Self-service card issuing equipment integrating AI vision and mechanical arm control and working method

Abstract

The invention discloses self-service card issuing equipment integrating AI vision and mechanical arm control and a working method, and the equipment comprises an AI vision recognition unit which is used for capturing vehicle image data and calculating the three-dimensional position information of an object; the main control module is used for receiving the three-dimensional position information, generating an action control instruction and a driving instruction according to the three-dimensional position information and sending the action control instruction and the driving instruction to the collaborative robot; the collaborative robot is used for operating according to the action control instruction and cooperating with the end executor to complete the tasks of card reading and writing, card preparation, card issuing and bad card recovery; the movement module is used for receiving the driving instruction and generating an execution instruction; and the end effector is used for receiving the execution instruction and cooperating with the collaborative robot to complete the tasks of card reading and writing, card preparation, card issuing and bad card recovery. By implementing the equipment provided by the invention, not only can the traffic efficiency be improved, but also the intelligent degree and adaptability of the system are enhanced, and the requirements of modern traffic management are met.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a self-service card issuing device and its operating method that integrates AI vision and robotic arm control. Background Technology

[0002] With the continuous expansion and improvement of the highway network, traffic flow is increasing daily, placing higher demands on the efficiency of toll stations. Traditional manual card issuance methods, due to their inefficiency and high manpower consumption, are no longer adequate to meet the modern society's demand for fast and efficient travel. Therefore, self-service card issuance machines are gradually being widely adopted as a modern solution.

[0003] Most mainstream self-service card dispensing devices on the market currently use a "button-operated card dispensing + retractable panel" method. This means drivers need to press a button to retrieve the card after parking, and may need to adjust their body posture to take the card from the device. However, this operating mode has several limitations: due to the uncertainty of vehicle parking positions, such as windows being too high or too low, drivers may have difficulty retrieving the card smoothly, thus affecting traffic efficiency. Existing devices cannot automatically recognize license plates and vehicle types, and their support for vehicles without license plates, vehicles with temporary license plates, and special vehicles such as trucks is insufficient. The system only determines that a card is faulty or has insufficient battery power after an attempt to read or write the CPC card fails, increasing the probability of card dispensing failure. Especially in inclement weather conditions, drivers need to lean out to retrieve the card, causing inconvenience and discomfort for users.

[0004] Therefore, it is necessary to design a new device that can automatically identify license plates, vehicle models, and window positions through AI vision technology. At the same time, it can use advanced read / write modules to detect the status of CPC cards in advance, effectively filter out bad cards and low-battery cards, and recycle them. This not only improves traffic efficiency but also enhances the intelligence and adaptability of the system, meeting the needs of modern traffic management. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a self-service card issuing device and its working method that integrates AI vision and robotic arm control.

[0006] To solve the above-mentioned technical problems, the purpose of this invention is achieved through the following technical solution: providing a self-service card issuing device integrating AI vision and robotic arm control, including: a main control module, a collaborative robot, an AI vision recognition unit, an end effector, and a core module;

[0007] The AI ​​visual recognition unit is used to capture vehicle image data and calculate the three-dimensional position information of the object.

[0008] The main control module is used to receive the three-dimensional position information, generate motion control commands and drive commands based on the three-dimensional position information, and send them to the collaborative robot.

[0009] The collaborative robot is used to operate according to the motion control instructions and cooperate with the end effector to complete the tasks of reading and writing cards, preparing cards, issuing cards, and recycling damaged cards.

[0010] The mechanism module is used to receive the drive instructions to generate execution instructions for card reading and writing, card backup, card issuance and bad card recycling functions;

[0011] The end effector is used to receive the execution instructions and cooperate with the collaborative robot to complete the tasks of reading and writing cards, preparing cards, issuing cards, and recycling damaged cards.

[0012] The further technical solution is as follows: it also includes a human-computer interaction module, which is connected to the main control module.

[0013] The further technical solution is as follows: The AI ​​visual recognition unit includes a binocular depth camera, which calculates the three-dimensional position information of the object by simulating the working principle of human eyes, using triangulation and stereo matching algorithms, and provides real-time vehicle point cloud data for vehicle recognition.

[0014] The further technical solution is as follows: The AI ​​visual recognition unit captures the outline of the vehicle and the position of the windows in real time through a binocular depth camera, and uses deep learning algorithms to identify the vehicle model, the specific position of the windows and the position of the driver; based on the camera installation position and angle as the origin of the three-dimensional coordinate system, the precise three-dimensional coordinates of the center point of the driver's side window are calculated and converted into Cartesian space coordinates with the base of the robotic arm as the origin, so as to determine the target position that the end of the robotic arm should reach. The main control module guides the collaborative robot to move to the designated spatial position to complete the card delivery operation.

