Control method and system of unmanned sanitation vehicle, product and medium

Abstract

A control method and system for an unmanned sanitation vehicle, a product and a medium relate to the field of sanitation vehicles, and the method comprises the following steps: obtaining garbage feature information of target garbage within a preset distance around a target sanitation vehicle, and storing the garbage information in a garbage distribution map, calculating a regional garbage treatment difficulty value according to the garbage quantity, the garbage type and the garbage occupied area information; obtaining task progress parameters of the target sanitation vehicle, wherein the task progress parameters comprise a cleaned mileage proportion, a garbage bin residual capacity proportion and a current road section completion progress; performing weighted operation on the task progress parameter and the regional garbage disposal difficulty value to obtain a garbage disposal priority coefficient; and planning a sweeping route of the target sanitation vehicle based on the garbage treatment priority coefficient and historical garbage distribution data. By implementing the method, the rationality of sanitation vehicle sweeping resource allocation can be improved.

Description

Technical Field

[0001] The present application relates to the field of sanitation vehicles, and in particular to a control method, system, product and medium for an unmanned sanitation vehicle. Background Art

[0002] With the acceleration of urbanization and the continuous growth of urban population, urban environmental sanitation maintenance is facing huge challenges. In order to improve the efficiency of urban sanitation operations and reduce labor costs, unmanned sanitation vehicles have gradually become an important development direction for urban sanitation operations.

[0003] In the related art, a preset route operation method can be adopted, in which a fixed cleaning route and operation time are planned in advance, and sanitation operations are performed along the predetermined route. This operation method usually adopts a simple path planning algorithm to set the operation route according to the road length and cleaning area.

[0004] However, since garbage distribution in urban environments has significant temporal and spatial dynamic characteristics, fixed-route operation methods are difficult to adapt to changes in garbage distribution in actual environments. In actual operations, some areas may have serious garbage accumulation, while other areas are relatively clean. In this case, fixed-route operation methods are likely to cause unreasonable allocation of cleaning resources and affect operation efficiency. Summary of the invention

[0005] The present application provides a control method, system, product and medium for an unmanned sanitation vehicle, which are used to improve the rationality of cleaning resource allocation of the sanitation vehicle.

[0006] In the first aspect, the present application provides a control method for an unmanned sanitation vehicle, which is applied to an unmanned sanitation vehicle control system, the method comprising: obtaining garbage characteristic information of target garbage within a preset distance around the target sanitation vehicle, the garbage information including garbage type, garbage quantity, garbage location and garbage area information; storing the garbage information in a garbage distribution map, the garbage distribution map dividing the garbage area in a grid form, each grid including garbage characteristic information within the garbage area; calculating a regional garbage disposal difficulty value based on the garbage quantity, the garbage type and the garbage area information; obtaining a task progress parameter of the target sanitation vehicle, the task progress parameter including the proportion of mileage cleaned, the proportion of remaining capacity of the garbage bin and the completion progress of the current section; performing a weighted operation on the task progress parameter and the regional garbage disposal difficulty value to obtain a garbage disposal priority coefficient; and planning a cleaning route for the target sanitation vehicle based on the garbage disposal priority coefficient and historical garbage distribution data.

[0007] By adopting the above technical solution, first obtain the characteristic information such as the type, quantity, location and floor area of the garbage within a preset distance around the target sanitation vehicle, and store it in a garbage distribution map in the form of a grid. Then calculate the regional garbage treatment difficulty value based on the garbage quantity, type and floor area, and then combine it with the task progress parameter of the sanitation vehicle to obtain the garbage treatment priority coefficient through weighting. Finally, plan the cleaning route based on this and the historical garbage distribution data, which can accurately analyze the garbage situation in each area and the vehicle task situation, make the cleaning route planning more scientific and reasonable, improve the cleaning efficiency of the sanitation vehicle, and ensure the orderly and efficient progress of the operation.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the step of calculating the regional garbage treatment difficulty value according to the garbage quantity, the garbage type and the garbage floor area information specifically includes: calculating the regional influence coefficient according to the garbage type and the floor area; calculating the cleaning time coefficient according to the garbage quantity and the unit garbage treatment reference time; performing weighted calculation on the regional influence coefficient and the cleaning time coefficient to obtain the regional garbage treatment difficulty value.

[0009] By adopting the above technical solution, calculate the regional influence coefficient according to the garbage type and area, obtain the cleaning time coefficient according to the quantity and reference time, and obtain the difficulty value through weighting, comprehensively consider the garbage characteristics and cleaning time, accurately quantify the difficulty, provide a basis for cleaning arrangement and resource allocation, enhance the pertinence of the operation, and improve the efficiency.

[0010] Combined with some embodiments of the first aspect, in some embodiments, the step of determining the regional garbage treatment priority based on the task progress parameter, the regional garbage treatment difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage treatment priority specifically includes: dividing the garbage area into an immediate treatment area, a delayed treatment area and a regular cleaning area according to the garbage treatment priority coefficient; establishing a spatio-temporal prediction model of the regional garbage distribution according to the historical garbage distribution data; inputting the task progress parameter into the spatio-temporal prediction model to obtain the garbage distribution prediction data, and performing data fusion on the garbage distribution prediction data and the real-time garbage distribution map to obtain the regional garbage accumulation trend information; generating a cleaning route according to the distribution positions of the immediate treatment area, the delayed treatment area, the regular cleaning area and the regional garbage accumulation trend information, and the cleaning route preferentially covers the immediate treatment area.

[0011] By adopting the above technical solution, divide the cleaning area, establish a model to obtain the trend information, combine the information to plan the route to preferentially process the emergency area, integrate multiple data to grasp the garbage dynamics, avoid blind cleaning, ensure the priority cleaning of key areas, improve the timeliness and efficiency of sanitation, and optimize the operation process.

