Intelligent driving control method and device

Abstract

The invention discloses an intelligent travelling crane control method and device, and the method comprises the following steps: receiving a material hoisting signal, and obtaining the first state information of each travelling crane at the current moment and the second state information of each travelling crane at the next moment; according to the first state information, outputting first track data of each travelling crane running from the first state to the to-be-hoisted material area, and according to the first state information and the second state information, outputting second track data of each travelling crane running from the first state to the second state; constructing a trajectory dual-objective optimization function based on the overlapping rate of the same driving trajectory data and the separation rate of different driving trajectory data; and taking the first trajectory data and the second trajectory data as input, and outputting a driving planning trajectory by using a trajectory dual-objective optimization function. The intelligent driving control method is not limited by a fixed process, so that the adjusted track is separated from the running tracks of other driving vehicles as much as possible, the problem of vibration superposition is reduced, and the running stability of the driving vehicles is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle driving control technology, and in particular to an intelligent vehicle driving control method and device. Background Art

[0002] The crane used in factories (also often called an overhead crane, a crane or an overhead crane) is essentially a crane and is widely used for lifting and moving heavy objects.

[0003] The intelligent crane system integrates advanced technologies and sensors on the basis of traditional cranes to achieve high-precision positioning, automatic control and intelligent operation. These technologies include but are not limited to PLC logic control, remote control, sensor detection, etc. Intelligent cranes can automatically complete hoisting operations, greatly improving production efficiency while reducing manual operation errors and safety hazards.

[0004] At present, in order to improve efficiency, multiple cranes are usually used to perform lifting tasks together. This parallel operation method can significantly reduce the overall completion time of the task and improve production efficiency. When multiple cranes are working at the same time, it is necessary to ensure coordinated control between them to avoid collisions or mutual interference. Lifting tasks need to be reasonably allocated to different cranes to ensure that the workload is evenly distributed and to maximize the lifting capacity of each crane. However, when laying out the crane tracks on the factory building and allowing multiple cranes to run on them together, there will indeed be vibration problems, especially when the cranes are close to each other, the impact of vibration will be more significant. This vibration may not only affect the stable operation of the crane, but also cause long-term damage to the factory building structure and the crane tracks.

[0005] The Chinese patent "A method for controlling the collaborative operation of multiple cranes", publication number: CN114610019 A, publication date: June 10, 2022, specifically discloses: (1) reading data and configuring basic crane data; (2) performing initial sorting according to the work order time priority of each crane in the work order pool; (3) generating a control mode based on the initial sorting result, and calculating and allocating the operation instructions of each crane according to the generated control mode and confirming the operation instructions of each crane; (4) confirming the final mode and generating the final decision instruction. This solution generates crane instructions through work orders, and the crane operation time is fixed. The personnel who need to execute the work order also strictly complete the production execution and lifting according to the production time, and cannot realize dynamic adjustment of the crane.

[0006] The Chinese patent "An unmanned aerial vehicle control system and method thereof", publication number: CN108706464 A, publication date: October 26, 2018, specifically discloses a material positioning subsystem, an aerial vehicle scheduling subsystem and an aerial vehicle body control subsystem. The material positioning subsystem is used to collect material information in the warehouse area and send the material information to the aerial vehicle scheduling subsystem; the aerial vehicle scheduling subsystem is used to receive and determine the operation area according to the material information, and send the aerial vehicle operation task to the aerial vehicle body control subsystem in the corresponding area. The aerial vehicle task includes the aerial vehicle operation target position and the grab weight information; the aerial vehicle body control subsystem receives the aerial vehicle task and obtains the three-dimensional coordinate information of the aerial vehicle body in real time; moves and grabs according to the aerial vehicle operation target position and the three-dimensional coordinate information of the aerial vehicle body; the material positioning subsystem and the aerial vehicle body control subsystem are respectively connected to the aerial vehicle scheduling subsystem. This solution controls the aerial vehicle through material information, but cannot solve the vibration superposition problem in the case of multiple aerial vehicles. Summary of the invention

[0007] In order to solve the problems in the prior art that multiple cranes cannot be dynamically adjusted and the vibration superposition of adjacent cranes may cause damage, the present application provides an intelligent crane control method and device. By utilizing the first trajectory data and the second trajectory data, a crane with a balanced trajectory overlap rate and a trajectory separation rate is obtained. This crane is used to perform additional lifting tasks, thereby improving efficiency while ensuring the stability of the crane operation. The application is suitable for factories with multiple assembly lines. Since the movement of the crane is affected by the lifting signal, it can adapt to the production process in the assembly line where the exact lifting time cannot be determined due to the influence of the workers' operation. The application range is wider and is not limited by fixed processes. At the same time, the adjusted trajectory is separated from the operation trajectory of the remaining cranes as much as possible, reducing the vibration superposition problem and improving the stability of the crane operation.

