A highway service area sanitation cleaning system based on vehicle-road cloud map linkage

Abstract

The present invention relates to the field of highway service area sanitation and cleaning technology, and in particular to a highway service area sanitation and cleaning system based on vehicle-road cloud map linkage. A road-side monitoring unit is deployed in a preset area of ​​the service area to collect image data in real time, extract scene change information through dynamic background modeling, and establish a three-dimensional mapping relationship between the image and the world coordinate system based on binocular vision calibration. The cloud monitoring management platform contains garbage detection, positioning calculation and task scheduling modules to identify and classify garbage, obtain the actual physical coordinates of garbage, generate cleaning tasks and assign them to cleaning vehicles. Multiple types of automatic cleaning vehicles include special vehicles for recyclable and non-recyclable garbage. The present invention realizes full-link closed-loop management of detection, positioning, cleaning and verification through the coordinated linkage of the vehicle side, road side, cloud side and map side. It can efficiently and accurately complete the service area sanitation and cleaning tasks, significantly improve the cleaning efficiency and intelligence level, and adapt to the complex and changeable service area environment.

Description

Technical Field

[0001] The present invention relates to the technical field of highway service area sanitation and cleaning, and in particular to a highway service area sanitation and cleaning system based on vehicle-road cloud map linkage. Background Art

[0002] With the increasing traffic volume on highways, the sanitation of service areas, as important places to ensure drivers and passengers' needs for rest and supplies, has attracted increasing attention. Traditional highway service area sanitation and cleaning methods have the following limitations:

[0003] Manual cleaning relies on a large amount of manpower, is inefficient, and cannot guarantee timeliness. The service area is large, and garbage is widely distributed, making it difficult for manual inspection and cleaning to achieve comprehensive coverage. This can easily lead to garbage being left for long periods of time, affecting the overall environmental image of the service area and user experience.

[0004] Existing attempts at automated cleaning often suffer from ineffective results due to immature technology. For example, some simple automated cleaning devices lack precise garbage detection and location capabilities. In complex service area environments, they are unable to accurately identify various types of garbage, resulting in incomplete cleaning. Furthermore, these devices lack effective response mechanisms in dynamically changing environments, such as heavy traffic and frequent pedestrian movement, making them difficult to adapt to complex scenarios.

[0005] When it comes to garbage detection, common object detection algorithms lack accuracy in service area scenarios. Garbage in service areas comes in a wide variety of sizes and shapes, and lighting conditions are complex and variable, making it difficult for traditional algorithms to accurately identify and classify all types of garbage. Furthermore, traditional algorithms are typically based solely on monocular vision and cannot accurately obtain the three-dimensional location of garbage, making it difficult to schedule subsequent cleaning tasks.

[0006] In terms of positioning technology, binocular vision positioning alone is susceptible to environmental interference and can result in large positioning errors in situations such as occlusion and light changes. Relying solely on RTK positioning can lead to unstable positioning in areas with poor signals, such as those with severe building obstruction within the service area.

[0007] In addition, the current sanitation and cleaning system lacks effective coordination among the vehicle, road, cloud, and map ends; each link is independent of each other, and real-time data sharing and interaction cannot be achieved, resulting in a lack of integrity and efficiency in the planning and execution of cleaning tasks.

[0008] To sum up, there is an urgent need to develop a sanitation and cleaning system that can adapt to the complex environment of highway service areas and has the capabilities of efficient garbage detection, precise positioning, intelligent task scheduling, and vehicle-road cloud map linkage and coordination. This invention is developed based on this background. Summary of the Invention

[0009] The purpose of the present invention is to provide a highway service area sanitation cleaning system based on vehicle-road cloud map linkage to solve the problems raised in the above background technology.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] A highway service area sanitation cleaning system based on vehicle-road cloud map linkage, including:

[0012] Roadside monitoring units are deployed in pre-set areas of service areas to collect real-time image data of the monitored area, extract scene change information through dynamic background modeling, and establish a stereo mapping relationship between the image coordinate system and the world coordinate system based on binocular vision calibration;

[0013] The cloud monitoring management platform communicates with the roadside monitoring unit and includes:

[0014] The garbage detection module uses an improved target detection algorithm to identify and classify garbage in image data;

[0015] The positioning calculation module converts the detected garbage pixel coordinates into actual physical coordinates based on binocular stereo vision and RTK collaborative positioning technology;

[0016] The task scheduling module generates cleaning tasks based on a multi-factor decision model and dynamically assigns them to cleaning vehicles;

[0017] Multiple types of automatic cleaning vehicles, including special cleaning vehicles for recyclable and non-recyclable garbage, each cleaning vehicle is equipped with:

[0018] High-precision positioning module, achieving centimeter-level positioning;

[0019] Semantic map navigation module, which plans dynamic paths based on incrementally updated maps;

[0020] Classification and cleaning devices that adapt to the physical characteristics of different types of garbage for sorting or compression;

[0021] Closed-loop verification module verifies the cleaning effect through deep feature comparison.

[0022] As a preferred solution, the improved target detection algorithm is the YOLOv11 improved model, including:

[0023] Based on the size distribution characteristics of garbage in the service area, the K-means++ clustering algorithm is used to optimize the anchor box size. The anchor box size is the logarithmic mean of the width and height of the annotation box. The specific calculation method is: after taking the natural logarithm of the width and height of the annotation box, the arithmetic mean is calculated as the anchor box size;

[0024] A binocular vision feature fusion mechanism is introduced into the Backbone network. The left and right eye feature maps are fused through a three-dimensional convolution operation. The spatial attention weights are generated and then multiplied element-wise with the left eye feature map to output the fused feature map.

[0025] The loss function is defined as the weighted sum of the improved Inner-IoU loss function and the RTK positioning coordinate regression loss, where the weight factor of the RTK regression loss is 0.8.

[0026] As a preferred solution, the coordinate conversion method of the positioning calculation module includes:

[0027] The camera intrinsic parameter matrix and extrinsic parameter matrix are obtained through dual-target positioning, where the camera intrinsic parameter matrix includes the focal length 、 and optical center coordinates , the camera external parameter matrix includes the rotation matrix and translation vectors , calculate the target's three-dimensional coordinates based on the difference in the horizontal coordinates of the left and right eye images of the target point:

[0028] Depth value Equal to the product of the equivalent focal length and the binocular baseline distance divided by the parallax value;

[0029] Target actual horizontal coordinate It is equal to the depth value multiplied by the difference between the horizontal coordinate of the left eye image and the horizontal coordinate of the optical center, and then divided by the left eye focal length;

[0030] Target actual vertical coordinate It is equal to the depth value multiplied by the difference between the left eye image ordinate and the optical center ordinate, and then divided by the left eye focal length;

[0031] When the binocular positioning depth error exceeds 0.1 meters, the coordinates are corrected based on the RTK positioning data. The correction weight is dynamically calculated based on the RTK signal quality. The higher the signal quality, the greater the weight of the RTK data.

