A multi-lane situation awareness regulation method and system based on intelligent cloud warehouse

Abstract

The application discloses a multi-lane situation awareness regulation method and system based on a smart cloud warehouse, and relates to the technical field of lane monitoring.The application acquires the condition of each lane of the smart cloud warehouse in advance, determines the real-time traffic efficiency and situation risk control information of each lane, and provides effective reference opinions for lane control.Meanwhile, the trajectory data of the entering vehicles are collected in real time, the entering vehicles are accurately positioned in the current lane and adjacent lane information through matching with the multi-lane distribution information, the congestion and collision risk of the entering vehicles in each lane in the future time period are predicted, and strong support is provided for the lane allocation regulation decision of the subsequent entering vehicles.The application can quickly respond to the traffic flow allocation of the multi-lane, quickly respond to the complex traffic situation, and avoid causing congestion or resource waste.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road image monitoring, in particular to a multi-lane situation awareness regulation method and system based on a smart cloud warehouse. BACKGROUND

[0002] The smart cloud warehouse constructs a full-chain digital system with station-level business as the core, strengthens station center collaboration and data interaction, and forms an efficient smart highway toll management system. At the station level, it deeply integrates transaction processing, department-station collaboration, and provincial-station data transmission functions to form a business operation foundation node. At the same time, it relies on the cloud to build a centralized service center and realizes efficient handling of special events through intelligent scheduling and remote collaboration. The center side iteratively upgrades the comprehensive business management system, integrates data platform capabilities, and connects online and offline collaboration processes for green pass inspection and other preferential services. With the help of Internet of Things technology, it realizes automatic verification and rapid release. In addition, relying on the distributed data architecture, it strengthens the two-way data interaction capabilities between the station level and the center, builds a real-time shared data resource pool, and provides full-dimensional support for comprehensive decision analysis, special situation early warning and handling, and business efficiency optimization, ultimately forming a more efficient integrated smart highway toll management system.

[0003] At present, the existing smart cloud warehouse has limited real-time position, speed and dynamic interaction perception ability of vehicles in multi-lane, resulting in low scheduling efficiency. It usually relies on a single sensor or simple algorithm, which cannot effectively integrate multi-source heterogeneous data, affecting decision accuracy. That is, the existing smart cloud warehouse cannot quickly respond to complex traffic situations, which can easily cause congestion or waste resources. SUMMARY

[0004] The purpose of the present application is to solve the problem of the prior art that the smart cloud warehouse cannot quickly respond to complex traffic situations, and a multi-lane situation awareness regulation method and system based on a smart cloud warehouse are proposed.

[0005] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a multi-lane situation awareness regulation method based on a smart cloud warehouse, comprising:

[0007] Obtain multi-lane distribution information of the smart cloud warehouse, and collect real-time state conditions of each lane;

[0008] Determine the real-time traffic efficiency of each lane according to the real-time state conditions of each lane;

[0009] Determine the situation risk control information of each lane according to the multi-lane distribution information of the smart cloud warehouse and the real-time traffic efficiency of each lane;

[0010] Obtain the entering vehicle trajectory of the intelligent cloud warehouse, and perform real-time situation awareness on the entering vehicle.

[0011] According to the situation risk control information of each lane, the real-time situation of the entering vehicle is regulated and controlled, and the regulation and control trajectory of the entering vehicle is determined.

[0012] In a feasible scheme, the method for determining the real-time traffic efficiency of each lane comprises:

[0013] According to the real-time state of each lane, key traffic parameters are extracted;

[0014] Among them, the key traffic parameters include lane traffic volume, average speed and vehicle type distribution;

[0015] According to the multi-lane distribution information of the intelligent cloud warehouse, and combined with the historical traffic data of each lane, a traffic efficiency evaluation model is preset and constructed;

[0016] Based on the preset traffic efficiency evaluation model, the key traffic parameters are input into the traffic efficiency evaluation model to determine the real-time traffic efficiency of each lane.