[0015] The further technical solution is as follows: the mechanism module includes a pre-reader / writer, a card feeding transmission mechanism, a bad card box, and a card box;

[0016] Before the end effector prepares the card, the pre-reader / writer checks the CPC card to be issued to confirm whether the card can be opened normally, whether the battery power is sufficient, and whether the 5.8G band function is activated. If the card cannot be opened or the power is insufficient, the card delivery transmission mechanism transfers the card into the recycling channel and transports it to the bad card box. If the card's 5.8G band function is activated, it reports to the lane software of the terminal, and the lane software decides whether the card needs to be recycled based on the specific situation.

[0017] The further technical solution is as follows: the end effector includes a reader / writer, an end card delivery mechanism, and a help button. The end effector is installed at the end of the collaborative robot and communicates wirelessly with the core module via Bluetooth.

[0018] In addition, to overcome the shortcomings of the prior art, the present invention also provides a method for operating the above-mentioned self-service card issuing device integrating AI vision and robotic arm control, comprising:

[0019] Qualified CPC cards are selected by checking their activation status, battery level, and activation status on specific frequency bands, while unqualified cards are processed.

[0020] The main control module drives the collaborative robot to transfer qualified CPC cards from the core module to the card reading area of ​​the end effector, ready to be delivered to the user;

[0021] The AI ​​vision recognition unit is used to determine the position of the driver's side window of the vehicle, providing three-dimensional position information for the robotic arm to deliver the card.

[0022] Based on the three-dimensional position information provided by the vision system, the main control module drives the collaborative robot to move along a predetermined path, deliver the qualified CPC card to the car owner, and confirm the card retrieval status.

[0023] The further technical solution is as follows: the process of screening qualified CPC cards by checking their activation status, battery level, and activation status in a specific frequency band, and processing unqualified cards, includes:

[0024] The mechanism module moves the CPC card to the pre-read area, unlocks the CPC card, and reads system information;

[0025] Check if the CPC card can be turned on normally, if the power is sufficient, and if the 5.8G band is activated;

[0026] If the card cannot be turned on or the battery is low, the card recycling process will begin. For unusable CPC cards, the unusable CPC cards will be moved from the pre-read area to the bad card box. If the 5.8G card has been activated, the lane software will be notified that the card has not been cleared. The lane software will then decide whether the card needs to be recycled and will execute the corresponding card recycling operation according to the instructions.

[0027] If the CPC card can be turned on normally, has sufficient power, and the 5.8G frequency band is not activated, then the CPC card is considered a qualified CPC card.

[0028] The further technical solution is as follows: The use of an AI visual recognition unit to determine the position of the driver's side window of the vehicle, providing three-dimensional position information for the robotic arm to deliver the card, includes:

[0029] After the inductive loop or radar detects a vehicle, the binocular depth camera collects real-time point cloud data.

[0030] Based on the real-time point cloud data, the YOLOv8 algorithm is used to identify the vehicle window and determine the three-dimensional coordinates of the center point of the driver's side window in the world coordinate system with the binocular camera installation center as the origin.

[0031] The coordinates of the center point of the vehicle window, based on the binocular camera coordinate system, are converted into new coordinates based on the coordinate system of the robotic arm base to obtain three-dimensional position information.

[0032] The further technical solution is as follows: based on the three-dimensional position information provided by the vision system, the main control module drives the collaborative robot to move along a predetermined path, deliver the qualified CPC card to the vehicle owner, and confirm the card retrieval status, including:

[0033] Convert 3D position information into Cartesian space position to determine the motion trajectory of the collaborative robot;

[0034] The main control module controls the movement of the collaborative robot according to a predetermined path until it reaches the designated position;

[0035] Read and write information from the CPC card in the end effector;

[0036] After the card is processed, wait for the car owner to pick it up;

[0037] The system uses a reflective sensor to monitor whether the card has been taken and sends the result back to the lane software, which then raises the barrier to allow the vehicle to pass.

