Heuristic Vehicle Routing Method Applied to Microscopic Traffic Simulation Engine

Abstract

The present invention discloses a heuristic vehicle path planning method applied to a microscopic traffic simulation engine, including constructing a road network road weight model; generating vehicles in the road network, planning an initial path for the vehicles according to the starting point and the ending point, and presetting a simulation step length; the vehicles travel along the initial path, and perform dynamic path planning once whenever the time reaches a simulation step length. If the path needs to be re-planned, the heuristic vehicle path planning method is adopted. The present invention proposes a new heuristic re-routing trigger mechanism, which combines factors such as the OD matrix, intersection congestion index, road congestion index, road congestion index threshold, intersection congestion index threshold, etc., to solve the problem of vehicle path re-planning in the process of urban area governance. It improves the flexibility, authenticity, and effectiveness of vehicles in the microscopic simulation process, proposes a new hybrid heuristic function, and improves the adaptability of vehicle path planning under multi-source environmental conditions in the simulation process.

Description

Technical Field

[0001] The present invention relates to a vehicle path planning method, and particularly to a heuristic vehicle path planning method applied to a microscopic traffic simulation engine. Background Art

[0002] In the process of urban traffic area governance, when traffic jams occur to vehicles, vehicle path replanning will be carried out to govern the urban area traffic flow. Currently, there are many vehicle path planning methods, such as: graph search algorithms, artificial potential field algorithms, and intelligent optimization algorithms. Among them, graph search algorithms include Dijkstra algorithm, Floyd algorithm, A* algorithm, etc.; intelligent optimization algorithms include genetic algorithm, ant colony algorithm, particle swarm algorithm, etc.

[0003] The Dijkstra algorithm is an efficient graph theory algorithm specifically used to calculate the shortest paths from a single source node to all other vertices in a weighted directed graph. This algorithm is based on a greedy strategy and gradually constructs a shortest path tree through an iterative process. The Dijkstra algorithm is applicable to graphs without negative weight edges because it relies on the cumulative property of edge weights to ensure the monotonic increase of path lengths.

[0004] The Floyd algorithm, as an algorithm based on the principle of dynamic programming, its core goal is to solve the shortest path problem between all vertex pairs in a weighted graph. The core strategy of this algorithm lies in optimizing and updating the existing shortest path estimates by iteratively introducing intermediate vertices. The Floyd algorithm is applicable to both directed and undirected graphs and can handle cases with negative weight edges, but the premise is that there are no negative weight cycles in the graph.

[0005] The A* algorithm is an efficient heuristic search strategy that combines the completeness of breadth-first search and the efficiency of greedy best-first search. The core of the A* algorithm lies in its evaluation function, which consists of two parts: the actual cost and the heuristic estimate. Among them, represents the actual path length from the starting point to the current node, and is a heuristic function used to estimate the shortest path length from the node to the end point. This heuristic function is usually designed based on problem domain knowledge. For example, in path planning, it can be the Euclidean distance or the Manhattan distance, etc. The A* algorithm searches for paths by preferentially expanding those nodes with the lowest value, thus significantly reducing the search space while ensuring finding the shortest path and improving the search efficiency. When the heuristic function satisfies conditions such as non-negative and admissible, i.e., when, the A* algorithm can guarantee to find the shortest path. Heuristic function As the embodiment of the A* algorithm heuristic, it can enable the algorithm to find the optimal path with less cost, where the estimated distance Often takes the Euclidean distance, Manhattan distance, diagonal distance, and Chebyshev distance, in the following four ways:

[0006] ,

[0007] ,

[0008] ,

[0009] ,

[0010] Among them, 、 are the x-axis coordinate and y-axis coordinate of the current node, 、 are the x-axis coordinate and y-axis coordinate of the end point.