[0032] As a preferred solution, in the path planning algorithm of the task scheduling module, the path cost function integrates the following factors:

[0033] The actual length of the path g(n) and the estimated remaining length h(n);

[0034] The priority weight of garbage type: the priority of flammable garbage is increased by 50%;

[0035] Real-time obstacle density factor. The higher the obstacle density, the greater the path cost.

[0036] RTK positioning confidence factor. The lower the confidence, the higher the path cost.

[0037] The weight coefficients of garbage priority, obstacle density, and RTK confidence in the cost function are 0.6, 0.3, and 0.1, respectively.

[0038] As a preferred solution, the closed-loop verification module is implemented through the following steps:

[0039] Extract multi-scale features of the images before and after cleaning, perform channel concatenation on the ResNet-50 features of the cleaned image and the coordinate-aware convolutional features of the pre-cleaned image to generate fused features;

[0040] The verification threshold is dynamically adjusted according to the ambient light intensity. The baseline threshold is 0.8. For every 1-fold increase in the baseline light intensity, the threshold is increased by 0.2 times.

[0041] If the verification fails, task reallocation, semantic map correction and binocular vision calibration parameter adjustment are triggered. The calibration parameter correction amount is proportional to the difference in fusion features.

[0042] As a preferred solution, the implementation of the high-precision positioning module includes:

[0043] Carrier phase differential technology is used to achieve RTK centimeter-level positioning, with a positioning error of less than 0.05 meters;

[0044] When the RTK signal is lost, it automatically switches to binocular vision positioning mode. The switching condition is that the deviation between three consecutive frames of binocular positioning data and the historical trajectory exceeds the threshold.

[0045] As a preferred solution, the working modes of the classification cleaning device include:

[0046] When sorting recyclable waste, the magnetic strength of the magnetic attraction mechanism is proportional to the target volume, with a proportional coefficient of 0.5;

[0047] When compressing non-recyclable garbage, the vacuum adsorption negative pressure value is the smaller value between 0.8 times the garbage density value and 20kPa, and the compressed volume is less than 1 / 5 of the original volume.

[0048] As a preferred solution, the incremental update method of the semantic map includes:

[0049] The grayscale difference between the current image and the reference map is dynamically compared through binocular vision to generate a difference mask. The area with a grayscale difference of more than 30 is marked as a changed area.

[0050] After reconstructing the three-dimensional point cloud of the changed area, the updated garbage distribution, obstacle location and charging pile status are integrated into the semantic map. The fusion weight of the new and old maps is 0.7, and a global consistency check is performed once an hour.

[0051] As a preferred solution, it also includes an exception handling mechanism. When the number of cleaning task failures exceeds the preset threshold, the manual intervention protocol is initiated and the fault data is uploaded to the cloud analysis platform, triggering equipment self-inspection and parameter optimization.

[0052] As a preferred solution, the update frequency of dynamic background modeling is positively correlated with traffic volume. For every 50 vehicles / minute increase in traffic volume, the update frequency increases by 100%, and the maximum update delay does not exceed 2 seconds.

[0053] It can be seen from the technical solutions provided by the present invention that the highway service area sanitation cleaning system based on vehicle-road cloud map linkage provided by the present invention has the following beneficial effects:

[0054] Efficient and accurate garbage removal: Roadside monitoring units collect real-time image data and utilize improved target detection algorithms, such as the YOLOv11 model, to accurately identify and classify garbage. Combining binocular stereo vision with RTK collaborative positioning technology accurately captures the actual physical coordinates of garbage. Using a multi-factor decision-making model, cleaning tasks are generated and dynamically assigned to cleaning vehicles, significantly improving the efficiency and accuracy of garbage removal and ensuring a clean and tidy service area.

[0055] High degree of intelligence and automation: Various types of autonomous cleaning vehicles are equipped with high-precision positioning modules, semantic map navigation modules, classification and cleaning devices, and closed-loop verification modules. They can automatically complete the entire process from locating garbage, planning routes, executing cleaning operations, to verifying results, reducing manual intervention, improving the intelligence and automation level of cleaning work, and lowering labor costs.

[0056] Flexible adaptation to complex environments: The semantic map uses an incremental update method to promptly reflect changes in the service area environment. The dynamic background modeling update frequency is positively correlated with traffic volume, with a maximum delay of no more than 2 seconds. This allows the system to flexibly adapt to the dynamically changing environment within the service area, ensuring that garbage detection and positioning are not excessively interfered with by environmental factors.

[0057] Reliable exception handling: The exception handling mechanism monitors all aspects of the system in real time. Once it detects a cleaning task failure, hardware device failure, or communication link anomaly, it automatically attempts recovery, issues an alarm, and initiates manual intervention. It also records and uploads data, ensuring that the system can maintain basic operation and recover in a timely manner even in the face of anomalies, thereby enhancing system reliability.

[0058] Optimal resource allocation: The task scheduling module comprehensively considers multiple factors to generate cleaning tasks and plan routes, rationally allocates cleaning vehicles, and achieves the optimal allocation of cleaning resources in time and space, improving resource utilization efficiency and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1This is a schematic diagram of the overall structure of a highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0062] like Figure 1 As shown, an embodiment of the present invention provides a highway service area sanitation cleaning system based on vehicle-road cloud map linkage, including a road-side monitoring unit, a cloud monitoring management platform and multiple types of automatic cleaning vehicles;

[0063] In the highway service area sanitation and cleaning system of the present invention, the vehicle side, road side, cloud side, and map side work closely together to build a full-link closed-loop management system for detection, positioning, cleaning, and verification, ensuring that the sanitation and cleaning work of the service area is carried out efficiently, accurately, and continuously optimized.

[0064] Roadside monitoring units (RMUs) play a key role as the forefront of information collection. Deployed in pre-set areas within service areas, they utilize advanced monitoring equipment to collect real-time image data from the monitored areas. Through dynamic background modeling technology, they sensitively extract scene changes and promptly detect the presence of foreign objects such as garbage. Furthermore, based on binocular vision calibration, they accurately establish a three-dimensional mapping between the image coordinate system and the world coordinate system, providing a solid data foundation for subsequent garbage detection and location. This collected and processed data is rapidly transmitted to the cloud via a stable communication link.