[0038] The advantages of this invention compared to existing technologies are as follows: Through the close collaboration of the main control module, collaborative robot, AI vision recognition unit, end effector, and core module, this invention achieves automatic recognition and precise positioning of license plates, vehicle models, and window positions. The AI ​​vision recognition unit captures vehicle image data and calculates the three-dimensional position information of objects, providing a basis for the main control module to generate precise motion control commands. Simultaneously, the advanced read / write module can detect the status of CPC cards in advance, effectively filtering and retrieving damaged and low-battery cards. Based on the received motion control commands, the collaborative robot, in conjunction with the end effector, completes tasks such as card reading / writing, card preparation, and card issuance. This not only significantly improves traffic efficiency but also enhances the system's intelligence and adaptability, fully meeting the demands of modern traffic management for efficiency, accuracy, and service quality.

[0039] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A schematic diagram of the structure of a self-service card issuing device integrating AI vision and robotic arm control provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart illustrating the working method of the self-service card issuing device integrating AI vision and robotic arm control provided in an embodiment of the present invention;

[0043] Figure 3 A sub-process illustration of the working method of the self-service card issuing device integrating AI vision and robotic arm control provided in the embodiments of the present invention. Figure 1 ;

[0044] Figure 4 A sub-process illustration of the working method of the self-service card issuing device integrating AI vision and robotic arm control provided in the embodiments of the present invention. Figure 2 ;

[0045] Figure 5 A sub-process illustration of the working method of the self-service card issuing device integrating AI vision and robotic arm control provided in the embodiments of the present invention. Figure 3 ;

[0046] Explanation of the markings in the image:

[0047] 10. Main control module; 20. Collaborative robot; 30. AI vision recognition unit; 40. End effector; 50. Mechanism module; 60. Human-computer interaction module. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0050] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] With the expansion of highway networks and the increase in traffic flow, the traditional manual card dispensing method is inefficient and consumes a lot of manpower, making it difficult to meet the demand for fast and efficient travel. This has led to the increasing popularity of self-service card dispensing machines as a modern solution. However, most of the mainstream self-service card dispensing equipment on the market currently adopts the "button card dispensing + retractable panel" method, which has limitations such as inconvenience for drivers to take cards, insufficient support for special vehicles, high card reading and writing failure rate, and poor user experience in inclement weather. These limitations are particularly evident in the handling of vehicles with uncertain parking locations, vehicles without license plates or with temporary license plates, and in dealing with inclement weather. These problems collectively lead to reduced traffic efficiency and decreased user satisfaction.

[0053] To address this, this invention provides a self-service card issuing device and its operating method that integrates AI vision and robotic arm control. Through AI vision technology, it can automatically identify license plates, vehicle models, and window positions. Simultaneously, by utilizing an advanced read / write module to detect the status of CPC cards in advance, it effectively filters out faulty and low-battery cards and recycles them. This not only improves traffic efficiency but also enhances the system's intelligence and adaptability, meeting the needs of modern traffic management.

[0054] This self-service card issuing device, integrating AI vision and robotic arm control, uses a binocular depth camera to capture vehicle image data and employs deep learning algorithms to automatically identify license plates, vehicle models, and window positions. The calculated 3D position information is then converted into operable commands for the robotic arm, enabling precise card delivery. Simultaneously, the device's built-in core module 50 and pre-reader / writer can detect the status of CPC cards in advance, including their activation status, battery level, and activation status on specific frequency bands, effectively filtering and retrieving faulty and low-battery cards. This system not only improves the efficiency of toll station traffic and reduces the need for manual intervention but also enhances adaptability to different vehicle types, particularly excelling in handling unlicensed or special vehicles. It significantly improves user experience and system intelligence, meeting the demands of modern traffic management for fast, efficient, and intelligent services.

[0055] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0056] Please see Figure 1 The aforementioned self-service card issuing device integrating AI vision and robotic arm control includes: a main control module 10, a collaborative robot 20, an AI vision recognition unit 30, an end effector 40, and a core module 50.

[0057] AI visual recognition unit 30 is used to capture vehicle image data and calculate the three-dimensional position information of objects;

[0058] The main control module 10 is used to receive three-dimensional position information and generate motion control commands and drive commands based on the three-dimensional position information, and send them to the collaborative robot 20.

[0059] The collaborative robot 20 is used to perform operations according to motion control instructions and cooperate with the end effector 40 to complete tasks such as card reading and writing, card preparation, card issuance and bad card recycling.

[0060] The mechanism module 50 is used to receive drive commands to generate execution commands for card reading and writing, card backup, card issuance and bad card recycling functions;

[0061] The end effector 40 is used to receive execution instructions and cooperate with the collaborative robot 20 to complete the tasks of reading and writing cards, preparing cards, issuing cards, and recycling damaged cards.