[0011] The application of the artificial potential field algorithm in the transportation field is mainly reflected in the simulation optimization and control of traffic flow. By simulating the interaction forces between vehicles, this algorithm simulates and predicts the dynamic behavior of traffic flow, thus providing decision-making support for traffic management and planning. In traffic flow simulation, each vehicle can be regarded as a particle, and its movement on the road is affected by the vehicle in front (repulsive force) and the destination (attractive force). The repulsive force ensures that vehicles maintain a safe distance and avoid collisions, while the attractive force guides the vehicles towards the destination. In addition, the artificial potential field algorithm can also be applied to ITS for the control and optimization of dynamic traffic flow. For example, in traffic signal control, the algorithm can be used to adjust the timing of traffic lights to reduce the waiting time at intersections and improve the traffic capacity of roads. In the path planning of emergency vehicles, the algorithm can help emergency vehicles find the fastest path to reach the destination while minimizing the impact on other vehicles.

[0012] The genetic algorithm is an optimization technique inspired by the theory of biological evolution. Its application in the field of traffic system optimization demonstrates its potential as an efficient search strategy, especially in solving complex traffic flow allocation and traffic signal control problems. By encoding the vehicle flow in the traffic network to form "chromosomes" representing different traffic configurations, the genetic algorithm iteratively optimizes the traffic flow by simulating the mechanisms of natural selection, such as elitist strategy, crossover, and mutation. The fitness function usually evaluates the performance of each solution based on indicators such as traffic flow, delay, or energy consumption.

[0013] Ant colony algorithm is a meta - heuristic optimization algorithm inspired by the foraging behavior of ants in nature. In the field of traffic system optimization, ant colony algorithm is applied to solve problems such as traffic flow assignment, route selection, and traffic signal control. The algorithm simulates the positive feedback mechanism of ants during the process of finding food: ants leave pheromones on the path, and other ants tend to walk along the path with higher pheromone concentration, thus gradually forming the optimal path. In the traffic network, the pheromone concentration of each path is positively correlated with the number of vehicles passing through the path, while the travel time of the path is negatively correlated with it. Through the iterative process, the algorithm can learn efficient paths to reduce congestion and travel time.

[0014] Particle swarm optimization is an optimization technique based on swarm intelligence. In the field of traffic system optimization, particle swarm optimization is effective in solving problems such as traffic flow assignment, traffic signal control, and path planning. The algorithm simulates the search behavior of a group of particles in the solution space, where each particle represents a potential solution, and updates its flight direction and speed by tracking the historical best positions of individuals and the group. In the traffic network, the position of the particle encodes the vehicle assignment or signal timing, and the update of the speed reflects the optimization process based on fitness functions such as traffic flow, delay, or energy consumption.

[0015] However, these algorithms have some problems. For example, Dijkstra's algorithm is not applicable to finding the shortest paths between all pairs of vertices and is also not suitable for handling negative - weighted edges. The artificial potential field algorithm may get stuck in local minima, that is, the robot may stop moving at a point that is not globally optimal, especially in complex environments. Genetic algorithms may require a large number of iterations to find the optimal solution or an approximate optimal solution, which may make its convergence speed slower than some traditional optimization algorithms. The performance of the ant colony algorithm highly depends on parameter settings such as crossover rate, mutation rate, and population size, and the selection of these parameters has a significant impact on the effect of the algorithm. Summary of the Invention

[0016] The object of the present invention is to provide a heuristic vehicle path planning method applied to a microscopic traffic simulation engine to solve the problem that the above - mentioned path planning algorithms have poor effects in the process of microscopic traffic simulation.

[0017] To achieve the above object, the technical solution adopted by the present invention is as follows: A heuristic vehicle path planning method applied to a microscopic traffic simulation engine, applied to road network traffic simulation, the road network includes multiple roads and multiple intersections, and includes the following steps;

[0018] S1, construct a road network road weight model for generating the road congestion index of each road and the intersection congestion index of each intersection, and preset the road congestion index threshold ThR and the intersection congestion index threshold ThC;

[0019] Construct a road congestion index array and an intersection congestion index array. The road congestion index array consists of the road congestion indexes of all roads, and the intersection congestion index array consists of the intersection congestion indexes of all intersections in the road network;

[0020] S2, Generate vehicles in the road network, plan an initial path for the vehicles according to the starting point and the ending point, and preset a simulation step size;

