An airport emergency rescue intelligent navigation method and system based on scene understanding

Abstract

The application relates to the field of artificial intelligence, in particular to an airport emergency rescue intelligent navigation method and system based on scene understanding, which responds to alarm information, determines alarm danger source positions and information of vehicles to be dispatched, establishes a multi-target risk avoidance path planning mathematical model of evacuation and rescue vehicles, plans a target function of the risk avoidance path of the vehicles to be dispatched, and obtains an optimal driving path of the vehicles to be dispatched by solving the target function. The application utilizes scene recognition technology to quickly plan a risk avoidance route, realizes cooperative navigation of evacuation vehicles and rescue vehicles, and guides various vehicles to drive to the nearest safe parking area or rescue target position.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an intelligent navigation method and system for airport emergency rescue based on scene understanding. Background Technology

[0002] With the continuous expansion of modern airports and the increasing complexity of their operations, airport emergency rescue management faces numerous challenges. Existing vehicle management systems primarily rely on GPS positioning technology for vehicle navigation. However, in the complex electromagnetic environment of airports, GPS signals are susceptible to interference, making it difficult to meet the precise positioning requirements of emergency rescue. This limitation of positioning technology prevents vehicles from accurately identifying safe parking areas, severely impacting emergency rescue efficiency.

[0003] In terms of scene recognition, existing systems mainly use visual cameras to identify fixed ground markings. However, these systems are primarily designed for pre-marked, fixed scenes and lack the ability to effectively identify and process dynamic scene changes such as temporary construction areas and temporary markings in emergencies. This limitation is particularly pronounced in emergency rescue scenarios, as it cannot adapt to complex and ever-changing on-site environments and increases safety hazards during rescue operations.

[0004] In terms of vehicle dispatching and management, existing technologies mainly rely on manual dispatching and driving, resulting in low levels of systematization and automation. In emergencies, this traditional manual dispatching model suffers from slow response times, a limited information transmission mechanism relying primarily on radio communication, and a lack of multi-dimensional human-vehicle information interaction methods. This hinders the rapid and accurate transmission of emergency information, impacting the timeliness and effectiveness of rescue efforts.

[0005] To address the aforementioned technical challenges, it is necessary to develop an intelligent navigation system that integrates high-precision positioning, scene understanding, and human-vehicle collaborative functions. Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] The main objective of this invention is to provide an intelligent navigation method and system for airport emergency rescue based on scene understanding, so as to solve the key technical problems in the prior art, such as limited scene recognition capability and low efficiency of human-vehicle collaboration.

[0008] (II) Technical Solution

[0009] To achieve the above objectives, the present invention provides an intelligent navigation method for airport emergency rescue based on scene understanding, comprising the following steps:

[0010] S1, Receive and respond to alarm information, and determine the location of the alarm hazard source based on the alarm information;

[0011] S2, determine the information of the vehicles to be dispatched based on the location of the hazard source;

[0012] S3, the objective function for planning the avoidance paths of the vehicles that need to be dispatched, includes:

[0013] S31, Based on the optimization objective, establish the objective function:

[0014] Objective function 1: Total distance traveled by the evacuation vehicles Minimum;

[0015] Objective function 2: Evacuation time of the last vehicle Minimum;

[0016] Objective function 3: Arrival time of rescue vehicles Minimum;

[0017] S32, Establishing constraints:

[0018] Uniqueness constraint: Each vehicle requiring dispatch is assigned to a unique safe parking location;

[0019] Speed ​​constraints: The speed of each vehicle to be dispatched must comply with the preset speed limit range;

[0020] Hazardous area constraints: The distance between the travel path of each dispatchable vehicle and the hazard source must meet the safe distance requirements;

[0021] Priority constraints: Evacuation priority constraints for vehicles that need to be dispatched;

[0022] S4. By solving the objective function, the optimal driving path for the vehicles to be dispatched is obtained.

