Path planning methods, devices and electronic equipment

By introducing time windows and state prediction into route planning, the problems of existing technologies being unable to predict future traffic conditions and distinguish differences in vehicle arrival times are solved, thereby improving the accuracy of route planning and user experience.

CN123065489APending Publication Date: 2026-11-10CHINA UNICOM SMART CONNECTION TECH LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610953748.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-29
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing technologies lack the ability to predict future traffic conditions and distinguish the time differences in vehicle arrival at the same road segment, resulting in low accuracy in vehicle route planning and a tendency to cause traffic congestion.

Method used

By introducing the concept of time windows into path planning, the target node is determined from multiple candidate nodes based on the target vehicle's time windows on multiple candidate roads and the expected travel time. Combined with the vehicle's state prediction in the future time period, the time difference of the vehicle's arrival at the candidate node is distinguished to generate the target planned path.

Benefits of technology

It improves the accuracy of route planning, reduces the likelihood of traffic congestion, and enhances the user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123065489A_ABST
    Figure CN123065489A_ABST
Patent Text Reader

Abstract

This invention provides a path planning method, apparatus, and electronic device, belonging to the field of artificial intelligence technology. The method includes: determining a target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on multiple candidate roads to the destination; designating the target node as a new historical target node, and continuing to execute the step of determining a new target node based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on multiple candidate roads to the destination; and, if the next node of the new target node is the destination, generating a target planned path for the target vehicle based on the starting point, the destination, and the determined multiple target nodes. Embodiments of this invention can improve the accuracy of generating target planned paths and reduce the possibility of traffic congestion.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a path planning method, apparatus, and electronic device. Background Technology

[0002] In current practical applications of traffic systems, navigation systems or traffic centers acquire real-time traffic flow data of the road network through devices such as floating cars and detectors. Based on this data, they plan routes for all vehicles in the network. However, because all vehicles are independently planned based on the same "current best" road condition information, this "memory" leads to a large number of vehicles being simultaneously guided onto at least a few seemingly unobstructed roads. This influx quickly overloads these roads, creating new congestion points. Furthermore, the technology cannot distinguish the time differences between different vehicles arriving at the same road segment. When this situation is treated as simultaneous entry, the system may allow following vehicles to detour to avoid congestion; or, if there is genuine congestion, the system may allow all vehicles to enter. This significantly reduces the accuracy of route planning for vehicles and degrades the user experience.

[0003] Therefore, a solution to the aforementioned technical problems is urgently needed. Summary of the Invention

[0004] To address this, the present invention provides a route planning method to solve the problem of low accuracy in vehicle route planning in the prior art due to the lack of prediction of future traffic conditions and the inability to distinguish the time differences in vehicle arrival at the same road segment.

[0005] To achieve the above objectives, a first aspect of the present invention provides a path planning method, the method comprising: determining a target node among multiple candidate nodes based on the time windows of a target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination, wherein the path of the target vehicle from the starting point to the multiple candidate nodes includes at least one planned historical target node; determining the target node as a new historical target node, and continuing to execute the step of determining a new target node based on the time windows of the target vehicle on the multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination; and, if the next node of the new target node is the destination, generating a target planned path for the target vehicle based on the starting point, the destination, and the determined multiple target nodes.

[0006] Optionally, determining the target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination includes: for each candidate road, determining the dynamic weight of the target vehicle traveling on the candidate road based on the set of time windows corresponding to the estimated arrival time of the target vehicle from the starting point to the candidate road; determining the path cost of the candidate node based on the dynamic weight of the candidate road, the dynamic weight of the historical target road corresponding to the at least one historical target node, and the estimated travel time of the target vehicle from the candidate node on the candidate road to the destination; and determining the target node from the multiple candidate nodes based on the path costs of the multiple candidate nodes.

[0007] Optionally, the dynamic weight of the target vehicle traveling on the candidate road is determined based on the set of time windows corresponding to the estimated arrival time of the target vehicle from the starting point to the candidate road. This includes: for each time window in the set of time windows, determining the road load cost of the candidate road within the time window based on the road carrying capacity of the candidate road within the time window; determining the dynamic weight of the candidate road within the time window based on the road length of the candidate road, the estimated travel time of the target vehicle traveling on the candidate road, and the road load cost; and determining the dynamic weight of the candidate road based on the dynamic weight of the candidate road within each time window.

