A route network planning method for dedicated unmanned sightseeing vehicles

Abstract

The present invention introduces a special unmanned sightseeing vehicle network planning method, which includes the following steps: Step 1: Use the original sightseeing vehicle route as the initial path of the algorithm, place a certain amount of pheromones on its path, and plan the route of the sightseeing vehicle; Step 2: Use the shortest path allocation method to allocate the passenger flow in the OD demand matrix to all sightseeing vehicle routes in the sightseeing vehicle network; Step 3: Update the pheromones; Step 4: Set a penalty mechanism for the travel of the solution that does not meet the constraint conditions. Compared with the sightseeing vehicle service model that adopts fixed routes and fixed sightseeing vehicle stops, this invention saves costs and improves the turnover efficiency of sightseeing vehicles by using an ant colony algorithm. While meeting the needs of all scenic spots, it finds the operation paths of multiple sightseeing vehicles with the largest passenger flow density and the smallest detours.

Description

Technical Field

[0001] The invention relates to vehicle route planning, in particular to a route network planning method for a special unmanned sightseeing vehicle. Background Art

[0002] Path planning for driverless cars refers to planning an effective path that is collision-free and can reach the destination safely based on performance indicators after the starting point and destination point of the driverless car are given on the basis of a certain environmental model. For driverless sightseeing cars, it is necessary to first determine their fixed stops and driving paths according to the needs of tourists. Based on the input stops, the driverless sightseeing car quickly searches for drivable paths in the environmental map in real time.

[0003] The conventional practice is to adopt a sightseeing bus service model with fixed routes and fixed sightseeing bus stops. However, the number of sightseeing buses in the scenic area is fixed. In order to save costs and improve the turnover efficiency of sightseeing buses, it is necessary to find a route for multiple sightseeing buses with the highest passenger density and the least detours while meeting the needs of all attractions.

[0004] The ant colony algorithm is a swarm intelligence evolutionary algorithm developed by learning the foraging behavior of ant colonies in the real world. Although a single ant looks very simple, an ant colony composed of many ants can show powerful energy different from that of an individual. The ant colony can find an optimal route in the intricate routes between the ant nest and the food, which is suitable for the network planning problem of the unmanned sightseeing car under the complex network in the present invention.

[0005] For example, the Chinese patent CN110032188A discloses an autonomous obstacle avoidance method based on an unmanned sightseeing electric vehicle, which belongs to the field of intelligent safety control and unmanned intelligent transportation. First, the obstacle data in front of the vehicle is collected by a laser radar sensor installed at the front of the sightseeing electric vehicle. Then, the obstacle data is converted to a coordinate system, and the coordinate points are divided into three areas: left, middle, and right. Obstacle clustering detection is performed on each area, and a judgment is made and an obstacle avoidance decision is made based on the detection results of each area. An autonomous obstacle avoidance method based on an unmanned sightseeing electric vehicle can solve the problem of autonomous and safe obstacle avoidance of unmanned sightseeing electric vehicles in scenic spots and parks, and is suitable for unmanned low-speed sightseeing electric vehicle unmanned driving systems for self-service sightseeing. Although it involves the field of unmanned driving, it only designs methods for avoiding obstacles, and does not design the overall route.

[0006] Another example is the intelligent unmanned sightseeing fleet disclosed in Chinese patent CN109979188B, which aims to combine seven functional modules through multiple systems, and the seven functional modules are combined to form normal sightseeing vehicles, patrol and cleaning multi-purpose vehicles, special population support vehicles, and patrol drones; to achieve the purpose of normal sightseeing vehicles carrying ordinary tourists, special population support vehicles carrying the elderly, children, the sick, the disabled, and pregnant women to visit scenic spots, and thus reduce the cost of hiring drivers; through the unique design of the special population support vehicle, the elderly, the sick, the disabled, and pregnant women can get a more comfortable sightseeing experience during the sightseeing of scenic spots; through patrol and cleaning multi-purpose vehicles to collect passenger flow and clean up road garbage, thereby reducing the investment cost of passenger flow collection personnel and road garbage cleaning personnel; through patrol drones to collect passenger flow density and take photos of garbage in areas that patrol and cleaning multi-purpose vehicles cannot reach, so that the passenger flow collection results are more complete and the garbage removal in the scenic area is more thorough. In this invention, although the sightseeing car uses unmanned driving technology, it cannot find the operation path of multiple sightseeing cars with the largest passenger flow density and the smallest detour while meeting the needs of all scenic spots.

