Intelligent trolley path tracking method and device, intelligent trolley and medium

Abstract

The invention relates to the technical field of path planning, in particular to an intelligent trolley path tracking method and device, an intelligent trolley and a medium, and the method comprises the steps that a grid map of a target area is constructed, and the grid map comprises a plurality of nodes; an objective function is constructed according to the driving distance and the driving cost of the multiple intelligent trolleys, multiple constraint conditions of the objective function are set, and the multiple constraint conditions constrain access target position nodes, passing nodes, loads, starting point positions, ending point positions and driving time of each intelligent trolley; and performing path tracking on the plurality of intelligent trolleys based on a dung beetle optimization algorithm and the target function to obtain target paths of the plurality of intelligent trolleys from the distribution center to the plurality of nodes on the grid map. Therefore, the problems of poor precision and efficiency of path planning, low applicability and the like caused by the fact that the path planning is usually limited to a lower dimension and a smaller range and is difficult to adapt to a complicated environment in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a method and device for tracking a path of an intelligent vehicle, an intelligent vehicle and a medium. Background Art

[0002] Path planning is one of the core issues in the fields of intelligent transportation systems, logistics distribution, robot navigation, etc. With the development of automation technology and artificial intelligence, the demand for efficient and intelligent path planning algorithms is growing. The goal of path planning is to find one or more optimal paths that meet specific conditions given a starting point and an end point.

[0003] Among the related technologies, most of them use particle swarm optimization algorithm or ant colony algorithm, among which particle swarm optimization algorithm continuously updates its own position according to its own speed and position to explore the solution space, but it cannot handle high-dimensional complex problems and leads to falling into local optimality without considering the global situation. It is difficult to adapt to complex environments. If the quality of the initial solution is not high, it will affect the final result. As the number of iterations increases, the diversity of the group gradually decreases, resulting in a smaller exploration scope; and the ant colony algorithm requires more time to find the optimal solution for large-scale problems, and the search efficiency is low in the initial stage; therefore, existing path planning is often limited to lower dimensions and smaller ranges, and it is difficult to adapt to complex environments, resulting in poor accuracy and efficiency of path planning and low applicability. Summary of the invention

[0004] The present invention provides an intelligent vehicle path tracking method, device, intelligent vehicle and medium to solve the problems in related technologies that path planning is often limited to lower dimensions and smaller ranges, and is difficult to adapt to complex environments, resulting in poor accuracy and efficiency of path planning and low applicability.

[0005] The first aspect of the present invention provides a method for tracking a path of an intelligent vehicle, comprising the following steps: constructing a grid map of a target area, the grid map including a plurality of nodes; constructing an objective function according to the driving distances and driving costs of a plurality of intelligent vehicles, and setting a plurality of constraints of the objective function, wherein the plurality of constraints constrain a plurality of target location nodes visited, passed nodes, load, starting location, end location and driving time of each intelligent vehicle; tracking the paths of the plurality of intelligent vehicles based on a dung beetle optimization algorithm and the objective function, and obtaining target paths of the plurality of intelligent vehicles from a distribution center to a plurality of nodes on the grid map.

[0006] Optionally, the objective function is: ； Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

[0007] Optionally, the multiple constraints include the following: the smart car is allowed to visit each target location node once; the number of times the smart car enters and leaves any node in the path is equal; the load of the smart car is less than or equal to the upper capacity limit; the starting position and the end position of the smart car are located at the distribution center; the travel time of the smart car satisfies the following formula:

[0008] in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

[0009] Optionally, the dung beetle optimization algorithm includes: using the randomly generated paths of the smart cars on the grid map as the population individuals of the dung beetle optimization algorithm, initializing the population, iteratively updating the population by simulating navigation behavior, calculating the fitness value of each population individual, and selecting the solution of the objective function according to the fitness value of each population individual; when the population meets the convergence conditions, outputting the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map.