[0017] In a feasible scheme, the method for determining the situation risk control information of each lane comprises:

[0018] According to the multi-lane distribution information of the intelligent cloud warehouse and the real-time traffic efficiency of each lane, the potential risk points currently existing in each lane are identified;

[0019] Based on the identified potential risk points, the potential risk of each lane is quantitatively evaluated to obtain the risk evaluation value of each lane;

[0020] According to the risk evaluation value of each lane and the preset risk level division standard, the situation risk control level of each lane is determined;

[0021] The situation risk control level of each lane and the corresponding potential risk point information are integrated to form the situation risk control information of each lane.

[0022] In a feasible scheme, the potential risk point comprises one or more combinations of lane congestion risk point, lane collision risk point and special vehicle driving risk point.

[0023] In a feasible scheme, the method for performing real-time situation awareness on the entering vehicle comprises:

[0024] Obtain the real-time trajectory data of any entering vehicle;

[0025] According to the multi-lane distribution information of the intelligent cloud warehouse, a lane coordinate system is constructed;

[0026] mapping real-time trajectory data of any entering vehicle into the lane coordinate system to determine the relative position of any entering vehicle in the multi-lane;

[0027] calculating the relative distance between the entering vehicle and other vehicles in the lane according to the real-time state of each lane;

[0028] determining real-time situational awareness information of the entering vehicle according to real-time trajectory data of any entering vehicle and real-time traffic efficiency of each lane, and in combination with the relative distance between the entering vehicle and other vehicles in the lane.

[0029] In a feasible solution, the method for real-time situational awareness of the entering vehicle further comprises:

[0030] Let the current position coordinates of any entering vehicle be and the relative position of the entering vehicle in the multi-lane be , then the relative distance between the entering vehicle and other vehicles in the lane is :

[0031] Formula 1;

[0032] In Formula 1, is the entering vehicle, is the other vehicle in the lane, and the real-time situational awareness value of the entering vehicle at this time is :

[0033] Formula 2;

[0034] In Formula 2, is the entering vehicle speed, is the real-time traffic efficiency of the lane, , , are preset weight coefficients, respectively, , , are respectively used to balance the contribution of distance, speed and traffic efficiency, and .

[0035] In a feasible solution, the method for determining the control trajectory of the entering vehicle comprises:

[0036] obtaining situational risk control information of each lane, and in combination with real-time situational awareness information of the entering vehicle, determining a matching lane set of the entering vehicle;

[0037] determining a lane allocation strategy according to the real-time state of each lane and in combination with the situational risk control information of each lane;

[0038] According to the lane allocation strategy, the matching lane set of the entering vehicle is optimized, and the final matching lane of the entering vehicle is determined.

[0039] In a feasible solution, the method for determining the regulated trajectory of the entering vehicle further comprises:

[0040] Supposing that the situation risk level of the final matching lane of the entering vehicle is, the regulated trajectory optimization function of the entering vehicle is :

[0041] Formula 3.

[0042] In formula 3, is the current speed of the entering vehicle, is the recommended speed of the final matching lane, is the safety distance from the front vehicle, is the prediction time window, , , are preset weight coefficients respectively, is the current time;

[0043] According to formula 3, the regulated trajectory of the entering vehicle is determined :

[0044] ;

[0045] wherein, is the acceleration.

[0046] The present application also provides, in a second aspect, a multi-lane situation awareness regulation system based on a smart cloud warehouse, wherein the regulation system adopts the multi-lane situation awareness regulation method based on a smart cloud warehouse according to the first aspect, and further comprises:

[0047] a data acquisition module, configured to acquire real-time state conditions of each lane;

[0048] a data analysis module, configured to analyze and determine real-time traffic efficiency of each lane;

[0049] a situation awareness module, configured to perform real-time situation awareness on the entering vehicle;

[0050] a regulation decision module, configured to regulate the real-time situation of the entering vehicle.

