Embedded artificial intelligence teaching platform

Abstract

The utility model provides an embedded artificial intelligence teaching platform. The embedded artificial intelligence teaching platform comprises a main control module, and a sensor module, an execution mechanism module, a power supply module, a matrix keyboard, shortcut keys, a knob, an array microphone and a display screen which are all wirelessly connected with the main control module, the sensor module is used for collecting analog signal data, the execution mechanism module is used for transmitting and sorting preset objects, the matrix keyboard is used for receiving data in various formats, the shortcut key is used for starting preset operation in a first preset scene, and the knob is used for switching voice and gesture modes in a second preset scene. The array microphone is used for acquiring voice in a third preset scene, and the main control module is used for calculating the analog signal data according to an EB algorithm model to obtain a control instruction. According to the embedded artificial intelligence teaching platform, the problems of insufficient teaching resources and insufficient functions of the embedded artificial intelligence teaching platform in the prior art are solved.

Description

Technical Field

[0001] The utility model relates to the technical field of artificial intelligence, in particular to an embedded artificial intelligence teaching platform. Background Art

[0002] With the widespread application of embedded artificial intelligence technology in the fields of industry, Internet of Things, smart home, etc., the market demand for related talents is also increasing day by day. The existing embedded artificial intelligence teaching platform has insufficient teaching resources and functions, which cannot meet the teaching needs of many schools and educational institutions, resulting in students' learning in this field being restricted. Utility Model Content

[0003] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide an embedded artificial intelligence teaching platform, which solves the problems of insufficient teaching resources and insufficient functions of the embedded artificial intelligence teaching platform in the prior art.

[0004] To achieve the above purpose, the utility model provides the following solutions:

[0005] An embedded artificial intelligence teaching platform, comprising:

[0006] A main control module and a sensor module, an actuator module, a power module, a matrix keyboard, shortcut keys, a knob, an array microphone, and a display screen, all of which are wirelessly connected to the main control module;

[0007] The sensor module is used to collect analog signal data, and the analog signal data includes: light intensity data, infrared data, distance data, temperature and humidity data, heart rate data, RFID data, inertia data, millimeter data, volume data, rotation speed data, gesture data, communication data and gas data. The actuator module is used to transmit and sort preset objects. The matrix keyboard is used to receive data in multiple formats. The shortcut key is used to start the preset operation in the first preset scene. The knob is used to switch the voice and gesture mode in the second preset scene. The array microphone is used to obtain the voice in the third preset scene. The power module is used to supply power to the main control module, the sensor module, the actuator module, the matrix keyboard, the shortcut key, the knob, the array microphone, and the display screen. The main control module is used to calculate the analog signal data according to the EB algorithm model to obtain control instructions.

[0008] Preferably, the main control module includes:

[0009] A main controller, a first assistant controller and a second assistant controller;

[0010] The first auxiliary controller is wirelessly connected to the second auxiliary controller, and the second auxiliary controller and the first auxiliary controller are both wirelessly connected to the main controller;

[0011] The first auxiliary controller is used to collect the analog signal data and transmit it to the second auxiliary controller, the second auxiliary controller is used to summarize the analog signal data and transmit it to the main controller, and the main controller is used to calculate the summarized analog signal data according to the EB algorithm model to obtain control instructions.

[0012] Preferably, the main controller is an Edgeboard computing card, wherein the processor of the Edgeboard computing card is a 4-core A75@1.8GHz+4-core A55@1.8GHz, the memory is 4GB, LPDDR4x, and the AI ​​computing power is 3.2TOPs@int8.

[0013] Preferably, the first co-controller and the second co-controller are both STM32F407VET6 main control chip core board, wherein the STM32F407VET6 main control chip core board adopts ARM Cortex-M4 core with a main frequency of 168MHz.

[0014] Preferably, the sensor module comprises:

[0015] A light intensity detection sensor, an infrared obstacle detection sensor, a laser ranging sensor, a temperature and humidity sensor, a heart rate and blood oxygen sensor, an RFID sensor, an inertial detection sensor, a millimeter wave sensor, a volume detection sensor, a rotation speed measurement sensor, a gesture sensor, a wireless communication sensor, and a gas sensor connected to the first co-controller;

[0016] The light intensity detection sensor is used to obtain light intensity data, the infrared obstacle detection sensor is used to obtain infrared data, the laser ranging sensor is used to obtain distance data, the temperature and humidity sensor is used to obtain temperature and humidity data, the heart rate and blood oxygen sensor is used to obtain heart rate data, the RFID sensor is used to obtain RFID data, the inertial detection sensor is used to obtain inertial data, the millimeter wave sensor is used to obtain millimeter data, the volume detection sensor is used to obtain volume data, the rotation speed measurement sensor is used to obtain rotation speed data, the gesture sensor is used to obtain gesture data, the wireless communication sensor is used to obtain communication data, and the gas sensor is used to obtain gas data.