[0010] Optionally, the navigation behavior simulation method includes at least one of direction update, rolling adjustment and jump search, wherein direction update is: each population individual adjusts the current solution by randomly selecting neighbor nodes or exchanging path order; rolling adjustment is: adjustment is made based on the current path; jump search is: random disturbance is introduced to randomly reorganize the path plans of the population individuals to generate a new search direction.

[0011] Optionally, the convergence condition includes that the number of iterations reaches a preset number, or the fitness value is less than a preset threshold.

[0012] Optionally, the fitness value is calculated as:

[0013] Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

[0014] The second aspect of the present invention provides a path tracking device for an intelligent vehicle, including: a construction module, used to construct a grid map of a target area, the grid map includes multiple nodes; a setting module, used to construct an objective function based on the driving distance and driving cost of multiple intelligent vehicles, and set multiple constraints of the objective function, wherein the multiple constraints constrain the visited target position nodes, passed nodes, load, starting position, end position and driving time of each intelligent vehicle; a tracking module, used to track the paths of multiple intelligent vehicles based on the dung beetle optimization algorithm and the objective function, and obtain the target paths of multiple intelligent vehicles from the distribution center to multiple nodes on the grid map. Optionally, the objective function is:

[0015] Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

[0016] Optionally, the multiple constraints include the following: the smart car is allowed to visit each target location node once; the number of times the smart car enters and leaves any node in the path is equal; the load of the smart car is less than or equal to the upper capacity limit; the starting position and the end position of the smart car are located at the distribution center; the travel time of the smart car satisfies the following formula:

[0017] in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

[0018] Optionally, the dung beetle optimization algorithm includes: using the randomly generated paths of the smart cars on the grid map as the population individuals of the dung beetle optimization algorithm, initializing the population, iteratively updating the population by simulating navigation behavior, calculating the fitness value of each population individual, and selecting the solution of the objective function according to the fitness value of each population individual; when the population meets the convergence conditions, outputting the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map.

[0019] Optionally, the navigation behavior simulation method includes at least one of direction update, rolling adjustment and jump search, wherein direction update is: each population individual adjusts the current solution by randomly selecting neighbor nodes or exchanging path order; rolling adjustment is: adjustment is made based on the current path; jump search is: random disturbance is introduced to randomly reorganize the path plans of the population individuals to generate a new search direction.

[0020] Optionally, the convergence condition includes that the number of iterations reaches a preset number, or the fitness value is less than a preset threshold.

[0021] Optionally, the fitness value is calculated as:

[0022] Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

[0023] The third aspect of the present invention provides an intelligent car, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the intelligent car path tracking method as described in the above embodiment.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the intelligent car path tracking method as described in the above embodiment.

[0025] Thus, the present invention includes the following beneficial effects: The embodiment of the present invention can construct a grid map of the target area to make path planning more intuitive, construct an objective function according to the driving distance and driving cost of multiple smart cars, and set multiple constraints of the objective function to obtain multiple path planning results that meet the constraints, so as to screen out a relatively high-quality path plan according to the objective function and the constraints, and optimize the path tracking of multiple smart cars based on the dung beetle optimization algorithm and the objective function to obtain the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map. The dung beetle optimization algorithm can effectively jump out of the local optimal solution and find the global optimal path, and can dynamically adjust the path tracking according to real-time data, which can not only improve the accuracy and efficiency of path tracking, but also ensure the practical feasibility and dynamic adaptability of the path plan, ensure that it can adapt to complex environments, and has high applicability.

