An energy consumption optimization operation scheduling method for an unmanned sweeper

Abstract

The present application relates to the technical field of sweeper scheduling, and particularly relates to an energy consumption optimization operation scheduling method for unmanned sweeper; a current state variation degree is obtained according to the difference characteristics of the road section environment state parameters of the adjacent scheduling periods of the cleaning road section; a state energy consumption correlation degree is obtained according to the change correlation characteristics of the historical cleaning energy consumption and the historical road section environment state parameters of the cleaning road section; a state energy consumption variation influence degree is obtained according to the mutation characteristics of the road section environment state parameters and the mutation characteristics of the cleaning energy consumption of the cleaning road section; a state comprehensive influence degree is obtained according to the state energy consumption correlation degree and the state energy consumption variation influence degree; a trigger priority and a trigger level index are obtained according to the current state variation degree of the road section environment state parameters, the road section state correlation degree and the state comprehensive influence degree. The present application adaptively adjusts the scheduling of the cleaning task sequence of the sweeper according to the trigger level index, and improves the cleaning efficiency and the energy utilization rate of the sweeper.

Description

Technical Field

[0001] This invention relates to the field of sweeper scheduling technology, and specifically to an energy-optimized operation scheduling method for unmanned sweepers. Background Technology

[0002] Unmanned sweeping vehicles are increasingly being used in urban roads, industrial parks, and other scenarios to replace traditional manually driven sweeping vehicles for road cleaning and environmental maintenance. These vehicles typically use batteries as their primary power source, and their range and energy consumption directly impact the duration and overall efficiency of the cleaning operation. Therefore, it is necessary to reduce vehicle energy consumption through reasonable task allocation and route planning. Existing scheduling methods rely on historical data of preset areas or infrequently updated road segment information to minimize the total energy consumption of the unmanned sweeping vehicle throughout the entire operation while completing the predetermined cleaning tasks.

[0003] The unmanned sweeper operation scheduling system periodically updates the road environment status during operation and performs rolling optimization for future task windows. When events affecting sweeping energy consumption occur, it uses the existing Dijkstra algorithm to replan the sweeping path to minimize energy consumption. However, frequent planning updates lead to frequent path changes by the sweeper. As a low-speed, heavy-load device, the frequent turning, deceleration, and re-acceleration significantly increase the consumption of the drive system, making the actual additional energy consumption potentially higher than the theoretically optimized energy savings. Furthermore, frequent path adjustments increase the sweeper's ineffective empty driving distance and time, reducing sweeping efficiency. Therefore, frequent path adjustments during sweeping make it difficult to balance energy consumption and sweeping efficiency, reducing the rationality of path planning. Summary of the Invention

[0004] To address the aforementioned technical problems, the present invention aims to provide an energy-optimized operation scheduling method for unmanned sweeping vehicles, the specific technical solution of which is as follows: Obtain the cleaning energy consumption and environmental parameters of different road sections in the cleaning task sequence of the sweeper; The degree of change in the current state of the swept road segment is obtained based on the differences in the environmental state parameters of the road segment in adjacent scheduling cycles; the degree of correlation between state energy consumption and historical environmental state parameters of the swept road segment is obtained based on the correlation characteristics between these two factors; the impact of state energy consumption changes is obtained based on the abrupt changes in the environmental state parameters and energy consumption of the swept road segment; and the overall impact of the state is obtained based on the degree of correlation between state energy consumption and the impact of state energy consumption changes. The road segment status correlation degree is obtained based on the change correlation characteristics between road segment environmental status parameters of the same cleaning section; the trigger priority is obtained based on the current status change degree of the road segment environmental status parameters, the road segment status correlation degree, and the overall status influence degree; the trigger level index of the road segment environmental status parameters is obtained based on the difference characteristics of the trigger priority of all road segment environmental status parameters of the same cleaning section. The scheduling of the sweeper's sweeping task sequence is adaptively adjusted based on the trigger level index.

[0005] Furthermore, the step of obtaining the degree of change in the current state of the swept road segment based on the differences in the environmental state parameters of the road segment in adjacent scheduling cycles includes: In the formula This indicates the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment; This represents the value of the j-th type of road segment environmental state parameter for the i-th cleaning segment in the current scheduling cycle; This represents the value of the environmental state parameter of the j-th type of road segment for the i-th cleaning segment in the previous scheduling cycle adjacent to the current scheduling cycle; This represents the average absolute value of the difference between adjacent scheduling cycles of the i-th cleaning segment and the j-th type of road segment environmental state parameter within a preset historical time period.

