Control method and system for multi-machine cooperative security patrol car based on autonomous navigation

Abstract

The invention relates to a control method and system for a security patrol car based on autonomous navigation multi-machine cooperation, and the method comprises the steps: U1, enabling a plurality of security patrol cars to carry out a patrol task, collecting the data information of the historical driving track of each patrol car, obtaining the data information of the position and state of each patrol car in real time, and carrying out the data information of the position and state of each patrol car; the method comprises the following steps: constructing a multi-machine cooperative path planning model of a security patrol car, predicting a track point of each patrol car based on an improved BP neural network regression prediction algorithm of a Spearman correlation coefficient to obtain predicted data information of the track point of each patrol car, constructing the multi-machine cooperative path planning model of the security patrol car, and performing synchronous dynamic planning on a driving path of each patrol car to obtain a multi-machine cooperative path planning model of the security patrol car. And data information of the planned driving path of each patrol car is obtained. Inspection security tasks of different vehicles can be shared at the cloud terminal, task arrangement is changed according to execution conditions of the tasks, group operation efficiency of the security patrol car is improved, and practical application value of the security patrol car is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of security patrol vehicles, and in particular to a control method and system for a security patrol vehicle based on autonomous navigation and multi-machine collaboration. Background Art

[0002] As cities continue to expand, security work plays an increasingly important role in today's society. In densely populated areas such as residential communities, commercial areas, and business office areas, various incidents occur frequently, and it is often necessary to deploy police officers and patrol cars to facilitate patrol inspections and rapid response to emergency incidents.

[0003] However, judging from the functions currently demonstrated in the industry, the service focus of security patrol cars (robots) will be on monitoring and patrolling. Through fully autonomous patrolling and monitoring in the scene, data from the real world will be collected, and then analyzed and identified through AI algorithms to identify dangerous factors that affect social security, provide feedback to the background and remind humans or contact the police for processing.

[0004] As for automatic patrol, that is, patrol based on autonomous navigation system, the industry mostly purchases laser SLAM technology. Although SLAM technology is constantly being updated, the current single-vehicle (robot) mapping and navigation technology has a certain degree of robustness. However, when faced with mapping requirements in large-scale environments, global errors will continue to accumulate, and the mapping accuracy of single vehicles (robots) will be greatly affected. In addition, in some harsh environments, when a single vehicle fails unexpectedly, it will be unable to complete the security task.

[0005] Compared with single-vehicle intelligence, multi-vehicle intelligent collaborative technology has stronger perception and action capabilities in large and complex scenarios, and is the key to improving efficiency and robustness. It includes complex scene matching, path planning and cruising, obstacle avoidance, and intelligent monitoring of targets in military and civilian activities. Summary of the invention

[0006] In view of the above problems, the present invention provides a control method and system for a multi-machine collaborative security patrol vehicle based on autonomous navigation. Not only can the inspection and security tasks of different vehicles be shared on the cloud terminal, and the task arrangement can be changed according to the execution of the task to expand the group operation efficiency of the security patrol vehicle, but also the practical application value of the security patrol vehicle is improved.

[0007] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a control method of a multi-machine collaborative security patrol vehicle based on autonomous navigation, the method comprising:

[0008] U1. Multiple security patrol cars are on patrol missions, collecting data information on the historical driving trajectory of each patrol car, and obtaining data information on the location and status of each patrol car in real time;

[0009] U2. Based on the data information of the historical driving trajectory of each patrol car, the trajectory point of each patrol car is predicted by using an improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient to obtain the data information of the trajectory point of each patrol car after the prediction;

[0010] U3. Based on the data information of the predicted trajectory points of each patrol car, the data information of the position of each patrol car and the data information of the state of each patrol car, a multi-machine collaborative path planning model for security patrol cars is constructed, and the driving path of each patrol car is synchronously and dynamically planned to obtain the data information of the planned driving path of each patrol car;

[0011] U4. Based on the data information of the planned driving path of each patrol car, the driving path of the patrol car is optimized by using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm to obtain the optimized data information of the driving path of each patrol car.

[0012] Furthermore, in step U2, the prediction of the trajectory points of each patrol car using the improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient includes:

[0013] U21. Based on the data information of the historical driving trajectory of each patrol car, establish the Spearman correlation function Q of the patrol car,

[0014]

[0015] Among them, x i is the data information of the historical driving trajectory of the i-th patrol car, f is the rank function of the historical driving trajectory of the patrol car, n is the sample size, λ i is a weight factor of the patrol car's historical driving trajectory, characterizes the relevance of the patrol car's historical driving trajectory, and obtains data information on the relevance of the patrol car's historical driving trajectory;

[0016] U22. The data information of the correlation of the historical driving trajectory of the patrol car is input into the BP neural network for training and learning, and the regression prediction function W of the trajectory point of the patrol car is determined.