[0008] Optionally, determining the road load cost of the candidate road within the time window based on the road carrying capacity of the candidate road within the time window includes: determining the ratio between the road carrying capacity of the candidate road within the time window and the road infrastructure capacity of the candidate road; and determining the road load cost of the candidate road within the time window based on the ratio.

[0009] Optionally, the method further includes: when the road load cost exceeds a preset load threshold, selecting some vehicles among the multiple vehicles in the target area where the target vehicle is located for route replanning, and generating new target planning routes for the selected vehicles.

[0010] Optionally, the method further includes: updating the road carrying capacity within each time window based on a capacity deduction factor, when generating the target planned path.

[0011] Optionally, the method further includes: for each candidate road, determining the estimated arrival time of the target vehicle from the starting point to the candidate road based on the estimated travel time of the target vehicle on the historical target road corresponding to each historical target node; determining the estimated departure time of the target vehicle from the candidate road based on the estimated arrival time and the estimated travel time of the target vehicle on the candidate road; and determining the time window of the target vehicle on the candidate road based on the estimated arrival time and the estimated departure time.

[0012] Optionally, determining the time window of the target vehicle on the candidate road based on the estimated arrival time and the estimated departure time includes: determining the time interval of the target vehicle's occupation of the candidate road based on the estimated arrival time and the estimated departure time; and determining the time window of the target vehicle on the candidate road as the time window of the target vehicle in the preset time window sequence that overlaps with the time interval of occupation.

[0013] Secondly, the present invention provides a path planning apparatus, comprising: a node determination module configured to determine a target node from multiple candidate nodes based on time windows of a target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination, wherein the path of the target vehicle from the starting point to the multiple candidate nodes includes at least one planned historical target node; to determine the target node as a new historical target node, and to continue executing the step of determining a new target node based on time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination; and a path generation module configured to generate a target planned path for the target vehicle based on the starting point, the destination, and the determined multiple target nodes, when the next node of the new target node is the destination.

[0014] Thirdly, the present invention provides an electronic device comprising: one or more processors; a memory storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the path planning method described above; and one or more I / O interfaces connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the path planning method described above.

[0016] The present invention has the following advantages:

[0017] For the target vehicle, a target node is determined from multiple candidate nodes based on the target vehicle's time windows on multiple candidate roads and the estimated travel time from each candidate node to the destination. Since the determination of the target node incorporates the target vehicle's time windows on multiple candidate roads—that is, the predicted state of the target vehicle traveling to candidate roads in the future time period—and uses time windows to determine the time differences in the vehicle's arrival at candidate nodes, the accuracy of target node determination is improved. Using the same method, multiple target nodes are determined during the target vehicle's journey. After determining these multiple target nodes, a target planning path for the target vehicle is generated based on the origin, destination, and multiple target nodes, further improving the accuracy of the generated target planning path, reducing the possibility of traffic congestion, and improving the user experience.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the detailed description of exemplary embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 A flowchart of a path planning method provided in an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of path planning provided in an embodiment of the present invention;

[0022] Figure 3 A flowchart illustrating a path planning method provided in an embodiment of the present invention;

[0023] Figure 4 A block diagram of a path planning device provided in an embodiment of the present invention;

[0024] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0026] As used in this invention, the term "and / or" includes any and all combinations of one or more of the associated enumerated entries.

[0027] The terminology used in this invention is for describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms "a" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0028] When the terms “comprising” and / or “made of” are used in this invention, the presence of the said feature, integral, step, operation, element and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or groups thereof is not excluded.

[0029] Unless otherwise specified, all terms used in this invention (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined by the invention.

