in an embodiment of the application. DETAILED DESCRIPTION

[0045] To make the purpose, technical scheme and advantages of the embodiments of the application clearer, the technical scheme of the embodiments of the application will be described clearly and completely below with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the described embodiments of the application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the application.

[0046] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should also be understood that when the terms "comprise" and / or "include" are used in the specification, there is a feature, step, operation, device, component and / or combination thereof.

[0047] The present application fuses GPS positioning technology, electromagnetic suspension technology, CAN bus collection technology, 5G communication technology, voice recognition technology, directional sound field technology, image recognition technology, emotion recognition technology and Internet of Things technology to provide a more personalized new intelligent man-machine interaction for an intelligent networked vehicle. In the starting process of the intelligent networked vehicle, the magnetic suspension dynamic control module of the suspended multifunctional vehicle-mounted interactive robot is powered on to provide a current to generate a magnetic field to provide a magnetic suspension force field, and the position sensor determines whether the current interactive robot is in a self-rotation state and the direction of rotation in the horizontal direction, and generates a magnetic field force in the opposite direction of rotation by the magnetic suspension dynamic control module, so that the vehicle-mounted interactive robot can stably float in the air. At the same time, the image and voice recognition capability is turned on, and after calibrating the camera and left and right microphone matrix of the vehicle-mounted interactive robot in advance, the driver image is collected preferentially, but since the suspended multifunctional vehicle-mounted interactive robot needs to face all passengers in the vehicle, its installation position is mainly in the central position of the vehicle center console, which may result in that the vehicle-mounted interactive robot cannot directly obtain the complete facial image of the interactive personnel, especially the driver, during the image collection process. Therefore, in the case that the obtained facial image is incomplete or not complete enough, the half facial image is processed first, and the complete facial image is completed based on the data, and compared with the pre-stored driver image to determine whether the current driver is the owner, and through the 5G network and Internet of Things service background interaction, the owner is notified of the vehicle start condition in the case that the driver is not the owner. When the driver communicates with the interactive controller by voice, the interactive controller first determines the sound source by directional sound field technology, and controls the display screen of the interactive controller by the steering control module to make the display screen face the driver, and then performs facial image recognition, focuses on collecting the eye corners, mouth corners and face that can indicate human emotions, and uploads the facial and key part information through the 5G network and Internet of Things service background interaction, and judges the facial emotion of the person at the current sound source according to the feedback of the background, displays various expressions on the display screen to give the interactive person a friendly facial interaction feeling, and understands the instructions issued by the driver through voice recognition technology and executes them. When the vehicle is driving, in order to prevent the interactive controller from flying out of the magnetic suspension dynamic control module due to inertia caused by emergency braking and causing accidental injury, the vehicle speed information is obtained through the vehicle body data module, and when a certain speed threshold is reached, the magnetic suspension force field provided by the magnetic suspension dynamic control module is adjusted by reducing the current output to reduce the magnetic suspension force and the suspension height of the interactive controller, so that the interactive controller enters the lower limit groove of the magnetic suspension dynamic control module.

[0048] The application will show that the voice and image effective fusion will integrate the original fragmented functions, and introduce the personalized, three-dimensional and interactive interaction mode, so that the car human-computer interaction mode is more humanized, convenient and fast. At the same time, the voice is used as the main interaction mode to ensure that the driver keeps the line of sight in the front of the vehicle during driving, reduces the time of deviating from the forward line of sight, and enhances the driving safety.

[0049] In an embodiment of the application, a control method of a suspended multifunctional vehicle interactive robot is provided.

[0050] In this embodiment, as shown in the figure, the method comprises the following steps: Figure 1

[0051] 1) When the intelligent connected vehicle starts, the vehicle interactive robot is suspended in the air, it is determined whether the current driver is the vehicle owner, the vehicle owner's facial expression is recognized, and friendly interaction is performed;

[0052] 2) The vehicle owner issues a voice command and interacts with the vehicle interactive robot through voice, and the vehicle interactive robot faces the vehicle owner according to the direction of the vehicle owner;

[0053] 3) The vehicle speed information is obtained, and the magnetic suspension force field of the vehicle interactive robot is adjusted according to the vehicle speed information to avoid the vehicle interactive robot flying out from above the magnetic suspension dynamic control module and causing accidental injury.