[0007] Therefore, how to design a dedicated unmanned sightseeing vehicle network planning method that can find the operating routes of multiple sightseeing vehicles with the largest passenger flow density and the smallest detours while meeting the needs of all scenic spots to save costs and improve the turnover efficiency of sightseeing vehicles is an urgent issue that needs to be solved and is of great significance. Summary of the invention

[0008] In view of this, the purpose of this application is to provide a route network planning method for a dedicated unmanned sightseeing vehicle.

[0009] In order to achieve the above objectives, this application provides the following technical solutions.

[0010] A method for planning a line network for a dedicated unmanned sightseeing vehicle, the steps of which include:

[0011] Step 1: Use the original sightseeing bus route as the initial path of the algorithm, place a certain amount of pheromones on its path, and plan the route of the sightseeing bus;

[0012] Step 2: Use the shortest path allocation method to allocate the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network;

[0013] Step 3: Update pheromones;

[0014] Step 4: Set up a penalty mechanism for the travel of solutions that do not meet the constraints.

[0015] Preferably, the goal of sightseeing vehicle line network planning is to find a sightseeing vehicle line set with the largest passenger flow density and the smallest non-linear coefficient. The objective function is:

[0016] maxf=max∑ r∈R f r ,

[0017]

[0018] The constraints for its setting are:

[0019]

[0020] Among them, f r is the evaluation function, R is the set of sightseeing bus operation routes; is the passenger flow of route r; l r is the length of line r; l min is the minimum length limit, l max is the maximum length limit, Z r is the nonlinear coefficient of line r, d r The straight-line distance between the starting and ending points of a route.

[0021] Preferably, the formula of the pheromone placed in step 1 is i, j are the adjacent sightseeing bus stops on the initial route r, f r is the evaluation function, and τ is the pheromone.

[0022] Preferably, the transfer formula in step 1 is based on the pheromone strength and heuristic information between the current sightseeing bus stop and the next sightseeing bus stop, and the transfer formula is as follows:

[0023]

[0024] in, The probability that the kth ant chooses the next sightseeing bus stop j from the current sightseeing bus stop; is the pheromone intensity on the path (i, j), is the heuristic information on the path (i, j). Preferably, the formula of the heuristic information in step 1 is:

[0025]

[0026] Among them, start is the starting point, n ij is the number of sightseeing bus routes passing through ij, p is a constant, Od is the number of tourists, and l is the length of the route. It can be seen from the formula that the heuristic information includes the sum of the number of tourists from the starting point to the next sightseeing bus stop j, the route length from the starting point to the next sightseeing bus stop j, and the number of existing sightseeing bus routes from the starting point to the next j (this can reduce the duplication rate of the route and serve more tourists).

[0027] Preferably, step 2 comprises the following steps:

[0028] S201: Assign an initial departure frequency f to each sightseeing bus route init ;

[0029] S202: Calculation of operating expenses between sightseeing bus stops;

[0030] S203: OD ij Assigned to the route with the least cost;

[0031] S204: Recalculate the departure frequencies of all sightseeing buses on the route.

[0032] Preferably, the calculation formula for the operating cost in step S202 is:

[0033]

[0034] in, The cost of choosing route route from sightseeing bus stop i to sightseeing bus stop j; is the waiting time of route route (equal to half of the sum of the departure intervals of all sightseeing bus lines in route route); C w is the weight of waiting time; C1 represents the penalty of one transfer, when one transfer is required, X1 is 1, otherwise it is 0; C2 represents the penalty of two transfers, when two transfers are required, X2 is 1, otherwise it is 0; represents the travel time from sightseeing bus stop i to sightseeing bus stop j. t is the weight.