[0021] S3, The vehicle travels along the initial path, and whenever the time reaches a simulation step size, a dynamic path planning is performed once. The dynamic path planning in the t-th simulation step size includes steps S31~S36;

[0022] S31, Obtain the current position of the vehicle, the road congestion index array, the intersection congestion index array, and the OD matrix at the current moment;

[0023] S32, Determine whether the current OD matrix has changed compared with the OD matrix in the (t - 1)-th dynamic path planning. If so, re-plan the path, generate the t-th simulation path, and use the next intersection of the current position as the relevant intersection and all roads from the current position to the ending point as the relevant roads;

[0024] S33, Compare whether the intersection congestion index of the relevant intersection has changed between the t-th simulation path and the (t - 1)-th simulation path. If so, enter step S34; otherwise, use the (t - 1)-th simulation path as the t-th simulation path;

[0025] S34, Determine whether the intersection congestion index of the relevant intersection exceeds the intersection congestion index threshold ThC. If it exceeds, enter step S35; otherwise, use the (t - 1)-th simulation path as the t-th simulation path;

[0026] S35, Determine whether the road congestion index of the relevant roads has changed. If at least one of the relevant roads has changed, enter step S36; otherwise, use the (t - 1)-th simulation path as the t-th simulation path;

[0027] S36, Determine whether the road congestion index of the relevant roads exceeds the road congestion index threshold ThR;

[0028] If at least one of the relevant roads exceeds, re-plan the path; otherwise, use the (t - 1)-th simulation path as the t-th simulation path.

[0029] Preferably: In S1, label each road and each intersection in the road network. Among them, the road congestion index of the i-th road , and the intersection congestion index of the j-th intersection are obtained according to the following formula;

[0030] ,

[0031] Wherein, is the actual travel time, is the free flow time; is the length of the th road; is the real-time traffic speed of the th road, is the free flow speed;

[0032] ,

[0033] The jth intersection corresponds to n inlet roads, and the kth inlet road is , and its real-time traffic speed is , 1 ≤ k ≤ n.

[0034] Preferably: in S32 and S36, a heuristic vehicle path planning method is adopted to re-plan the path, and the heuristic vehicle path planning method includes the following steps;

[0035] a1. Select the A* algorithm, and the heuristic function of the A* algorithm is h(n);

[0036] a2. Construct a hybrid heuristic function ;

[0037] ,

[0038] Wherein, , are the x-axis coordinate and y-axis coordinate of the current node, , are the x-axis coordinate and y-axis coordinate of the parent node of the current node, , are the x-axis coordinate and y-axis coordinate of the end point, T is the distance from the starting point to the end point, is the road congestion index of the next road at the current position in the (t - 1)th simulation path, is the intersection congestion index of the next intersection at the current position in the (t - 1)th simulation path;

[0039] a3. Replace the heuristic function h(n) in the A* algorithm with the hybrid heuristic function to obtain the heuristic vehicle path planning method.

[0040] Regarding the OD matrix: The OD matrix is a table of the number of trips exchanged between all origins and destinations in a transportation network, reflecting the basic needs of users for the transportation network and the spatial distribution of road network traffic flow. The dynamic OD matrix reflects the time-varying traffic demand within a specific period for each OD pair (corresponding to each specific origin-destination pair in the transportation network). In the intelligent transportation system (ITS), the dynamic OD matrix is important data in the advanced traveler information system (ATIS) and the advanced traffic management system (ATMS), and it is also the basic data for dynamic traffic assignment models and some microscopic traffic simulators, directly affecting the real-time effectiveness of ITS. There are static matrix estimation methods, dynamic matrix estimation methods, etc. for estimating the OD matrix. This invention does not improve them but only utilizes this matrix.

[0041] Compared with the prior art, the advantages of the present invention are as follows:

[0042] (1) A new heuristic rerouting trigger mechanism is proposed, which combines factors such as the OD matrix, intersection congestion index, road congestion index, road congestion index threshold ThR, intersection congestion index threshold ThC, etc., to solve the problem of vehicle path replanning in the process of urban area governance. It improves the flexibility, authenticity, and effectiveness of vehicles in the microscopic simulation process.