[0012] In some embodiments in combination with some embodiments of the first aspect, after the steps of determining the regional waste treatment priority based on the task progress parameter, the regional waste treatment difficulty value, and the historical waste distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional waste treatment priority, the method further includes: real-time monitoring of the cleaning status information of the target sanitation vehicle, where the cleaning status information includes a cleaning effect parameter and an equipment status parameter; when the cleaning effect parameter is lower than a preset cleaning quality threshold, determining the cleaning anomaly type according to a preset anomaly type determination rule; obtaining a corresponding operation parameter adjustment plan from a preset parameter adjustment rule library according to the cleaning anomaly type; and sending an adjustment instruction including the adjustment plan to the target sanitation vehicle.

[0013] By adopting the above technical solution, after the route is planned, the cleaning status of the sanitation vehicle is monitored. When the cleaning effect parameter is lower than the threshold, the anomaly type is determined according to the preset rule, and then the adjustment plan is retrieved from the rule library and sent to the sanitation vehicle to prompt it to adjust the operation status and ensure efficient and high-quality cleaning.

[0014] In some embodiments in combination with some embodiments of the first aspect, after the steps of determining the regional waste treatment priority based on the task progress parameter, the regional waste treatment difficulty value, and the historical waste distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional waste treatment priority, the method further includes: detecting whether there are dynamic obstacles around the target sanitation vehicle; if so, obtaining the motion data of the dynamic obstacle and determining whether the motion trajectory of the dynamic obstacle will cross the cleaning route; if a crossing will occur, calculating the estimated passing time of the dynamic obstacle according to the motion data; and sending a waiting instruction including the estimated passing time to the target sanitation vehicle.

[0015] By adopting the above technical solution, after the route is planned, dynamic obstacles are detected, data is collected by sensors, and the crossing situation with the cleaning route is determined. If there is a crossing, the passing time is calculated based on the motion data and a waiting instruction is sent to enable the sanitation vehicle to avoid and ensure safe and stable operation.

[0016] In some embodiments in combination with some embodiments of the first aspect, after the steps of determining the regional waste treatment priority based on the task progress parameter, the regional waste treatment difficulty value, and the historical waste distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional waste treatment priority, the method further includes: obtaining the weather forecast information within the operation area of the sanitation vehicle; when there is rainy weather, setting the waste treatment priority coefficient of the predicted rainfall area to the highest priority; and re-planning the cleaning route based on the set waste treatment priority coefficient and planning the predicted rainfall area as the priority cleaning area.

[0017] By adopting the above technical solution, after planning the route, the weather forecast is obtained. When it rains, the garbage disposal priority in the rainfall area is increased and the route is replanned, so that the sanitation vehicle can clean up in advance, prevent the spread of garbage pollution, and maintain the environmental cleanliness.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value, and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority, the method further includes: sending a cleaning instruction including the cleaning route to the target sanitation vehicle.

[0019] By adopting the above technical solution, after planning the cleaning route, the system packages it into an instruction containing key information and sends it to the sanitation vehicle via the wireless communication network. After receiving and parsing it, the control unit of the vehicle cleans precisely according to the route, improving the operation accuracy and efficiency, and ensuring the effective implementation of the environmental sanitation cleaning work.

[0020] In a second aspect, an embodiment of the present application provides an unmanned sanitation vehicle control system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to make the unmanned sanitation vehicle control system execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions. When the above computer program product runs on the unmanned sanitation vehicle control system, the above unmanned sanitation vehicle control system is made to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions. When the above instructions run on the unmanned sanitation vehicle control system, the above unmanned sanitation vehicle control system is made to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the unmanned sanitation vehicle control system provided in the second aspect above, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application first obtains the characteristic information such as the type, quantity, location, and floor area of the garbage within a preset distance around the target sanitation vehicle, and stores it in a garbage distribution map in the form of a grid. Then, based on the garbage quantity, type, and floor area, it calculates the garbage treatment difficulty value for the area, and combines it with the task progress parameters of the sanitation vehicle to obtain the garbage treatment priority coefficient through weighting. Finally, based on this and the historical garbage distribution data, it plans the cleaning route, which can accurately analyze the garbage situation in each area and the vehicle task situation, making the cleaning route planning more scientific and reasonable, improving the cleaning efficiency of the sanitation vehicle, and ensuring the orderly and efficient progress of the operation.

[0025] 2. This application calculates the regional influence coefficient according to the garbage type and area, obtains the cleaning time coefficient according to the quantity and the reference time, and obtains the difficulty value through weighting, comprehensively considering the garbage characteristics and cleaning time, accurately quantifying the difficulty, providing a basis for cleaning arrangement and resource allocation, enhancing the pertinence of the operation, and improving the efficiency.

[0026] 3. This application divides the cleaning area, builds a model to obtain the trend information, combines the information to plan the route to give priority to the emergency area, integrates multiple data to grasp the garbage dynamics, avoids blind cleaning, ensures the priority cleaning of the key area, improves the timeliness and efficiency of the sanitation work, and optimizes the operation process. Description of the Drawings

[0027] Figure 1 is a flowchart of a control method for an unmanned sanitation vehicle in an embodiment of this application; Figure 2 is another flowchart of a control method for an unmanned sanitation vehicle in an embodiment of this application; Figure 3 is a schematic structural diagram of an entity device of an unmanned sanitation vehicle control system in an embodiment of this application. Detailed Embodiments

[0028] The terms used in the following embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application, the singular forms "a", "an", "above-mentioned", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0030] For ease of understanding, the method provided in this embodiment will be described in terms of its process below. Please refer to Figure 1 , which is a schematic flowchart of the control method of the driverless sanitation vehicle in the embodiment of the present application.

[0031] S101. Obtain the garbage feature information of the target garbage within a preset distance around the target sanitation vehicle. The garbage information includes garbage type, garbage quantity, garbage location, and garbage floor area information.