[0006] Furthermore, the step of obtaining the degree of correlation between state energy consumption and historical environmental state parameters of the swept road section includes: Calculate the absolute value of the Pearson correlation coefficient between the sequence of road environmental state parameters and the sequence of cleaning energy consumption when cleaning the road section, and obtain the correlation degree; calculate the average value of the correlation degree of all cleaning of the road section within a preset historical period, and obtain the state-energy consumption correlation degree of the road environmental state parameters of the road section.

[0007] Furthermore, the step of obtaining the influence degree of state energy consumption change based on the abrupt change characteristics of the road segment environmental state parameters and the abrupt change characteristics of cleaning energy consumption includes: In the formula The state energy consumption change influence of the j-th environmental state parameter of the i-th cleaning segment is represented, and M represents the number of times the cleaning segment is cleaned within a preset historical time period. This represents the absolute value of the difference between the actual average cleaning energy consumption and the predicted average cleaning energy consumption for the i-th cleaning segment during the m-th cleaning cycle. It represents the absolute value of the difference between the actual change and the predicted change of the environmental state parameter sequence of the i-th road segment in the m-th cleaning session, where norm represents normalization.

[0008] Furthermore, the step of obtaining the overall state influence degree based on the state energy consumption correlation degree and the state energy consumption change influence degree includes: In the formula This represents the overall influence of the environmental state parameters of the j-th road segment in the i-th cleaning segment on the cleaning energy consumption. This indicates the degree of correlation between the environmental state parameters of the j-th type of road segment in the i-th cleaning segment and the state energy consumption of cleaning; This represents the degree of influence of the environmental state parameter of the j-th road segment in the i-th cleaning segment on the state energy consumption change of cleaning energy consumption.

[0009] Furthermore, the step of obtaining the road segment state correlation degree based on the change correlation characteristics between road segment environmental state parameters of the same cleaning section includes: Calculate the absolute value of the Pearson correlation coefficient between any two road segment environmental state parameter sequences when cleaning the road segment to obtain the degree of state correlation; calculate the average value of the degree of state correlation for all cleaning of the road segment within a preset historical period to obtain the degree of road segment state correlation between any two road segment environmental state parameters.

[0010] Furthermore, the step of obtaining the triggering priority based on the current state change degree of the road segment environmental state parameters, the road segment state correlation degree, and the overall state influence degree includes: In the formula This indicates the trigger priority of the j-th type of road segment environmental state parameter for the i-th cleaning segment. This represents the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment. Let H represent the overall impact of the j-th type of road segment environmental state parameter on the cleaning energy consumption of the i-th cleaning segment, and let H represent the number of other road segment environmental state parameters besides the j-th type. This represents the correlation degree between the j-th and h-th environmental state parameters of the i-th cleaning segment. This represents the overall influence of the h-th type of road segment environmental state parameters of the i-th cleaning segment on cleaning energy consumption.

[0011] Furthermore, the step of obtaining the trigger level index of the road segment environmental state parameters based on the difference in trigger priority characteristics of all road segment environmental state parameters of the same cleaning section includes: In the formula This represents the trigger level index for the j-th type of road segment environmental state parameter in the i-th cleaning segment. This indicates the trigger priority of the j-th type of road segment cleaning status parameter for the i-th cleaning segment. This represents the average trigger priority of all road segment environmental state parameters for the i-th cleaning segment, where norm represents normalization.

