Intelligent container truck collaborative scheduling method for port vehicle scheduling-regulation and control coupling

Abstract

The present invention relates to an intelligent container truck collaborative scheduling method for port area vehicle scheduling-regulation and control coupling, including: real-time monitoring of port area operation information; outputting the optimal operation sequence of intelligent container trucks based on the collected port area operation information and the comprehensive interests and needs of multiple parties; constructing a path adjustment algorithm, adjusting the intelligent container truck path considering the purpose of multi-vehicle collaboration, obtaining a conflict-free trajectory of the multi-vehicle system, and determining the point objects through which the container truck path's spatiotemporal characteristics pass; constructing a speed adjustment algorithm, optimizing the path output by the path adjustment algorithm, and optimizing the points through which the container truck path's spatiotemporal characteristics pass; the container truck executes actions according to the control instructions output by the speed adjustment algorithm, and feeds back the real-time status information of the container truck to the path adjustment algorithm and the speed adjustment algorithm, so as to realize the collaborative scheduling of intelligent container trucks. Compared with the prior art, the present invention improves the efficiency and safety of port area operations while ensuring the accuracy of container truck execution through the mutual coordination of macro task scheduling and micro container truck regulation and control.

Description

Technical Field

[0001] The present invention relates to the field of transportation technology, and in particular to an intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling. Background Art

[0002] As an important hub connecting maritime and inland transportation, ports play an important role in the transportation system. In recent years, the continuous growth of port container throughput and the rapid development of large-scale container ships have put forward higher requirements for the efficiency of loading and unloading operations at container terminals. With the continuous application of automation technology, the intelligence level of ports has been significantly improved, and the loading and unloading efficiency of container terminals has been greatly improved accordingly. As a key transportation tool for automated container terminals, smart container trucks undertake the main task of container loading and transportation. In the actual port operation environment, the necessity of efficient and stable operation of smart container trucks and reasonable coordinated scheduling between container trucks is also increasing.

[0003] The construction of V2X vehicle-road collaborative infrastructure in the port area realizes the interconnection of vehicles, roads, and operating equipment, and makes it possible to perceive the real-time holographic operation in the port area. At the same time, autonomous driving realizes the partial commercialization of closed port environments. The new transportation environment provides an opportunity to promote changes in port transportation management and solve practical problems. How to use the advantages of autonomous driving and vehicle-road networking to further improve the transportation efficiency of the port area is the focus of future development. The current intelligent container truck collaborative scheduling methods mainly focus on macro-overall task scheduling optimization or micro-vehicle regulation and control. The former mainly focuses on how to optimize the transportation efficiency of the entire port area through reasonable task allocation and resource scheduling, and the latter mainly considers multi-vehicle collaboration to reduce conflicts and improve the efficiency of the entire operation process by optimizing the execution process of a single operation.

[0004] Although the existing intelligent container truck collaborative scheduling methods can provide a reference for improving the scheduling effect of the port area, most of them do not take into account the execution capability of the container truck, and the scheduling decision is separated from the execution of the container truck. With the continuous improvement of the automation level of the port area, the dynamic and random operating environment faced by autonomous driving after landing in the port area has put forward higher requirements for the accuracy and robustness of the intelligent container truck scheduling method. However, the single task scheduling optimization cannot guarantee the execution of the scheduling plan and the safety of the operating environment. The single vehicle regulation and control method has a large amount of calculation and slow solution speed, and cannot optimize the overall efficiency and cost of the port area. Therefore, the existing methods are difficult to directly apply to the actual dynamically changing operating environment of the port area. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent container truck collaborative scheduling method for port vehicle scheduling-regulation and control coupling, connect task scheduling and vehicle regulation and control with spatiotemporal feature points, formulate a scheduling plan based on real-time operation information in the port area, and coordinate macro task scheduling with micro container truck regulation and control to improve transportation efficiency while considering the execution capability of container trucks to ensure the accuracy of container truck execution in the port area.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] An intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling includes the following steps:

