A pedestrian reminding system, method and electronic device of an intelligent networked vehicle

Abstract

The application discloses a pedestrian reminding system and method of an intelligent networked vehicle and an electronic device, relates to the technical field of vehicle reminding, and comprises a perception layer, a decision layer and an execution layer. The perception layer is used for collecting vehicle driving environment data, vehicle state data and target object data, and transmitting the collected data to the decision layer. The decision layer performs environment scene identification and target object risk level evaluation based on the data transmitted by the perception layer, and generates acoustic warning control instructions and optical warning control instructions. The execution layer comprises an acoustic warning module and an optical warning module. The acoustic warning module and the optical warning module respectively receive the control instructions of the decision layer and cooperatively execute warning operations. The optical warning module also has an interactive feedback function and can transmit a vehicle perception state signal and a risk warning signal to a target object. The scheme realizes the safety warning function of a new energy vehicle through multi-sensory cooperation.

Description

Technical Field

[0001] This invention relates to the field of vehicle alert technology, and in particular to a pedestrian alert system for intelligent connected vehicles, a pedestrian alert method for intelligent connected vehicles, electronic devices, and storage media. Background Technology

[0002] As the automotive industry undergoes a profound transformation towards intelligence and connectivity, the penetration rate of intelligent connected vehicles continues to increase, making their driving safety, especially pedestrian safety, a core focus of industry attention. Electric vehicles, hybrid vehicles, and other new energy intelligent connected vehicles are nearly silent at low speeds, making it difficult for pedestrians and cyclists to perceive their approach by sound, significantly increasing the risk of collisions at low speeds. Therefore, pedestrian warning systems have become an essential safety feature for these vehicles. According to the Chinese recommended national standard GB / T 37153-2018 "Low-Speed ​​Warning Sounds for Electric Vehicles," all new electric vehicles, mild hybrid vehicles, and plug-in hybrid models must be equipped with an Acoustic Vehicle Alarm System (AVAS) to address the blind spot caused by low-speed silence.

[0003] Currently, most pedestrian warning technologies for intelligent connected vehicles rely on single-modal warnings. Acoustic warnings depend on AVAS (Automatic Visual Alarm System), which emits a fixed-frequency, fixed-amplitude warning sound through a speaker, automatically activating when the vehicle speed is below 20 km / h. However, this system suffers from significant environmental adaptability limitations. In scenarios with high background noise (typically 65-70 dB) such as busy urban traffic, the fixed sound pressure level (56-75 dB) of the AVAS system's warning sound is easily masked by ambient noise, significantly reducing its effectiveness. Conversely, in quiet residential areas, the fixed volume of the warning sound can cause unnecessary noise pollution, impacting user experience and the urban acoustic environment. Furthermore, existing AVAS systems often employ a single-speaker design, resulting in low sound field diffusion efficiency and difficulty in dynamically adjusting warning sound parameters based on risk level and scenario type, leading to poor adaptability.

[0004] In terms of optical warnings, existing technologies mostly employ simple flashing light designs, providing only basic vehicle presence indication. They lack tiered warning capabilities and interactive feedback, failing to convey the vehicle's perception status and collision risk level to the target, making it difficult for pedestrians and cyclists to accurately judge the vehicle's intentions and potential risks, easily leading to accidents due to misjudgment. Furthermore, existing optical warning devices are functionally limited, often providing fixed-position light prompts, unable to achieve precise warning effects such as directional or dynamic following warnings. In densely populated multi-vehicle scenarios, the source of the warning can easily become confused, further reducing the reliability of the warnings.

[0005] At the perception level, existing pedestrian alert systems mostly add separate perception modules, failing to effectively reuse existing vehicle sensor resources such as LiDAR and high-definition cameras, leading to increased system costs. Meanwhile, some systems employ a pure visual perception solution of "camera + millimeter-wave radar," which is prone to image blurring, target misses, or misjudgments in complex environments such as heavy rain and backlighting, resulting in insufficient perception accuracy and stability. Furthermore, most perception modules lack dedicated interface adapters, making it difficult to efficiently connect to the vehicle's CAN bus to obtain vehicle status signals such as speed, steering, and reversing. Additionally, the collected LiDAR point cloud data and camera image data are not effectively pre-processed for noise reduction and stitching, further impacting the accuracy of subsequent risk assessment and decision-making.

