Operation method and system for unmanned container truck to move along with quay crane and storage medium

Abstract

The invention relates to an operation method and system for an unmanned container truck to move along with a quay crane and a storage medium, and the method comprises the steps: L1, enabling the port unmanned container truck to start an operation task, obtaining the position data information of a vehicle and the data information of the motion state of the vehicle in real time, and obtaining the position data information of the quay crane in real time; and L2, on the basis of the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay crane, a regression prediction algorithm of an attention mechanism of a two-way long-short-term memory network optimized by a crown porcupine is adopted to predict a driving path of the vehicle, and the data information of the predicted driving path of the vehicle is obtained. The operation efficiency of the automatic driving unmanned container truck on the quay crane is improved to the maximum extent, manual takeover caused by movement of the quay crane is eliminated, the operation efficiency is improved, the running distance and cost of the truck are reduced, and the automation level and safety are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned container trucks, and in particular to an operation method, system and storage medium for an unmanned container truck to move following a quay crane. Background Art

[0002] The mainstream collaborative operation method based on quay cranes and unmanned container trucks mainly considers the quay crane buffer area and energy-saving AGV collaboration. However, currently, unmanned container trucks and quay crane operations are two independent units that cannot meet consistent requirements. Most quay crane operations are remotely controlled and manually operated, while unmanned container trucks are purely unmanned equipment, which has higher requirements than quay cranes. When the AGV arrives at the loading quay crane to carry out loading operations, the terminal operating system creates AGV re-entry and re-exit instructions. The main purpose is to ensure the improvement of operating efficiency. It does not deal with related issues such as manual intervention and AGV detours, and the effects of manual intervention and AGV detours are not significantly improved. Summary of the invention

[0003] In view of the above problems, the present invention provides an operation method, system and storage medium for an unmanned container truck to follow the movement of a quay crane, which not only maximizes the efficiency of the automatic driving unmanned container truck operating on the quay crane, eliminates the manual takeover caused by the movement of the quay crane, improves the operation efficiency, but also reduces the vehicle's operating distance and cost, and effectively improves the level of automation and safety.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0005] An operation method for an unmanned container truck to follow a quay crane, the method comprising:

[0006] L1. The port unmanned container truck starts its operation task, obtains the vehicle's location data information and vehicle's motion status data information in real time, and obtains the quay crane's location data information in real time;

[0007] L2. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay crane, the vehicle's driving path is predicted by using a regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine to obtain the data information of the predicted vehicle's driving path;

[0008] L3. Based on the predicted data information of the vehicle's driving path, the vehicle's driving path is optimized using a bat algorithm based on an adaptive control factor to obtain optimized data information of the vehicle's driving path;

[0009] L4. Based on the data information of the optimized vehicle's driving path, establish the feasibility function Q of the unmanned container truck's operation task, evaluate the feasibility of the vehicle's operation completion, and obtain data information of the feasibility evaluation value of the vehicle's operation task completion.

[0010] Furthermore, the method further comprises:

[0011] L5. Based on the data information of the feasibility evaluation value of the vehicle's operation task completion, set a preset threshold. If the feasibility evaluation value of the vehicle's operation task completion is less than the preset threshold, the vehicle can complete the operation task. If the feasibility evaluation value of the vehicle's operation task completion is greater than the preset threshold, the vehicle cannot complete the operation task, and return to step L2.

[0012] Furthermore, the feasibility function Q of the unmanned container truck operation task is:

[0013]

[0014] Among them, x is the data information of the optimized vehicle's driving path, α 1 , α 2 and α 3 It is the feasibility assessment factor of unmanned container truck operation task.

[0015] Furthermore, the feasibility assessment factor α of the unmanned truck operation task is 1 , α 2 and α 3 for,

[0016]

[0017] Wherein, x is the data information of the optimized vehicle's driving path.