[0023] Preferably, step S2 further includes: determining the information of the vehicle to be dispatched based on the location of the hazard source, and issuing an alarm to the vehicle to be dispatched and the corresponding personnel or nearby personnel of the vehicle to be dispatched; the alarm includes: mobile terminal alarm or on-site alarm.

[0024] Preferably, in step S31:

[0025] Objective function 1: Total distance traveled by the evacuation vehicles Minimum;

[0026] ,

[0027] In the formula, V represents the set of vehicles that need to be evacuated. Indicates that vehicle i starts from its current position. To the designated safe parking location The path distance;

[0028] Objective function 2: Evacuation time of the last vehicle Minimum;

[0029] ,

[0030] In the formula, This indicates the time when vehicle i reaches a safe position. Indicates the moment when vehicle i begins to evacuate;

[0031] ,

[0032] This represents the actual speed of vehicle i at time t;

[0033] Objective function 3: Arrival time of rescue vehicles Minimum;

[0034] ;

[0035] In the formula, R represents the set of rescue vehicles. This indicates the time when rescue vehicle j arrives at the rescue location. This is the start time;

[0036] ,

[0037] This indicates the distance of rescue vehicle j from its initial position to the hazard source. This indicates the speed of rescue vehicle j.

[0038] Preferably, in step S32:

[0039] Uniqueness constraint: Each vehicle requiring dispatch is assigned to a unique safe parking location; ,

[0040] In the formula, The variable is a 0-1 decision variable, with a value of 1 when vehicle i is assigned to parking space j at time t, and 0 otherwise; V is the set of vehicles that need to be evacuated; P is the set of safe parking locations; T is the time series set.

[0041] ;

[0042] Speed ​​constraints: The speed of each vehicle to be dispatched must comply with the preset speed limit range; ,

[0043] In the formula, Let be the actual speed of vehicle i at time t. Let be the minimum permissible speed of vehicle i. Let V be the maximum permissible speed of vehicle i, and V∪R represent the set of all evacuation and rescue vehicles;

[0044] Hazardous area constraints: The distance between the travel path of each dispatchable vehicle and the hazard source must meet the safe distance requirements; ,

[0045] In the formula, Let be the distance from vehicle i to hazard source d at time t. Where D is the preset danger distance threshold, and D is the set of danger source locations;

[0046] , Let be the position coordinates of vehicle i at time t. Let be the coordinates of the location of hazard source d at time t;

[0047] Priority constraints: Evacuation priority constraints for vehicles that need to be dispatched; M is a positive number that ensures that rescue vehicles have higher priority than all evacuation vehicles; R is the set of rescue vehicles;

[0048] , In the formula, priority(i) is the priority score of vehicle i. The larger the value, the higher the evacuation priority of the vehicle. for The minimum distance from vehicle i to all hazard sources at any given time; Let be the distance from vehicle i to its target parking position p; This refers to the risk weighting coefficient. This is the distance weighting coefficient.

[0049] Preferably, step S4 includes:

[0050] S41, Population Initialization: Calculate a suitable chromosome encoding scheme to represent the solution to the problem. In the formula, Let i represent the path point sequence of the i-th vehicle; This represents the speed value at the corresponding path point, which must satisfy the speed constraint of formula (8); The matrix representing the allocation relationship between vehicles and parking spaces satisfies the uniqueness constraints of formulas (6) and (7); n is the total number of vehicles, including evacuation vehicles and rescue vehicles; m is the number of control points for each path;

[0051] S42, Objective Function Evaluation: Calculate three objective function values ​​for each individual: In the formula, Calculate the total travel distance of the evacuation vehicles according to formula (1); Calculate the maximum completion time using formulas (2) and (3); Calculate the arrival time of the rescue vehicle according to formulas (4) and (5);

[0052] S43, Fast Non-Dominated Sort: Based on an objective function, it performs a non-dominated sort on individuals in a population, dividing the population into different levels;

[0053] S44, Crowding Calculation: Calculate the crowding level for each individual. In the formula, M is the number of objective functions; Let i be the function value of individual i on the k-th objective; and These are the maximum and minimum values ​​of the k-th target, respectively;

[0054] S45, Selection Operation, employing a tournament selection method, compares the merits of two individuals, including:

[0055] Compare the levels of dominance; the one with the lower level wins.