[0017] Preferably, the actuator module comprises:

[0018] a robotic arm and a conveyor belt both connected to the first co-controller;

[0019] The robotic arm is used to sort the preset objects, and the conveyor belt is used to transport the preset objects.

[0020] Preferably, the power supply of the power module is set to 12V / 6A.

[0021] According to the specific embodiments provided by the utility model, the utility model discloses the following technical effects:

[0022] The utility model provides an embedded artificial intelligence teaching platform, including: a main control module and a sensor module, an actuator module, a power module, a matrix keyboard, a shortcut key, a knob, an array microphone, and a display screen, all of which are wirelessly connected to the main control module; the sensor module is used to collect analog signal data, and the analog signal data includes: light intensity data, infrared data, distance data, temperature and humidity data, heart rate data, RFID data, inertia data, millimeter data, volume data, speed data, gesture data, communication data, and gas data; the actuator module is used to transmit and sort preset objects; the matrix keyboard is used to receive data in multiple formats; the shortcut key is used to start a preset operation in a first preset scene; the knob is used to switch the mode of voice and gesture in a second preset scene; the array microphone is used to obtain voice in a third preset scene; the power module is used to power the main control module, the sensor module, the actuator module, the matrix keyboard, the shortcut key, the knob, the array microphone, and the display screen; the main control module is used to calculate the analog signal data according to the EB algorithm model to obtain control instructions. The utility model improves the teaching resources and functions of the embedded artificial intelligence teaching platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0024] Figure 1 A schematic diagram of the teaching platform structure provided by an embodiment of the utility model;

[0025] Figure 2 A diagram of the teaching platform architecture provided for an embodiment of the utility model;

[0026] Figure 3 This is a schematic diagram of the appearance of a teaching platform provided in an embodiment of the utility model.

[0027] Reference numerals:

[0028] 1-Edgeboard computing card, 2-STM32F407VET6 main control chip core board, 3-display screen, 4-robotic arm, 5-operating table, 6-conveyor belt, 7-USB interface, 8-array microphone, 9-laser ranging sensor, 10-relay, 11-matrix keyboard, 12-shortcut keys, 13-knob, 14-infrared obstacle detection sensor, 15-volume detection sensor, 16-light intensity detection sensor, 17-gas sensor, 18-wireless communication sensor, 19-temperature and humidity sensor, 20-RFID sensor, 21-millimeter wave sensor, 22-heart rate blood oxygen sensor, 23-inertial detection sensor, 24-gesture sensor. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.

[0030] The purpose of the utility model is to provide an embedded artificial intelligence teaching platform, which solves the problems of insufficient teaching resources and insufficient functions of the embedded artificial intelligence teaching platform in the prior art.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0032] like Figure 1 As shown, the utility model provides an embedded artificial intelligence teaching platform, including:

[0033] A main control module and a sensor module, an actuator module, a power module, a matrix keyboard 11, a shortcut key 12, a knob 13, an array microphone 8, and a display screen 3, all of which are wirelessly connected to the main control module;

[0034] The sensor module is used to collect analog signal data, and the analog signal data includes: light intensity data, infrared data, distance data, temperature and humidity data, heart rate data, RFID data, inertia data, millimeter data, volume data, rotation speed data, gesture data, communication data and gas data. The actuator module is used to transmit and sort preset objects. The matrix keyboard 11 is used to receive data in multiple formats. The shortcut key 12 is used to start the preset operation in the first preset scene. The knob 13 is used to switch the voice and gesture mode in the second preset scene. The array microphone 8 is used to obtain the voice in the third preset scene. The power module is used to supply power to the main control module, the sensor module, the actuator module, the matrix keyboard 11, the shortcut key 12, the knob 13, the array microphone 8, and the display screen 3. The main control module is used to calculate the analog signal data according to the EB algorithm model to obtain control instructions.

[0035] Specifically, this teaching platform integrates a variety of sensors and actuators, and is equipped with a chip with powerful processing performance. Therefore, it can be applied to a variety of scenarios, including but not limited to six major scenarios: intelligent voice interaction, intelligent security, smart medical care, smart warehousing, smart factory, and smart home.