[0051] The present application has the following beneficial effects:

[0052] The application determines the real-time traffic efficiency and situation risk control information of each lane in advance by acquiring the condition of each lane of the intelligent cloud warehouse, realizes the lane control and provides effective reference opinions. Meanwhile, the trajectory data of the entering vehicle is also collected in real time, through the matching with the multi-lane distribution information, the current lane and adjacent lane information of the entering vehicle is accurately positioned, the congestion and collision risk of the entering vehicle in each lane in the future time period is predicted, and strong support is provided for the lane allocation and control decision of the subsequent entering vehicle. That is, the application can quickly respond to the traffic flow allocation of multiple lanes, realize the rapid response to complex traffic situation, and avoid causing congestion or resource waste. BRIEF DESCRIPTION OF DRAWINGS

[0053] Fig. 1 A whole flow schematic diagram of a multi-lane situation awareness regulation and control method based on an intelligent cloud warehouse provided in an embodiment of the application;

[0054] Fig. 2 A flow schematic diagram of determining real-time situation awareness information of an entering vehicle in a multi-lane situation awareness regulation and control method based on an intelligent cloud warehouse provided in an embodiment of the application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0056] If the description of "first", "second" and the like is involved in the embodiments of the application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. Taking "A and / or B" as an example, it includes A solution, or B solution, or A and B solutions. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of those skilled in the art. When the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the protection scope of the application.

[0057] REFERENCE Figs. 1-2The present application provides a multi-lane situation awareness regulation method based on a smart cloud warehouse to solve the problem that the smart cloud warehouse cannot quickly respond to complex traffic situations in the prior art. The regulation method determines the real-time traffic efficiency and situation risk control information of each lane by obtaining the situation of each lane of the smart cloud warehouse in advance, provides effective reference opinions for the control of the lane. At the same time, the trajectory data of the entering vehicle is collected in real time, and through matching with the multi-lane distribution information, the current lane and adjacent lane information of the entering vehicle is accurately positioned, the congestion and collision risk of the entering vehicle in each lane in the future time period is predicted, and strong support is provided for the lane allocation regulation decision of the subsequent entering vehicle. That is, the present application can quickly respond to multi-lane traffic distribution, quickly respond to complex traffic situations, and avoid causing congestion or resource waste.

[0058] Specifically, the present application provides a multi-lane situation awareness regulation method based on a smart cloud warehouse, which comprises: the distribution state of the multi-lane in the smart cloud warehouse can be collected in real time by using multi-source data (such as camera, RFID tag, laser radar, etc. Collection equipment), and the real-time state of the lane is collected at the same time, specifically including the vehicle / goods flow, speed, position and abnormal point (such as control point, congestion point or fault point, etc.) in the lane. Then the real-time traffic efficiency of each lane can be determined according to the real-time state of each lane, that is, the traffic volume of each lane can be predicted in advance, and the real-time traffic efficiency of each lane can be calculated. Then the situation risk control information of each lane can be determined according to the multi-lane distribution information of the smart cloud warehouse and the real-time traffic efficiency of each lane, that is, whether congestion and other abnormal situations will occur can be judged according to the traffic volume of each lane, and then the situation risk control information of each lane is determined. When there are external vehicles, the trajectory of the entering vehicle of the smart cloud warehouse is obtained in advance, the real-time situation of the entering vehicle is perceived, such as collecting the position, speed, type and other conditions of the entering vehicle, and the congestion and collision risk of the entering vehicle in each lane is predicted. Then the real-time situation of the entering vehicle can be regulated according to the situation risk control information of each lane, the regulation trajectory of the entering vehicle is determined, and the risk of congestion and collision of the entering vehicle is avoided. That is, in this embodiment, through matching with the multi-lane distribution information, the current lane and adjacent lane information of the entering vehicle is accurately positioned, the congestion and collision risk of the entering vehicle in each lane in the future time period is predicted, and strong support is provided for the lane allocation regulation decision of the subsequent entering vehicle. That is, the present application can quickly respond to multi-lane traffic distribution, quickly respond to complex traffic situations, and avoid causing congestion or resource waste.