[0062] In one embodiment, please refer to Figure 1 The aforementioned self-service card issuing device integrating AI vision and robotic arm control also includes a human-computer interaction module 60, which is connected to the main control module 10.

[0063] In one embodiment, please refer to Figure 1 The aforementioned AI visual recognition unit 30 includes a binocular depth camera, which simulates the working principle of human eyes, uses triangulation and stereo matching algorithms to calculate the three-dimensional position information of objects, and provides real-time vehicle point cloud data for vehicle recognition.

[0064] In this embodiment, the collaborative robot 20 includes a six-axis robotic arm.

[0065] The main control module 10 is the central hub of the entire system, responsible for coordinating and managing the work of various subsystems. It receives vehicle image data from the AI ​​vision recognition unit 30 and calculates the three-dimensional position information of the object. Based on this information, the main control module 10 generates motion control commands and drive commands, and sends them to the collaborative robot 20 (i.e., the robotic arm). In addition, the main control module 10 also interfaces with lane software and remote control systems externally, and connects to other functional modules internally to ensure the efficient operation of the overall system.

[0066] The collaborative robot 20 employs a six-axis robotic arm design and communicates with the main control module 10 via an Ethernet interface. It executes precise operations based on motion control commands issued by the main control module 10. Specifically, the collaborative robot 20 can move its end effector 40 to a designated position according to instructions, completing tasks such as card reading and writing, card preparation, card issuance, and damaged card collection. Its flexibility and precision ensure the accuracy and efficiency of the card delivery process.

[0067] At the core of the AI ​​vision recognition unit 30 is a binocular depth camera that simulates the working principle of human eyes, using triangulation and stereo matching algorithms to capture and analyze real-time point cloud data of vehicles. This enables the system to accurately calculate the three-dimensional position information of objects, including the license plate, vehicle model, and the position of windows. The real-time vehicle point cloud data provided by the AI ​​vision recognition unit 30 is used for vehicle recognition, further guiding the robotic arm to perform precise positioning and operation.

[0068] The mechanism module 50 includes functional components such as a pre-reader / writer, a card feeding mechanism, a damaged card bin, and a card bin. It receives drive commands from the main control module 10 and then generates specific execution commands for card reading / writing, card preparation, card issuance, and damaged card recycling. Before issuing cards, the pre-reader / writer checks the status of the CPC cards to ensure that only cards in good condition are issued to the user, while any problematic cards are automatically moved to the damaged card bin.

[0069] The end effector 40 is installed at the end of the collaborative robot 20 and includes functional components such as a reader / writer, a card feeding mechanism, and an emergency call button. It connects to the core module 50 via Bluetooth wireless communication technology and, after receiving execution commands, works with the collaborative robot 20 to complete tasks such as card reading / writing, card preparation, card issuance, and damaged card retrieval. This design not only improves the system's response speed but also increases operational flexibility.

[0070] In one embodiment, please refer to Figure 1 The aforementioned self-service card issuing device integrating AI vision and robotic arm control also includes a human-machine interaction module 60, which is directly connected to the main control module 10. The human-machine interaction module 60 includes a display screen, microphone, speaker, and camera, supporting intuitive interaction between the user and the system. For example, when encountering a problem, the user can press the help button to activate the visual intercom function and communicate with remote agents to resolve questions or seek assistance.

[0071] In one embodiment, please refer to Figure 1The aforementioned AI visual recognition unit 30 captures the vehicle's outline and window position in real time using a binocular depth camera, and uses deep learning algorithms to identify the vehicle model, the specific position of the window, and the driver's position. Based on the camera's installation position and angle as the origin of the three-dimensional coordinate system, it calculates the precise three-dimensional coordinates of the center point of the driver's side window and converts them into Cartesian space coordinates with the robotic arm base as the origin to determine the target position that the robotic arm's end should reach. The main control module 10 then guides the collaborative robot 20 to move to the designated spatial position to complete the card delivery operation.

[0072] A binocular depth camera captures the vehicle's outline and window positions in real time, and a deep learning algorithm accurately identifies the vehicle model, window position, and driver's position. Using the camera's mounting position and angle as the origin of a three-dimensional coordinate system, the precise three-dimensional coordinates of the center point of the driver's side window are calculated and converted into Cartesian space coordinates with the robotic arm's base as the origin, thus determining the target position that the robotic arm's end effector should reach. Based on this, the main control module 10 guides the collaborative robot 20 to move to the designated spatial position to complete a precise card delivery operation.

