Multi-target intelligent tracking trolley

Abstract

The invention discloses a multi-target intelligent tracking trolley which comprises a trolley body, two ultrasonic modules are symmetrically installed on the two sides of the front end of the trolley body, an image recognition module, a WiFi module and a lower computer module are installed on the trolley body, the image recognition module is close to the front end of the trolley body, and the WiFi module and the lower computer module are close to the rear end of the trolley body. The trolley body is further provided with a power module and a moving assembly. According to the multi-target intelligent tracking trolley, the two-harsh graph algorithm serves as the core, the recognition and positioning capacity of the intelligent trolley in a complex environment is remarkably improved by optimizing and improving the algorithm, the trolley has higher stability and reliability in actual operation by optimizing a driving system and a control system, and the multi-target intelligent tracking trolley has the advantages of being high in practicability and easy to popularize. By arranging the sensor module, the trolley can autonomously adjust the driving strategy according to the environment change, so that the trolley can better adapt to various complex environments.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a multi-target intelligent tracking vehicle. Background Art

[0002] With the rapid advancement of artificial intelligence technology, image recognition technology has become one of the hot research areas. Image recognition technology can help computers identify and analyze the content in images, thereby realizing various applications such as human-computer interaction and intelligent control. Among them, the intelligent car following system based on image recognition color is an application direction with important research significance.

[0003] As an important platform for the research of autonomous driving technology, the smart car plays a vital role in promoting the development of intelligent transportation systems. The design and implementation of the smart car not only needs to fully consider its technical feasibility, but also needs to take into account its stability and reliability in practical applications. To this end, we design a multi-target intelligent tracking car here to improve the environmental adaptability and autonomous navigation capabilities of the car. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-target intelligent tracking vehicle to address the deficiencies of the prior art and to solve the problems raised in the background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a multi-target intelligent tracking vehicle, comprising a vehicle body, two ultrasonic modules are symmetrically installed on both sides of the front end of the vehicle body, an image recognition module, a WiFi module and a lower computer module are installed on the top of the vehicle body, the image recognition module is close to the front end of the vehicle body, the WiFi module and the lower computer module are close to the rear end of the vehicle body, and a power module and a mobile component are also installed on the vehicle body.

[0006] Preferably, the power module includes a battery, a charging module and a power module. The battery and the power module are both installed on the top of the trolley body, the charging module is installed on the bottom of the trolley body, the battery is connected to the charging module, and the charging port of the charging module is located at the front edge of the trolley body.

[0007] Preferably, the mobile component includes a drive motor, a motor drive module, a drive wheel and a universal wheel. Two symmetrical drive motors and a universal wheel are installed under the trolley body. The two drive motors are located in front of the universal wheel. Drive wheels are installed on the output shafts of the two drive motors. The motor drive module is installed on the top of the trolley body, and the motor drive module is connected to the two drive motors.

[0008] Preferably, the ultrasonic module adopts HC-SR4 ultrasonic module.

[0009] Preferably, the image recognition module includes an Erha image recognition module equipped with a K210 processor, and a camera module installed on the Erha image recognition module, and the Erha image recognition module is installed on the vehicle body through a bracket.

[0010] Preferably, the slave computer module adopts an ATmega328P single-chip microcomputer.

[0011] Preferably, the driving motor is a reduction group motor.

[0012] Preferably, the motor drive module adopts L298N motor drive module, adopts Multiwatt 15-pin package, accepts TTL logic level signal, is equipped with enable control terminal, supports dynamic adjustment circuit operation, has logic power input terminal, and has built-in voltage regulator chip 78MO5.

[0013] Preferably, the multi-target intelligent tracking car has a built-in software design programming module, as well as a visual target tracking algorithm, an ultrasonic obstacle avoidance algorithm, a motor control algorithm, a PID control algorithm and a speed smooth transition algorithm.

[0014] Preferably, the multi-target intelligent tracking car also includes a mobile phone APP, and the mobile phone APP is written using App Inventor.

[0015] Compared with the prior art, the present invention provides a multi-target intelligent tracking vehicle, which has the following beneficial effects:

[0016] The multi-target intelligent tracking car is based on the Erha image recognition algorithm. By optimizing and improving the algorithm, the recognition and positioning capabilities of the intelligent car in complex environments are significantly improved. By optimizing the drive system and control system, the car has higher stability and reliability in actual operation. By setting up sensor modules, the car can autonomously adjust its driving strategy according to environmental changes, so as to better adapt to various complex environments. In practical applications, it will help promote the development of intelligent transportation systems, bring more convenience and safety to my country's transportation, and also provide new ideas and directions for the research of autonomous driving technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the top structure of the trolley body of the present invention;

[0018] Figure 2 This is a schematic diagram of the bottom structure of the trolley body of the present invention;

[0019] Figure 3 is a circuit block diagram of the present invention;

[0020] Figure 4 This is a single chip microcomputer control circuit diagram of the present invention;

[0021] Figure 5 This is a power supply circuit diagram of the present invention;

[0022] Figure 6 This is a diagram of the motor drive module of the present invention;

[0023] Figure 7 This is the truth table diagram of the L298N chip of the present invention;

[0024] Figure 8 It is a flow chart of the program of the present invention;

[0025] Fig. 9 A graphical programming page diagram of the present invention;

[0026] Fig.10 This is the page diagram of the mobile phone APP of the present invention.

