Vehicle scheduling method and device and computer readable storage medium

Abstract

The invention relates to the technical field of vehicle management, in particular to a vehicle scheduling method and device and a computer readable storage medium. The vehicle scheduling method comprises the steps of determining a scheduling range of a plurality of vehicles according to real-time state information of the plurality of vehicles and information of scenes where the plurality of vehicles are located; determining a scheduling scheme of the plurality of vehicles according to the scheduling range of the plurality of vehicles and a plurality of scheduling targets of vehicle scheduling; and scheduling the plurality of vehicles according to the scheduling scheme.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle management technology, and in particular to a vehicle dispatching method and apparatus, a computer-readable storage medium, and a computer program product. Background Technology

[0002] As vehicle operations become increasingly systematic, vehicle system management is involved in many operational scenarios. Taking mining loading and unloading transportation as an example, managing the transportation vehicle system typically involves scheduling multiple vehicles within the system, such as vehicle grouping, vehicle routes, and vehicle speeds.

[0003] In related technologies, the operating routes, loading points, and unloading points of each vehicle are pre-set and relatively fixed under normal operating conditions. However, in the complex and ever-changing mining environment, this static grouping and speed distribution mode has limitations. In particular, when faced with dynamic interference factors such as sudden road congestion, short-term equipment failure, and abnormal queuing at loading points, it is difficult to make timely and effective scheduling responses, resulting in low operating efficiency of the entire vehicle transportation system. Summary of the Invention

[0004] In view of this, this disclosure provides a vehicle scheduling method and apparatus, a computer-readable storage medium, and a computer program product. First, by combining real-time vehicle status information with scenario information for vehicle scheduling, the schedulable range of each vehicle is determined. Then, within the schedulable range, multiple scheduling objectives are optimized to determine the optimal scheduling scheme and execute it. Through the above process, the decoupling and linkage between vehicle operation requirements and objective optimization can be achieved, enabling dynamic vehicle scheduling and improving the operational efficiency of the vehicle system.

[0005] According to one aspect of this disclosure, a vehicle dispatching method is provided, comprising: determining a dispatching range for the multiple vehicles based on real-time status information of multiple vehicles and information about the scene in which the multiple vehicles are located; determining a dispatching scheme for the multiple vehicles based on the dispatching range of the multiple vehicles and multiple dispatching targets for vehicle dispatching; and dispatching the multiple vehicles according to the dispatching scheme.

[0006] In some embodiments, determining the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles and the information of the scenario in which the multiple vehicles are located includes: determining the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles, the information of the scenario in which the multiple vehicles are located, and in combination with vehicle scheduling constraints, wherein the constraints include at least one of vehicle operation constraints, vehicle waiting time constraints, and vehicle task execution constraints.

[0007] In some embodiments, determining the scheduling scheme for the plurality of vehicles based on the scheduling range of the plurality of vehicles and the plurality of scheduling targets for vehicle scheduling includes: generating a target vector based on the plurality of scheduling targets, wherein each component of the target vector corresponds to a scheduling target; and determining the scheduling scheme for the plurality of vehicles based on the target vector within the scheduling range.

[0008] In some embodiments, within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector includes: determining a method for determining the scheduling scheme based on the complexity of the scenario in which the plurality of vehicles are located and / or the urgency of the vehicle scheduling, wherein the method for determining the scheduling scheme includes at least one of local search determination, rolling update, multi-objective heuristic determination, and historical data-assisted prediction; and within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector and using the method for determining the scheduling scheme.

[0009] In some embodiments, within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector includes: generating a plurality of candidate scheduling schemes within the scheduling range; and determining the scheduling scheme for the plurality of vehicles based on the target vector corresponding to each candidate scheduling scheme.

[0010] In some embodiments, determining the scheduling scheme for the plurality of vehicles based on the target vector corresponding to each candidate scheduling scheme and the scheduling range includes: performing a non-dominated sorting of the plurality of candidate scheduling schemes based on the target vector of each candidate scheduling scheme to determine the scheduling scheme for the plurality of vehicles.

[0011] In some embodiments, determining the scheduling scheme for the multiple vehicles by performing a non-dominated sorting of the multiple candidate scheduling schemes based on the target vectors of each candidate scheduling scheme includes: treating the multiple candidate scheduling schemes as a scheme population, performing a non-dominated sorting of the target vectors corresponding to the scheme population to determine multiple levels and target vectors within each level; updating the scheme population based on the multiple levels and the congestion degree of the target vectors within each level, where the congestion degree represents the difference between target vectors within the same level; and, if a termination condition is met, determining the scheduling scheme for the multiple vehicles based on the weights of the multiple scheduling targets among the candidate scheduling schemes corresponding to the target vector of the highest level.

[0012] In some embodiments, updating the scheme population based on the multiple levels and the crowding of candidate scheduling schemes within each level includes: performing at least one of elite selection, crossover selection, and mutation operations on the scheme population based on the multiple levels and the crowding of candidate scheduling schemes within each level to generate a offspring population; screening candidate scheduling schemes in the offspring population that meet the scheduling range; merging the scheme population and the screened offspring population to generate a joint population; performing a non-dominated sort on the joint population, and determining the candidate scheduling schemes ranked first by a specified number as the updated scheme population.