[0056] When the levels are the same, the degree of crowding is compared, and the one with the higher degree of crowding wins.

[0057] Select NP individuals to form the parent population;

[0058] S46, Adaptive Crossover Operation:

[0059] Introducing adaptive crossover probability pc: , In the formula, pc1 and pc2 are the upper and lower limits of the crossover probability; The fitness value of the better individual participating in the crossover; and These are the maximum and minimum fitness values ​​in the population, respectively;

[0060] Perform SBX crossover on the selected parent individuals: In the formula, p1 and p2 are parent individuals; c1 and c2 are child individuals; The cross-distribution index;

[0061] S47, Adaptive mutation operation: Adaptive mutation probability pm , In the formula, pm1 and pm2 are the upper and lower limits of the mutation probability; f is the fitness value of the individual to be mutated.

[0062] S48, an elite retention strategy, includes:

[0063] The parent population Pt and the offspring population Qt are merged to form a population Rt of size 2NP;

[0064] Perform non-dominated sorting and crowding calculation on Rt;

[0065] Based on the rank and crowding degree, select NP optimal individuals to form a new population Pt+1;

[0066] Determine if the termination condition is met. If not, return to step S45. If it is met, terminate the iteration and obtain a set of Pareto optimal solutions as the optimal driving path for the vehicles to be scheduled.

[0067] Preferably, the method further includes the step of updating the location of the hazard source and returning to step S1.

[0068] Preferably, after step S4, the method further includes: updating the optimal driving route to the mobile terminal of the vehicle to be dispatched or the corresponding driver in real time.

[0069] The present invention also provides an airport emergency rescue intelligent navigation system based on scene understanding, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-described airport emergency rescue intelligent navigation method based on scene understanding.

[0070] (III) Beneficial Effects

[0071] This application proposes an intelligent navigation method and system for airport emergency rescue based on scene understanding. Compared with the prior art, the present invention has the following advantages:

[0072] (1) This invention provides a complete solution integrating high-precision positioning, scene understanding and human-vehicle collaboration. Through the organic combination of multi-functional modules, it significantly improves the level of intelligence in airport emergency rescue process.

[0073] (2) This invention establishes a mathematical model for multi-objective risk avoidance path planning, and can quickly obtain the Pareto optimal solution set through the improved NSGA-II algorithm. Attached Figure Description

[0074] Figure 1 This embodiment provides a schematic flowchart of an intelligent navigation method for airport emergency rescue based on scene understanding.

[0075] Figure 2 This is a schematic diagram of the hardware structure of an airport emergency rescue intelligent navigation system based on scene understanding, provided in this embodiment. Detailed Implementation

[0076] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0077] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0078] Please combine them together Figure 1 and Figure 2 This embodiment provides an intelligent navigation method for airport emergency rescue based on scene understanding, which includes steps S1 to S4.

[0079] S1 receives and responds to alarm information, and determines the location of the alarm hazard source based on the alarm information.

[0080] S2, determine the information of the vehicles to be dispatched based on the location of the hazard source.

[0081] In one specific implementation, the system first receives alarm information sent from the backend and then uses a parser to identify and analyze the alarm information type. For example, a 5G network (SA+NSA dual mode) can be used as the primary communication method to receive backend alarm information. When the 5G signal quality is poor, the system will automatically switch to a 4G network to ensure communication reliability. After receiving the alarm information, the system immediately determines the specific location coordinates of the hazard source and initiates the emergency response procedure.