[0017] Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car, and the regression prediction parameters of the trajectory points of α1, α2 and α3 patrol cars are obtained to obtain the trained neural network model;

[0018] U23. Based on the trained neural network model, the data information of the historical driving trajectory of each patrol car is input, and the trajectory points of each patrol car are predicted to obtain the data information of the predicted trajectory points of each patrol car.

[0019] Furthermore, the regression prediction parameters α1, α2 and α3 of the trajectory points of the patrol car are,

[0020]

[0021]

[0022] Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car.

[0023] Furthermore, the ranking function f of the historical driving trajectory of the patrol car is,

[0024]

[0025] Among them, x i is the data information of the historical driving trajectory of the i-th patrol car.

[0026] Furthermore, in step U3, the multi-machine collaborative path planning model of the security patrol car is constructed, and the synchronous dynamic planning of the driving path of each patrol car includes:

[0027] U31. Based on the predicted trajectory point data information of each patrol car, the position data information of each patrol car and the state data information of each patrol car, a patrol car Fourier series fitting trajectory point distribution function R is established.

[0028]

[0029] , where r1 is the data information of the trajectory point of each patrol car after prediction, r2 is the data information of the position of each patrol car, r3 is the data information of the state of each patrol car, δ1, δ2 and δ3 are the penalty weight factors of the patrol car trajectory point distribution, g is the Dirac function of the patrol car trajectory point distribution, and the distribution of the patrol car trajectory points is characterized to obtain the data information of the patrol car trajectory point distribution;

[0030] U32. Based on the data information of the distribution of the patrol car's trajectory points, a synchronous dynamic programming function P of the patrol car's driving path is constructed.

[0031]

[0032] Among them, z is the data information of the distribution of the patrol car's trajectory points, γ1, γ2 and γ3 are the dynamic programming factors of the patrol car's driving trajectory;

[0033] U33. Based on the synchronous dynamic programming function P of the patrol car's driving path, the driving path of each patrol car is synchronously and dynamically planned to obtain data information of the planned driving path of each patrol car.

[0034] Furthermore, the Dirac function g of the patrol car trajectory point distribution is,

[0035]

[0036] Among them, r1 is the data information of the predicted trajectory point of each patrol car, r2 is the data information of the position of each patrol car, and r3 is the data information of the state of each patrol car.

[0037] Furthermore, the constraints of the penalty weight factors δ1, δ2 and δ3 of the patrol car trajectory point distribution are:

[0038]

[0039] Further, in step U4, the optimization of the patrol car's driving path using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm includes:

[0040] U41. Based on the data information of the travel path of each patrol car after the planning, the salp population is initialized, the maximum number of iterations of the population parameters is determined, and the data information of the initialized salp population is obtained;

[0041] U42. Based on the data information of the initialized Salp Intense population, establish the fitness function S of the population individuals,

[0042]

[0043] Among them, h is the data information of the initialized salp population, η1, η2 and η3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the data information of the fitness values ​​of the population individuals;

[0044] U43. Based on the data information of the fitness values ​​of the individuals in the population, establish the target optimization function G of the population,

[0045]

[0046] Among them, a is the data information of the fitness value of the individual in the population, q is the non-uniform Gaussian variation function of the multi-subgroup, μ1, μ2 and μ3 are the variation factors of the adaptive adjustment step size, and the driving path of the patrol car is optimized to obtain the data information of the optimized driving path of each patrol car.

[0047] Furthermore, the non-uniform Gaussian variance function q of the multi-subgroup is:

[0048]

[0049] Among them, a is the data information of the fitness value of the individual in the population.

[0050] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a control system based on an autonomous navigation multi-machine collaborative security patrol vehicle, including a computer device, which is programmed or configured to execute any one of the steps of the control method based on an autonomous navigation multi-machine collaborative security patrol vehicle.

[0051] The present invention has the following positive effects:

[0052] 1. The present invention predicts the trajectory points of each patrol car by adopting an improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient, and combines the construction of a multi-machine collaborative path planning model for security patrol cars to perform synchronous dynamic planning on the driving path of each patrol car. It can not only accurately predict the driving trajectory points of each patrol car, thereby performing dynamic adjustments to improve the operating efficiency of the patrol car, but also solve the problem of overall or local deployment and scheduling difficulties.