[0065] The cloud is the core brain of the entire system, where the cloud monitoring and management platform performs multiple important functions. The garbage detection module receives image data from the road side and uses improved target detection algorithms, such as the improved YOLOv11 model, to accurately identify and classify garbage. The positioning calculation module uses binocular stereo vision and RTK collaborative positioning technology to convert the detected garbage pixel coordinates into actual physical coordinates, providing accurate location information for cleaning tasks. The task scheduling module comprehensively considers multiple factors such as garbage location, type, cleaning vehicle status, and service area road conditions. It generates scientific and reasonable cleaning tasks through a multi-factor decision-making model and dynamically and efficiently allocates them to the most suitable cleaning vehicles. In addition, the cloud also receives information such as cleaning task execution status and equipment status uploaded by the vehicle side, as well as map data updated by the map side, for unified analysis and management.

[0066] The vehicle side comprises multiple types of autonomous cleaning vehicles, which are the direct executors of sanitation and cleaning tasks. Recyclable and non-recyclable garbage cleaning vehicles are each equipped with a high-precision positioning module, capable of centimeter-level positioning, allowing them to accurately know their own position in any complex environment. The semantic map navigation module plans a dynamic and optimal driving path for the vehicle based on incrementally updated maps, guiding the vehicle to quickly reach the garbage location. The classification cleaning device uses the physical characteristics of the garbage type, such as the magnetic suction mechanism adaptively adjusting the magnetic force to sort recyclable garbage according to the target volume, and the vacuum suction device adjusts the negative pressure value according to the garbage density to compress non-recyclable garbage, completing the cleaning work efficiently. The closed-loop verification module verifies the cleaning effect through deep feature comparison and feeds the verification results back to the cloud.

[0067] The map side is primarily responsible for managing and updating semantic maps. The incremental update method for semantic maps uses binocular vision to generate difference masks, identify areas of environmental change in the service area, and then fuses the updated semantic layer with the original map. A global consistency check is also performed every hour to ensure the map is real-time and accurate. Updated map data is promptly transmitted to the cloud and vehicle side, providing the latest environmental information for vehicle navigation and mission planning.

[0068] When the system is started, the road side first collects data and transmits it to the cloud; the cloud side completes garbage detection and positioning, generates cleaning tasks and assigns them to the vehicle side; the vehicle side cleaning vehicle, based on the task instructions, uses the positioning and navigation modules to go to the garbage location, uses the classification cleaning device to clean it, and then confirms the cleaning effect through the closed-loop verification module and feeds back to the cloud; at the same time, the map side updates the map in real time and provides it to other sides; throughout the process, the vehicle side, road side, cloud side, and map side continuously interact with data, forming a cyclical and continuously optimized full-link closed-loop management process of detection, positioning, cleaning and verification, thereby ensuring that the highway service area always maintains a good sanitary environment.

[0069] In this embodiment, the roadside monitoring unit is deployed in a preset area of ​​the service area to collect image data of the monitoring area in real time, extract scene change information through dynamic background modeling, and establish a stereo mapping relationship between the image coordinate system and the world coordinate system based on binocular vision calibration;

[0070] Furthermore, the roadside monitoring unit is a key component of the highway service area sanitation and cleaning system based on vehicle-road cloud mapping. Its main function is to be deployed in a preset area of ​​the service area, collect image data from the monitored area in real time, extract scene change information through dynamic background modeling, and establish a stereo mapping relationship between the image coordinate system and the world coordinate system based on binocular vision calibration, providing basic data for subsequent garbage detection, positioning, and other operations. The following is a detailed and specific description of this unit:

[0071] Overall function overview:

[0072] The roadside monitoring unit collects real-time image data from a preset area within the service area, uses dynamic background modeling technology to capture changes in the scene, and utilizes binocular vision calibration technology to establish a three-dimensional mapping relationship between the image coordinate system and the world coordinate system. These operations accurately identify the distribution of garbage within the service area and its location in the real world, providing accurate data support for garbage detection and positioning calculations on the cloud monitoring management platform, thereby ensuring the efficient operation of the entire sanitation system.

[0073] Data collection:

[0074] One of the core functions of the roadside monitoring unit is to collect image data, as follows:

[0075] Image data collection: Monitoring equipment is deployed in pre-set areas within the service area to collect real-time image information of the area. This image data contains information about various scenes within the service area and serves as the basis for subsequent garbage identification and location.

[0076] Dynamic background modeling:

[0077] The roadside monitoring unit uses dynamic background modeling technology to extract scene change information. Its specific principles and functions are as follows:

[0078] Background modeling principle: By analyzing continuous image data, a background model of the service area scene is established; this model will be dynamically updated over time and as the scene changes to adapt to different environmental conditions;

[0079] Change information extraction: Compares real-time image data with the background model to extract changes in the scene. This change information may include the presence of garbage, vehicle movement, etc., providing important clues for subsequent garbage detection.

[0080] Binocular vision calibration:

[0081] The roadside monitoring unit uses binocular vision calibration technology to establish a three-dimensional mapping relationship between the image coordinate system and the world coordinate system. The specific steps are as follows:

[0082] Obtaining internal and external parameters: Obtain the camera's internal and external parameter matrices through binocular positioning. The camera's internal parameter matrix includes the focal length 、 and optical center coordinates , the camera external parameter matrix includes the rotation matrix and translation vectors The intrinsic parameter matrix reflects the internal characteristics of the camera, such as focal length, principal point position, etc.; the extrinsic parameter matrix describes the position and posture of the camera in the world coordinate system;

[0083] Establishing a stereo mapping relationship: Based on the acquired intrinsic and extrinsic parameter matrices and combined with binocular vision principles, a stereo mapping relationship between the image coordinate system and the world coordinate system is established. This allows the coordinates of garbage pixels detected in the image to be converted into actual physical coordinates, providing accurate location information for subsequent cleaning task scheduling.