[0006] At the decision-making level, existing technologies employ relatively simple risk assessment methods, often relying solely on the distance between the target object and the vehicle. They fail to incorporate relative speed and scenario complexity to construct a comprehensive risk assessment model, thus hindering accurate collision risk classification (typically less than three levels). Furthermore, the lack of mature dual-modal linkage strategy algorithms prevents dynamic adjustment of the acoustic and optical warning modules' operating parameters and warning weights based on risk level and environmental scenario. This results in the two warning modes operating independently, failing to achieve a synergistic warning effect and making it difficult to adapt to the warning needs of different driving scenarios such as low-speed cruising, turning / reversing, and high-risk warnings. In addition, existing systems lack closed-loop control design in their perception-decision-execution chain. Insufficient coordination in perception data transmission, decision command generation, and execution leads to uncertainties in end-to-end response latency, compromising the real-time performance and accuracy of warning operations and failing to meet the pedestrian safety protection needs of intelligent connected vehicles in complex driving scenarios.

[0007] In terms of reminder methods and execution, existing pedestrian reminder methods are incomplete, lacking systematic scene recognition, three-dimensional risk assessment, and bimodal control command generation. They can only achieve basic warning operations and cannot trigger corresponding exclusive warning combinations according to different scenarios. At the same time, the related programs stored in existing electronic devices and computer-readable storage media can mostly only drive single-modal warning devices to work. They cannot efficiently execute a complete pedestrian reminder process that takes into account perception preprocessing, risk classification assessment, bimodal collaborative warning, and interactive feedback, making it difficult to adapt to the needs of multi-scenario and high-precision pedestrian safety protection.

[0008] Furthermore, under the existing vehicle-road-cloud integration framework, pedestrian alert systems also face problems such as insufficient coordination in the perception-decision-execution link and poor data interoperability. Different manufacturers' perception modules and warning devices have different interface protocols, forming data silos, making it difficult to achieve continuous and reliable warning services across scenarios and vehicles, which further limits the application effect and promotion value of pedestrian alert systems.

[0009] In summary, current pedestrian alert systems and related methods and devices for intelligent connected vehicles have significant shortcomings in terms of perception accuracy, decision rationality, warning adaptability, coordination, and interactivity. They cannot effectively address the pedestrian safety protection needs in complex driving scenarios and are unable to achieve accurate, efficient, and adaptive pedestrian alert functions. Therefore, developing an intelligent connected vehicle pedestrian alert system and related methods and devices that can solve the above-mentioned technical pain points and achieve closed-loop control of perception-decision-execution, dual-modal collaborative hierarchical warning, and interactive feedback has become an urgent technical problem to be solved by those skilled in the art. Summary of the Invention

[0010] In view of this, the purpose of the present invention is to provide a pedestrian warning system for intelligent connected vehicles, a pedestrian warning method for intelligent connected vehicles, an electronic device and a storage medium, in order to solve the technical problems in the prior art.

[0011] This invention provides the following solution:

[0012] According to one aspect of this application, a pedestrian alert system for intelligent connected vehicles is provided, comprising:

[0013] Perception layer, decision-making layer, and execution layer;

[0014] The perception layer, decision-making layer, and execution layer are sequentially connected by signals to form a closed-loop control;

[0015] The perception layer is used to collect vehicle driving environment data, vehicle status data and target object data, and transmit the collected data to the decision layer;

[0016] Based on the data transmitted from the perception layer, the decision-making layer identifies environmental scenes and assesses the risk level of target objects, generating acoustic and optical warning control commands.

[0017] The execution layer includes an acoustic warning module and an optical warning module. The acoustic warning module and the optical warning module respectively receive the control commands from the decision layer and work together to execute warning operations. The optical warning module also has an interactive feedback function, which can transmit the vehicle's perception status signal and risk warning signal to the target object.

