Desktop-level AI education robot fused with large model and programming control method of desktop-level AI education robot

Abstract

The invention relates to the technical field of robot programming design, and particularly discloses a desktop-level AI education robot fused with a large model and a programming control method thereof.The desktop-level AI education robot comprises a robot body and hardware equipment internally integrating sensing, execution and display functions, achieves movement and rotation on a desktop based on the hardware equipment and has the communication capacity, and the robot body is provided with the communication function. The processor is responsible for executing programming instructions and processing sensor information; the external module is used for expanding the functions of the robot and comprises various modules which are modularly designed; the positioning pad provides positioning information of the current robot; and the programming card provides card ID information and a relative rotation angle for the robot, and different programming programs can be configured based on the ID information. Through the modular design and advanced communication capability, the system can adapt to various teaching and scientific research scenes, and supports multi-device cooperation and large model interfaces, so that the flexibility, operability and expansibility of the system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of robot programming and design technology, and more specifically, to a desktop-level AI educational robot integrating a large model and a programming and control method thereof. Background Art

[0002] With the rapid development of science and technology, artificial intelligence and robotics are changing all walks of life at an unprecedented speed. Presenting the most cutting-edge technology to students in an intuitive and easy-to-operate way, and encouraging them to practice it themselves and explore independently in the project, can effectively stimulate their curiosity and desire to explore new technologies. At the same time, researchers also need to have a robot platform that can deploy artificial intelligence algorithms such as reinforcement learning, imitation learning, and large models to achieve a complete process from algorithm simulation to on-site application. This not only promotes technological innovation, but also provides strong support for the close integration of scientific research and education.

[0003] For example, the Chinese patent authorization number: CN 215987638 U discloses an AI intelligent education robot for smart education, which projects content according to the teacher's voice instructions and controls the height and angle of the projection screen through an electromechanical structure; the Chinese patent application number: CN 116682298A discloses an AI artificial intelligence children's companion education robot that focuses on human-computer interaction in the form of companionship, and is designed with voice, display and other modules; the Chinese patent authorization number: CN 217736769 U discloses an AI artificial intelligence children's companion education robot with features such as an adjustable touch display, infrared sensing distance reminder and remote monitoring. Although the interaction with students is enhanced through projection, screen, touch screen and other methods, they have failed to effectively mobilize the students' main participation, especially in the interactive methods such as hands-on programming and robot construction, there are obvious deficiencies, so it is relatively limited in stimulating students' hands-on ability and educational effects.

[0004] In addition, compared with traditional robot toys and teaching aids, such as the publicly available programming robots with Chinese patent authorization number: CN215495470U, although they solve the needs of robot structure construction and expansion, allowing users to DIY modify robots, they are still limited in interactivity and feedback, and cannot allow students to experience artificial intelligence technology; while Chinese patent authorization numbers: CN108664026 B and CN 212491537 U use optical recognition code technology to achieve automatic driving and path recognition, improving the level of intelligence; but they are closed in hardware interfaces and software expansion, and cannot be expanded and integrated with external devices or other modules with artificial intelligence functions, limiting more complex artificial intelligence application scenarios and students' actual hands-on experience.

[0005] In view of this, the present invention provides a desktop-level AI educational robot integrating a large model and a programming control method thereof to solve the above-mentioned problems. Summary of the invention

[0006] In order to overcome the problems in the prior art, the present invention proposes a desktop-level AI educational robot integrating a large model and a programming and control method thereof, aiming to provide students with richer interactive experiences and practical opportunities, and to expose them to artificial intelligence and robotics technology during autonomous exploration and generate interest in them.

[0007] In a first aspect, the present invention provides a desktop AI educational robot including a fusion large model, comprising:

[0008] Robot, a hardware device with integrated sensing, execution and display functions, which can move and rotate on the desktop based on the hardware device and has communication capabilities, responsible for executing programming instructions and processing sensor information;

[0009] External modules, various modules with modular design, are used to expand the functions of the robot;

[0010] Positioning pad, which provides the robot with current positioning information;

[0011] The programming card provides the robot with card ID information and relative rotation angle. Different programming programs can be configured based on the ID information.

[0012] As a preferred technical solution of the first aspect of the present invention, the robot comprises a circuit module, a motion module, a battery module and a housing module;

[0013] The circuit module is used for robot control, positioning, driving, communication, sensing, display and sound output;

[0014] The motion module controls the movement and rotation of the robot, so that the robot can move freely on a plane;

[0015] The battery module is connected to the circuit module to provide power supply so that the robot can operate independently without external power supply;

[0016] The housing module protects the internal components while providing structural support.

[0017] As a preferred technical solution of the first aspect of the present invention, the circuit module includes:

[0018] The control unit includes an MCU chip, which controls the robot's behavior and stores the robot's operating data;

[0019] A positioning unit, including an OID reader, can identify information on the positioning pad to obtain the current robot positioning data, or identify a programming card to obtain the ID information of the programming card;

[0020] A power supply unit, used for charge and discharge management, and realizing power supply to each unit in the circuit module 110;

[0021] A driving unit, which drives each motor in the robot motion module 120;

[0022] Communication unit, which realizes the functions of burning program firmware, communicating with programming software, and communicating with host computers or other devices;

[0023] The sensor unit is used to obtain the rotation speed of the motor in the motion module, measure the voltage of the battery module, obtain button information, etc.

[0024] The display unit provides users with a programmable graphic display platform with functions such as prompts and decorations;

[0025] The sound unit controls the voice or ringtone effects output by the robot in a programmable way;

[0026] The expansion unit includes power supply and communication to the external module through the driving circuit.