[0059] In the embodiment, in order to facilitate understanding how to calculate the real-time traffic efficiency of each lane, the following is described, specifically, the method for determining the real-time traffic efficiency of each lane comprises: extracting key traffic parameters according to the real-time state of each lane, wherein the key traffic parameters include the traffic volume, average speed and vehicle type distribution of each lane; then according to the multi-lane distribution information of the wisdom cloud warehouse, and combining the historical traffic data of each lane, a preset traffic efficiency evaluation model is constructed, and then the key traffic parameters are input into the traffic efficiency evaluation model based on the preset traffic efficiency evaluation model, and the real-time traffic efficiency of each lane is determined. In the embodiment, in order to ensure the accuracy of the obtained initial traffic efficiency of each lane, the initial traffic efficiency can be corrected in combination with historical traffic data and real-time weather conditions to determine the real-time traffic efficiency of each lane. In addition, it should be noted that the preset traffic efficiency evaluation model can be constructed by collecting historical lane traffic data, and the traffic data covers lane traffic volume and average speed information under different time periods, different weather conditions and different vehicle type distributions; the collected historical lane traffic data is preprocessed to remove abnormal data and noise data, ensuring the accuracy and reliability of the data. Then based on the preprocessed historical lane traffic data, such as using machine learning algorithms, such as neural network algorithms or decision tree algorithms, an initial traffic efficiency evaluation model is constructed; part of the historical lane traffic data is used as a test set to test and verify the initial traffic efficiency evaluation model, the parameters of the model are adjusted according to the test results to improve the accuracy and generalization ability of the model, and then through multiple iterations and optimization, the final preset traffic efficiency evaluation model can be determined.

[0060] In the present embodiment, in order to facilitate understanding how to determine the situation risk control information of each lane, the following is explained, specifically, the method for determining the situation risk control information of each lane comprises: according to the multi-lane distribution information of the intelligent cloud warehouse and the real-time traffic efficiency of each lane, the potential risk points (such as containment points, congestion points or fault points, etc.) currently existing in each lane can be identified. Then, based on the identified potential risk points, the potential risk of each lane is quantitatively evaluated to obtain the risk evaluation value of each lane. Then, according to the risk evaluation value of each lane and the preset risk level division standard, the situation risk control level of each lane can be determined; then the situation risk control level of each lane and the corresponding potential risk point information can be integrated to form the situation risk control information of each lane. In the present embodiment, in order to improve the accuracy and practicality of the situation risk control information, real-time weather conditions, road construction information and other external factors can be further introduced to dynamically correct and update the situation risk control information. At the same time, the preset risk evaluation rules and risk level division standard can be flexibly adjusted and optimized according to the actual application scene and demand. In addition, in the present embodiment, in order to facilitate the quantitative evaluation of the potential risk of each lane, the corresponding basic risk weight can be set according to the type of the potential risk point of each lane; for example, the basic congestion risk weight is set for the lane congestion risk point, the basic collision risk weight is set for the lane collision risk point, and the basic special vehicle risk weight is set for the special vehicle driving risk point (such as ambulance, emergency rescue vehicle occupying lane, etc.); combined with historical risk event data, the probability of actual risk event occurring under different risk point combinations is analyzed as a risk combination coefficient; based on the basic risk weight and the risk combination coefficient, a risk evaluation formula is constructed; the specific formula can be that the basic risk weight of each potential risk point is multiplied by the corresponding risk combination coefficient and then added to obtain a preliminary risk evaluation value; considering the influence of real-time traffic flow change on risk, a flow correction factor is introduced to correct the preliminary risk evaluation value; the flow correction factor can be determined according to the ratio of real-time traffic flow to historical average traffic flow; the risk evaluation value corrected by the flow correction factor is taken as the risk evaluation value of each lane; at the same time, the preset risk level division standard can set multiple level thresholds according to actual demand, and the calculated risk evaluation value is compared with these thresholds to determine the corresponding situation risk control level of each lane. It should be noted that in the present embodiment, the potential risk point comprises one or more combinations of lane congestion risk point, lane collision risk point and special vehicle driving risk point. That is, in the present embodiment, the current risk level of each lane can be determined according to the real-time traffic efficiency of each lane combined with the preset situation risk control rules.The situation risk control rule can be set according to actual needs. For example, when the real-time traffic efficiency of a lane is lower than a preset threshold, it is determined that the lane has a congestion risk, and the risk level of the lane is set to be higher. Or when an abnormal point (such as a control point, a congestion point or a fault point) appears in a lane, it is directly determined that the lane has a safety risk, and the risk level of the lane is set to be the highest. Then, according to the current risk level of each lane, the overall traffic situation of the intelligent cloud warehouse is combined to dynamically adjust the situation risk control information of each lane, so as to ensure the accuracy and effectiveness of the regulation and control decision. For example, when multiple lanes in a certain area of the intelligent cloud warehouse all have congestion risks, the overall risk level of the area can be increased, so that the subsequent regulation and control of the vehicles entering the area can be more strict.