[0018] Furthermore, the perception layer also includes:

[0019] Interface adapter module;

[0020] The interface adapter module is used to connect to the vehicle's CAN bus and obtain vehicle status signals such as vehicle speed, steering, and reversing.

[0021] The perception layer performs noise reduction and stitching preprocessing on the collected lidar point cloud data and camera image data.

[0022] Furthermore, the decision-making layer incorporates a risk level assessment algorithm and a dual-modal linkage strategy algorithm.

[0023] The risk level assessment algorithm constructs a three-dimensional assessment model based on the distance between the target object and the vehicle, the relative speed, and the complexity of the scene, and divides the risk level into at least 3 levels;

[0024] The dual-modal linkage strategy algorithm dynamically adjusts the working parameters and warning weights of the acoustic warning module and the optical warning module according to the risk level and environmental scene type.

[0025] Furthermore, including:

[0026] The decision-making layer's dual-modal linkage strategy satisfies the following: when the background noise exceeds a preset threshold or the environment is interfering, the working weight of the optical warning module is increased, and the output parameters of the acoustic warning module are optimized simultaneously.

[0027] When in a densely populated multi-vehicle scenario, the optical warning module is controlled to output differentiated signals to mark the source of the warning for this vehicle.

[0028] Furthermore, including:

[0029] The optical warning module includes a vehicle under-body projection unit, a side LED array unit, and an intelligent headlight unit;

[0030] The undercarriage projection unit is used to project dynamic light strips;

[0031] Side LED array units are used to achieve graded flashing;

[0032] The intelligent headlamp unit is used to project directional symbols or warning boxes.

[0033] Furthermore, including:

[0034] The acoustic warning module reuses the speakers and amplifiers of the vehicle's existing AVAS system, and dynamically adjusts the frequency, amplitude and rhythm of the warning sound according to the instructions of the decision-maker to adapt to different risk levels and scenario requirements.

[0035] Furthermore, including:

[0036] The interactive feedback function of the optical warning module is as follows: when the sensing layer identifies a target object, the side LED array unit projects a dotted light spot that moves with the target object to transmit the sensing signal;

[0037] When the decision-making level determines the risk to be medium or above, the side LED array unit switches from stable constant light to graded flashing, and the flashing frequency increases with the risk level.

[0038] Furthermore, including:

[0039] The decision-making level can trigger corresponding dual-modal warning combinations based on the vehicle driving scenario:

[0040] In low-speed cruising scenarios: the acoustic warning module outputs a standard warning tone, and the under-vehicle projection unit projects a dynamic light strip that is the same width as the vehicle body;

[0041] In turning or reversing scenarios: the acoustic warning module outputs a dedicated warning sound, the undercarriage projection unit projects a directional arrow, and the side LED array unit works with the turn signal to achieve graded flashing;

[0042] High-risk warning scenario: The acoustic warning module outputs a high-frequency warning sound, the side LED array unit flashes at a preset frequency, and the intelligent headlamp unit projects a red warning frame onto the target object.

[0043] According to two aspects of this application, a method for pedestrian alerting of intelligent connected vehicles is provided, comprising the following steps:

[0044] Data acquisition steps: The vehicle perception module collects driving environment data, vehicle status data, and target object data, including data related to pedestrians, cyclists, and non-standard obstacles.

[0045] Scene recognition and risk assessment steps: Based on the collected data, environmental scene classification and identification are performed, and a three-dimensional risk assessment model is constructed to classify the collision risk of the target object into different levels;

[0046] Dual-modal control command generation steps: Based on the scene recognition results and risk level assessment results, generate appropriate acoustic warning control commands and optical warning control commands, wherein the optical warning control commands include perception status feedback commands and risk warning commands;

[0047] Collaborative alert execution steps: Respond to the corresponding control command and collaboratively execute the alert operation;

[0048] At the same time, the vehicle's perception status signals are transmitted to the target object.

[0049] According to three aspects of this application, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0050] The memory stores a computer program, which, when executed by a processor, causes the processor to perform steps of a pedestrian alert method for intelligent connected vehicles.