[0043] (2) The road congestion index and the intersection congestion index of intersections are combined into the heuristic function of the A* algorithm, thus obtaining a new hybrid heuristic function , and this method improves the adaptability of vehicle path planning under multi-source environmental conditions in the simulation process by modifying the estimated value of the heuristic vehicle path search algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is the flow chart of the present invention;

[0045] Figure 2 is the road network of the map used in Embodiment 2;

[0046] Figure 3 is for Figure 2 the traffic volume statistical results of a 30-minute short-term traffic simulation for the area shown;

[0047] Figure 4 is for Figure 2 the traffic volume statistical results of a 60-minute short-term traffic simulation for the area shown;

[0048] Figure 5 is for Figure 2 the bayonet congestion coefficient results of a 30-minute short-term traffic simulation for the area shown;

[0049] Figure 6For the Figure 2 results of the congestion coefficient of the checkpoint for short-term traffic simulation of 60 minutes in the area shown. Specific implementation manners

[0050] The present invention will be further described below with reference to the accompanying drawings.

[0051] Example 1: Refer to Figure 1 , a heuristic vehicle path planning method applied to a microscopic traffic simulation engine, applied to road network traffic simulation, the road network including multiple roads and multiple intersections, comprising the following steps;

[0052] S1, construct a road network road weight model for generating a road congestion index for each road and an intersection congestion index for each intersection, and preset a road congestion index threshold ThR and an intersection congestion index threshold ThC;

[0053] Construct a road congestion index array and an intersection congestion index array, the road congestion index array being composed of the road congestion indexes of all roads, and the intersection congestion index array being composed of the intersection congestion indexes of all intersections in the road network;

[0054] S2, generate vehicles in the road network, plan an initial path for the vehicles according to the starting point and the ending point, and preset a simulation step size;

[0055] S3, the vehicles travel along the initial path, and whenever the time reaches a simulation step size, perform a dynamic path planning once. The dynamic path planning in the t-th simulation step size includes steps S31 to S36;

[0056] S31, obtain the current position of the vehicle, the road congestion index array, the intersection congestion index array and the OD matrix at the current moment;

[0057] S32, determine whether the current OD matrix has changed compared with the OD matrix in the (t - 1)-th dynamic path planning. If so, re-plan the path to generate the t-th simulation path, and use the next intersection of the current position as the relevant intersection and all roads from the current position to the ending point as the relevant roads;

[0058] S33, compare whether the intersection congestion index of the relevant intersection has changed between the t-th simulation path and the (t - 1)-th simulation path. If so, enter step S34, otherwise, use the (t - 1)-th simulation path as the t-th simulation path;

[0059] S34, determine whether the intersection congestion index of the relevant intersection exceeds the intersection congestion index threshold ThC. If it exceeds, enter step S35, otherwise, use the (t - 1)-th simulation path as the t-th simulation path;

[0060] S35. Determine whether the road congestion index of the relevant roads has changed. If the road congestion index of at least one relevant road has changed, proceed to step S36; otherwise, use the simulation path of the (t - 1)-th time as the simulation path of the t-th time.

[0061] S36. Determine whether the road congestion index of the relevant roads exceeds the road congestion index threshold ThR.

[0062] If the road congestion index of at least one relevant road exceeds the threshold, re-plan the path; otherwise, use the simulation path of the (t - 1)-th time as the simulation path of the t-th time.

[0063] In S1, label each road and each intersection in the road network. The road congestion index of the i-th road and the intersection congestion index of the j-th intersection are obtained according to the following formula:

[0064] ,

[0065] In the formula, is the actual travel time, is the free flow time; is the length of the i-th road; is the real-time road condition speed of the i-th road, is the free flow speed;

[0066] ,

[0067] The j-th intersection corresponds to n incoming roads, and the k-th incoming road is , and its real-time road condition speed is , where 1 ≤ k ≤ n.