[0084] Data output:

[0085] The roadside monitoring unit transmits the collected image data, extracted scene change information, established three-dimensional mapping relationships and other data to the cloud monitoring management platform. The specific content is as follows:

[0086] Image data transmission: Real-time collected image data is sent to the garbage detection module of the cloud monitoring management platform for garbage identification and classification;

[0087] Change information and mapping relationship transmission: The extracted scene change information and the established stereo mapping relationship data are transmitted to the positioning calculation module to convert the detected garbage pixel coordinates into actual physical coordinates;

[0088] Application value of the module:

[0089] The roadside monitoring unit provides accurate basic data for the highway service area sanitation and cleaning system by collecting image data in real time, extracting scene change information, and establishing three-dimensional mapping relationships. This data is the key basis for subsequent garbage detection, positioning, and cleaning task scheduling, helping to improve the efficiency and accuracy of the entire sanitation and cleaning system and ensure that the sanitary environment of the service area is effectively maintained. At the same time, the application of dynamic background modeling and binocular vision calibration technology enables the unit to adapt to different environmental conditions and scene changes, with strong flexibility and adaptability.

[0090] In this embodiment, the cloud monitoring management platform is in communication with the road-side monitoring unit and includes a garbage detection module, a positioning calculation module, and a task scheduling module;

[0091] Furthermore, the garbage detection module uses an improved target detection algorithm to identify and classify garbage in image data. This module is a key component of the cloud monitoring and management platform within the highway service area sanitation and cleaning system, based on vehicle-road cloud mapping. Its primary function is to use an improved target detection algorithm to identify and classify garbage in image data collected by roadside monitoring units, providing a foundation for subsequent positioning and cleaning tasks. The following is a detailed and specific description of this module:

[0092] Overall function overview:

[0093] The garbage detection module receives image data transmitted by roadside monitoring units and uses an improved object detection algorithm to accurately identify garbage in the images and classify it into recyclable and non-recyclable garbage. By optimizing algorithms and introducing specific mechanisms, this module improves the accuracy and efficiency of garbage detection, providing key support for the efficient operation of the entire sanitation system.

[0094] Data input:

[0095] The operation of the garbage detection module relies on the image data provided by the roadside monitoring unit, as follows:

[0096] Image data: The roadside monitoring unit collects real-time image information of the preset area of ​​the service area and transmits it to the garbage detection module. This image data contains various scene information within the service area and is the basis for garbage identification and classification.

[0097] Improved object detection algorithm:

[0098] The garbage detection module uses the improved YOLOv11 model to identify and classify garbage. The specific improvements are as follows:

[0099] Anchor box size optimization:

[0100] Based on the size distribution characteristics of garbage in the service area, the K-means++ clustering algorithm is used to optimize the anchor frame size. The anchor frame size calculation satisfies the formula:

[0101] (in, is the number of labeled boxes within the cluster, is the width of the annotation box, In this way, the anchor frame size can be made closer to the actual size of the garbage in the service area, thus improving the accuracy of target detection.

[0102] Binocular vision feature fusion mechanism:

[0103] A binocular visual feature fusion mechanism is introduced into the Backbone network to generate spatial attention weights, which are calculated to satisfy the formula:

[0104] (in, It is the feature map output after fusing the left and right visual features. is the activation function, is a three-dimensional convolution operation, Input feature map for the left eye, Input feature map for the right eye); This mechanism can fully utilize binocular vision information, enhance the feature extraction capability of garbage targets, and improve detection accuracy;

[0105] Loss function definition:

[0106] The loss function is defined as the weighted sum of the improved Inner-IoU loss and the RTK positioning coordinate regression loss, and the weight factor ; By reasonably designing the loss function, the model can be better optimized during the training process and the performance of the model can be improved;

[0107] Garbage identification and classification:

[0108] The garbage detection module uses an improved object detection algorithm to identify and classify garbage in image data. The specific process is as follows:

[0109] Feature extraction: Extract features from the input image data and extract the feature information of junk targets through the improved network structure of the target detection algorithm;

[0110] Target recognition: Based on the extracted feature information, identify the garbage targets in the image and determine their location and bounding box;

[0111] Garbage classification: Classify identified garbage targets into recyclable garbage and non-recyclable garbage, providing a classification basis for subsequent cleaning tasks;

[0112] Data output:

[0113] The spam detection module outputs the identified and classified spam information to other modules of the cloud monitoring management platform. The specific contents are as follows:

[0114] Garbage location and classification information: The location information of the detected garbage in the image and the classification results (recyclable or non-recyclable) are transmitted to the positioning calculation module for coordinate conversion and cleaning task scheduling;

[0115] Application value of the module:

[0116] The garbage detection module improves the accuracy and efficiency of garbage identification and classification within highway service areas through an improved target detection algorithm. Accurate garbage detection results provide a reliable foundation for subsequent positioning and cleaning tasks, helping to optimize the allocation of cleaning resources, improve the overall operational efficiency of the sanitation and cleaning system, and ensure the effective maintenance of the sanitary environment in service areas. Furthermore, the module's improved algorithms and mechanisms enable it to adapt to different environmental conditions and garbage types, demonstrating its versatility and adaptability.

[0117] Furthermore, the positioning calculation module uses binocular stereo vision and RTK collaborative positioning technology to convert the coordinates of detected garbage pixels into actual physical coordinates. The positioning calculation module is a key component of the cloud monitoring and management platform in the highway service area sanitation and cleaning system based on vehicle-road cloud mapping. Its main function is to convert the coordinates of garbage pixels detected by the garbage detection module into actual physical coordinates based on binocular stereo vision and RTK collaborative positioning technology, providing accurate location information for the scheduling of subsequent cleaning tasks. The following is a detailed description of this module:

[0118] Overall function overview:

[0119] The positioning calculation module receives the garbage pixel coordinates output by the garbage detection module and uses binocular stereo vision and RTK collaborative positioning technology to accurately calculate the actual physical coordinates of the garbage in the real world. During the calculation process, the characteristics and advantages of binocular vision positioning and RTK positioning are comprehensively considered. Through operations such as coordinate conversion and error correction, the accuracy and reliability of the positioning results are ensured, providing strong support for the cleaning vehicles to efficiently perform cleaning tasks.

[0120] Data input:

[0121] The operation of the positioning calculation module depends on the data provided by multiple modules, as follows:

[0122] Garbage pixel coordinates: provided by the garbage detection module. These coordinates are the garbage location information detected in the image coordinate system and are the starting data for positioning calculations.