[0018] Furthermore, in step L2, the prediction of the vehicle's driving path by the regression prediction algorithm using the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine includes:

[0019] L21. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay bridge, a sequence function W of the relative position relationship between the vehicle and the quay bridge is established,

[0020] ,

[0021] Among them, y 1 is the vehicle’s location data, y 2 is the data information of the vehicle's motion status, y 3 is the location data information of the quay crane, β 1 , β 2 and β3 is the relative error factor between the vehicle and the quay crane, f is the position state function of the vehicle, the relative position relationship sequence between the vehicle and the quay crane is characterized, and the data information of the relative position relationship sequence between the vehicle and the quay crane is obtained;

[0022] L22. Based on the data information of the relative position relationship sequence between the vehicle and the quay crane, the relative position relationship between the vehicle and the quay crane is optimized using the crown porcupine optimization algorithm to obtain the data information of the relative position relationship sequence between the vehicle and the quay crane after optimization;

[0023] L23. Input the data information of the relative position relationship sequence of the optimized vehicle and the quay crane into the bidirectional long short-term memory network for training and learning, and determine the regression prediction function R of the network model.

[0024]

[0025] Among them, z is the data information of the relative position relationship sequence between the optimized vehicle and the quay crane, δ 1 ,δ 2 and δ 3 is the weight coefficient of the attention mechanism, and the trained bidirectional long short-term memory network is obtained;

[0026] L24. Based on the trained bidirectional long short-term memory network, the position data information of the vehicle, the data information of the vehicle's motion state and the position data information of the quay crane are input to predict the vehicle's driving path, and obtain the data information of the predicted vehicle's driving path.

[0027] Further, in step L22, the optimization of the relative position relationship between the vehicle and the quay crane using the crown porcupine optimization algorithm includes:

[0028] L221. Based on the data information of the relative position relationship sequence of the vehicle and the quay crane, the crowned porcupine population is initialized, the population parameters are determined, and the data information of the initialized crowned porcupine population is obtained;

[0029] L222. Based on the data information of the initialized crested porcupine population, establish the fitness function P of the population individuals,

[0030]

[0031] Among them, q is the data information of the initialized crested porcupine population, γ1, γ2 and γ3 are the fitness determining factors of the individuals in the crested porcupine population, and the fitness values ​​of the individuals in the crested porcupine population are calculated to obtain the data information of the fitness values ​​of the individuals in the crested porcupine population;

[0032] L223. Based on the data information of the fitness values ​​of the individuals in the crested porcupine population, a target optimization function S of the crested porcupine population is established.

[0033]

[0034] Among them, r is the data information of the fitness value of the crested porcupine population, η 1 , η 2 and η 3 The relative position relationship between the vehicle and the quay crane is optimized as the target optimization factor, and the data information of the optimized relative position relationship sequence between the vehicle and the quay crane is obtained.

[0035] Furthermore, the weight coefficient δ of the attention mechanism 1 ,δ 2 and δ 3 The constraints are:

[0036]

[0037] Furthermore, in step L3, the optimization of the vehicle's driving path using the bat algorithm based on the adaptive control factor includes:

[0038] L31. Based on the data information of the predicted vehicle's driving path, the bat population is initialized, the parameters of the bat population and the maximum number of iterations are determined, and the data information of the initialized bat population is obtained;

[0039] L32. Based on the data information of the initialized bat population, establish the fitness function G of the individual bat population,

[0040]

[0041] Among them, g is the data information of the initialized bat population, λ 1 , 2 and λ 3 is the fitness weight function of the individuals in the bat population, and the fitness values ​​of the individuals in the bat population are estimated to obtain data information of the fitness values ​​of the individuals in the bat population;

[0042] L33. Based on the data information of the fitness values ​​of the individuals in the bat population, an optimization function H of the bat population is established.

[0043]

[0044] Among them, r is the data information of the fitness value of the individual bat population, μ 1 , μ 2 and μ 3The adaptive control factor is used to optimize the vehicle's driving path and obtain data information of the optimized vehicle's driving path.

[0045] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides an operation system for an unmanned container truck to follow the movement of a quay crane, including a computer device, which is programmed or configured to execute the steps of any one of the operation methods for an unmanned container truck to follow the movement of a quay crane.

[0046] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the operating methods of an unmanned container truck following a quay crane.