[0027] Figure numerals: 1. Car body; 2. Ultrasonic module; 3. Image recognition module; 4. WiFi module; 5. Lower computer module; 6. Battery; 7. Charging module; 8. Driving motor; 9. Motor driving module; 10. Driving wheel; 11. Universal wheel; 12. Power switch. DETAILED DESCRIPTION

[0028] 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.

[0029] See also Figure 1-Figure 10 In this embodiment: the multi-target intelligent tracking vehicle includes a vehicle body 1, please refer to Figure 1 and Figure 2 Two ultrasonic modules 2 are symmetrically installed on both sides of the front end of the trolley body 1. The ultrasonic module 2 is responsible for detecting surrounding obstacles and taking obstacle avoidance measures. An image recognition module 3, a WiFi module 4 and a lower computer module 5 are installed on the top of the trolley body 1. The image recognition module 3 is close to the front end of the trolley body 1. The image recognition module 3 is responsible for collecting image information and performing color recognition and processing on the image. The WiFi module 4 and the lower computer module 5 are close to the rear end of the trolley body 1. The lower computer module 5 is responsible for receiving instructions from the image recognition module 3 and controlling the movement of the trolley. A power module and a mobile component are also installed on the trolley body 1.

[0030] The image recognition module 3 includes an Erha image recognition module equipped with a K210 processor, and a camera module installed on the Erha image recognition module. The Erha image recognition module is installed on the car body 1 through a bracket. The camera module uses a high-resolution, color-restored device to ensure that the image is clear and accurate. The image recognition module 3 has a built-in deep learning-based algorithm that can quickly identify the target color, and calculate the car's movement trajectory based on the identified color information, and track the target object in real time. The image recognition module 3 can communicate with the lower computer through IIC and communicate with the remote APP through WiFi to work together to complete the task.

[0031] The power module includes a battery 6, a charging module 7 and a power switch 12. The battery 6 and the power switch 12 are both installed on the top of the trolley body 1, and the charging module 7 is installed on the bottom of the trolley body 1. The battery 6 is connected to the charging module 7. The charging port of the charging module 7 is located at the front edge of the trolley body 1. The battery 6 is responsible for supplying power to the trolley. The battery 6 can be charged by connecting the power supply and the charging port of the charging module 7 with a charger.

[0032] The mobile component includes a drive motor 8, a motor drive module 9, a drive wheel 10 and a universal wheel 11. Two symmetrical drive motors 8 and a universal wheel 11 are installed under the trolley body 1. The two drive motors 8 are located in front of the universal wheel 11. The drive wheels 10 are installed on the output shafts of the two drive motors 8. The motor drive module 9 is installed on the top of the trolley body 1. The motor drive module 9 is connected to the two drive motors 8. The motor drive module 9 is responsible for converting the control signal into the actual movement of the drive motor 8.

[0033] The driving motor 8 adopts a reduction group motor, and the current is relatively large, so the motor driving module 9 adopts the L298N motor driving module. L298N is a high-performance chip, suitable for high voltage and high current applications, supports dual-channel full-bridge drive, has a maximum operating voltage of 46V, and an output current of up to 4A. It adopts a Multiwatt 15-pin package, accepts TTL logic level signals, is equipped with an enable control terminal, supports dynamic adjustment of circuit operation, has a logic power input terminal, and has a built-in voltage regulator chip 78MO5, which can stably work at low voltage and has an output logic voltage of 5V.

[0034] The ultrasonic module 2 adopts the HC-SR04 ultrasonic module. The HC-SR04 module has excellent performance, integrated transmitter, receiver and control circuit, and has an accuracy of 3mm. The HC-SR04 ultrasonic module has a ranging range of 2cm to 400cm, which meets the 3m measurement requirement. The module requires a 10 microsecond pulse trigger signal to start, continuously emits 8 cycles of 40kHz ultrasonic waves and detects echoes. The echo pulse width is linearly related to the distance. To avoid interference, the trigger period must be greater than the return time of the transmitted wave.