[0026] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flow chart of a path tracking method for an intelligent vehicle provided according to an embodiment of the present invention; Figure 2 A schematic diagram of an initial path for path planning optimization according to an embodiment of the present invention; Figure 3 A schematic diagram of an optimized path for path planning optimization provided according to an embodiment of the present invention; Figure 4 A schematic diagram of a final optimization path provided according to an embodiment of the present invention; Figure 5 A schematic diagram of a planning target provided according to an embodiment of the present invention; Figure 6 A flow chart of a smart car path planning algorithm provided according to an embodiment of the present invention; Figure 7 This is an example diagram of a path tracking device for an intelligent vehicle according to an embodiment of the present invention; Figure 8 Schematic diagram of the structure of an intelligent car according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0029] Currently, the most widely used algorithms in the field of path planning are particle swarm optimization and ant colony algorithms. The elements of these algorithms will thoroughly explore and develop the environment space of the optimization problem according to their own speed and position until the optimal solution is found. However, these existing algorithms have problems such as low exploration dimension and small range, slow convergence speed, and easy to fall into local optimality. According to the complexity, dynamics and target requirements of the problem, various swarm intelligence algorithms are used to explore and optimize the path, and the appropriate algorithm or its combination is selected to achieve path optimization. However, in multi-objective optimization scenarios, it is still easy to fall into the local optimal solution due to early convergence, and it is impossible to find a truly efficient path.

[0030] The dung beetle optimization algorithm is inspired by the rolling, dancing, foraging, stealing and breeding behaviors of dung beetles. It uses celestial clues to navigate, such as the sun, moon and polarized light, to make the dung ball roll in a straight line. If it encounters an obstacle and cannot move forward, the dung beetle will readjust its direction by dancing, thereby optimizing the search process. It can simulate the uncertain behavior of dung beetles in complex environments and improve the algorithm's ability to jump out of the local optimum through random perturbations. This algorithm is a new type of swarm intelligence optimization algorithm with high computational efficiency in population initialization, fitness calculation and local search strategy. It is suitable for processing large-scale path planning problems. The dung beetle optimization algorithm adjusts the priorities of different targets through weight coefficients to achieve balanced optimization of multiple targets. It has the characteristics of strong optimization ability and fast convergence speed. In particular, the dung beetle optimization algorithm will enhance the algorithm's global search ability and improve path planning efficiency through the "jump search" mechanism.

[0031] The following describes the intelligent car path tracking method, device, intelligent car and storage medium according to the embodiments of the present invention with reference to the accompanying drawings.

[0032] Specifically, Figure 1 A schematic flow chart of a path tracking method for an intelligent vehicle provided in an embodiment of the present invention.

[0033] like Figure 1 As shown, the intelligent car path tracking method includes the following steps: In step S101, a grid map of a target area is constructed, and the grid map includes a plurality of nodes.

[0034] It is understandable that the embodiment of the present invention can divide the target area into multiple evenly distributed grids, each grid can represent a node, so as to construct a grid map of the target area, making subsequent path tracing more intuitive and improving path tracing efficiency.

[0035] In step S102, an objective function is constructed according to the driving distance and driving cost of multiple smart cars, and multiple constraints of the objective function are set, wherein the multiple constraints constrain the visited target location nodes, passed nodes, load, starting location, end location and driving time of each smart car.

[0036] Among them, the objective function is: ； Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

[0037] It should be noted that when When it is 1, it indicates that the path from node i to node j of the kth vehicle is selected. When it is 0, it indicates that the path from node i to node j of the kth vehicle has not been selected; the driving cost includes distance or time, and may also include electricity consumption cost or fuel cost, without specific limitation.

[0038] Among them, the multiple constraints include the following: the smart car is allowed to visit each target location node once; the number of times the smart car enters and leaves any node in the path is equal; the load of the smart car is less than or equal to the capacity limit; the starting position and the end position of the smart car are located at the distribution center; the travel time of the smart car satisfies the following formula:

[0039] in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

[0040] It can be understood that constructing the objective function and setting the constraints in the embodiment of the present invention play an important role in the path planning of the intelligent car. The objective function provides direction for the search process and is used to measure the quality of the path planning solution, while the constraints ensure that the solution found is not only optimal but also feasible, which can not only improve the efficiency and effectiveness of path planning, but also better cope with complex and changeable practical application scenarios.