[0027] As a preferred technical solution of the first aspect of the present invention, the expansion unit includes 4 pin interfaces, the 4 pin interfaces include A1 pin, A2 pin, A3 pin and A4 pin, A1 pin and A4 pin are power pins, A2 pin and A3 pin are signal pins, which are used to connect to the MCU chip.

[0028] The 4 pin interfaces in the external module are: B1 pin, B2 pin, B3 pin and B4 pin. The 4 pin interfaces in the external module are respectively connected to the A1 pin, A2 pin, A3 pin and A4 pin of the expansion unit in the robot.

[0029] Structurally, the magnetic connector of the robot's expansion unit is recessed a certain distance inward relative to the shell module, and the spring pin magnetic connector in the external module protrudes a certain distance outward relative to its shell, making the magnetic connection between the two less likely to loosen and more secure.

[0030] As a preferred technical solution of the first aspect of the present invention, the motion module includes a right motor and a left motor with the same transmission mode, and the right motor and the left motor are connected to the driving unit 114 on the circuit module;

[0031] Among them: the right motor is fixed on the chassis of the shell, meshed with the right driving wheel through gear transmission, the right driving wheel and the right driven wheel are driven by tracks, the left motor and its transmission method are the same, thereby driving the robot to move.

[0032] As a preferred technical solution of the first aspect of the present invention, the housing module is divided into a housing upper cover and a housing chassis, the housing upper cover is equipped with an LCD screen, and the circuit module and the motion module are fixed on the housing chassis.

[0033] In a second aspect, the present invention provides a programming control method for a desktop AI educational robot integrating a large model, based on the implementation of the first aspect, comprising the following steps:

[0034] After writing the robot virtual machine firmware and graphical building block library, the robot can be graphically programmed through the graphical programming interface. The constructed building block program will be converted into instructions in the graphical programming interface and communicate with the robot's virtual machine through a simple serial protocol or BLE, thereby realizing real-time programming.

[0035] As a preferred technical solution of the second aspect of the present invention, programming cards are matched one-to-one with the functions of the robot 10 in advance to realize the screenless programming function, including the following functions:

[0036] The programming cards include cards with different patterns, and a card corresponding to a pattern corresponds to an ID information, and the ID information is accompanied by angle information;

[0037] Users can programmatically set the functions of these cards in advance;

[0038] After that, each programming card will trigger the robot to perform the corresponding function. There is no need to use computers or other equipment for programming. Instead, the effect of screenless programming can be achieved directly by arranging the positions of programming cards or other methods.

[0039] As a preferred technical solution for the second aspect of the present invention, a communication interface can also be written, expanded through a graphical programming library, and an advanced communication interface can be implemented through Bluetooth low energy or WiFi to deploy artificial intelligence algorithms such as reinforcement learning, imitation learning, and large language models to a single or multiple robots.

[0040] In a third aspect, the present invention provides an electronic device, comprising:

[0041] at least one processor; and,

[0042] A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the second aspect.

[0043] The specific advantages of the present invention are as follows:

[0044] The present invention integrates high-precision OID positioning technology, magnetic modular expansion interface, real-time interactive programming and advanced communication interface into an integrated robot, providing a flexible, easy-to-use and powerful platform suitable for education and scientific research. The compact design and diversified programming modes lower the threshold for use, while the modular design and advanced communication capabilities enable it to adapt to various teaching and scientific research scenarios, support multi-device collaboration and large model integration, thereby significantly improving the flexibility, operability and scalability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 An illustrative view of an example configuration of a desktop-level AI educational robot that integrates a large model of the present invention.

[0046] Figure 2 The figure is a schematic diagram of the mechanism of a robot according to the present invention.

[0047] Figure 3 2 is an example of a front view of a robot according to an embodiment of the present invention.

[0048] Figure 4 An example of a back stereoscopic view of a robot according to an embodiment of the present invention

[0049] Figure 5 2 is an example of a bottom perspective view of a robot according to an embodiment of the present invention.

[0050] Figure 6 This is a functional configuration block diagram of a robot according to the present invention.

[0051] Figure 7 The present invention is a functional configuration block diagram of a circuit module in a robot.

[0052] Figure 8 The figure is a schematic diagram of the structural design of a motion module in a robot of the present invention.

[0053] Fig. 9 The present invention is a schematic diagram of the circuit design of an expansion unit in a robot.

[0054] Fig.10 FIG. 2 is a schematic diagram of a circuit design of an external module 20 a of the present invention.

[0055] Fig.11 FIG. 2 is a schematic diagram of a circuit design of an external module 20 b of the present invention.

[0056] Fig.12 FIG. 2 is a schematic diagram of a circuit design of an external module 20c of the present invention.

[0057] Fig.13 FIG. 2 is a schematic diagram of a circuit design of an external module 20d of the present invention.

[0058] Fig.14 FIG. 2 is a schematic diagram of a circuit design of an external module 20 e of the present invention.

[0059] Fig.15 FIG. 2 is a schematic diagram of a circuit design of an external module 20 f according to the present invention.

[0060] Fig.16 FIG. 2 is a schematic diagram of a circuit design of an external module 20g of the present invention.

[0061] Fig.17 FIG. 2 is a schematic diagram of a circuit design of an external module 20h of the present invention.

[0062] Fig.18 FIG. 2 is a schematic diagram of a circuit design of an external module 20i according to the present invention.

[0063] Fig.19 FIG. 2 is a schematic diagram of a circuit design of an external module 20j according to the present invention.