[0123] Dual-target calibration parameters: including internal parameter matrix ( ) and external parameter matrix ,These parameters are obtained through the dual target positioning of the road end ,monitoring unit and are used to establish the connection between the image ,coordinate system and the world coordinate system;

[0124] RTK data: The RTK positioning data provided by the high-precision positioning module is used to perform coordinate correction when the binocular positioning error is large, thereby improving positioning accuracy;

[0125] Coordinate transformation method:

[0126] Binocular vision positioning:

[0127] The intrinsic parameter matrix and extrinsic parameter matrix obtained by dual-target positioning are used to calculate the target's three-dimensional coordinates based on the parallax. The calculation formula is as follows:

[0128] , , (in, is the binocular baseline distance, that is, the distance between the optical centers of the left and right cameras; is the disparity value, that is, the horizontal pixel difference between corresponding points of the same object in the left and right images; is the camera focal length; is the horizontal pixel coordinate of the target point in the left image; The vertical pixel coordinates of the target point in the target image; and The camera is and focal length of the direction; and are the coordinates of the origin of the image coordinate system in the pixel coordinate system respectively); using these formulas, the pixel coordinates of the garbage can be converted into preliminary physical coordinates in the three-dimensional space;

[0129] RTK collaborative positioning and error correction:

[0130] When the binocular positioning error exceeds the threshold Meters, coordinate correction is performed through RTK data; correction weight The RTK confidence level is dynamically calculated to ensure that the binocular vision positioning and RTK positioning results can be reasonably integrated under different positioning accuracy conditions, thereby improving the accuracy of the final positioning.

[0131] Data output:

[0132] The positioning calculation module outputs the converted actual physical coordinates of the garbage to the task scheduling module of the cloud monitoring management platform. The specific contents are as follows:

[0133] Actual physical coordinates of garbage: Accurate actual physical coordinates of garbage provide accurate location basis for the task scheduling module to plan cleaning tasks and allocate cleaning vehicles, enabling cleaning vehicles to quickly and accurately reach the garbage location for cleaning operations;

[0134] Application value of the module:

[0135] The positioning calculation module uses binocular stereo vision and RTK collaborative positioning technology to achieve precise conversion of garbage pixel coordinates to actual physical coordinates. Accurate positioning results provide a key guarantee for the efficient operation of the sanitation cleaning system, enabling cleaning vehicles to quickly reach garbage locations, improving cleaning efficiency and reducing the time garbage stays in the service area, thereby improving the overall sanitation quality of the service area. At the same time, the error correction mechanism ensures reliable positioning results under different environmental and positioning conditions, enhancing the stability and adaptability of the system.

[0136] Furthermore, the task scheduling module generates cleaning tasks based on a multi-factor decision model and dynamically assigns them to cleaning vehicles. The task scheduling module is the core component of the cloud monitoring and management platform in the highway service area sanitation and cleaning system, which is based on the vehicle-road cloud map. Its main responsibility is to generate cleaning tasks based on a multi-factor decision model and dynamically assign these tasks to cleaning vehicles, ensuring the entire sanitation and cleaning process is carried out efficiently and orderly. The following is a detailed description of this module:

[0137] Overall function overview:

[0138] The task scheduling module comprehensively analyzes multiple factors, including the garbage information identified by the garbage detection module, the actual physical coordinates of the garbage obtained by the positioning calculation module, and the real-time status of the cleaning vehicles. Using a multi-factor decision-making model, it generates the most optimized cleaning task plan and dynamically and rationally allocates tasks to each cleaning vehicle. By continuously optimizing task allocation, the utilization efficiency of cleaning resources is improved, garbage removal time is shortened, and the sanitation of the service area is ensured to be maintained in a good state.

[0139] Data input:

[0140] The task scheduling module relies on a wide range of data sources, as follows:

[0141] Garbage location and classification information: Obtained from the garbage detection and positioning calculation module; this information specifies the specific location coordinates of garbage within the service area and the type of garbage (recyclable or non-recyclable). This serves as the basic data for generating cleaning tasks, determining where cleaning vehicles need to go and the cleaning methods to be adopted.

[0142] Cleaning vehicle status information: including the vehicle's current location, remaining battery or fuel level, and the operating status of the vehicle's cleaning equipment. Real-time understanding of cleaning vehicle status helps to rationally allocate tasks, avoiding assigning tasks to vehicles that are not functioning properly or are too far away, thereby improving the feasibility and efficiency of task execution.

[0143] Service area maps and traffic information: These include service area layout maps, including location information such as roads, buildings, and parking lots, as well as real-time traffic data, such as congested sections and construction areas. This information is used to plan cleaning vehicle routes, avoid congested sections, reduce travel time, and ensure efficient completion of cleaning tasks.

[0144] Multi-factor decision model and task generation:

[0145] The task scheduling module uses a multi-factor decision model to generate cleaning tasks. The specific contents are as follows:

[0146] Multi-factor considerations: Comprehensively consider multiple factors, including the priority of the garbage, the distance between the cleaning vehicle and the garbage, the current state of the vehicle, and road conditions. For example, hazardous waste, such as flammable waste, is given higher priority and is cleared by cleaning vehicles first. Cleaning vehicles that are closer and in good condition are prioritized to reduce the total time required to complete the task.

[0147] Task generation logic: Based on a comprehensive evaluation of multiple factors, the order in which each piece of garbage needs to be cleaned and the corresponding cleaning vehicle are determined; the generated cleaning task contains detailed information such as garbage location, garbage type, estimated cleaning time, and assigned cleaning vehicle number;

[0148] Path planning algorithm:

[0149] When assigning tasks, the task scheduling module needs to plan the driving path for the cleaning vehicle. The path cost function is defined as:

[0150] (in, 、 、 ; From the starting point to the node The actual cost of the vehicle, such as the distance and time traveled; For slave nodes The estimated cost to reach the destination; For nodes The priority of garbage disposal, which is calculated as the weighted sum of the garbage flammability weight and the RTK confidence; For nodes Traffic condition factors at the location, such as congestion level; For nodes The confidence level of RTK positioning); through the path cost function, a variety of factors are comprehensively considered to plan the optimal driving path for the cleaning vehicle, reduce the task execution cost, and improve the cleaning efficiency;

[0151] Task allocation and dynamic adjustment:

[0152] Initial task allocation: Based on the cleaning task plan generated by the multi-factor decision-making model, the task is assigned to the most suitable cleaning vehicle. During the allocation process, the matching degree between the vehicle and the task is fully considered. For example, the recyclable garbage task is assigned to a special recyclable garbage cleaning vehicle equipped with the corresponding sorting equipment.

[0153] Dynamic Adjustment Mechanism: During the cleaning process, if unexpected situations occur, such as vehicle failure or the discovery of new garbage, the task scheduling module can monitor and re-evaluate the tasks in real time. Based on the new situation, the task allocation can be dynamically adjusted, and the tasks of the faulty vehicle can be promptly reallocated to other available vehicles to ensure that the cleaning tasks are not affected and continue to be carried out efficiently.

