Vehicle control method and device based on visual guidance, electronic device and computer readable medium

Abstract

The application provides a vehicle control method and device based on visual guidance, an electronic device and a computer readable medium, and belongs to the technical field of vehicle control. The method comprises the following steps: continuously laying a light source array on a preset traffic path, the light source array being divided into a plurality of continuous light-emitting sections; each light-emitting section comprises a first color channel and a second color channel; encoding a task instruction containing a target position identifier into a driving signal, driving the first color channel of all light-emitting sections to emit a light signal corresponding to the driving signal; acquiring image information of a current light-emitting section; decoding the light signal of the second color channel to acquire the position identifier of the current light-emitting section, and decoding the light signal of the first color channel to acquire the target position identifier; comparing the target position identifier with the position identifier of the current light-emitting section, and if they are inconsistent, controlling the vehicle to travel along the light source array until the position identifier of the current light-emitting section is consistent with the target position identifier. The application improves the robustness of vehicle navigation.

Description

Technical Field

[0001] This application belongs to the technical field of vehicle control, and particularly relates to a vision-guided vehicle control method and device, electronic device and computer-readable medium. Background Technology

[0002] Automated Guided Vehicles (AGVs) are used in warehousing, manufacturing, chemical, and other fields. The automated operation of AGVs relies on command transmission and positioning / navigation technologies. Traditional AGV systems typically use wired network communication (such as conductor rails or cable chains) or wireless communication (such as Wi-Fi, Bluetooth, Zigbee, and ultra-wideband) to achieve data exchange between the central dispatch system and the AGVs.

[0003] However, the inventors of this application have discovered that while wired communication methods offer high reliability and anti-interference capabilities, their complex wiring, high maintenance costs, and limitations on the flexibility of AGV travel paths make them difficult to adapt to dynamically changing work scenarios. Therefore, modern AGV systems increasingly employ wireless communication technology. However, in industrial environments with potential explosive risks such as flammable gases, vapors, dust, or fibers (e.g., petrochemical production workshops, chemical production workshops, oil and gas storage areas, coal mine tunnels, metal grinding workshops, grain processing workshops, painting workshops, and military ammunition production lines), wireless communication technology faces the following prominent problems: First, there are safety risks. Wireless communication relies on electromagnetic waves to transmit signals. During propagation, electromagnetic waves may generate electrical sparks or induced currents, posing a risk of ignition and explosion in flammable and explosive environments, thus failing to meet the requirements of explosion-proof safety standards.

[0004] Second, information security risks. Wireless signals are open and easily eavesdropped on, intercepted, or interfered with by external devices, leading to the leakage of mission instructions or attacks on the control system, which fails to meet the requirements of industrial information security and confidentiality.

[0005] Third, poor environmental adaptability. Industrial sites contain numerous sources of strong electromagnetic interference, such as motors and frequency converters, which can easily interfere with wireless communication signals, leading to unstable communication, lost or delayed commands, and affecting the operational reliability of AGVs.

[0006] The content of the background section is merely the technology known to the inventor and does not necessarily represent the prior art in this field. Summary of the Invention

[0007] This application aims to provide a vision-guided vehicle control method and apparatus, electronic device, and computer-readable medium to solve at least one of the above-mentioned technical problems.

[0008] According to one aspect of this application, a vision-guided vehicle control method is provided. The vehicle operates along a preset travel path. The vehicle control method includes: continuously laying a light source array along the preset travel path, the light source array being divided into multiple continuous light-emitting segments along the preset travel path; wherein each light-emitting segment includes at least a first color channel and a second color channel; encoding a task instruction containing a target location identifier into a drive signal according to a preset encoding rule, and driving the first color channel of all light-emitting segments to emit light signals corresponding to the drive signal according to the drive signal; acquiring image information of the current light-emitting segment where the vehicle is located; decoding the light signal of the second color channel in the image information to acquire the location identifier of the current light-emitting segment, and decoding the light signal of the first color channel in the image information to acquire the target location identifier; comparing the target location identifier with the location identifier of the current light-emitting segment, and if they are inconsistent, controlling the vehicle to travel along the light source array until the location identifier of the current light-emitting segment matches the target location identifier.

[0009] According to some embodiments of this application, a task instruction containing a target location identifier is encoded into a drive signal according to a preset encoding rule, and the first color channel of all light-emitting segments is driven to emit a light signal corresponding to the drive signal according to the drive signal. This includes: converting the task instruction into a binary sequence according to a brightness binarization encoding rule; converting the binary sequence into a PWM drive signal and sending it to the first color channel of all light-emitting segments, so that the first color channel of all light-emitting segments emits a light signal corresponding to the binary sequence.

[0010] According to some embodiments of this application, decoding the light signal of the second color channel in image information to obtain the position identifier of the current emitting segment, and decoding the light signal of the first color channel in image information to obtain the target position identifier, includes: performing color segmentation on the acquired image information to extract the image region corresponding to the first color channel and the image region corresponding to the second color channel; decoding the light signal in the image region corresponding to the second color channel to obtain the position identifier of the current emitting segment; and decoding the light signal in the image region corresponding to the first color channel to obtain the target position identifier.

[0011] According to some embodiments of this application, color segmentation is performed on the acquired image information to extract the image region corresponding to the first color channel and the image region corresponding to the second color channel, including: converting the acquired image into the HSV color space; generating a color mask according to a preset HSV range; and separating the image region corresponding to the first color channel and the image region corresponding to the second color channel according to the color mask.

[0012] According to some embodiments of this application, the task instruction also includes motion parameters, and the vehicle control method further includes: decoding the light signal of the first color channel in the image information to obtain the motion parameters.

[0013] According to some embodiments of this application, controlling a vehicle to travel along a light source array until the position marker of the current light-emitting segment matches the target position marker includes: determining the vehicle's driving direction based on the relative positional relationship between the current light-emitting segment's position marker and the target position marker; and controlling the vehicle to travel along the light source array according to motion parameters and driving direction until the position marker of the current light-emitting segment matches the target position marker.