[0032] Among them, the target sanitation vehicle refers to the specific driverless sanitation vehicle performing the cleaning task; the preset distance refers to the effective detection range of the sanitation vehicle sensor, usually set to 10 - 20 meters; the garbage feature information refers to the data set used to describe the attributes of the garbage; the garbage type is used to distinguish different types of garbage, such as plastics, paper, fallen leaves, etc.; the garbage quantity represents the number of identified garbage individuals; the garbage location is represented by spatial coordinates (x, y); the garbage floor area information is used to represent the size of the ground area covered by the garbage.

[0033] This step is periodically executed when the sanitation vehicle starts to perform the cleaning task or during the execution process. Specifically, the sanitation vehicle obtains the surrounding environment information through the onboard sensor system: the vision camera collects image data for garbage recognition and classification, the lidar measures the garbage location and contour dimensions, and after multi-sensor data fusion, complete garbage feature information is obtained. The system preprocesses and extracts features from the acquired raw data to generate a garbage feature data packet in a standard format.

[0034] In some embodiments, the acquisition of the garbage feature information can be achieved in the following ways: Optionally, a deep learning method is used for garbage detection and classification. First, a target detection network is used to locate the garbage location and extract the bounding box, then a classification network is used to identify the garbage type, and finally, the area of the bounding box is calculated to obtain the floor area; Optionally, a multi-sensor collaborative perception method is adopted, where the vision camera is responsible for garbage type recognition, the lidar is responsible for position and size measurement, and the millimeter-wave radar is used for auxiliary verification. The multi-source data is fused through the Kalman filter algorithm. It can be understood that other sensor combinations or algorithms can also be used to achieve the acquisition of the garbage feature information, which is not limited here.

[0035] S102. Store the garbage information in the garbage distribution map. The garbage distribution map divides the garbage area in a grid form, and each grid contains the garbage feature information within the garbage area.

[0036] Among them, the garbage distribution map refers to the digital map describing the garbage distribution in the operation area; the grid refers to the basic unit obtained by dividing the map according to a fixed size (such as 1 meter × 1 meter); the garbage area represents the geographical area containing garbage; the garbage feature information includes the attribute data of all the garbage identified within the grid.

[0037] This step is executed immediately after obtaining the garbage feature information. Specifically, the system first creates a local map centered on the current position of the sanitation vehicle and divides the map into grids of equal size. Then, the obtained garbage feature information is mapped to the corresponding grids according to the position coordinates, and each grid stores all the garbage information in that area. The system updates the map data regularly to ensure the timeliness of the garbage distribution information.

[0038] In some embodiments, the map storage of garbage information can be achieved in the following ways: Optionally, a hierarchical storage structure is adopted, with the original grid data stored at the bottom layer, the garbage feature data stored at the middle layer, and the statistical information stored at the top layer. The data of each layer is associated through an index; Optionally, a dynamic update mechanism is adopted, setting the information validity period, regularly cleaning up expired data, and dynamically maintaining active data to ensure the timeliness of the map information. It can be understood that other data structures or storage strategies can also be used to manage the garbage distribution map, which is not limited here.

[0039] S103. Calculate the regional garbage treatment difficulty value according to the garbage quantity, the garbage type, and the garbage floor area information.

[0040] Among them, the garbage quantity refers to the total number of garbage individuals identified in a unit area; the garbage type represents the material and property classification of the garbage; the garbage floor area information is used to represent the size of the ground area covered by the garbage; the regional impact coefficient refers to the degree of impact of the garbage on environmental hygiene; the cleaning time coefficient represents the standardized time required to clean the garbage in this area; the regional garbage treatment difficulty value is a quantitative index of the regional cleaning difficulty level obtained by comprehensively considering multiple factors, and the value range is 0 - 100.

[0041] This step is executed after obtaining the garbage distribution information. Specifically, the system first queries the preset type weight table according to the garbage type. The weight coefficients (W_type) of different types of garbage are different. For example, the weight of perishable garbage is 0.8, and the weight of plastic garbage is 0.6. Then, calculate the area impact factor (F_area) according to the floor area, using a piecewise function: when the area is less than 1 square meter, the value is 0.6; when it is 1 - 3 square meters, the value is 0.8; when it is greater than 3 square meters, the value is 1.0. The regional impact coefficient is equal to the product of the type weight and the area factor. Then, calculate the cleaning time coefficient according to the garbage quantity (N) and the unit garbage treatment reference time (T_base, default is 30 seconds): T_coef = N × T_base / 3600. Finally, perform a weighted calculation on the regional impact coefficient (R_impact) and the cleaning time coefficient (T_coef) to obtain the regional garbage treatment difficulty value: Difficulty = 0.6 × R_impact + 0.4 × T_coef.

[0042] In some embodiments, the calculation of the regional waste treatment difficulty value can be achieved in various ways: Optionally, first construct a multi-layer neural network model. The input layer contains waste feature parameters, the hidden layer performs feature extraction and non-linear mapping, and the output layer obtains the difficulty value. The model parameters are trained with historical data to achieve the adaptive calculation of the difficulty value; Optionally, adopt the fuzzy logic inference method, fuzzify the waste feature parameters, establish a fuzzy rule base, obtain the membership degree through fuzzy inference, and finally defuzzify to obtain the final difficulty value. It can be understood that other machine learning algorithms or mathematical models can also be used to calculate the regional waste treatment difficulty value, which is not limited here.

[0043] This step specifically includes: Calculate the regional impact coefficient according to the waste type and the occupied area. Calculate the cleaning time coefficient according to the waste quantity and the unit waste treatment benchmark time. Perform weighted calculation on the regional impact coefficient and the cleaning time coefficient to obtain the regional waste treatment difficulty value.

[0044] Among them, the waste type represents the classification of the material attributes of the waste, such as plastics, paper, fallen leaves, etc.; the occupied area represents the size of the ground area covered by the waste; the regional impact coefficient refers to the degree of impact of the waste on the environment; the waste quantity refers to the total number of waste individuals in a unit area; the unit waste treatment benchmark time represents the standard time required to process a single waste; the cleaning time coefficient refers to the time evaluation value required to clean the waste in this area; the regional waste treatment difficulty value represents a quantitative index of the difficulty level of regional cleaning.