[0012] The present invention has the following beneficial effects: In this invention, obtaining the degree of change in the current state reflects whether the environmental state parameters of the sweeping section have changed in the current scheduling cycle and their impact on the scheduling of sweeping task sequences. Obtaining the degree of correlation between state and energy consumption reflects the long-term correlation between the environmental state parameters of the road segment and sweeping energy consumption; obtaining the degree of influence of state energy consumption changes reflects the degree of influence of the abrupt changes in the environmental state parameters of the road segment on the changes in sweeping energy consumption; obtaining the comprehensive influence of the state combines the degree of correlation and the degree of influence of state energy consumption changes to more accurately characterize the impact of the environmental influence parameters of the road segment on energy consumption changes. Obtaining the degree of correlation between road segment states characterizes the correlation characteristics between environmental state parameters of different road segments within the same sweeping section; obtaining the trigger priority comprehensively judges the necessity of changes in the environmental state parameters of the road segment for the scheduling of sweeping task sequences within the current scheduling cycle. Obtaining the trigger level index accurately determines whether changes in the environmental state parameters of the road segment require scheduling adjustments; finally, adaptive adjustments to the scheduling of the sweeping task sequence of the sweeper are made based on the trigger level index, which can improve the sweeping efficiency and energy utilization rate of the sweeper. Attached Figure Description

[0013] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 The flowchart illustrates an energy consumption optimization operation scheduling method for unmanned cleaning vehicles, as provided in one embodiment of the present invention. Detailed Implementation

[0015] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an energy-optimized operation scheduling method for unmanned sweeping vehicles proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0017] The following description, in conjunction with the accompanying drawings, details a specific scheme for an energy-optimized operation scheduling method for unmanned sweeping vehicles provided by the present invention.

[0018] Please see Figure 1 The diagram illustrates a flowchart of an energy-optimized operation scheduling method for unmanned cleaning vehicles according to an embodiment of the present invention. The method includes the following steps: Step S1: Obtain the cleaning energy consumption and environmental parameters of different road sections in the cleaning task sequence of the sweeper.

[0019] In this embodiment of the invention, the implementation scenario is to optimize the energy consumption of unmanned sweeping vehicle operation scheduling, improve the energy utilization efficiency and sweeping efficiency of the sweeping vehicle in dynamic operating environments, and increase the rationality of scheduling. First, the basic road data of the area to be swept is obtained, including road direction, road segment connection relationship and key nodes such as intersections and turning points. The entire sweeping area is abstracted into a road topology structure composed of multiple road segment nodes and connecting edges; each sweeping road segment is defined as a basic operation unit for subsequent scheduling and path planning.

[0020] Furthermore, for each cleaning section and unmanned sweeping vehicle, environmental parameters related to the cleaning process are collected, including: pedestrian congestion, reflecting the impact of pedestrian gathering on the passage and cleaning efficiency of the unmanned sweeping vehicle; pedestrians can be identified and counted using roadside cameras to calculate the pedestrian density per unit area of ​​the road section; the higher the pedestrian congestion, the more frequently the sweeping vehicle starts and stops in order to avoid pedestrians, the more obvious the problem of repeated and disorderly cleaning, and thus the higher the cleaning energy consumption. Traffic congestion, reflecting the vehicle passage efficiency of the road section; the average vehicle speed of the road section is obtained through road monitoring equipment, and the preset normal average speed and the current average speed are calculated; the lower the traffic congestion, the smoother the road, the smoother the cleaning process, and the lower the energy consumption. Obstacle occupancy rate reflects the extent to which temporary obstacles occupy the passable area of ​​the road. This is determined by roadside cameras, which identify the area occupied by obstacles such as stockpiled materials, stationary vehicles, and construction barriers. A higher obstacle occupancy rate means the sweeper is more likely to turn frequently in that section, resulting in more complex sweeping paths and consequently higher energy consumption. Road traffic fluctuation reflects the stability of traffic conditions in a road segment. This is determined by edge network analysis of vehicle speed changes per unit time, calculating the average speed change of all vehicles. Higher traffic fluctuation indicates more complex road conditions, leading to more frequent speed changes in the sweeper and increased energy consumption. Sweeping energy consumption is characterized by power consumption per unit time, representing the instantaneous power consumption of the sweeper during operation, calculated as the product of voltage and current. After data collection, all data types are normalized. The data update frequency is 10 seconds, with each 10-second period constituting a scheduling cycle, which can be determined by the implementer based on the implementation scenario.

[0021] Furthermore, road topology data, environmental parameters of the swept sections, and energy consumption data of the sweepers are uniformly organized to construct a comprehensive dataset for job scheduling. Based on the characteristics of road topology and energy consumption, several continuous swept sections are formed using the existing Dijkstra algorithm and assigned as scheduling task units to different unmanned sweepers. Each sweeper corresponds to a different sweeping task sequence. This sweeping task sequence is the job path with the lowest energy consumption under the road conditions at the time of preparation for sweeping. It should be noted that the Dijkstra algorithm is existing technology, and the specific steps are not described in detail.