[0008] S1. Port data collection: Investigate port operation information, clarify overall dispatching requirements, and monitor port operation information in real time;

[0009] S2. Task scheduling: Based on the collected port operation information and the interests and needs of multiple parties, the optimal operation sequence of smart container trucks is output;

[0010] S3, Path Adjustment: Based on the optimal operation sequence of the smart container truck, a path adjustment algorithm is constructed, and the path of the smart container truck is adjusted considering the purpose of multi-vehicle collaboration, so as to obtain a conflict-free trajectory of the multi-vehicle system and determine the point objects through which the spatiotemporal characteristics of the container truck path pass;

[0011] S4, speed adjustment: construct a speed adjustment algorithm, perform multi-vehicle coordinated speed adjustment, optimize the path output by the path adjustment algorithm, and obtain the points through which the space-time characteristics of the optimized container truck path are passed;

[0012] S5. Control instruction execution and feedback: The container truck executes actions according to the control instructions output by the speed adjustment algorithm, and feeds back the real-time status information of the container truck to the path adjustment algorithm and the speed adjustment algorithm to realize the coordinated scheduling of intelligent container trucks.

[0013] The step S1 specifically includes the following steps:

[0014] S11. Analyze the port area dispatching needs: Investigate the port area road network structure, traffic conditions, types and quantity of smart container trucks, types and quantity of operating equipment, and determine the port area dispatching goals;

[0015] S12. Real-time monitoring of port operation information: Dynamically collect the operating status of operating equipment and smart container trucks, as well as the operating information of each container and the loading and unloading information of vehicles.

[0016] The step S2 is specifically as follows: according to the real-time operation information of the port area, combined with the scheduling requirements of minimizing the idle time of the operating equipment, the waiting time of the smart container trucks, and the path conflicts between the smart container trucks, a task scheduling objective function is established, and task scheduling constraints are constructed to solve the optimal operation sequence of the smart container trucks.

[0017] The task scheduling objective function is:

[0018]

[0019]

[0020]

[0021] Among them, Q f is the type of operating equipment. If the operating equipment f is a rail crane, Q f =1, if the operating equipment f is a tire crane, Q f =0; is the sum of idle time of operating equipment f, is the total waiting time of unmanned transport container truck h, g l is the total number of times the container truck passes through the intersection node i of the port area road network; a, b, c are weight coefficients respectively;

[0022] The first term in the formula The second term is the sum of the idle time of the quay crane operation. represents the sum of the waiting time of all unmanned transport container trucks, the third term Represents the conflict index of unmanned transport container trucks in the road network;

[0023] Z fi When the equipment for loading and unloading operation i is f, Z fi =1, otherwise Z fi =0; represents the completion time of the operation equipment corresponding to the loading and unloading operation i; y ij Indicates that loading and unloading operation i is the direct predecessor task y of loading and unloading operation j ij =1, otherwise y ij =0; represents the start time of the operation equipment corresponding to the loading and unloading operation j; x hi If the loading and unloading operation i is carried out by unmanned container truck h, x hi =1, otherwise x hi =0; Indicates the moment when loading and unloading operation i enters the corresponding operating equipment.

[0024] The task scheduling constraints include loading and unloading logic constraints, time constraints, and vehicle load constraints, among which:

[0025] The loading and unloading logic constraints include: all loading and unloading operations are completed by intelligent container trucks, all loading and unloading operations have and only have one direct predecessor and direct successor operation, a loading and unloading operation itself cannot be its own direct predecessor or successor operation, and the first loading and unloading operation of the same container is before the second loading and unloading operation;

[0026] The time constraints include: both loading and unloading operations of the same container are completed by the same smart container truck, the time when the container arrives at the corresponding equipment, the time when the operating equipment starts working, the time when the operating equipment completes the operation, and the time when the container leaves the operating equipment is not less than 0;

[0027] The vehicle load constraint is specifically: a vehicle can only carry one 40-foot container or two 20-foot containers at most.