[0014] According to some embodiments of this application, each light-emitting segment further includes a third color channel, and the vehicle control method further includes: decoding the light signal of the third color channel in the image information to obtain verification information; and verifying the integrity of the target location identifier and / or the location identifier of the current light-emitting segment according to the verification information.

[0015] According to another aspect of this application, a vision-guided vehicle control device is also provided, including a light source array, a controller, an image acquisition module, an image decoding module, and a navigation control module. The light source array is continuously laid along a preset travel path and divided into multiple continuous light-emitting segments along the preset travel path; wherein each light-emitting segment includes at least a first color channel and a second color channel; the controller is connected to the light source array and is used to encode a task instruction containing a target location identifier into a drive signal according to a preset encoding rule, and drive the first color channel of all light-emitting segments to emit light signals corresponding to the drive signal according to the drive signal; the image acquisition module is disposed on the vehicle and is used to acquire image information of the current light-emitting segment where the vehicle is located; the image decoding module is disposed on the vehicle and connected to the image acquisition module and is used to decode the light signal of the second color channel in the image information to obtain the location identifier of the current light-emitting segment, and to decode the light signal of the first color channel in the image information to obtain the target location identifier; the navigation control module is disposed on the vehicle and connected to the image decoding module and is used to compare the target location identifier with the location identifier of the current light-emitting segment; if they are inconsistent, the vehicle is controlled to travel along the light source array until the location identifier of the current light-emitting segment matches the target location identifier.

[0016] According to another aspect of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the vehicle control methods described above.

[0017] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided, the program code causing the processor to perform any of the vehicle control methods described above.

[0018] According to another aspect of this application, a computer program product is also provided, including a computer program stored on a computer-readable medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform any of the vehicle control methods described above.

[0019] The beneficial effects of the technical solutions provided in this application are: This application utilizes a light source array with first and second color channels, continuously laid along a preset travel path. It drives all emitting segments to synchronously encode the first color channel with a task command light signal indicating the target location. Simultaneously, it acquires images of the current emitting segment, decodes the second color channel to obtain the current location identifier, and decodes the first color channel to obtain the target location identifier. By comparing these two, it autonomously controls the journey until the target is reached. The specific effects of this technical solution are: this solution uses visible light communication instead of traditional radio electromagnetic wave communication, physically eliminating electromagnetic radiation and the risk of ignition and explosion; this solution utilizes light... The signal cannot penetrate the workshop walls, possessing physical isolation characteristics to prevent external eavesdropping and hacker attacks, ensuring industrial information security and confidentiality; this solution does not rely on easily interfered wireless frequency bands such as Wi-Fi and Bluetooth, and can still work stably in industrial environments with strong electromagnetic interference such as large motors and frequency converters; this solution determines the vehicle's driving direction and stopping time by comparing the current position with the target position, reducing system communication load and the risk of single point of failure; the light source array (such as LED light strips) and vehicle-mounted camera in this solution are inexpensive, easy to deploy, and the light signal is visible to the human eye, facilitating on-site maintenance personnel's inspection and troubleshooting. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a vision-guided vehicle control method according to an embodiment of this application is shown. Figure 2 A flowchart illustrating step S200 of the vision-guided vehicle control method according to an embodiment of this application is shown. Figure 3 A flowchart illustrating step S400 of the vision-guided vehicle control method according to an embodiment of this application is shown. Figure 4 A flowchart illustrating step S410 of the vision-guided vehicle control method according to an embodiment of this application is shown. Figure 5 A flowchart illustrating step S500 of the vision-guided vehicle control method according to an embodiment of this application is shown. Figure 6 This illustration shows another schematic flowchart of the vision-guided vehicle control method according to an embodiment of this application; Figure 7 A schematic diagram of the structure of a vision-guided vehicle control device according to an embodiment of this application is shown.

[0022] Explanation of reference numerals in the attached figures: Vehicle control device 1; light source array 11; controller 12; image acquisition module 13; image decoding module 14; navigation control module 15. Detailed Implementation

[0023] The present application will now be described in detail with reference to the accompanying drawings and embodiments. Various examples are provided by way of interpretation and not by way of limitation. In fact, those skilled in the art will recognize that modifications and variations can be made to the present application without departing from the scope or spirit thereof. For example, a feature represented or described as part of one embodiment may be used in another embodiment to produce yet another embodiment. Therefore, it is desirable that the present application encompass such modifications and variations that fall within the scope of the appended claims and their equivalents.

[0024] The accompanying drawings illustrate one or more examples of this application. The detailed description uses numerical and alphabetic designations to refer to features in the drawings. Similar or analogous designations in the drawings and description have been used to refer to similar or analogous parts of this application. As used herein, the terms “first,” “second,” “third,” and “fourth,” etc., are used interchangeably to distinguish one component from another and are not intended to indicate the location or importance of a single component.

[0025] The accompanying drawings in the following embodiments clearly and completely describe the technical solutions of this application. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] The technical solution of this application is applied to the field of vehicle control technology, operating in industrial locations with potential explosive risks such as flammable gases, vapors, dust, or fibers, such as petrochemical production workshops, chemical production workshops, oil and gas storage areas, coal mine tunnels, metal grinding workshops, grain processing workshops, painting workshops, and military ammunition production lines. In these explosive locations, the traditional wireless communication methods (such as Wi-Fi, Bluetooth, Zigbee, etc.) used by Automated Guided Vehicles (AGVs) rely on electromagnetic wave transmission, posing a safety risk of ignition and explosion, and the wireless signals are easily eavesdropped or interfered with. The technical solution of this application proposes a vision-guided vehicle control method, which uses a light source array (such as LED light strips) laid on a preset travel path to transmit coded instructions through visible light. The vehicle control device collects and decodes the light signals in real time through an onboard camera to realize the navigation, positioning, and task execution of the AGV. This method does not generate electromagnetic radiation, thus eliminating the risk of ignition at the physical level. It also has advantages such as resistance to electromagnetic interference, anti-eavesdropping, low cost, and easy deployment, making it particularly suitable for flammable and explosive environments with high requirements for safety and confidentiality.