[0013] In some embodiments, the scheduling method further includes: after scheduling the plurality of vehicles, reacquiring the real-time status information of the plurality of vehicles and updating the scheduling range of the plurality of vehicles; determining whether to update the scheduling scheme of the plurality of vehicles based on the updated scheduling range; and if the scheduling scheme is updated, rescheduling the plurality of vehicles.

[0014] In some embodiments: the scenario in which the plurality of vehicles are located is a loading and unloading scenario; and / or the real-time status information includes at least one of the location, speed, and load status of the plurality of vehicles; the information of the scenario in which the plurality of vehicles are located includes at least one of the operation progress, idle status, and waiting time of the loading and unloading equipment at the loading and unloading point, the number of vehicles at the loading and unloading point, and the traffic status of the loading and unloading path; and / or the plurality of scheduling objectives include multiple of the following: shortest overall waiting time, lowest degree of operational imbalance, highest resource utilization, lowest energy consumption, shortest running time, and fastest completion of the specified task; and / or the scheduling scheme includes at least one of the loading and unloading tasks, departure time, loading and unloading path, and running speed of each of the plurality of vehicles.

[0015] According to a second aspect of this disclosure, a vehicle dispatching device is provided, comprising: a dispatching range determination module configured to determine the dispatching range of the multiple vehicles based on real-time status information of the multiple vehicles and information about the scene in which the multiple vehicles are located; a dispatching scheme determination module configured to determine a dispatching scheme for the multiple vehicles based on the dispatching range of the multiple vehicles and multiple dispatching targets for vehicle dispatching; and a dispatching module configured to dispatch the multiple vehicles according to the dispatching scheme.

[0016] According to a third aspect of this disclosure, a vehicle scheduling apparatus is provided, comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor being configured to perform a scheduling method as described in any embodiment of this disclosure based on a scheme stored in the at least one memory.

[0017] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores a computer scheme, which, when executed by a processor, implements a scheduling method as described in any embodiment of this disclosure.

[0018] According to a fifth aspect of this disclosure, a computer program product is provided that, when run on a computer, causes the computer to implement the scheduling method as described in any embodiment of this disclosure. Attached Figure Description

[0019] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0020] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein:

[0021] Figure 1 A flowchart illustrating a vehicle scheduling method according to some embodiments of the present disclosure is provided.

[0022] Figure 2 A flowchart illustrating the determination of a scheduling scheme according to some embodiments of the present disclosure is shown;

[0023] Figure 3 A flowchart illustrating the determination of a scheduling scheme by non-dominant sorting according to some embodiments of the present disclosure is shown;

[0024] Figure 4 A schematic diagram illustrating a vehicle dispatching process according to some embodiments of the present disclosure is shown;

[0025] Figure 5 A block diagram of a scheduling apparatus according to some embodiments of the present disclosure is shown;

[0026] Figure 6 A block diagram of a vehicle dispatching apparatus according to other embodiments of the present disclosure is shown;

[0027] Figure 7 This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.

[0028] It should be understood that the dimensions of the various parts shown in the accompanying drawings are not drawn to actual scale. Furthermore, the same or similar reference numerals denote the same or similar components. Detailed Implementation

[0029] Various embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The descriptions of the embodiments are merely illustrative and are in no way intended to limit the scope of the disclosure or its application or use. The present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully express the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specifically stated, the relative arrangement of components and steps set forth in these embodiments should be interpreted as merely illustrative and not as limiting.

[0030] The terms “first,” “second,” and similar words used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different parts. Words such as “including” mean that the element preceding the word covers the element listed after the word, and do not exclude the possibility of covering other elements as well.

[0031] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0032] All terms used in this disclosure (including technical or scientific terms) have the same meaning as understood by one of ordinary skill in the art to which this disclosure pertains, unless otherwise specifically defined. It should also be understood that terms defined in a general dictionary, such as a dictionary, should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or highly formalized meaning, unless expressly defined herein.

[0033] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0034] In traditional vehicle dispatching methods, the dispatching scheme is preset and relatively fixed under normal operating conditions. When faced with dynamic interference factors, it is impossible to make timely dispatching responses, resulting in low operational efficiency of vehicle dispatching.

[0035] In view of this, this disclosure proposes a vehicle scheduling method. First, by combining the real-time status information of vehicles with the scenario information of vehicle scheduling, the schedulable range of each vehicle is determined. Then, within the schedulable range, multiple scheduling objectives are optimized to determine the optimal scheduling scheme and execute it. Through the above process, the decoupling and linkage between vehicle operation requirements and objective optimization can be achieved, enabling dynamic vehicle scheduling and improving the operating efficiency of the vehicle system.

[0036] First, combined Figure 1 The vehicle scheduling method in this disclosure is described. Figure 1A flowchart illustrating a vehicle scheduling method according to some embodiments of the present disclosure is shown.

[0037] like Figure 1 As shown, the vehicle scheduling method may include: step S1, determining the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles and the information of the scene in which the multiple vehicles are located; step S2, determining the scheduling scheme of the multiple vehicles based on the scheduling range of the multiple vehicles and multiple scheduling targets of the vehicle scheduling; step S3, scheduling the multiple vehicles according to the scheduling scheme.

[0038] In step S1, the schedulable range of each vehicle can be determined first, which is the parameters that the vehicle can operate, such as the range of paths the vehicle can run on and the speed range.