[0064] Fig. 20 The figure is a schematic diagram of an embodiment of an ultrasonic external module of the present invention.

[0065] Fig.21 The figure is a schematic diagram of an embodiment of an ultrasonic external module of the present invention.

[0066] Fig. 22 The figure is a schematic diagram of an embodiment of a light board external module of the present invention.

[0067] Fig.23 The figure is a schematic diagram of an embodiment of a light board external module of the present invention.

[0068] Fig.24 The figure is a schematic diagram of an embodiment of a steering gear clamp external module of the present invention.

[0069] Fig.25 The figure is a schematic diagram of an embodiment of a steering gear clamp external module of the present invention.

[0070] Fig.26 A schematic diagram of a software architecture for implementing basic programming functions in a programming control method of the present invention.

[0071] Fig. 27 A schematic diagram of a software architecture for realizing a screenless programming function in a programming control method of the present invention.

[0072] Fig.28 A schematic diagram of a software architecture for implementing a high-level communication interface in a programming control method of the present invention.

[0073] Fig.29 This is an application case of the present invention based on an advanced communication interface.

[0074] Fig.30This is an application case of the present invention based on an advanced communication interface.

[0075] Fig.31 This is an application case of the present invention based on an advanced communication interface.

[0076] In the figure: 10, moving body; 110, circuit module; 111, control unit; 112, positioning unit; 113, power supply unit; 113A, charging interface; 113B, power management module; 114, driving unit; 115, communication unit; 116, sensor unit; 116A, user button A; 116B, user button B; 117, display unit; 117A, LCD screen; 117B, power indicator light; 117C, power indicator light; 118, sound unit; 119, expansion unit;

[0077] 120, motion module; 121, right motor; 122, left motor; 123, right driving wheel; 124, left driving wheel; 125, right driven wheel; 126, right driven wheel; 127, right crawler track; 128, left crawler track;

[0078] 130. Battery module;

[0079] 140, housing module; 141, housing upper cover; 141A, power switch; 142, housing chassis;

[0080] 20. External module; 21. Spring pin magnetic connector; 22. Ultrasonic module external module; 23. Light board external module; 24. Servo gripper external module;

[0081] 30. Positioning pad; 31. Visual pattern; 32. Coding pattern;

[0082] 40. Programming cards. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] Example 1: Figure 1 As shown, this embodiment provides a technical solution: a desktop AI educational robot integrating a large model, comprising a robot 10, an external module 20, a positioning pad 30 and a programming card 40;

[0085] like Figure 2-5As shown, the robot 10 has hardware devices with sensing, execution and display functions integrated inside, realizes movement and rotation on the desktop based on the hardware devices, and has communication capabilities;

[0086] Specifically, if Figure 6 As shown, the robot 10 includes a circuit module 110, a motion module 120, a battery module 130 and a housing module 140;

[0087] like Figure 7 As shown, the circuit module 110 is used for robot control, positioning, driving, communication, sensing, display and sound output; wherein:

[0088] The control unit 111 includes an MCU chip, which controls the movement of the robot and stores the operation data of the robot.

[0089] The positioning unit 112 includes an OID reader, which can identify the information on the positioning pad 30 to obtain the current positioning data of the robot 10 , or identify the programming card 40 to obtain the ID information of the current programming card 40 .

[0090] The power supply unit 113 includes a charging interface 113A and a power management module 113B. The power management module 113B is used for charge and discharge management, and supplies power to each unit in the circuit module 110 through the charging interface 113A.

[0091] The driving unit 114 drives the right motor 121 and the left motor 122 in the robot motion module 120 .

[0092] The communication unit 115 includes a serial communication module and a wireless communication module, wherein: the serial communication module is used to realize the functions of stable program firmware burning and programming software communication; the wireless communication module has the functions of Bluetooth, BLE and Wi-Fi, and realizes the connection with computers, tablets, mobile phones and remote controllers, realizes wireless firmware update, wireless program update, communication with programming software, communication with the host computer, receiving remote control instructions and communicating with other robots.

[0093] The sensing unit 116 includes a power button 141A, two user buttons 161A, a user button 161B, an encoder, etc., and is used to obtain the user button pressing time, the rotation speed of the two motors in the motion module 120, and measure the voltage in the battery module 130, etc.

[0094] The display unit 117 includes an LCD screen 117A, a power indicator light 117B and a charging indicator light 117C; the LCD screen 117A is located on the top of the robot 10, providing the user with a programmable graphic display platform to display text, shapes, patterns and pictures; the power indicator light 117B is used to indicate whether the robot is turned on, and it will light up when turned on and will not light up when turned off; the power indicator light 117C is used to indicate the robot's charging, full power and low power status.

[0095] The sound unit 118 includes a buzzer, a speaker and a sound control circuit, and mainly realizes functions such as playing voice or ringtones. The user can control the voice or ringtone effects output by the robot 10 in a programmable manner.

[0096] The expansion unit 119 includes a driving circuit and a connection end, and is connected to the external module 20 based on a magnet on the connection end. A four-pin interface is provided on the connection end, and power and communication are provided to the external module 20 through the driving circuit.

[0097] Specifically, if Fig. 9 As shown, the expansion unit 119 includes 4 pin interfaces, including A1 pin, A2 pin, A3 pin and A4 pin, A1 pin and A4 pin are power pins, A2 pin and A3 pin are signal pins, which are used to connect the MCU chip; among them: A1 pin is a 5V power output pin, and the robot's internal microcontroller can control whether the pin outputs power to ensure safety; A4 pin is a GND pin;

[0098] The magnetic connector of the expansion unit 119 of the robot 10 is recessed a certain distance inward relative to the shell module 140, and the spring pin magnetic connector 21 in the external module 20 protrudes a certain distance outward relative to its shell, so that the magnetic connection between the two is not easy to loosen and is more secure.

