Task-oriented resource allocation scheme optimization method for amphibious unmanned vehicle

Abstract

The invention discloses a task-oriented resource allocation scheme optimization method for an amphibious unmanned vehicle, and belongs to the technical field of resource allocation optimization of amphibious unmanned vehicles. The method comprehensively considers use scenes such as a water area, a land area and a land and water interval and tasks such as rapid patrol and efficient cargo loading, selects a proper amphibious unmanned vehicle walking mechanism and a control strategy thereof, selects and installs a proper load, configures reasonable energy and supplies, determines an optimal task-oriented resource allocation scheme of the amphibious unmanned vehicle, and improves the resource allocation efficiency of the amphibious unmanned vehicle. And finally, guiding a user to carry out rapid configuration. According to the method, the optimal configuration scheme of the amphibious unmanned vehicle resources in a typical scene can be obtained by utilizing the cost mapping function which is simulated and estimated in advance and a multi-target optimization technology according to task requirements, so that the optimization target calculation time and cost of the amphibious unmanned vehicle in a given task and scene are shortened, and the calculation efficiency is improved. The rapid decision-making ability of the user in the application process is improved, and meanwhile, the dependence on artificial experience is greatly reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of resource configuration optimization of amphibious unmanned vehicles, and in particular relates to a method for optimizing a task-oriented resource configuration scheme of an amphibious unmanned vehicle. Background Art

[0002] Amphibious unmanned vehicles have the functions of traveling on land, sailing on water, and transitioning between land and water areas. They are widely used in the civilian field for flood control and disaster relief, coastal patrol, material transportation in water-related areas, beach and sea entertainment, etc. The use of amphibious vehicles requires changes in task focus and scenarios, making the resource allocation of amphibious unmanned vehicles more complicated. The specific use of what kind of walking mechanism and its control strategy, what kind of load to configure, how much energy to carry, etc., in order to better adapt to the application scenario and maximize the completion of the given task, poses a severe challenge to the user's ability to make quick decisions. For example, when an amphibious vehicle is used for emergency rescue and supply, it is required not only to have a large enough load, but also to have sufficient land and water interval capabilities; when an amphibious vehicle is used for border and coastal patrol, it is required to have a fast speed, flexible water and land switching, and be equipped with long-range detection equipment with strong detection capabilities. At the same time, the operating environment of the amphibious vehicle will also affect the configuration of its walking mechanism and control strategy. For example, when the amphibious vehicle is mainly used in a hard road environment, its walking mechanism tends to be wheeled, while when the amphibious vehicle is mainly used in a sandy or muddy environment, its walking mechanism tends to be triangular tracks or strip tracks.

[0003] Different purposes and usage scenarios require the platform to have different functions. Different requirements exist in different complex scenarios, including one or more requirements such as minimum energy consumption, fastest completion time, and highest task completion. Traditionally, the selection of walking mechanisms, load selection, and energy configuration of amphibious unmanned vehicles often rely on manual experience. This problem itself is a multi-objective optimization problem. These demand indicators are often coupled with each other and increase or decrease. The NSGA-III algorithm is a multi-objective optimization algorithm that supports mixed input of continuous and discrete variables and quickly solves Pareto dominance relationships. Summary of the invention

[0004] (I) Purpose of the invention

[0005] The purpose of the present invention is to provide a method for optimizing a task-oriented resource allocation scheme for an amphibious unmanned vehicle. The technical problem to be solved by the present invention is that when the existing amphibious unmanned vehicle performs tasks across land and water, the selection of its motion walking mechanism and the configuration of its task load are all determined by manual experience. The present invention provides a method for optimizing a task-oriented resource allocation scheme for an amphibious unmanned vehicle. The optimization method comprehensively considers the use scenarios (water areas, land areas, water-land areas, etc.) and tasks (rapid patrol, efficient cargo loading, etc.), selects a suitable amphibious unmanned vehicle walking mechanism and its control strategy, selects and installs appropriate loads (photoelectric reconnaissance loads, mechanical arm loads, etc.), configures reasonable energy (fuel, batteries, etc.) and supplies, determines the best task-oriented resource allocation scheme for the amphibious unmanned vehicle, and finally guides the user to carry out rapid configuration.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned purpose, the present invention comprehensively considers the tasks and usage environment of amphibious unmanned vehicles, adopts pre-simulation estimation of the travel cost function and improved target optimization algorithm, optimizes the resource (travel mechanism and control strategy, load selection, energy supply, etc.) configuration scheme of the unmanned vehicle, and proposes a task-oriented resource configuration optimization method for amphibious unmanned vehicles.