[0008] In order to achieve the above-mentioned technical objectives, a technical solution provided by the present application is an intelligent vehicle control method, comprising the following steps: S1: receiving a material lifting signal, obtaining the first state information of each vehicle at the current moment and the second state information of each vehicle at the next moment; S2: outputting the first trajectory data of each vehicle running from the first state to the material area to be lifted according to the first state information, and outputting the second trajectory data of each vehicle running from the first state to the second state according to the first state information and the second state information; S3: constructing a trajectory dual-objective optimization function based on the overlap rate of the same vehicle trajectory data and the separation rate of different vehicle trajectory data; S4: using the first trajectory data and the second trajectory data as input to output the vehicle planning trajectory using the trajectory dual-objective optimization function, and controlling the intelligent movement of the vehicle with the vehicle planning trajectory.

[0009] Furthermore, the S2 also includes: screening available vehicles according to the first lifting information and the second lifting information; outputting first trajectory data of the available vehicles running from the first state to the area where materials are to be lifted according to the first position information; and outputting second trajectory data of the available vehicles running from the first state to the second state according to the first position information and the second position information.

[0010] Furthermore, the constructing of a trajectory dual-objective optimization function based on the overlap rate of the same driving trajectory data and the separation rate of different driving trajectory data also includes: constructing an overlapping objective optimization function based on the overlap rate of the same driving trajectory data; constructing a separation objective optimization function based on the separation rates of different driving trajectory data; and constructing a trajectory dual-objective optimization function with the overlapping objective optimization function and the separation objective optimization function.

[0011] Furthermore, constructing an overlapping target optimization function based on the overlapping rate of the same driving trajectory data also includes: calculating the overlapping rate of the same driving trajectory data using a similarity metric to construct an overlapping target optimization function.

[0012] Furthermore, constructing a separation target optimization function based on separation rates of different driving trajectory data includes: constructing a separation target optimization function based on lateral separation rates and longitudinal separation rates of different driving trajectory data.

[0013] Furthermore, S3 also includes: acquiring historical vehicle operation data, and constructing a vibration correction model based on the vibration superposition principle and the historical vehicle operation data.

[0014] Furthermore, the S2 also includes: constructing third trajectory data of each vehicle traveling from the first state through the area for hoisting materials to the second state according to the first trajectory data and the second trajectory data.

[0015] Furthermore, the S3 further includes: constructing a separation target optimization function based on the third trajectory data of different vehicles and the trajectory separation rate of the second trajectory data.

[0016] Furthermore, it also includes: S5: when it is identified that there are people in the driving planning trajectory range, the driving is controlled to stop; when it is identified that the people have left, the driving planning trajectory of the remaining vehicles is adjusted using the trajectory adjustment objective function to control the intelligent movement of the vehicle with the adjusted driving planning trajectory.

[0017] Another technical solution provided by the present application is an intelligent driving control device, which is connected to each driving and lifting control unit, and is used to implement the method as mentioned above, including: a communication module, which is used to receive material lifting signals, first state information and second state information; a trajectory analysis module, which is used to output first trajectory data and second trajectory data according to the information uploaded by the communication module; a control module, which is used to output a driving planning trajectory according to the first trajectory data and the second trajectory data using a trajectory dual-objective optimization function, and control the driving operation with the driving planning trajectory.

[0018] Another technical solution provided by the present application is that a computer-readable storage medium is used to store a computer program or instruction. When the computer program or instruction is executed by a processing device, the above-mentioned distribution network voltage disturbance coupling characteristic analysis method is implemented. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk), etc.