[0068] In S32 and S36, use the heuristic vehicle path planning method to re-plan the path. The heuristic vehicle path planning method includes the following steps:

[0069] a1. Select the A* algorithm, and the heuristic function of the A* algorithm is h(n).

[0070] a2. Construct a hybrid heuristic function ;

[0071] ,

[0072] In the formula, , are the x-axis coordinate and y-axis coordinate of the current node, , are the x-axis coordinate and y-axis coordinate of the parent node of the current node, , The x-axis coordinate and y-axis coordinate with [the end point], and T is the distance from the starting point to the end point. is the road congestion index of the next road at the current position in the (t - 1)-th simulation path. is the intersection congestion index of the next intersection at the current position in the (t - 1)-th simulation path;

[0073] a3, using the hybrid heuristic function Replace the heuristic function in the A* algorithm with h(n) to obtain a heuristic vehicle path planning method.

[0074] Example 2: Refer to Figures 2 to 6 , to illustrate the effect of the present invention, the open dataset of Xuancheng, Anhui is used to provide bayonet point data, signal machine point data, road section travel time, and intersection lane traffic flow data for the experiment. In this experiment, the traffic road network formed by Zhongshan Road, Zhuangyuan Road, Lingxi Road, Jincheng Road, and Diezhang Road is combined with the heuristic vehicle path planning algorithm to verify the optimization of the urban area road network. The figure includes 6 intersections, namely HK-101, HK-103, HK-104, HK-96, HK-95, HK-94. In this embodiment, the intersection is also called a bayonet.

[0075] This experiment uses real data to compare with the micro-traffic simulation results of three groups. The micro-traffic simulation results of the three groups are from the following three methods.

[0076] Method 1: They are the original micro-traffic simulation results, in English as Original Simulation, abbreviated as OrS.

[0077] Method 2: The micro-traffic simulation results optimized by digital twin technology, in English as Optimized Simulation, abbreviated as OpS.

[0078] Method 3: The method of the present invention, which is the optimized micro-traffic simulation results combined with the heuristic vehicle path planning algorithm, in English as Heuristic Simulation, abbreviated as HS.

[0079] For Figure 2 The traffic flow statistics results of the short-term traffic simulation for 30 minutes of the urban area shown are as Figure 3As shown, the initial OD matrix is used in OpS to monitor the traffic flow data of six checkpoints in the simulated road network. Real Data is the real data, showing the real traffic flow data of six checkpoints in Xuancheng, Anhui at 8:30. By comparing the traffic flow data of checkpoints in Real Data, OrS, and OpS, it shows that the authenticity of the microscopic traffic simulation engine optimized using digital twin technology has been significantly improved. At the same time, the default simulation path planning algorithm can more accurately describe the real traffic flow under the simulated road network.

[0080] For Figure 2 The results of a 60-minute long-term traffic simulation for the urban area shown are as Figure 4 shown. The predicted OD matrix is used in OpS. It can be seen that whether it is short-term or long-term traffic simulation, the data difference between OpS and Real Data is not significant. After using HS, the traffic flow of all six checkpoints has decreased, indicating that the total number of vehicles in the simulated road network has decreased. HS can better plan the driving paths of vehicles compared to OpS. At the same moment of simulation, it can make vehicles leave the simulated road network of the urban area faster.

[0081] For Figure 2 The results of the checkpoint congestion coefficient for a 30-minute short-term traffic simulation of the area shown are as Figure 5 shown. By comparing the congestion coefficients of Real Data and OrS, it can be seen that serious congestion occurs in the OrS simulation process after 30 minutes, and the congestion coefficients of all six checkpoints are very high. While Real Data shows that only HK-101 and HK-104 are significantly congested. It can be seen that when using the original simulation engine for traffic simulation, the authenticity of the simulation is lacking. After using OpS for simulation, the congestion coefficient of OpS is close to that of Real Data, indicating that the authenticity of OpS for simulating the urban area has been significantly improved. From the HS simulation results, it can be seen that compared with Real Data, except that the congestion coefficient of the HK-104 checkpoint does not decrease significantly, the congestion coefficients of the other five checkpoints have decreased significantly.