[0045] Specifically, for the calculation of the regional impact coefficient, first establish a waste type weight mapping table: the weight of plastic waste is 0.6, the weight of paper waste is 0.4, the weight of fallen leaves is 0.3, and the weight of other types is 0.5. Set the area coefficient according to the occupied area: less than 0.5 square meters is 0.6, 0.5 - 2 square meters is 0.8, and greater than 2 square meters is 1.0. The regional impact coefficient is equal to the product of the type weight and the area coefficient. For the calculation of the cleaning time coefficient, the total treatment time is obtained by multiplying the waste quantity by the unit treatment benchmark time (default 30 seconds), and the total treatment time is divided by 3600 seconds to obtain the standardized coefficient in hours. The final regional waste treatment difficulty value adopts the weighted calculation method: difficulty value = 0.7×regional impact coefficient + 0.3×cleaning time coefficient. For example, if there are 5 plastic wastes in a certain area with an occupied area of 1.5 square meters, then the regional impact coefficient is 0.6×0.8 = 0.48, the cleaning time coefficient is (5×30) / 3600 = 0.042, and the final difficulty value is 0.7×0.48 + 0.3×0.042 = 0.349. The larger the regional waste treatment difficulty value, the more difficult it is to treat the waste in this area, and more cleaning resources need to be invested.

[0046] S104. Obtain the task progress parameters of the target sanitation vehicle, where the task progress parameters include the proportion of the swept mileage, the remaining capacity ratio of the garbage bin, and the completion progress of the current road section.

[0047] Among them, the task progress parameters refer to the set of quantitative indicators describing the current operation status of the sanitation vehicle; the proportion of the swept mileage represents the ratio of the completed swept distance to the total task distance; the remaining capacity ratio of the garbage bin is the ratio of the current remaining space in the garbage bin to the total capacity; the completion progress of the current road section is used to represent the degree of completion of the operation on the currently swept road section, and the value range is 0 - 100%.

[0048] This step is periodically executed during the process of the sanitation vehicle performing the sweeping task, and the time interval is usually 1 minute. Specifically, the system collects various status data through on-vehicle sensors: the GPS module records the driving trajectory to calculate the swept mileage, the weight sensor monitors the loading amount of the garbage bin to calculate the remaining capacity, and the position sensor combines with the electronic map to calculate the completion progress of the road section. The system standardizes the collected raw data, uniformly converts it into a percentage form, and generates a standardized task progress parameter data packet.

[0049] In some embodiments, the task progress parameters can be obtained in multiple ways: Optionally, a distributed sensing network solution is adopted, multiple sensor nodes are arranged at key parts of the sanitation vehicle, data is collected through the CAN bus, the local processor performs data preprocessing and feature extraction, and finally it is uploaded to the control system through wireless communication; Optionally, based on the cloud-edge collaboration architecture, the on-vehicle terminal collects raw data in real time and performs preliminary processing, and the cloud server performs in-depth analysis and status evaluation after receiving the data, and the results are fed back in real time through the 5G network. It can be understood that other data collection schemes or processing architectures can also be used to obtain the task progress parameters, which are not limited here.

[0050] S105. Perform a weighted operation on the task progress parameters and the regional garbage treatment difficulty value to obtain the garbage treatment priority coefficient.

[0051] Among them, the task progress parameters represent the set of quantitative indicators of the current operation status of the sanitation vehicle; the regional garbage treatment difficulty value refers to the quantified difficulty level of regional cleaning; the weighted operation refers to the process of performing mathematical calculations on multiple parameters according to different weights; the garbage treatment priority coefficient represents the quantitative indicator of the urgency of garbage cleaning in a certain area, and the value range is 0 - 100, and the larger the value, the higher the priority; the weight coefficient is used to represent the importance of different parameters in the calculation.

[0052] This step is executed immediately after obtaining the task progress parameter and the regional garbage disposal difficulty value. Specifically, the system first normalizes the task progress parameter: the proportion of the cleaned mileage is denoted as P1, the remaining capacity ratio of the garbage bin is denoted as P2, the completion progress of the current road section is denoted as P3, and the regional garbage disposal difficulty value is denoted as D. Then, weighted calculation is performed according to the preset weights: the weight of the cleaned mileage W1 = 0.3, the weight of the garbage bin capacity W2 = 0.4, the weight of the road section progress W3 = 0.3, and the weight of the difficulty value W4 = 0.6. Finally, the garbage disposal priority coefficient is calculated: Priority = (W1×P1 + W2×P2 + W3×P3)×0.4 + W4×D×0.6.

[0053] In some embodiments, the calculation of the garbage disposal priority coefficient can be achieved in various ways: Optionally, the analytic hierarchy process is used to determine the parameter weights. First, a judgment matrix is established to compare the importance of parameters pairwise, then the eigenvector is calculated to obtain the weight value, and finally, a consistency test is performed to ensure the rationality of the weights. The priority coefficient is calculated according to the final weights; Optionally, based on the dynamic weight adjustment mechanism, first set the initial weight value, then analyze the influence degree of different parameters on the cleaning effect according to the historical operation data, and dynamically adjust the weight coefficient to achieve the adaptive optimization of the priority calculation. It can be understood that other weight determination methods or calculation models can also be used to calculate the garbage disposal priority coefficient, which is not limited here.

[0054] S106. Plan the cleaning route of the target sanitation vehicle based on the garbage disposal priority coefficient and the historical garbage distribution data.

[0055] Among them, the garbage disposal priority coefficient refers to a quantitative index of the urgency of regional garbage cleaning; the historical garbage distribution data represents the garbage distribution situation recorded in the past period; the cleaning route refers to the sequence of path points that the sanitation vehicle needs to pass through in order; the immediate treatment area refers to the high-priority area that needs to be cleaned immediately; the delayed treatment area refers to the medium-priority area that can be treated later; the regular cleaning area represents the low-priority area that is cleaned according to the regular frequency.