[0036] Furthermore, the main control module includes:

[0037] A main controller, a first assistant controller and a second assistant controller;

[0038] The first auxiliary controller is wirelessly connected to the second auxiliary controller, and the second auxiliary controller and the first auxiliary controller are both wirelessly connected to the main controller;

[0039] The first auxiliary controller is used to collect the analog signal data and transmit it to the second auxiliary controller, the second auxiliary controller is used to summarize the analog signal data and transmit it to the main controller, and the main controller is used to calculate the summarized analog signal data according to the EB algorithm model to obtain control instructions.

[0040] Furthermore, the main controller is Edgeboard computing card 1, wherein the processor of Edgeboard computing card 1 is 4-core A75@1.8GHz+4-core A55@1.8GHz, the memory is 4GB, LPDDR4x, and the AI ​​computing power is 3.2TOPs@int8.

[0041] Furthermore, the first co-controller and the second co-controller are both STM32F407VET6 main control chip core board 2, wherein the STM32F407VET6 main control chip core board 2 adopts an ARM Cortex-M4 core with a main frequency of 168 MHz.

[0042] Specifically, the main control module includes 1 Edgeboard computing card 1 and 2 STM32F407VET6 main control chip core boards 2. The processor of Edgeboard computing card 1 is 4-core A75@1.8GHz+4-core A55@1.8GHz, the memory is 4GB, LPDDR4x, and the AI ​​computing power is 3.2TOPs@int8. As an AI control motherboard, it is mainly used for model deployment and calculation. The two STM32F407VET6 main control chip core boards 2 both use the ARM Cortex-M4 core with a main frequency of 168MHz. As co-controllers, they are mainly responsible for the data processing of sensors and the control output of actuators.

[0043] The main control core board is equipped with two external crystal oscillators (8MHz / 32.75KHz) for accurate system clock and RT oscillation clock. The controller adopts JATG-SWD program download method and designs a 256K external EEPROM chip for user-level data storage and interaction. The core board power supply is designed with multi-channel low-pass filter circuit to ensure analog-to-digital sampling and system safety.

[0044] Furthermore, the sensor module comprises:

[0045] A light intensity detection sensor 16, an infrared obstacle detection sensor 14, a laser distance measurement sensor 9, a temperature and humidity sensor 19, a heart rate and blood oxygen sensor 22, an RFID sensor 20, an inertial detection sensor 23, a millimeter wave sensor 21, a volume detection sensor 15, a rotation speed measurement sensor, a gesture sensor 24, a wireless communication sensor 18 and a gas sensor 17 connected to the first co-controller;

[0046] The light intensity detection sensor 16 is used to obtain light intensity data, the infrared obstacle detection sensor 14 is used to obtain infrared data, the laser ranging sensor 9 is used to obtain distance data, the temperature and humidity sensor 19 is used to obtain temperature and humidity data, the heart rate blood oxygen sensor 22 is used to obtain heart rate data, the RFID sensor 20 is used to obtain RFID data, the inertial detection sensor 23 is used to obtain inertial data, the millimeter wave sensor 21 is used to obtain millimeter data, the volume detection sensor 15 is used to obtain volume data, the speed measurement sensor is used to obtain speed data, the gesture sensor 24 is used to obtain gesture data, the wireless communication sensor 18 is used to obtain communication data, and the gas sensor 17 is used to obtain gas data.

[0047] Specifically, all sensors are pluggable and can be used individually or simultaneously.

[0048] The sensor module is plugged in through the Mini-PCIE interface, supporting hot plugging and bus communication. The 10 groups of sensor sockets have analog signal acquisition (ADC), bus communication (SPI, CAN, UART, IIC) and GPIO control functions to ensure the switching and plugging of each module.

[0049] Furthermore, the actuator module comprises:

[0050] A robotic arm 4 and a conveyor belt 6, both connected to the first co-controller;

[0051] The robot arm 4 is used to sort the preset objects, the conveyor belt 6 is used to transport the preset objects, the robot arm 4 is located on the operating table 5, and the operating table 5 is used to perform robot arm related operations.

[0052] Specifically, the robot arm 4 is driven by a 6-DOF servo and has an embedded industrial camera that can be used to collect images and supports UART communication. The conveyor belt 6 has a size of 290mm x 22.44mm x 107.29mm and is driven by a DC motor for transporting items. The cooperation between the robot arm 4 and the conveyor belt 6 can realize smart warehousing / smart factory scenarios such as express sorting and cargo handling.

[0053] The robot arm 4 is designed for single-line serial communication, with a control power supply of 7.4V / 5A, and can drive 6 bus servos to work at the same time.