[0019] The beneficial effects of the present application are as follows: by using the first trajectory data and the second trajectory data to obtain a vehicle with a balanced trajectory overlap rate and trajectory separation rate, the vehicle can perform additional lifting tasks, while improving efficiency and ensuring the stability of the vehicle operation. It is suitable for multi-assembly line factories. Since the movement of the vehicle is affected by the lifting signal, it can adapt to the production process in the assembly line where the accurate lifting time cannot be determined due to the operation of the workers. It has a wider range of applications and is not restricted by fixed processes. At the same time, the planned trajectory is separated from the running trajectory of the remaining vehicles as much as possible, reducing the problem of vibration superposition and improving the stability of the vehicle operation. The separation rate and arrival time are used to readjust the vehicle trajectory after parking to avoid vehicle collisions caused by time differences, further improving the stability of the vehicle operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the intelligent driving control method of this application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in conjunction with the drawings and examples. It should be understood that the specific implementation method described here is only an optimal embodiment of the present application, which is only used to explain the present application and does not limit the scope of protection of the present application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0022] like Figure 1 As shown, as the first embodiment of the present application, the intelligent driving control method includes the following steps: S1: Receive material hoisting signals, and obtain the first state information of each vehicle at the current moment and the second state information of each vehicle at the next moment; S2: outputting first trajectory data of each vehicle running from the first state to the area where materials are to be hoisted according to the first state information, and outputting second trajectory data of each vehicle running from the first state to the second state according to the first state information and the second state information; S3: Construct a trajectory dual-objective optimization function based on the overlap rate of the same driving trajectory data and the separation rate of different driving trajectory data; S4: using the first trajectory data and the second trajectory data as inputs and using the trajectory dual-objective optimization function to output a driving planning trajectory, and controlling the driving intelligent movement with the driving planning trajectory.

[0023] In this embodiment, by comparing the current state of each vehicle and the preset state of the next moment, the first trajectory that the vehicle needs to move from the current position to the area of ​​materials to be hoisted and the second trajectory that the vehicle needs to move from the current position to the position at the next moment are obtained, and the overlap rate of the first trajectory and the second trajectory of the same vehicle, that is, the overlap rate of the same vehicle trajectory data, and the separation rate of the first trajectory and the second trajectory of different vehicles, that is, the separation rate of different vehicle trajectory data, are calculated. The trajectory dual-objective optimization function is used to obtain the vehicle trajectory that satisfies both the most overlap of its own trajectory and the most separation from the other vehicle trajectories, and this is used as the vehicle planning trajectory to control the intelligent movement of the vehicle. While driving along the line to carry out new hoisting to improve driving efficiency, the separation rate is used to select the driving trajectory that has the least impact on the movement of other vehicles along the line to reduce path interference and improve safety.

[0024] Specifically, the first state information includes at least the first position information and the first lifting information, and the second state information includes at least the second position information and the second lifting information. The first lifting information includes the first lifting weight, and the second lifting information includes the second lifting weight. The first lifting weight is the weight of the hoisted materials when the vehicle is in the first position, and the second lifting weight is the weight of the hoisted materials when the vehicle is in the second position. It can be understood that under normal circumstances, each vehicle moves according to the set vehicle planning trajectory, so the second state information is the second position information and the second lifting information at the preset next moment obtained according to the initially set vehicle planning trajectory.

[0025] When the vehicle is running according to the initially set driving planning trajectory, the next moment considered is the next stop moment of the vehicle. Step S2 also includes: Filter available vehicles according to the first hoisting information and the second hoisting information; Outputting first trajectory data of the spare vehicle running from the first state to the area where the materials are to be hoisted according to the first position information; The second trajectory data of the free vehicle running from the first state to the second state is outputted according to the first position information and the second position information.

[0026] When the crane executes an additional lifting plan, the original lifting plan cannot be destroyed. Therefore, it is necessary to screen the available cranes according to the first lifting information and the second lifting information, that is: g m +g1+g2≤G; g m is the weight of the material to be hoisted, g1 is the first hoisting weight, g2 is the second hoisting weight, and G is the rated hoisting weight of the crane.