[0051] According to four aspects of this application, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a pedestrian alert method for intelligent connected vehicles.

[0052] Compared with the prior art, the present invention has the following advantages:

[0053] This application reuses the vehicle's existing LiDAR and high-definition camera, adds an interface adapter module to connect to the vehicle's CAN bus, and collects vehicle status data such as speed, steering, and reversing. No additional sensing hardware is required, which greatly reduces the system's hardware and modification costs and enables rapid adaptation based on the vehicle's existing configuration.

[0054] This application effectively solves the problems of decreased point cloud density and image blurring in complex environments such as heavy snow, dense fog, and backlighting through data preprocessing, thereby improving perception accuracy and reducing the false and false recognition rates of target objects, especially improving the recognition effect of non-standard obstacles, pedestrians wearing black clothing, and cyclists.

[0055] This application further reduces system deployment costs by reusing existing AVAS hardware, ensuring compatibility with existing vehicle acoustic warning configurations, and improving the scenario-specific adaptability and recognizability of acoustic warnings. Through scenario-specific prompts, pedestrians can quickly identify vehicle driving intentions (such as turning / reversing), shortening pedestrian auditory perception reaction time and solving the problems of poor sound quality and ineffective warning effects in low-to-mid-range AVAS systems.

[0056] This application uses visual feedback of risk levels to allow pedestrians to quickly perceive the degree of collision risk, prompting them to make a quick avoidance reaction and improving the accuracy of pedestrians' understanding of vehicle intentions. Attached Figure Description

[0057] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0058] Figure 1 This is an architecture diagram of a pedestrian alert system for intelligent connected vehicles provided by one or more embodiments of the present invention.

[0059] Figure 2 This is a flowchart of a pedestrian alert method for intelligent connected vehicles provided in one or more embodiments of the present invention.

[0060] Figure 3 This is an electronic device structural block diagram of a pedestrian alert method for intelligent connected vehicles provided by one or more embodiments of the present invention. Detailed Implementation

[0061] The technical solution of the present invention will now be clearly and completely described 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.

[0062] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0063] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0064] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0065] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0066] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0067] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0068] Figure 1 This is an architecture diagram of a pedestrian alert system for intelligent connected vehicles provided by one or more embodiments of the present invention.

[0069] like Figure 1 As shown, it includes:

[0070] Perception layer, decision-making layer, and execution layer;

[0071] The perception layer is used to collect vehicle driving environment data, vehicle status data and target object data, and transmit the collected data to the decision layer;

[0072] Specifically, the perception layer also includes:

[0073] Interface adapter module;

[0074] The interface adapter module is used to connect to the vehicle's CAN bus and obtain vehicle status signals such as vehicle speed, steering, and reversing.

[0075] The perception layer performs noise reduction and stitching preprocessing on the collected lidar point cloud data and camera image data.

[0076] Based on the data transmitted by the perception layer, the decision-making layer identifies the environmental scene and assesses the risk level of the target object, and generates acoustic warning control commands and optical warning control commands.

[0077] Specifically, the decision-making layer incorporates a risk level assessment algorithm and a dual-modal linkage strategy algorithm.

[0078] The risk level assessment algorithm constructs a three-dimensional assessment model based on the distance between the target object and the vehicle, the relative speed, and the complexity of the scene, and divides the risk level into at least 3 levels;

[0079] The dual-modal linkage strategy algorithm dynamically adjusts the working parameters and warning weights of the acoustic warning module and the optical warning module according to the risk level and environmental scene type.

[0080] In one embodiment, the dual-modal linkage strategy of the decision layer satisfies the following: when the background noise is greater than a preset threshold or when the environment is in an interfering environment, the working weight of the optical warning module is increased, and the output parameters of the acoustic warning module are optimized simultaneously.

[0081] When in a densely populated multi-vehicle scenario, the optical warning module is controlled to output differentiated signals to mark the source of the warning for this vehicle.