[0030] In current practical applications of traffic systems, navigation systems or traffic centers acquire real-time traffic flow data (such as average speed and travel time) from road networks using floating cars, detectors, and other devices. The system processes this data to create weights reflecting the current road conditions (e.g., using travel time as edge weights). When a user initiates a route request, the system calculates an "optimal" route (usually the fastest or shortest path) based on the current road network weights using shortest path algorithms such as Dijkstra's or A*. The core of this approach is rapid response to the current state, aiming to find routes for individual vehicles that avoid current congestion. However, because all vehicles independently plan based on the same "current optimal" road condition information, it easily leads to a large number of vehicles being simultaneously guided onto at least a few currently seemingly unobstructed roads. This concentrated influx quickly overloads these roads, creating new congestion points, a phenomenon known as "congestion shifting." The root cause lies in the instantaneous and independent planning, lacking prediction of future traffic evolution and coordination between vehicles. Furthermore, related technologies cannot distinguish the time differences in vehicle arrival at the same road segment. For example, two vehicles might pass through the same road segment one after the other an hour later. In the current timeline's planning, they are considered to be occupying the road segment's resources "simultaneously." This could lead the algorithm to either allow the following vehicle to detour to avoid a "virtual conflict" or ignore a real conflict and allow both vehicles to enter. This stems from the model's lack of a time-dimensional distribution model of road capacity, making it unable to perform refined spatiotemporal resource reservation and conflict detection. In current practical applications, the system only assigns higher costs to subsequent vehicles in its planning after detecting a decrease in speed or an increase in travel time on a certain road. This response is lagging and cannot proactively divert and guide traffic before actual congestion occurs due to traffic flow convergence.

[0031] Based on this, embodiments of the present invention provide a path planning method, a path planning device, an electronic device, and a computer-readable storage medium, which are explained in detail in the following embodiments.

[0032] In a first aspect, embodiments of the present invention provide a path planning method.

[0033] See Figure 1 , Figure 1 A flowchart of a path planning method provided in an embodiment of the present invention is shown, the method specifically including the following steps:

[0034] Step 102: Based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from the candidate nodes of the multiple candidate roads to the destination, determine the target node among the multiple candidate nodes. The path of the target vehicle from the starting point to the multiple candidate nodes includes at least one planned historical target node.

[0035] Step 104: Determine the target node as a new historical target node, and continue to execute the step of determining the target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from the candidate nodes of the multiple candidate roads to the destination, and determine the new target node.

[0036] Step 106: If the next node after the new target node is the destination, generate the target planning path for the target vehicle based on the starting point, the destination, and the determined multiple target nodes.

[0037] In this context, "target vehicle" refers to any vehicle in a real traffic scenario that requires route planning. "Start point" refers to the starting point of the target vehicle, which can be a geographical location or a road, depending on the specific application. "End point" refers to the destination of the target vehicle, which can also be a geographical location or a road, depending on the specific application. "Candidate node" refers to the next node to be determined on the planned path from the start point to the end point. The planned path refers to a portion of the path already planned for the target vehicle starting from the start point, including at least one historical target node. Historical target nodes are the target nodes that constitute the planned path. For example, if the planned path of the target vehicle is: start point - node 1 - node 2 - node 3, then the next node after node 3 needs to be determined among nodes 4, 5, and 6. Nodes 4, 5, and 6 are all candidate nodes. In this embodiment, the node mentioned refers to the endpoint of a road, specifically the end point of the road in the direction of vehicle travel. "Estimated travel time" refers to the predicted time it will take for the target vehicle to travel on a certain road. A time window refers to multiple discrete time windows pre-divided within the system's planned time range. For example, if the system's planned time range is [0, T], it can be divided into multiple discrete time windows as T = {t1, t2, ..., t...}. k},in, , This indicates the length of the time window. The target node is the next node on the planned path, determined from multiple candidate nodes.

[0038] Specifically, for each of the multiple candidate roads, a target node is determined from among the candidate nodes based on the target vehicle's time window on the candidate road and the estimated travel time from its corresponding candidate node to its destination. This target node, together with the planned path, constitutes a new planned path. After determining the target node, the same method is used to determine the next node from among the multiple candidate nodes of that target node, i.e., to determine a new target node. This process is repeated to determine multiple target nodes. When the next node of the most recently determined target node is the destination of the target vehicle, it indicates that the most recently determined target node is the last target node. At this point, based on the target vehicle's start point, destination, and the determined multiple target nodes, a target planned path for the target vehicle is generated.

[0039] In this embodiment of the invention, for any vehicle in a traffic scenario, i.e., the target vehicle, a target node is determined from multiple candidate nodes based on the target vehicle's time windows on multiple candidate roads and the estimated travel time from each candidate node to the destination. Because the determination of the target node incorporates the target vehicle's time windows on multiple candidate roads—that is, it incorporates the predicted state of the target vehicle traveling to candidate roads in the future time period—and determines the time difference of the vehicle's arrival at the candidate nodes through the time windows, the accuracy of target node determination is improved. Based on the same method, multiple target nodes are determined during the target vehicle's journey. After determining multiple target nodes, a target planning path for the target vehicle is generated based on the starting point, destination, and multiple target nodes, further improving the accuracy of the generated target planning path, reducing the possibility of traffic congestion, and improving the user experience.