[0035] Preferably, in step S204, the calculation formula of the departure frequency is:

[0036]

[0037] in, is the maximum cross-sectional passenger flow on the sightseeing bus route r (unit: person / hour), CAP is the maximum passenger capacity of a standard vehicle, and F r Cannot exceed the maximum departure frequency F max .

[0038] Preferably, step three comprises the following steps:

[0039] S301: Reduce the amount of pheromones on each edge by simulating the evaporation of pheromones in nature;

[0040] S302: Calculate the pheromone increment on the path traveled by each ant.

[0041] Preferably, the updating formula of pheromone in step 3 is:

[0042]

[0043] in, It is an updated pheromone. is the pheromone before the update; ρ is the constant that controls the volatilization of pheromone; k is the number of ants; is the amount of pheromone updated by the kth ant on ij.

[0044] Preferably, the specific calculation formula for the pheromone amount updated by the kth ant on ij is as follows:

[0045]

[0046] Among them, w k is the sightseeing bus route found by the kth ant, f wk Yes k The evaluation function value of .

[0047] Preferably, the solutions that do not meet the constraint conditions in step 4 include:

[0048] First, loops appear during the search process;

[0049] Second, the searched path r does not meet the line length constraint;

[0050] Third, the searched path r does not meet the non-linear coefficient constraint.

[0051] Preferably, in step 4, the penalty mechanism is to perform additional pheromone evaporation on the path passed by the ants that need to be punished after the pheromone is updated, and the formula is:

[0052]

[0053] Among them, L penalty represents the path searched by the ant that needs to be punished, ρ penalty Indicates additional pheromone volatilization parameters.

[0054] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0055] (1) Compared with the sightseeing bus service model with fixed routes and fixed sightseeing bus stops, the use of the ant colony algorithm reduces the travel time and distance of the sightseeing buses, improves the turnover efficiency of the sightseeing buses, and increases economic benefits. While meeting the needs of all attractions, the operation paths of multiple sightseeing buses with the highest passenger flow density and the least detours are found.

[0056] (2) When allocating the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network, the costs of various situations, including no transfer, single transfer, and multiple transfers, are fully considered. While ensuring that all attractions are met, the travel time and distance of the sightseeing bus are reduced, thereby increasing economic benefits.

[0057] (3) The turnover efficiency of sightseeing vehicles is improved through the renewal of pheromones.

[0058] (4) Constraints and penalty mechanisms are used to eliminate impractical sightseeing bus routes, thereby improving the accuracy and practicality of route planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creative work. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0060] Figure 1 A flowchart of a route network planning method for a dedicated unmanned sightseeing vehicle provided by the present invention;

[0061] Figure 2 A flowchart of an ant colony algorithm for a line network planning method for a dedicated unmanned sightseeing vehicle provided by the present invention;

[0062] Figure 3 The present invention provides an algorithm design flow chart of a special unmanned sightseeing vehicle line network planning method. DETAILED DESCRIPTION

[0063] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, rather than all of the embodiments. In the following description, specific details such as specific configuration and components are provided only to help fully understand the embodiments of the present application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, for clarity and brevity, the description of known functions and structures is omitted in the embodiment.

[0064] It should be understood that the references to "one embodiment" or "this embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "one embodiment" or "this embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0065] In addition, the present application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0066] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" in this article describes another type of association object relationship, indicating that there can be two relationships. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0067] The term "at least one" in this article is merely a description of the association relationship of associated objects, indicating that there may be three relationships. For example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0068] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusions.

[0069] Example 1

[0070] This embodiment introduces a route network planning method for a dedicated unmanned sightseeing vehicle.

[0071] Please refer to Figure 1 , Figure 1 A flowchart of a dedicated unmanned sightseeing vehicle line network planning method provided by the present invention is provided, which shows a dedicated unmanned sightseeing vehicle line network planning method, including the following steps:

[0072] Step 1: Use the original sightseeing bus route as the initial path of the algorithm, place a certain amount of pheromones on its path, and plan the route of the sightseeing bus;

[0073] Step 2: Use the shortest path allocation method to allocate the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network;

[0074] Step 3: Update pheromones;

[0075] Step 4: Set up a penalty mechanism for the travel of solutions that do not meet the constraints.