[0022] Step S2: Obtain the degree of change in the current state of the sweeping section based on the differences in the environmental state parameters of the sweeping section in adjacent scheduling cycles; obtain the degree of correlation between state energy consumption and historical sweeping energy consumption and changes in historical environmental state parameters of the sweeping section; obtain the degree of influence of state energy consumption change based on the abrupt changes in the environmental state parameters and sweeping energy consumption of the sweeping section; obtain the comprehensive state influence based on the degree of correlation between state energy consumption and the degree of influence of state energy consumption change.

[0023] The operating environment of sweepers is dynamically changing, and they are affected by changes in road conditions during actual operations. The original scheduling plan may gradually deviate from the actual operating conditions. Therefore, it is necessary to collect vehicle and environmental status data in real time and perform rolling optimization based on future work sections to output updated task sequences. However, not all dynamic events require rescheduling. To avoid frequent and ineffective scheduling adjustments that lead to low sweeping efficiency and additional energy consumption, it is necessary to analyze the changes in sweeper status and road environment during operation to determine whether adjustments to the work schedule are needed. For each sweeping section within the area of ​​responsibility of a single sweeper, the dynamic changes of each data point are analyzed, combining road environment status parameters collected during actual operations. In actual operation, for example, if a certain cleaning section is a necessary passage for mass gatherings, its crowding level may suddenly increase. The sweeper's trajectory in this section may become repetitive and disorderly, and the cleaning time may lengthen, leading to increased energy consumption. At this time, the route planning may change; the sweeper may prioritize cleaning other sections and only resume cleaning when the current section returns to normal, thus saving energy. If the crowding level of the cleaning section in the current scheduling cycle differs significantly from historical periods, it indicates a significant change in the section's condition. Therefore, the degree of change in the current state can be obtained based on the differences in the environmental state parameters of the cleaning section in adjacent scheduling cycles. Preferably, in this embodiment of the invention, the step of obtaining the degree of change in the current state includes: , In the formula, This indicates the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment; This represents the value of the j-th type of road segment environmental state parameter for the i-th cleaning segment in the current scheduling cycle; This represents the value of the environmental state parameter of the j-th type of road segment for the i-th cleaning segment in the previous scheduling cycle adjacent to the current scheduling cycle; This represents the average absolute value of the differences between adjacent scheduling cycles of the i-th cleaning segment and the j-th segment's environmental state parameter within a preset historical time period. In this embodiment of the invention, the preset historical time period is the most recent week, which can be determined by the implementer according to the implementation scenario. It should be noted that the i-th cleaning segment is the cleaning segment of a future task in the cleaning task sequence of the sweeper vehicle. It represents the average value of the cleaning section under similar future task conditions in the past. The greater the change in the current state, the more significant the environmental change of that cleaning section in the current scheduling cycle, and the more likely scheduling adjustments will be needed.

[0024] Furthermore, when analyzing the impact of changes in the working environment and vehicle status on cleaning energy consumption, it is first necessary to determine whether the change has a significant impact on the established energy consumption optimization target. For example, if the traffic congestion of a certain cleaning section fluctuates slightly, although there is a change in status, the impact on the overall operation path and energy consumption is small. In this case, there is no need to adjust the original cleaning scheduling plan, reduce the ineffective movement of cleaning vehicles, and thus achieve a balance between energy consumption and cleaning efficiency. If there is a sudden increase in personnel congestion or an excessively high rate of road obstruction, the original low-energy cleaning operation plan will be directly changed and cleaning energy consumption will be significantly increased. It is necessary to trigger scheduling adjustments in a timely manner to ensure the overall energy consumption optimization effect. Therefore, to optimize the energy consumption of sweepers, it is necessary to focus on abnormal changes in road segment environmental state parameters that are strongly correlated with energy consumption changes. Then, based on the correlation characteristics between the historical sweeping energy consumption and the historical changes in road segment environmental state parameters, the degree of correlation between state and energy consumption is obtained. Preferably, in this embodiment of the invention, the step of obtaining the degree of correlation between state and energy consumption includes: calculating the absolute value of the Pearson correlation coefficient between the road segment environmental state parameter sequence and the sweeping energy consumption sequence when sweeping the road segment, to obtain the correlation; and calculating the average value of the correlations for all sweepings of the road segment within a preset historical period, to obtain the degree of correlation between the state and energy consumption of the road segment environmental state parameters. It should be noted that the Pearson correlation coefficient is existing technology, and the specific steps will not be elaborated further. The more correlated the changes in the two sequences, the larger the absolute value of the Pearson correlation coefficient. Therefore, the greater the correlation between the environmental state parameters of the sweeping section and the energy consumption, the stronger the correlation between the environmental state parameters and the sweeping energy consumption in the sweeping section, and the more attention needs to be paid to the environmental state parameters of the section during route planning and scheduling.