[0027] Figure 1 A schematic flowchart of a vision-guided vehicle control method according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 1 As shown, the vehicle control method includes steps S100-S500. Exemplarily, the vehicle control method of this application can be executed in a computer system such as a set of executable instructions. Exemplarily, the computer system is a vehicle control device. Furthermore, although a logical sequence is shown in the flowchart, under default conditions, the steps shown or described may be executed in a different order than that shown in the flowchart.

[0028] In step S100, a light source array is continuously laid on a preset passage path, and the light source array is divided into multiple continuous light-emitting segments along the preset passage path.

[0029] According to the example embodiment, each light-emitting segment includes at least a first color channel and a second color channel. Exemplarily, the first color channel can be used to carry task instructions, and the second color channel can be used to carry the location identifier of the light-emitting segment. Exemplarily, the light source array consists of multiple sets of LED light strips, each set of LED light strips constituting a light-emitting segment, and each set of LED light strips is composed of multiple LED beads arranged together. Exemplarily, each LED bead corresponds to one color channel. The light source array is connected to the vehicle control device via wired communication. The vehicle is the aforementioned AGV. The preset travel path is the predetermined travel route of the AGV within the aforementioned flammable and explosive location, set by the user according to the actual site layout, and is not limited here. Each light-emitting segment has a unique location identifier (ID, Identifier), which uniquely identifies the position of the corresponding light-emitting segment on the preset travel path. For example, the light-emitting segments can be sequentially numbered along the preset travel path as ID=1, 2, 3, ..., N, with each ID corresponding to a physical coordinate.

[0030] For example, physical coordinates are coordinate values ​​in a two-dimensional coordinate system (i.e., a map coordinate system) established within a flammable and explosive location. This map coordinate system uses a fixed point within the flammable and explosive location (such as a workshop entrance, pillar, or equipment reference point) as its origin (0,0), and the direction of a preset travel path as the positive X-axis or Y-axis, with units in millimeters (mm). For instance, ID=5 corresponds to coordinates (X=3500mm, Y=1200mm) in the map coordinate system, indicating that the luminous segment is located 3500 mm from the origin in the X direction and 1200 mm in the Y direction. This map coordinate system and coordinate mapping relationship are pre-stored in the vehicle control device. The vehicle control device can obtain the physical coordinates of the AGV within the flammable and explosive location by reading the ID of the luminous segment where the AGV is located and looking up the table.

[0031] In step S200, the task instruction containing the target location identifier is encoded into a drive signal according to a preset encoding rule, and the first color channel of all light-emitting segments is driven to emit light signals corresponding to the drive signal according to the drive signal.

[0032] According to the example embodiment, the preset encoding rule refers to the agreed method of converting task instructions (such as target location identifiers, motion parameters, etc.) into intermediate representations or driving signals that can control the light source to emit preset types of light signals.

[0033] For example, the preset encoding rules include: I. Color Coding Rules: Used to distinguish information types. For example, the first color channel (green) carries task instructions, the second color channel (red) carries location identifiers, and the third color channel (blue) carries verification information.

[0034] II. Numerical Encoding Rules: Used to convert information into light signals within color channels. Numerical encoding rules include, but are not limited to, one or more of the following: 1. Brightness Binarization Encoding Rule: Time is divided into equal-length preset time periods (called time slices). Within each time slice, the LED maintains a specific brightness state, and one binary bit is transmitted per time slice. High brightness of the LED represents binary "1", while low brightness or being off represents binary "0". The transmitting end outputs a brightness sequence according to the time slices, and the receiving end reconstructs the binary data by detecting brightness changes.

[0035] 2. Pulse Counting Encoding Rule: Within a preset time window, the numerical value is represented by the number of LED flashes. The receiving end obtains the corresponding value by counting the number of flashes, which is typically used to transmit slowly changing identification information (such as location ID). 3. PWM Duty Cycle Encoding Rules: Within a modulation cycle, different values ​​are represented by the proportion of the LED's illumination time to the total cycle time (duty cycle). The duty cycle can be divided into multiple levels (such as 0%, 25%, 50%, 75%, 100%), each level corresponding to a symbol or value.

[0036] According to the example embodiment, the vehicle control device is connected to all light-emitting segments via wired communication. The vehicle control device converts the task command containing the target location identifier (e.g., "target location ID=5") to be issued into a drive signal according to a preset encoding rule, and then synchronously drives the first color channel of all light-emitting segments via wired communication, so that the first color channel of all light-emitting segments emits the same light signal at the same time, thereby realizing the broadcast issuance of the task command.

[0037] For example, the target location identifier refers to the location identifier of the target illuminated segment that the AGV needs to reach, as specified by the vehicle control device. For instance, the vehicle control device can specify target location ID=5, indicating that the AGV needs to travel to the illuminated segment location corresponding to ID=5. The task instruction can also include motion parameters, such as direction of movement (forward / backward), speed level (low / medium / high speed), and steering instructions (straight / turn).

[0038] In step S300, image information of the current luminous segment where the vehicle is located is obtained.

[0039] According to an example embodiment, the vehicle control device includes an image acquisition module. Exemplarily, the image acquisition module can be an image acquisition device (e.g., a camera) installed at the bottom of the AGV. The image acquisition device captures an image in real time of the AGV's current location within the light-emitting segment. Since the AGV travels along the light source array, the image acquisition device is always aligned with the light source array laid on the ground; therefore, the acquired image contains light source information (i.e., light signal) of the light-emitting segment where the vehicle is currently located.

[0040] For example, the distance between the image acquisition device and the light source array remains constant (e.g., 50-200mm), and the acquisition frame rate of the image acquisition device is not less than 30fps to capture changes in the light signal of the light source array in real time.

[0041] In step S400, the light signal of the second color channel in the image information is decoded to obtain the position identifier of the current light-emitting segment, and the light signal of the first color channel in the image information is decoded to obtain the target position identifier.