[0039] The scenario in which the multiple vehicles are located could be, for example, a loading and unloading scenario. In a loading and unloading scenario, it is usually necessary to dispatch vehicles to travel back and forth between the loading point and the unloading point.

[0040] The information regarding the scenario in which the multiple vehicles are located includes at least one of the following: the operation progress, idle status, and waiting time of the loading and unloading equipment at the loading and unloading point; the number of vehicles at the loading and unloading point; and the traffic status of the loading and unloading route. The real-time status information of the multiple vehicles may include at least one of the following: the location, speed, and load status of the multiple vehicles.

[0041] The aforementioned information can be obtained, for example, from real-time status awareness modules deployed at task points and vehicles. These modules can be implemented in the form of devices such as Global Positioning System (GPS), Inertial Measurement Unit (IMU), and load sensors, and are used to collect information including vehicle position, speed, load status, train group affiliation, task point queuing status, and road capacity.

[0042] By acquiring vehicle status information and other information about the vehicle's environment, the system can promptly obtain the status of vehicles and task points within the system. This allows for the determination of appropriate scheduling plans for vehicles, thereby improving the overall operational efficiency of the system. For example, it can reduce vehicle waiting time at loading and unloading points and lower vehicle energy consumption.

[0043] In some embodiments, determining the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles and the information of the scenario in which the multiple vehicles are located includes: determining the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles, the information of the scenario in which the multiple vehicles are located, and in combination with vehicle scheduling constraints, wherein the constraints include at least one of vehicle operation constraints, vehicle waiting time constraints, and vehicle task execution constraints.

[0044] In the above embodiments, the above information can be combined with the constraints of vehicle scheduling to determine the feasible scheduling range of vehicles.

[0045] As an example, for each vehicle, a state vector can be created based on the vehicle's state information, where each component of the state vector corresponds to a type of state information. For instance, if the acquired vehicle state information includes the vehicle's position, speed, and load status, a three-dimensional state vector can be created. ,in, It can represent the position of vehicle i. It can represent the speed of vehicle i. It can characterize the load status of vehicle i.

[0046] After creating the state vector, the space in which the state vector is allowed to be located can be determined within the dimension of the state vector, based on the constraints of vehicle scheduling, such as rule restrictions in the transportation system, and thus serve as the scheduling range for the vehicle.

[0047] Constraints on vehicle operation may include, for example, vehicle avoidance rules, vehicle spacing rules, or vehicle speed rules.

[0048] Vehicle yielding rules refer to the ability for vehicles to have different priorities. When multiple vehicles arrive at a meeting point simultaneously, the vehicle with the higher priority is given priority. Vehicle priority can be determined by factors such as load status, whether it is going uphill, and whether it is in a special emergency situation. Different weights can be assigned to these factors, and the priority of each vehicle can be determined through a weighted average, making priority-based scheduling more aligned with the actual needs of the system.

[0049] Vehicle spacing rules refer to the requirement that the distance between vehicles during travel must exceed a certain threshold. For two vehicles traveling in the same direction, such as two vehicles performing the same loading and unloading task, the distance between them must be greater than a certain threshold. The spacing threshold can also be determined based on a basic safety distance and the speed difference between the two vehicles. The greater the speed difference, the larger the spacing threshold can be, thereby ensuring vehicle driving safety.

[0050] Vehicle speed rules stipulate that a vehicle's speed must be less than a maximum speed threshold. This maximum speed threshold can vary depending on the area the vehicle is in; different maximum speed thresholds can be set for different areas of the scene.

[0051] Constraints on vehicle waiting time can include, for example, vehicle waiting time control rules. Vehicle waiting time control rules refer to measures that can be taken to increase the priority of a vehicle or reassign it to other tasks if the waiting time of a vehicle exceeds the maximum waiting time threshold.

[0052] Constraints for vehicles performing tasks may include, for example, vehicle grouping consistency rules, vehicle grouping capacity rules, and task point queuing number rules.

[0053] The vehicle formation consistency rule means that all vehicles in the same formation should be heading to the same loading / unloading point. In other words, vehicle formation can be a combination of vehicles performing the same task or a combination of vehicles heading to the same loading / unloading point, thereby avoiding path conflicts.

[0054] Vehicle grouping capacity rules refer to situations where the number of vehicles in a group is less than a certain threshold. If the number of vehicles in the same group exceeds the threshold, a group reassignment can be triggered, thereby making the vehicle grouping in the system more rational.

[0055] The task point queuing rule refers to the number of vehicles queuing at a task point falling within a certain range. For example, if the number of vehicles queuing exceeds the maximum queue length threshold, scheduling intervention can be triggered to reduce the number of vehicles going to that task point. If the number of vehicles queuing is less than the maximum queue length threshold, other vehicles can be allowed to prioritize joining the task point.

[0056] The above scheduling rules can make the allocation of vehicles in the system more balanced and reasonable, thereby improving the system's operating efficiency.

[0057] Based on the above scheduling rules, for example, within the dimension of the state vector, determine the space in which the rule-allowed state vector can be located, as the scheduling range of the vehicle.

[0058] Referring to the example above where the state vector is a three-dimensional vector including position, speed, and load status, based on the scheduling rules in the system, the space in which the state vector can exist can be determined. For example, the space defined by the allowable range of position, speed, and load status can be used as the dispatchable range for vehicles. In other words, the scheduling instructions for vehicles must ensure that the state vector does not exceed its allowed space.