[0027] During the operation of the vehicle, the new lifting plan is added to the lifting plan of the vehicles along the line, so as to reduce the moving distance of the vehicle and improve the efficiency of the vehicle. However, if multiple vehicles are running on the same track, if the distance between the vehicles is too close, the track vibration will be superimposed, affecting the stable operation of the vehicle and may also cause long-term damage to the plant structure and the vehicle track. Therefore, a trajectory dual-objective optimization function is constructed based on the overlap rate of the same vehicle trajectory data and the separation rate of different vehicle trajectory data: Construct an overlapping target optimization function based on the overlapping rate of the same driving trajectory data; Construct a separation target optimization function based on the separation rates of different driving trajectory data; The trajectory dual-objective optimization function is constructed using overlapping objective optimization function and separate objective optimization function.

[0028] Constructing the overlapping target optimization function based on the overlap rate of the same driving trajectory data includes: The overlap rate of the same driving trajectory data is calculated using similarity metrics to construct an overlap objective optimization function.

[0029] In this embodiment, the similarity measurement algorithm is a dynamic time warping algorithm. The dynamic time warping algorithm is used to calculate the overlap rate of the first trajectory data and the second trajectory data of the same vehicle: Wherein, f1(i) is the overlap ratio between the first trajectory data and the second trajectory data of vehicle i, i1 is the first trajectory data of vehicle i, i2 is the second trajectory data of vehicle i, and i 2,n is the nth trajectory point in the second trajectory data, i 1,n is the nth trajectory point in the first trajectory data, and m is the total number of corresponding trajectory points.

[0030] The dynamic time warping algorithm is used to calculate the distance between the first trajectory data and the second trajectory data, that is, DTW(d1, d2). When the DTW distance is smaller, the first trajectory data and the second trajectory data are more similar. The DTW distance is divided by the maximum possible DTW distance to obtain the overlap rate of the first trajectory data and the second trajectory data. The smaller the DTW distance, the closer the overlap rate is to 1, and the larger the DTW distance, the closer the overlap rate is to 0. The maximum possible DTW distance is the normalization factor, and the actual DTW distance is converted into a ratio of 0 to 1 to obtain the overlap rate of the first trajectory data and the second trajectory data. The overlap rate of the first trajectory data and the second trajectory data of the same vehicle is used as the overlap rate of the same vehicle trajectory data to show if the vehicle needs to perform additional lifting tasks, that is, the overlap of the path of the original moving trajectory when moving to the area where the materials to be lifted are located, and the "on the way" situation of the vehicle movement is obtained. The most "on the way" vehicle is used as the optimization solution target, and the overlapping target optimization function is constructed:

[0031] The separation target optimization function based on the separation rate of different driving trajectory data includes: The separation objective optimization function is constructed based on the lateral separation rate and longitudinal separation rate of different driving trajectory data.

[0032] The separation rate of different driving trajectory data is the separation rate of the first trajectory data and the second trajectory data between different driving vehicles. If there are driving vehicles p and q, compare the separation of the first trajectory data of driving vehicle p and the second trajectory data of driving vehicle q, and compare the separation of the first trajectory data of driving vehicle p and the second driving trajectory data of driving vehicle q. The separation situation is the spatial position distance between the trajectories. For example, when driving vehicle p is used as a vehicle on the way, calculate the distance between it and the normal operating trajectory of the other vehicles, and calculate the separation rate. When different vehicles are used as vehicles on the way, the vehicle with the largest distance from the other vehicles is used as the optimization target to avoid collision or superposition problems. The spatial position includes the lateral spatial position and the longitudinal spatial position. The lateral separation rate of different driving trajectory data is: in, is the horizontal coordinate of the nth track point in the first track data of vehicle p, is the lateral coordinate of the nth trajectory point in the second trajectory data of vehicle q, p∈i, q∈i.

[0033] The difference between the lateral coordinates of the first trajectory data of each vehicle and the lateral coordinates of the second trajectory data of the remaining vehicles is calculated to obtain the lateral separation rate of the trajectory data between different vehicles to show whether a vehicle is laterally adjacent to the trajectory of the remaining vehicles traveling from the first position to the second position according to the preset strategy when the vehicle is running according to the first trajectory data. It can be understood that when the lateral coordinates of the first trajectory data of a vehicle are the same as the lateral coordinates of the second trajectory data of the remaining vehicles, it means that the two will collide laterally in this case, so the lateral separation rate analysis can simultaneously avoid the lateral collision problem during trajectory planning.

[0034] The lateral separation rate of different driving trajectory data is: in, is the longitudinal coordinate of the nth track point in the first track data of vehicle p, is the longitudinal coordinate of the nth trajectory point in the second trajectory data of vehicle q, p∈i, q∈i.