[0042] According to the example embodiment, the vehicle control device performs real-time decoding processing on the acquired images. The optical signal of the second color channel encodes the position identifier of the current emitting segment, and the optical signal of the first color channel encodes the task instructions (including the target position identifier) ​​broadcast by the vehicle control device.

[0043] For example, assuming the AGV is located in the light-emitting segment with ID=8, the second color channel (e.g., a red LED) emits a light signal indicating "ID=8"; the first color channel (e.g., a green LED) emits a task instruction broadcast by the vehicle control device, which includes "target position ID=5". The vehicle control device obtains the current position identifier (i.e., ID=8) of the light-emitting segment by decoding the light signal of the second color channel in the image information, and obtains the target position identifier (i.e., ID=5) by decoding the light signal of the first color channel in the image information.

[0044] In step S500, the target position identifier is compared with the position identifier of the current light-emitting segment. If they are inconsistent, the vehicle is controlled to move along the light source array until the position identifier of the current light-emitting segment matches the target position identifier.

[0045] According to the example embodiment, the vehicle control device compares the decoded target position identifier with the position identifier of the current luminous segment. If they match, it indicates that the AGV has reached the target position, triggering a stop at the target position; if they do not match, the AGV is controlled to continue traveling along the light source array, and steps S300 to S500 are repeated during the travel process to update the position identifier of the current luminous segment in real time and compare it with the target position identifier until the position identifier of the current luminous segment matches the target position identifier.

[0046] For example, when the vehicle is at ID=8 and the target position is ID=5, since 8≠5, the vehicle control device controls the vehicle to travel along the light source array in the direction of decreasing ID, passing ID=7 and ID=6 in sequence. When it reaches ID=5, the current position identifier matches the target position identifier, and the vehicle stops. Conversely, when the vehicle is at ID=3 and the target position is ID=5, it travels in the direction of increasing ID.

[0047] Through the above embodiments, this application, by continuously laying out light source arrays with first and second color channels along a preset travel path, and driving all light-emitting segments to synchronously encode the first color channel with a task command light signal indicating the target location, simultaneously utilizes the acquisition of the current light-emitting segment image, decodes the second color channel to obtain the current location identifier, and decodes the first color channel to obtain the target location identifier. Furthermore, by comparing the two, the application autonomously controls its movement until it reaches the target. The specific effects of this application's technical solution are: this solution uses visible light communication instead of traditional radio electromagnetic wave communication, physically eliminating electromagnetic radiation and the risk of ignition and explosion; this solution... The light signals used cannot penetrate workshop walls, providing physical isolation and preventing external eavesdropping and hacker attacks, thus ensuring industrial information security and confidentiality. This solution does not rely on easily interfered wireless frequency bands such as Wi-Fi and Bluetooth, and can still work stably in industrial environments with strong electromagnetic interference such as large motors and frequency converters. This solution determines the vehicle's driving direction and stopping time by comparing the current position with the target position, reducing system communication load and the risk of single point of failure. The light source array (such as LED light strips) and vehicle-mounted camera in this solution are inexpensive, easy to deploy, and the light signals are visible to the human eye, facilitating on-site maintenance personnel's inspection and troubleshooting.

[0048] Figure 2 A flowchart illustrating step S200 of a vision-guided vehicle control method according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 2 As shown, step S200 includes steps S210-S220.

[0049] In step S210, the task instruction is converted into a binary sequence according to the brightness binarization encoding rule.

[0050] For example, the task instruction includes: target position ID=5, and motion parameters "forward + straight + medium speed". This task instruction is encoded into a binary sequence according to a preset bit mapping table, such as an 8-bit binary sequence "01011010", where the high 4 bits "0101" represent target position ID=5, and the low 4 bits "1010" represent the motion parameters (1=forward, 0=straight, 10=medium speed). For example, the motion parameters 'forward + straight + medium speed + no load' can be encoded as a 5-bit binary sequence "10100" (1=forward, 0=straight, 10=medium speed, 0=no load).

[0051] The vehicle control device controls the brightness change of the first color channel according to the binary sequence: the LED is controlled to be bright during the time slice corresponding to binary "1", and the LED is controlled to be dim (or off) during the time slice corresponding to binary "0".

[0052] In step S220, the binary sequence is converted into a PWM drive signal and sent to the first color channel of all light-emitting segments so that the first color channel of all light-emitting segments emits a light signal corresponding to the binary sequence.

[0053] According to the example embodiment, a PWM (Pulse Width Modulation) drive signal is an electrical signal that controls the brightness of an LED by adjusting the pulse duty cycle. The vehicle control unit converts the binary sequence into a corresponding PWM waveform (e.g., a high level corresponds to the LED being lit, and a low level corresponds to the LED being turned off), and then sends the same PWM drive signal synchronously to the first color channel of all light-emitting segments.

[0054] For example, for the binary sequence "1010", the vehicle control unit generates a PWM waveform: the first time slot is high (LED bright), the second time slot is low (LED low), the third time slot is high, and the fourth time slot is low. This PWM signal is simultaneously sent to the first color channel of all light-emitting segments, causing all first color channels to emit light signals simultaneously in a "high-low-high-low" pattern. In this way, regardless of which light-emitting segment the vehicle is currently in, it can receive the same task instructions.

[0055] Through the above embodiments, this application realizes the brightness binarization encoding of task instructions and the synchronous broadcasting of all light-emitting segments, ensuring that the vehicle can receive the task instructions issued by the vehicle control device at all locations of the preset passage section, and the encoding method is simple, reliable and easy to identify.

[0056] Figure 3 A flowchart illustrating step S400 of a vision-guided vehicle control method according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 3 As shown, step S400 includes steps S410-S430.

[0057] In step S410, the acquired image information is segmented by color to extract the image region corresponding to the first color channel and the image region corresponding to the second color channel.