[0099] like Figure 8 As shown, the motion module 120 includes a motor and a driving wheel, which are responsible for the movement and rotation of the robot, so that the robot can move freely on a plane;

[0100] Specifically, the right motor 121 is fixed on the housing chassis 142, meshed with the right driving wheel 123 through a gear transmission method, and the right driving wheel 123 and the right driven wheel 125 are transmitted through the crawler 127; the left motor 122 and its transmission method are similar. The right motor 121 and the left motor 122 are connected to the drive unit 114 on the circuit module 110.

[0101] The motion module 120 can save space and reduce the size of the robot chassis, and the tracked mobile chassis has good friction and obstacle-crossing ability, can move on smooth or rugged surfaces, and can enable the robot to rotate in situ.

[0102] The battery module 130 is connected to the circuit module 110 to provide power supply so that the robot 10 can operate independently without an external power source;

[0103] The housing module 140 protects the internal components while providing structural support.

[0104] Specifically, the housing module 140 is divided into a housing upper cover 141 and a housing bottom plate 142 , which are connected by buckles or screws, etc. The housing upper cover 141 is equipped with an LCD screen 117A, and the housing bottom plate 142 is fixed with the circuit module 110 and the motion module 120 .

[0105] In summary, this embodiment provides a desktop-level AI educational robot with a compact overall design, rich functions, and is presented in the form of a mobile robot; the equipped OID reader can obtain its own high-precision absolute position on the positioning pad, and can also identify the coded information on the programming card. It is simple to operate and easy to use, which is convenient for students to start learning anytime and anywhere, providing students with richer interactive experience and practical opportunities, and allowing them to get in touch with artificial intelligence and robotics technology in independent exploration and generate interest; in addition, the magnetic interface can expand various types of sensors, actuators, displays or composite modules, as well as modules embedded with AI functions, providing students with the opportunity to learn electronic hardware and artificial intelligence technology, and has the advantages of easy replacement and firm connection.

[0106] The external module 20 includes a modular function expansion module, the expansion end of which is connected to the robot 10 through a magnetic connector 21, and the robot function is expanded based on the principle of pin multiplexing. The function expansion module includes a sensor, an actuator, a display and a composite module, and a module with AI function is embedded in the function expansion module, such as a TTS module for voice-to-text, a gesture recognition module, an AI camera module, etc.

[0107] When the external module 20 is connected to the expansion unit 119 of the robot 10 through the pins shown in the circuit design schematic diagram, different pin interface types are set according to the different communication interfaces of the expansion unit 119 to achieve power supply and data communication.

[0108] Specifically, if Figure 10-19 As shown, the four pin interfaces in the external module 20 are: B1 pin, B2 pin, B3 pin and B4 pin. The four pin interfaces in the external module 20 are respectively connected to the A1 pin, A2 pin, A3 pin and A4 pin of the expansion unit 119 in the robot 10.

[0109] When the A2 and A3 pins are multiplexed and configured as an I2C communication interface, for example, the A2 pin is SDA and the A3 pin is SCL, then the robot can communicate with external modules that support I2C, such as controlling Fig.10 In the example, the OLED screen module 20a of the I2C interface displays characters or patterns, wherein the B2 interface and the B3 interface are respectively connected to the SDA and SCL pins of the OLED screen; or the control Fig.11 In the embodiment, the gesture recognition module 20b of the I2C interface is used to recognize various gesture operations of the user.

[0110] When the A2 and A3 pins are multiplexed and configured as a serial port (UART) communication interface, for example, the A2 pin is RX and the A3 pin is TX, the robot can communicate with an external module that supports UART, such as controlling Fig.12 In the example, the TTS player 20c of the UART interface converts the input text into audio and plays it, wherein the B2 interface and the B3 interface are respectively connected to the TX and RX pins of the TTS player chip; or controls Fig.13 The AI ​​camera module 20d in the system realizes AI vision functions such as color recognition, visual line patrol, traffic card, color block detection or object classification.

[0111] When the A2 and A3 pins are multiplexed as normal GPIO pins, they can be configured as needed and connected to some external modules. Fig.14 The ultrasonic sensor module 20e is connected to the robot to detect the distance of obstacles in front of the robot, or to Fig.15 The mid-infrared transceiver module 20f is connected to send and receive infrared signals.

[0112] This embodiment also supports the case where the external module only needs one signal pin to communicate. For example, Fig.16 In the servo module 20g, only the A3 pin sends PWM to the B3 pin to control the rotation angle of the servo output shaft, or Fig.17 In the NeoPixel light strip module 20h, you only need to send a specific Single-Wire signal from the A3 pin to the B3 pin to control the color and brightness of each lamp bead in the light strip.

[0113] In addition, when the functions of the external module are more complex, or the module is difficult to communicate directly through the GPIO, I2C and UART protocols, an MCU can be added to the external module 20 as a transfer, and then communicate with the robot through I2C or UART, such as Fig.18 20i and Fig.19 As shown in 20j.