[0041] Specifically, in the constraints: (1) The smart car is allowed to visit each target location node once, which means that each key location node i can only be visited by one car once. The corresponding formula is: ; Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, =1 indicates that the path from node i to node j for the kth vehicle is selected.

[0042] (2) The number of times the smart car enters and leaves any node in the path is equal. The corresponding formula is: ; Where n represents the number of path nodes, i and j represent any node in the path, Represented as the path decision variable of the kth vehicle from node i to node j.

[0043] (3) When the load of the smart car is less than or equal to the upper capacity limit, the corresponding formula is:

[0044] in, It is expressed as the demand of node i; It is represented as the capacity of the kth vehicle, Represented as any smart car, Represented as the path decision variable of the kth vehicle from node i to node j.

[0045] (4) The starting and ending positions of the smart car are located at the distribution center, and the corresponding formula is:

[0046] in, represents the path decision variable of the kth vehicle from the distribution center to node j, represents the path decision variable of the kth vehicle from node i to the distribution center.

[0047] In step S103, path tracking is performed on the multiple smart cars based on the dung beetle optimization algorithm and the objective function to obtain target paths of the multiple smart cars from the distribution center to the multiple nodes on the grid map.

[0048] It can be understood that the embodiments of the present invention can perform path tracking for multiple smart cars based on the dung beetle optimization algorithm and the objective function, and optimize the path tracking of multiple smart cars based on the dung beetle optimization algorithm and the objective function to obtain the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map. The dung beetle optimization algorithm can effectively jump out of the local optimal solution and find the global optimal path, and can dynamically adjust the path tracking according to real-time data, which can not only improve the accuracy and efficiency of path tracking, but also ensure the actual feasibility and dynamic adaptability of the path plan, ensure that it can adapt to complex environments, and has high applicability.

[0049] In an embodiment of the present invention, a dung beetle optimization algorithm includes: using the randomly generated paths of smart cars on a grid map as population individuals of the dung beetle optimization algorithm, initializing the population, iteratively updating the population by simulating navigation behavior, calculating the fitness value of each population individual, and selecting a solution to the objective function according to the fitness value of each population individual; when the population meets the convergence conditions, outputting the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map.

[0050] The calculation formula of the fitness value is:

[0051] Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

[0052] The convergence condition includes that the number of iterations reaches a preset number, or the fitness value is less than a preset threshold.

[0053] Among them, the preset number of times or the preset threshold can be set according to actual needs and is not specifically limited.

[0054] It can be understood that the embodiments of the present invention can use the paths randomly generated by the smart car on the grid map as the population individuals of the dung beetle optimization algorithm, screen out the paths that meet the constraints by initializing the population, and iteratively update the population by simulating the navigation behavior to simulate the unique behavior of dung beetles in nature, jump out of the local optimal solution, and increase the diversity of paths; and calculate the fitness value of each population individual, evaluate the quality of each path plan according to the fitness value of each population individual, and select the solution of the objective function, so as to select the optimal path from multiple paths. When the population meets the convergence conditions, the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map are output, which can not only improve the accuracy and efficiency of path tracking, but also ensure the practical feasibility and dynamic adaptability of the path plan, and ensure that it can adapt to complex environments with high applicability.

[0055] Specifically, the dung beetle optimization algorithm optimizes the path plan by simulating the positioning, rolling dung balls and navigation behaviors of dung beetles. Specifically: (1) Population initialization: Each individual in the population represents a path plan for the intelligent car. The path is randomly generated to ensure that the initial solution meets the basic constraints. The fitness of each individual in the population, that is, the total travel distance of the path, is calculated.

[0056] (2) Calculate fitness: Calculate the total travel distance of each individual in the population and select the best solution based on the fitness value; retain the optimal solution and a certain proportion of the best solutions as the basis for the next generation of population.

[0057] The calculation formula of the fitness value is:

[0058] Where Z is the objective function value, is an infinitesimal positive number, For a certain path plan.