[0082] The execution layer includes an acoustic warning module and an optical warning module. The acoustic warning module and the optical warning module respectively receive control commands from the decision layer and work together to execute warning operations. The optical warning module also has an interactive feedback function, which can transmit the vehicle's perception status signal and risk warning signal to the target object.

[0083] The optical warning module includes a vehicle under-body projection unit, a side LED array unit, and an intelligent headlight unit.

[0084] The undercarriage projection unit is used to project dynamic light strips;

[0085] Side LED array units are used to achieve graded flashing;

[0086] The intelligent headlamp unit is used to project directional symbols or warning boxes.

[0087] In one embodiment, the acoustic warning module reuses the speakers and amplifiers of the vehicle's existing AVAS system, and dynamically adjusts the frequency, amplitude and rhythm of the warning sound according to the instructions of the decision-making level to adapt to different risk levels and scenario requirements.

[0088] In one embodiment, the interactive feedback function of the optical warning module is as follows: when the sensing layer identifies a target object, the side LED array unit projects a dotted light spot that moves with the target object to transmit a sensing signal;

[0089] When the decision-making level determines the risk to be medium or above, the side LED array unit switches from stable constant light to graded flashing, and the flashing frequency increases with the risk level.

[0090] In one embodiment, the decision-making layer can trigger a corresponding dual-modal warning combination based on the vehicle driving scenario:

[0091] In low-speed cruising scenarios: the acoustic warning module outputs a standard warning tone, and the under-vehicle projection unit projects a dynamic light strip that is the same width as the vehicle body;

[0092] In turning or reversing scenarios: the acoustic warning module outputs a dedicated warning sound, the undercarriage projection unit projects a directional arrow, and the side LED array unit works with the turn signal to achieve graded flashing;

[0093] High-risk warning scenario: The acoustic warning module outputs a high-frequency warning sound, the side LED array unit flashes at a preset frequency, and the intelligent headlamp unit projects a red warning frame onto the target object.

[0094] Specifically, the system adopts a three-layer decoupled architecture consisting of a perception layer, a decision-making layer, and an execution layer to reduce system coupling and improve scalability and ease of maintenance. The design of multi-source data acquisition and preprocessing in the perception layer, combined with CAN bus interface adaptation, improves perception accuracy while reducing hardware modification costs and vehicle model adaptation difficulty.

[0095] The decision-making layer's three-dimensional risk assessment model and dual-modal linkage strategy enable precise risk quantification and adaptive adjustment of audio-visual warnings, effectively solving problems such as warning failure and source confusion in complex environments. The execution layer's audio-visual dual-modal collaboration and optical multi-unit combination design, coupled with interactive feedback functions and scenario-based warning combinations, enable proactive interaction between vehicles and pedestrians, improving the reliability and relevance of warnings.

[0096] By reusing the original vehicle's AVAS system hardware, the overall vehicle cost is further reduced. The fully automated operation enhances the vehicle's active safety performance, effectively reducing the risk of collisions between people and vehicles, and balancing safety, compatibility, and user experience.

[0097] It is worth noting that although only some basic functional modules are disclosed in this embodiment, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules does not mean that the scope of protection of the claims of this invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0099] Figure 2 This is a flowchart of a pedestrian alert method for intelligent connected vehicles provided in one or more embodiments of the present invention.

[0100] like Figure 2 As shown, it includes the following steps:

[0101] Data acquisition step S1: Collect driving environment data, vehicle status data and target object data through the vehicle perception module. The target object data includes data related to pedestrians, cyclists and non-standard obstacles.

[0102] Scene recognition and risk assessment step S2: Based on the collected data, classify and identify the environmental scene, construct a three-dimensional risk assessment model, and classify the collision risk of the target object into levels;

[0103] Dual-modal control command generation step S3: Based on the scene recognition results and risk level assessment results, generate appropriate acoustic warning control commands and optical warning control commands, wherein the optical warning control commands include perception status feedback commands and risk warning commands;

[0104] Collaborative alert execution step S4: Respond to the corresponding control command and collaboratively execute the alert operation;

[0105] At the same time, the vehicle's perception status signals are transmitted to the target object.