[0058] According to the example embodiment, color segmentation refers to an image processing operation that separates regions of different colors based on the color values ​​of pixels in an image. Since the first color channel and the second color channel use different colors (e.g., green and red), green and red regions can be extracted separately through color segmentation.

[0059] For example, the image acquired by the vehicle control device is in RGB format. During color segmentation, the acquired image is converted from the BGR color space to the HSV color space. For the first color channel (green), the preset HSV range can be: H (hue) channel value between 35° and 85°, S (saturation) channel value greater than 50, and V (lightness) channel value greater than 100. For the second color channel (red), since red is distributed in two intervals in the HSV space, the preset HSV range can be: H channel value between 0° and 10° or 160° and 180°, S channel value greater than 50, and V channel value greater than 100. A color mask is generated based on the above HSV ranges to separate the green and red regions. Then, the pixel regions belonging to the first color channel (green) and the second color channel (red) can be extracted from the image to obtain two independent image regions.

[0060] In step S420, the light signal in the image area corresponding to the second color channel is decoded to obtain the position identifier of the current light-emitting segment.

[0061] According to the example embodiment, the position identifier of the current emitting segment is encoded in the light signal of the second color channel. During decoding, the vehicle control device identifies the value of the position identifier according to preset encoding rules (such as pulse counting method, PWM duty cycle method, etc.).

[0062] For example, suppose the second color channel (red LED) uses pulse counting to encode the location identifier: 5 LED flashes represent ID=5. The vehicle analyzes the brightness change sequence in the extracted red image area within the ID encoding cycle, counts the LED flashes as 5, and thus decodes the current luminous segment's location identifier as ID=5. This ID corresponds to precise coordinates in the map coordinate system (e.g., X=3500mm, Y=1200mm). For example, each ID encoding cycle contains a fixed time window (e.g., 1 second), and the number of LED flashes within the window is the ID value. A fixed-length silence interval (e.g., 500ms when all LEDs are off) is inserted between windows as a frame synchronization signal to identify the start and end of each ID encoding cycle.

[0063] In step S430, the light signal in the image area corresponding to the first color channel is decoded to obtain the target location identifier.

[0064] According to the example embodiment, the optical signal in the first color channel encodes a task instruction broadcast by the vehicle control device, which includes a target location identifier. During decoding, the binary sequence is recovered from the brightness change sequence according to the decoding rules corresponding to the encoding rules, and then the target location identifier is parsed out.

[0065] For example, continuing the example of step S210, the first color channel (green LED) emits an 8-bit light signal sequence according to the brightness binarization encoding rule, corresponding to binary "0101 1010". The vehicle obtains the binary sequence "0101 1010" by analyzing the brightness changes in the extracted green image area, and then decodes the target position identifier as ID=5 according to the preset instruction mapping table, where the high 4 bits "0101" are interpreted as target position ID=5 (the low 4 bits "1010" are interpreted as motion parameters for subsequent control).

[0066] Through the above embodiments, this application converts the image to HSV space in step S410 and generates a color mask using a preset HSV threshold. This accurately separates the image regions corresponding to the first and second color channels, avoiding the impact of illumination changes on color recognition and improving the robustness and accuracy of color segmentation. Based on this, step S420 decodes the light signal of the second color channel using pulse counting, obtaining the current luminous segment's position identifier (ID) by counting the number of flashes. Step S430 decodes the light signal of the first color channel using luminance binarization, recovering the task command from the luminance sequence and extracting the target position identifier (ID). These three steps collaboratively achieve independent and parallel decoding of dual-channel information, enabling the vehicle to simultaneously know its real-time position and the target position without wireless communication, thus improving the robustness of vehicle navigation in flammable and explosive environments.

[0067] Figure 4 A flowchart illustrating step S410 of a vision-guided vehicle control method according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 4 As shown, step S410 includes steps S411-S412.

[0068] In step S411, the acquired image is converted to the HSV color space.

[0069] According to the example implementation, the HSV color space is a color model that represents color using three components: hue, saturation, and value. Compared to the RGB color space, the HSV space is closer to human color perception, and color recognition is less affected by light intensity, making it more suitable for color segmentation.

[0070] For example, the image acquired by the vehicle control system is in BGR format (similar to RGB, but with a different channel order). First, the image is denoised using Gaussian filtering. Then, the denoised image is converted from the BGR color space to the HSV color space. After conversion, each pixel of the image is represented by three components (H, S, V), where the H component represents the color type (e.g., red, green, blue), the S component represents the color purity, and the V component represents the color brightness.

[0071] In step S412, a color mask is generated according to a preset HSV range, and the image region corresponding to the first color channel and the image region corresponding to the second color channel are separated according to the color mask.

[0072] According to the example embodiment, a color mask is a binary image, where a pixel value of 1 indicates that the pixel belongs to the target color range, and a pixel value of 0 indicates that it does not belong to the target color range. By setting the HSV threshold range corresponding to each color, a mask for a preset color can be generated.

[0073] For example, for a red LED (second color channel), the preset HSV range can be: H channel 0-10 and 160-180 (red is distributed in two intervals in the HSV space), S channel greater than a certain threshold (e.g., 50), and V channel greater than a certain threshold (e.g., 100). For a green LED (first color channel), the preset HSV range can be: H channel 35-85, S channel greater than 50, and V channel greater than 100. For a blue LED (third color channel), the preset HSV range can be: H channel 90-130, S channel greater than 50, and V channel greater than 100. Based on these preset ranges, red, green, and blue masks are generated respectively. Then, morphological closing operations (dilation followed by erosion) are performed on the masks to optimize their connectivity. The region defined by the extracted mask contour is the image region corresponding to the color channel. The image regions corresponding to the first and second color channels are separated in the above manner.

[0074] Through the above embodiments, this application achieves accurate color segmentation based on the HSV color space, which can effectively distinguish between red, green and blue light sources, overcome the influence of illumination changes on color recognition, and improve the robustness of decoding.

[0075] According to the example embodiment, the task instruction also includes motion parameters, and the vehicle control method further includes step S600.