[0008] The present invention adopts the following technical solutions:

[0009] A method for optimizing a task-oriented resource allocation scheme for an amphibious unmanned vehicle comprises the following steps:

[0010] Step 1: Pre-build the unit distance travel cost mapping of amphibious unmanned vehicles in three domains (water, land, and water-land interval) r (m,v,α,β);

[0011] Where m is the load mass of the amphibious unmanned vehicle (including energy, load, etc.), v is the speed of the amphibious unmanned vehicle, α is the walking mechanism and its control strategy, β is the traffic condition coefficient, which represents the difficulty of the road section, represents the wind and wave conditions in the water area, represents the slope conditions in the water-land area, represents the road conditions in the land area, and r represents one of the three traffic sections of land, water, and water-land area.

[0012] Step 2: Define the parameters to be configured for the amphibious unmanned vehicle resource configuration plan;

[0013] The variables that need to be configured include 1: Amphibious unmanned vehicle load or resource load j, this variable determines the load mass of the amphibious unmanned vehicle. Different resource configurations have different masses. For example, the laser radar is about 10kg, while the energy supply may be 500kg, which will cause drastic changes in the loss target and timeliness target; 2: Amphibious unmanned vehicle walking mechanism and control strategy α, this variable determines the walking method of the amphibious unmanned vehicle through special terrain; 3: The travel speed v of the amphibious unmanned vehicle on each road section i , the movement speed of the amphibious unmanned vehicle depends not only on the configuration of the walking mechanism and the mass of the load, but also on the environmental road where the mission is performed; the subscript i represents the different stages of the amphibious unmanned vehicle, and the subscript j represents the jth resource;

[0014] Step 3: Based on the specific mission requirements and the use scenarios of amphibious unmanned vehicles, define the multi-objective optimization problem of resource allocation, and its optimization performance indicators are:

[0015]

[0016] st0 <v i <V r

[0017]

[0018] Where: J1, J2, and J3 are the three optimization objectives in the multi-objective optimization problem of amphibious unmanned vehicle resource allocation. J1 is the loss objective: that is, minimizing the full-process traffic cost of the task. Assume that the task can be divided into N sections according to the traffic interval, and the traffic cost of the i-th section is r i , k t i is the mileage of each segment in the task; J2 is the time efficiency target: that is, the time cost to complete the entire task, the travel time k of the i-th segment area t i / v i ,All kinds of tasks usually have the goal of completing the task as quickly as possible, that is, minimizing the time cost; J3 is the task goal: that is, the resource allocation can support the amphibious unmanned vehicle to achieve the task, load j Indicates the quality The jth category selects a suitable load or supply resource, M is the upper limit of the amphibious unmanned vehicle resource configuration, and when load j is selected to match the task j =1, otherwise load j =0;

[0019] Comprehensively optimize the above objective functions and transform the task-oriented resource allocation optimization problem into a multi-objective optimization problem;

[0020] Step 4: Optimize the crossover, mutation, perturbation mode and probability of the NSGA-III algorithm;

[0021] Step 5, solving the multi-objective resource allocation of amphibious unmanned vehicles based on the improved NSGA-III algorithm;

[0022] Based on the above multi-objective function, the multi-objective optimization solution is carried out, and the process is as follows:

[0023] S51. Initialize the total number of iterations N gen , population size N grp , randomly initialized to include N grp The initial population P of individuals t ;

[0024] S52. Start the i-th iteration: from the parent population P t Perform crossover and mutation operations to generate offspring populations

[0025] Q t , merge the parent and child populations into a new population of size 2N grp The population R t =P t +Q t ;

[0026] S53. R based on multi-objective function t Perform non-dominated sorting to obtain the non-dominated layer sorting F1, F2, ..., and put the members F1, ..., F1 in the non-dominated layer into S in sequence. t middle go;

[0027] S54. If | S t |=N grp Then enter the next round of iteration, and the next generation population P t+1 =S t Otherwise, F l+1 Individuals at the front of the layer are added to P in turn. t+1 until the number of individuals reaches N grp ;

[0028] S55. Repeat S2 until i ≥ N gen

[0029] S56. Obtain the Pareto optimal solution set in the population n is the number of non-dominated solutions;

[0030] Step 6: Obtain the optimal solution for the amphibious unmanned vehicle resource allocation plan;