[0059] Furthermore, the overall state vector of the vehicle system can be generated based on the state information of each vehicle and the information of the scene, instead of generating state vectors for each vehicle separately. For the overall state vector of the system, its components can respectively represent the state information of each vehicle and the state information of the task points in the scene.

[0060] By generating a state vector for the entire system, the correlation between vehicles can be further reflected, enabling the overall scheduling of vehicles within the system and thus improving the system's operational efficiency.

[0061] The above text has elaborated on how to determine the dispatch range of vehicles. Below, we will return to... Figure 1Next, we will introduce how to determine the vehicle dispatching plan in step S2.

[0062] In step S2, based on the determined scheduling range and combined with multiple scheduling objectives of vehicle scheduling, multi-objective optimization can be performed within the scheduling range to determine the optimal vehicle scheduling scheme.

[0063] The multiple scheduling objectives may include, for example, the shortest overall waiting time for the multiple vehicles, the lowest degree of operational imbalance, the highest resource utilization, the lowest energy consumption, the shortest running time, and the fastest completion of the specified task.

[0064] The scheduling scheme may include, for example, at least one of the following for each of the plurality of vehicles: loading and unloading task, departure time, loading and unloading route, and running speed.

[0065] The scheduling objectives and scheduling schemes mentioned above can also correspond to each other. A scheduling scheme can be a set of scheduling instructions used to achieve a scheduling objective.

[0066] It should be understood that the scheduling objectives and scheduling schemes described above are merely exemplary and not restrictive. The scheduling method disclosed herein can also be used in systems with other scheduling objectives and scheduling schemes.

[0067] Below, we will combine Figure 2 This section will elaborate on how to perform multi-objective optimization. Figure 2 A flowchart illustrating the determination of a scheduling scheme according to some embodiments of the present disclosure is shown.

[0068] like Figure 2 As shown, step S2, determining the scheduling scheme for the multiple vehicles based on the scheduling range of the multiple vehicles and the multiple scheduling targets of the vehicle scheduling, may include: step S21, generating a target vector based on the multiple scheduling targets, wherein each component of the target vector corresponds to a scheduling target; step S22, determining the scheduling scheme for the multiple vehicles based on the target vector within the scheduling range.

[0069] In step S21, multiple scheduling objectives to be optimized can be integrated into a multi-dimensional objective vector, and each component of the objective vector can be used to represent a scheduling objective.

[0070] For example, when scheduling objectives include four goals: minimizing overall vehicle waiting time, minimizing operational imbalance, maximizing resource utilization, and minimizing energy consumption, a four-dimensional target vector can be created. The components of this target vector can be, for example, overall vehicle waiting time, vehicle idle rate, vehicle utilization rate, and total vehicle operating energy consumption, each representing one of the four scheduling objectives.

[0071] In step S22, multi-objective optimization can be performed based on the target vector within the scheduling range defined above.

[0072] In some embodiments, within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector may include: determining a method for determining the scheduling scheme based on the complexity of the scenario in which the plurality of vehicles are located and / or the urgency of the vehicle scheduling, wherein the method for determining the scheduling scheme includes at least one of local search determination, rolling update, multi-objective heuristic determination, and historical data-assisted prediction; within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector and using the method for determining the scheduling scheme.

[0073] Before performing multi-objective optimization, the optimization method of the objective vector can be determined based on the complexity of the scenario in which the vehicle is located and the urgency of vehicle dispatch.

[0074] Local search can determine the optimal point by starting from an initial sampling point and continuously exploring its neighboring sampling points. If a neighboring sampling point is better, the user moves to that sampling point, repeating this process until the optimal point is reached. Local search does not need to traverse all possible sampling points, making it computationally efficient and suitable for scenarios with low complexity or high urgency in vehicle scheduling.

[0075] Rolling updates can be implemented by setting a fixed-length time window, predicting future system behavior within the window based on the current state at each time step, and then solving the objective optimization problem within that window to determine the scheduling scheme. Rolling updates enable real-time iterative optimization in dynamic environments and can be used for dynamic scheduling situations where vehicle changes are frequent.

[0076] Multi-objective heuristics can be used to find a set of non-dominated optimal solutions in multi-objective optimization processes by simulating natural phenomena or group behaviors, such as ant colony foraging or flocks of birds / schools of fish cooperating. Multi-objective heuristics can optimize multiple conflicting metrics and can be used in scenarios with high complexity.

[0077] Historical data-assisted prediction can be achieved by using machine learning models to predict the future state of a vehicle system based on its historical data, thus supporting the determination of scheduling schemes. Historical data-assisted prediction can also provide support for optimization by simplifying the dimensions of complex systems through dimensionality reduction, and can be applied to scenarios with high complexity.

[0078] The above optimization methods are merely exemplary and not restrictive. Other optimization methods can also be used to determine the vehicle scheduling scheme based on the actual situation of the vehicle system.

[0079] After determining the optimization method, multi-objective optimization can be performed within the scheduling scope. Below, we will use a multi-objective heuristic optimization method as an example to illustrate the process of determining the scheduling scheme in some embodiments of this disclosure.

[0080] In some embodiments, within the scheduling range, determining the scheduling scheme for the plurality of vehicles based on the target vector may include: generating a plurality of candidate scheduling schemes within the scheduling range; and determining the scheduling scheme for the plurality of vehicles based on the target vector corresponding to each candidate scheduling scheme.