[0040] The path planning method provided by the embodiments of the present invention will be explained in detail below.

[0041] Since determining the time window for the target vehicle to travel on each road is the basis for determining the target node among multiple candidate nodes, before determining the target node among multiple candidate nodes based on the time window of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from multiple candidate nodes to the destination, the time window corresponding to the target vehicle's travel on the candidate road can be determined based on the estimated arrival time of the target vehicle from the starting point to the candidate road and the estimated departure time of the target vehicle through the candidate road.

[0042] In a specific embodiment of the present invention, the time window of a target vehicle on a candidate road can be determined according to the following method: for each candidate road, the estimated arrival time of the target vehicle from the starting point to the candidate road is determined based on the estimated travel time of the target vehicle on the historical target road corresponding to each historical target node; the estimated departure time of the target vehicle from the candidate road is determined based on the estimated arrival time and the estimated travel time of the target vehicle on the candidate road; and the time window of the target vehicle on the candidate road is determined based on the estimated arrival time and the estimated departure time.

[0043] Here, "historical target road" refers to the road corresponding to the historical target node. "Estimated departure time" refers to the predicted time required for a target vehicle to leave a certain road. "Estimated arrival time" refers to the predicted time required for a target vehicle to arrive at a certain road.

[0044] Specifically, for each candidate road, the estimated arrival time of the target vehicle from the starting point to the candidate road is determined based on the estimated travel time of the target vehicle through the historical target roads corresponding to each historical target node. That is, before the target vehicle travels from the starting point to the candidate road, it needs to sequentially travel through the historical target roads between multiple historical target nodes according to the planned route. Therefore, the sum of the estimated travel times of the target vehicle through multiple historical target roads is the estimated arrival time of the target vehicle from the starting point to the candidate road. See Formula 1 below for details:

[0045] Formula 1

[0046] in, For vehicles Road to reach The estimated arrival time For vehicles accessible road The estimated travel time, For the planned route The first road There are 1 roads, 1≤ ≤ .

[0047] For roads Determine the target vehicle from the road To the road The sum of the estimated travel times, that is, the travel time of the target vehicle from the starting point to the road. The total estimated travel time is the time it takes for the target vehicle to reach the road. The estimated arrival time.

[0048] Furthermore, since the vehicle speed in the actual traffic environment will change dynamically with the change of road load, in this embodiment of the invention, the estimated travel time of a vehicle on each road can be determined by the average actual speed of the vehicle on the road. The estimated travel time can be determined according to the following formula 2.

[0049] Formula 2

[0050] in, Roads for vehicle passage The estimated travel time, For roads The length of the road, For vehicles on the road The average actual vehicle speed on the road, where i and j are the average speeds on the road. The identifiers of two road nodes, a road node can be represented as and In practical applications, the estimated travel time of a vehicle on a road can be determined by the road length and the vehicle's average actual speed on that road. In other words, the ratio of road length to the vehicle's average actual speed on the road is used to determine the estimated travel time of the vehicle on the road.

[0051] Furthermore, in real-world traffic environments, each road has its corresponding speed limit to prevent vehicles from traveling too fast. Based on this, in this embodiment of the invention, the free-flowing time of a vehicle on the road can also be determined, and the estimated travel time of the vehicle on the road can be determined based on the free-flowing time. The free-flowing time can be determined according to the following formula 3.

[0052] Formula 3

[0053] in, Roads for vehicle passage The duration of free circulation, For roads The road speed limit is determined by the ratio of the road length to the road speed limit. The free-flow time for vehicles is then calculated. As mentioned above, in actual traffic environments, vehicle speeds dynamically change with road load conditions. Therefore, in this embodiment of the invention, the estimated travel time is preferably determined using the calculation method in Formula 2.

[0054] This invention determines the estimated travel time of a vehicle on a road based on the road length and the vehicle's speed on the road. Specifically, it is determined based on the vehicle's average actual speed and the road speed limit. Determining the estimated travel time based on the vehicle's average actual speed makes the estimated travel time more consistent with the actual traffic environment, while determining the estimated travel time based on the road speed limit reduces the amount of calculation required to determine the estimated travel time and improves calculation efficiency.