[0031] A weight-based approach is used to obtain the optimal solution from the non-dominated solutions by evaluating:

[0032]

[0033] In the formula, σ1, σ2, and σ3 are weight factors, and the weight values ​​are determined according to the task requirements. For example, in the disaster relief process, the requirements of speed and supply are the first consideration, so the weights of σ2 and σ3 are relatively large, while in the daily patrol process, the task is required to be completed under the condition of controlling costs, so the weights of σ1 and σ3 are relatively large;

[0034] Regarding the unit distance travel cost mapping of amphibious unmanned vehicles in the three domains in step 1 r (m i ,v i ,α,β), respectively changing the load, driving speed, walking mechanism and control strategy, and road conditions in the water, land, and waterway environments, and using nested loops to obtain the mapping relationship of the unit distance travel cost of the unmanned vehicle under different road conditions. r ; Among them, when the load is too heavy to pass a certain section of road, its cost is set to infinity.

[0035] (III) Effective income

[0036] Compared with the prior art, the present invention has the following advantages:

[0037] 1. The present invention can be used to obtain the optimal configuration scheme of amphibious unmanned vehicle resources in typical scenarios based on task requirements by using the pre-simulated estimated cost mapping function and multi-objective optimization technology, shortening the optimization target calculation time and cost of amphibious unmanned vehicles in given tasks and scenarios, improving the user's rapid decision-making ability during the application process, and also greatly reducing the dependence on manual experience;

[0038] 2. The present invention comprehensively considers the impact of water, land and water-land environment on amphibious unmanned vehicles, and also considers the impact of resource allocation such as different walking mechanisms and strategies of amphibious unmanned vehicles, obtains the best resource allocation plan, and maximizes the mission effectiveness of the amphibious unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a resource allocation scheme optimization framework based on unit distance cost mapping;

[0040] Figure 2 It is a schematic diagram of the process of the present invention; DETAILED DESCRIPTION

[0041] The following is combined with Figure 1 , Figure 2 The present invention is explained and illustrated in more detail by taking the case of island rescue and supply implementation into consideration.

[0042] The present invention proposes to use pre-simulation to estimate the unit distance travel cost of an amphibious unmanned vehicle in three domains, and combines the multi-objective function of task construction to use an improved NSGA-III algorithm to quickly obtain an optimization method for the task-oriented resource allocation scheme of an amphibious unmanned vehicle. Different from the traditional method of deciding which walking mechanism, load, energy, and speed to use based on usage experience, this patent fully considers the usage environment and task characteristics, and evaluates the optimal resource allocation scheme of the unmanned vehicle through precise simulation to ensure that the configuration scheme can maximize the use efficiency of the amphibious unmanned vehicle.

[0043] In an ideal implementation of the present invention, a method for optimizing a task-oriented resource allocation scheme for an amphibious unmanned vehicle comprises the following steps:

[0044] Step 1: Pre-build the unit distance travel cost mapping of amphibious unmanned vehicles in three areas: water area, land area, and water-land area. r (m i ,v i ,α,β);

[0045] In the simulation software, the load simulation of the amphibious unmanned vehicle in the three domains is set up respectively, and the nested loop test m i ,v i ,α,βThe movement of the amphibious unmanned vehicle when the four variables have different values, and record its movement energy consumption, movement bumpiness, vehicle control accuracy, etc.; i is the load mass of the amphibious unmanned vehicle (including energy, load, etc.), and its value changes from 50kg increments until the maximum load of the amphibious unmanned vehicle is reached; v i is the speed of the amphibious unmanned vehicle, incremented by 1m / s to the upper limit of the speed of the unmanned vehicle in the three domains, α is the walking mechanism and its control strategy, including wheeled mechanism, triangular track mechanism, long track mechanism and its control strategy, etc., β is the traffic condition coefficient, representing the difficulty of the road section, and represents the water wind and headwind value in water, incremented by 1m / s to the upper limit of the design of the amphibious unmanned vehicle, and the water and land section represents the slope degree, incremented by 1° to the upper limit of the design of the amphibious unmanned vehicle;

[0046] Step 2: Define the parameters to be configured for the amphibious unmanned vehicle resource configuration plan;

[0047] In this case, consider the island rescue and supply mission and usage scenario, variable 1: load or resource load j For replenishment of materials, the algorithm does not care about the type of replenishment, but focuses on the quality of the replenishment finally loaded; variable 2 walking mechanism control strategy α, the mechanism configuration scheme of the amphibious unmanned vehicle landing and leaving the island, which can be wheeled, triangular track or long track; variable 3: the speed v of the amphibious unmanned vehicle on each section i ;