[0154] Data output:

[0155] The task scheduling module outputs the generated cleaning tasks and corresponding allocation plans to the cleaning vehicles. The specific contents are as follows:

[0156] Cleaning task instructions: Contains detailed information about the task, such as garbage location coordinates, garbage type, cleaning requirements, and planned driving routes, and is sent to the corresponding cleaning vehicle to guide the cleaning vehicle to accurately perform the cleaning task;

[0157] Application value of the module:

[0158] The task scheduling module achieves efficient generation and dynamic allocation of cleaning tasks through a scientific multi-factor decision-making model and a reasonable path planning algorithm. This greatly improves the overall operating efficiency of the highway service area sanitation and cleaning system, optimizes the allocation of cleaning resources, reduces garbage removal time, and improves the sanitary environment quality of the service area. At the same time, the dynamic adjustment mechanism enables the system to have the ability to respond to emergencies, enhances the system's stability and reliability, and provides strong guarantees for the normal operation of the service area.

[0159] In this embodiment, the multiple types of automatic cleaning vehicles include cleaning vehicles for recyclable and non-recyclable garbage, and each cleaning vehicle is equipped with:

[0160] High-precision positioning module, achieving centimeter-level positioning;

[0161] Semantic map navigation module, which plans dynamic paths based on incrementally updated maps;

[0162] Classification and cleaning devices that adapt to the physical characteristics of different types of garbage for sorting or compression;

[0163] Closed-loop verification module verifies cleaning results through deep feature comparison;

[0164] Furthermore, multi-type autonomous cleaning vehicles are key execution units of the highway service area sanitation and cleaning system based on vehicle-road cloud mapping. Their main function is to efficiently clean different types of garbage in the service area based on cleaning tasks assigned by the cloud monitoring and management platform, ensuring a clean and tidy service area environment. The following is a detailed description:

[0165] Overall function overview:

[0166] Multiple types of automated cleaning vehicles are divided into dedicated cleaning vehicles for recyclable and non-recyclable garbage. They are equipped with a variety of advanced modules and devices that can accurately locate garbage, plan the optimal cleaning path, and implement targeted cleaning operations based on garbage type. At the same time, they verify the cleaning effect, forming a complete cleaning closed-loop process.

[0167] Vehicle configuration and functional modules:

[0168] High-precision positioning module:

[0169] Positioning technology application: Carrier phase differential technology is used to achieve RTK centimeter-level positioning, which can reduce the positioning error to less than 0.05 meters. This technology accurately calculates the real-time position of the vehicle within the service area by receiving satellite signals and differential signals from base stations.

[0170] Positioning mode switching: When the RTK signal is lost, it automatically switches to binocular vision positioning mode. The switching condition is that three consecutive frames of positioning data are out of tolerance. Utilizing the binocular vision principle similar to that of the roadside monitoring unit, the vehicle obtains image information through the binocular camera on the vehicle, calculates the vehicle position, ensures the continuity and accuracy of positioning, and provides stable position support for the execution of cleaning tasks.

[0171] Semantic map navigation module:

[0172] Map construction and updating: Navigation based on incrementally updated semantic maps; generating difference masks through binocular vision (in, is the image at the current moment, is the reference image, To take the absolute value operation, is the difference mask, ), identifying environmental changes within the service area;

[0173] Then the updated semantic layers are fused, and the fusion formula is: (in, is the updated semantic map, is the semantic map before updating, For the updated semantic layer, is the fusion coefficient), and a global consistency check is triggered every hour to ensure the map is accurate in real time;

[0174] Path planning and execution: Dynamic paths are planned based on tasks assigned by the cloud monitoring and management platform and real-time updated semantic maps. Taking into account road conditions within the service area, dynamic information about other vehicles and pedestrians, an efficient and safe driving path is planned for the vehicle, guiding it to quickly reach the garbage location.

[0175] Classification cleaning device:

[0176] Recyclable waste sorting: For recyclable waste, it is equipped with magnetic suction mechanism and other sorting devices; the magnetic strength of the magnetic suction mechanism is Adaptive adjustment (where is the magnetic strength of the magnetic attraction mechanism, the target volume is the volume of the recyclable garbage target, ), which can automatically adjust the magnetic force according to the different volumes of recyclable garbage, accurately adsorb and sort out ferromagnetic recyclables, such as cans;

[0177] Compression of non-recyclable garbage: For non-recyclable garbage, a vacuum adsorption device is used for compression; the vacuum adsorption negative pressure value is based on Adjustment (where is the vacuum adsorption negative pressure value, is the density of non-recyclable garbage), compression ratio ≥5:1; by reasonably adjusting the negative pressure value, non-recyclable garbage can be efficiently compressed to reduce the volume of garbage and facilitate subsequent transportation and processing;

[0178] Closed-loop verification module:

[0179] Cleaning effect verification principle: Verify the cleaning effect by comparing the deep features. First, extract the multi-scale features of the images before and after cleaning and perform channel splicing. The feature fusion formula is: ( This is the image before cleaning. For the cleaned image, It is a deep residual network used to extract image features. CoordConv is a coordinate convolution layer. Indicates channel splicing operation);

[0180] Dynamic adjustment of verification threshold: verification threshold Dynamic adjustment according to ambient light, the adjustment formula is: (in, is the initial verification threshold, is the light adjustment coefficient, the light change is the difference between the current light and the reference light, and the reference light is a pre-set reference light value). In this way, it is possible to accurately determine whether the garbage is effectively cleaned under different lighting conditions to ensure the cleaning quality;

[0181] Collaboration between modules:

[0182] Each module works closely together. The high-precision positioning module provides accurate location information to the semantic map navigation module, enabling the vehicle to accurately navigate to the task location. The semantic map navigation module plans the path to guide the vehicle's efficient movement and provides real-time road conditions feedback to the task scheduling module. The classification cleaning device performs the appropriate cleaning operation based on the garbage type identified by the garbage detection module and the vehicle's arrival location. The closed-loop verification module provides feedback on the cleaning results to the cloud monitoring management platform. If the standards are not met, the platform can reschedule the vehicle for a second cleaning.

[0183] Application value of the vehicle:

[0184] With their advanced configuration and efficient working mode, various types of automatic cleaning vehicles have greatly improved the automation and intelligence level of sanitation and cleaning in highway service areas. They can quickly and accurately clean up all kinds of garbage, improve cleaning efficiency, reduce labor costs, and at the same time ensure cleaning quality, creating a clean and comfortable environment for the service area and improving the overall service quality and image of the service area.