[0076] Furthermore, the goal of sightseeing vehicle line network planning is to find a sightseeing vehicle line set with the largest passenger flow density and the smallest non-linear coefficient. The objective function is:

[0077] maxf=maxΣ r∈R f r ,

[0078]

[0079] The constraints for its setting are:

[0080]

[0081] Among them, f r is the evaluation function, R is the set of sightseeing bus operation routes; is the passenger flow of route r; l r is the length of line r; l min is the minimum length limit, l max is the maximum length limit, Z r is the nonlinear coefficient of line r, d r The straight-line distance between the starting and ending points of a route.

[0082] Example 2

[0083] Based on the above-mentioned embodiment 1, this embodiment mainly introduces the ant colony algorithm and step 1 applied in a line network planning method for a special unmanned sightseeing vehicle.

[0084] The first ant colony algorithm is applied, please refer to Figure 2 , Figure 2 The flowchart of the ant colony algorithm of the line network planning method for a dedicated unmanned sightseeing vehicle provided by the present invention shows that the ant colony algorithm includes the following steps:

[0085] S101: Initialize the ant colony size antsize and the number of iterations K;

[0086] S102: assign antsize ants to the starting point, and add the starting point to the taboo table;

[0087] S103: Each ant selects the next node according to the heuristic information and the pheromone strength according to the following probability selection formula. If the end point is reached or the next node to be selected cannot be found, the search stops, otherwise the search continues.

[0088]

[0089] in, is the probability that the kth ant selects the next node j from the current node i, is the pheromone intensity on edge (i, j); represents the heuristic information on the edge (i, j); α and β are the influencing factors of pheromone and heuristic information respectively; the size of α represents the intensity of pheromone effect during the path search process of the ant colony. The larger the value, the greater the possibility that the ant will choose the optimal path obtained by the previous search, so that the randomness of the search will be weakened. However, when the α value is too large, the ant colony will fall into the local optimum too early; the size of β represents the intensity of heuristic information effect during the path search process of the ant colony. The larger the value, the greater the possibility that the ant will choose the local shortest path, and when the β value is too large, the ant colony will fall into the local optimum too early; tabu k is the set of nodes visited by the kth ant and the set of inaccessible nodes.

[0090] S104: Calculate the evaluation function of each ant's solution.

[0091] S105: Based on the evaluation function obtained for each ant, the pheromone is updated using the following method.

[0092]

[0093] in It is an updated pheromone. is the pheromone before the update, ρ is the constant that controls the volatilization of pheromone, antsize is the size of the ant colony, is the amount of pheromone updated by the kth ant at (i, j).

[0094] Next, we introduce step 1 using the ant colony algorithm.

[0095] Please refer to Figure 3 , Figure 3 The present invention provides an algorithm design flow chart of a special unmanned sightseeing vehicle line network planning method, which shows step one: using the original sightseeing vehicle route as the initial path of the algorithm, placing a certain amount of pheromones on its path, and planning the route of the sightseeing vehicle.

[0096] Before the ant colony algorithm starts searching for a path, the original sightseeing bus route is used as the initial path of the algorithm, and a certain amount of pheromone is placed on the path to provide some guidance for the search process of the ant colony algorithm and prevent the path searched by the ant colony algorithm from deviating too much from the original route. The specific formula is as follows:

[0097]

[0098] Among them, i, j are the adjacent sightseeing bus stops on the initial route r, and f r is the evaluation function, and τ is the pheromone.