[0082] For Figure 2 The results of the checkpoint congestion coefficient for a 60-minute short-term traffic simulation of the area shown are as Figure 6 shown. It can be seen that in the HS simulation results, the congestion coefficients of all six checkpoints have decreased significantly. The decrease in the intersection congestion coefficient indirectly indicates the decrease in the road congestion coefficient. For the urban area road network, the total number of vehicles in the road network has decreased, and the overall road network has been optimized. The heuristic vehicle path planning algorithm can effectively improve the overall efficiency of the urban area road network by planning paths for vehicles, and the planned driving paths can provide effective reference and strong support for the trips of real vehicles.

[0083] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A heuristic vehicle path planning method applied to a microscopic traffic simulation engine, applied to a road network traffic simulation, wherein the road network includes a plurality of roads and a plurality of intersections, characterized in that: The steps include: S1, constructing a road network road weight model to generate a road congestion index for each road and an intersection congestion index for each intersection, and presetting a road congestion index threshold ThR and an intersection congestion index threshold ThC; Construct a road congestion index array and an intersection congestion index array, wherein the road congestion index array is composed of the road congestion indexes of all roads, and the intersection congestion index array is composed of the congestion indexes of all intersections in the road network; S2, generating vehicles in the road network, planning the initial path for the vehicles according to the starting point and the end point, and presetting the simulation step length; S3, the vehicle travels along the initial path, and performs dynamic path planning every time the time reaches a simulation step. The dynamic path planning in the t-th simulation step includes steps S31 to S36; S31, obtaining the current position of the vehicle, the road congestion index array at the current moment, the intersection congestion index array and the OD matrix; S32, determining whether the current OD matrix has changed compared to the OD matrix in the t-1th dynamic path planning, and if so, replanning the path to generate the tth simulation path, and taking the next intersection of the current position as the relevant intersection, and all roads from the current position to the end point as the relevant roads; S33, comparing the intersection congestion index of the relevant intersection in the t-th simulation path and the t-1th simulation path to see if it has changed, if so, proceeding to step S34, otherwise, taking the t-1th simulation path as the t-th simulation path; S34, determining whether the intersection congestion index of the relevant intersection exceeds the intersection congestion index threshold ThC, if so, proceeding to step S35, otherwise, taking the t-1th simulation path as the tth simulation path; S35, determining whether the road congestion index of the relevant roads has changed, if at least one relevant road has changed, proceeding to step S36, otherwise, taking the t-1th simulation path as the tth simulation path; S36, determining whether the road congestion index of the relevant road exceeds the road congestion index threshold ThR; If at least one relevant road exceeds, the path is replanned, otherwise the t-1th simulation path is used as the tth simulation path.

2. The heuristic vehicle path planning method applied to a microscopic traffic simulation engine according to claim 1, characterized in that: In S1, each road and each intersection in the road network is labeled, where the road congestion index of the i-th road is , intersection congestion index of the jth intersection According to the following formula: ， In the formula, The actual travel time, is the free flow time; For the the length of the road; For the Real-time traffic speed of roads, is the free flow speed; ， The j-th intersection corresponds to n entrance roads, and the k-th entrance road is , the actual road speed is , 1≤k≤n.

3. The heuristic vehicle path planning method applied to a microscopic traffic simulation engine according to claim 1, characterized in that: In S32 and S36, a heuristic vehicle path planning method is used to replan the path, and the heuristic vehicle path planning method includes the following steps; a1, select the A-star algorithm, the heuristic function of the A-star algorithm is h(n); a2, construct a mixed heuristic function ; ， In the formula, , is the x-axis coordinate and y-axis coordinate of the current node, , is the x-axis coordinate and y-axis coordinate of the parent node of the current node. , are the x-axis and y-axis coordinates of the end point, T is the distance from the starting point to the end point, is the road congestion index of the next road at the current location in the t-1th simulation path, is the intersection congestion index of the next intersection of the current position in the t-1th simulation path; a3, using a mixed heuristic function Replace the heuristic function in the A-star algorithm with h(n) to obtain a heuristic vehicle path planning method.

Images