[0025] By comparing the energy consumption and abrupt changes in environmental parameters of different road sections during a preset historical period, it can be identified that abnormal changes in environmental parameters of certain road sections can significantly increase cleaning energy consumption. Therefore, the influence of changes in environmental parameters can be obtained based on the abrupt changes in environmental parameters and energy consumption of the road sections being cleaned. Preferably, in this embodiment of the invention, the step of obtaining the influence of changes in environmental parameters includes: , In the formula, The state energy consumption change influence of the j-th environmental state parameter of the i-th cleaning segment is represented, and M represents the number of times the cleaning segment is cleaned within a preset historical time period. This represents the absolute value of the difference between the actual average cleaning energy consumption and the predicted average cleaning energy consumption for the i-th cleaning segment during the m-th cleaning cycle. This represents the absolute value of the difference between the actual and predicted changes in the environmental state parameter sequence of the i-th sweeping segment during the m-th sweep. `norm` represents normalization, performed using the maximum-minimum method. Average energy consumption refers to the average value of the sweeping energy consumption sequence corresponding to one sweep of the sweeping segment. It is predicted using the existing ARIMA time series model based on historically collected average sweeping energy consumption of the sweeping segment. Similarly, it is predicted using the existing ARIMA time series model based on historically collected environmental state parameter sequences of the sweeping segment. The actual change rate is the average of the absolute values ​​of the differences between the environmental state parameters of adjacent segments in the actual environmental state parameter sequence, while the predicted change rate is the average of the absolute values ​​of the differences between the environmental state parameters of adjacent segments in the predicted environmental state parameter sequence. It can reflect the abrupt changes in energy consumption. The greater the difference between the predicted and actual values, the more obvious the abrupt changes in energy consumption. This value reflects the abrupt changes in road segment environmental parameters. A larger value indicates a more pronounced abrupt change in environmental conditions. The greater the degree of energy consumption change, and the more consistent the degree of energy consumption change with the change in road segment environmental parameters, the greater the impact of the corresponding change in energy consumption. This means that a sudden change in road segment environmental parameters is more likely to cause a significant change in cleaning energy consumption. Conversely, a smaller impact of the change in energy consumption means that a sudden change in road segment environmental parameters is less likely to cause a change in cleaning energy consumption.

[0026] Furthermore, analyzing the correlation between the environmental state parameters of each sweeping section and energy consumption only reflects the correlation characteristics of long-term or overall trends, but it cannot reflect the immediate impact on current energy consumption when a certain state parameter becomes significantly abnormal during actual operation. The influence of state energy consumption changes, however, characterizes the degree of additional energy consumption change that occurs when state parameters deviate from historical prediction levels. Therefore, based on the correlation characteristics, a larger influence of state energy consumption changes means a greater dynamic impact of the environmental state parameters of that sweeping section on energy consumption. Thus, a comprehensive state influence can be obtained based on the correlation degree and the influence of state energy consumption changes. Preferably, in this embodiment of the invention, the step of obtaining the comprehensive state influence includes: , In the formula, This represents the overall influence of the environmental state parameters of the j-th road segment in the i-th cleaning segment on the cleaning energy consumption. This indicates the degree of correlation between the environmental state parameters of the j-th type of road segment in the i-th cleaning segment and the state energy consumption of cleaning; This represents the degree of influence of the j-th environmental state parameter of the i-th cleaning segment on the state energy consumption change. The greater the degree of influence of the state energy consumption change, the more easily the dynamic changes of the environmental state parameter in that cleaning segment will affect the cleaning energy consumption.