[0099] When the ant colony algorithm is used to implement the route adjustment process, each ant builds a route from the starting point i, and continuously selects the next sightseeing bus stop j until it reaches the terminal or there is no next sightseeing bus stop to choose from. If the sightseeing bus route searched is better than the current route, the new route replaces the original route. However, a feasible sightseeing bus route should also satisfy the length constraint, non-linear coefficient constraint, etc. mentioned above. When the ant selects the next sightseeing bus stop, it does not select randomly, but selects according to the transfer formula. They select based on the pheromone intensity and heuristic information between the current sightseeing bus stop and the next sightseeing bus stop. Pheromone information and heuristic information are the key points of the ant colony algorithm, and pheromones are usually related to its evaluation function. The heuristic information is obtained through a greedy algorithm, which encourages ants to choose the local optimal path, which mainly includes passenger flow and the distance between sightseeing bus stops in route planning. The specific calculation formula is as follows:

[0100]

[0101] Among them, start is the starting point, n ij is the number of sightseeing bus routes passing through ij, p is a constant, Od is the number of tourists, and l is the length of the route. From the formula, it can be seen that the heuristic information includes the sum of the number of tourists from the starting point to the next sightseeing bus stop j, the route length from the starting point to the next sightseeing bus stop j, and the number of sightseeing bus routes from the starting point to the next j (this can reduce the duplication rate of the route and serve more tourists). The kth ant uses the following probability formula to select the next sightseeing bus stop j at the sightseeing bus stop i:

[0102]

[0103] in, The probability that the kth ant chooses the next sightseeing bus stop j from the current sightseeing bus stop; is the pheromone intensity on the path (i, j), is the heuristic information on the path (i, j).

[0104] Compared with the sightseeing bus service model with fixed routes and fixed sightseeing bus stops, the use of ant colony algorithm reduces the travel time and distance of sightseeing buses, improves the turnover efficiency of sightseeing buses, and increases economic benefits. While meeting the needs of all attractions, the operating paths of multiple sightseeing buses with the highest passenger density and the least detours are found.

[0105] Example 3

[0106] Based on the above-mentioned embodiment 2, this embodiment mainly introduces step 2 in a method for planning a line network for a dedicated unmanned sightseeing vehicle.

[0107] Step 2: Use the shortest path allocation method to allocate the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network.

[0108] In the ant colony algorithm, each ant tries to find a new route for a sightseeing bus line. When the ant finds a new route, it needs to use the evaluation function to calculate it. In order to calculate the evaluation function value, Must be calculated.

[0109] In order to evaluate the newly generated routes by ants, the newly generated routes are used to replace the original routes that need to be adjusted, and then the new routes and other sightseeing bus routes in the original sightseeing bus network are combined to form a new sightseeing bus network. Because in the process of adjusting the sightseeing bus network, the performance of the entire sightseeing bus network needs to be considered. It is necessary to redistribute the passenger flow in the network and redistribute these passenger flows to all sightseeing bus routes in the network. The newly generated routes are calculated using the evaluation function value of the entire newly formed sightseeing bus network.

[0110] The shortest path allocation method is used to allocate the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network. Each sightseeing bus route has a capacity limit, which is determined by the number of passengers and the departure frequency of the sightseeing bus.

[0111] The specific allocation method includes the following steps:

[0112] S201: Assign an initial departure frequency f to each sightseeing bus route init ;

[0113] S202: Calculation of operating expenses between sightseeing bus stops;

[0114] S203: OD ij Assigned to the route with the least cost;

[0115] S204: Recalculate the departure frequencies of all sightseeing buses on the route.

[0116] Further, in step S202, for every two sightseeing bus stop points OD ij There may be many routes from sightseeing bus stop i to sightseeing bus stop j. ij Assign the route with the lowest cost among one sightseeing bus line (no transfer), two sightseeing bus lines (one transfer) or three sightseeing bus lines (two transfers). Assuming that this route is the path from sightseeing bus stop i to sightseeing bus stop j, it contains one, two or three sightseeing bus lines, depending on whether transfers are required. The calculation formula for the running cost is:

[0117]

[0118] in, The cost of choosing route route from sightseeing bus stop i to sightseeing bus stop j; is the waiting time of route route (equal to half of the sum of the departure intervals of all sightseeing bus lines in route route); C w is the weight of waiting time; C1 represents the penalty of one transfer, when one transfer is required, X1 is 1, otherwise it is 0; C2 represents the penalty of two transfers, when two transfers are required, X2 is 1, otherwise it is 0; represents the travel time from sightseeing bus stop i to sightseeing bus stop j. t is the weight.