[0061] In the embodiment, in order to facilitate understanding how to perform real-time situation awareness on the entering vehicles, the method of performing real-time situation awareness on the entering vehicles includes: real-time trajectory data of any entering vehicle can be acquired; in order to facilitate understanding the relative position of the entering vehicle in the intelligent cloud warehouse, a lane coordinate system can be constructed according to the multi-lane distribution information of the intelligent cloud warehouse; then the real-time trajectory data of any entering vehicle is mapped into the lane coordinate system to determine the relative position of the entering vehicle in the multi-lane, and then the relative distance between the entering vehicle and other vehicles in the lane can be calculated according to the real-time state of each lane. Finally, the real-time situation awareness information of the entering vehicle can be determined according to the real-time trajectory data of any entering vehicle and the real-time traffic efficiency of each lane, and in combination with the relative distance between the entering vehicle and other vehicles in the lane. In the embodiment, the trajectory data of the entering vehicle can be acquired in real time by deploying a sensor network at the entrance and periphery of the intelligent cloud warehouse; the acquired trajectory data of the entering vehicle is matched with the multi-lane distribution information of the intelligent cloud warehouse to determine the current lane and adjacent lane information of the entering vehicle; then, based on the current lane and adjacent lane information of the entering vehicle, in combination with the real-time traffic efficiency and situation risk control information of each lane, the congestion and collision risks of the entering vehicle in each lane in the future time period can be predicted; the predicted congestion and collision risk results are integrated to form the real-time situation awareness information of the entering vehicle.

[0062] Specifically, the method of performing real-time situation awareness on the entering vehicles further includes:

[0063] Let the current position coordinate of any entering vehicle be The relative position of the entering vehicle in the multi-lane is The relative distance between the entering vehicle and other vehicles in the lane is :

[0064] Equation 1;

[0065] In formula 1, is the entering vehicle, is other vehicles in the lane, at this time the real-time situational awareness value of the entering vehicle is is:

[0066] Formula 2;

[0067] In formula 2, is the entering vehicle speed, is the real-time traffic efficiency of the lane, , , are preset weight coefficients respectively, , , are respectively used to balance the contribution of distance, speed and traffic efficiency, and It should be noted that in actual application, the preset weight coefficients can be set and adjusted according to the actual operation situation and historical data statistics results of the wisdom cloud warehouse. For example, if the historical data shows that the distance factor has a greater impact on vehicle situational awareness, the value of may be appropriately increased; on the contrary, if the speed or traffic efficiency is more significant, the value of or may be increased accordingly. By flexibly adjusting these weight coefficients, the real-time situational awareness value can more accurately reflect the actual situation of the entering vehicle in a multi-lane environment.

[0068] In this embodiment, in order to facilitate understanding how to determine the regulation trajectory of the entering vehicle, the method for determining the regulation trajectory of the entering vehicle comprises: acquiring the situation risk control information of each lane, and determining a matching lane set of the entering vehicle in combination with real-time situation awareness information of the entering vehicle; determining a lane allocation strategy according to a real-time state of each lane in combination with the situation risk control information of each lane; and optimizing the matching lane set of the entering vehicle according to the lane allocation strategy to determine a final matching lane of the entering vehicle. That is, in this embodiment, the optimal driving path of the entering vehicle is planned according to the situation risk control information of each lane and the real-time situation awareness information of the entering vehicle. Specifically, whether a lane is suitable for the entering vehicle to drive can be determined according to the situation risk control level of the lane. If the situation risk control level of a lane is too high, there is a high risk of congestion or collision, and the lane is excluded from the optional path. Meanwhile, in combination with the real-time situation awareness value of the entering vehicle, the relative distance between the entering vehicle and other vehicles in the lane, the speed of the entering vehicle, and the real-time traffic efficiency of the lane are considered to select a relatively safe and efficient lane as the driving path. For example, when the entering vehicle is far away from other vehicles in a lane, the speed of the entering vehicle is moderate, and the real-time traffic efficiency of the lane is high, the lane can be preferentially considered to be included in the driving path. It should be noted that after the regulation trajectory of the entering vehicle is determined, the regulation trajectory information needs to be fed back to the entering vehicle in real time. The relevant information of the optimal driving path, such as the lane number, the driving direction, the predicted driving time, etc., can be accurately conveyed to the driver through a vehicle terminal device or a mobile application, so that the driver can safely drive according to the planned trajectory. At the same time, the system can continuously monitor the actual driving situation of the entering vehicle. If the vehicle deviates from the regulation trajectory or other abnormal situations are found, the system can timely adjust and re-plan to ensure the stability and efficiency of the multi-lane traffic situation.