[0073] In one embodiment, please refer to Figure 1 The aforementioned mechanism module 50 includes a pre-reader / writer, a card feeding transmission mechanism, a bad card box, and a card box;

[0074] Before the end effector 40 prepares the card, the pre-reader checks the CPC card to be issued to confirm whether the card can be opened normally, whether the battery power is sufficient, and whether the 5.8G band function is activated. If the card cannot be opened or the power is insufficient, the card delivery mechanism will transfer the card to the recycling channel and send it to the bad card box. If the 5.8G band function of the card has been activated, it will report to the lane software of the terminal, and the lane software will decide whether to recycle the card according to the specific situation.

[0075] In one embodiment, please refer to Figure 1 The aforementioned end effector 40 includes a reader / writer, an end card delivery mechanism, and an emergency call button. The end effector 40 is installed at the end of the collaborative robot 20 and communicates wirelessly with the core module 50 via Bluetooth.

[0076] In practice, to ensure that every CPC card issued is usable, this embodiment proposes a dual-check mechanism of pre-reading and pre-judgment. Specifically, before the end effector 40 prepares a card, the contactless card reader in the core module 50 performs a pre-read check on the CPC card to be issued, determining whether the card can be opened normally, whether the battery power is sufficient, and whether the 5.8G band function is activated. If the card cannot be opened or the power is insufficient, it is automatically transferred to the recycling channel; if the 5.8G band function is activated, this status is reported to the lane software, and the lane decides whether to recycle it.

[0077] In this embodiment, the traditional method relies on pressing a button to dispense the card or retracting a panel, while this embodiment adopts a robotic arm to actively deliver the card, which greatly improves the user experience and eliminates the need for the driver to lean out to retrieve the card.

[0078] Compared to traditional methods that only recognize license plates and vehicle models, this embodiment combines AI vision and 3D positioning technology to achieve accurate identification of vehicle window positions, further improving the level of automation. Traditional faulty card handling only involves retrieving the card after it has been issued if reading fails; however, this embodiment proposes a pre-reading and pre-judgment mechanism, enabling card screening before issuance and avoiding unnecessary problems. Traditional fixed-height card dispensing designs limit applicability; this embodiment, through a robotic arm that adjusts the height, can adapt to the needs of various vehicle models. The device in this embodiment not only provides voice prompts and button-based assistance but also adds support for proactive interaction and remote video conferencing, greatly enhancing the user's interactive experience. The device in this embodiment integrates multiple modules such as vision, robotic arm, card reader, mechanism, and end effector 40, achieving multi-module collaborative control and improving the overall performance and reliability of the system.

[0079] In summary, the device in this embodiment represents a highly efficient, intelligent, and user-friendly solution, aiming to address the problems existing in the prior art and improve the quality and efficiency of self-service card issuance on highways. Applicable to highway toll station entrance lanes, it achieves fully automated operations including automatic vehicle information recognition, CPC card pre-reading and writing, damaged card screening, and precise card delivery by a robotic arm, representing a technological innovation in smart highway toll terminal equipment. AI vision automatically recognizes the license plate, vehicle type, and window position; the corresponding reading and writing module pre-reads the CPC card, screening for damaged and low-battery cards and retrieving them in advance; the robotic arm is controlled based on AI visual recognition information to precisely deliver the card to the driver through the window.

[0080] In this embodiment, the self-service card issuing device aims to achieve efficient and accurate issuance of CPC cards through a series of automated and intelligent operations. First, the pre-reading card screening function ensures that every issued card is in good condition. During this process, the core module 50 automatically moves the CPC card to be issued to the pre-reading area and uses a contactless card reader to perform card opening detection and information reading. If the card cannot be opened normally or has insufficient power, it will be automatically transferred to the recycling channel and placed in the bad card bin; if the card's 5.8G frequency band is activated, it reports a "card not cleared" status to the lane software, which then decides whether to recycle it. Next, the automatic card preparation function uses a robotic arm to precisely align the end effector 40 with the card outlet of the core module, transferring the CPC card that has passed the pre-reading detection from the core module to the end effector 40, completing the card preparation process, and reporting the "card in reading area" status to the lane software, preparing for card delivery.