[0059] It should be noted that the larger the fitness value, the better the path plan.

[0060] (3) The calculation formula for navigation behavior simulation is: ; in, is the current optimal solution, that is, the optimal solution for the current path planning. is the new position of the smart car in the tth iteration, is the new position of the smart car in the t+1 iteration, , is the control parameter, is a random disturbance.

[0061] It should be noted that α represents the emphasis on local characteristics, such as distance and attraction; β represents the degree of dependence on global characteristics, such as historical information or group behavior; they jointly determine the behavioral strategy of individuals in the navigation or optimization process.

[0062] The navigation behavior simulates the behavioral positioning of dung beetles. Different neighbor nodes in the first term in the calculation formula represent different directions, that is, direction update. The second term adds a weight factor α based on the current path to point to the direction of the global optimal solution. The third term introduces random disturbance to help the smart car jump out of the local optimal solution and enhance the global search capability.

[0063] In an embodiment of the present invention, the navigation behavior simulation method includes at least one of direction update, rolling adjustment and jump search, wherein direction update is: each population individual adjusts the current solution by randomly selecting neighbor nodes or exchanging path order; rolling adjustment is: adjustment is made based on the current path; jump search is: random disturbance is introduced to randomly reorganize the path plans of the population individuals to generate a new search direction.

[0064] It can be understood that the direction update in the embodiment of the present invention can adjust the current solution by randomly selecting neighbor nodes or exchanging the path order, which increases the diversity of path solutions, helps to explore a wider solution space, avoids premature concentration in a certain area, and increases the possibility of jumping out of the local optimal solution; the rolling adjustment makes subtle adjustments based on the current path, similar to the dung beetle adjusting the direction of the rolling dung ball according to the position of the sun, so that it gradually approaches a better solution, maintains a certain consistency and rationality, and improves the search efficiency; the jump search introduces random disturbances, randomly reorganizes the path plans of individuals in the population to generate a new search direction, helps the algorithm jump out of the local optimal solution, and conducts a wider global search. The global search is performed through the direction update and jump mechanism, and the rolling behavior is used for local optimization. The convergence speed and accuracy of the algorithm are significantly improved, ensuring that high-quality paths are found, and it can flexibly respond to environmental changes and improve the accuracy and efficiency of path tracking.

[0065] Specifically, the behavior model includes three processes: (1) Direction update: simulating dung beetles to adjust the path direction according to the position of the sun. Each individual adjusts the current solution by randomly selecting neighbor nodes or exchanging the path order; (2) Rolling adjustment: simulating the behavior of dung beetles rolling dung balls to conduct local search, that is, to make fine-grained local adjustments based on the current path; (3) Jump search: simulating dung beetles to make random jumps due to environmental changes to prevent them from falling into local optimality; environmental parameters include traffic conditions, height and weight limits, etc. Random disturbances are introduced into the model to randomly reorganize the individual path plans, and the optimized path is adjusted in real time with dynamic changes to ensure global search capabilities and generate new search directions.

[0066] According to the intelligent vehicle path tracking method proposed in an embodiment of the present invention, a grid map of the target area is constructed to make path planning more intuitive, and an objective function is constructed according to the driving distances and driving costs of multiple intelligent vehicles. At the same time, multiple constraints of the objective function are set to obtain multiple path planning results that meet the constraints, so as to screen out relatively high-quality path plans according to the objective function and the constraints, and based on the dung beetle optimization algorithm and the objective function, path tracking optimization is performed on multiple intelligent vehicles to obtain target paths of multiple intelligent vehicles from the distribution center to multiple nodes on the grid map. The dung beetle optimization algorithm can effectively jump out of the local optimal solution and find the global optimal path, and can dynamically adjust the path tracking according to real-time data, which can not only improve the accuracy and efficiency of path tracking, but also ensure the practical feasibility and dynamic adaptability of the path plan, ensure that it can adapt to complex environments, and has high applicability.