[0056] This step is executed after calculating the garbage disposal priority coefficient. Specifically, the system first divides the garbage areas into three categories according to the priority coefficient value: the priority coefficient greater than 80 is the immediate treatment area, 60 - 80 is the delayed treatment area, and less than 60 is the regular cleaning area. Then, a spatio-temporal prediction model is established based on the historical data to predict the future garbage distribution trend. Combining the regional classification results and the prediction data, an improved A* algorithm is used for path planning: giving priority to covering the immediate treatment area, and at the same time considering constraints such as path length and number of turns to generate the optimal cleaning route.

[0057] In some embodiments, the cleaning route can be planned in various ways: Optionally, a hierarchical planning strategy is adopted. First, the access order of the main cleaning areas is planned at the macroscopic level, then the connection paths between areas are planned at the mesoscopic level, and finally the smoothness and feasibility of local paths are optimized at the microscopic level. Optionally, path optimization is performed based on the ant colony algorithm. Multiple candidate paths are initialized, and iterative optimization is carried out through pheromone update and path evaluation. At the same time, a dynamic obstacle avoidance mechanism is introduced to handle real-time environmental changes. It can be understood that other path planning algorithms or optimization methods can also be used to generate the cleaning route, which is not limited here.

[0058] This step specifically includes: According to the waste treatment priority coefficient, the waste area is divided into an immediate treatment area, a delayed treatment area, and a regular cleaning area; A spatio-temporal prediction model of regional waste distribution is established based on historical waste distribution data; The task progress parameter is input into the spatio-temporal prediction model to obtain waste distribution prediction data. The waste distribution prediction data is fused with the real-time waste distribution map to obtain regional waste accumulation trend information; A cleaning route is generated according to the distribution positions of the immediate treatment area, the delayed treatment area, the regular cleaning area, and the regional waste accumulation trend information. The cleaning route preferentially covers the immediate treatment area.

[0059] Among them, the waste treatment priority coefficient represents a quantitative index of the urgency of regional waste cleaning, with a value range of 0-100; the immediate treatment area refers to the area with a priority coefficient higher than 80; the delayed treatment area refers to the area with a priority coefficient between 60-80; the regular cleaning area refers to the area with a priority coefficient lower than 60; the historical waste distribution data refers to the waste distribution information recorded in the past 30 days; the spatio-temporal prediction model refers to a mathematical model used to predict the future waste distribution trend; data fusion refers to the process of combining prediction data and real-time data to form comprehensive information; the waste accumulation trend information represents the law of the change of the regional waste quantity over time.

[0060] Specifically, first classify the areas according to the garbage disposal priority coefficient: grids with a priority coefficient greater than 80 are marked as immediate processing areas, grids with a priority coefficient of 60 - 80 are marked as delayed processing areas, and grids with a priority coefficient less than 60 are marked as regular cleaning areas. Then, construct an LSTM neural network model based on historical data. The input features include time, location, garbage type, and quantity, etc. Through deep learning, predict the garbage distribution in the next 24 hours. Input the current task progress parameters (including the proportion of the cleaned mileage, the remaining capacity ratio of the garbage bin, and the completion progress of the current section) into the prediction model to obtain the garbage distribution prediction data considering the cleaning capacity constraint. Use the Kalman filter algorithm to fuse the prediction data with the real-time collected garbage distribution data to generate the regional garbage accumulation trend information. Based on the regional classification results and trend information, use the improved A* algorithm to plan the cleaning route: first, take the grids in the immediate processing area as the necessary passing points, and set a relatively large heuristic weight to ensure priority access; then, take the delayed processing area as the secondary priority points; finally, incorporate the regular cleaning area into the path planning, while considering constraints such as minimizing the path length and the number of turns, and output the final cleaning route. For example, when it is detected that the garbage accumulation speed in a certain area is fast and the priority is high, the algorithm will give priority to arranging the sanitation vehicle to go to this area for cleaning operations.

[0061] The following further describes the method provided in this embodiment in a more specific process. Please refer to Figure 2 , which is another process schematic diagram of the control method of the driverless sanitation vehicle in the embodiment of the present application.

[0062] S201. Plan the cleaning route of the target sanitation vehicle based on the garbage disposal priority coefficient and historical garbage distribution data.

[0063] S202. Send a cleaning instruction containing the cleaning route to the target sanitation vehicle.

[0064] The cleaning route refers to the sequence of path points that the driverless sanitation vehicle needs to pass through in order. Each path point contains information such as longitude and latitude coordinates, driving speed, and operation status. The cleaning instruction is a control command sent by the control system to the sanitation vehicle, which encapsulates the complete cleaning route data in a standard data format. The target sanitation vehicle refers to an intelligent sanitation vehicle equipped with an autonomous driving system and a cleaning operation execution system.

[0065] Specifically, the control system packs the planned cleaning route data according to a predefined data protocol to form a data instruction containing complete information such as path points, speed, and operation status. This instruction is sent in real time to the vehicle control unit of the target sanitation vehicle through a wireless communication network (such as a 4G / 5G network). After receiving the instruction, the sanitation vehicle will navigate and drive point by point according to the route information in the instruction and perform the corresponding cleaning operation. The cleaning instruction contains information such as route number, path point sequence, position coordinates of each path point, driving speed, and operation status.

[0066] S203. Real-time monitor the cleaning status information of the target sanitation vehicle. The cleaning status information includes cleaning effect parameters and equipment status parameters.

[0067] The cleaning effect parameters include quantitative indicators such as cleaning coverage rate, cleaning quality score, and residual garbage rate to measure the cleaning operation effect. The equipment status parameters include operating parameters such as the battery power of the sanitation vehicle, the capacity of the garbage bin, and the working status of key components. Real-time monitoring means continuously collecting these parameter data at a fixed time interval (such as 1 second).