[0185] In this embodiment, the system also includes an exception handling mechanism. When the number of cleaning task failures exceeds a preset threshold, a manual intervention protocol is initiated and fault data is uploaded to the cloud analysis platform, triggering equipment self-test and parameter optimization;

[0186] Furthermore, the exception handling mechanism is an integral part of the highway service area sanitation and cleaning system based on the vehicle-road cloud map. Its primary function is to ensure that the system can maintain basic operation and promptly restore normal status in the face of various abnormal situations. It also effectively records and analyzes abnormal situations, providing a basis for continuous system optimization. The following is a detailed description of this mechanism:

[0187] Overall function overview:

[0188] The exception handling mechanism monitors key aspects such as the execution status of cleaning tasks, the operation of various hardware devices, and the stability of system communication links in real time. Once an abnormality is detected, the corresponding response measures are immediately initiated, including automatic recovery attempts, alarm issuance, manual intervention, and data recording and uploading, to ensure system reliability and the continuity of sanitation and cleaning work.

[0189] Abnormal monitoring range:

[0190] The exception handling mechanism mainly monitors the following aspects:

[0191] Abnormal cleaning task execution: Continuously track the cleaning vehicle's performance on assigned tasks. If the number of cleaning task failures exceeds a preset threshold, such as three consecutive unsuccessful attempts to clean the same garbage spot, it is considered a cleaning task execution abnormality. This may be due to a cleaning vehicle equipment malfunction, inaccessible garbage locations, or other unexpected factors.

[0192] Hardware failure: Monitor the status of various hardware devices on cleaning vehicles, such as high-precision positioning modules, classification cleaning devices, drive systems, and roadside monitoring units and the hardware facilities of the cloud monitoring management platform. For example, if the positioning module of a cleaning vehicle fails to obtain valid positioning data for 5 consecutive minutes, or if the CPU usage of the cloud platform server exceeds 90% for more than 10 minutes, it is considered a hardware failure.

[0193] Communication link anomalies: Monitor the data transmission links between the vehicle, road, and cloud. If data transmission interruptions last longer than one minute, or the packet loss rate exceeds 10% for five consecutive minutes, the communication link is considered abnormal. This may affect the coordination between various parts of the system, leading to problems in task allocation, data transmission, and other links.

[0194] Exception handling process:

[0195] Automatic recovery attempts:

[0196] When an abnormality is detected, the system first attempts automatic recovery. For example, if a communication link is abnormal, the system will automatically reconnect the communication port and attempt to restore data transmission. If a cleaning vehicle's task execution is abnormal due to a temporary software malfunction, the system will automatically restart the relevant software module. Automatic recovery attempts will be made multiple times within a set time. If recovery is successful within the specified number of times, the system will continue normal operation and record the abnormality and recovery process.

[0197] Alert issued:

[0198] If the automatic recovery attempt fails, the exception handling mechanism will immediately issue an alert. This alert will be notified to relevant personnel through various means, such as text message alerts to the system administrator's mobile phone and a prominent red pop-up alert on the cloud monitoring management platform interface. The alert will detail key information such as the type of exception, time of occurrence, and location (including the vehicle number and approximate location if a cleaning vehicle is involved), allowing administrators to quickly understand the situation and take further action.

[0199] Manual intervention started:

[0200] When the number of cleaning task failures exceeds the threshold or other serious abnormalities occur and automatic recovery is ineffective, the manual intervention protocol is initiated; the system will suspend the automatic scheduling of related abnormal tasks and generate a detailed manual intervention task list on the cloud monitoring management platform, which includes abnormality details, recommended treatment measures, and other information. At the same time, maintenance personnel are notified to go to the site or conduct manual inspection and repair of the system through remote operation. For example, if the classification cleaning device of a cleaning vehicle fails, maintenance personnel need to go to the vehicle location for inspection and repair.

[0201] Data recording and uploading:

[0202] During exception handling, the system records all exception-related data in detail, including the operating parameters of each system module in the period before the exception occurred, the specific status information at the time of the exception, the operation records of automatic recovery attempts, and the various operations and feedback during manual intervention. This data will be uploaded to the cloud analysis platform for subsequent exception cause analysis, system performance evaluation, and optimization and improvement. By analyzing large amounts of exception data, potential weaknesses in the system can be discovered, targeted optimization and upgrades can be carried out, and the stability and reliability of the system can be improved.

[0203] Application value of the mechanism:

[0204] The exception handling mechanism effectively enhances the robustness and fault tolerance of the highway service area sanitation and cleaning system. When faced with a complex and changeable actual operating environment, it can respond to various abnormal situations in a timely manner, ensure the continuous progress of sanitation and cleaning work, and reduce the deterioration of service area sanitation conditions caused by abnormalities. At the same time, through the recording and analysis of abnormal data, it provides a valuable basis for the optimization and improvement of the system, which helps to continuously improve the overall performance and reliability of the system and provide service areas with more stable and efficient sanitation and cleaning services.

[0205] In this embodiment, the update frequency of the dynamic background modeling is positively correlated with the traffic volume. For every 50 vehicles / minute increase in traffic volume, the update frequency is doubled, and the maximum update delay does not exceed 2 seconds.

[0206] Specifically, dynamic background modeling plays a key role in the highway service area sanitation and cleaning system of the present invention, and a sophisticated correlation mechanism is established between its update frequency and traffic volume;

[0207] In complex environments like highway service areas, traffic flow is constantly changing. Roadside monitoring units (RMUs) are tasked with real-time monitoring of traffic flow. Using advanced sensor technology and intelligent algorithms, they can accurately count the number of vehicles passing through a specific area within a specific timeframe, quantifying this data on a minute-by-minute basis.

[0208] When traffic volume is relatively low, the dynamic background model is updated at a base rate. For example, if traffic volume is below 50 vehicles per minute, the background model is updated every four seconds. As traffic volume increases, once the incremental threshold of 50 vehicles per minute is reached, the update frequency increases accordingly. Specifically, the update frequency doubles from every four seconds to every two seconds. If traffic volume continues to increase, the update frequency doubles again to every 1 second each time the incremental threshold of 50 vehicles per minute is reached, and so on.