[0047] The present invention has the following positive effects:

[0048] 1. The present invention predicts the vehicle's driving path by adopting a regression prediction algorithm of the attention mechanism of a bidirectional long short-term memory network optimized by a crown porcupine, and optimizes the vehicle's driving path by combining a bat algorithm based on an adaptive control factor. This not only maximizes the efficiency of autonomous driving unmanned container trucks operating on the quay crane, eliminates the human takeover caused by the movement of the quay crane, improves operating efficiency, but also reduces the vehicle's operating distance and cost, and effectively improves the level of automation and safety.

[0049] 2. The present invention establishes the feasibility function Q of the unmanned container truck's operation task to evaluate the feasibility of the vehicle's operation completion. It can not only accurately monitor the operation process of the unmanned container truck and the quay crane to ensure the accuracy of the unmanned container truck in completing the operation task, but also solve the problem of the quay crane moving while the automatic driving unmanned container truck is operating on the quay crane, thereby improving operation efficiency and reducing human intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0051] Figure 2 A schematic flow chart of a regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized for the crested porcupine of the present invention;

[0052] Figure 3 It is a schematic diagram of the process flow of the crested porcupine optimization algorithm of the present invention;

[0053] Figure 4 A schematic diagram of a process of a bat algorithm based on an adaptive control factor of the present invention;

[0054] Figure 5 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0055] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0056] Example 1: Figure 1 As shown, an operation method for an unmanned container truck to follow a quay crane, the method comprising:

[0057] L1. The port unmanned container truck starts its operation task, obtains the vehicle's location data information and vehicle's motion status data information in real time, and obtains the quay crane's location data information in real time;

[0058] L2. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay crane, the vehicle's driving path is predicted by using a regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine to obtain the data information of the predicted vehicle's driving path;

[0059] L3. Based on the predicted data information of the vehicle's driving path, the vehicle's driving path is optimized using a bat algorithm based on an adaptive control factor to obtain optimized data information of the vehicle's driving path;

[0060] L4. Based on the data information of the optimized vehicle's driving path, establish the feasibility function Q of the unmanned container truck's operation task, evaluate the feasibility of the vehicle's operation completion, and obtain data information of the feasibility evaluation value of the vehicle's operation task completion.

[0061] In this embodiment, the method further includes:

[0062] L5. Based on the data information of the feasibility evaluation value of the vehicle's operation task completion, set a preset threshold. If the feasibility evaluation value of the vehicle's operation task completion is less than the preset threshold, the vehicle can complete the operation task. If the feasibility evaluation value of the vehicle's operation task completion is greater than the preset threshold, the vehicle cannot complete the operation task, and return to step L2.

[0063] In this embodiment, the feasibility function Q of the unmanned container truck operation task is:

[0064]

[0065] Among them, x is the data information of the optimized vehicle's driving path, α 1 , α2 and α 3 It is the feasibility assessment factor of unmanned container truck operation task.

[0066] In this embodiment, the feasibility assessment factor α of the unmanned truck operation task is 1 , α 2 and α 3 for,

[0067]

[0068] Wherein, x is the data information of the optimized vehicle's driving path.

[0069] In this embodiment, if Figure 2 As shown, in step L2, the regression prediction algorithm using the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine predicts the driving path of the vehicle, including:

[0070] L21. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay bridge, a sequence function W of the relative position relationship between the vehicle and the quay bridge is established,

[0071] ,

[0072] Among them, y 1 is the vehicle’s location data, y 2 is the data information of the vehicle's motion status, y 3 is the location data information of the quay crane, β 1 , β 2 and β 3 is the relative error factor between the vehicle and the quay crane, f is the position state function of the vehicle, the relative position relationship sequence between the vehicle and the quay crane is characterized, and the data information of the relative position relationship sequence between the vehicle and the quay crane is obtained;

[0073] L22. Based on the data information of the relative position relationship sequence between the vehicle and the quay crane, the relative position relationship between the vehicle and the quay crane is optimized using the crown porcupine optimization algorithm to obtain the data information of the relative position relationship sequence between the vehicle and the quay crane after optimization;

[0074] L23. Input the data information of the relative position relationship sequence of the optimized vehicle and the quay crane into the bidirectional long short-term memory network for training and learning, and determine the regression prediction function R of the network model.