[0069] In this embodiment, in order to facilitate understanding how to achieve stable and efficient regulation of multi-lane traffic situation, the method for determining the regulation trajectory of the entering vehicle further comprises:

[0070] Let the situation risk control level of the final matching lane of the entering vehicle be, then the regulation trajectory optimization function of the entering vehicle is

[0071] Equation 3;

[0072] In equation 3, is the current speed of the entering vehicle, is the recommended speed of the final matching lane, is the safe distance from the front vehicle, is the prediction time window, is the current time, is the time one hour before the current time; ​

[0073] According to formula 3, the regulation trajectory of the entering vehicle is determined :

[0074] .

[0075] In formula 3, , , are preset weight coefficients for balancing the influence degree of speed deviation, safety distance and lane risk level on the regulation trajectory optimization. It should be noted that these weight coefficients can be flexibly set and adjusted according to the actual operation requirements and historical data statistics results of the wisdom cloud warehouse. For example, if more attention is paid to the matching degree of the driving speed of the vehicle and the recommended speed, the value of may be appropriately increased; if more attention is paid to the safety distance between the vehicle and the front vehicle to avoid collision risk, the value of may be increased; if the lane risk level is more critical to the regulation trajectory, the value of may be correspondingly increased. In addition, according to the regulation trajectory optimization function determined by formula 3, the system can calculate the optimal position , speed and acceleration of the entering vehicle at different time points, thereby forming a complete regulation trajectory . By comprehensively considering the real-time state of the entering vehicle and the real-time traffic efficiency of the lane, and combining the situation risk control information of the lane, the safety and efficiency of the vehicle in the driving process are ensured. In addition, the setting of the prediction time window , can plan the driving path of the vehicle in advance, effectively responding to the possible changes in traffic conditions in the future.

[0076] The application also provides a multi-lane situation awareness regulation system based on the intelligent cloud warehouse in a second aspect. The regulation system adopts the multi-lane situation awareness regulation method based on the intelligent cloud warehouse in the first aspect. The regulation system further comprises a data acquisition module, a data analysis module, a situation awareness module, and a regulation decision module. The data acquisition module is used to acquire the real-time state of each lane. The data analysis module is used to analyze and determine the real-time traffic efficiency of each lane. The situation awareness module is used to perform real-time situation awareness on the entering vehicle. The regulation decision module is used to regulate the real-time situation of the entering vehicle. In this embodiment, the regulation system first needs to deploy a multi-source data acquisition module, such as a high-definition camera, an RFID reader, a laser radar, etc. to capture the vehicle flow, speed change, position information, and any possible abnormal point in the intelligent cloud warehouse, such as a temporary control area, congestion caused by goods accumulation, or a device failure point, etc. Then the collected data is transmitted to the data analysis module. The data analysis module first analyzes the real-time state of each lane and extracts key traffic parameters, including but not limited to lane traffic volume, average speed, and vehicle type distribution, etc. Meanwhile, combined with the preset traffic efficiency evaluation model, the data analysis module can calculate the real-time traffic efficiency of each lane to provide basic data support for subsequent situation risk control. The situation awareness module is responsible for constructing a lane coordinate system according to the obtained entering vehicle trajectory data and the multi-lane distribution information of the intelligent cloud warehouse, and mapping the real-time trajectory of the entering vehicle into the coordinate system to determine the relative position of the vehicle in the multi-lane. Meanwhile, by calculating the relative distance between the entering vehicle and other vehicles in the lane, combined with the real-time traffic efficiency of each lane, the situation awareness module can generate real-time situation awareness information of the entering vehicle, including but not limited to the current safety state of the vehicle, potential congestion or collision risk, etc. The regulation decision module makes a comprehensive judgment according to the information provided by the situation awareness module and the situation risk control information of each lane. First, the regulation decision module determines the matching lane set of the entering vehicle, i.e. those lanes suitable for the vehicle to drive under the current situation. Then, according to the real-time state and situation risk control level of each lane, the regulation decision module formulates a lane allocation strategy to optimize traffic distribution and reduce congestion and collision risk. Finally, through the optimization processing of the matching lane set, the regulation decision module determines the final matching lane of the entering vehicle and generates a corresponding regulation trajectory to guide the entering vehicle to drive safely and efficiently. It should be noted that in actual operation, the optimization of the regulation trajectory also involves the comprehensive consideration of factors such as the speed of the entering vehicle, the safety distance from the front vehicle, and the recommended speed of the final matching lane. By constructing a regulation trajectory optimization function, the regulation system can calculate the optimal driving path and speed control strategy to ensure that the entering vehicle can still maintain fast response and safe driving under complex traffic situation.