[0067] The following will be combined Figures 2 to 6 The intelligent vehicle path tracking method of the present invention is described in detail, wherein, Figure 5 As shown in the figure, the ultimate goal of intelligent car path planning is to minimize the total driving cost; the details are as follows: Step 1, initialize the population: random generation of intelligent car path plans and preliminary processing of constraints.

[0068] Each population individual represents a path intelligent car path plan, randomly generating paths to ensure that the initial solution meets the basic constraints, specifically: The objective function is: ； Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

[0069] It should be noted that when When it is 1, it indicates that the path from node i to node j of the kth vehicle is selected. When it is 0, it indicates that the path from node i to node j of the kth vehicle has not been selected.

[0070] The multiple constraints include the following: (1) The smart car is allowed to visit each target location node once, which means that each key location node i can only be visited by one car once. The corresponding formula is: ; Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, =1 indicates that the path from node i to node j for the kth vehicle is selected.

[0071] (2) The number of times the smart car enters and leaves any node in the path is equal. The corresponding formula is: ; Where n represents the number of path nodes, i and j represent any node in the path, Represented as the path decision variable of the kth vehicle from node i to node j.

[0072] (3) When the load of the smart car is less than or equal to the upper capacity limit, the corresponding formula is:

[0073] in, It is expressed as the demand of node i; It is represented as the capacity of the kth vehicle, Represented as any smart car, Represented as the path decision variable of the kth vehicle from node i to node j.

[0074] (4) The starting and ending positions of the smart car are located at the distribution center, and the corresponding formula is:

[0075] in, represents the path decision variable of the kth vehicle from the distribution center to node j, represents the path decision variable of the kth vehicle from node i to the distribution center.

[0076] (5) The driving time of the smart car satisfies the following formula:

[0077] in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

[0078] Step 2, fitness calculation: Design a fitness function based on indicators such as total path distance, cost, and time.

[0079] Calculate the total path travel distance of each population individual, and select the best solution based on the fitness value; retain the optimal solution and a certain proportion of high-quality solutions as the population basis for the next generation.

[0080] The calculation formula of the fitness value is:

[0081] Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

[0082] It should be noted that the larger the fitness value, the better the path plan.

[0083] Step 3, navigation behavior simulation: specific design and implementation of direction update, scroll adjustment optimization, and jump update.

[0084] The calculation formula for navigation behavior simulation is:

[0085] in, is the current optimal solution, that is, the optimal solution for the current path planning. is the new position of the smart car in the tth iteration, is the new position of the smart car in the t+1 iteration, , is the control parameter, is a random disturbance.

[0086] The behavior model includes three processes: (1) Direction update: simulating dung beetles to adjust the path direction according to the sun's position. Each individual adjusts the current solution by randomly selecting neighbor nodes or exchanging the path order; (2) Rolling adjustment: simulating the behavior of dung beetles rolling dung balls to conduct local search, that is, to make fine-grained local adjustments based on the current path; (3) Jump search: simulating dung beetles to make random jumps due to environmental changes to prevent them from falling into local optimality; environmental parameters include traffic conditions, height and weight limits, etc. Random disturbances are introduced into the model to randomly reorganize the individual's path plan, and the optimized path is adjusted in real time with dynamic changes to ensure global search capabilities and generate new search directions.

[0087] Step 4, dynamic update mechanism: adaptive optimization for changes in the external environment.

[0088] like Figure 2-Figure 4 Demonstrates the dynamic changes in the path planning optimization process: The dynamic optimization of the path shows the gradual improvement of the algorithm through different stages, where e.g. Figure 2 The first stage shown: the initial path is randomly generated, not optimized, the path is complex and the efficiency is low; Figure 3 The second stage shown: optimizing the path, local improvement, the path begins to become more reasonable; Figure 4 Phase 3 shown: Final path, the global optimal solution, with significantly reduced travel distance and cost.