[0082] A multi-layered human-vehicle information interaction mechanism is activated, displaying real-time warning information including the location and level of hazards on the vehicle's LED display screen, while simultaneously pushing detailed warning information to the driver's mobile device. The system also triggers the phone's vibration alert function and issues different levels of audible and visual alarms based on the hazard level, ensuring rapid and accurate transmission of emergency information.

[0083] S3, the objective function for planning the avoidance paths of the vehicles that need to be dispatched, includes:

[0084] S31, Based on the optimization objective, establish the objective function:

[0085] Objective function 1: Total distance traveled by the evacuation vehicles Minimum;

[0086] Objective function 2: Evacuation time of the last vehicle Minimum;

[0087] Objective function 3: Arrival time of rescue vehicles Minimum;

[0088] S32, Establishing constraints:

[0089] Uniqueness constraint: Each vehicle requiring dispatch is assigned to a unique safe parking location;

[0090] Speed ​​constraints: The speed of each vehicle to be dispatched must comply with the preset speed limit range;

[0091] Hazardous area constraints: The distance between the travel path of each dispatchable vehicle and the hazard source must meet the safe distance requirements;

[0092] Priority constraints: Evacuation priority constraints for vehicles that need to be dispatched.

[0093] This embodiment aims to solve the path optimization problem in the process of multi-target vehicle evacuation, and mainly considers three optimization objectives: to minimize the total travel distance of all evacuation vehicles and improve evacuation efficiency; to ensure the timeliness of the overall evacuation process, it is necessary to minimize the time it takes for the last evacuation vehicle to reach the safe area; and to improve rescue efficiency, it is necessary to ensure that rescue vehicles reach the rescue area in the shortest possible time.

[0094] Objective function 1 optimizes the total travel distance by minimizing the sum of the path distances of all evacuation vehicles. Objective function 1: Minimize the total travel distance of evacuation vehicles. , In the formula, V represents the set of vehicles that need to be evacuated. Indicates that vehicle i starts from its current position. To the designated safe parking location The objective function is to determine the path distance, ensuring that all evacuation vehicles choose the optimal route and reduce unnecessary detours.

[0095] Objective function 2 aims to ensure overall evacuation efficiency by calculating and minimizing the time required for the last vehicle to complete the evacuation. Objective function 2: Minimize the evacuation time of the last vehicle. ; In the formula, This indicates the time when vehicle i reaches a safe position. This indicates the moment when vehicle i begins to evacuate.

[0096] Calculate the evacuation time for each vehicle: ; This represents the actual speed of vehicle i at time t.

[0097] Objective function 3 aims to improve rescue effectiveness by minimizing the response time of rescue vehicles. Objective function 3: Minimize the arrival time of rescue vehicles. ; In the formula, R represents the set of rescue vehicles. This indicates the time when rescue vehicle j arrives at the rescue location. This is the start time.

[0098] Calculation of rescue vehicle travel time: , In the formula, This indicates the distance of rescue vehicle j from its initial position to the hazard source. This indicates the speed of rescue vehicle j.

[0099] To ensure the feasibility and safety of the solution, the implementation plan incorporates a strict system of constraints. Uniqueness constraints ensure that each evacuation vehicle is assigned to a unique safe parking location, preventing conflicts; speed constraints ensure driving safety by reasonably limiting vehicle speed; danger zone constraints prevent vehicles from entering high-risk areas; and an evacuation / rescue priority constraint mechanism based on vehicle type and distance is also established.

[0100] (1) Uniqueness constraint:

[0101] This constraint ensures that each evacuation vehicle is assigned to a unique safe parking location, and that each parking space can only be assigned to one vehicle. This one-to-one mapping avoids conflicts between vehicle destinations, ensuring the orderly conduct of the evacuation process.

[0102] The sole allocation of vehicles to parking spaces: , In the formula, The variable is a 0-1 decision variable, which takes the value 1 when vehicle i is assigned to parking space j at time t, and 0 otherwise; V is the set of vehicles that need to be evacuated; P is the set of safe parking locations; and T is the time series set.