[0035] The difference between the longitudinal coordinates of the first trajectory data of each vehicle and the longitudinal coordinates of the second trajectory data of the remaining vehicles is calculated to obtain the longitudinal separation rate of the trajectory data between different vehicles to show whether a vehicle is longitudinally adjacent to the trajectory of the remaining vehicles traveling from the first position to the second position according to the preset strategy when the vehicle is running according to the first trajectory data. It can be understood that when the longitudinal coordinates of the first trajectory data of a vehicle are the same as the longitudinal coordinates of the second trajectory data of the remaining vehicles, it means that the two will collide longitudinally in this case, so the use of lateral separation rate analysis can simultaneously avoid the longitudinal collision problem during trajectory planning.

[0036] The separation target optimization function is constructed based on the lateral separation rate and longitudinal separation rate of different driving trajectory data: maxf2(i)=max(w h ·HSR+w v VSR); Among them, w h is the weight coefficient of the lateral separation rate, w v is the weight coefficient of the longitudinal separation rate.

[0037] The weight coefficients of the lateral separation rate and the longitudinal separation rate can be initially set according to the actual track layout, and then the weight coefficients can be corrected by vibration superposition. Therefore, step S3 also includes: Obtain historical driving operation data and build a vibration correction model based on the vibration superposition principle and historical driving operation data.

[0038] The vibration superposition principle means that when there are multiple vibrations on the same object, these vibrations will be superimposed to form a new vibration, and the amplitude and frequency of this new vibration are the sum of the original vibrations. Whether in the longitudinal or transverse direction, the superposition of vibrations can follow the principle of vector superposition. Therefore, according to the vibration superposition principle, we can get: Wherein, A is the superimposed lateral vibration amplitude, α is the attenuation coefficient, 0<α<1, φ is the phase difference between the first driving amplitude A1 and the second driving amplitude A2, 0≤φ≤2π.

[0039] The attenuation coefficient α is related to the distance between vehicles. The farther the distance between vehicles, the greater the attenuation and the smaller the impact. The closer the distance between vehicles, the smaller the attenuation and the greater the impact. Based on the attenuation principle, the correlation between the driving distance and the attenuation coefficient is constructed: Where d is the driving distance and D is the characteristic attenuation length, which is related to the vibration properties and the propagation medium.

[0040] Therefore, the historical driving data is used for training, and the characteristic attenuation length is adjusted to obtain the vibration correction model: Among them, α h is the lateral attenuation coefficient of the vehicle, d h is the lateral distance of the vehicle, Dh is the lateral characteristic attenuation length of the vehicle, α v is the longitudinal attenuation coefficient of the vehicle, d v is the longitudinal distance of the vehicle, D v is the longitudinal characteristic attenuation length of the vehicle. When the lateral attenuation coefficient of the vehicle is larger, the influence of the lateral separation rate of the vehicle is smaller; when the lateral attenuation coefficient of the vehicle is smaller, the influence of the lateral separation rate of the vehicle is larger; when the longitudinal attenuation coefficient of the vehicle is larger, the influence of the longitudinal separation rate of the vehicle is smaller; when the longitudinal attenuation coefficient of the vehicle is smaller, the influence of the longitudinal separation rate of the vehicle is smaller. Therefore, the weight coefficient is corrected by the lateral attenuation coefficient of the vehicle and the longitudinal attenuation coefficient of the vehicle: w h =w′ h α h ; w v =w′ v α v ; w′ h is the initial weight coefficient of the lateral separation rate, w′ vis the initial weight coefficient of the longitudinal separation rate. After obtaining the first trajectory data and the second trajectory data, the lateral attenuation coefficient of the vehicle and the longitudinal attenuation coefficient of the vehicle are output according to the vibration correction model, and the lateral separation rate and the longitudinal separation rate in the separation target optimization function are corrected. Therefore, step S3 also includes: The weight of the separation objective optimization function is corrected using the vibration correction model, and the separation objective optimization function is updated.

[0041] The trajectory dual-objective optimization function is constructed by overlapping objective optimization function and separation objective optimization function: Then, the constraints of the trajectory dual-objective optimization function are constructed. It is necessary to avoid the emergency lifting task and perform additional tasks, so the constraints are constructed according to the target arrival time: Among them, t m is the target arrival time, is the average moving speed of vehicle i. The target arrival time is the latest time for the material to arrive at the second location calculated by obtaining production information.