[0119] Furthermore, in step S204, the calculation formula of the departure frequency is:

[0120]

[0121] in, is the maximum cross-sectional passenger flow on the sightseeing bus route r (unit: person / hour), CAP is the maximum passenger capacity of a standard vehicle. And F r Cannot exceed the maximum departure frequency F max If F r Less than or equal to F max , then update the departure frequency, otherwise, in the same way, allocate the remaining passenger flow to other routes that can reach j from sightseeing bus stop i. In order to ensure that sightseeing bus line r is not selected in the next allocation process, the waiting time of sightseeing bus line r is set to a large constant. Until all sightseeing bus stops are selected.

[0122] When allocating the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network, the costs of various situations such as no transfer, single transfer and multiple transfers are fully considered. While ensuring that all attractions are met, the travel time and distance of the sightseeing buses are reduced, thereby increasing economic benefits.

[0123] Example 4

[0124] Based on the above-mentioned embodiment 3, this embodiment mainly introduces steps three and four in a line network planning method for a dedicated unmanned sightseeing vehicle.

[0125] Step 3: Update pheromones;

[0126] Pheromones are important information for ants to communicate in the ant colony algorithm. They need to be updated after all ants have searched the wide area for the route. Before updating the pheromone, the route searched by each ant needs to be assigned passenger flow, and then the evaluation function is calculated based on the result of passenger flow assignment. After the evaluation function is calculated, the pheromone can be updated based on the evaluation function of each route.

[0127] Furthermore, the updating of pheromones includes the following steps:

[0128] S301: Reduce the amount of pheromones on each edge by simulating the evaporation of pheromones in nature;

[0129] S302: Calculate the pheromone increment on the path walked by each ant. Further, the pheromone update formula in step 3 is:

[0130]

[0131] in, It is an updated pheromone. is the pheromone before the update; ρ is the constant that controls the volatilization of pheromone; k is the number of ants; is the amount of pheromone updated by the kth ant on ij.

[0132] Furthermore, the specific calculation formula for the pheromone amount updated by the kth ant on ij is as follows:

[0133]

[0134] Among them, w k is the sightseeing bus route found by the kth ant, f wk Yes k The evaluation function value of .

[0135] Step 4: Set up a penalty mechanism for the travel of solutions that do not meet the constraints.

[0136] During the search process of the ant colony algorithm, some solutions that do not meet the constraints may appear. If there are too many solutions that do not meet the constraints, the quality of the solution will inevitably be affected. Therefore, in order to reduce the number of solutions that do not meet the constraints, it is decided to add a penalty mechanism. Penalties are required when the following situations occur.

[0137] Fourth, loops appear during the search process.

[0138] Fifth, the searched path r does not meet the line length constraint.

[0139] Sixth, the searched path r does not meet the non-linear coefficient constraint.

[0140] The specific method of punishment is to evaporate additional pheromones on the path passed by the ants that need to be punished after the pheromone is updated. The formula is:

[0141]

[0142] Among them, L penalty represents the path searched by the ant that needs to be punished, ρ penalty Indicates additional pheromone volatilization parameters.

[0143] The present invention improves the turnover efficiency of the sightseeing vehicle by updating the pheromone.

[0144] The present invention eliminates sightseeing car routes that do not meet practicality through constraint conditions and penalty mechanisms, thereby improving the accuracy and practicality of route planning.