[0068] This step collects operation data in real time through an in-vehicle sensor network: the cleaning effect is evaluated by an in-vehicle camera in cooperation with computer vision algorithms, and the change in ground cleanliness before and after cleaning can be calculated; the equipment status is directly measured by sensors distributed throughout the vehicle. These data will be uploaded to the control system in real time. The specific implementation method is: the vehicle control unit collects all sensor data once every 1 second, packs them into a status data packet and uploads it. After receiving the data, the system stores it in a real-time monitoring database for subsequent status evaluation and anomaly judgment.

[0069] S204. When the cleaning effect parameter is lower than the preset cleaning quality threshold, determine the cleaning anomaly type according to the preset anomaly type determination rule.

[0070] The cleaning quality threshold is the lowest standard of the preset cleaning effect, including specific indicators such as the cleaning coverage rate not less than 95% and the residual garbage rate not exceeding 5%. The anomaly type determination rule is a set of logical rule sets for diagnosing the reasons for cleaning operation anomalies. The cleaning anomaly types include specific abnormal situations such as incomplete cleaning, missed cleaning, and secondary pollution.

[0071] The execution process of this step is: the system compares the monitored cleaning effect parameters with the preset threshold in real time, and triggers anomaly diagnosis when any parameter is lower than the threshold. The diagnosis program analyzes each parameter according to the preset rules, and determines the specific anomaly type according to the combined characteristics of parameter anomalies. For example: when the cleaning coverage rate is lower than 95% and the vehicle speed is normal, it is determined as a missed cleaning anomaly; when the residual garbage rate exceeds 5% and the cleaning motor current is normal, it is determined as an insufficient cleaning intensity anomaly. The system will record the determination result and use it for subsequent parameter adjustment.

[0072] S205. Obtain the corresponding operation parameter adjustment plan from the preset parameter adjustment rule library according to the cleaning anomaly type.

[0073] The parameter adjustment rule library is a database that stores the mapping relationship between cleaning anomaly types and corresponding processing solutions, including fields such as anomaly type, trigger condition, adjustment parameter type, adjustment range, etc. The operation parameter adjustment plan includes the adjustment values of specific parameters such as the rotation speed of the cleaning motor, the power of the dust suction fan, and the driving speed. Preset refers to the fixed rules configured by the system based on professional knowledge and historical experience before operation.

[0074] The specific execution process of this step is as follows: The system first reads the identified cleaning anomaly type identifier, and performs index matching in the rule library through the anomaly type identifier. After matching the corresponding record, extract the parameter adjustment plan field in this record. The specific content of the adjustment plan includes the parameter items to be adjusted and the adjustment values. For example, for the anomaly of insufficient cleaning intensity, the adjustment plan stipulates that: the rotation speed of the cleaning motor is increased by 20% (from the original rotation speed of 2000 rpm to 2400 rpm), the power of the dust suction fan is increased by 15% (from the original power of 2000 W to 2300 W), and the driving speed is decreased by 10% (from the original speed of 15 km / h to 13.5 km / h). The system organizes these specific parameter adjustment values into a standard format adjustment plan data packet.

[0075] S206. Send the adjustment instruction containing this adjustment plan to the target sanitation vehicle.

[0076] The adjustment instruction is a control command containing the operation parameter adjustment plan, encapsulated in a standard data format, and includes the adjustment target values of each parameter. The adjustment plan is a set of specific parameter adjustment values obtained from the parameter adjustment rule library. The target sanitation vehicle refers to the driverless sanitation vehicle that is currently performing cleaning operations and has an anomaly.

[0077] The execution process of this step is: The system converts the obtained parameter adjustment plan into a data format, generates an adjustment instruction that meets the requirements of the communication protocol. Send the adjustment instruction to the control unit of the target sanitation vehicle through the wireless communication network. The sending process adopts a reliable transmission mechanism, including an acknowledgment confirmation mechanism, to ensure the reliable delivery of the instruction. After receiving the adjustment instruction, the on-vehicle control system of the sanitation vehicle will immediately adjust the corresponding actuators according to the parameter values in the instruction, including adjusting the output parameters of the motor controller, adjusting the working frequency of the fan frequency converter, adjusting the driving speed, etc., and return an execution confirmation message after the parameter adjustment is completed.

[0078] S207. Detect whether there are dynamic obstacles around the target sanitation vehicle.

[0079] A dynamic obstacle refers to an object moving within the operation area of a sanitation vehicle, including pedestrians, non-motor vehicles, motor vehicles, etc. The detection process relies on the sensor system installed on the sanitation vehicle, including various sensing devices such as lidar, millimeter-wave radar, and vision cameras. The area around the target sanitation vehicle refers to the safety monitoring area in front of, behind, to the left, and to the right of the sanitation vehicle.

[0080] The specific implementation process of this step is as follows: The on-vehicle sensor system continuously collects environmental data around the sanitation vehicle. The lidar measures the distance and contour features of obstacles by emitting laser light, with a scanning frequency of 10 Hz and a detection range of 0 - 100 meters within a 360-degree range. The millimeter-wave radar is mainly used to measure the relative speed of obstacles, with a detection range of 0 - 200 meters within a 150-degree range in front of the vehicle. The vision system uses six high-definition cameras around the vehicle for image acquisition, with a resolution of 1920×1080 and a frame rate of 30 fps. The raw data collected by the sensors is processed by the object detection algorithm of the on-vehicle processing unit to extract feature information such as the position, speed, and size of the obstacles, and classify and identify the types of obstacles.

[0081] S208. If it exists, obtain the motion data of the dynamic obstacle and determine whether the motion trajectory of the dynamic obstacle will cross the cleaning route.

[0082] The motion data of the dynamic obstacle includes information such as the position coordinates, moving speed, and motion direction of the obstacle. The motion trajectory is the moving path of the obstacle calculated based on the motion data, represented by a series of position coordinates corresponding to time points. The cleaning route is the preset working path of the sanitation vehicle, consisting of a sequence of path points. Trajectory crossing means that the two paths overlap or intersect in the spatio-temporal dimension.