[0053] 2. The present invention optimizes the driving path of patrol cars by adopting an improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm. Not only can the inspection and security tasks of different vehicles be shared on the cloud terminal, and the task arrangement can be changed according to the execution of the task to expand the group operation efficiency of the security patrol car, but also the practical application value of the security patrol car is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0055] Figure 2 It is a schematic flow chart of the improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient of the present invention;

[0056] Figure 3 A schematic diagram of the process of constructing a multi-machine collaborative path planning model for a security patrol vehicle according to the present invention;

[0057] Figure 4 It is a schematic flow chart of the improved multi-subgroup symbiotic non-uniform Gaussian mutation salp group optimization algorithm of the present invention. DETAILED DESCRIPTION

[0058] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0059] Example 1: Figure 1 As shown, a control method for a multi-machine collaborative security patrol vehicle based on autonomous navigation, the method comprising:

[0060] U1. Multiple security patrol cars are on patrol missions, collecting data information on the historical driving trajectory of each patrol car, and obtaining data information on the location and status of each patrol car in real time;

[0061] U2. Based on the data information of the historical driving trajectory of each patrol car, the trajectory point of each patrol car is predicted by using an improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient to obtain the data information of the trajectory point of each patrol car after the prediction;

[0062] U3. Based on the data information of the predicted trajectory points of each patrol car, the data information of the position of each patrol car and the data information of the state of each patrol car, a multi-machine collaborative path planning model for security patrol cars is constructed, and the driving path of each patrol car is synchronously and dynamically planned to obtain the data information of the planned driving path of each patrol car;

[0063] U4. Based on the data information of the planned driving path of each patrol car, the driving path of the patrol car is optimized by using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm to obtain the optimized data information of the driving path of each patrol car.

[0064] In this embodiment, if Figure 2 As shown, in step U2, the prediction of the trajectory points of each patrol car using the improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient includes:

[0065] U21. Based on the data information of the historical driving trajectory of each patrol car, establish the Spearman correlation function Q of the patrol car,

[0066]

[0067] Among them, x i is the data information of the historical driving trajectory of the i-th patrol car, f is the rank function of the historical driving trajectory of the patrol car, n is the sample size, λ iis a weight factor of the patrol car's historical driving trajectory, characterizes the relevance of the patrol car's historical driving trajectory, and obtains data information on the relevance of the patrol car's historical driving trajectory;

[0068] U22. The data information of the correlation of the historical driving trajectory of the patrol car is input into the BP neural network for training and learning, and the regression prediction function W of the trajectory point of the patrol car is determined.

[0069] Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car, and the regression prediction parameters of the trajectory points of α1, α2 and α3 patrol cars are obtained to obtain the trained BP neural network model;

[0070] U23. Based on the trained BP neural network model, the data information of the historical driving trajectory of each patrol car is input, and the trajectory points of each patrol car are predicted to obtain the predicted data information of the trajectory points of each patrol car.

[0071] In this embodiment, the regression prediction parameters α1, α2 and α3 of the trajectory points of the patrol car are,

[0072]

[0073]

[0074] Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car.

[0075] In this embodiment, the ranking function f of the historical driving trajectory of the patrol car is,

[0076]

[0077] Among them, x i is the data information of the historical driving trajectory of the i-th patrol car.

[0078] In this embodiment, if Figure 3 As shown, in step U3, the multi-machine collaborative path planning model for the security patrol car is constructed, and the synchronous dynamic planning of the driving path of each patrol car includes:

[0079] U31. Based on the predicted trajectory point data information of each patrol car, the position data information of each patrol car and the state data information of each patrol car, a patrol car Fourier series fitting trajectory point distribution function R is established.

[0080]

[0081] , where r1 is the data information of the trajectory point of each patrol car after prediction, r2 is the data information of the position of each patrol car, r3 is the data information of the state of each patrol car, δ1, δ2 and δ3 are the penalty weight factors of the patrol car trajectory point distribution, g is the Dirac function of the patrol car trajectory point distribution, and the distribution of the patrol car trajectory points is characterized to obtain the data information of the patrol car trajectory point distribution;

[0082] U32. Based on the data information of the distribution of the patrol car's trajectory points, a synchronous dynamic programming function P of the patrol car's driving path is constructed.

[0083]

[0084] Among them, z is the data information of the distribution of the patrol car's trajectory points, γ1, γ2 and γ3 are the dynamic programming factors of the patrol car's driving trajectory;

[0085] U33. Based on the synchronous dynamic programming function P of the patrol car's driving path, the driving path of each patrol car is synchronously and dynamically planned to obtain data information of the planned driving path of each patrol car.