[0081] As mentioned earlier, the scheduling range refers to the permitted operating range of each vehicle. Within the vehicle's scheduling range, the feasible operational space of the vehicle system can be determined, which is the range of feasible scheduling schemes for the vehicles. Scheduling schemes within the feasible operational space will not cause vehicles to exceed their scheduling range.

[0082] Within the action space, multiple candidate scheduling schemes can be generated as multiple initial sampling points. The candidate scheduling schemes can be generated uniformly within the action space or randomly within the space.

[0083] The candidate scheduling scheme can include a scheme for each vehicle, such as the vehicle's task point allocation, target operating speed, departure sequence, and route number. Using these scheduling schemes, vehicles can be accurately scheduled, thereby achieving the aforementioned scheduling objectives.

[0084] After generating candidate scheduling schemes, the target vector corresponding to each candidate scheduling scheme can be calculated separately. For example, for a certain candidate scheduling scheme, the overall waiting time of the vehicles, the empty running rate of the vehicles, the utilization rate of the vehicles, and the total operating energy consumption of the vehicles can be determined based on the information such as the task, speed, and path of the vehicles after the candidate scheduling scheme is executed. These can be used as the target vector corresponding to the candidate scheduling scheme in order to determine the optimal scheduling scheme.

[0085] In some embodiments, determining the scheduling scheme for the plurality of vehicles based on the target vector corresponding to each candidate scheduling scheme and the scheduling range may include: performing a non-dominated sorting of the plurality of candidate scheduling schemes based on the target vector of each candidate scheduling scheme to determine the scheduling scheme for the plurality of vehicles.

[0086] In the above embodiments, after determining the target vector corresponding to each candidate scheduling scheme, it can be sorted in a non-dominated manner.

[0087] Non-dominated ranking refers to stratifying all candidate scheduling schemes based on the "dominance relationships" between target vectors. A "dominance relationship" refers to whether there exists a relationship between target vectors where one target vector is comprehensively superior to another. For example, if all components of target vector A are not inferior to target vector B, and at least one component of target vector A is superior to the corresponding component of target vector B, then target vector A dominates target vector B.

[0088] The specific process of non-dominated sorting could be, for example, to first traverse all target vectors and determine the dominated count and dominant set for each target vector. The dominated count refers to the number of other target vectors that dominate that target vector. The dominant set refers to the set of target vectors dominated by that target vector.

[0089] After determining the above information for each target vector, the target vector with the fewest dominated counts can be identified as the target vector of the first layer, which is the optimal layer. Furthermore, after determining the target vectors of the first layer, the dominated counts of the target vectors in the dominating set can be reduced by 1 based on the dominating set of the first-layer target vectors, and the target vectors of the second layer can be determined based on the dominated counts of the remaining target vectors.

[0090] The above process can be repeated until all target vectors are sorted hierarchically, which is a non-dominated sort.

[0091] After performing non-dominated sorting, for example, in the first-level target vector, the optimal target vector can be determined according to the weight relationship between multiple scheduling targets, and the candidate scheduling scheme corresponding to the target vector can be determined as the scheduling scheme for multiple vehicles in the vehicle system.

[0092] Furthermore, based on non-dominated sorting, we can first iteratively explore candidate scheduling schemes, and then determine the final scheduling scheme based on the non-dominated sorting results of the target vector after iteration. The following will combine... Figure 3 This section introduces how to iterate on candidate scheduling schemes. Figure 3 A flowchart illustrating a scheduling scheme determined by non-dominant sorting according to some embodiments of the present disclosure is shown.

[0093] like Figure 3As shown, determining the scheduling scheme for the multiple vehicles by performing non-dominated sorting on the multiple candidate scheduling schemes based on the target vectors of each candidate scheduling scheme may include: Step S221, taking the multiple candidate scheduling schemes as a scheme population, performing non-dominated sorting on the target vectors corresponding to the scheme population to determine multiple levels and the target vectors within each level; Step S222, updating the scheme population based on the congestion of the multiple levels and the target vectors within each level, where the congestion represents the difference between target vectors within the same level; Step S223, under the condition of satisfying the termination condition, determining the scheduling scheme for the multiple vehicles based on the weights of the multiple scheduling targets among the candidate scheduling schemes corresponding to the target vector of the highest level.

[0094] In step S221, the multiple candidate scheduling schemes generated within the scheduling range above can be used as the initial scheme population, and the target vectors corresponding to the initial scheme population can be sorted non-dominated as described above to determine the result of the non-dominated sorting.

[0095] In step S222, the scheme population can be iteratively updated based on the multiple levels of the target vector and the crowding degree of the target vector within each level.

[0096] The crowding degree of target vectors within each level refers to the "distance" between target vectors. At each component dimension, target vectors of the same level can be sorted, and the difference between a target vector and its sorted neighboring vectors at that component dimension is taken as the crowding degree of that target vector at that component dimension.

[0097] By combining the dimensions of each component, the overall crowding level of the target vector can be determined. The higher the crowding level of the target vector, the smaller the difference between it and other vectors. Conversely, the lower the crowding level of the target vector, the larger the difference between it and other vectors.

[0098] Based on the two parameters mentioned above, the target vector can be filtered, thereby iteratively updating the scheme population to conduct a more comprehensive exploration within the action space.