[0035] The overall circuit is as follows Figure 3 As shown, the overall system is divided into four parts: the first part is the power supply for the entire system, which includes two power supply solutions: 5V power supply and 3.3V and 12V power supply; the second part is the camera and visual processing unit; the third part is the lower computer MCU program processing; the fourth part is the ultrasonic module and the motor drive processing unit.

[0036] The lower computer module 5 adopts ATmega328P single-chip microcomputer, which is a low-power AVR8-bit microprocessor with two different communication modes: IIC and SPI. The single-chip microcomputer has six PWM output channels, a 16-bit timer / counter (Tirme0) and two interrupt control pins. The 16-bit timer / counter (Tirme0) has an independent frequency division function, a comparison function and a capture mode. The ATmega328P single-chip microcomputer can process optical signals. The control circuit of the single-chip microcomputer can be seen in Figure 4 .

[0037] Power circuit such as Figure 5 As shown, the voltage regulator chip used in the power supply circuit is LM2940 (converted to 5V), and the VIN network port adopts LM358 comparator to stabilize the output voltage at 5V. In the power supply circuit, 47uF electrolytic capacitor and 1uF non-polar capacitor are respectively connected to the input and output for filtering. 47uF is mainly used to filter out 50-60HZ mains noise, and 1uF is mainly used to filter out high-frequency signals.

[0038] Motor drive circuit such as Figure 6 As shown, the motor drive module 9 is mainly used to control the current of the drive motor 8. Because the output current of the single-chip microcomputer is weak and insufficient to drive the drive motor 8 to run, a motor drive chip (L298N) is needed to provide energy. The principle of the motor drive chip is equivalent to the H bridge composed of MOS tubes. A 74LS00 NAND gate is added to the front stage of the motor drive. Because L298N needs to control 6 pins (ENA, ENB, IN1, IN2, IN3, IN4) at the same time when working, in order to reduce the control pins, a NAND gate is introduced. Its feature is to reduce the single-chip microcomputer and motor drive control pins. The working principle is to give two pins of the single-chip microcomputer to ENA and ENB respectively, and the other two PWM pins of the single-chip microcomputer are connected to the NAND gate, so that IN1 and IN2 (a group) are always in opposite states. Figure 7 shown.

[0039] The multi-target intelligent tracking car has a built-in software design and programming module, which includes a main program, T0 interrupt, external interrupt and ultrasonic generation subroutine. For the specific program flow, please refer to Figure 8 The software adopts modular design, which can facilitate expansion and transplantation between the same type of equipment and facilitate assembly line production.

[0040] The multi-target intelligent tracking car also includes a mobile phone APP, which is written in App Inventor. For the specific graphical programming interface, please refer to Fig. 9 The user can select the target color through the APP and send a signal to the car. The WiFi module 4 can receive the color setting data sent by the remote APP. The APP page is as follows Fig.10 .

[0041] The multi-target intelligent tracking car has a built-in visual target tracking algorithm. In visual object tracking, a tracking method based on a color histogram is used. First, the target area is selected by a camera and a color histogram is calculated. Then, the most matching color histogram area is searched in subsequent frames to determine the target position. In order to improve the accuracy, a target position prediction mechanism is introduced to predict the target position range based on the motion trajectory to narrow the search range. At the same time, a re-capture mechanism is designed after the target is lost. When the target is not detected for multiple consecutive frames, the search range is expanded and the target is re-captured.

[0042] The multi-target intelligent tracking car has a built-in ultrasonic obstacle avoidance algorithm, which is based on the HC-SR04 ultrasonic module. When the vehicle is driving, the sensor emits ultrasonic waves and detects echoes. After finding an obstacle, the sensor sends distance information to the microcontroller. The microcontroller combines speed and direction to calculate the obstacle avoidance strategy. Close obstacles trigger emergency braking or steering. The fuzzy control algorithm is introduced to improve accuracy and reliability. By fuzzy processing input variables and design rules, the car can flexibly adjust the obstacle avoidance strategy to achieve intelligent obstacle avoidance.

[0043] The multi-target intelligent tracking car has a built-in motor control algorithm, which controls the speed and direction of the car. According to the results of the ultrasonic obstacle avoidance algorithm and the visual target tracking algorithm, the single chip adjusts the output signal of the motor drive circuit in real time to control the speed and direction of the motor. In order to improve the driving stability and response speed of the car, the PID control algorithm is used to adjust the speed of the drive motor 8. By continuously adjusting the PWM duty cycle of the drive motor 8, the actual driving speed of the car is kept consistent with the target speed. At the same time, a speed smooth transition algorithm is designed to enable the car to maintain a stable driving state during acceleration and deceleration.