[0055] In this embodiment of the invention, a road topology network in the city is pre-constructed, represented as follows: The road topology network can be constructed for a specific area within a city, depending on the actual application. Represents the set of road nodes; This represents a set of roads. Each road... Represents a node With nodes The accessible roads between them. Each road corresponds to a set of road attribute parameters, which can be represented as follows: .in, Indicates road The length of the road; Indicates road The number of lanes; Indicates road Speed ​​limits on roads; Indicates road Real-time traffic flow on roads; Indicates road Road traffic density; Indicates road The basic capacity of a road is, specifically, the theoretical maximum number of vehicles that a road can carry before it becomes congested under ideal conditions. Indicates road The duration of free circulation.

[0056] In practical applications, These are all fixed values, determined based on actual application conditions. The following continues with further details... The determination of [the specific details] will be explained.

[0057] In this embodiment of the invention, the road traffic density can be determined according to the following formula 4.

[0058] Formula 4

[0059] in, For roads The formula for calculating the road space occupied by all vehicles is as follows:

[0060] Formula 5

[0061] in, For roads The number of vehicles on board and These are vehicle length and safe driving distance, respectively, both of which are fixed values. Indicates road The effective passage space. Specifically, the road traffic density can be calculated using formulas 4 and 5 above.

[0062] Real-time traffic flow on roads can be determined using the following formula 6.

[0063] Formula 6

[0064] In other words, the real-time traffic flow is determined by multiplying the road traffic density by the average actual speed of vehicles on the road.

[0065] Furthermore, as mentioned above, in actual traffic environments, vehicle speeds vary with changes in road load conditions, which are related to road traffic density. Based on this, embodiments of the present invention determine the average actual vehicle speed on the road according to road traffic density.

[0066] Formula 7

[0067] in, The maximum traffic density of a road refers to the threshold of space occupancy when a road is in a state of extreme congestion. Its value can be preset according to the road type, and the preferred value is 0.85 to 1.0. This is the traffic density sensitivity coefficient. As road traffic density gradually approaches its maximum, the average road speed gradually decreases.

[0068] This invention determines the average actual vehicle speed on the road based on the road traffic density in the actual traffic environment, and realizes dynamic prediction of the average actual vehicle speed based on the road load status. Therefore, when determining the expected travel time based on the road length and the average actual vehicle speed, the accuracy of the result is improved, and it is more in line with the vehicle's operating status in the actual traffic environment.

[0069] Furthermore, the road infrastructure capacity can be determined according to the following formula 8.

[0070] Formula 8

[0071] in, For the theoretical maximum capacity of the road, For the road stability coefficient, This indicates the capacity ratio when the road maintains a stable traffic flow.

[0072] In practical applications, a road may include multiple lanes, and each lane will carry a different number of vehicles. Therefore, in this embodiment of the invention, the number of vehicles that can be accommodated in each lane is determined based on the road length and vehicle length, and then the total number of vehicles that the entire road can accommodate is determined by combining the number of lanes, which is the theoretical maximum capacity of the road.

[0073] Formula 9

[0074] Since a large number of vehicles need to maintain a safe driving distance when driving on the road, the embodiments of the present invention can further consider the safe driving distance of vehicles when determining the number of vehicles that can be accommodated on each vehicle based on the road length and vehicle length, i.e., the above formula 9.

[0075] This invention utilizes a constructed road topology network and corresponding road attribute parameters to determine and update the real-time load status of each road. This enables subsequent route planning for vehicles based on the real-time load status of the roads, minimizing traffic congestion.

[0076] Following the above, after determining the estimated arrival time of the target vehicle from the starting point to the candidate road, the estimated departure time of the target vehicle from the candidate road is determined based on the estimated arrival time and the estimated travel time of the target vehicle through the candidate road. That is, the estimated arrival time of the target vehicle to the candidate road is added to the estimated travel time of the target vehicle through the candidate road to obtain the estimated departure time of the target vehicle from the candidate road. See Formula 10 below for details:

[0077] Formula 10

[0078] in, For vehicles drive off the road The estimated departure time, For vehicles accessible road The estimated travel time is determined. After determining the estimated arrival time of a vehicle to a candidate road and the estimated departure time of a vehicle from a candidate road, the time window for the vehicle on the candidate road is determined based on the estimated arrival time and the estimated departure time.