[0103] The sole occupant of the parking space: .

[0104] (2) Speed ​​constraints:

[0105] To ensure safe vehicle operation, it is necessary to reasonably limit vehicle speed. At the same time, setting a minimum speed prevents vehicles from coming to a standstill, ensuring the continuity of evacuation. ; In the formula, Let be the actual speed of vehicle i at time t. Let be the minimum permissible speed of vehicle i. Let V be the maximum permissible speed of vehicle i, and V∪R represent the set of all evacuation and rescue vehicles.

[0107] (3) Hazardous area constraints:

[0108] To ensure vehicles maintain a safe distance from hazards and prevent them from entering high-risk areas, while also considering the dynamic characteristics of hazards and adjusting vehicle avoidance behavior in real time, it is necessary to identify hazardous areas.

[0109] (9); In the formula, Let be the distance from vehicle i to hazard source d at time t. D is the preset danger distance threshold, and D is the set of danger source locations.

[0110] Distance calculation formula: ; In the formula, Let be the position coordinates of vehicle i at time t. Let be the coordinates of the location of hazard source d at time t.

[0111] (4) Evacuation / Rescue Priority Constraints:

[0112] Priority constraints are used to determine the evacuation order of vehicles. They take into account factors such as the distance between the vehicle and the hazard source and the vehicle type, and calculate the evacuation priority of each vehicle. Vehicles with higher priority will be given priority to evacuate.

[0113] Rescue vehicles have the highest priority, above all evacuation vehicles. Therefore, the priority of rescue vehicles is: ; In the formula, M is a sufficiently large positive number to ensure that rescue vehicles have a higher priority than all evacuation vehicles; R is the set of rescue vehicles.

[0114] Priority for evacuation vehicles: ; In the formula, priority(i) is the priority score of vehicle i. The larger the value, the higher the evacuation priority of the vehicle. for The minimum distance from vehicle i to all hazard sources at any given time; Let be the distance from vehicle i to its target parking position p; This refers to the risk weighting coefficient. This is the distance weighting coefficient.

[0115] S4. By solving the objective function, the optimal driving path for the vehicles to be dispatched is obtained.

[0116] This embodiment employs an improved NSGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm to solve a multi-objective optimization problem. The NSGA-II algorithm is a multi-objective evolutionary algorithm based on Pareto dominance relations, characterized by high computational efficiency and good convergence. Specifically addressing the characteristics of multi-vehicle disaster avoidance and rescue path planning problems, this invention improves the traditional NSGA-II algorithm, primarily by: employing adaptive crossover and mutation operators to enhance search efficiency; introducing an elite retention strategy to accelerate convergence; and designing a targeted encoding scheme to better represent the characteristics of the solution.

[0117] Preferably, step S4 includes:

[0118] S41, Population Initialization: Calculate a suitable chromosome encoding scheme to represent the solution to the problem. In the formula, Let i represent the path point sequence of the i-th vehicle; This represents the speed value at the corresponding path point, which must satisfy the speed constraint of formula (8); The matrix representing the allocation relationship between vehicles and parking spaces satisfies the uniqueness constraints of formulas (6) and (7); n is the total number of vehicles, including evacuation vehicles and rescue vehicles; m is the number of control points for each path.

[0119] S42, Objective Function Evaluation: Calculate three objective function values ​​for each individual: , In the formula, Calculate the total travel distance of the evacuation vehicles according to formula (1); Calculate the maximum completion time using formulas (2) and (3); The arrival time of the rescue vehicle is calculated according to formulas (4) and (5).

[0120] S43, Fast Non-Dominated Sort: Based on an objective function, it performs a non-dominated sort on individuals in a population, dividing the population into different levels.