[0054] The H-bridge circuit is designed to drive the DC brushed motor to control the conveyor belt 6. The circuit uses PWM pulse signals to control the bipolar ridge driver chip to achieve flexible switching of the upper and lower bridge arms of the MOS full bridge to complete the speed and direction control of the motor. In order to prevent the upper and lower bridge arms of the bridge circuit from being turned on at the same time and burning the device, the circuit is designed with a NOT gate (1G04) and an AND gate (1G08) structure to achieve hardware exclusion and ensure that the unidirectional bridge arm connection is completed at the same time.

[0055] Specifically, the matrix keyboard 11 has a specific specification of 4*3, and can input data in various formats. The shortcut keys 12 and the knobs 13 can specify corresponding functions in different usage scenarios and quickly perform corresponding operations. For example, the shortcut key 12 can be used as a selection button for the ABC options in the smart medical scenario, and as a start button in the smart warehousing / smart factory scenario; the knob 13 can be pressed to replay the prompt word in the smart security scenario, and the knob 13 can switch between voice mode and gesture mode in the smart medical scenario. The specific specifications of the array microphone 8 are 4 microphone arrays, 5m field voice capture, support USB2.0, and have functions such as noise reduction, dereverberation, voice activity detection, sound source localization, beamforming, etc., to collect sound and determine the direction of the sound source in various voice scenarios. The display screen 3 includes a 17-inch HDMI display screen 3 and a 4.0-inch TFT LCD full-color display screen 3, which display the status of the experimental box and related information in real time in each scene.

[0056] Furthermore, the matrix keyboard 11, the shortcut keys 12, the knob 13, the array microphone 8 and the display screen 3 constitute a human-computer interaction module.

[0057] Specifically, the matrix keyboard 11 circuit is driven by the CH455G chip, scans the 12-bit (3x4) button status in real time, and completes the MCU response by outputting an interrupt signal. The MCU reads the key value through the IIC protocol.

[0058] The knob 13 button circuit is designed with a low-pass filter to capture the A / B phase pulse signal of the rotary encoder, and a pull-up resistor is set to provide the bias voltage required by the encoder. At the same time, the pull-up resistor prevents the influence of the floating signal when the button is lifted.

[0059] Bus RGB lamp circuit design WS2812 bus series light strip, MCU controls the color of 5 RGB full-color lamp beads through a single bus protocol, and realizes the switching of lighting effect modes such as flowing light, flashing light and constant light.

[0060] Furthermore, the power supply of the power module is set to 12V / 6A.

[0061] Specifically, the power module includes a power switch and a USB interface 7, controls the power supply of the test box and provides the USB interface 7 to the outside. The power supply used by the test box is 12V / 6A.

[0062] The power consumption of the whole machine is divided into the mainboard logic power supply, sensor peripheral power supply, robot arm 4 power supply, AI board power supply, conveyor power supply and other peripheral power supplies. Its rated power consumption is designed to be 12V / 3A. Considering the system redundancy design measures, a 12V / 6A adapter is designed to supply power to it.

[0063] All the above components can be used at the same time without interfering with each other, supporting multi-task parallel processing. At the same time, the integrated design is adopted, and the main controller and various sensor resources are closely combined, which is convenient for users to develop and learn.

[0064] Specifically, this product is a comprehensive artificial intelligence teaching platform for Internet of Things and automation-related majors. It integrates embedded systems, robotic arms 4, computer vision systems, intelligent voice processing, as well as cameras, temperature and humidity sensors 19, infrared ranging and other sensor application modules. By building edge computing terminals, it provides unified communication protocols and interfaces for related application development. The embedded artificial intelligence platform includes a core AI control motherboard (Edgeboard) and two co-control motherboards. Among them, co-control motherboard A is responsible for the control of multiple devices such as terminal power relays 10 and LCD display screens 3; co-control motherboard B is responsible for up to 9 sensor data sampling and multiple human-computer interaction device information input. Co-control motherboard A transmits sensor and command data to co-control motherboard B in real time, and finally co-control motherboard B summarizes it to Edgeboard. After the EB algorithm model completes the calculation, it sends the terminal control command to the coprocessor to complete the control task. The architecture is as follows Figure 2 shown.

[0065] Specifically, the upper part of the product is a depth camera and an LCD screen 3, and the lower part is divided into two layers. The upper layer is an integrated circuit board matrix keyboard 11 combined with sensors, RGB lights, microphone arrays, etc., and the lower layer stores power adapters, teaching aids, wireless keyboards and mice, etc. The lower end of the back of the product is a power interface and a network cable interface. The power interface is used to power the entire experimental box, and the network cable interface can be connected to the network to remotely control the experimental box. The overall appearance size of the product is 550mm x400mmx 200mm, such as Figure 3 shown.