[0027] Step S3: Obtain the road segment status correlation degree based on the change correlation characteristics between road segment environmental status parameters of the same cleaning section; obtain the trigger priority based on the current status change degree of the road segment environmental status parameters, the road segment status correlation degree, and the overall status influence degree; obtain the trigger level index of the road segment environmental status parameters based on the difference characteristics of the trigger priority of all road segment environmental status parameters of the same cleaning section.

[0028] The impact of road segment environmental state parameters on energy consumption is not isolated but interconnected and interactive. Changes in the environmental state parameters of one road segment can affect the environmental state parameters of other road segments, potentially leading to an additive effect on overall energy consumption. Firstly, the correlation degree of road segment states is obtained based on the correlation characteristics of changes in the environmental state parameters of the same road segment. Preferably, in this embodiment of the invention, the step of obtaining the correlation degree of road segment states includes: calculating the absolute value of the Pearson correlation coefficient between any two sequences of road segment environmental state parameters during cleaning of the road segment to obtain the degree of state correlation; calculating the average value of the degree of state correlation for all cleaning of the road segment within a preset historical period to obtain the correlation degree of road segment states between the two sequences of environmental state parameters. A higher correlation degree of road segment states means that the road conditions reflected by the two road segment environmental state parameters are more correlated, and therefore, the impact of the two on cleaning energy consumption is more likely to be additive.

[0029] Furthermore, when the degree of change in the current state of a certain road segment's environmental state parameter is greater, and it is more likely to affect cleaning energy consumption, while other road segment environmental state parameters related to this road segment's environmental state parameter also affect cleaning energy consumption, then the cleaning path should be scheduled more promptly to reduce cleaning energy consumption. Therefore, the trigger priority is obtained based on the degree of change in the current state of the road segment's environmental state parameter, the correlation between road segment states, and the comprehensive influence of the states; preferably, in this embodiment of the invention, the step of obtaining the trigger priority includes: , In the formula, This indicates the trigger priority of the j-th type of road segment environmental state parameter for the i-th cleaning segment. This represents the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment. Let H represent the overall impact of the j-th type of road segment environmental state parameter on the cleaning energy consumption of the i-th cleaning segment, and let H represent the number of other road segment environmental state parameters besides the j-th type. This represents the correlation degree between the j-th and h-th environmental state parameters of the i-th cleaning segment. This represents the overall influence of the h-th type of road segment environmental state parameter on the cleaning energy consumption of the i-th cleaning segment. The larger the value, the more correlated the environmental state parameter of the j-th road segment is with the environmental state parameters of other road segments. Furthermore, the environmental state parameters of these correlated road segments reflect road conditions that have a greater impact on cleaning energy consumption, thus requiring more attention to changes in the environmental state parameter of that road segment. Therefore, the more significant the change in the environmental state parameter of that road segment in the current scheduling cycle, and the greater its impact on energy consumption, the higher the trigger priority, and the more necessary it is to adjust the cleaning order of the road segment. Conversely, when the trigger priority is low, it means that the change in the environmental state parameter of that road segment is not significant and its impact on energy consumption is small. At the same time, the environmental state parameters of other correlated road segments also have a small impact on energy consumption. Therefore, even if there is a small energy consumption optimization, in order to balance cleaning efficiency and reduce ineffective scheduling time, a scheduling request may not be triggered.

[0030] After obtaining the trigger priorities of environmental state parameters for all road segments in the cleaning section, the relative importance of each parameter under the current operating conditions can be quantified by comparing the trigger priorities of environmental parameters for different road segments within the cleaning section. When the trigger priority of an environmental state parameter for a certain road segment is significantly higher than that of other road segment environmental state parameters, it indicates that its potential impact on cleaning energy consumption is greater, and the corresponding trigger level index should also be higher. Therefore, the trigger level index of the road segment environmental state parameters is obtained based on the differences in the trigger priorities of all road segment environmental state parameters in the same cleaning section. Preferably, in this embodiment of the invention, the step of obtaining the trigger level index includes: , In the formula, This represents the trigger level index for the j-th type of road segment environmental state parameter in the i-th cleaning segment. This indicates the trigger priority of the j-th type of road segment cleaning status parameter for the i-th cleaning segment. This represents the average trigger priority of all environmental state parameters for the i-th cleaning segment, where norm represents normalization, achieved through the maximum and minimum values. A higher trigger level indicates a greater need for cleaning planning and scheduling.