[0077] In some embodiments, the control system can communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communications (e.g., a communications network) of any form or medium, including, but not limited to, a local area network ("LAN"), a wide area network ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

[0078] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[0079] A third aspect of the present disclosure provides a computer readable medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method of any one of the first aspect. The computer readable medium in the embodiments of the present disclosure can be written in one or more programming languages or combinations of languages for executing operations of some embodiments of the present disclosure, including an object-oriented programming language such as Java, Smalltalk, C++, and a conventional procedural programming language such as "C" language or similar programming languages. The program code can be executed completely on a user computer, partially on a user computer, as an independent software package, partially on a user computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet by using an Internet service provider).

[0080] The computer program product of the fifth aspect of the present application can be stored in the memory of the electronic device of the first aspect of the present application, and / or can be stored in a computer program product which is separate from the electronic device of the first aspect of the present application.

[0081] In particular, the processes described above with reference to the flow charts can be implemented in computer software programs according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product comprising a computer program which is carried on a computer readable medium and which comprises program code for implementing the methods illustrated in the flow charts.

[0082] The fourth aspect of the present application provides an electronic device, comprising: one or more processors; a memory device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the multi-lane situation awareness regulation method based on the intelligent cloud warehouse as described in the first aspect. Wherein the above-mentioned computer readable medium can be contained in the above-mentioned electronic device; it can also exist separately, that is, not assembled into the electronic device. The above-mentioned computer readable medium carries one or more programs, when the above-mentioned one or more programs are executed by the electronic device, the electronic device can implement the multi-lane situation awareness regulation method based on the intelligent cloud warehouse as described in the first aspect.

[0083] The fifth aspect of the present application provides a computer program product, comprising a computer program which, when executed by a processor, implements the multi-lane situation awareness regulation method based on the intelligent cloud warehouse as described in the first aspect.

[0084] The above description is merely exemplary of some of the many possible embodiments of the present disclosure and of the principles thereof. It is to be understood that those skilled in the art will be able to devise various embodiments of the present disclosure without departing from the scope of the present disclosure as disclosed in the above description and attached claims, and that the scope of the present disclosure is not limited to the specific embodiments described above. For example, the features of the above-described embodiments can be combined with other features of the present disclosure (not only those disclosed in the above description but also those known to those skilled in the art) to form other embodiments of the present disclosure.