[0076] In step S600, the light signal of the first color channel in the image information is decoded to obtain motion parameters.

[0077] According to the example embodiment, motion parameters refer to parameters that control the vehicle's driving state, including but not limited to motion direction (forward / backward), steering state (straight / turning), speed level (low / medium / high speed), and load state (unloaded / heavy load). These parameters, along with the target location identifier, are encoded in the optical signal of the first color channel.

[0078] For example, continuing the encoding example of step S210, assume that the lower 4 bits of the binary sequence emitted by the first color channel (green LED) are "1010". The meaning of each bit in this sequence is preset as follows: the 1st bit represents the direction of movement (1=forward, 0=backward), the 2nd bit represents the direction of turn (1=turn, 0=straight), and the 3rd-4th bits represent the speed level (00=low speed, 01=medium speed, 10=high speed, 11=maximum speed). Then "1010" is decoded as: direction of movement = forward, direction of turn = straight, speed level = high speed. For more complex instructions such as "1101", it can be decoded as: direction of movement = forward, direction of turn = turn, speed level = medium speed (01 corresponds to medium speed).

[0079] Through the above embodiments, this application realizes the encoding and downlink of motion parameters, enabling the vehicle control device to remotely control the vehicle's driving status and achieve centralized vehicle scheduling.

[0080] Figure 5 A flowchart illustrating step S500 of a vision-guided vehicle control method according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 5 As shown, step S500 includes steps S510-S520.

[0081] In step S510, the driving direction of the vehicle is determined based on the relative positional relationship between the current position marker of the luminous segment and the target position marker.

[0082] According to the example embodiment, the relative positional relationship refers to the numerical relationship between the current position marker of the light-emitting segment and the target position marker. Since the light-emitting segments of the light source array are arranged sequentially along the travel path (e.g., ID=1, 2, 3, ..., N), the travel direction can be determined by comparing the numerical values ​​of the two markers.

[0083] For example, if the current position identifier of the illuminated segment (e.g., ID=8) is greater than the target position identifier (e.g., ID=5), the vehicle needs to travel in the direction where ID decreases (i.e., the reverse direction). If the current position identifier of the illuminated segment (e.g., ID=3) is less than the target position identifier (e.g., ID=5), the vehicle needs to travel in the direction where ID increases (i.e., the forward direction). If the two are equal, the vehicle has reached the target position and does not need to travel further.

[0084] In step S520, the vehicle is controlled to travel along the light source array according to the motion parameters and the direction of travel until the position mark of the current light-emitting segment matches the target position mark.

[0085] According to the example embodiment, the vehicle control device combines the driving direction determined in step S510 with the motion parameters (such as speed level) obtained in step S600 to control the vehicle's drive system to travel along the light source array. During driving, the vehicle continuously executes steps S300-S500, updating the position identifier of the current light-emitting segment in real time and comparing it with the target position identifier until the two match, triggering a stop.

[0086] For example, suppose the vehicle is currently at ID=8, the target position is ID=5, and the motion parameter is "high speed". The vehicle determines its direction of travel as "towards the direction of decreasing ID" and controls itself to travel backward at high speed. When it passes ID=7, it reads that the current ID=7 is inconsistent with the target ID=5, and continues to travel; when it passes ID=6, it reads that the current ID=6 is inconsistent with the target ID=5, and continues to travel; when it reaches ID=5, it reads that the current ID=5 is consistent with the target ID=5, and triggers a stop at the target position. Optionally, a position detection condition can also be set: a stop is triggered only when a stable second color channel light signal is continuously received for more than a preset time threshold (e.g., 200ms) to improve position accuracy.

[0087] In a specific application example, the AGV receives a task instruction coded as "0101 10100" (target ID=5, motion parameters=forward + straight + medium speed + no load), where the medium speed is 0.8 m / s. The AGV travels along the light source array at a speed of 0.8 m / s. When the AGV reaches directly below the light-emitting segment with ID=5 and continuously detects a stable red light signal for 200 ms, it triggers a stop.

[0088] Through the above embodiments, this application realizes vehicle navigation and stopping at the destination based on location comparison. The vehicle does not need the vehicle control device to guide the path in real time, which reduces communication dependence and improves the security and reliability of the system.

[0089] Figure 6 This illustration shows another schematic flowchart of a vision-guided vehicle control method according to an embodiment of this application. According to an example embodiment, such as... Figure 6 As shown, the vehicle control method also includes steps S700-S800.

[0090] In step S700, the light signal of the third color channel in the image information is decoded to obtain the verification information.

[0091] According to the example embodiment, each light-emitting segment may further include a third color channel (e.g., a blue LED), which is used to carry verification information. The verification information is used to verify the integrity of the data transmitted by the first and second color channels, preventing data errors caused by site interference, equipment failure, or other reasons.

[0092] For example, after the vehicle control device sends the task instruction through the first color channel, it sends a preset verification signal through the third color channel, such as a blue LED flashing in a preset pattern (e.g., flashing three times consecutively). The vehicle camera captures and decodes the light signal from the third color channel to obtain the verification information (e.g., the number of flashes, 3 times).

[0093] In step S800, the integrity of the target location identifier and / or the location identifier of the current light-emitting segment is verified according to the verification information.

[0094] According to the example embodiment, the vehicle compares the decoded verification information with the preset verification rules to determine whether the received target location identifier and / or the location identifier of the current luminous segment is complete and correct.

[0095] For example, in a loading and unloading scenario, the vehicle control device sends a task instruction via the first color channel (red ID=12 identifies the assembly station, green PWM=1101 encodes the loading and unloading instruction), and then flashes the third color channel (blue LED) three times as a data integrity confirmation signal. After receiving the task instruction, if the vehicle detects the blue LED flashing three times within a preset time (e.g., 10 seconds), it confirms the received instruction is complete and valid, and continues the loading and unloading actions (e.g., raising the forks to a height of 150mm, locking the cargo with the grippers, etc.). If no valid verification signal is detected within the preset time, a fault handling mechanism is triggered, such as illuminating a yellow fault light and initiating an automatic retransmission request to notify the vehicle control device to rebroadcast the task instruction.