[0079] According to the road load status of vehicles in the actual traffic environment, this invention predicts the expected arrival time and expected departure time of vehicles on candidate roads, and further combines the pre-divided discrete time windows to determine the time window corresponding to the vehicle on the candidate road, so as to distinguish the time difference when different vehicles arrive at the same road.

[0080] In practical applications, the estimated arrival time of a vehicle on a candidate road and the estimated departure time from a candidate road can be used to determine the time interval during which the vehicle occupies the candidate road. This time interval can then be mapped to the corresponding time window set to determine the time window for the vehicle on the candidate road.

[0081] Based on this, in a specific embodiment provided by the present invention, determining the time window of the target vehicle on the candidate road according to the expected arrival time and the expected departure time includes: determining the time interval of the target vehicle's occupation of the candidate road based on the expected arrival time and the expected departure time; and determining the time window of the target vehicle on the candidate road as the time window of the target vehicle in the preset time window sequence that overlaps with the time interval of occupation.

[0082] The occupancy time interval refers to the time interval consisting of the estimated arrival time and the estimated departure time, used to characterize the range of time the target vehicle occupies on the candidate road. That is, For example, if the estimated arrival time is 30 minutes and the estimated departure time is 36 minutes, then the time interval is [30, 36].

[0083] In practical applications, the time window occupied by the target vehicle on the candidate road may be multiple. Therefore, this embodiment of the invention uses a set to represent the time window occupied by the target vehicle on the candidate road; that is, the set of time windows occupied by the target vehicle on the candidate road is represented as... For details, please refer to Formula 11 below.

[0084] Formula 11

[0085] The meaning of Formula 11 above is: vehicle On the road The set of time windows occupied above consists of all time windows that satisfy the condition "the k-th time window". and vehicles On the road The time window number k is composed of the actual occupancy time intervals that overlap. In other words, after determining the occupancy time intervals of the target vehicle on the candidate road, the system determines whether there is an overlap between the occupancy time intervals and the time window sequence according to the preset time window sequence. If there is an overlap, the time window with the overlap is determined as the time window for the target vehicle to occupy the candidate road.

[0086] Continuing with the previous example, we convert the time intervals during which a vehicle occupies the road into corresponding time periods. For example, a vehicle... On the road The time slot occupied is [9:02, 9:08], and the system's preset time window is divided into 5-minute intervals: Corresponding to 9:00~9:05 The corresponding times are 9:05 to 9:10, so both of these time windows are related to the vehicle. On the road The time periods occupied overlap, resulting in a set of time windows including and These two time windows.

[0087] This invention constructs a time interval for vehicle occupancy on candidate roads based on the estimated arrival and departure times of vehicles. Furthermore, it combines this with a pre-defined time window sequence to determine the set of time windows from which the target vehicle occupies the candidate roads. Thus, the road's future capacity is discretized into continuous time windows for modeling, transforming road capacity from a static spatial resource into a dynamic spatiotemporal two-dimensional resource, enabling refined management of spatiotemporal resources.

[0088] Furthermore, after determining the time window occupied by the target vehicle on the candidate road, dynamic path planning is performed on the target vehicle based on the time window and the estimated travel time of the target vehicle from the candidate node of the candidate road to the destination, that is, the next target node of the planned path of the target vehicle is determined in sequence.

[0089] In a specific embodiment of the present invention, determining a target node among multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination includes: for each candidate road, determining the dynamic weight of the target vehicle traveling on the candidate road based on the set of time windows corresponding to the estimated arrival time of the target vehicle from the starting point to the candidate road; determining the path cost of the candidate node based on the dynamic weight of the candidate road, the dynamic weight of the historical target road corresponding to at least one historical target node, and the estimated travel time of the target vehicle from the candidate node on the candidate road to the destination; and determining the target node among the multiple candidate nodes based on the path costs of the multiple candidate nodes.

[0090] Dynamic weights refer to road weights that change dynamically based on road capacity within different time windows. They can be used to characterize road congestion and avoid traffic congestion caused by homogenized road planning. Each time window corresponds to a road capacity, which characterizes the number of vehicles each road can accommodate within that window. Path cost refers to the accumulated path cost incurred by a target vehicle traveling from its starting point to its destination based on a planned route and candidate nodes.