Claims

1. A method for multi-lane situation awareness regulation based on intelligent cloud warehouse, characterized in that, The application comprises the following steps: acquiring multi-lane distribution information of the intelligent cloud warehouse and collecting real-time state conditions of each lane; determining real-time traffic efficiency of each lane according to the real-time state conditions of each lane; determining situation risk control information of each lane according to the multi-lane distribution information of the intelligent cloud warehouse and the real-time traffic efficiency of each lane; acquiring the trajectory of an entering vehicle in the intelligent cloud warehouse and performing real-time situation awareness on the entering vehicle; controlling the real-time situation of the entering vehicle according to the situation risk control information of each lane and determining the control trajectory of the entering vehicle; The method for performing real-time situation awareness on the entering vehicle comprises the following steps: Let any entering vehicle's current position coordinate be its relative position in the multi-lane be then the relative distance between the entering vehicle and other vehicles in the lane is Formula 1; In formula 1, is the entering vehicle, is other vehicles in the lane, at this time the real-time situation awareness value of the entering vehicle is: Formula 2; In formula 2, is the entering vehicle speed, is the real-time traffic efficiency of the lane, , , are preset weight coefficients, respectively. In addition, the method for determining the control trajectory of the entering vehicle comprises the following steps: acquiring the situation risk control information of each lane and combining the real-time situation awareness information of the entering vehicle to determine a matching lane set of the entering vehicle; determining a lane allocation strategy according to the real-time state conditions of each lane and the situation risk control information of each lane; optimizing the matching lane set of the entering vehicle according to the lane allocation strategy and determining the final matching lane of the entering vehicle; Specifically, the method for determining the control trajectory of the entering vehicle further comprises the following steps: Let the situational risk level of the final matching lane of the entering vehicle be Then the control trajectory optimization function of the entering vehicle is : Formula 3; In formula 3, is the current speed of the vehicle, is the recommended speed of the final matching lane, is the safety distance from the front vehicle, is the prediction time window, , , are preset weight coefficients, respectively, is the current time; determining a regulated trajectory into the vehicle according to equation 3 : ； wherein is the acceleration. 2.The multi-lane situation awareness regulation method based on the intelligent cloud warehouse according to claim 1, wherein, The method for determining the real-time traffic efficiency of each lane comprises the following steps: extracting key traffic parameters according to the real-time state conditions of each lane; The key traffic parameters comprise lane traffic volume, average vehicle speed and vehicle type distribution; presetting a traffic efficiency evaluation model according to the multi-lane distribution information of the intelligent cloud warehouse and historical traffic data of each lane; inputting the key traffic parameters into the traffic efficiency evaluation model based on the preset traffic efficiency evaluation model to determine the real-time traffic efficiency of each lane. 3.The multi-lane situation awareness regulation method based on the intelligent cloud warehouse according to claim 2, wherein, The method for determining the situation risk control information of each lane comprises the following steps: determining potential risk points currently existing in each lane according to the multi-lane distribution information of the intelligent cloud warehouse and the real-time traffic efficiency of each lane; quantitatively evaluating the potential risk of each lane according to the potential risk points currently existing in each lane to obtain a risk evaluation value of each lane; determining the situation risk control level of each lane according to the risk evaluation value of each lane and a preset risk level division standard; determining the situation risk control information of each lane according to the situation risk control level of each lane and the potential risk points currently existing in each lane.

4. The multi-lane situation awareness regulation method based on the intelligent cloud warehouse according to claim 3, characterized in that, The potential risk points comprise one or more combinations of the following: lane congestion risk points, lane collision risk points and special vehicle driving risk points.

5. The multi-lane situation awareness regulation method based on the intelligent cloud warehouse according to claim 4, characterized in that, The method for performing real-time situation awareness on the entering vehicle comprises the following steps: acquiring real-time trajectory data of any entering vehicle; constructing a lane coordinate system according to the multi-lane distribution information of the intelligent cloud warehouse; mapping the real-time trajectory data of any entering vehicle into the lane coordinate system to determine the relative position of any entering vehicle in the multi-lane; calculating the relative distance between the entering vehicle and other vehicles in the lane according to the real-time state conditions of each lane; determining real-time situation awareness information of the entering vehicle according to the real-time trajectory data of any entering vehicle, the real-time traffic efficiency of each lane and the relative distance between the entering vehicle and other vehicles in the lane.

6. A multi-lane situation awareness regulation system based on a smart cloud warehouse, characterized in that, The method comprises the following steps: a data acquisition module is used to acquire the real-time state of each lane; a data analysis module is used to analyze and determine the real-time traffic efficiency of each lane; a situation awareness module is used to perform real-time situation awareness on the entering vehicles; and a regulation and decision module is used to regulate the real-time situation of the entering vehicles. The method comprises the following steps: a data acquisition module is used to acquire the real-time state of each lane; a data analysis module is used to analyze and determine the real-time traffic efficiency of each lane; a situation awareness module is used to perform real-time situation awareness on the entering vehicles; and a regulation and decision module is used to regulate the real-time situation of the entering vehicles. ​ ​ ​

Images