[0121] S44, Crowding Calculation: To maintain population diversity, the crowding level of each individual is calculated. , In the formula, M is the number of objective functions; Let i be the function value of individual i on the k-th objective; and These are the maximum and minimum values ​​of the k-th target, respectively.

[0122] S45, Selection Operation, employing a tournament selection method, compares the merits of two individuals, including:

[0123] Comparing dominance levels, the lower the level, the better; a lower level means the solution is less dominated, closer to the Pareto optimal front, and of better quality.

[0124] When the ranks are the same, crowding is compared, and the one with greater crowding wins; this helps to maintain the diversity of the population and makes the final Pareto front distribution more uniform.

[0125] Select NP individuals to form the parent population.

[0126] S46, Adaptive Crossover: In the evolutionary process, crossover is an important means of generating new individuals, and its intensity is controlled by the crossover probability. Different individuals have different evolutionary needs: for individuals with poor fitness, a higher crossover probability is needed to accelerate improvement; for individuals with good fitness, a lower crossover probability should be used to protect their characteristics.

[0127] Introducing adaptive crossover probability pc: , In the formula, pc1 and pc2 are the upper and lower limits of the crossover probability; The fitness value of the better individual participating in the crossover; and These are the maximum and minimum fitness values ​​in the population, respectively;

[0128] Perform SBX crossover on the selected parent individuals: In the formula, p1 and p2 are parent individuals; c1 and c2 are child individuals; The cross-distribution index;

[0129] S47, Adaptive Mutation Operation: The mutation operation increases population diversity by locally perturbing individuals, and its strength is determined by the mutation probability. Similar to the crossover operation, the strength of the mutation operation should also be dynamically adjusted according to the quality of the individuals: for poorer individuals, larger mutations help them escape local optima; for better individuals, mild mutations can fine-tune existing characteristics while preserving them. Based on this, an adaptive mutation probability adjustment mechanism was designed.

[0130] Adaptive mutation probability pm, , In the formula, pm1 and pm2 are the upper and lower limits of the mutation probability; f is the fitness value of the individual to be mutated.

[0131] S48, Elite Preservation Strategy: To ensure the stability of the evolutionary process and the continuous improvement of the solution set quality, this scheme adopts an elite preservation strategy. This strategy preserves superior individuals and maintains population diversity through merging parent and offspring populations, non-dominant ordering, and crowding calculation. This mechanism ensures the correctness of the evolutionary direction while avoiding premature population convergence. Includes:

[0132] The parent population Pt and the offspring population Qt are merged to form a population Rt of size 2NP;

[0133] Perform non-dominated sorting and crowding calculation on Rt;

[0134] Based on the rank and crowding degree, select NP optimal individuals to form a new population Pt+1;

[0135] Determine if the termination condition is met. If not, return to step S45. If it is met, terminate the iteration and obtain a set of Pareto optimal solutions as the optimal driving path for the vehicles to be scheduled.

[0136] Preferably, the method further includes the step of updating the location of the hazard source and returning to step S1.

[0137] Preferably, after step S4, the method further includes: updating the optimal driving route to the mobile terminal of the vehicle to be dispatched or the corresponding driver in real time.

[0138] like Figure 2 As shown, this application also provides an airport emergency rescue intelligent navigation system based on scene understanding, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the airport emergency rescue intelligent navigation method based on scene understanding as described above.

[0139] like Figure 2 As shown, this embodiment / computer 6 includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60, such as a program for running a scene-understanding-based intelligent navigation method for airport emergency rescue. When the processor 60 executes the computer program 62, it implements the steps described in the various embodiments of running a scene-understanding-based intelligent navigation method for airport emergency rescue. Alternatively, when the processor 60 executes the computer program 62, it implements the functions of each module / unit in the various device embodiments described above.

[0140] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the computer 6.

[0141] The computer 6 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The computer 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 2 This is merely an example of computer 6 and does not constitute a limitation on computer 6. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer 6 may also include input / output devices, network access devices, buses, etc.