[0114] The external module 20 includes an ultrasonic module external module 22, a light board external module 23 and a servo clamp external module 24. The ultrasonic module external module 22, the light board external module 23 and the servo clamp external module 24 are all equipped with a spring pin magnetic connector 21 on their backs. On one side of the robot, the expansion unit 119 is also equipped with a magnetic connector. The two are attracted by magnets to ensure a tight connection while preventing the pins from being reversed. Structurally, the magnetic connector of the expansion unit 119 of the robot 10 is recessed a certain distance inward relative to the shell module 140, and the spring pin magnetic connector 21 in the external module 20 protrudes a certain distance outward relative to its shell, so that the magnetic connection between the two is not easy to loosen and is more secure.

[0115] Among them: Figure 20-21 As shown, the external module 20 is a circuit connection diagram of the ultrasonic external module 22. Figure 22-23 As shown, the external module 20 is a circuit connection diagram of the light board external module 23. Figure 24-25 As shown, the external module 20 is a circuit connection diagram of the steering gear clamp external module 24.

[0116] The positioning pad 30 is used to provide positioning information of the robot; the OID code and pattern are printed on the positioning pad 30, and the robot reads the code points on the positioning pad 30 through the OID code reader to obtain the position and angle information of the robot on the positioning pad in real time.

[0117] Specifically, if Figure 1 The positioning pad 30 shown in the figure is a paper material, on which the OID code and the color pattern visible to the human eye are printed. The OID code is composed of many tiny dots that are difficult to be directly identified by the human eye. They are arranged according to specific rules to form a pattern, and can correspond to a set of specific values ​​after decoding. The diameter of these tiny dots is between 40 microns and 80 microns, so they can be hidden under the color pattern of the positioning pad 30.

[0118] An OID reader is fixed on the robot 10 and reads the code points on the positioning pad through the hole in the center of the housing chassis 142 to obtain positioning information in real time, including x-coordinate, y-coordinate and rotation angle.

[0119] In terms of the design of the positioning pad, since the OID code reader is highly sensitive to carbon-containing black ink, the positioning map needs to be printed in two layers. One layer is the color layer, which is mainly for the human eye to see the pattern, using C (cyan) M (magenta) Y (yellow) three-color ink; the other layer is the OID code layer, which needs to use carbon-containing black ink. The paper is selected as smooth coated paper to meet the requirements of high resolution, and a high-resolution laser printer is used for printing, and the surface is coated to be more wear-resistant.

[0120] In addition, OID technology supports a larger positioning area. It can be expanded to a larger size by splicing multiple standard size positioning mats.

[0121] The programming card 40 adopts OID technology, is printed with an OID code and pattern, and is used to trigger the robot's actions or programs based on the robot 10 identifying ID information.

[0122] Specifically, the programming card 40 is similar to the positioning pad 30, using OID technology, with an OID code and a color pattern visible to the human eye printed on the paper, and cut into a card shape. Based on the OID technology, the card can be recognized by the robot 10 as a specific ID, and each ID information can be used to trigger a specific action or program of the robot 10. And the programming card 40 can provide the robot 10 with the same rotation angle information as the positioning pad 30.

[0123] The programming card 40 also provides a screen-free programming method, which controls the behavior of the robot by placing programming cards. It is suitable for young children or scenarios where screen operation is not required.

[0124] The robot 10 described in this embodiment is designed with an integrated body shape, so that the entire system is easy to carry and use, suitable for operation in a desktop space, and has a lower usage threshold, and is particularly suitable for use in scenarios such as schools or homes.

[0125] Compared with existing AI educational robots, robots currently on the market usually only have low-precision positioning or obstacle avoidance functions such as infrared tracking or ultrasonic sensing, and cannot obtain their own high-precision posture in real time. The OID reader equipped in this embodiment can obtain high-precision absolute posture on the positioning mat for precise motion control, and can also recognize the coded information on the programming card, which is suitable for physical interaction scenarios.

[0126] In terms of extended functions, the functions of existing AI educational robots are often relatively fixed and lack scalability. However, this embodiment designs a magnetic suction module that supports the access of various sensors, actuators, displays, composite modules, and modules embedded with AI functions, and programs the external modules through graphical programming software. This design greatly enhances the robot's functional expansion capabilities and further enriches students' learning and practical experience.

[0127] In terms of programming mode, existing AI educational robots usually only support physical programming for young children, and only support computer programming for teenagers. However, this robot supports both physical programming and computer programming, which can cover a wider user group and improve user experience and ease of use.

[0128] In terms of programming operation, existing robots, whether text code or graphical programming, require complicated compilation and uploading processes, which easily confuses students and makes them lose interest. This embodiment supports interactive programming, allows real-time debugging of graphical code, and can run autonomously after the program is written, supporting offline operation functions, thereby simplifying the operation process and improving students' programming experience.

[0129] Finally, in terms of communication capabilities, existing AI educational robots usually need to be operated by fixed infrared or Bluetooth remote controls, with limited functions and mostly supporting only one wireless communication method. The robot of this embodiment not only supports BLE communication and Wi-Fi communication, but also supports a host computer (such as a computer, tablet, mobile phone) to connect multiple robots simultaneously via BLE or Wi-Fi, which is suitable for scenarios such as batch programming, cluster performances, deployment of reinforcement learning, large models and other artificial intelligence algorithms. The system also supports multi-robot collaboration or communication between robots in a local area network. This design can cultivate students' teamwork ability in educational scenarios.