[0089] Step 5, update the path solution: The above algorithm is continuously iterated to gradually converge to the global optimal solution by updating the path plan; when the convergence conditions are met, such as the number of iterations reaches the set value or the fitness change is less than the threshold, the algorithm is stopped.

[0090] Step 6: Output optimization results Optimal path plan: the driving path of each vehicle; Optimization indicators: total driving distance, number of smart cars, operating time, etc.

[0091] Next, the intelligent vehicle path tracking device according to the embodiment of the present invention is described with reference to the accompanying drawings.

[0092] Figure 7 4 is a block diagram of a smart car path tracking device according to an embodiment of the present invention.

[0093] like Figure 7 As shown, the intelligent vehicle path tracking device 10 includes: a construction module 100, a setting module 200 and a tracking module 300.

[0094] Among them, the construction module 100 is used to construct a grid map of the target area, which includes multiple nodes; the setting module 200 is used to construct an objective function based on the driving distance and driving cost of multiple smart cars, and set multiple constraints of the objective function, wherein the multiple constraints constrain the target location node visited, the passed nodes, the load, the starting position, the end position and the driving time of each smart car; the tracking module 300 is used to track the paths of multiple smart cars based on the dung beetle optimization algorithm and the objective function, and obtain the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map. Optionally, the objective function is: ； Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

[0095] Optionally, the multiple constraints include the following: the smart car is allowed to visit each target location node once; the number of times the smart car enters and leaves any node in the path is equal; the load of the smart car is less than or equal to the upper capacity limit; the starting position and the end position of the smart car are located at the distribution center; the travel time of the smart car satisfies the following formula:

[0096] in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

[0097] Optionally, the dung beetle optimization algorithm includes: using the randomly generated paths of the smart cars on the grid map as the population individuals of the dung beetle optimization algorithm, initializing the population, iteratively updating the population by simulating navigation behavior, calculating the fitness value of each population individual, and selecting the solution of the objective function according to the fitness value of each population individual; when the population meets the convergence conditions, outputting the target paths of multiple smart cars from the distribution center to multiple nodes on the grid map.

[0098] Optionally, the convergence condition includes that the number of iterations reaches a preset number, or the fitness value is less than a preset threshold.

[0099] Optionally, the fitness value is calculated as:

[0100] Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

[0101] Optionally, the navigation behavior simulation method includes at least one of direction update, rolling adjustment and jump search, wherein direction update is: each population individual adjusts the current solution by randomly selecting neighbor nodes or exchanging path order; rolling adjustment is: adjustment is made based on the current path; jump search is: random disturbance is introduced to randomly reorganize the path plans of the population individuals to generate a new search direction.

[0102] It should be noted that the aforementioned explanation of the embodiment of the intelligent vehicle path tracking method is also applicable to the intelligent vehicle path tracking device of this embodiment, and will not be repeated here.

[0103] According to the intelligent vehicle path tracking device proposed in the embodiment of the present invention, a grid map of the target area is constructed to make path planning more intuitive, and an objective function is constructed according to the driving distance and driving cost of multiple intelligent vehicles. At the same time, multiple constraints of the objective function are set to obtain multiple path planning results that meet the constraints, so as to screen out relatively high-quality path plans according to the objective function and the constraints, and based on the dung beetle optimization algorithm and the objective function, path tracking optimization is performed on multiple intelligent vehicles to obtain target paths of multiple intelligent vehicles from the distribution center to multiple nodes on the grid map. The dung beetle optimization algorithm can effectively jump out of the local optimal solution and find the global optimal path, and can dynamically adjust the path tracking according to real-time data, which can not only improve the accuracy and efficiency of path tracking, but also ensure the practical feasibility and dynamic adaptability of the path plan, ensure that it can adapt to complex environments, and has high applicability.

[0104] Figure 8 This is a schematic diagram of the structure of a smart car provided by an embodiment of the present invention. The smart car may include: A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0105] When the processor 802 executes the program, the intelligent car path tracking method provided in the above embodiment is implemented.