[0075]

[0076] Among them, z is the data information of the relative position relationship sequence between the optimized vehicle and the quay crane, δ 1 ,δ 2and δ 3 is the weight coefficient of the attention mechanism, and the trained bidirectional long short-term memory network is obtained;

[0077] L24. Based on the trained bidirectional long short-term memory network, the position data information of the vehicle, the data information of the vehicle's motion state and the position data information of the quay crane are input to predict the vehicle's driving path, and obtain the data information of the predicted vehicle's driving path.

[0078] In this embodiment, if Figure 3 As shown, in step L22, the use of the crown porcupine optimization algorithm to optimize the relative position relationship between the vehicle and the quay crane includes:

[0079] L221. Based on the data information of the relative position relationship sequence of the vehicle and the quay crane, the crowned porcupine population is initialized, the population parameters are determined, and the data information of the initialized crowned porcupine population is obtained;

[0080] L222. Based on the data information of the initialized crested porcupine population, establish the fitness function P of the population individuals,

[0081]

[0082] Among them, q is the data information of the initialized crested porcupine population, γ1, γ2 and γ3 are the fitness determining factors of the individuals in the crested porcupine population, and the fitness values ​​of the individuals in the crested porcupine population are calculated to obtain the data information of the fitness values ​​of the individuals in the crested porcupine population;

[0083] L223. Based on the data information of the fitness values ​​of the individuals in the crested porcupine population, a target optimization function S of the crested porcupine population is established.

[0084]

[0085] Among them, r is the data information of the fitness value of the crested porcupine population, η 1 , η 2 and η 3 The relative position relationship between the vehicle and the quay crane is optimized as the target optimization factor, and the data information of the optimized relative position relationship sequence between the vehicle and the quay crane is obtained.

[0086] In this embodiment, the weight coefficient δ of the attention mechanism 1 ,δ 2 and δ 3 The constraints are:

[0087]

[0088] Embodiment 2: Based on the operation method of an unmanned container truck following the movement of a quay crane in Embodiment 1, the present invention is further illustrated and described below.

[0089] like Figure 1 As shown, an operation method for an unmanned container truck to follow a quay crane, the method comprising:

[0090] L1. The port unmanned container truck starts its operation task, obtains the vehicle's location data information and vehicle's motion status data information in real time, and obtains the quay crane's location data information in real time;

[0091] L2. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay crane, the vehicle's driving path is predicted by using a regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine to obtain the data information of the predicted vehicle's driving path;

[0092] L3. Based on the predicted data information of the vehicle's driving path, the vehicle's driving path is optimized using a bat algorithm based on an adaptive control factor to obtain optimized data information of the vehicle's driving path;

[0093] L4. Based on the data information of the optimized vehicle's driving path, establish the feasibility function Q of the unmanned container truck's operation task, evaluate the feasibility of the vehicle's operation completion, and obtain data information of the feasibility evaluation value of the vehicle's operation task completion.

[0094] In this embodiment, if Figure 4 As shown, in step L3, the use of the bat algorithm based on the adaptive control factor to optimize the vehicle's driving path includes:

[0095] L31. Based on the data information of the predicted vehicle's driving path, the bat population is initialized, the parameters of the bat population and the maximum number of iterations are determined, and the data information of the initialized bat population is obtained;

[0096] L32. Based on the data information of the initialized bat population, establish the fitness function G of the individual bat population,

[0097]

[0098] Among them, g is the data information of the initialized bat population, λ 1 , 2 and λ 3 is the fitness weight function of the individuals in the bat population, and the fitness values ​​of the individuals in the bat population are estimated to obtain data information of the fitness values ​​of the individuals in the bat population;

[0099] L33. Based on the data information of the fitness values ​​of the individuals in the bat population, an optimization function H of the bat population is established.