[0028] The path adjustment algorithm aims to minimize the change in the length of the vehicle's driving path before and after the path adjustment and minimize the increase in the number of conflicts with other nodes after the path adjustment. Its objective function is:

[0029]

[0030]

[0031]

[0032]

[0033] ΔL h =L′ h -L h

[0034] Among them, α1 is the weight of the excess load objective function of other road sections, α2 is the weight of the adjusted vehicle path objective function; R i is the conflict change caused by node i after path adjustment; ΔL h is the change in path length of vehicle h after path adjustment; after path adjustment, is the time when vehicle h arrives at node i, T h is the departure time of the vehicle, is a 0-1 variable. If vehicle h passes through node i L′ h is the path length of vehicle h after adjusting the path; e ij is the length of the road section ij; L min is the minimum safe distance; V is the expected speed of the vehicle; is a decision variable. When vehicle h passes through road section ij, otherwise

[0035] The constraints of the path adjustment algorithm are:

[0036] The path is continuous from the starting point o to the end point d. The mathematical expression of this constraint is:

[0037]

[0038]

[0039]

[0040] Among them, R′ ij Indicates the load status of each section in the road network after the path adjustment; R ij represents the vehicle load on the road section between intersections i and j; ΔR ij Indicates the overload value of other paths after adjustment; R max Indicates the maximum vehicle load on the road section.

[0041] The speed adjustment algorithm aims to minimize the average speed fluctuation between adjacent sections, the time it takes for the vehicle to reach the end of the planned path, and the minimum collision risk. Its objective function is:

[0042]

[0043] The first of these represents the fluctuation of the average speed of adjacent sections, and the second term Indicates the difference between the planned time and the actual time to complete the path;

[0044] In the formula, A represents the vehicle set, N a represents the set of nodes that vehicle a passes through, E a represents the set of road sections that vehicle a passes through, e ij Indicates road segment ij Length, and They represent the time when vehicle a arrives at the end of the path and the start of the path, respectively, and v ij is the average speed of the vehicle on road section ij.

[0045] The constraints of the speed adjustment algorithm include:

[0046] The average speed of each road section meets the speed limit requirement. The mathematical expression of this constraint is:

[0047]

[0048] Among them, v max For speed limit;

[0049] The time difference between the two vehicles arriving at the conflict node meets the safety requirement. The mathematical expression of this constraint is:

[0050]

[0051]

[0052] Among them, H conflict is the set of conflicting vehicles; N conflict is the set of conflict points, the common nodes of the paths of conflicting vehicles; L is the length of the vehicle; L s is the minimum safe distance between vehicles; β is the reduction coefficient. When calculating the time difference of the conflict point, the maximum speed is reduced by considering safety redundancy; is the node where vehicle h arrives moment; is the node where vehicle h′ arrives moment.

[0053] The step S5 comprises the following steps:

[0054] S51, control command execution: the container truck control unit receives the control command issued by the speed adjustment module in real time, and instructs the container truck to execute the action;

[0055] S52, intelligent container truck status information feedback: The running status of the container truck is collected in real time through the vehicle status detector, and fed back to the path adjustment algorithm and the speed adjustment algorithm to provide information for the next step of issuing vehicle control instructions, wherein the running status of the container truck includes the vehicle position, speed, and operation status.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] (1) The present invention realizes the bidirectional coupling of task scheduling and vehicle regulation and control, which improves the efficiency and safety of port operations while ensuring the accuracy of vehicle execution and formulating a scheduling plan that is more in line with the actual port operation needs.

[0058] (2) The present invention targets the highly dynamic characteristics of the actual port area autonomous driving environment, obtains port area operation information in real time to optimize task scheduling and improve transportation efficiency, and regulates and controls vehicles including path and speed adjustment to achieve multi-vehicle collaboration and reduce conflicts between vehicles.