[0042] During the operation of the crane, the operating speed needs to match the lifting weight to avoid material shaking caused by excessive speed. Therefore, the moving speed of the crane is calculated based on the material weight: Among them, v q is the hoisting speed influencing parameter, with the unit of m / s·kg. The hoisting speed influencing parameters related to hoisting are obtained by using the historical crane operation data.

[0043] The first trajectory data and the second trajectory data are used to obtain a crane with a balanced trajectory overlap rate and trajectory separation rate. This crane is used to perform additional lifting tasks, which improves efficiency while ensuring the stability of the crane operation. It is suitable for multi-assembly line factories. Since the movement of the crane is affected by the lifting signal, it can adapt to the production process in the assembly line where the exact lifting time cannot be determined due to the influence of the workers' operation. It has a wider range of applications and is not limited by fixed processes.

[0044] It is understandable that in the present application, the second state information at the next moment may also be the state information of the remaining lifting moments of the original lifting task, in which case the second position information includes the position information of the remaining lifting points, and the second lifting information includes the lifting information of the remaining lifting points. The second trajectory data at least includes the remaining lifting points. At this time: g m +g1+...+g s ≤G; g s It is the lifting weight of the lifting position before the additional lifting target position.

[0045] The constraints are:

[0046] The first trajectory data and the second trajectory data are used as inputs to output the optimal balanced line and the vehicle separated from the rest of the vehicles using the trajectory dual-objective optimization function, and the vehicle planning trajectory is obtained using the first trajectory data and the second trajectory data of the vehicle. At this time, considering that the first trajectory data and the second trajectory data may not be completely spliced, that is, the end position of the first trajectory data is not at any position in the second trajectory data, therefore, step S2 also includes: Constructing third trajectory data of each vehicle from the first state through the area for hoisting materials to the second state according to the first trajectory data and the second trajectory data; Step S3 also includes: A separation target optimization function is constructed based on the third trajectory data of different vehicles and the trajectory separation rate of the second trajectory data.

[0047] By filling the moving track between the first trajectory data and the second trajectory data, and then comparing the entire trajectory data when calculating the separation rate, the mutual influence between the vehicles is further reduced, and the stability of the vehicle operation is improved. It can be understood that although calculating the third trajectory data can further improve the stability of the vehicle operation, it will also increase the calculation data. When the third trajectory data is not calculated, since the optimal separation rate between the first trajectory and the second trajectory is calculated, the separation between the selected vehicle and the remaining vehicles can meet the requirement that there will be no collision when moving from the area where the materials to be hoisted are moved to a certain trajectory point position in the original second trajectory, that is, the two methods can be selected according to the actual situation.

[0048] As a second embodiment of the present application, the intelligent driving control method further includes: S5: When a person is identified in the range of the planned driving trajectory, the vehicle is controlled to stop; when the person is identified to have left, the planned driving trajectory of the remaining vehicles is adjusted using the trajectory adjustment objective function, and the intelligent movement of the vehicle is controlled by the adjusted planned driving trajectory.

[0049] In this embodiment, it is considered that in the factory space, when the vehicle is running according to the planned trajectory, there may be workers staying within the trajectory range, which may cause a collision between the vehicle and the personnel, thus causing serious safety problems. Therefore, personnel identification is performed, and when a person is identified within the planned trajectory range of the vehicle, the vehicle stops, and when the person leaves, the planned trajectory of the vehicle is adjusted using the trajectory adjustment objective function.

[0050] The trajectory adjustment objective function is: Among them, S l is the average separation rate of the lth vehicle trajectory, T l is the running time of the lth driving trajectory.

[0051] After the vehicle stops, the driving trajectory to reach the remaining lifting points of the vehicle is replanned. The dynamic time warping algorithm is used to calculate the average separation rate of each driving trajectory compared with the remaining driving planned trajectories, and the time it takes for each driving trajectory to reach the final lifting point is calculated. The running trajectory with the minimum running time and the maximum separation rate is selected to adjust the planned trajectory of the stopped vehicle to avoid collisions caused by the time difference after parking.