[0096] Through the above embodiments, this application introduces a third color channel for data verification, which effectively improves the reliability of communication and prevents misoperation caused by data errors. It is especially suitable for industrial sites with high security requirements.

[0097] According to the example embodiment, when the vehicle's safety lidar detects an obstacle within a preset distance ahead, the vehicle control device enters an emergency coding mode. Exemplarily, the emergency coding mode specifically involves controlling the vehicle's warning lights to flash red and blue alternately at a frequency of 10Hz and a duty cycle of 50%, while simultaneously turning off the vehicle's white lighting to enhance visual cues. After recognizing this emergency coding mode, the vehicle executes the following three-level response: Level 1, electric braking (0-100ms), cutting off the drive motor power supply, converting kinetic energy into heat from the braking resistor; Level 2, mechanical braking (100-500ms), locking the drive wheels with a spring-loaded brake; Level 3, audible and visual alarm (greater than 500ms), triggering a 105dB buzzer and 360° red warning lights.

[0098] Figure 7 A schematic diagram of a vision-guided vehicle control device according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 7As shown, the vehicle control device 1 includes a light source array 11, a controller 12, an image acquisition module 13, an image decoding module 14, and a navigation control module 15.

[0099] The light source array 11 is continuously laid on a preset passage path and is divided into multiple continuous light-emitting segments along the preset passage path; wherein each light-emitting segment includes at least a first color channel and a second color channel.

[0100] The controller 12 is connected to the light source array 11 and is used to encode the task instruction containing the target position identifier into a drive signal according to the preset encoding rules, and drive the first color channel of all light-emitting segments to emit light signals corresponding to the drive signal according to the drive signal.

[0101] For example, the preset encoding rules have been described in detail in step S200 and will not be repeated here. For example, the controller 12 is connected to all light-emitting segments via wired communication. The controller 12 converts the task instruction containing the target location identifier (e.g., "target location ID=5") to be issued into a drive signal according to the preset encoding rules, and then synchronously drives the first color channel of all light-emitting segments via wired communication, so that the first color channel of all light-emitting segments emits the same light signal at the same time, thereby realizing the broadcast issuance of the task instruction.

[0102] For example, the target location identifier refers to the location identifier of the target illuminated segment that the AGV needs to reach, as specified by the vehicle control device 1. For instance, the vehicle control device 1 can specify target location ID=5, indicating that the AGV needs to travel to the illuminated segment location corresponding to ID=5. The task instruction can also include motion parameters, such as direction of movement (forward / backward), speed level (low / medium / high speed), and steering instructions (straight / turning).

[0103] An image acquisition module 13 is mounted on the vehicle and is used to acquire image information of the current light-emitting segment in which the vehicle is located. Exemplarily, the image acquisition module 13 can be an image acquisition device (e.g., a camera) mounted at the bottom of the AGV. The image acquisition device captures images of the light-emitting segment in which the AGV is currently located in real time. Since the AGV travels along the light source array 11, the image acquisition module 13 is always aligned with the light source array 11 laid on the ground; therefore, the acquired image contains the light source information (i.e., light signal) of the light-emitting segment in which the vehicle is currently located. Exemplarily, the distance between the image acquisition module 13 and the light source array 11 remains constant (e.g., 50-200 mm), and the image acquisition device has a frame rate of not less than 30 fps to capture changes in the light signal of the light source array 11 in real time.

[0104] The image decoding module 14 is installed on the vehicle and connected to the image acquisition module 13. It is used to decode the light signal of the second color channel in the image information to obtain the position identifier of the current light-emitting segment, and to decode the light signal of the first color channel in the image information to obtain the target position identifier.

[0105] According to the example embodiment, the image decoding module 14 performs real-time decoding processing on the acquired image. The optical signal of the second color channel encodes the position identifier of the current emitting segment, and the optical signal of the first color channel encodes the task instructions (including the target position identifier) ​​broadcast by the vehicle control device 1.

[0106] For example, assuming the AGV is located in the light-emitting segment with ID=8, the second color channel (e.g., a red LED) emits a light signal indicating "ID=8"; the first color channel (e.g., a green LED) emits a task instruction broadcast by the controller 12, which includes "target position ID=5". The image decoding module 14 obtains the current light-emitting segment's position identifier (i.e., ID=8) by decoding the light signal of the second color channel in the image information, and obtains the target position identifier (i.e., ID=5) by decoding the light signal of the first color channel in the image information.

[0107] The navigation control module 15 is installed on the vehicle and connected to the image decoding module 14. It is used to compare the target position marker with the position marker of the current luminous segment. If they are inconsistent, the vehicle is controlled to drive along the light source array 11 until the position marker of the current luminous segment matches the target position marker.

[0108] According to the example embodiment, the navigation control module 15 compares the decoded target position identifier with the position identifier of the current luminous segment. If they match, it indicates that the AGV has reached the target position, triggering a stop at the target position; if they do not match, the AGV is controlled to continue traveling along the light source array 11, and during the travel process, the vehicle control device 1 repeatedly executes steps S300 to S500, updating the position identifier of the current luminous segment in real time and comparing it with the target position identifier until the position identifier of the current luminous segment matches the target position identifier.

[0109] For example, when the vehicle is at ID=8 and the target position is ID=5, since 8≠5, the controller 12 controls the vehicle to travel along the light source array 11 in the direction of decreasing ID, passing ID=7 and ID=6 in sequence. When it reaches ID=5, the current position identifier matches the target position identifier, and the vehicle stops. Conversely, when the vehicle is at ID=3 and the target position is ID=5, it travels in the direction of increasing ID.