[0083] The specific execution process of this step is as follows: The system obtains the real-time coordinates (x, y), velocity vector (vx, vy), and motion direction angle θ of the obstacle from the sensor data processing unit. Based on these data, use the uniform motion model to predict the sequence of motion trajectory points of the obstacle within the next 5 seconds: For the time point t, the predicted position coordinates are (x + vx×t, y + vy×t). Then compare the predicted trajectory point sequence with the cleaning route of the sanitation vehicle and calculate the minimum distance between the two paths. When the minimum distance is less than the safety threshold (such as 2 meters), it is determined that there is a trajectory crossing. At the same time, calculate the specific position coordinates of the crossing point and the predicted crossing time point.

[0084] S209. If a crossing will occur, calculate the predicted passing time of the dynamic obstacle based on the motion data.

[0085] The motion data includes kinematic parameters such as the current position, speed, and acceleration of the obstacle. The predicted passing time refers to the time period required for the obstacle to completely pass through the trajectory crossing area. The calculation process needs to consider the size and motion characteristics of the obstacle.

[0086] The execution process of this step is as follows: First, determine the range of the trajectory intersection area. Draw a circle with the intersection point as the center and a radius of 1.5 times the maximum size of the obstacle. The area covered by the circle is the intersection area. Calculate the distance S that the obstacle needs to travel from entering to completely leaving the intersection area. This distance is equal to the diameter of the intersection area plus the length of the obstacle itself. According to the current speed v of the obstacle and the distance d from the intersection area, use the uniform motion model to calculate the passing time: the time t1 to enter the intersection area is t1 = d / v, the time t2 to pass through the intersection area is t2 = S / v, and the total estimated passing time T = t1 + t2. Add a safety margin of 1 second to the calculation result as the final passing time.

[0087] If no intersection will occur, the sanitation vehicle continues the cleaning process.

[0088] S210. Send a waiting instruction containing the estimated passing time to the target sanitation vehicle.

[0089] The waiting instruction is a control command to control the sanitation vehicle to wait in place for the obstacle to pass. The estimated passing time is the time value required for the obstacle to completely leave the intersection area. The target sanitation vehicle refers to the driverless sanitation vehicle that needs to perform the waiting operation.

[0090] The execution process of this step is as follows: The system generates a waiting instruction containing information such as the waiting duration, waiting position, and recovery time based on the calculated estimated passing time. The waiting position is set to a safe parking point 2 meters in front of the current position of the sanitation vehicle to the intersection point. The instruction clearly specifies the start time point (current time) and end time point (current time + estimated passing time) of the waiting. Send the waiting instruction to the control unit of the target sanitation vehicle through the wireless communication network. After receiving the waiting instruction, the sanitation vehicle will perform the parking and waiting operation according to the specified position and time, and automatically resume the cleaning operation until the waiting time ends. The system continuously monitors the actual motion state of the obstacle during the waiting process to ensure the safety of the entire avoidance process.

[0091] S211. Obtain the weather forecast information within the operation area of the sanitation vehicle.

[0092] The operation area of the sanitation vehicle refers to the geographical range where the sanitation vehicle performs the cleaning task, usually a collection of one or more street areas. The weather forecast information includes meteorological data such as temperature, precipitation, precipitation probability, and precipitation period. The data source is the weather forecast interface of the meteorological department. The obtaining process uses the real-time data interface call method.

[0093] The execution process of this step is as follows: The system obtains the meteorological forecast data for the next 24 hours according to the geographical coordinate range (longitude and latitude) of the operation area through a preset meteorological data interface. The interface is called once per hour, and the obtained data includes: hourly precipitation (mm / h), precipitation probability (%), and precipitation period (start and end times). The system spatially distributes the obtained meteorological data according to the operation area grid (100m×100m) to establish a precipitation prediction map for the operation area. Each grid contains the precipitation prediction data for this location within the next 24 hours, which is used for subsequent adjustment of operation priorities.

[0094] S212. When there is rainy weather, set the garbage disposal priority coefficient of the predicted rainfall area to the highest priority.

[0095] Rainy weather refers to the weather condition where the predicted precipitation is greater than 0.1 mm / h. The predicted rainfall area refers to the geographical area where rainfall is predicted to occur within the next 24 hours. The garbage disposal priority coefficient is a numerical indicator measuring the urgency of area cleaning, with a value range of 0 - 100. The priority coefficient value corresponding to the highest priority is 100.

[0096] The specific execution process of this step is as follows: The system traverses all grids in the operation area and reads the precipitation prediction data of each grid. When the predicted precipitation within the next 24 hours of a certain grid is greater than 0.1 mm / h, mark this grid as a predicted rainfall area. For all grids in the predicted rainfall area, update their garbage disposal priority coefficient values to 100. The update calculation of the priority coefficient considers the urgency of the rainfall start time. For areas where the rainfall start time is relatively close to the current time (such as within 2 hours), an additional 10% urgency weight is added to the priority coefficient.

[0097] S213. Re-plan the cleaning route based on the set garbage disposal priority coefficient, and plan the predicted rainfall area as the priority cleaning area.

[0098] The garbage disposal priority coefficient is the priority value of each grid in the operation area. The priority cleaning area refers to the grid area with a priority coefficient value of 100. The cleaning route is the working path of the sanitation vehicle, which consists of a series of path point coordinates.

[0099] The execution process of this step is as follows: First, the system sorts all the grids in the operation area in descending order of the priority coefficient values, and takes the set of grids with a priority coefficient of 100 as the priority cleaning area. Based on the distribution positions of the priority cleaning areas, an improved A* algorithm is used to re-plan the cleaning route. The optimization goal of route planning is to complete the operations in the priority cleaning areas in the shortest time while ensuring the continuity and smoothness of the path. Specifically, first calculate the shortest paths from the current position to each priority cleaning area, and select the path sequence with the shortest total time consumption as the main route. Then, based on the main route, through local path adjustment, the grids with higher priorities in the surrounding areas are included in the cleaning scope to form a complete cleaning route.

[0100] The control system of the driverless sanitation vehicle in the embodiment of the present invention application will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the control system of the driverless sanitation vehicle in the embodiment of the present application.