[0081] The visual positioning function utilizes a binocular depth camera to capture the vehicle's outline and window position in real time. Combined with the YOLOv8 object detection algorithm, it identifies the vehicle model, window position, and driver's position, outputting the 3D coordinates A(x, y, z) of the driver's side window center point in a world coordinate system with the binocular camera's mounting center point as the origin. Since the relative position between the binocular camera and the robotic arm base is fixed, these coordinates can be converted into new coordinates A'(x', y', z') with the robotic arm base as the origin, used to calculate the robotic arm's movement path. This step provides precise target point coordinates for the subsequent card delivery by the robotic arm, ensuring the card is accurately delivered to the vehicle owner.

[0082] Finally, the robotic arm card delivery function converts coordinates A' into a Cartesian space position (x, y, z, Rx, Ry, Rz) based on the coordinates provided by visual positioning, and sets the robotic arm's movement trajectory accordingly. After the robotic arm moves to the designated spatial position according to the predetermined trajectory, it reads and writes the CPC card in the end effector 40 to complete the necessary writing operation, then hands the card to the car owner and waits for the owner to pick it up. Once the reflection sensor confirms that the card has been taken, it reports a "card taken" status to the lane software, and then the lane software controls the barrier to raise and allow the vehicle to pass. The entire process not only improves the accuracy of card issuance but also greatly enhances service efficiency and user experience.

[0083] Compared with the prior art, the beneficial effects of the device in this embodiment are shown in Table 1.

[0084] Table 1. Beneficial Effects

[0085]

[0086] The aforementioned self-service card issuing device, integrating AI vision and robotic arm control, achieves automatic recognition and precise positioning of license plates, vehicle models, and window positions through the close collaboration of the main control module 10, collaborative robot 20, AI vision recognition unit 30, end effector 40, and core module 50. The AI ​​vision recognition unit 30 captures vehicle image data and calculates the object's three-dimensional position information, providing a basis for the main control module 10 to generate precise motion control commands. Simultaneously, the advanced read / write module can detect the status of CPC cards in advance, effectively filtering and retrieving damaged and low-battery cards. Based on the received motion control commands, the collaborative robot 20, in conjunction with the end effector 40, completes tasks such as card reading / writing, card preparation, and card issuance. This not only significantly improves traffic efficiency but also enhances the system's intelligence and adaptability, fully meeting the demands of modern traffic management for efficiency, accuracy, and service quality.

[0087] In one embodiment, please refer to Figure 2 The above-mentioned working method of the self-service card issuing device integrating AI vision and robotic arm control includes steps S110 to S140.

[0088] S110. Select qualified CPC cards by checking their activation status, battery level, and activation status on specific frequency bands, and process unqualified cards.

[0089] In one embodiment, please refer to Figure 3 The above-mentioned step S110 may include steps S111 to S114.

[0090] S111, the mechanism module 50 moves the CPC card to the pre-read area, performs an opening operation on the CPC card, and reads system information.

[0091] S112. Check if the CPC card can be turned on normally, if the power is sufficient, and if the 5.8G band has been activated;

[0092] S113. When the card cannot be turned on or the battery is low, the card recycling process will be initiated. For unusable CPC cards, the unusable CPC cards will be moved from the pre-reading area to the bad card box. If 5.8G has been activated, the lane software will be notified that the card has not been cleared. The lane will decide whether to recycle the card and will execute the corresponding card recycling operation according to the instructions.

[0093] S114. If the CPC card can be turned on normally, has sufficient power, and the 5.8G frequency band is not activated, then the CPC card is determined to be a qualified CPC card.

[0094] S120, the main control module 10 drives the collaborative robot 20 to transfer the qualified CPC card from the core module 50 to the card reading area of ​​the end effector 40, ready to be delivered to the user;

[0095] S130: The AI ​​vision recognition unit 30 is used to determine the position of the driver's side window of the vehicle, providing three-dimensional position information for the robotic arm to hand over the card.

[0096] In one embodiment, please refer to Figure 4 The above-mentioned step S130 may include steps S131 to S133.

[0097] S131. After the inductive loop or radar senses the vehicle, the binocular depth camera collects real-time point cloud data.

[0098] S132. Based on the real-time point cloud data, the YOLOv8 algorithm is used to identify the vehicle window and determine the three-dimensional coordinates of the center point of the driver's side window in the world coordinate system with the binocular camera installation center as the origin.

[0099] S133. Convert the coordinates of the center point of the vehicle window based on the binocular camera coordinate system into new coordinates based on the coordinate system of the robotic arm base to obtain three-dimensional position information.