[0059] (3) The present invention takes into account the vehicle execution capability, connects the scheduling plan with the vehicle execution by using spatiotemporal feature points, and maximizes the execution freedom of the vehicle while transmitting the scheduling information, thus solving the problem of the separation between scheduling decision and vehicle execution and greatly improving the accuracy of scheduling execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a flow chart of the method of the present invention;

[0061] Figure 2 Schematic diagram of an actual application scenario in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0063] This embodiment provides an intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling, such as Figure 1 As shown, it is applied to Figure 2 In the automated container port dispatching and command system shown in the figure, this method is applied to the intelligent container truck collaborative dispatching in the port area. The required operation information is collected in real time through the existing dispatching system in the port area, and the container tasks are reasonably allocated. The conflicts between container trucks are reduced by adjusting the path and speed, and the conflict-free trajectory and collaborative speed of the vehicles are planned. Finally, the vehicle executes the corresponding control instructions and the vehicle operating status is fed back in real time through the vehicle detector; in the entire intelligent collaborative dispatching process, task scheduling and vehicle regulation and control are bidirectionally coupled, and a dispatching plan that better meets the actual port operation needs is designed.

[0064] Specifically, the intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling includes the following steps:

[0065] S1. Port data collection: Investigate port operation information, clarify overall dispatch requirements, and monitor port operation information in real time.

[0066] S11. Analyze the dispatching needs of the port area: Investigate the road network structure, traffic conditions, types and quantity of smart container trucks, types and quantity of operating equipment in the port area, analyze the overall dispatching needs of the port area, and determine the dispatching goals of the port area;

[0067] S12. Real-time monitoring of port operation information: Dynamically collect the operating status of operating equipment and smart container trucks, as well as port operation information such as the operating information of each container and the loading and unloading information of vehicles.

[0068] S2. Task scheduling: Based on the collected port operation information and the interests of multiple parties, the optimal operation sequence of the smart container truck is output.

[0069] Specifically, based on the real-time operation information of the port area, combined with the scheduling requirements of minimizing the idle time of operating equipment, the waiting time of smart container trucks, and the path conflicts between smart container trucks, a task scheduling objective function is established, and task scheduling constraints are constructed to solve the optimal operation sequence of smart container trucks.

[0070] The task scheduling objective function is:

[0071]

[0072]

[0073]

[0074] Among them, Q f is the type of operating equipment. If the operating equipment f is a rail crane, Q f =1, if the operating equipment f is a tire crane, Q f =0; is the sum of idle time of operating equipment f, is the total waiting time of unmanned transport container truck h, g l is the total number of times the container truck passes through the intersection node i of the port area road network; a, b, c are weight coefficients respectively;

[0075] The first term in the formula The second term is the sum of the idle time of the quay crane operation. represents the sum of the waiting time of all unmanned transport container trucks, the third term Represents the conflict index of unmanned transport container trucks in the road network;

[0076] Z fi When the equipment for loading and unloading operation i is f, Z fi =1, otherwise Z fi =0; represents the completion time of the operation equipment corresponding to the loading and unloading operation i; y ij Indicates that loading and unloading operation i is the direct predecessor task y of loading and unloading operation j ij =1, otherwise y ij =0; represents the start time of the operation equipment corresponding to the loading and unloading operation j; x hi If the loading and unloading operation i is carried out by unmanned container truck h, x hi =1, otherwise x hi =0; Indicates the moment when loading and unloading operation i enters the corresponding operating equipment.

[0077] To ensure that the container scheduling model complies with the loading and unloading logic, the task scheduling constraints include loading and unloading logic constraints, time constraints, and vehicle load constraints.