[0054] In the above step 1), it is determined whether the current driver is the vehicle owner, specifically: through image recognition, it is determined whether the current driver is the vehicle owner, and through 5G network and Internet of Things service background interaction, the driver information is uploaded, if the driver information is inconsistent with the information in the Internet of Things service background, the vehicle owner is notified of the vehicle start condition; if consistent, facial expression recognition is performed.

[0055] In the above step 1), the user's current facial expression is recognized, the user's emotion is judged, the expression is displayed, and a friendly interactive feeling is formed.

[0056] In the above step 2), the voice interaction method specifically comprises the following steps:

[0057] 2.1) When the vehicle owner interacts with the vehicle interactive robot through voice, the vehicle owner first sends a voice command, and the vehicle interactive robot receives the sound source signal of the vehicle owner through the microphones respectively arranged on the left and right sides of the vehicle interactive robot;

[0058] ​2.2) The in-vehicle interactive robot parses the voice commands, sends corresponding control instructions to other controllers in the vehicle, controls the other controllers in the vehicle to complete the command requirements, and processes the measured sound signals based on the sound field localization method and the time delay of the driver's sound source signal reaching the two microphones. It only determines the direction and distance of the driver's sound source relative to the microphone in the horizontal direction, thereby determining the direction of the driver.

[0059] In step 2) above, the in-vehicle interactive robot is made to face the driver based on the driver's direction. Specifically, the in-vehicle interactive robot is made to face the user based on the driver's direction through steering control.

[0060] Preferably, in the above steps, such as Figure 3 As shown, the method for the floating multi-functional in-vehicle interactive robot to recognize the driver's facial expressions and locate the sound field includes the following steps:

[0061] 2.2.1) The driver issues voice commands to the suspended multi-functional vehicle-mounted interactive robot;

[0062] 2.2.2) Determine whether the instruction information includes the driver's voice and image information. If it includes image information, proceed to step 2.2.3); if it includes voice information, proceed to step 2.2.4.

[0063] 2.2.3) The suspended multi-functional vehicle-mounted interactive robot collects facial images of the driver through a camera and performs image processing;

[0064] Specifically, image processing includes the following steps:

[0065] 2.2.3.1) The driver's image is filtered by an image filtering algorithm. After the camera of the vehicle interactive robot is calibrated in advance, the background of the image recognition is removed and the distortion of the face image caused by the camera shooting from a low angle is corrected. Then, it is determined whether the collected face image is complete. If it is incomplete or not complete enough, half of the face image is recognized first, and the complete face image is completed based on this data, thereby obtaining the driver's face image area.

[0066] 2.2.3.2) Extract features from the driver's facial image, focusing on the corners of the eyes, mouth, cheeks, and other parts that can reflect the driver's emotions;

[0067] 2.2.4) The suspended multi-functional vehicle-mounted interactive robot collects the driver's voice through a microphone for sound field localization;

[0068] Specifically, sound field localization includes the following steps:

[0069] 2.2.4.1) Filter the noise of the driver's voice through an audio filtering algorithm, remove background noise and other interference sources;

[0070] 2.2.4.2) Use an audio amplification algorithm to amplify the time difference of the driver's voice reaching the two microphones of the robot, determine the direction of the sound source in front of the robot, and instruct the robot to rotate towards the sound source. The robot display screen will rotate according to the instructions;

[0071] 2.2.4.3) Feature extraction of the driver's voice, focusing on obtaining speech, tone and other parts that can reflect the driver's emotions;