[0142] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0143] The memory 61 can be an internal storage unit of the computer 6, such as a hard drive or memory. The memory 61 can also be an external storage device of the computer 6, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device. Furthermore, the memory 61 can include both internal storage units and external storage devices of the computer 6. The memory 61 is used to store the computer program and other programs and data required by the terminal device. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0144] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0145] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0146] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0147] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0148] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0149] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0150] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0151] The above are merely specific application examples of the present invention and do not constitute any limitation on the scope of protection of the present invention. In addition to the above embodiments, the present invention may have other implementations. All technical solutions formed by equivalent substitution or equivalent transformation fall within the scope of protection claimed by the present invention.

Claims

1. A scene-understanding-based intelligent navigation method for airport emergency rescue, characterized in that, Including the following steps: S1, Receive and respond to alarm information, and determine the location of the alarm hazard source based on the alarm information; S2, determine the information of the vehicles to be dispatched based on the location of the hazard source; S3, the objective function for planning the avoidance paths of the vehicles that need to be dispatched, includes: S31, Based on the optimization objective, establish the objective function: Objective function 1: Total distance traveled by the evacuation vehicles Minimum; Objective function 2: Evacuation time of the last vehicle Minimum; Objective function 3: Arrival time of rescue vehicles Minimum; S32, Establishing constraints: Uniqueness constraint: Each vehicle requiring dispatch is assigned to a unique safe parking location; Speed ​​constraints: The speed of each vehicle to be dispatched must comply with the preset speed limit range; Hazardous area constraints: The distance between the travel path of each dispatchable vehicle and the hazard source must meet the safe distance requirements; Priority constraints: Evacuation priority constraints for vehicles that need to be dispatched; S4. By solving the objective function, the optimal driving path for the vehicles to be dispatched is obtained.

2. The intelligent navigation method for airport emergency rescue based on scene understanding according to claim 1, characterized in that, Step S2 further includes: determining the information of the vehicle to be dispatched based on the location of the hazard source, and issuing an alarm to the vehicle to be dispatched and the corresponding personnel or nearby personnel of the vehicle to be dispatched; the alarm includes: mobile terminal alarm or on-site alarm.

3. The intelligent navigation method for airport emergency rescue based on scene understanding according to claim 1, characterized in that, In step S31: Objective function 1: Total distance traveled by the evacuation vehicles Minimum; ， In the formula, V represents the set of vehicles that need to be evacuated. Indicates that vehicle i starts from its current position. To the designated safe parking location The path distance; Objective function 2: Evacuation time of the last vehicle Minimum; ， In the formula, This indicates the time when vehicle i reaches a safe position. Indicates the moment when vehicle i begins to evacuate; ， This represents the actual speed of vehicle i at time t; Objective function 3: Arrival time of rescue vehicles Minimum; ； In the formula, R represents the set of rescue vehicles. This indicates the time when rescue vehicle j arrives at the rescue location. This is the start time; ， This indicates the distance of rescue vehicle j from its initial position to the hazard source. This indicates the speed of rescue vehicle j.

4. The intelligent navigation method for airport emergency rescue based on scene understanding according to claim 3, characterized in that, In step S32: Uniqueness constraint: Each vehicle requiring dispatch is assigned to a unique safe parking location; ， In the formula, The variable is a 0-1 decision variable, with a value of 1 when vehicle i is assigned to parking space j at time t, and 0 otherwise; V is the set of vehicles that need to be evacuated; P is the set of safe parking locations; T is the time series set. ； Speed ​​constraints: The speed of each vehicle to be dispatched must comply with the preset speed limit range; , In the formula, Let be the actual speed of vehicle i at time t. Let be the minimum permissible speed of vehicle i. Let V be the maximum permissible speed of vehicle i, and V∪R represent the set of all evacuation and rescue vehicles; Hazardous area constraints: The distance between the travel path of each dispatchable vehicle and the hazard source must meet the safe distance requirements; ， In the formula, Let be the distance from vehicle i to hazard source d at time t. Where D is the preset danger distance threshold, and D is the set of danger source locations; , Let be the position coordinates of vehicle i at time t. Let be the coordinates of the location of hazard source d at time t; Priority constraints: Evacuation priority constraints for vehicles that need to be dispatched; M is a positive number that ensures that rescue vehicles have higher priority than all evacuation vehicles; R is the set of rescue vehicles; In the formula, priority(i) is the priority score of vehicle i. The larger the value, the higher the evacuation priority of the vehicle. for The minimum distance from vehicle i to all hazard sources at any given time; Let be the distance from vehicle i to its target parking position p; This refers to the risk weighting coefficient. This is the distance weighting coefficient.