[0145] The above description is only the preferred embodiment of the present invention, which does not limit the protection scope of the present invention. For those skilled in the art, the present invention can be modified and varied in various ways. Within the spirit and principle of the present invention, any change, modification, replacement, integration and parameter change of these embodiments by conventional substitution or capable of achieving the same function without departing from the principle and spirit of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for planning a line network for a dedicated unmanned sightseeing vehicle, characterized in that: The steps include: Step 1: Use the original sightseeing bus route as the initial path of the algorithm, place a certain amount of pheromones on its path, and plan the route of the sightseeing bus; Step 2: Use the shortest path allocation method to allocate the passenger flow in the OD demand matrix to all sightseeing bus routes in the sightseeing bus network; Step 3: Update pheromones; Step 4: Set up a penalty mechanism for the travel of solutions that do not meet the constraints; The pheromone calculation formula in step 1 is: Among them, i, j are the adjacent sightseeing bus stops on the initial route r, and f r is the evaluation function, It’s pheromone; The evaluation function formula is: The constraints for its setting are: in, is the passenger flow of route r, l r is the length of line r, Z r is the nonlinear coefficient of line r, d r is the straight-line distance between the starting and ending points of the line; The step 2 comprises the following steps: S201: Assign an initial departure frequency f to each sightseeing bus route init ; S202: Calculation of operating expenses between sightseeing bus stops; S203: Set every two sightseeing bus stops at OD ij Assigned to the route with the least cost; S204: recalculating the departure frequencies of all sightseeing buses on the route; The step three comprises the following steps: S301: Reduce the amount of pheromones on each edge by simulating the evaporation of pheromones in nature; S302: Calculate the pheromone increment on the path walked by each ant; The update formula of pheromone in step 3 is: in, It is an updated pheromone. is the pheromone before the update; ρ is the constant that controls the volatilization of pheromones; k is the number of ants; antsize is the size of the ant colony, is the amount of pheromone updated by the kth ant on ij; The solutions that do not meet the constraint conditions in step 4 include: First, loops appear during the search process; Second, the searched path r does not meet the line length constraint; Third, the searched path r does not meet the non-linear coefficient constraint; In step 4, the penalty mechanism is to perform additional pheromone evaporation on the path passed by the ants that need to be punished after the pheromone is updated. The formula is: Among them, L penalty represents the path searched by the ant that needs to be punished, ρ penalty represents additional pheromone volatilization parameters; The route for the sightseeing bus is chosen based on a transfer formula; The transfer formula is as follows: in, The probability that the kth ant chooses the next sightseeing bus stop j from the current sightseeing bus stop i; is the pheromone intensity on the path (i, j), is the heuristic information on the path (i, j), α and β are the influencing factors of pheromone and heuristic information respectively; the size of α indicates the intensity of pheromone effect in the process of path search of ant colony; the size of β indicates the intensity of heuristic information effect in the process of path search of ant colony; tabu k is the set of nodes visited by the kth ant and the set of inaccessible nodes.

2. A method for planning a line network for a dedicated unmanned sightseeing vehicle according to claim 1, characterized in that: The formula for the heuristic information in step 1 is: Among them, start is the starting point, n ij is the number of sightseeing bus routes passing through ij, p is a constant, Od is the number of tourists, and l is the length of the route. It can be seen from the formula that the heuristic information includes the sum of the number of tourists from the starting point to the next sightseeing bus stop j, the length of the route from the starting point to the next sightseeing bus stop j, and the number of existing sightseeing bus routes from the starting point to the next j.

3. A method for planning a line network for a dedicated unmanned sightseeing vehicle according to claim 1, characterized in that: The calculation formula of the operating cost in step S202 is: in, The cost of choosing route route from sightseeing bus stop i to sightseeing bus stop j; is the waiting time of route route; C w is the weight of waiting time; C1 represents the penalty of one transfer, when one transfer is required, X1 is 1, otherwise it is 0; C2 represents the penalty of two transfers, when two transfers are required, X2 is 1, otherwise it is 0; represents the travel time from sightseeing bus stop i to sightseeing bus stop j. t is the weight.

4. A method for planning a line network for a dedicated unmanned sightseeing vehicle according to claim 1, characterized in that: In step S204, the calculation formula of the departure frequency is: in, is the maximum cross-sectional passenger flow on the sightseeing bus route r, CAP is the maximum passenger capacity of a standard vehicle and F r Cannot exceed the maximum departure frequency F max .

5. A method for planning a line network for a dedicated unmanned sightseeing vehicle according to claim 1, characterized in that: The specific calculation formula for the pheromone amount updated by the kth ant on ij is as follows: Among them, w k is the sightseeing bus route found by the kth ant, f wk Yes k The evaluation function value of .

Images