[0130] Embodiment 2, as Figure 3 As shown, the part not described in detail in this embodiment is as shown in Example 1. This embodiment provides a programming control method for a desktop AI educational robot integrating a large model, including the following steps:

[0131] After writing the robot virtual machine firmware and graphical building block library, the robot can be graphically programmed through the graphical programming interface to achieve basic programming functions that support real-time operation and wireless connection;

[0132] The programming cards are matched one by one with the functions of the robot 10 in advance to realize the screenless programming function; the communication interface can also be written to realize the deployment of artificial intelligence algorithms such as reinforcement learning, imitation learning, large language models, etc. to a single or multiple robots 10 based on the advanced communication interface function.

[0133] Specifically, if Fig.26 As shown, the software architecture for implementing this embodiment includes a virtual machine running on the control unit 111 in the robot 10 and a graphical programming interface corresponding to the device end; the device end includes a computer, a tablet and a mobile phone.

[0134] A virtual machine is a stack machine or interpreter running on the robot 10MCU chip. The instructions of the virtual machine are 32 bits or 16 bits, consisting of an opcode and an operand. The opcode is used to instruct the virtual machine to issue a control instruction. Different opcodes use operands in different ways, such as encoding constant values ​​or jump offsets.

[0135] The graphical programming interface allows the user to construct building blocks, convert the building blocks into the above-mentioned 32-bit or 16-bit instructions through a virtual machine, and communicate with the virtual machine of the robot 10 through a simple serial protocol or BLE, thereby achieving real-time programming.

[0136] It should be noted that the software architecture described in this embodiment does not require users to recompile and upload codes every time they modify the code. Instead, it allows the program to be changed and run directly on the hardware, allowing the program effect to be seen in real time, supports multi-tasking, and allows the program to continue to run independently after the microcontroller is disconnected from the computer, allowing users to create more interactive and autonomous projects in the physical world.

[0137] Specifically, in the virtual machine part, the main tasks are pin definition, driver encapsulation (such as LCD screen driver, encoder driver, motor driver, OID reader driver, etc.) and primitive encapsulation (such as encapsulating the x-coordinate, y-coordinate and rotation angle obtained by the OID reader; battery power and other information into primitives).

[0138] On the graphical programming interface side, the main function is to encapsulate common libraries, such as various display functions of the LCD screen, closed-loop control of motor rotation, reading the coordinates and rotation angle of the robot, etc., in the form of building blocks. Users can use these building block libraries to quickly develop the required functions. In addition, users can also customize the graphical building block library to meet specific application requirements.

[0139] In the case of expanding more external modules 20 for the robot 10, this embodiment encapsulates the functions of various external modules 20 into an external module library for users to use. A modular magnetic interface is adopted to support the expansion of various sensors, actuators, display modules and composite modules, and functional modules are added as needed, thereby realizing multi-level expansion from basic programming teaching to complex artificial intelligence applications, which is completed in the form of building blocks. Users do not need to care about the underlying virtual machine program, which not only simplifies the programming process, but also makes the real-time update and debugging of the program extremely convenient, and adaptable to different scenarios.

[0140] The programming control method supports a variety of programming interaction modes, including graphical programming through computers, tablets or mobile phones, real-time debugging, offline interactive programming, and physical programming or screenless programming through cards. At the same time, the system has wireless communication functions, supports BLE communication and Wi-Fi communication, and is compatible with wired and wireless programming. The advanced communication interface it provides allows robots to access large language models, further stimulate students' interest in artificial intelligence and robotics, help them quickly explore artificial intelligence technology, and achieve the goals of AI and robotics education and research.

[0141] Embodiment 3: The undetailed parts of this embodiment are as shown in Embodiment 1. This embodiment provides a programming control method for a desktop AI educational robot with a screenless programming function, which realizes high-precision positioning and interactive operation through OID technology, supports precise motion control of the device at a specific position, positioning on a plane with special code points, and interacting with physical cards, providing a high-precision and stable operating environment for multi-device application scenarios; mainly for young users who are not proficient in operating computers, tablets and other devices, or are worried about the impact of the screen on their eyesight, this embodiment also includes realizing screenless programming through programming cards 40,

[0142] Specifically, if Fig. 27 As shown, the programming card 40 includes cards with different patterns, and a card corresponding to a pattern corresponds to an ID information, and the ID information includes angle information;

[0143] For example, the cards include card 40a, card 40b, card 40c, card 40d, card 40e and card 40f; wherein card 40a is identified as ID=1, card 40b is identified as ID=2, card 40c is identified as ID=3, card 40d is identified as ID=4, card 40e is identified as ID=5 and card 40f is identified as ID=6; that is, cards 40a to 40f can be identified as ID=1 to 6 respectively;

[0144] Users can set the functions corresponding to these cards programmatically;

[0145] For example, the robot moves forward in the direction of 0 degrees, turns right and moves forward, turns around and moves forward, turns left and moves forward, plays music, and stops moving;

[0146] Young users only need to place these programming cards 40 in a specific order to trigger the robot to perform different functions, thereby achieving the effect of screen-free programming.

[0147] For example, when the robot 10 is placed Fig. 27 When the robot is on the programming card 40a in the lower right corner, the robot will follow the instructions of different programming cards in the order of the dotted lines and finally move to the end point, that is, the position of the programming card 40f.

[0148] It should be noted that parents or teachers can also program the robot in advance and use programming cards 40 with more IDs to trigger more customized functions. In this way, when the robot is handed over to young users, it can achieve rich interactive effects such as music programming and maze walking, allowing users to explore creatively in a screenless programming environment.