[0044] After the system is built and programmed, it is necessary to enter the debugging test. First, check the power supply circuit to ensure that the non-polarized capacitor can work stably and provide a stable power supply for the system. Then, verify the motor drive circuit. By giving a NOT gate signal, confirm whether the L298N chip can control the motor. At the same time, verify whether the diode can absorb the reverse electromotive force and protect the circuit.

[0045] During software debugging, the operation of the main program, interrupt service program and ultrasonic generation subroutine is verified, and the functions and performance of the mobile phone APP development program, visual tracking, ultrasonic obstacle avoidance and motor control algorithms are tested. During the mobile phone APP test, the user is simulated to select colors and send signals through the APP to see whether the system can successfully receive and parse the signals and perform operations.

[0046] Finally, the overall test of the system needs to be carried out, including target color tracking test, ultrasonic obstacle avoidance test and motor control test. The specific test plan is as follows:

[0047] Target color tracking test: Select the target color through the mobile phone APP written by App Inventor and send the signal to the car. After receiving the signal, the car starts the visual target tracking algorithm, captures and tracks the target color object through the camera, moves the color object in different scenes, and observes the tracking effect of the car;

[0048] Ultrasonic obstacle avoidance test: obstacles of different distances and shapes are set in the test environment to observe whether the car can detect obstacles in real time and take corresponding obstacle avoidance strategies during driving. Testers simulate different obstacle avoidance scenarios by changing the position and number of obstacles to test the car's obstacle avoidance performance.

[0049] Motor control test: By adjusting the speed and direction of the car, the accuracy and stability of the motor control algorithm are tested. The tester sets different speed and direction parameters, observes the actual driving conditions of the car, and compares and analyzes them with the target values.

[0050] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multi-target intelligent tracking vehicle, comprising a vehicle body (1), characterized in that: Two ultrasonic modules (2) are symmetrically installed on both sides of the front end of the trolley body (1); an image recognition module (3), a WiFi module (4) and a lower computer module (5) are installed on the top of the trolley body (1); the image recognition module (3) is close to the front end of the trolley body (1); the WiFi module (4) and the lower computer module (5) are close to the rear end of the trolley body (1); and a power module and a moving component are also installed on the trolley body (1).

2. The multi-target intelligent tracking vehicle according to claim 1 is characterized in that: The power module comprises a battery (6), a charging module (7) and a power switch (12); the battery (6) and the power switch (12) are both installed on the top of the trolley body (1); the charging module (7) is installed on the bottom of the trolley body (1); the battery (6) is connected to the charging module (7); and the charging port of the charging module (7) is located at the front edge of the trolley body (1).

3. The multi-target intelligent tracking vehicle according to claim 1 is characterized in that: The mobile assembly comprises a drive motor (8), a motor drive module (9), a drive wheel (10) and a universal wheel (11); two symmetrical drive motors (8) and a universal wheel (11) are installed below the trolley body (1); the two drive motors (8) are located in front of the universal wheel (11); the output shafts of the two drive motors (8) are both installed with drive wheels (10); the motor drive module (9) is installed above the trolley body (1); and the motor drive module (9) is connected to the two drive motors (8).

4. The multi-target intelligent tracking vehicle according to claim 1 is characterized in that: The ultrasonic module (2) adopts the HC-SR04 ultrasonic module.

5. The multi-target intelligent tracking vehicle according to claim 1 is characterized in that: The image recognition module (3) comprises an Erha image recognition module equipped with a K210 processor, and a camera module installed on the Erha image recognition module. The Erha image recognition module is installed on the vehicle body (1) via a bracket.

6. The multi-target intelligent tracking vehicle according to claim 3 is characterized in that: The lower computer module (5) adopts an ATmega328P single-chip microcomputer.

7. The multi-target intelligent tracking vehicle according to claim 3 is characterized in that: The driving motor (8) is a reduction group motor.

8. The multi-target intelligent tracking vehicle according to claim 3 is characterized in that: The motor drive module (9) adopts an L298N motor drive module, adopts a Multiwatt 15-pin package, accepts TTL logic level signals, is equipped with an enable control terminal, supports dynamic adjustment of circuit operation, has a logic power input terminal, and has a built-in voltage regulator chip 78MO5.

9. The multi-target intelligent tracking vehicle according to claim 1, characterized in that: The multi-target intelligent tracking car has built-in software design and programming modules, as well as visual target tracking algorithms, ultrasonic obstacle avoidance algorithms, motor control algorithms, PID control algorithms and speed smooth transition algorithms.

10. The multi-target intelligent tracking vehicle according to claim 1, characterized in that: The multi-target intelligent tracking car also includes a mobile phone APP, and the mobile phone APP is written using App Inventor.

Images