[0091] Specifically, for each candidate road, a set of time windows is defined based on the estimated arrival time of the target vehicle from the starting point to the candidate road, which is the time window set determined by the method described above. In practical applications, since the determined time window set is based on the time interval occupied by the target vehicle on the candidate road, and the time interval is composed of the estimated arrival time of the target vehicle to the candidate road and the estimated departure time of the target vehicle from the candidate road, and the time window set is obtained by mapping the time interval to the time window sequence, that is, there is a mapping relationship between the time interval and the time window set. Therefore, given the estimated arrival time or estimated departure time of the target vehicle, the set of time windows occupied by the target vehicle on the candidate road can be queried based on the estimated arrival time or estimated departure time of the target vehicle.

[0092] Therefore, after determining the estimated arrival time of the target vehicle to the candidate road, the set of time windows occupied by the target vehicle on the candidate road can be queried based on the estimated arrival time, or based on the estimated departure time. Based on the set of time windows occupied by the target vehicle on the candidate road, the dynamic weight of the candidate road for the target vehicle is determined. Using the same method as above for determining the estimated travel time of the target vehicle on the candidate road, the estimated travel time of the target vehicle from the candidate node to the destination is determined. Then, based on the determined dynamic weights of the candidate roads, the dynamic weights of each historical target road in the planned path, and the estimated travel time of the target vehicle from the candidate node to the destination, the path cost of the candidate node is determined. Finally, by comparing the path costs of all candidate nodes, the candidate node with the lowest path cost is selected as the target node.

[0093] Furthermore, the method for calculating the path cost of candidate nodes can be found in Formula 12 below.

[0094] Formula 12

[0095] in, Candidate nodes Path cost, The target vehicle travels from the starting point to the candidate node. The sum of dynamic weights, For the target vehicle, candidate nodes The estimated travel time to the destination, i.e., the time taken by the candidate nodes. The sum of the estimated travel time for each road between the destination and the destination.

[0096] In this embodiment of the invention, an improved A* path planning algorithm or a time-dependent shortest path (TDSP) algorithm is used for path planning. In the time-dependent shortest path algorithm, the determined dynamic weights can be used as input to the time-dependent edge weight function before solving. In this embodiment of the invention, the improved A* path planning algorithm is preferred for path planning.

[0097] See Figure 2 , Figure 2 A path planning diagram provided for an embodiment of the present invention, such as Figure 2 As shown, nodes 1 and 2 are the next candidate nodes to be determined for the target vehicle starting from the origin. As described above, the estimated arrival time of the target vehicle from the origin to nodes 1 and 2 is determined (this is just an example of the estimated arrival time; it could also be the estimated departure time). Based on the estimated arrival time of node 1, the time window set occupied by the target vehicle on road 1 (i.e., the passable road between the origin and node 1) corresponding to node 1 is queried. Based on the time window set occupied by the target vehicle on road 1, the dynamic weight of road 1 for the target vehicle and the estimated travel time of the target vehicle from node 1 to the destination are determined. Then, based on the determined dynamic weight of road 1 and the estimated travel time of the target vehicle from node 1 to the destination, the path cost of node 1 is determined. The path cost of node 2 is determined using the same method. The node with the smaller path cost is determined as the target node; that is, node 1 is designated as the target node. Figure 2 (Using node 1 as the target node as an example for illustration). Furthermore, based on the same method as above, the subsequent target nodes of node 1 are determined, namely... Figure 2 The diagram shows nodes 3, 4, 5, and 6. Since the next node after node 6 is the destination of the target vehicle, node 6 is the last target node to be determined. This completes the path planning for the target vehicle. The target vehicle's planned path is: Start - Node 1 - Node 3 - Node 4 - Node 5 - Node 6 - Destination.

[0098] This invention determines the path cost of candidate nodes by determining the dynamic weight of the road carrying capacity of a road in different time windows. Since the road carrying capacity in the corresponding time window is different when a vehicle arrives at the same road at different times, the path cost of different vehicles is different even if they pass through the same road, thus realizing the temporal dynamism in path planning.

[0099] The following section will further explain the specific method for determining the dynamic weights of candidate roads.

[0100] In a specific embodiment of the present invention, determining the dynamic weight of the target vehicle traveling on the candidate road based on the set of time windows corresponding to the estimated arrival time of the target vehicle traveling from the starting point to the candidate road includes: for each time window in the set of time windows, determining the road load cost of the candidate road within the time window based on the road carrying capacity of the candidate road within the time window; determining the dynamic weight of the candidate road within the time window based on the road length of the candidate road, the estimated travel time of the target vehicle traveling on the candidate road, and the road load cost; and determining the dynamic weight of the candidate road based on the dynamic weight of the candidate road within each time window.