[0106] Figure 3 This is a control flowchart of a pedestrian alert method for intelligent connected vehicles according to a specific embodiment of the present invention.

[0107] like Figure 3 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0108] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps of a pedestrian alert method for intelligent connected vehicles.

[0109] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a pedestrian alert method for intelligent connected vehicles.

[0110] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0111] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A pedestrian alert system for intelligent connected vehicles, characterized in that, include: Perception layer, decision-making layer, and execution layer; The perception layer is used to collect vehicle driving environment data, vehicle status data and target object data, and transmit the collected data to the decision layer; The decision-making layer performs environmental scene recognition and target object risk level assessment based on the data transmitted by the perception layer, and generates acoustic warning control commands and optical warning control commands. The execution layer includes an acoustic warning module and an optical warning module; The acoustic warning module and the optical warning module respectively receive control commands from the decision-making layer and work together to execute warning operations; The optical warning module transmits vehicle perception status signals and risk warning signals to the target object.

2. The pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, The perception layer also includes: an interface adaptation module; The interface adapter module is used to access the vehicle CAN bus and obtain vehicle status signals; the vehicle status signals include: vehicle speed signal, steering signal and reversing signal; The perception layer performs noise reduction and splicing preprocessing on the collected vehicle driving environment data, vehicle status data, and target object data.

3. The pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, The decision-making layer incorporates a risk level assessment algorithm and a dual-modal linkage strategy algorithm. The risk level assessment algorithm constructs a three-dimensional assessment model based on the distance between the target object and the vehicle, the relative speed, and the complexity of the scene, and classifies the risk level. The dual-modal linkage strategy algorithm dynamically adjusts the working parameters and warning weights of the acoustic warning module and the optical warning module according to the risk level and environmental scene type.

4. The pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, include: The dual-modal linkage strategy of the decision layer satisfies the following: when the background noise is greater than a preset threshold or when the environment is in an interfering environment, the working weight of the optical warning module is increased, and the output parameters of the acoustic warning module are optimized simultaneously. When in a densely populated multi-vehicle scenario, the optical warning module is controlled to output differentiated signals to mark the source of the warning for this vehicle.

5. A pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, include: The optical warning module includes a vehicle under-body projection unit, a side LED array unit, and an intelligent headlight unit; The undercarriage projection unit is used to project dynamic light strips; The side LED array unit is used to achieve graded flashing; The intelligent headlamp unit is used to project directional symbols or warning boxes.

6. The pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, include: The acoustic warning module uses the vehicle's speakers and amplifiers to dynamically adjust the frequency, amplitude, and rhythm of the warning sound according to the instructions of the decision-makers, adapting to different risk levels and scenario requirements.

7. A pedestrian alert system for intelligent connected vehicles according to claim 1, characterized in that, include: The interactive feedback function of the optical warning module is as follows: when the sensing layer identifies a target object, the side LED array unit projects a dotted light spot that moves with the target object to transmit a sensing signal; When the decision-making level determines the risk to be medium or above, the side LED array unit switches from stable constant light to graded flashing, and the flashing frequency increases with the risk level.

8. A method for pedestrian alerting in intelligent connected vehicles, characterized in that, Includes the following steps: Data acquisition steps: The vehicle perception module collects driving environment data, vehicle status data, and target object data, including data related to pedestrians, cyclists, and non-standard obstacles. Scene recognition and risk assessment steps: Based on the collected data, environmental scene classification and identification are performed, and a three-dimensional risk assessment model is constructed to classify the collision risk of the target object into different levels; Dual-modal control command generation steps: Based on the scene recognition results and risk level assessment results, generate appropriate acoustic warning control commands and optical warning control commands, wherein the optical warning control commands include perception status feedback commands and risk warning commands; Collaborative alert execution steps: Respond to the corresponding control command and collaboratively execute the alert operation; At the same time, the vehicle's perception status signals are transmitted to the target object.

9. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the pedestrian alert method for an intelligent connected vehicle as described in claim 8.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the pedestrian alert method for an intelligent connected vehicle as described in claim 8.

Images