[0078] ① Loading and unloading logic constraints

[0079] All loading and unloading operations are completed by intelligent container trucks. The mathematical expression of this constraint is:

[0080]

[0081] Among them, I is the set of loading and unloading operations, H is the set of container trucks, and x hi is a 0-1 variable. If vehicle h passes through node i

[0082] All loading and unloading operations have and only have one direct predecessor and direct successor operation. The mathematical expression of this constraint is:

[0083]

[0084] Among them, y ij is a decision variable, indicating that loading and unloading operation i is the direct predecessor task y of loading and unloading operation j ij =1, otherwise y ij =0; I0 is the virtual starting loading and unloading operation, and I1 is the virtual ending loading and unloading operation.

[0085] A loading and unloading operation cannot be its own direct predecessor or successor operation. The mathematical expression of this constraint is:

[0086]

[0087]

[0088] in, If loading and unloading operation i corresponds to the first operation of container c otherwise is the operation completion time of the operating equipment corresponding to the loading and unloading operation i; The time when the operating equipment corresponding to loading and unloading operation i starts operating.

[0089] The first loading and unloading operation of the same container is before the second loading and unloading operation. The mathematical expression of this constraint is:

[0090]

[0091] Among them, C is the set of containers waiting for operation.

[0092] ②Time constraints

[0093] The two loading and unloading operations of the same container are completed by the same intelligent container truck. The mathematical expression of this constraint is:

[0094]

[0095] in, The moment of entering the corresponding operating equipment for loading and unloading operation i; The time when loading and unloading operation i leaves the corresponding operating equipment; D ij is the length of road section ij; V represents the expected speed of the vehicle.

[0096] The time when the container arrives at the corresponding equipment, the time when the operating equipment starts working, the time when the operating equipment completes working, and the time when the container leaves the operating equipment are not less than 0. The mathematical expression of this constraint is:

[0097]

[0098]

[0099]

[0100]

[0101]

[0102]

[0103]

[0104] Among them, Z fj If the equipment for loading and unloading operation j is f, Z fj =1, otherwise Z fj =0. The moment when the loading and unloading operation i enters the corresponding operating equipment; Z f The time required for port operating equipment to complete a container loading and unloading operation.

[0105] ③Vehicle load constraints

[0106] A vehicle can only carry one 40-foot container or two 20-foot containers at most. The mathematical expression of this constraint is:

[0107]

[0108]

[0109] Among them, R i1 is the change in vehicle load caused by a 40-foot container during loading and unloading operation i, R i2 is the vehicle load change caused by the 20-foot container in loading and unloading operation i; Q is the maximum transport capacity of the transport vehicle.

[0110] S3. Path adjustment: According to the optimal operation sequence of the smart container truck, a path adjustment algorithm is constructed. Based on the shortest path of the multi-vehicle system and the minimum vehicle conflict requirements, the path of the smart container truck is adjusted for the purpose of multi-vehicle collaboration, and a conflict-free trajectory of the multi-vehicle system is obtained. The spatiotemporal characteristics of the container truck path are determined through point objects.

[0111] The path adjustment algorithm aims to minimize the change in the length of the vehicle's driving path before and after the path adjustment and minimize the increase in the number of conflicts with other nodes after the path adjustment. Its objective function is:

[0112]

[0113]

[0114]

[0115]

[0116] ΔL h =L′ h -L h

[0117] Among them, α1 is the weight of the excess load objective function of other road sections, α2 is the weight of the adjusted vehicle path objective function; R i is the conflict change caused by node i after path adjustment; ΔL h is the change in path length of vehicle h after path adjustment; after path adjustment, is the time when vehicle h arrives at node i, T h is the departure time of the vehicle, is a 0-1 variable. If vehicle h passes through node i L′ h is the path length of vehicle h after adjusting the path; e ij is the length of the road section ij; L min is the minimum safe distance; V is the expected speed of the vehicle; is a decision variable. When vehicle h passes through road section ij, otherwise The conflicting vehicle path adjustment should meet the two goals of minimizing the impact on other vehicles and minimizing the change in path length before and after the adjustment for the conflicting vehicle. i is the increase in load on other paths after the first item in the objective function is adjusted, ΔL h The second term in the objective function is adjusted for the increase in vehicle paths.