[0100] S140. Based on the three-dimensional position information provided by the vision system, the main control module 10 drives the collaborative robot 20 to move along the predetermined path, deliver the qualified CPC card to the car owner and confirm the card retrieval status.

[0101] In one embodiment, please refer to Figure 5 The above-mentioned step S140 may include steps S141 to S145.

[0102] S141. Convert the three-dimensional position information into Cartesian space position and formulate the motion trajectory of the collaborative robot 20;

[0103] S142. The main control module 10 controls the movement of the collaborative robot 20 according to a predetermined path until it reaches the designated position.

[0104] S143. Read and write CPC card information in end effector 40;

[0105] S144. After the card is processed, wait for the vehicle owner to pick up the card.

[0106] S145. The reflective sensor monitors whether the card has been taken and feeds the result back to the lane software to control the barrier to lift and allow the vehicle to pass.

[0107] The self-service card issuing device integrating AI vision and robotic arm control operates through a series of steps, from screening qualified CPC cards to delivering them to the user, ensuring the entire process is efficient and accurate. First, in step S110, the CPC card is moved to the pre-reading area via the mechanism module 50 for activation and system information reading (S111). Then, it checks whether the card can be activated normally, whether the battery is sufficient, and whether the 5.8GHz band is activated (S112). For cards that cannot be activated or have low battery, they directly enter the recycling process, moving these cards to the bad card bin; if the 5.8GHz band is activated, the lane software is notified to decide whether the card needs to be recycled (S113). Only cards that can be activated normally, have sufficient battery, and whose 5.8GHz band is not activated are considered qualified cards (S114).

[0108] Next, in step S120, the main control module 10 drives the collaborative robot 20 to transfer the qualified CPC card from the core module 50 to the card reading area of ​​the end effector 40, ready to deliver it to the user. In step S130, after the AI ​​vision recognition unit 30 senses the vehicle through the inductive loop or radar, the binocular depth camera collects real-time point cloud data (S131), and uses the YOLOv8 algorithm to identify the window position based on this data, calculating the three-dimensional coordinates of the center point of the driver's side window (S132). Then, these coordinates are converted from the binocular camera coordinate system to a new coordinate system of the robotic arm base to obtain accurate three-dimensional position information (S133).

[0109] Finally, in step S140, based on the three-dimensional position information provided by the vision system, the main control module 10 drives the collaborative robot 20 to move along a predetermined path to complete the task of delivering the card to the driver. This includes converting the three-dimensional position information into a Cartesian space position to plan the robot's trajectory (S141), precisely controlling the robot's movement along the predetermined path until it reaches the designated position (S142), and reading and writing the CPC card information in the end effector 40 (S143). After the card is processed, it waits for the driver to take the card (S144), and monitors whether the card has been taken by a reflection sensor, feeding the result back to the lane software, which then controls the barrier to raise and allow the vehicle to pass (S145). In this way, through this series of precise operations, effective card management and improved service quality are achieved, meeting the needs of modern traffic management.

[0110] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned self-service card issuing device integrating AI vision and robotic arm control can be referred to the corresponding description in the aforementioned device embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0111] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A self-service card issuing device integrating AI vision and robot control, characterized in that, Comprise: Master module, collaborative robot, AI vision recognition unit, end effector and movement module; The AI vision recognition unit is used for capturing vehicle image data and calculating three-dimensional position information of objects; The master module is used for receiving the three-dimensional position information and generating action control instructions and driving instructions according to the three-dimensional position information, and sending to the collaborative robot; The collaborative robot is used for operating according to the action control instructions, and cooperating with the end effector to complete the tasks of card reading and writing, card preparation, card issuing and bad card recycling; The movement module is used for receiving the driving instructions to generate execution instructions of card reading and writing, card preparation, card issuing and bad card recycling functions; The end effector is used for receiving the execution instructions to cooperate with the collaborative robot to complete the tasks of card reading and writing, card preparation, card issuing and bad card recycling.

2. The integrated Al vision and robotic arm controlled self-service card issuing device according to claim 1, wherein, Also include a human-computer interaction module, the human-computer interaction module is connected with the master module.

3. The integrated Al vision and robotic arm controlled self-service card issuance device of claim 1, wherein, The AI vision recognition unit includes a binocular depth camera, which calculates the three-dimensional position information of objects by simulating the working principle of human eyes, using triangulation and stereo matching algorithm, and provides real-time vehicle point cloud data for vehicle identification.