5. The intelligent navigation method for airport emergency rescue based on scene understanding according to claim 4, characterized in that, Step S4 includes: S41, Population Initialization: Design a suitable chromosome encoding scheme to represent the solution to the problem. In the formula, Let i represent the path point sequence of the i-th vehicle; This represents the speed value at the corresponding path point, which must satisfy the speed constraint of formula (8); The matrix representing the allocation relationship between vehicles and parking spaces satisfies the uniqueness constraints of formulas (6) and (7); n is the total number of vehicles, including evacuation vehicles and rescue vehicles; m is the number of control points for each path; S42, Objective Function Evaluation: Calculate three objective function values ​​for each individual: In the formula, Calculate the total travel distance of the evacuation vehicles according to formula (1); Calculate the maximum completion time using formulas (2) and (3); Calculate the arrival time of the rescue vehicle according to formulas (4) and (5); S43, Fast Non-Dominated Sort: Based on an objective function, it performs a non-dominated sort on individuals in a population, dividing the population into different levels; S44, Crowding Calculation: Calculate the crowding level for each individual. In the formula, Q represents the number of objective functions; Let i be the function value of individual i on the k-th objective; and These are the maximum and minimum values ​​of the k-th target, respectively; S45, Selection Operation, employing a tournament selection method, compares the merits of two individuals, including: Compare the levels of dominance; the one with the lower level wins. When the levels are the same, the degree of crowding is compared, and the one with the higher degree of crowding wins. Select NP individuals to form the parent population; S46, Adaptive Crossover Operation: Introducing adaptive crossover probability pc: In the formula, pc1 and pc2 are the upper and lower limits of the crossover probability; The fitness value of the better individual participating in the crossover; and These are the maximum and minimum fitness values ​​in the population, respectively; Perform SBX crossover on the selected parent individuals: In the formula, p1 and p2 are parent individuals; c1 and c2 are child individuals; The cross-distribution index; S47, Adaptive mutation operation: Adaptive mutation probability pm ， In the formula, pm1 and pm2 are the upper and lower limits of the mutation probability; f is the fitness value of the individual to be mutated. S48, an elite retention strategy, includes: The parent population Pt and the offspring population Qt are merged to form a population Rt of size 2NP; Perform non-dominated sorting and crowding calculation on Rt; Based on the rank and crowding degree, select NP optimal individuals to form a new population Pt+1; Determine if the termination condition is met. If not, return to step S45. If it is met, terminate the iteration and obtain a set of Pareto optimal solutions as the optimal driving path for the vehicles to be scheduled.

6. A scene-understanding-based intelligent navigation method for airport emergency rescue according to any one of claims 1-5, characterized in that, It also includes the step of updating the location of the hazard source and returning to step S1.

7. The intelligent navigation method for airport emergency rescue based on scene understanding according to claim 6, characterized in that, After step S4, the method further includes: updating the optimal driving route to the mobile terminal of the vehicle to be dispatched or the corresponding driver in real time.

8. An airport emergency rescue intelligent navigation system based on scene understanding, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent navigation method for airport emergency rescue based on scene understanding as described in any one of claims 1 to 7.

Images