[0099] In some embodiments, updating the scheme population based on the multiple levels and the crowding of candidate scheduling schemes within each level may include: performing at least one of elite selection, crossover selection, and mutation operations on the scheme population based on the multiple levels and the crowding of candidate scheduling schemes within each level to generate a offspring population; screening candidate scheduling schemes in the offspring population that meet the scheduling range; merging the scheme population and the screened offspring population to generate a joint population; performing a non-dominated sort on the joint population, and determining the candidate scheduling schemes ranked first by a specified number as the updated scheme population.

[0100] In the above embodiments, elite selection refers to a selection strategy that prioritizes the retention of high-quality individuals in the population. For example, performing elite selection on the current population can select individuals with high non-dominated levels and reasonable crowding of the target vector to directly enter the next generation population. This ensures that high-quality scheduling schemes discovered during the iteration process are not eliminated, improving iteration convergence efficiency.

[0101] Crossover selection refers to the operation of simulating biological gene recombination. Performing crossover selection on a population can be done for example, by selecting a parent scheduling scheme in the population's scheduling scheme, exchanging a portion of the components according to preset rules, generating a offspring scheduling scheme with mixed characteristics of the parent, expanding the search range, and exploring better action options.

[0102] Mutation operations refer to random perturbation operations used to introduce new factors and prevent the iterative process from converging prematurely. Performing mutation operations on the population of schemes can, for example, randomly modify a portion of the scheduling schemes to generate offspring individuals that differ from their parents, thus preventing the iterative process from getting trapped in local optima and ensuring the comprehensiveness of the iterative exploration.

[0103] By using the rank and crowding of the target vector, the above operations can be performed on the scheme population, thereby improving the comprehensiveness and efficiency of iterative exploration.

[0104] After generating the iterative offspring population, we can first determine whether the scheduling schemes in the offspring population are within the scheduling range, such as whether they meet the vehicle scheduling constraints. For scheduling schemes that are not within the scheduling range, we can delete or add penalty terms to ensure that the scheduling schemes in the iterative process still meet the vehicle scheduling requirements.

[0105] Merging the parent population and the selected offspring population generates a joint population for the current iteration. Subsequently, the target vectors corresponding to the joint population are non-dominated, and a specified number of scheduling schemes at the top of the sort are determined as the result of this iteration, i.e., the updated scheme population. This improves the quality of the scheme population and ensures a sufficient number of scheduling schemes within it, preventing excessive computational overhead.

[0106] In step S223, if the iteration termination condition is met, the target vector corresponding to the scheme population after the update can be determined and non-dominated sorting can be performed.

[0107] The termination condition for an iteration can include, for example, reaching a predetermined number of iterations or the convergence of the population of the proposed solutions. By setting the termination condition described above, the iterative optimization process can be made more efficient.

[0108] Subsequently, based on the weight of the scheduling objectives, for example, by prioritizing the target vectors of the first layer, i.e. the optimal layer, the target vector of the preferred scheduling objective can be selected, and its corresponding scheduling scheme can be determined as the final scheduling scheme for multiple vehicles.

[0109] The process described above allows for a comprehensive iterative search within the action space to dynamically determine the optimal scheduling scheme for multiple vehicles in the vehicle system, thereby improving the system's operational efficiency.

[0110] The above text has elaborated on how to determine the scheduling scheme. Below, we will return to... Figure 1 Next, we will introduce how to dispatch vehicles in step S3.

[0111] In step S3, the scheduling execution module in the vehicle system can convert the optimization results into standard control commands and send them to each vehicle or scheduling terminal through the communication interface so as to execute the optimized scheduling scheme.

[0112] In some embodiments, the vehicle system can perform scheduling optimization again after the initial scheduling to achieve closed-loop control. Figure 4 A schematic diagram illustrating a vehicle dispatching process according to some embodiments of the present disclosure is shown.

[0113] like Figure 4 As shown, the scheduling method may further include: after scheduling the multiple vehicles, reacquiring the real-time status information of the multiple vehicles and updating the scheduling range of the multiple vehicles; determining whether to update the scheduling scheme of the multiple vehicles based on the updated scheduling range; and, if the scheduling scheme is updated, rescheduling the multiple vehicles.

[0114] In other words, after the scheduling plan is executed, the real-time status information of the vehicles can be retrieved again, and the optimal scheduling plan can be re-determined. If the scheduling plan changes, multiple vehicles in the vehicle system can be rescheduled according to the updated scheduling plan.

[0115] For example, after the scheduling plan is executed, the real-time status information of the vehicles can be obtained every 30 seconds, and the scheduling plan can be dynamically optimized to ensure that the system is always in a state of efficient operation and improve the operating efficiency of the vehicle system.

[0116] The above describes a vehicle scheduling method provided in this disclosure. This scheduling method first determines the schedulable range of each vehicle by combining real-time vehicle status information with scenario information. Then, within the schedulable range, it optimizes multiple scheduling objectives to determine and execute the optimal scheduling scheme. Through this process, the decoupling and linkage between vehicle operation requirements and objective optimization can be achieved, enabling dynamic vehicle scheduling and improving the operational efficiency of the vehicle system.

[0117] The following is for reference. Figure 5 and Figure 6 A vehicle dispatching apparatus according to an embodiment of the present disclosure is described, which is used to execute any of the embodiments of the control method described above. Figure 5 A block diagram of a scheduling apparatus according to some embodiments of the present disclosure is shown.