[0149] Embodiment 3: Parts not described in detail in this embodiment As shown in Embodiment 1, this embodiment provides a programming control method for a desktop AI educational robot with advanced communication interface functions, supports real-time programming and interactive debugging, and users can directly modify and debug the code through Bluetooth without repeated compilation and uploading, which significantly improves the fluency and efficiency of programming; at the same time, it has the function of offline operation to ensure that the device can still independently complete the established operation after disconnection; in advanced application scenarios, the programming control method of this embodiment supports connecting the robot 10 to a large language model to realize intelligent functions, or deploy artificial intelligence algorithms to multiple robots 10. These applications can be expanded through graphical programming libraries, and ultimately realize advanced communication interfaces through BLE (Bluetooth Low Energy) or WiFi.

[0150] Specifically, if Fig.28 As shown in the figure, in the graphical programming interface, each functional module of the programming library (including custom modules) is associated with a specific function name, and the user only needs to call the corresponding module to control the various functions of the robot. For example, the communication protocol format sent by the computer to the robot 10 is "0 / 1,<msg_id> ,cmd_name,cmd_args_list". Among them, 0 / 1 indicates whether the instruction is a non-blocking (such as forward) or blocking operation (such as forward 1 second); msg_id is a unique identifier generated by the computer to ensure the uniqueness of each communication; cmd_name and cmd_args_list correspond to the called function name and parameter list respectively. After completing the command, the robot will attach the execution result to msg_id and return it, thus ensuring smooth cross-language system collaboration.

[0151] In some advanced scenarios, the computer needs to obtain the status information of the robot 10 in real time (such as x-coordinate, y-coordinate, rotation angle, battery power, etc.). The user can write a corresponding program in the graphical programming interface to enable the robot to periodically send this status information to the computer. In addition, the robot is not limited to communicating with the computer, but can also communicate with other robots 10 through broadcast or unicast to achieve collaboration between multiple robots; or communicate with cloud servers to achieve functions such as access to large language models.

[0152] When the system is used for the first time, the user needs to load the bridge program into the device and perform the necessary initialization configuration. The graphical programming environment provides easy-to-use expansion functions, allowing users to easily add new modules and functions, ensuring the flexibility of the system. Whether it is an application in basic education or a demand in advanced scientific research, such as deploying artificial intelligence algorithms such as reinforcement learning, imitation learning, and large language models to a single or multiple robots 10, the system can simplify the operation process and adapt to complex scenarios of multi-device collaboration.

[0153] This design not only ensures flexibility, but also greatly simplifies the operational processes in complex scenarios. It is widely applicable to various applications from education to scientific research, especially those involving artificial intelligence algorithms and robot collaboration.

[0154] For the advanced communication interface function, this embodiment provides three specific embodiments:

[0155] Multi-machine follow-up experiment (such as Fig.29 As shown): In this experiment, the system is applied to a multi-robot collaborative following scenario. The experiment uses a small-sized positioning mat 30 with four robots 10 on it. Each robot sends its own number (such as 1, 2, 3, 4) and coordinate position to other robots in the form of BLE broadcast. Each robot achieves queue following by keeping a certain distance from the robot in front. When the distance between the robots is too large, the rear robot moves closer to the front; when the distance is too small, the rear robot moves away from the front robot. In the end, the four robots can maintain a stable queue, simulating the state of "following the car". This experiment can verify the real-time communication and queue control capabilities between robots, and is suitable for scenarios of multi-machine collaboration.

[0156] Item sorting experiment (such as Fig.30 As shown): This experiment demonstrates the application of the system in item sorting tasks. On a small-sized positioning pad 30, there are two robots 10 connected to a servo gripper module 24, and a plurality of scattered small objects. After obtaining the coordinates of the small objects in a specific way, the system can send the coordinate information to the robot 10 via Wi-Fi. The robot will automatically identify the object closest to itself and grab it, and then transport it to both sides of the positioning pad 30. Throughout the process, the robot can use traditional algorithms such as path planning and automatic obstacle avoidance to complete the task, or use advanced algorithms such as reinforcement learning and imitation learning to perform complex task operations, and even directly realize the entire process of perception to operation based on a large visual language model. This experiment simulates the scenario of robots collaborating to complete sorting tasks in an industrial environment.

[0157] Formation performance experiment (such as Fig.31 As shown in the figure): In this experiment, the system is applied to a large-scale formation performance. The experimental scene uses a large-size positioning mat 30 made of multiple pieces of spliced ​​together, on which there are 32 robots 10. When the user interacts with the computer through voice or handwriting, the computer calls the large language model interface to command all robots to move to the specified position. The robot can also display specific colors through the top LCD screen 117A, and with the movement trajectory, present a visually appealing formation performance picture. This experiment demonstrates the application of robots in the fields of performance and entertainment, especially the ability to perform advanced control and multi-device collaboration through large models.

[0158] These three examples demonstrate the application of the system in complex scenarios such as multi-robot collaboration, item sorting, and formation performances. It can be used for real-time control of multiple devices. Whether it is BLE broadcasting, Wi-Fi communication, or integration with large models, it reflects the flexibility and strong scalability of the system in terms of advanced communication interface functions. The WiFi-based interface meets a variety of communication needs, realizes parallel control of multiple devices through the interface, and adapts to different network environments and complex scene applications. It supports cross-language calls and controls, making it easy to integrate with large models, making the system compatible with more development environments and widely used in a variety of fields from industrial automation to entertainment performances.

[0159] Embodiment 4: The parts not described in detail in this embodiment are as shown in Embodiment 1. This embodiment provides an electronic device, including:

[0160] at least one processor; and,

[0161] A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a programming control method for a desktop-level AI educational robot integrating a large model.