[0066] The beneficial effects of the utility model are as follows:

[0067] (1) The platform integrates multiple intelligent scenarios into a comprehensive test box;

[0068] (2) A reasonable and detailed class schedule can be customized according to the actual situation of each school;

[0069] (3) The embedded artificial intelligence teaching platform is committed to solving technical problems in the field of embedded artificial intelligence technology, such as hardware and software integration, embedded system design and optimization, sensor and actuator applications, and real-time operating systems and algorithm optimization. It provides students with comprehensive learning resources and practical opportunities to help them better master and apply related technologies.

[0070] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0071] This article uses specific examples to illustrate the principles and implementation methods of the utility model. The above examples are only used to help understand the method and core ideas of the utility model. At the same time, for those skilled in the art, according to the ideas of the utility model, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the utility model.

Claims

1. An embedded artificial intelligence teaching platform, characterized in that: include: A main control module and a sensor module, an actuator module, a power module, a matrix keyboard, shortcut keys, a knob, an array microphone, and a display screen, all of which are wirelessly connected to the main control module; The sensor module is used to collect analog signal data, and the analog signal data includes: light intensity data, infrared data, distance data, temperature and humidity data, heart rate data, RFID data, inertia data, millimeter data, volume data, rotation speed data, gesture data, communication data and gas data. The actuator module is used to transmit and sort preset objects. The matrix keyboard is used to receive data in multiple formats. The shortcut key is used to start the preset operation in the first preset scene. The knob is used to switch the voice and gesture mode in the second preset scene. The array microphone is used to obtain the voice in the third preset scene. The power module is used to supply power to the main control module, the sensor module, the actuator module, the matrix keyboard, the shortcut key, the knob, the array microphone, and the display screen. The main control module is used to calculate the analog signal data according to the EB algorithm model to obtain control instructions.

2. An embedded artificial intelligence teaching platform according to claim 1, characterized in that: The main control module comprises: A main controller, a first assistant controller and a second assistant controller; The first auxiliary controller is wirelessly connected to the second auxiliary controller, and the second auxiliary controller and the first auxiliary controller are both wirelessly connected to the main controller; The first auxiliary controller is used to collect the analog signal data and transmit it to the second auxiliary controller, the second auxiliary controller is used to summarize the analog signal data and transmit it to the main controller, and the main controller is used to calculate the summarized analog signal data according to the EB algorithm model to obtain control instructions.

3. An embedded artificial intelligence teaching platform according to claim 2, characterized in that: The main controller is an Edgeboard computing card, wherein the processor of the Edgeboard computing card is a 4-core A75@1.8GHz+4-core A55@1.8GHz, the memory is 4GB, LPDDR4x, and the AI ​​computing power is 3.2TOPs@int8.

4. An embedded artificial intelligence teaching platform according to claim 2, characterized in that: The first co-controller and the second co-controller are both STM32F407VET6 main control chip core boards, wherein the STM32F407VET6 main control chip core board adopts an ARM Cortex-M4 core with a main frequency of 168 MHz.

5. An embedded artificial intelligence teaching platform according to claim 2, characterized in that: The sensor module comprises: A light intensity detection sensor, an infrared obstacle detection sensor, a laser ranging sensor, a temperature and humidity sensor, a heart rate and blood oxygen sensor, an RFID sensor, an inertial detection sensor, a millimeter wave sensor, a volume detection sensor, a rotation speed measurement sensor, a gesture sensor, a wireless communication sensor, and a gas sensor connected to the first co-controller; The light intensity detection sensor is used to obtain light intensity data, the infrared obstacle detection sensor is used to obtain infrared data, the laser ranging sensor is used to obtain distance data, the temperature and humidity sensor is used to obtain temperature and humidity data, the heart rate and blood oxygen sensor is used to obtain heart rate data, the RFID sensor is used to obtain RFID data, the inertial detection sensor is used to obtain inertial data, the millimeter wave sensor is used to obtain millimeter data, the volume detection sensor is used to obtain volume data, the speed measurement sensor is used to obtain speed data, the gesture sensor is used to obtain gesture data, the wireless communication sensor is used to obtain communication data, and the gas sensor is used to obtain gas data.

6. An embedded artificial intelligence teaching platform according to claim 5, characterized in that: The actuator module comprises: a robotic arm and a conveyor belt both connected to the first co-controller; The robotic arm is used to sort the preset objects, and the conveyor belt is used to transport the preset objects.

7. The embedded artificial intelligence teaching platform according to claim 1, characterized in that: The power supply of the power module is set to 12V / 6A.

Images