[0052] In this embodiment, the dynamic time warping algorithm calculates the separation rate of corresponding points in the time series, and calculates the separation rate of the positions of different vehicles at corresponding times, so as to avoid misjudgment of collisions caused by the same positions at different times, thereby improving the accuracy of driving planning.

[0053] The driving planning trajectory range can be within five meters from the driving vehicle, or within ten meters from the driving vehicle. It can be set according to the actual material box size and driving deceleration time.

[0054] In other embodiments, step S5 further includes: When a person is detected within the planned driving trajectory, the vehicle is stopped and an alarm is sounded; The estimated separation time and the planned driving trajectory of the remaining vehicles are used to adjust the planned driving trajectory using the trajectory adjustment objective function. When the estimated separation time is reached and the personnel are separated, the adjusted planned driving trajectory is used to control the intelligent movement of the vehicle.

[0055] The estimated departure time can be set according to the actual time it takes for the person to leave after the alarm is issued. Subsequent driving planning can be carried out when the vehicle stops according to the estimated departure time. When the person leaves according to the estimated departure time, the intelligent movement of the vehicle can be immediately controlled according to the adjusted driving planning trajectory.

[0056] As a third embodiment of the present application, the intelligent driving control device is connected to each driving and hoisting control unit, including: A communication module, used for receiving a material hoisting signal, first status information and second status information; A trajectory analysis module, used for outputting first trajectory data and second trajectory data according to the information uploaded by the communication module; The control module is used to output a driving planning trajectory using a trajectory dual-objective optimization function according to the first trajectory data and the second trajectory data, and control the driving operation with the driving planning trajectory.

[0057] In this embodiment, the communication module is connected to each crane and the hoisting control unit, the trajectory analysis module is connected to the communication module and the control module, and the control module is connected to each crane to achieve trajectory control of each crane.

[0058] In the remaining embodiments, the intelligent crane control device is connected to the MES system, receives the production plan issued by the MES system, and outputs the original driving planning trajectory according to the production plan during the initial operation. In the absence of additional lifting requirements, the crane operates according to the original driving planning trajectory.

[0059] Intelligent driving control device also includes: The human body recognition module is used to identify whether there are people within the planned driving trajectory.

[0060] The human body recognition module is connected to the control module. The control module includes at least a first function unit, a second function unit, a third function unit and a fourth function unit. The first function unit is constructed with an overlapping target optimization function, the second function unit is constructed with a separation target optimization function, the third function unit is constructed with a trajectory dual-target optimization function, and the fourth function unit is constructed with a trajectory adjustment target function. The first function unit, the second function unit and the third function unit are connected, and the fourth function unit is connected with the second function unit.

[0061] The human body recognition module can be an RFID radio frequency identifier. The RFID radio frequency identifier is installed on the driving vehicle. The work clothes and safety helmets of the personnel in this area of ​​the workshop are respectively installed with an RFID tag that matches the RFID radio frequency identifier on the trolley. When the driving vehicle detects the above-mentioned personnel activities on the running route, the driving vehicle will automatically detect the distance from the above-mentioned personnel. When the person is within the driving trajectory range, an alarm will be issued and the driving vehicle will stop running. After the person is away from the driving trajectory range and the alarm is lifted, the driving vehicle will re-plan the driving trajectory to reach the remaining lifting points of the driving vehicle and run according to the adjusted driving trajectory. Or install visual recognition equipment to detect personnel activities. When the person is on the driving route or target location, it can slow down or stop and have an alarm function.

[0062] Intelligent driving control device also includes: The sampling module installed on the crane is used to collect the driving speed, the weight of the crane hoisting and the driving position.

[0063] The sampling module includes at least a gravity sensor, a position sensor and a speed sensor.

[0064] The communication module uses network cable series connection communication to receive material lifting signals, material lifting completion signals, fault signals, etc.

[0065] Intelligent driving control device also includes: The interaction module is used to control the driving action according to the interaction information.

[0066] The interactive module is connected to each crane and can be a PAD or an on-site touch screen, such as a Siemens resistive screen human-machine interface or a handheld wireless pad. The operator can input or select the starting point and the end point through the PAD or on-site touch screen, and then control the crane to transport the materials from the starting point to the end point.