[0110] Through the above embodiments, this application, by continuously laying out a light source array 11 with first and second color channels along a preset travel path, and driving all light-emitting segments to synchronously encode the target location identifier in the first color channel, simultaneously acquires the current location identifier by capturing the image of the current light-emitting segment, decodes the second color channel to obtain the current location identifier, and decodes the first color channel to obtain the target location identifier, and then autonomously controls the journey until the target is reached by comparing the two. The specific effects of this application's technical solution are as follows: This solution uses visible light communication to replace traditional radio electromagnetic wave communication, eliminating electromagnetic radiation at the physical level and eliminating the risk of ignition and explosion; this solution The light signals used cannot penetrate workshop walls, providing physical isolation and preventing external eavesdropping and hacker attacks, thus ensuring industrial information security and confidentiality. This solution does not rely on easily interfered wireless frequency bands such as Wi-Fi and Bluetooth, and can still work stably in industrial environments with strong electromagnetic interference such as large motors and frequency converters. This solution determines the vehicle's driving direction and stopping time by comparing the current position with the target position, reducing system communication load and the risk of single point of failure. The light source array 11 (such as LED light strips) and vehicle-mounted camera in this solution are inexpensive, easy to deploy, and the light signals are visible to the human eye, facilitating on-site maintenance personnel's inspection and troubleshooting.

[0111] According to another aspect of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the vehicle control methods described above.

[0112] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided, the program code causing the processor to perform any of the vehicle control methods described above.

[0113] According to another aspect of this application, a computer program product is also provided, including a computer program stored on a computer-readable medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform any of the vehicle control methods described above.

[0114] As is known from common technical knowledge, this application can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative in all respects and are not the only ones. All modifications within the scope of this application or equivalent to this application are included in this application.

Claims

1. A vision-guided vehicle control method, characterized in that, The vehicle operates along a preset travel path, and the vehicle control method includes: A light source array is continuously laid along the preset passage path, and the light source array is divided into multiple continuous light-emitting segments along the preset passage path; wherein each light-emitting segment includes at least a first color channel and a second color channel; According to the preset encoding rules, the task instruction containing the target location identifier is encoded into a driving signal, and the first color channel of all light-emitting segments is driven to emit a light signal corresponding to the driving signal according to the driving signal; Obtain image information of the current luminous segment where the vehicle is located; Decode the light signal of the second color channel in the image information to obtain the position identifier of the current light-emitting segment, and decode the light signal of the first color channel in the image information to obtain the target position identifier; The target position identifier is compared with the position identifier of the current emitting segment. If they are inconsistent, the vehicle is controlled to travel along the light source array until the position identifier of the current emitting segment matches the target position identifier.

2. The vehicle control method according to claim 1, characterized in that, The step of encoding the task instruction containing the target location identifier into a drive signal according to a preset encoding rule, and driving the first color channel of all light-emitting segments to emit light signals corresponding to the drive signal according to the drive signal, includes: The task instructions are converted into binary sequences according to the luminance binarization encoding rules; The binary sequence is converted into a PWM drive signal and sent to the first color channel of all the light-emitting segments, so that the first color channel of all the light-emitting segments emits a light signal corresponding to the binary sequence.

3. The vehicle control method according to claim 1, characterized in that, Decoding the light signal of the second color channel in the image information to obtain the position identifier of the current emitting segment, and decoding the light signal of the first color channel in the image information to obtain the target position identifier, includes: The acquired image information is segmented by color to extract the image region corresponding to the first color channel and the image region corresponding to the second color channel. Decode the light signal in the image region corresponding to the second color channel to obtain the position identifier of the current light-emitting segment; Decode the light signal in the image region corresponding to the first color channel to obtain the target location identifier.

4. The vehicle control method according to claim 3, characterized in that, The step of performing color segmentation on the acquired image information and extracting the image region corresponding to the first color channel and the image region corresponding to the second color channel includes: Convert the acquired image to the HSV color space; A color mask is generated based on a preset HSV range, and the image region corresponding to the first color channel and the image region corresponding to the second color channel are separated based on the color mask.

5. The vehicle control method according to claim 1, characterized in that, The task instructions also include motion parameters, and the vehicle control method further includes: Decode the light signal of the first color channel in the image information to obtain the motion parameters.

6. The vehicle control method according to claim 5, characterized in that, Controlling the vehicle to travel along the light source array until the position marker of the current emitting segment matches the target position marker includes: The driving direction of the vehicle is determined based on the relative positional relationship between the current luminous segment position marker and the target position marker. The vehicle is controlled to travel along the light source array according to the motion parameters and the driving direction until the position marker of the current light-emitting segment matches the target position marker.

7. The vehicle control method according to claim 1, characterized in that, Each of the light-emitting segments also includes a third color channel, and the vehicle control method further includes: Decode the light signal of the third color channel in the image information to obtain verification information; Verify the integrity of the target location identifier and / or the location identifier of the current luminous segment based on the verification information.

8. A vision-guided vehicle control device, characterized in that, include: A light source array is continuously laid along a preset passageway and is divided into multiple continuous light-emitting segments along the preset passageway; wherein each light-emitting segment includes at least a first color channel and a second color channel; The controller, connected to the light source array, is used to encode the task instruction containing the target location identifier into a drive signal according to the preset encoding rule, and drive the first color channel of all light-emitting segments to emit light signals corresponding to the drive signal according to the drive signal; An image acquisition module, installed on the vehicle, is used to acquire image information of the current luminous segment in which the vehicle is located; An image decoding module, installed on the vehicle and connected to the image acquisition module, is used to decode the light signal of the second color channel in the image information to obtain the position identifier of the current light-emitting segment, and to decode the light signal of the first color channel in the image information to obtain the target position identifier; A navigation control module, installed on the vehicle and connected to the image decoding module, is used to compare the target location marker with the location marker of the current luminous segment. If they are inconsistent, the module controls the vehicle to travel along the light source array until the location marker of the current luminous segment matches the target location marker.

9. An electronic device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the vehicle control method according to any one of claims 1-7.

10. A computer-readable medium having processor-executable non-volatile program code, characterized in that, The program code causes the processor to execute the vehicle control method according to any one of claims 1-7.

Images