[0048] Step 3: Based on the specific mission requirements and the use scenarios of amphibious unmanned vehicles, define the multi-objective optimization problem of resource allocation, and its optimization performance indicators are:

[0049]

[0050] st0<v i <V r

[0051]

[0052] Where: J1, J2, and J3 are the three optimization objectives in the multi-objective optimization problem of amphibious unmanned vehicle resource allocation. J1 is the loss objective: that is, minimizing the full-process traffic cost of the task. Assume that the task can be divided into N sections according to the traffic interval, and the traffic cost of the i-th section is r i , k t i is the mileage of each segment in the task; J2 is the time efficiency target: that is, the time cost to complete the entire task, the travel time k of the i-th segment area t i / v i ,All kinds of tasks usually have the goal of completing the task as quickly as possible, that is, minimizing the time cost; J3 is the task goal: that is, the resource allocation can support the amphibious unmanned vehicle to achieve the task, load j Indicates the quality The jth category selects the appropriate load or supply resources, M is the upper limit of the amphibious unmanned vehicle resource configuration, and load j that matches the task is selected. j =1, otherwise load j =0;

[0053] In the embodiment of the present invention, the above task flow is based on eight sections, namely, load on land, load between land and water, load on water, load between land and water (landing), no load between land and water (leaving the island), no load on water, no load between land and water, and no load on the road, that is, N=8; when N≥4, the load mass is subtracted from the supply mass;

[0054] Comprehensively optimize the above objective functions and transform the task-oriented resource allocation optimization problem into a multi-objective optimization problem;

[0055] Step 4: Optimize the crossover, mutation, perturbation mode and probability of the NSGA-III algorithm;

[0056] Step 5, solving the multi-objective resource allocation of amphibious unmanned vehicles based on the improved NSGA-III algorithm;

[0057] Based on the above multi-objective function, the multi-objective optimization solution is carried out, and the process is as follows:

[0058] S51. Initialize the total number of iterations N gen =1000, population size N grp =80, random initialization includes N grp The initial population P of individuals t ;

[0059] S52. Start the i-th iteration: from the parent population P t Perform crossover and mutation operations to generate the offspring population Q t , merge the parent and child populations into a new population of size 2N grp The population R t =P t +Q t ;

[0060] S53. R based on multi-objective function t Perform non-dominated sorting to obtain the non-dominated layer sorting F1, F2, ..., and put the members F1, ..., F1 in the non-dominated layer into S in sequence. t middle go;

[0061] S54. If | S t |=N grp Then enter the next round of iteration, and the next generation population P t+1 =S t Otherwise, F l+1 Individuals at the front of the layer are added to P in turn. t+1 until the number of individuals reaches N grp ;

[0062] S55. Repeat S2 until i ≥ N gen

[0063] S56. Obtain the Pareto optimal solution set in the population n is the number of non-dominated solutions;

[0064] Step 6: Obtain the optimal solution for the amphibious unmanned vehicle resource allocation plan;

[0065] A weight-based approach is used to obtain the optimal solution from the non-dominated solutions by evaluating:

[0066]

[0067] In the formula, σ1, σ2, and σ3 are weight factors, and the weight values ​​are determined according to the task requirements. For example, in the disaster relief process, the requirements of speed and supply are the first consideration, so the weights of σ2 and σ3 are relatively large, while in the daily patrol process, the task is required to be completed under the condition of controlling costs, so the weights of σ1 and σ3 are relatively large;