[0072] 2.2.5) Pack the driver's face image and the emotional information in the voice, and send it to the Internet of Things service background through the 5G network for unified processing. Face recognition big data processing, check whether the driver is the owner of the vehicle. If it is the owner, execute the next step. If it is not the owner, execute step 2.2.9);

[0073] 2.2.6) The human emotion big data processing of the Internet of Things service background will intelligently match the tens of thousands of Chinese and Asian facial emotion libraries in the Internet of Things service background, accurately determine the emotional state of the interactive personnel, especially the driver, and assist with the driver's voice, tone and other parts that can reflect the emotions. To comprehensively determine the current driver's emotions, and return the current driver's emotional results to the robot through 5G communication;

[0074] 2.2.7) The robot uses corresponding interactive expressions and tone to communicate with the driver to improve the friendliness of the interaction;

[0075] 2.2.8) Inform the owner of the vehicle through SMS or other means that there is a non-owner driving the vehicle, whether to authorize service; If authorized, execute step 2.2.6), if not authorized, execute the next step;

[0076] 2.2.9) Send the current unlicensed result back to the robot through 5G communication, and the robot gives a voice prompt to the driver that the driver is not authorized, and completes the current interaction action.

[0077] In the above step 3), when the vehicle is driving, in order to prevent the vehicle from being thrown out from above due to inertia caused by emergency braking, causing accidental injury, the magnetic suspension force field of the vehicle-mounted interactive robot needs to be adjusted. Specifically, if the vehicle speed reaches the pre-set speed preset, the magnetic suspension force is reduced, the suspension height of the interactive controller is reduced, and the vehicle-mounted interactive robot is reset.

[0078] In one embodiment of the present application, a control device for a suspended multifunctional vehicle-mounted interactive robot is provided, which is used to implement the control method in each of the above embodiments, as shown in the figure, and the control device comprises: Figure 2

[0079] A magnetic suspension dynamic force control module is connected with the artificial intelligence controller, receives the control instructions transmitted by the artificial intelligence controller, controls the magnetic suspension force field of the vehicle-mounted interactive robot, and suspends the vehicle-mounted interactive robot in the air or resets it;

[0080] A voice recognition module is used to recognize the voice instructions of the driver, and transmit them to the artificial intelligence controller for voice interaction with the driver;

[0081] An image recognition module is used to recognize the facial expressions of the driver, and transmit them to the artificial intelligence controller for friendly interaction with the driver according to the recognized expressions; for example, the current emotions are happiness, sadness, fatigue, etc., and corresponding functional responses are made;

[0082] A steering control module is connected with the artificial intelligence controller, controls the steering of the vehicle-mounted interactive robot suspended in the air according to the control instructions transmitted by the artificial intelligence controller, and makes it face the driver;

[0083] A vehicle body data module is used to obtain the current state information of the vehicle and transmit it to the artificial intelligence controller;

[0084] In the above embodiment, the control device further comprises a man-machine interaction display screen; the current emotions of the driver obtained by the image recognition module are transmitted to the man-machine interaction display screen, and the corresponding expressions are given by the man-machine interaction display screen to display the corresponding data of the vehicle.

[0085] In the above embodiment, the control device further comprises a GPS positioning module connected with the artificial intelligence controller, and the GPS positioning module transmits the collected positioning data of the vehicle and the driving direction of the vehicle to the artificial intelligence controller.

[0086] In use, the intelligent networked vehicle suspends the vehicle-mounted interactive robot in the air by the artificial intelligence controller controlling the magnetic suspension dynamic force control module during the starting process, and synchronously opens the positioning, communication, voice recognition, image recognition functions, and turns on the man-machine interaction display screen to display the initial greeting picture and the robot expression; and adjusts the magnetic suspension force field provided by the magnetic suspension dynamic force control module according to the vehicle speed information to avoid accidental injury caused by the vehicle-mounted interactive robot flying out from above.

[0087] The device provided in the embodiment is used to execute the above method embodiments, and the specific process and detailed content are referred to the above embodiments, which will not be described here.