[0101] It should be noted that Figure 3 the structure of the control system of the driverless sanitation vehicle shown is only an example, and should not bring any limitations to the functions and usage scopes of the embodiments of the present invention.

[0102] As Figure 3 shown, the control system of the driverless sanitation vehicle includes a central processing unit (Central Processing Unit, CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (Read-Only Memory, ROM) 302 or the program loaded from the storage part 308 into the random access memory (Random Access Memory, RAM) 303, such as executing the methods described in the above embodiments. In the RAM 303, various programs and data required for system operations are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. The input / output (Input / Output, I / O) interface 305 is also connected to the bus 304.

[0103] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0104] Specifically, according to an embodiment of the present invention, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are executed.

[0105] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, device, or component.

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings.

[0107] Specifically, the control system of the driverless sanitation vehicle in this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, it implements the control method of the driverless sanitation vehicle provided in the above embodiment.

[0108] On the other hand, the present invention also provides a computer-readable storage medium, which may be included in the control system of the driverless sanitation vehicle described in the above embodiment; or it may exist alone without being assembled into the control system of the driverless sanitation vehicle. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of the control system of the driverless sanitation vehicle, the control system of the driverless sanitation vehicle implements the control method of the driverless sanitation vehicle provided in the above embodiment.

[0109] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0110] As used in the above embodiments, depending on the context, the term "when..." may be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" may be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by relevant hardware instructed by a computer program. This program can be stored in a computer-readable storage medium. When this program is executed, it can include the processes of the above method embodiments. The aforementioned storage media include various media that can store program codes, such as ROM or random access memory RAM, magnetic disks, or optical discs.

Claims

1. A control method for an unmanned sanitation vehicle, characterized in that: Applied to the control system of an unmanned sanitation vehicle, the method comprises: Obtaining garbage characteristic information of target garbage within a preset distance around a target sanitation vehicle, wherein the garbage information includes garbage type, garbage quantity, garbage location, and garbage area information; The garbage information is stored in a garbage distribution map, wherein the garbage distribution map divides garbage areas into grids, and each grid contains garbage feature information in the garbage area; Calculate the regional garbage disposal difficulty value according to the garbage quantity, the garbage type and the garbage occupation area information; Obtaining the task progress parameters of the target sanitation vehicle, wherein the task progress parameters include the percentage of mileage cleaned, the percentage of remaining capacity in the garbage bin, and the completion progress of the current road section; Performing a weighted calculation on the task progress parameter and the regional garbage disposal difficulty value to obtain a garbage disposal priority coefficient; The cleaning route of the target sanitation vehicle is planned based on the garbage disposal priority coefficient and historical garbage distribution data.

2. The method according to claim 1, characterized in that The step of calculating the regional garbage disposal difficulty value according to the garbage quantity, the garbage type and the garbage occupation area information specifically includes: Calculate regional impact coefficients based on waste type and area occupied; Calculate the cleaning time coefficient based on the amount of garbage and the unit garbage disposal benchmark time; The regional impact coefficient and the cleaning time coefficient are weighted and calculated to obtain the regional garbage disposal difficulty value.

3. The method according to claim 1, characterized in that The step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority specifically includes: Dividing the garbage area into an immediate processing area, a delayed processing area and a regular cleaning area according to the garbage processing priority coefficient; Establish a spatiotemporal prediction model of regional garbage distribution based on historical garbage distribution data; Inputting the task progress parameter into the spatiotemporal prediction model to obtain garbage distribution prediction data, fusing the garbage distribution prediction data with the real-time garbage distribution map to obtain regional garbage accumulation trend information; A cleaning route is generated according to the distribution positions of the immediate processing area, the delayed processing area, the regular cleaning area and the regional garbage accumulation trend information, and the cleaning route preferentially covers the immediate processing area.

4. The method according to claim 1, characterized in that: After the step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority, the method further includes: Real-time monitoring of the cleaning status information of the target sanitation vehicle, wherein the cleaning status information includes cleaning effect parameters and equipment status parameters; When the cleaning effect parameter is lower than a preset cleaning quality threshold, determining the cleaning abnormality type according to a preset abnormality type determination rule; Obtaining a corresponding operation parameter adjustment plan from a preset parameter adjustment rule library according to the cleaning abnormality type; An adjustment instruction including the adjustment plan is sent to the target sanitation vehicle.

5. The method according to claim 1, characterized in that After the step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority, the method further includes: Detecting whether there are dynamic obstacles around the target sanitation vehicle; If so, obtaining the motion data of the dynamic obstacle and determining whether the motion trajectory of the dynamic obstacle intersects with the cleaning route; If an intersection will occur, the estimated passing time of the dynamic obstacle is calculated based on the motion data; A waiting instruction including the estimated passing time is sent to the target sanitation vehicle.

6. The method according to claim 1, characterized in that After the step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority, the method further includes: Obtain weather forecast information within the sanitation vehicle operation area; When there is rainfall, the garbage disposal priority coefficient of the predicted rainfall area is set to the highest priority; The cleaning route is replanned based on the set garbage disposal priority coefficient, and the predicted rainfall area is planned as a priority cleaning area.

7. The method according to claim 1, characterized in that After the step of determining the regional garbage disposal priority based on the task progress parameter, the regional garbage disposal difficulty value and the historical garbage distribution data, and planning the cleaning route of the target sanitation vehicle according to the regional garbage disposal priority, the method further includes: A cleaning instruction including the cleaning route is sent to the target sanitation vehicle.

8. An unmanned sanitation vehicle control system, characterized in that: The unmanned sanitation vehicle control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the unmanned sanitation vehicle control system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the unmanned sanitation vehicle control system, the unmanned sanitation vehicle control system executes the method as described in any one of claims 1-7.

10. A computer program product, characterized in that When the computer program product runs on an unmanned sanitation vehicle control system, the unmanned sanitation vehicle control system executes the method as described in any one of claims 1-7.

Images