[0118] like Figure 5 As shown, the vehicle dispatching device 5 includes: a dispatching range determination module 51, configured to determine the dispatching range of the multiple vehicles based on the real-time status information of the multiple vehicles and the information of the scene in which the multiple vehicles are located; a dispatching scheme determination module 52, configured to determine the dispatching scheme of the multiple vehicles based on the dispatching range of the multiple vehicles and multiple dispatching targets of the vehicle dispatching; and a dispatching module 53, configured to dispatch the multiple vehicles according to the dispatching scheme.

[0119] The scheduling range determination module 51 of the scheduling device 5 can, for example, be used to perform... Figure 1 Step S1. The scheduling scheme determination module 52 of the scheduling device 5 can, for example, be used to perform... Figure 1 Step S2. The scheduling module 53 of the scheduling device 5 can, for example, be used to execute... Figure 1 Step S3.

[0120] The vehicle dispatching device disclosed herein first determines the dispatchable range of each vehicle by combining real-time vehicle status information with vehicle dispatching scenario information. Then, within the dispatchable range, it optimizes multiple dispatching objectives to determine and execute the optimal dispatching scheme. Through this process, it achieves decoupling and linkage between vehicle operation requirements and objective optimization, enabling dynamic vehicle dispatching and improving the operational efficiency of the vehicle system.

[0121] Figure 6 A block diagram of a vehicle dispatching apparatus according to other embodiments of the present disclosure is shown.

[0122] like Figure 6 As shown, the vehicle dispatching device 6 includes: at least one memory 61; and at least one processor 62 coupled to the at least one memory 61, the at least one processor 62 being configured to execute the control method as described in any of the foregoing embodiments based on instructions stored in the at least one memory 61.

[0123] Memory 61 is used to store one or more computer-readable instructions. Memory 61 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 61 may, for example, store operating systems, applications, bootloaders, databases, and other programs, as well as various applications and various data.

[0124] The processor 62 is configured to execute computer-readable instructions to implement the control method described in any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments, for example... Figures 1 to 3 The steps involved are repeated here, so the details will not be repeated.

[0125] The vehicle dispatching device disclosed herein first determines the dispatchable range of each vehicle by combining real-time vehicle status information with vehicle dispatching scenario information. Then, within the dispatchable range, it optimizes multiple dispatching objectives to determine and execute the optimal dispatching scheme. Through this process, it achieves decoupling and linkage between vehicle operation requirements and objective optimization, enabling dynamic vehicle dispatching and improving the operational efficiency of the vehicle system.

[0126] The processor 62 can be various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be based on x86 or ARM architectures, etc.

[0127] The processor 62 and the memory 61 can communicate with each other directly or indirectly. For example, the processor 62 and the memory 61 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. The processor 62 and the memory 61 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0128] It should be noted that Figure 6 The components of the vehicle dispatching device 6 shown are merely exemplary and not limiting. The vehicle dispatching device 6 may have other components depending on the specific application requirements. The processor 62 can control other components in the vehicle dispatching device 6 to perform desired functions.

[0129] The vehicle dispatching device 6 can be implemented by software, firmware and / or hardware, and can be integrated into a device with the relevant application installed.

[0130] Figure 7 This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.

[0131] like Figure 7 As shown, the computer system 7 can be represented in the form of a general computing device. The computer system 7 includes a memory 71, a processor 72, and a bus 70 connecting different system components.

[0132] The memory 71 can be various forms of computer-readable storage media, such as system memory, non-volatile storage media, etc. System memory may store, for example, an operating system, application programs, a bootloader, and other programs. System memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. Non-volatile storage media may store, for example, schemes for implementing corresponding embodiments of the vehicle scheduling method. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.

[0133] The processor 72 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Accordingly, each module can be implemented by a scheme in which the central processing unit (CPU) runs the memory to execute the corresponding steps, or by a dedicated circuit that executes the corresponding steps.

[0134] Bus 70 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.

[0135] The computer system 7 may also include an input / output interface 73, a network interface 74, and a storage interface 75. These interfaces 73, 74, and 75, as well as the memory 71 and processor 72, can be connected via a bus 70. The input / output interface 73 provides a connection interface for input / output devices such as a monitor, mouse, and keyboard. The network interface 74 provides a connection interface for various networked devices. The storage interface 75 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.

[0136] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to implement the vehicle scheduling method described in any of the foregoing embodiments. The computer program product includes a computer solution carried on a computer-readable medium, the computer solution containing program code for performing the methods shown in the flowcharts.

[0137] Various embodiments of this disclosure have now been described in detail. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art will fully understand how to implement the technical solutions disclosed herein based on the above description.

[0138] While specific embodiments of this disclosure have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments or equivalent substitutions can be made to some technical features without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A vehicle dispatching method, comprising: The scheduling range of the multiple vehicles is determined based on the real-time status information of the multiple vehicles and the information of the scene in which the multiple vehicles are located. Based on the scheduling range of the multiple vehicles and the multiple scheduling objectives of the vehicles, a scheduling plan for the multiple vehicles is determined; The multiple vehicles are dispatched according to the dispatching scheme.