[0209] However, in order to ensure the stability of the system and the effectiveness of data processing, a maximum update delay limit is set; no matter how rapidly the traffic volume increases, the update delay of the dynamic background modeling is strictly controlled to no more than 2 seconds; this means that even if the traffic volume increases significantly, the update frequency may theoretically be extremely high, but the actual update interval will not be shorter than 2 seconds; for example, when the traffic volume continues to increase, the update frequency should reach once every 0.5 seconds according to the positive correlation rule, but due to the maximum update delay limit, the actual update frequency remains at once every 2 seconds; this limitation avoids excessive consumption of system resources due to too fast an update frequency, ensuring that the system can maintain stable operation while efficiently capturing dynamic changes in the environment, thereby providing timely and reliable background data support for subsequent links such as garbage detection, and contributing to the efficient operation of the sanitation and cleaning system of the entire highway service area.

[0210] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A highway service area sanitation cleaning system based on vehicle-road cloud map linkage, characterized by: include: Roadside monitoring units are deployed in pre-set areas of service areas to collect real-time image data of the monitored area, extract scene change information through dynamic background modeling, and establish a stereo mapping relationship between the image coordinate system and the world coordinate system based on binocular vision calibration; The cloud monitoring management platform communicates with the roadside monitoring unit and includes: The garbage detection module uses the improved YOLOv11 model to identify and classify garbage in image data. The improved YOLOv11 model includes: Based on the size distribution characteristics of garbage in the service area, the K-means++ clustering algorithm is used to optimize the anchor box size. The anchor box size is the logarithmic mean of the width and height of the annotation box. The specific calculation method is: after taking the natural logarithm of the width and height of the annotation box, the arithmetic mean is calculated as the anchor box size; A binocular vision feature fusion mechanism is introduced into the Backbone network. The left and right eye feature maps are fused through a three-dimensional convolution operation. The spatial attention weights are generated and then multiplied element-wise with the left eye feature map to output the fused feature map. The loss function is defined as the weighted sum of the improved Inner-IoU loss function and the RTK positioning coordinate regression loss, where the weight factor of the RTK regression loss is 0.8; The positioning calculation module converts the detected garbage pixel coordinates into actual physical coordinates based on binocular stereo vision and RTK collaborative positioning technology; The task scheduling module generates cleaning tasks based on a multi-factor decision model and dynamically assigns them to cleaning vehicles; Multiple types of automatic cleaning vehicles, including special cleaning vehicles for recyclable and non-recyclable garbage, each cleaning vehicle is equipped with: High-precision positioning module, achieving centimeter-level positioning; Semantic map navigation module, which plans dynamic paths based on incrementally updated maps; Classification and cleaning devices that adapt to the physical characteristics of different types of garbage for sorting or compression; Closed-loop verification module verifies the cleaning effect through deep feature comparison.

2. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The coordinate conversion method of the positioning calculation module includes: The camera intrinsic parameter matrix and extrinsic parameter matrix are obtained through dual-target positioning, where the camera intrinsic parameter matrix includes the focal length 、 and optical center coordinates , the camera external parameter matrix includes the rotation matrix and translation vectors , calculate the target's three-dimensional coordinates based on the difference in the horizontal coordinates of the left and right eye images of the target point: Depth value Equal to the product of the equivalent focal length and the binocular baseline distance divided by the parallax value; Target actual horizontal coordinate It is equal to the depth value multiplied by the difference between the horizontal coordinate of the left eye image and the horizontal coordinate of the optical center, and then divided by the left eye focal length; Target actual vertical coordinate It is equal to the depth value multiplied by the difference between the left eye image ordinate and the optical center ordinate, and then divided by the left eye focal length; When the binocular positioning depth error exceeds 0.1 meters, the coordinates are corrected based on the RTK positioning data. The correction weight is dynamically calculated based on the RTK signal quality. The higher the signal quality, the greater the weight of the RTK data.

3. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: In the path planning algorithm of the task scheduling module, the path cost function combines the following factors: The actual length of the path g(n) and the estimated remaining length h(n); The priority weight of garbage type: the priority of flammable garbage is increased by 50%; Real-time obstacle density factor. The higher the obstacle density, the greater the path cost. RTK positioning confidence factor. The lower the confidence, the higher the path cost. The weight coefficients of garbage priority, obstacle density and RTK confidence in the cost function are 0.6, 0.3 and 0.1 respectively.

4. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The closed-loop verification module is implemented by the following steps: Extract multi-scale features of the images before and after cleaning, perform channel concatenation on the ResNet-50 features of the cleaned image and the coordinate-aware convolutional features of the pre-cleaned image to generate fused features; The verification threshold is dynamically adjusted according to the ambient light intensity. The baseline threshold is 0.

8. For every 1-fold increase in the baseline light intensity, the threshold is increased by 0.2 times. If the verification fails, task reallocation, semantic map correction and binocular vision calibration parameter adjustment are triggered. The calibration parameter correction amount is proportional to the difference in fusion features.

5. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The implementation of the high-precision positioning module includes: Carrier phase differential technology is used to achieve RTK centimeter-level positioning, with a positioning error of less than 0.05 meters; When the RTK signal is lost, it automatically switches to binocular vision positioning mode. The switching condition is that the deviation between three consecutive frames of binocular positioning data and the historical trajectory exceeds the threshold.

6. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The working modes of the classification cleaning device include: When sorting recyclable waste, the magnetic strength of the magnetic attraction mechanism is proportional to the target volume, with a proportional coefficient of 0.5; When compressing non-recyclable garbage, the vacuum adsorption negative pressure value is the smaller value between 0.8 times the garbage density value and 20kPa, and the compressed volume is less than 1 / 5 of the original volume.

7. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The incremental update method of the semantic map includes: The grayscale difference between the current image and the reference map is dynamically compared through binocular vision to generate a difference mask. The area with a grayscale difference of more than 30 is marked as a changed area. After reconstructing the three-dimensional point cloud of the changed area, the updated garbage distribution, obstacle location and charging pile status are integrated into the semantic map. The fusion weight of the new and old maps is 0.7, and a global consistency check is performed once an hour.

8. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: It also includes an exception handling mechanism. When the number of cleaning task failures exceeds the preset threshold, the manual intervention protocol is initiated and the fault data is uploaded to the cloud analysis platform, triggering equipment self-inspection and parameter optimization.

9. The highway service area sanitation cleaning system based on vehicle-road cloud map linkage according to claim 1 is characterized by: The update frequency of the dynamic background modeling is positively correlated with the traffic volume. For every 50 vehicles / minute increase in traffic volume, the update frequency increases by 1 time, and the maximum update delay does not exceed 2 seconds.

Images