[0068] The above contents are further detailed descriptions of the present invention in combination with specific implementation methods, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A task-oriented resource allocation scheme optimization method for an amphibious unmanned vehicle, characterized in that: The steps include: Step 1: Pre-build the unit distance travel cost mapping of amphibious unmanned vehicles in three areas: water area, land area, and water-land area. r (m,v,α,β); Where m is the load mass of the amphibious unmanned vehicle, v is the speed of the amphibious unmanned vehicle, α is the walking mechanism of the amphibious unmanned vehicle and its control strategy, β is the traffic condition coefficient of the amphibious unmanned vehicle, β represents the traffic difficulty of the section, which represents the wind and wave conditions in the water area, the road conditions on land, and the slope conditions in the water-land section; r represents one of the three traffic sections of land, water, and water-land section respectively; Step 2: Define the parameters to be configured for the amphibious unmanned vehicle resource configuration plan; The variables that need to be configured include 1: Amphibious unmanned vehicle load or resource load j , which is used to determine the load mass of the amphibious unmanned vehicle. Different resource configurations have different masses; 2: The walking mechanism and control strategy of the amphibious unmanned vehicle α, which determines the walking method of the amphibious unmanned vehicle through special terrain; 3: The travel speed v of the amphibious unmanned vehicle on each road section i , the movement speed of the amphibious unmanned vehicle depends not only on the configuration of the walking mechanism and the mass of the load, but also on the environmental road where the mission is performed; the subscript i represents the different stages of the amphibious unmanned vehicle, and the subscript j represents the jth resource; Step 3: Based on the mission requirements and the use scenarios of the amphibious unmanned vehicle, define the multi-objective optimization problem of resource allocation, and its optimization performance indicators are: Where: J1, J2, and J3 are the three optimization objectives in the multi-objective optimization problem of amphibious unmanned vehicle resource allocation. J1 is the loss objective: that is, minimizing the full-process traffic cost of the task. Assume that the task can be divided into N sections according to the traffic interval, and the traffic cost of the i-th section is r i , k t i is the mileage of each segment in the task; J2 is the time efficiency target: that is, the time cost to complete the entire task, the travel time k of the i-th segment area t i / v i ,All kinds of tasks usually have the goal of completing the task as quickly as possible, that is, minimizing the time cost; J3 is the task goal: that is, the resource allocation can support the amphibious unmanned vehicle to achieve the task, load j Indicates the quality The jth category selects the appropriate load or supply resources, M is the upper limit of the amphibious unmanned vehicle resource configuration, and load j that matches the task is selected. j =1, otherwise load j =0; Comprehensively optimize the above objective functions and transform the task-oriented resource allocation optimization problem into a multi-objective optimization problem; Step 4: Optimize the crossover, mutation, perturbation mode and probability of the NSGA-III algorithm; Step 5, solving the multi-objective resource allocation of amphibious unmanned vehicles based on the improved NSGA-III algorithm; Based on the above multi-objective function, the multi-objective optimization solution is carried out, and the process is as follows: S51. Initialize the total number of iterations N gen , population size N grp , randomly initialized to include N grp The initial population P of individuals t ; S52. Start the i-th iteration: from the parent population P t Perform crossover and mutation operations to generate the offspring population Q t , merge the parent and child populations into a new population of size 2N grp The population R t =P t +Q t ; S53. R based on multi-objective function t Perform non-dominated sorting to obtain the non-dominated layer sorting F1, F2, ..., and sort the members F1, ..., F l Put S in turn t middle go; S54. If | S t |=N grp Then enter the next round of iteration, and the next generation population P t+1 =S t Otherwise, F l+1 Individuals at the front of the layer are added to P in turn. t+1 until the number of individuals reaches N grp ; S55. Repeat S2 until i ≥ N gen S56. Obtain the Pareto optimal solution set in the population n is the number of non-dominated solutions; Step 6: Obtain the optimal solution for the amphibious unmanned vehicle resource allocation plan; A weight-based approach is used to obtain the optimal solution from the non-dominated solutions by evaluating: In the formula, σ1, σ2, σ3 are weight factors, and the weight values ​​are determined according to task requirements.

2. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 1, characterized in that: The unit distance travel cost mapping of the amphibious unmanned vehicle in the three domains in step 1 is traffic r (m i ,v i ,α,β), respectively changing the load, driving speed, walking mechanism and control strategy, and road conditions in the water, land, and waterway environments, and using nested loops to obtain the mapping relationship of the unit distance travel cost of the unmanned vehicle under different road conditions. r ; Among them, when the load is too heavy to pass a certain section of road, its cost is set to infinity.

3. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 1 is characterized in that: In step 6, if the requirements of rapid energy and replenishment are considered, the weights of σ2 and σ3 are relatively large.

4. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 1, characterized in that: In step 6, if the task is completed under the condition of controlling the cost during daily patrol, the weights of σ1 and σ3 are relatively large.

5. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 1, characterized in that: The payload is an optoelectronic reconnaissance payload or a mechanical arm payload.

6. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 3, characterized in that: The energy sources are oil and batteries.

7. The method for optimizing task-oriented resource allocation scheme for an amphibious unmanned vehicle according to claim 1, characterized in that: The mission requirements are fast patrol or efficient cargo transportation.

Images