2. The scheduling method according to claim 1, wherein, Based on the real-time status information of multiple vehicles and the information about the scenarios in which the multiple vehicles are located, the scheduling range of the multiple vehicles is determined to include: Based on the real-time status information of multiple vehicles, the information of the scenarios in which the multiple vehicles are located, and the constraints of vehicle scheduling, the scheduling range of the multiple vehicles is determined. The constraints include at least one of the following: constraints on vehicle operation, constraints on vehicle waiting time, and constraints on vehicle task execution.

3. The scheduling method according to claim 1, wherein, Based on the scheduling range of the multiple vehicles and the multiple scheduling targets of the vehicles, the scheduling scheme for the multiple vehicles is determined as follows: Based on the plurality of scheduling targets, a target vector is generated, wherein each component of the target vector corresponds to a scheduling target. Within the scheduling range, a scheduling scheme for the multiple vehicles is determined based on the target vector.

4. The scheduling method according to claim 3, wherein, Within the scheduling range, determining the scheduling scheme for the multiple vehicles based on the target vector includes: Based on the complexity of the scenarios in which the multiple vehicles are located and / or the urgency of the vehicle dispatch, the method for determining the dispatch scheme is determined, and the method includes at least one of local search determination, rolling update, multi-objective heuristic determination, and historical data-assisted prediction. Within the scheduling range, a scheduling scheme for the multiple vehicles is determined based on the target vector and using the determination method.

5. The scheduling method according to claim 3, wherein, Within the scheduling range, determining the scheduling scheme for the multiple vehicles based on the target vector includes: Within the specified scheduling range, multiple candidate scheduling schemes are generated; Based on the target vector corresponding to each candidate scheduling scheme, the scheduling scheme for the multiple vehicles is determined.

6. The scheduling method according to claim 5, wherein, Determining the scheduling scheme for the multiple vehicles based on the target vector corresponding to each candidate scheduling scheme and the scheduling range includes: Based on the target vector of each candidate scheduling scheme, the multiple candidate scheduling schemes are sorted in a non-dominated manner to determine the scheduling scheme for the multiple vehicles.

7. The scheduling method according to claim 6, wherein, Based on the target vectors of each candidate scheduling scheme, the multiple candidate scheduling schemes are non-dominated and sorted to determine the scheduling schemes for the multiple vehicles, including: The multiple candidate scheduling schemes are used as a scheme population. The target vectors corresponding to the scheme population are non-dominated and sorted to determine multiple levels and the target vectors within each level. The population of the scheme is updated based on the multiple levels and the crowding degree of the target vectors within each level, where the crowding degree represents the difference between target vectors within the same level. If the termination condition is met, a scheduling scheme for the multiple vehicles is determined based on the weights of the multiple scheduling targets from among the candidate scheduling schemes corresponding to the highest-level target vector.

8. The scheduling method according to claim 7, wherein, The update of the scheme population based on the multiple levels and the congestion of candidate scheduling schemes within each level includes: Based on the multiple levels and the crowding of candidate scheduling schemes within each level, at least one of elite selection, crossover selection, and mutation operations is performed on the scheme population to generate a offspring population; Candidate scheduling schemes that meet the scheduling range in the offspring population are screened; The population of the proposed scheme and the selected offspring population are merged to generate a joint population; The joint population is sorted non-dominated, and the candidate scheduling schemes that rank first by a specified number are determined as the updated scheme population.

9. The scheduling method according to claim 1, further comprising: After dispatching the multiple vehicles, the real-time status information of the multiple vehicles is retrieved again, and the dispatch range of the multiple vehicles is updated. Based on the updated scheduling range, determine whether to update the scheduling scheme for the multiple vehicles; If the scheduling scheme is updated, the multiple vehicles are rescheduled.

10. The scheduling method according to claim 1, wherein: The multiple vehicles are in a loading and unloading scenario; and / or The real-time status information includes at least one of the position, speed, and load status of the multiple vehicles. The information regarding the scenarios in which the multiple vehicles are located includes at least one of the following: the operation progress, idle status, and waiting time of the loading and unloading equipment at the loading and unloading point; the number of vehicles at the loading and unloading point; and / or the traffic status of the loading and unloading route. The multiple scheduling objectives include multiple factors such as the shortest overall waiting time for the vehicles, the lowest degree of operational imbalance, the highest resource utilization, the lowest energy consumption, the shortest running time, and the fastest completion of the designated task; and / or The scheduling scheme includes at least one of the following for each of the multiple vehicles: loading and unloading task, departure time, loading and unloading route, and running speed.

11. A vehicle dispatching device, comprising: The scheduling range determination module is configured to determine the scheduling range of the multiple vehicles based on the real-time status information of the multiple vehicles and the information of the scene in which the multiple vehicles are located. The scheduling scheme determination module is configured to determine the scheduling scheme for the multiple vehicles based on the scheduling range of the multiple vehicles and the multiple scheduling targets of the vehicle scheduling. The scheduling module is configured to schedule the multiple vehicles according to the scheduling scheme.

12. A vehicle dispatching device, comprising: At least one memory; as well as At least one processor coupled to the at least one memory, the at least one processor being configured to perform the scheduling method as described in any one of claims 1 to 10 based on a scheme stored in the at least one memory.

13. A computer-readable storage medium having a computer scheme stored thereon, which, when executed by a processor, implements the scheduling method as described in any one of claims 1 to 10.

14. A computer program product, when run on a computer, causes the computer to implement the scheduling method as described in any one of claims 1 to 10.

Images