[0162] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more control components, wherein the control component stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the programming control method of the desktop AI educational robot provided by the above-mentioned various method embodiments. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for input and output. The embodiments of this application are not described in detail here.

[0163] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0164] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0166] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0169] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0170] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0171] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A desktop AI educational robot integrating a large model, characterized in that: include: The robot (10) is a hardware device that integrates sensing, execution and display functions, realizes movement and rotation on the desktop based on the hardware device, and has communication capabilities, and is responsible for executing programming instructions and processing sensor information; External modules (20), various modules of modular design, used to expand the functions of the robot (10); A positioning pad (30) for providing current positioning information to the robot (10); The programming card (40) provides the robot with card ID information, and different programming programs can be configured based on the ID information.

2. A desktop AI educational robot integrating a large model according to claim 1, characterized in that: The robot (10) comprises a circuit module (110), a motion module (120), a battery module (130) and a housing module (140); The circuit module (110) is used for robot control, positioning, driving, communication, sensing, display and sound output; The motion module (120) controls the movement and rotation of the robot so that the robot can move freely on a plane; A battery module (130) is connected to the circuit module (110) to provide power supply so that the robot (10) can operate independently without an external power source; The housing module (140) protects the internal components while providing structural support.

3. A desktop AI educational robot integrating a large model according to claim 2, characterized in that: The circuit module (100) comprises: A control unit (111), including an MCU chip, controls the behavior of the robot through the MCU chip and stores the operation data of the robot; The positioning unit (112) includes an OID reader, which can identify information on the positioning pad 30 to obtain the current positioning data of the robot (10), or identify the programming card (40) to obtain the ID information and relative rotation angle of the programming card (40); A power supply unit (113), used for charge and discharge management, to supply power to each unit in the circuit module (110); A driving unit (114) for driving each motor in the robot motion module (120); A communication unit (115) realizes the functions of burning program firmware, communicating with programming software, and communicating with a host computer or other devices; The sensor unit (116) is used to obtain the rotation speed of the motor in the motion module (120), measure the voltage of the battery module (130), obtain key information, etc. The display unit (117) provides the user with a programmable graphic display platform with functions such as prompting and decoration; A sound unit (118) for controlling the voice or ringtone effect output by the robot (10) in a programmed manner; The expansion unit (119) provides power and communication to the external module (20) through a driving circuit.

4. A desktop AI educational robot integrating a large model according to claim 3, characterized in that: The expansion unit (119) comprises four pin interfaces, the four pin interfaces comprising an A1 pin, an A2 pin, an A3 pin and an A4 pin, the A1 pin and the A4 pin are power pins, the A2 pin and the A3 pin are signal pins, and are used to connect to the MCU chip. The four pin interfaces in the external module (20) are: B1 pin, B2 pin, B3 pin and B4 pin. The four pin interfaces in the external module (20) are respectively connected to the A1 pin, A2 pin, A3 pin and A4 pin of the expansion unit (119) in the robot (10). The magnetic attraction connector of the expansion unit (119) of the robot (10) is recessed inwardly by a certain distance relative to the housing module (140), and the spring pin magnetic attraction connector (21) in the external module (20) is protruding outwardly relative to its housing.

5. A desktop AI educational robot integrating a large model according to claim 4, characterized in that: The motion module (120) comprises a right motor (121) and a left motor (122) having the same transmission mode, and the right motor (121) and the left motor (122) are connected to a driving unit (114) on the circuit module (110); Wherein: the right motor (121) is fixed on the housing chassis (142), meshed with the right driving wheel (123) through a gear transmission method, and the right driving wheel (123) and the right driven wheel (125) are driven through a crawler (127). The left motor (122) and its transmission method are similar, thereby driving the robot (10) to move.

6. A desktop AI educational robot integrating a large model according to claim 4, characterized in that: The housing module (140) is divided into a housing upper cover (141) and a housing bottom plate (142); the housing upper cover (141) is provided with an LCD screen (117A); and the circuit module (110) and the motion module (120) are fixed on the housing bottom plate (142).

7. A programming control method for a desktop AI educational robot integrating a large model, based on the implementation of a real-time graphical interface programming control as described in any one of claims 1 to 6, characterized in that: The following steps are involved: After writing the robot virtual machine firmware and the graphical building block library, the robot can be graphically programmed through a graphical programming interface. The constructed building block program will be converted into instructions in the graphical programming interface and communicate with the robot (10) virtual machine through a simple serial protocol or BLE, thereby realizing real-time programming.

8. The programming control method of a desktop AI educational robot integrating a large model according to claim 7 is characterized in that: The programming cards (40) are matched one by one with the functions of the robot (10) in advance to realize the screenless programming function, including the following functions: The programming card (40) includes cards with different patterns, and a card corresponding to a pattern corresponds to an ID information and is accompanied by angle information; The user can set the functions corresponding to these programming cards (40) in advance by programming; Afterwards, each programming card (40) will trigger the robot (10) to execute the corresponding function. There is no need to use a computer or other equipment for programming. Instead, the robot (10) can interact directly with different programming cards (40) to achieve the effect of screenless programming.

9. The programming control method of a desktop AI educational robot integrating a large model according to claim 7 is characterized in that: It is also possible to write communication interfaces, expand them through graphical programming libraries, implement communication interfaces based on high-level languages ​​such as C++ and Python through Bluetooth low energy or WiFi, and deploy artificial intelligence algorithms such as reinforcement learning, imitation learning, and large language models to single or multiple robots (10).

10. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a programming control method for a desktop-level AI educational robot integrating a large model as described in any one of claims 7 to 9.

Images