4. The integrated Al vision and robotic arm controlled self-service card issuing device according to claim 3, wherein, The AI vision recognition unit captures the outline and window position of the vehicle in real time through the binocular depth camera, and identifies the vehicle type, the specific position of the window and the position of the driver by using deep learning algorithm; Based on the camera installation position and angle as the origin of the three-dimensional coordinate system, the accurate three-dimensional coordinates of the center point of the driver's window are calculated, and are converted into Cartesian space coordinates with the robot base as the origin, to determine the target position of the robot end, guided by the master module, to move to the specified spatial position and complete the card delivery operation.

5. The integrated Al vision and robotic arm controlled self-service card issuing device according to claim 1, wherein, The movement module includes a pre-reading and writing device, a card feeding transmission mechanism, a bad card box and a card box; Before the end effector prepares the card, the pre-reading and writing device checks the CPC card to be issued in advance to confirm whether the card can be normally opened, whether the battery capacity is sufficient and whether the 5.8G frequency function is activated, when the card cannot be opened or the capacity does not meet the requirements, the card feeding transmission mechanism will transfer the card to the recycling channel and deliver it to the bad card box; When the 5.8G frequency function of the card has been activated, it reports to the terminal lane software, which decides whether to recycle the card according to the specific situation.

6. The integrated Al vision and robotic arm controlled self-service card issuing device according to claim 5, wherein, The end effector includes a reader, an end card feeding transmission mechanism and a help button, which is installed at the end of the collaborative robot, and communicates with the movement module through Bluetooth.

7. A working method of the integrated AI vision and robotic arm controlled self-service card issuing device according to any one of claims 1 to 6, characterized in that, Comprise: By checking the opening state, capacity and specific frequency activation of the card, qualified CPC cards are screened out, and unqualified cards are processed; The master module drives the collaborative robot to operate, and transfers the qualified CPC cards from the movement module to the card reading area of the end effector, ready to be delivered to the user; The AI vision recognition unit determines the position of the driver's window to provide three-dimensional position information for the card delivery of the robot arm; According to the three-dimensional position information provided by the vision system, the collaborative robot is driven by the master module to move along the predetermined path, deliver the qualified CPC card to the vehicle owner, and confirm the card taking state.

8. The working method of the integrated AI vision and robot control self-service card issuing device according to claim 7, characterized in that, The qualified CPC card is screened out by checking the opening state, power and specific frequency band activation of the card, and unqualified cards are processed, including: The movement of the CPC card to the pre-reading area is controlled by the core module, the opening operation of the CPC card is performed, and the system information is read; Check if the CPC card can be normally opened, if the power is sufficient, and if the 5.8G frequency band has been activated; If it cannot be opened or the power is low, the recycling process is entered, and the CPC card that cannot be used is moved from the pre-reading area to the bad card box, if the 5.8G has been activated, the lane software is notified that the card is not clear, and the lane decides whether it needs to be recycled, and the corresponding card recycling operation is performed according to the instruction; If the CPC card can be normally opened, the power is sufficient, and the 5.8G frequency band is not activated, it is determined that the CPC card is a qualified CPC card.

9. The working method of the integrated AI vision and robotic arm controlled self-service card issuing device according to claim 7, characterized in that, The AI vision recognition unit determines the position of the driver's window of the vehicle to provide three-dimensional position information for the mechanical arm card delivery, including: After the ground inductor or radar senses the vehicle, the binocular depth camera collects real-time point cloud data; Based on the real-time point cloud data, the YOLOv8 algorithm is used to identify the window and determine the three-dimensional coordinates of the driver's window center point in the world coordinate system with the binocular camera installation center as the origin; The window center point coordinates based on the binocular camera coordinate system are converted into new coordinates based on the mechanical arm base coordinate system to obtain three-dimensional position information.

10. The working method of the integrated AI vision and robotic arm controlled self-service card issuing device according to claim 7, characterized in that, According to the three-dimensional position information provided by the vision system, the collaborative robot is driven by the master module to move along the predetermined path, deliver the qualified CPC card to the vehicle owner, and confirm the card taking state, including: Convert the three-dimensional position information into Cartesian space position, and formulate the motion trajectory of the collaborative robot; The movement of the collaborative robot is controlled by the master module according to the predetermined path until the specified position is reached; Read and write the information of the CPC card in the end effector; After the card processing is completed, wait for the vehicle owner to take the card; Through the reflection sensor, monitor whether the card has been taken away, and feed back the result to the lane software to control the lifting rod to release the vehicle.

Images