[0100]

[0101] Among them, r is the data information of the fitness value of the individual bat population, μ 1 , μ 2 and μ 3 The adaptive control factor is used to optimize the vehicle's driving path and obtain data information of the optimized vehicle's driving path.

[0102] In this embodiment, the present invention also provides an operating system for an unmanned container truck to follow the movement of a quay crane, comprising a computer device, which is programmed or configured to execute the steps of any one of the operating methods for an unmanned container truck to follow the movement of a quay crane.

[0103] In this embodiment, if Figure 5 As shown, the modules consist of: quay crane RTK, vehicle-mounted communication terminal TBOX, vehicle-mounted positioning module (integrated navigation), IGV dispatching platform, etc.

[0104] 1. The quay crane RTK is responsible for locating the quay crane, determining its moving position and confirming the waiting point.

[0105] 2. The vehicle-mounted communication terminal TBOX is installed on the vehicle and is used for the interaction between the dispatching platform and the vehicle. It receives the parking and driving instructions issued by the platform through the real-time position and status of the vehicle uploaded by the vehicle-mounted positioning.

[0106] 3. The vehicle positioning module (combined navigation) cooperates with the vehicle's built-in high-precision map to determine the vehicle's location in real time, and connects to TBOX through the vehicle's CAN and other networks to report the vehicle's location information to the platform.

[0107] 4. The IGV dispatching platform, as the link between TOS instructions, vehicles, and quay cranes, is responsible for route planning, parking, and starting instructions for vehicles.

[0108] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the operating methods of an unmanned container truck following the movement of a quay crane.

[0109] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0110] In summary, the present invention not only maximizes the efficiency of autonomous driving unmanned container trucks operating on the quay crane, eliminates the manual takeover caused by the movement of the quay crane, and improves operating efficiency, but also reduces the operating distance and cost of the vehicle, and effectively improves the level of automation and safety.

[0111] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for an unmanned container truck to follow a quay crane, characterized in that: The method comprises: L1. The port unmanned container truck starts its operation task, obtains the vehicle's location data information and vehicle's motion status data information in real time, and obtains the quay crane's location data information in real time; L2. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay crane, the vehicle's driving path is predicted by using a regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine to obtain the data information of the predicted vehicle's driving path; L3. Based on the predicted data information of the vehicle's driving path, the vehicle's driving path is optimized using a bat algorithm based on an adaptive control factor to obtain optimized data information of the vehicle's driving path; L4. Based on the data information of the optimized vehicle's driving path, establish the feasibility function Q of the unmanned container truck's operation task, evaluate the feasibility of the vehicle's operation completion, and obtain data information of the feasibility evaluation value of the vehicle's operation task completion.

2. The method for operating an unmanned container truck following a quay crane according to claim 1, characterized in that: The method further comprises: L5. Based on the data information of the feasibility evaluation value of the vehicle's operation task completion, set a preset threshold. If the feasibility evaluation value of the vehicle's operation task completion is less than the preset threshold, the vehicle can complete the operation task. If the feasibility evaluation value of the vehicle's operation task completion is greater than the preset threshold, the vehicle cannot complete the operation task, and return to step L2.

3. The method for operating an unmanned container truck following a quay crane according to claim 1, characterized in that: The feasibility function Q of the unmanned container truck operation task is: Among them, x is the data information of the optimized vehicle's driving path, and α1, α2 and α3 are the feasibility evaluation factors of the unmanned truck operation task.

4. The method for operating an unmanned container truck following a quay crane according to claim 3 is characterized in that: The feasibility evaluation factors α1, α2 and α3 of the unmanned truck operation task are: Wherein, x is the data information of the optimized vehicle's driving path.