[0118] In order to ensure the continuity of the route, the constraints on the local route adjustment of the smart container truck are as follows:

[0119] The path is continuous from the starting point o to the end point d. The mathematical expression of this constraint is:

[0120]

[0121]

[0122]

[0123] Among them, R′ ij Indicates the load status of each section in the road network after the path adjustment; R ij represents the vehicle load on the road section between intersections i and j; ΔR ijIndicates the overload value of other paths after adjustment; R max Indicates the maximum vehicle load on the road section.

[0124] S4. Speed ​​adjustment: Construct a speed adjustment algorithm to make more precise adjustments to the speed of multiple vehicles in coordination based on the requirements of minimizing speed fluctuations, minimizing the time it takes for vehicles to reach the end of the planned path, and minimizing the risk of collision. Optimize the path output by the path adjustment algorithm to obtain the points through which the spatiotemporal characteristics of the optimized container truck path are passed.

[0125] The speed adjustment algorithm aims to minimize the fluctuation of average speed between adjacent sections, minimize the time it takes for vehicles to reach the end of the planned path, and minimize the risk of collision. Its objective function is:

[0126]

[0127] The first of these represents the fluctuation of the average speed of adjacent sections, and the second term Indicates the difference between the planned time and the actual time to complete the path;

[0128] In the formula, A represents the vehicle set, N a represents the set of nodes that vehicle a passes through, E a represents the set of road sections that vehicle a passes through, e ij represents the length of the road segment ij, and They represent the time when vehicle a arrives at the end of the path and the start of the path, respectively, and v ij is the average speed of the vehicle on road section ij.

[0129] In order to meet the speed limit requirements and safety needs, the constraints on the coordinated speed planning of smart container trucks are as follows:

[0130] The average speed of each road section meets the speed limit requirement. The mathematical expression of this constraint is:

[0131]

[0132] Among them, v max For speed limit;

[0133] The time difference between the two vehicles arriving at the conflict node meets the safety requirement. The mathematical expression of this constraint is:

[0134]

[0135]

[0136] Among them, H conflict is the set of conflicting vehicles; N conflictis the set of conflict points, the common nodes of the paths of conflicting vehicles; L is the length of the vehicle; L s is the minimum safe distance between vehicles; β is the reduction coefficient. When calculating the time difference of the conflict point, the maximum speed is reduced by considering safety redundancy; is the node where vehicle h arrives moment; is the node where vehicle h′ arrives moment.

[0137] S5. Control instruction execution and feedback: The container truck executes actions according to the control instructions output by the speed adjustment algorithm, and feeds back the real-time status information of the container truck to the path adjustment algorithm and the speed adjustment algorithm to realize the coordinated scheduling of intelligent container trucks.

[0138] S51, control command execution: the container truck control unit receives the control command issued by the speed adjustment module in real time, and instructs the container truck to execute the action;

[0139] S52, intelligent container truck status information feedback: through the vehicle status detector, the operating status of the container truck (including vehicle position, speed, operation status, etc.) is collected in real time, and fed back to the path adjustment algorithm and the speed adjustment algorithm to provide information for the next step of issuing vehicle control instructions.

[0140] The method adopted in this embodiment is not limited to optimizing task scheduling objectives or only considering multi-vehicle path coordination to reduce conflicts. Instead, it coordinates macro task scheduling with micro vehicle regulation and control to improve port operation efficiency and safety while ensuring the accuracy of vehicle execution, and formulates a scheduling plan that is more in line with the actual application needs of port operations.