[0086] In this embodiment, the Dirac function g of the patrol car trajectory point distribution is,

[0087]

[0088] Among them, r1 is the data information of the predicted trajectory point of each patrol car, r2 is the data information of the position of each patrol car, and r3 is the data information of the state of each patrol car.

[0089] In this embodiment, the constraints of the penalty weight factors δ1, δ2 and δ3 of the patrol car trajectory point distribution are:

[0090]

[0091] Embodiment 2: Based on the control method of a multi-machine collaborative security patrol vehicle based on autonomous navigation in Embodiment 1, the present invention is further illustrated and described below.

[0092] like Figure 1 As shown, a control method for a multi-machine collaborative security patrol vehicle based on autonomous navigation, the method comprising:

[0093] U1. Multiple security patrol cars are on patrol missions, collecting data information on the historical driving trajectory of each patrol car, and obtaining data information on the location and status of each patrol car in real time;

[0094] U2. Based on the data information of the historical driving trajectory of each patrol car, the trajectory point of each patrol car is predicted by using an improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient to obtain the data information of the trajectory point of each patrol car after the prediction;

[0095] U3. Based on the data information of the predicted trajectory points of each patrol car, the data information of the position of each patrol car and the data information of the state of each patrol car, a multi-machine collaborative path planning model for security patrol cars is constructed, and the driving path of each patrol car is synchronously and dynamically planned to obtain the data information of the planned driving path of each patrol car;

[0096] U4. Based on the data information of the planned driving path of each patrol car, the driving path of the patrol car is optimized by using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm to obtain the optimized data information of the driving path of each patrol car.

[0097] In this embodiment, if Figure 4 As shown, in step U4, the optimization of the patrol car's driving path using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm includes:

[0098] U41. Based on the data information of the travel path of each patrol car after the planning, the salp population is initialized, the maximum number of iterations of the population parameters is determined, and the data information of the initialized salp population is obtained;

[0099] U42. Based on the data information of the initialized Salp Intense population, establish the fitness function S of the population individuals,

[0100]

[0101] Among them, h is the data information of the initialized salp population, η1, η2 and η3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the data information of the fitness values ​​of the population individuals;

[0102] U43. Based on the data information of the fitness values ​​of the individuals in the population, establish the target optimization function G of the population,

[0103]

[0104] Among them, a is the data information of the fitness value of the individual in the population, q is the non-uniform Gaussian variation function of the multi-subgroup, μ1, μ2 and μ3 are the variation factors of the adaptive adjustment step size, and the driving path of the patrol car is optimized to obtain the data information of the optimized driving path of each patrol car.

[0105] In this embodiment, the non-uniform Gaussian variance function q of the multi-subgroup is:

[0106]

[0107] Among them, a is the data information of the fitness value of the individual in the population.

[0108] In this embodiment, the present invention provides a control system based on autonomous navigation multi-machine collaborative security patrol vehicle, including a computer device, which is programmed or configured to execute any one of the steps of the control method based on autonomous navigation multi-machine collaborative security patrol vehicle.

[0109] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the control methods for a multi-machine collaborative security patrol vehicle based on autonomous navigation.

[0110] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0111] In summary, the present invention not only allows the inspection and security tasks of different vehicles to be shared on the cloud terminal, and changes the arrangement of tasks according to the execution of tasks to expand the group operation efficiency of security patrol vehicles, but also improves the practical application value of security patrol vehicles.

[0112] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A control method for a multi-machine collaborative security patrol vehicle based on autonomous navigation, characterized in that: The method comprises: U1. Multiple security patrol cars are on patrol missions, collecting data information on the historical driving trajectory of each patrol car, and obtaining data information on the location and status of each patrol car in real time; U2. Based on the data information of the historical driving trajectory of each patrol car, the trajectory point of each patrol car is predicted by using an improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient to obtain the data information of the trajectory point of each patrol car after the prediction; U3. Based on the data information of the predicted trajectory points of each patrol car, the data information of the position of each patrol car and the data information of the state of each patrol car, a multi-machine collaborative path planning model for security patrol cars is constructed, and the driving path of each patrol car is synchronously and dynamically planned to obtain the data information of the planned driving path of each patrol car; U4. Based on the data information of the planned driving path of each patrol car, the driving path of the patrol car is optimized by using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm to obtain the optimized data information of the driving path of each patrol car.

2. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 1 is characterized in that: In step U2, the prediction of the trajectory points of each patrol car using the improved BP neural network regression prediction algorithm based on the Spearman correlation coefficient includes: U21. Based on the data information of the historical driving trajectory of each patrol car, establish the Spearman correlation function Q of the patrol car, Among them, x i is the data information of the historical driving trajectory of the i-th patrol car, f is the rank function of the historical driving trajectory of the patrol car, n is the sample size, λ i is a weight factor of the patrol car's historical driving trajectory, characterizes the relevance of the patrol car's historical driving trajectory, and obtains data information of the relevance of the patrol car's historical driving trajectory; U22. The data information of the correlation of the historical driving trajectory of the patrol car is input into the BP neural network for training and learning, and the regression prediction function W of the trajectory point of the patrol car is determined. Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car, and the regression prediction parameters of the trajectory points of α1, α2 and α3 patrol cars are obtained to obtain the trained neural network model; U23. Based on the trained neural network model, the data information of the historical driving trajectory of each patrol car is input, and the trajectory points of each patrol car are predicted to obtain the data information of the predicted trajectory points of each patrol car.

3. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 2 is characterized in that: The regression prediction parameters α1, α2 and α3 of the trajectory points of the patrol car are, Among them, y is the data information of the correlation of the historical driving trajectory of the patrol car.

4. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 2 is characterized in that: The ranking function f of the patrol car's historical driving trajectory is: Among them, x i is the data information of the historical driving trajectory of the i-th patrol car.

5. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 1 is characterized in that: In step U3, the multi-machine collaborative path planning model for security patrol vehicles is constructed, and the synchronous dynamic planning of the driving path of each patrol vehicle includes: U31. Based on the predicted trajectory point data information of each patrol car, the position data information of each patrol car and the state data information of each patrol car, a patrol car Fourier series fitting trajectory point distribution function R is established. ， Among them, r1 is the data information of the trajectory point of each patrol car after prediction, r2 is the data information of the position of each patrol car, r3 is the data information of the state of each patrol car, δ1, δ2 and δ3 are the penalty weight factors of the patrol car trajectory point distribution, g is the Dirac function of the patrol car trajectory point distribution, and the distribution of the patrol car trajectory points is characterized to obtain the data information of the patrol car trajectory point distribution; U32. Based on the data information of the distribution of the patrol car's trajectory points, a synchronous dynamic programming function P of the patrol car's driving path is constructed. Among them, z is the data information of the distribution of the patrol car's trajectory points, γ1, γ2 and γ3 are the dynamic programming factors of the patrol car's driving trajectory; U33. Based on the synchronous dynamic programming function P of the patrol car's driving path, the driving path of each patrol car is synchronously and dynamically planned to obtain data information of the planned driving path of each patrol car.

6. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 5 is characterized in that: The Dirac function g of the patrol car trajectory point distribution is, Among them, r1 is the data information of the predicted trajectory point of each patrol car, r2 is the data information of the position of each patrol car, and r3 is the data information of the state of each patrol car.

7. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 5 is characterized in that: The constraints of the penalty weight factors δ1, δ2 and δ3 of the patrol car trajectory point distribution are:

8. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 1 is characterized in that: In step U4, the optimization of the patrol car's driving path using the improved multi-subgroup symbiotic non-uniform Gaussian variation salp swarm optimization algorithm includes: U41. Based on the data information of the travel path of each patrol car after the planning, the salp population is initialized, the maximum number of iterations of the population parameters is determined, and the data information of the initialized salp population is obtained; U42. Based on the data information of the initialized Salp Intense population, establish the fitness function S of the population individuals, Among them, h is the data information of the initialized salp population, η1, η2 and η3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the data information of the fitness values ​​of the population individuals; U43. Based on the data information of the fitness values ​​of the individuals in the population, establish the target optimization function G of the population, Among them, a is the data information of the fitness value of the individual in the population, q is the non-uniform Gaussian variation function of the multi-subgroup, μ1, μ2 and μ3 are the variation factors of the adaptive adjustment step size, and the driving path of the patrol car is optimized to obtain the data information of the optimized driving path of each patrol car.

9. The control method of the multi-machine cooperative security patrol vehicle based on autonomous navigation according to claim 8 is characterized in that: The non-uniform Gaussian variance function q of the multi-subgroup is: Among them, a is the data information of the fitness value of the individual in the population.

10. A control system based on autonomous navigation multi-machine cooperative security patrol vehicle, including computer equipment, characterized in that: The computer device is programmed or configured to execute the steps of the control method of a multi-machine collaborative security patrol vehicle based on autonomous navigation as described in any one of claims 1 to 8.

Images