[0031] Step S4: Adaptively adjust the scheduling of the sweeper's sweeping task sequence based on the trigger level index.

[0032] After obtaining the trigger level index of the environmental state parameters of different road segments in the future cleaning route sequence of the sweeper, the scheduling of the sweeper's cleaning task sequence can be adaptively adjusted according to the trigger level index. Specifically, this includes: when the environmental state parameters of any road segment in any future cleaning route exceed a preset threshold, the scheduling adjustment of the cleaning task sequence is triggered, thereby ensuring that the overall cleaning energy consumption is lower after the road segment order is adjusted. In this embodiment of the invention, the preset threshold is 0.4, which can be determined by the implementer based on historical data statistics of the implementation scenario. When it does not exceed the preset threshold, it means that the impact of road condition changes on energy consumption is small, and no scheduling adjustment is required to improve cleaning efficiency and reduce ineffective energy consumption during scheduling. When it exceeds the preset threshold, it means that the road condition changes at this time will have a significant impact on energy consumption, and scheduling adjustment is required. When scheduling and adjusting the cleaning task sequence, the Dijkstra algorithm is used to recalculate the sweeper's path planning. The steps of the Dijkstra algorithm include: first, abstracting the cleaning area into a weighted directed graph, with road segment nodes as vertices and passable paths as edges, and constructing edge weights based on factors such as road segment length, road segment environmental state parameters, and cleaning energy consumption; then, starting from the current position of the unmanned sweeper and ending at the target cleaning segment or task node, the Dijkstra algorithm is used to progressively expand the shortest path set, calculating the minimum cumulative cost from the starting point to each node, and determining the optimal path while satisfying traffic constraints; finally, updating the vehicle's travel path based on the calculation results, enabling it to complete path adjustments with minimal additional energy consumption while avoiding obstacles or responding to new tasks, thereby ensuring operational efficiency and energy consumption optimization. This algorithm is existing technology, and the specific steps are not detailed here. Specific scheduling and adjustment methods can be further set by the implementer based on trigger level indicators, and are not limited here. Thus, by calculating the trigger level indicators of environmental state parameters of different road sections during the sweeping process, the sweeping operation scheduling was adaptively adjusted, thereby balancing and optimizing the overall sweeping efficiency and energy consumption of the sweeper.

[0033] In summary, this invention provides an energy-optimized operation scheduling method for unmanned sweeping vehicles. It obtains the degree of change in the current state of a sweeping segment based on the differences in environmental state parameters between adjacent scheduling cycles; it obtains the correlation between state energy consumption and historical environmental state parameter changes in the sweeping segment; it obtains the impact of state energy consumption changes based on the abrupt changes in environmental state parameters and energy consumption of the sweeping segment; it obtains the overall state impact based on the correlation between state energy consumption and the impact of state energy consumption changes; and it obtains trigger priority and trigger level indicators based on the degree of change in the current state of the environmental state parameters, the correlation between the road segment states, and the overall state impact. This invention adaptively adjusts the scheduling of the sweeping task sequence based on the trigger level indicators, improving the sweeping efficiency and energy utilization rate of the sweeping vehicle.

[0034] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0035] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for optimizing the operation scheduling of unmanned sweeping vehicles, characterized in that, The method includes the following steps: Obtain the cleaning energy consumption and environmental parameters of different road sections in the cleaning task sequence of the sweeper; The degree of change in the current state of the swept road segment is obtained based on the differences in the environmental state parameters of the road segment in adjacent scheduling cycles; the degree of correlation between state energy consumption and historical environmental state parameters of the swept road segment is obtained based on the correlation characteristics between these two factors; the impact of state energy consumption changes is obtained based on the abrupt changes in the environmental state parameters and energy consumption of the swept road segment; and the overall impact of the state is obtained based on the degree of correlation between state energy consumption and the impact of state energy consumption changes. The road segment status correlation degree is obtained based on the change correlation characteristics between road segment environmental status parameters of the same cleaning section; the trigger priority is obtained based on the current status change degree of the road segment environmental status parameters, the road segment status correlation degree, and the overall status influence degree; the trigger level index of the road segment environmental status parameters is obtained based on the difference characteristics of the trigger priority of all road segment environmental status parameters of the same cleaning section. The scheduling of the sweeper's sweeping task sequence is adaptively adjusted based on the trigger level index.

2. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the degree of change in the current state of the swept road section based on the differences in the environmental state parameters of the road section in adjacent scheduling cycles includes: In the formula This indicates the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment; This represents the value of the j-th type of road segment environmental state parameter for the i-th cleaning segment in the current scheduling cycle; This represents the value of the environmental state parameter of the j-th type of road segment for the i-th cleaning segment in the previous scheduling cycle adjacent to the current scheduling cycle; This represents the average absolute value of the difference between adjacent scheduling cycles of the i-th cleaning segment and the j-th type of road segment environmental state parameter within a preset historical time period.

3. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the correlation degree of state energy consumption based on the historical cleaning energy consumption and the historical environmental state parameters of the cleaning section includes: Calculate the absolute value of the Pearson correlation coefficient between the sequence of road environmental state parameters and the sequence of cleaning energy consumption when cleaning the road section, and obtain the correlation degree; calculate the average value of the correlation degree of all cleaning of the road section within a preset historical period, and obtain the state-energy consumption correlation degree of the road environmental state parameters of the road section.

4. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the influence of state energy consumption changes based on the abrupt change characteristics of the road segment environmental state parameters and the abrupt change characteristics of cleaning energy consumption of the cleaning segment includes: In the formula The state energy consumption change influence of the j-th environmental state parameter of the i-th cleaning segment is represented, and M represents the number of times the cleaning segment is cleaned within a preset historical time period. This represents the absolute value of the difference between the actual average cleaning energy consumption and the predicted average cleaning energy consumption for the i-th cleaning segment during the m-th cleaning cycle. It represents the absolute value of the difference between the actual change and the predicted change of the environmental state parameter sequence of the i-th road segment in the m-th cleaning session, where norm represents normalization.

5. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the overall state influence degree based on the state energy consumption correlation degree and the state energy consumption change influence degree includes: In the formula This represents the overall influence of the environmental state parameters of the j-th road segment in the i-th cleaning segment on the cleaning energy consumption. This indicates the degree of correlation between the environmental state parameters of the j-th type of road segment in the i-th cleaning segment and the state energy consumption of cleaning; This represents the degree of influence of the environmental state parameter of the j-th road segment in the i-th cleaning segment on the state energy consumption change of cleaning energy consumption.

6. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the road segment state correlation degree based on the change correlation characteristics between road segment environmental state parameters of the same cleaning section includes: Calculate the absolute value of the Pearson correlation coefficient between any two road segment environmental state parameter sequences when cleaning the road segment to obtain the degree of state correlation; calculate the average value of the degree of state correlation for all cleaning of the road segment within a preset historical period to obtain the degree of road segment state correlation between any two road segment environmental state parameters.

7. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the trigger priority based on the current state change degree of the road segment environmental state parameters, the road segment state correlation degree, and the overall state influence degree includes: In the formula This indicates the trigger priority of the j-th type of road segment environmental state parameter for the i-th cleaning segment. This represents the degree of change in the current state of the environmental state parameter of the j-th type of road segment in the i-th cleaning segment. Let H represent the overall impact of the j-th type of road segment environmental state parameter on the cleaning energy consumption of the i-th cleaning segment, and let H represent the number of other road segment environmental state parameters besides the j-th type. This represents the correlation degree between the j-th and h-th environmental state parameters of the i-th cleaning segment. This represents the overall influence of the h-th type of road segment environmental state parameters of the i-th cleaning segment on cleaning energy consumption.

8. The energy consumption optimization operation scheduling method for unmanned sweeping vehicles according to claim 1, characterized in that, The step of obtaining the trigger level index of the road segment environmental state parameters based on the difference in trigger priority of all road segment environmental state parameters of the same cleaning section includes: In the formula This represents the trigger level index for the j-th type of road segment environmental state parameter in the i-th cleaning segment. This indicates the trigger priority of the j-th type of road segment cleaning status parameter for the i-th cleaning segment. This represents the average trigger priority of all road segment environmental state parameters for the i-th cleaning segment, where norm represents normalization.

Images