[0106] Furthermore, the smart car also includes: The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0107] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0108] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0109] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0110] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0111] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0112] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned intelligent vehicle path tracking method when executed by a processor.

[0113] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0114] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0115] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0116] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, the steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0117] A person of ordinary skill in the art may understand that all or part of the steps carried by the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the above-mentioned program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0118] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for tracking a path of an intelligent vehicle, characterized in that: The following steps are involved: Constructing a grid map of the target area, wherein the grid map includes a plurality of nodes; An objective function is constructed according to the driving distance and driving cost of the plurality of smart cars, and a plurality of constraint conditions of the objective function are set, wherein the plurality of constraint conditions constrain the target location node visited, the node passed, the load, the starting location, the end location and the driving time of each smart car; Based on the dung beetle optimization algorithm and the objective function, the multiple smart cars are tracked to obtain target paths of the multiple smart cars from the distribution center to the multiple nodes on the grid map.

2. The intelligent vehicle path tracking method according to claim 1, characterized in that: The objective function is: ； Among them, k represents the number of smart cars, n represents the number of path nodes, i and j represent any node in the path, It is represented as the travel cost from node i to node j, It is represented as the path decision variable of the kth vehicle from node i to node j, and Z is represented as the total driving distance of the smart car.

3. The intelligent vehicle path tracking method according to claim 1, characterized in that: The plurality of constraints include the following: The smart car is allowed to visit each target location node once; The number of times the smart car enters and leaves any node in the path is equal; The load of the smart car is less than or equal to the upper capacity limit; The starting point and the end point of the smart car are located at the distribution center; The driving time of the smart car satisfies the following formula: in, It is represented as the time when the smart car arrives at node i. It is represented as the time when the smart car arrives at node j; It is represented as the residence time of node i; It is expressed as the travel time from node i to node j.

4. The intelligent vehicle path tracking method according to claim 1, characterized in that: The dung beetle optimization algorithm comprises: The paths randomly generated by the smart car on the grid map are used as population individuals of the dung beetle optimization algorithm. Initializing the population, iteratively updating the population by simulating navigation behavior, calculating the fitness value of each individual in the population, and selecting a solution to the objective function according to the fitness value of each individual in the population; When the population meets the convergence condition, target paths of multiple smart cars from the distribution center to multiple nodes on the grid map are output.

5. The intelligent vehicle path tracking method according to claim 4, characterized in that: The navigation behavior simulation method includes at least one of direction update, scroll adjustment and jump search, wherein: The direction update is as follows: each population individual adjusts the current solution by randomly selecting neighbor nodes or exchanging path order; The scrolling adjustment is: adjusting based on the current path; The jump search is to introduce random disturbances and randomly reorganize the path plans of the individuals in the population to generate a new search direction.

6. The intelligent vehicle path tracking method according to claim 4, characterized in that: The convergence condition includes that the number of iterations reaches a preset number, or the fitness value is less than a preset threshold.

7. The intelligent vehicle path tracking method according to claim 4, characterized in that: The calculation formula of the fitness value is: Among them, Z is the objective function value, that is, the total driving distance of the smart car, is an infinitesimal positive number, For a certain path plan.

8. An intelligent vehicle path tracking device, characterized in that: include: A construction module, used for constructing a grid map of a target area, wherein the grid map includes a plurality of nodes; A setting module is used to construct an objective function according to the travel distance and travel cost of multiple smart cars, and set multiple constraint conditions of the objective function, wherein the multiple constraint conditions constrain the visit target location node, the passing node, the load, the starting location, the end location and the travel time of each smart car; The tracking module is used to track the paths of the multiple smart cars based on the dung beetle optimization algorithm and the objective function to obtain target paths of the multiple smart cars from the distribution center to the multiple nodes on the grid map.

9. A smart car, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent vehicle path tracking method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed, the intelligent vehicle path tracking method described in any one of claims 1-7 is implemented.

Images