[0088] ​In an embodiment of the present application, the computing device can be a terminal, which can include a processor, a communications interface, a memory, a display screen and an input device. The processor, the communications interface and the memory can communicate with each other through a communication bus. The processor is configured to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, which is executed by the processor to implement a control method of a suspended multi-functional vehicle interactive robot. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communications interface is configured to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a management network, NFC (Near Field Communication) or other technologies. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device can be a touch layer overlaid on the display screen, or a key, a trackball or a touchpad arranged on the shell of the computing device, or an external keyboard, a touchpad or a mouse, etc. The processor can call the logical instructions in the memory to execute the following method:

[0089] When the intelligent connected vehicle is started, the vehicle interactive robot is suspended in the air, it is determined whether the current driver is the vehicle owner, and the vehicle owner's facial expression is recognized for friendly interaction. The vehicle owner issues a voice command to interact with the vehicle interactive robot, and the vehicle interactive robot is made to face the vehicle owner according to the direction of the vehicle owner. Vehicle speed information is obtained, and the magnetic suspension force field of the vehicle interactive robot is adjusted according to the vehicle speed information to avoid the vehicle interactive robot flying out from above the magnetic suspension dynamic force control module to cause accidental injury.

[0090] In addition, the logical instructions in the memory described above can be implemented in the form of a software function unit and sold or used as an independent product. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0091] Those skilled in the art can understand that the structure shown by the above computing device is only part of the structure related to the scheme of the present application, and does not constitute a limitation on the computing device to which the scheme of the present application is applied. A specific computing device can include more or fewer components, or combine certain components, or have a different arrangement of components.

[0092] In an embodiment of the present application, a computer program product is provided, which includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, enable the computer to perform the method provided by any of the above method embodiments, for example including: when the intelligent connected vehicle starts, suspending the vehicle-mounted interactive robot in the air, determining whether the current driver is the vehicle owner, and performing vehicle owner facial expression recognition to perform friendly interaction; issuing a voice instruction by the vehicle owner, and performing voice interaction with the vehicle-mounted interactive robot, and making the vehicle-mounted interactive robot face the vehicle owner according to the direction in which the vehicle owner is located; obtaining vehicle speed information, and adjusting the magnetic levitation force field of the vehicle-mounted interactive robot according to the vehicle speed information to avoid the vehicle-mounted interactive robot flying out from above the magnetic levitation dynamic force control module to cause accidental injury.

[0093] In an embodiment of the present application, a non-transitory computer-readable storage medium is provided, which stores server instructions, the computer instructions enabling a computer to perform the method provided by any of the above embodiments, for example including: when the intelligent connected vehicle starts, suspending the vehicle-mounted interactive robot in the air, determining whether the current driver is the vehicle owner, and performing vehicle owner facial expression recognition to perform friendly interaction; issuing a voice instruction by the vehicle owner, and performing voice interaction with the vehicle-mounted interactive robot, and making the vehicle-mounted interactive robot face the vehicle owner according to the direction in which the vehicle owner is located; obtaining vehicle speed information, and adjusting the magnetic levitation force field of the vehicle-mounted interactive robot according to the vehicle speed information to avoid the vehicle-mounted interactive robot flying out from above the magnetic levitation dynamic force control module to cause accidental injury.

[0094] The computer-readable storage medium provided by the above embodiments has similar implementation principles and technical effects to the above method embodiments, and will not be described here.

[0095] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions described in the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 an apparatus for performing the functions specified in the flowchart or multiple flows and / or blocks.

[0096] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flowchart or multiple flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus for performing the functions specified in the flowchart or multiple flows and / or blocks.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart or multiple flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus for performing the functions specified in the flowchart or multiple flows and / or blocks.