[0141] According to the above method, this embodiment also provides an intelligent container truck collaborative scheduling system for port vehicle scheduling-regulation and control coupling, including a port data acquisition module, a task scheduling module, a path adjustment module, a speed adjustment module, and an intelligent container truck terminal module, wherein the port data acquisition module is used to collect port operation information in real time and clarify the overall scheduling requirements. The task scheduling module is used to combine container operation information and port operation equipment conditions, and comprehensively integrate the interests of multiple parties to output the optimal operation sequence of the intelligent container truck to the path adjustment module. The path adjustment module considers the purpose of multi-vehicle collaboration to adjust the intelligent container truck path, obtains a conflict-free trajectory of the multi-vehicle system, and determines the time-space feature point object of the vehicle path. The speed adjustment module performs more accurate multi-vehicle collaborative speed adjustment, determines the arrival time of the time-space feature point of the container truck path, and the intelligent container truck terminal module receives the control instructions issued by the speed adjustment module in real time, and feeds back the real-time status information of the intelligent container truck to the path adjustment module and the speed adjustment module. In this way, the two-way coupling of task scheduling and vehicle regulation and control is realized, while improving the efficiency and safety of port operations and ensuring the accuracy of vehicle execution.

[0142] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning, or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. An intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling, characterized in that: The following steps are involved: S1. Port data collection: Investigate port operation information, clarify overall dispatching requirements, and monitor port operation information in real time; S2. Task scheduling: Based on the collected port operation information and the interests and needs of multiple parties, the optimal operation sequence of smart container trucks is output; S3, Path Adjustment: Based on the optimal operation sequence of the smart container truck, a path adjustment algorithm is constructed, and the path of the smart container truck is adjusted considering the purpose of multi-vehicle collaboration, so as to obtain a conflict-free trajectory of the multi-vehicle system and determine the point objects through which the spatiotemporal characteristics of the container truck path pass; S4, speed adjustment: construct a speed adjustment algorithm, perform multi-vehicle coordinated speed adjustment, optimize the path output by the path adjustment algorithm, and obtain the points through which the space-time characteristics of the optimized container truck path are passed; S5, control command execution and feedback: The container truck executes actions according to the control command output by the speed adjustment algorithm, and feeds back the real-time status information of the container truck to the path adjustment algorithm and the speed adjustment algorithm to realize the coordinated dispatch of intelligent container trucks; The step S1 specifically includes the following steps: S11. Analyze the port area dispatching needs: Investigate the port area road network structure, traffic conditions, types and quantity of smart container trucks, types and quantity of operating equipment, and determine the port area dispatching goals; S12. Real-time monitoring of port operation information: Dynamically collect the operating status of operating equipment and smart container trucks, as well as the operating information of each container and the loading and unloading information of vehicles; The step S2 specifically includes: establishing a task scheduling objective function and constructing task scheduling constraints according to the real-time operation information of the port area, combining the scheduling requirements of minimizing the idle time of the operation equipment, the waiting time of the smart container truck, and the path conflicts between the smart container trucks, and solving to obtain the optimal operation sequence of the smart container truck; The task scheduling objective function is: Among them, Q f is the type of operating equipment. If the operating equipment f is a rail crane, Q f =1, if the operating equipment f is a tire crane, Q f =0; is the sum of idle time of operating equipment f, is the total waiting time of unmanned transport container truck h, g i is the total number of times the container truck passes through the intersection node i of the port area road network; a, b, c are weight coefficients respectively; The first term in the formula The second term is the sum of the idle time of the quay crane operation. represents the sum of the waiting time of all unmanned transport container trucks, the third term Represents the conflict index of unmanned transport container trucks in the road network; Z fp When the equipment for loading and unloading operation p is f, Z fp =1, otherwise Z fp =0; represents the completion time of the operation equipment corresponding to the loading and unloading operation p; y pq Indicates that loading and unloading operation p is the direct predecessor task y of loading and unloading operation q pq =1, otherwise y pq =0; represents the start time of the operation equipment corresponding to the loading and unloading operation q; x hp If the loading and unloading operation p is transported by an unmanned container truck h hp =1, otherwise x hp =0; Indicates the moment when the loading and unloading operation p enters the corresponding operating equipment.

2. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 1 is characterized in that: The task scheduling constraints include loading and unloading logic constraints, time constraints, and vehicle load constraints, among which: The loading and unloading logic constraints include: all loading and unloading operations are completed by intelligent container trucks, all loading and unloading operations have and only have one direct predecessor and direct successor operation, a loading and unloading operation itself cannot be its own direct predecessor or successor operation, and the first loading and unloading operation of the same container is before the second loading and unloading operation; The time constraints include: both loading and unloading operations of the same container are completed by the same smart container truck, the time when the container arrives at the corresponding equipment, the time when the operating equipment starts working, the time when the operating equipment completes the operation, and the time when the container leaves the operating equipment is not less than 0; The vehicle load constraint is specifically: a vehicle can only carry one 40-foot container or two 20-foot containers at most.

3. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 1 is characterized in that: The path adjustment algorithm aims to minimize the change in the length of the vehicle's driving path before and after the path adjustment and minimize the increase in the number of conflicts with other nodes after the path adjustment. Its objective function is: Among them, α1 is the weight of the excess load objective function of other road sections, α2 is the weight of the adjusted vehicle path objective function; R i is the conflict change caused by node i after path adjustment; ΔL h is the change in path length of vehicle h after path adjustment; after path adjustment, is the time when vehicle h arrives at node i, T h is the departure time of the vehicle, is a 0-1 variable. If vehicle h passes through node i L′ h is the path length of vehicle h after adjusting the path; e ij is the length of the road section ij; L min is the minimum safe distance; V is the expected speed of the vehicle; is a decision variable. When vehicle h passes through road section ij, otherwise 4. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 3 is characterized in that: The constraints of the path adjustment algorithm are: The path is continuous from the starting point o to the end point d. The mathematical expression of this constraint is: Among them, R′ ij Indicates the load status of each section in the road network after the path adjustment; R ij represents the vehicle load on the road section between intersections i and j; ΔR ij Indicates the overload value of other paths after adjustment; R max Indicates the maximum vehicle load on the road section.

5. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 1 is characterized in that: The speed adjustment algorithm aims to minimize the average speed fluctuation between adjacent sections, the time it takes for the vehicle to reach the end of the planned path, and the minimum collision risk. Its objective function is: The first of these represents the fluctuation of the average speed of adjacent sections, and the second term Indicates the difference between the planned time and the actual time to complete the path; In the formula, A represents the vehicle set, N a represents the set of nodes that vehicle a passes through, E a represents the set of road sections that vehicle a passes through, e ij represents the length of the road segment ij, and They represent the time when vehicle a arrives at the end of the path and the start of the path, respectively, and v ij is the average speed of the vehicle on road section ij.

6. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 5 is characterized in that: The constraints of the speed adjustment algorithm include: The average speed of each road section meets the speed limit requirement. The mathematical expression of this constraint is: Among them, v max For speed limit; The time difference between the two vehicles arriving at the conflict node meets the safety requirement. The mathematical expression of this constraint is: Among them, H conflict is the set of conflicting vehicles; N conflict is the set of conflict points, the common nodes of the paths of conflicting vehicles; L is the length of the vehicle; L s is the minimum safe distance between vehicles; β is the reduction coefficient. When calculating the time difference of the conflict point, the maximum speed is reduced by considering safety redundancy; is the node where vehicle h arrives moment; is the node where vehicle h′ arrives moment.

7. The intelligent container truck collaborative dispatching method for port vehicle dispatching-regulation and control coupling according to claim 1 is characterized in that: The step S5 comprises the following steps: S51, control command execution: the container truck control unit receives the control command issued by the speed adjustment module in real time, and instructs the container truck to execute the action; S52, intelligent container truck status information feedback: The running status of the container truck is collected in real time through the vehicle status detector, and fed back to the path adjustment algorithm and the speed adjustment algorithm to provide information for the next step of issuing vehicle control instructions, wherein the running status of the container truck includes the vehicle position, speed, and operation status.

Images