[0067] In this embodiment, the interface between the intelligent driving control device and the MES system adopts the TCP / IP protocol. The control module can adopt the Siemens S7-1500 PLC with a safety module and a digital IO module. The driving trajectory control adopts variable frequency speed control. The inverter adopts the Schneider ATV930 series, and uses the profinet bus and PLC for communication to ensure the synchronous operation of the running motor, with a simple structure, high efficiency and reliable operation.

[0068] As a fourth embodiment of the present application, a computer-readable storage medium is used to store a computer program or instruction. When the computer program or instruction is executed by a processing device, the above-mentioned distribution network voltage disturbance coupling characteristic analysis method is implemented. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk), etc.

[0069] The specific implementation described above is a preferred implementation of the intelligent driving control method and device of the present application, and is not intended to limit the specific implementation scope of the present application. The scope of the present application includes but is not limited to the specific implementation. All equivalent changes made in accordance with the shape and structure of the present application are within the protection scope of the present application.

Claims

1. An intelligent driving control method, characterized in that: The steps include: S1: Receive material hoisting signals, and obtain the first state information of each vehicle at the current moment and the second state information of each vehicle at the next moment; S2: outputting first trajectory data of each vehicle running from the first state to the area where materials are to be hoisted according to the first state information, and outputting second trajectory data of each vehicle running from the first state to the second state according to the first state information and the second state information; S3: Construct a trajectory dual-objective optimization function based on the overlap rate of the same driving trajectory data and the separation rate of different driving trajectory data; S4: using the first trajectory data and the second trajectory data as inputs and using the trajectory dual-objective optimization function to output a driving planning trajectory, and controlling the driving intelligent movement with the driving planning trajectory.

2. The intelligent driving control method according to claim 1, characterized in that: The S2 further includes: Filter available vehicles according to the first hoisting information and the second hoisting information; Outputting first trajectory data of the spare vehicle running from the first state to the area where the materials are to be hoisted according to the first position information; The second trajectory data of the free vehicle running from the first state to the second state is outputted according to the first position information and the second position information.

3. The intelligent driving control method according to claim 1, characterized in that: The dual-objective optimization function of trajectories constructed based on the overlap rate of the same driving trajectory data and the separation rate of different driving trajectory data also includes: Construct an overlapping target optimization function based on the overlapping rate of the same driving trajectory data; Construct a separation target optimization function based on the separation rates of different driving trajectory data; The trajectory dual-objective optimization function is constructed using overlapping objective optimization function and separate objective optimization function.

4. The intelligent driving control method according to claim 3, characterized in that: The overlapping target optimization function constructed based on the overlapping rate of the same driving trajectory data also includes: The overlap rate of the same driving trajectory data is calculated using similarity metrics to construct an overlap objective optimization function.

5. The intelligent driving control method according to claim 3, characterized in that: The separation target optimization function constructed based on the separation rates of different driving trajectory data includes: The separation objective optimization function is constructed based on the lateral separation rate and longitudinal separation rate of different driving trajectory data.

6. The intelligent driving control method according to claim 5, characterized in that: The S3 further includes: Obtain historical driving operation data and build a vibration correction model based on the vibration superposition principle and historical driving operation data.

7. The intelligent driving control method according to claim 1, characterized in that: The S2 further includes: The third trajectory data of each vehicle traveling from the first state through the area for hoisting materials to the second state is constructed according to the first trajectory data and the second trajectory data.

8. The intelligent driving control method according to claim 7, characterized in that: The S3 further includes: A separation target optimization function is constructed based on the third trajectory data of different vehicles and the trajectory separation rate of the second trajectory data.

9. The intelligent driving control method according to claim 7, characterized in that: Also includes: S5: When a person is identified within the planned driving trajectory, the vehicle is controlled to stop; When the identified person leaves, the planned driving trajectory of the remaining vehicles is adjusted using the trajectory adjustment objective function, and the adjusted planned driving trajectory is used to control the intelligent movement of the vehicle.

10. An intelligent driving control device, connected to each driving and hoisting control unit, for implementing the method according to any one of claims 1 to 9, characterized in that: include: A communication module, used for receiving a material hoisting signal, first status information and second status information; A trajectory analysis module, used for outputting first trajectory data and second trajectory data according to the information uploaded by the communication module; The control module is used to output a driving planning trajectory using a trajectory dual-objective optimization function according to the first trajectory data and the second trajectory data, and control the driving operation with the driving planning trajectory.

Images