[0098] Finally, it should be noted that the above examples are merely used to illustrate the technical solutions of the present application, and are not intended to limit the same; even though the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1.A control method of a suspended multi-functional vehicle interactive robot, characterized by, The application relates to an intelligent vehicle interaction system. When the intelligent vehicle interaction system is started, a vehicle-mounted interactive robot is suspended in the air, whether the current driver is the vehicle owner is determined, the facial expression of the vehicle owner is recognized, and friendly interaction is carried out. The vehicle owner issues a voice command, and the vehicle-mounted interactive robot carries out voice interaction, and the vehicle-mounted interactive robot faces the vehicle owner according to the direction of the vehicle owner. Vehicle speed information is acquired, and the magnetic suspension force field of the vehicle-mounted interactive robot is adjusted according to the vehicle speed information, so that the vehicle-mounted interactive robot does not fly out from above the magnetic suspension dynamic force control module and cause accidental injury. Whether the current driver is the vehicle owner is determined by image recognition, and driver information is uploaded to the Internet of Things service background through 5G network interaction. The voice interaction includes: The vehicle owner sends a voice command to the vehicle-mounted interactive robot, and the voice interaction is carried out. The vehicle-mounted interactive robot analyzes the voice command, sends corresponding control commands to other vehicle controllers, controls the other vehicle controllers to complete the command requirements, and determines the direction of the vehicle owner according to a sound field positioning method. The facial expression recognition and sound field positioning method includes: The driver issues a voice command to the suspended multifunctional vehicle-mounted interactive robot. It is judged whether the command information includes the voice and image information of the driver. The driver's face image and the part of the sound reflecting the emotion are packaged, and the 5G network is used to uniformly send the information to the Internet of Things service background for face recognition big data processing. The Internet of Things service background processes human emotion big data, intelligently matches the facial emotion library of the Internet of Things service background, judges the emotional state of the driver, and comprehensively judges the emotion of the current driver according to the part of the driver's voice and tone reflecting the emotion, and returns the emotional result of the current driver to the robot. The robot communicates with the driver by adopting corresponding interactive expressions and tones to improve the friendliness of interaction. The vehicle owner is informed by short message service whether the current driver is not the vehicle owner and whether service authorization is carried out. The current unauthorization result is sent back to the robot, the robot gives a voice prompt to the driver that the driver is not authorized, and the interaction action is completed. The image processing includes: The driver image is filtered through an image filtering algorithm, the background of image recognition is removed after the camera of the vehicle-mounted interactive robot is calibrated in advance, the face image distortion caused by the upward recording of the camera is corrected, whether the collected face image is complete is determined, in the case that the face image is not complete or the completeness is not enough, half of the face image is recognized first, and the complete face image is completed based on the data, and the face image area of the driver is acquired. The face image of the driver is extracted, and the part reflecting the emotion of the driver is extracted. The sound field positioning includes: The noise of the driver's voice is filtered through an audio filtering algorithm, and the background noise interference source is removed. The time difference of the amplified driver voice reaching the two microphones of the robot is judged by using an audio amplification algorithm, and the direction of the sound source is determined to be on the left side, right side or front of the robot, and the robot is instructed to rotate to the direction of the sound source, and the display screen of the robot will rotate according to the instruction; The driver's voice is extracted to obtain the part reflecting the driver's emotion. 2.The control method of the suspended multi-functional vehicle interactive robot according to claim 1, wherein, The car-mounted interactive robot is made to face the owner directly according to the direction of the owner, which includes making the car-mounted interactive robot face the user directly through steering control processing according to the direction of the owner. 3.The control method of the suspended multi-functional vehicle interactive robot according to claim 1, wherein, The magnetic suspension force field of the car-mounted interactive robot is adjusted, which includes reducing the magnetic suspension force and the suspension height of the interactive controller to reset the car-mounted interactive robot if the vehicle speed reaches the preset speed. The magnetic suspension force field of the car-mounted interactive robot is adjusted, which includes reducing the magnetic suspension force and the suspension height of the interactive controller to reset the car-mounted interactive robot if the vehicle speed reaches the preset speed.

Images