5. The method for operating an unmanned container truck following a quay crane according to claim 1, characterized in that: In step L2, the prediction of the vehicle's driving path using the regression prediction algorithm of the attention mechanism of the bidirectional long short-term memory network optimized by the crown porcupine includes: L21. Based on the position data information of the vehicle, the data information of the motion state of the vehicle and the position data information of the quay bridge, a sequence function W of the relative position relationship between the vehicle and the quay bridge is established, ， Among them, y1 is the position data information of the vehicle, y2 is the data information of the motion state of the vehicle, y3 is the position data information of the quay crane, β1, β2 and β3 are the relative error factors between the vehicle and the quay crane, and f is the position state function of the vehicle. The relative position relationship sequence between the vehicle and the quay crane is characterized to obtain the data information of the relative position relationship sequence between the vehicle and the quay crane; L22. Based on the data information of the relative position relationship sequence between the vehicle and the quay crane, the relative position relationship between the vehicle and the quay crane is optimized using the crown porcupine optimization algorithm to obtain the data information of the relative position relationship sequence between the vehicle and the quay crane after optimization; L23. Input the data information of the relative position relationship sequence of the optimized vehicle and the quay crane into the bidirectional long short-term memory network for training and learning, and determine the regression prediction function R of the network model. Among them, z is the data information of the relative position relationship sequence between the optimized vehicle and the quay crane, δ1, δ2 and δ3 are the weight coefficients of the attention mechanism, and the trained bidirectional long short-term memory network is obtained; L24. Based on the trained bidirectional long short-term memory network, the position data information of the vehicle, the data information of the vehicle's motion state and the position data information of the quay crane are input to predict the vehicle's driving path, and obtain the data information of the predicted vehicle's driving path.

6. The method for operating an unmanned container truck following a quay crane according to claim 5, characterized in that: In step L22, the optimization of the relative position relationship between the vehicle and the quay crane using the crown porcupine optimization algorithm includes: L221. Based on the data information of the relative position relationship sequence of the vehicle and the quay crane, the crowned porcupine population is initialized, the population parameters are determined, and the data information of the initialized crowned porcupine population is obtained; L222. Based on the data information of the initialized crested porcupine population, establish the fitness function P of the population individuals, Among them, q is the data information of the initialized crested porcupine population, γ1, γ2 and γ3 are the fitness determining factors of the individuals in the crested porcupine population, and the fitness values ​​of the individuals in the crested porcupine population are calculated to obtain the data information of the fitness values ​​of the individuals in the crested porcupine population; L223. Based on the data information of the fitness values ​​of the individuals in the crested porcupine population, a target optimization function S of the crested porcupine population is established. Among them, r is the data information of the fitness value of the individuals in the crested porcupine population, η1, η2 and η3 are the target optimization factors, and the relative position relationship between the vehicle and the quay crane is optimized to obtain the data information of the optimized relative position relationship sequence between the vehicle and the quay crane.

7. The method for operating an unmanned container truck following a quay crane according to claim 5, characterized in that: The constraints of the weight coefficients δ1, δ2 and δ3 of the attention mechanism are:

8. The method for operating an unmanned container truck following a quay crane according to claim 1, characterized in that: In step L3, the optimization of the vehicle's driving path using the bat algorithm based on the adaptive control factor includes: L31. Based on the data information of the predicted vehicle's driving path, the bat population is initialized, the parameters of the bat population and the maximum number of iterations are determined, and the data information of the initialized bat population is obtained; L32. Based on the data information of the initialized bat population, establish the fitness function G of the individual bat population, Among them, g is the data information of the initialized bat population, λ1, λ2 and λ3 are the fitness weight functions of the individuals in the bat population, and the fitness values ​​of the individuals in the bat population are calculated to obtain the data information of the fitness values ​​of the individuals in the bat population; L33. Based on the data information of the fitness values ​​of the individuals in the bat population, an optimization function H of the bat population is established. Among them, r is the data information of the fitness value of the individual bat population, μ1, μ2 and μ3 are adaptive control factors, and the vehicle's driving path is optimized to obtain the data information of the optimized vehicle's driving path.

9. An operation system for unmanned container trucks to follow the movement of quay cranes, comprising computer equipment, characterized in that: The computer device is programmed or configured to execute the steps of the method for operating an unmanned container truck following a quay crane as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program programmed or configured to execute the method for operating an unmanned container truck following a quay crane as described in any one of claims 1 to 8.

Images