[0101] In practical applications, each road corresponds to a carrying capacity sequence, that is... ,in, Indicates road In the time window The remaining number of vehicles that the road can accommodate, i.e., the road's carrying capacity. During system initialization, This indicates that each time window has an initial road carrying capacity. After completing route planning for vehicles, the system updates the road carrying capacity within the corresponding time window. Therefore, for each time window, the road carrying capacity within different time windows can be obtained.

[0102] Specifically, for each time window, the road load cost of the candidate road within the time window is determined based on its road carrying capacity, in order to assess the road load risk of the candidate road within the time window. Furthermore, the dynamic weight of the candidate road within the time window is determined based on its length, the estimated travel time of target vehicles traversing the candidate road, and the road load cost.

[0103] Formula 13

[0104] in, For the target vehicle within the time window Dynamic weights, For roads The road distance cost, specifically the road The length of the road, Roads for target vehicles The estimated travel time also represents the cost of the estimated travel time for roads. For roads In the time window The road load cost, , , All are weighted parameters, satisfying . , , The specific value can be a fixed value or an adaptively adjusted value, and can be preset based on actual experience. This invention does not limit the value.

[0105] Since candidate roads may occupy multiple time windows, the dynamic weights of candidate roads within each time window are determined, and these weights are summed to obtain the dynamic weights of candidate roads.

[0106] This invention incorporates road load cost into the dynamic weight calculation of roads, so that the dynamic weight includes road load cost, thereby guiding path planning based on road load cost and reducing the possibility of high congestion rate on the planned path.

[0107] In one specific embodiment of the present invention, determining the road load cost of the candidate road within the time window based on the road carrying capacity of the candidate road within the time window includes: determining the ratio between the road carrying capacity of the candidate road within the time window and the road infrastructure capacity of the candidate road; and determining the road load cost of the candidate road within the time window based on the ratio.

[0108] Specifically, for each time window, the ratio between the road carrying capacity and the road infrastructure capacity of the candidate road within the time window is determined, and the road load cost of the candidate road within the time window is determined based on this ratio. Specifically, the ratio can be subtracted from 1, and the resulting difference is determined as the road load cost.

[0109] Formula 14

[0110] In addition to the above implementation methods, nonlinear functions, such as exponential functions, can also be used to determine road load costs.

[0111] This invention determines the road load cost within a given time window based on the road's carrying capacity and basic infrastructure capacity. As the road's carrying capacity gradually decreases in future time windows, the road load cost increases, leading to a rise in the road's dynamic weight. Consequently, vehicles will proactively avoid potentially congested roads during route planning, preventing traffic congestion caused by homogenized planning.

[0112] To further improve overall traffic control capabilities and prevent localized traffic congestion caused by a large number of vehicles concentrating on the same road within a future time window, this invention introduces a dynamic replanning mechanism after route planning is completed. The system periodically detects the road load status in future time windows at fixed time intervals and adjusts the routes of some vehicles in advance based on future road load change trends.

[0113] Based on this, in a specific embodiment provided by the present invention, the method further includes: when the road load cost exceeds a preset load threshold, selecting some vehicles among multiple vehicles in the target area where the target vehicle is located for route replanning, and generating new target planning routes for the selected vehicles.

[0114] The preset load threshold refers to the upper limit of the road load cost set in advance. It is used to measure the road load status and to measure whether route replanning is needed for vehicles.

[0115] Specifically, the system continuously monitors the remaining carrying capacity of each road within future time windows and determines the corresponding road load cost. When the road load cost of a road exceeds a preset load threshold within a future time window, it indicates that the road may experience concentrated vehicle convergence in the future, posing a high risk of congestion. To reduce the probability of subsequent vehicles choosing this road, the dynamic weight of the road within the corresponding time window is set to a maximum value, giving it a higher path cost during path planning. A subset of vehicles passing through the road within that time window are selected for dynamic replanning, generating new target planning paths for these vehicles. Specifically, the system uses the vehicle's current position as the new path starting point, re-executes the improved A* path planning algorithm or the time-dependent shortest path algorithm, and recalculates the dynamic weights of the roads based on the updated future road load status, thereby generating new target planning paths.

[0116] Furthermore, in this embodiment of the invention, a certain proportion of vehicles in the vehicle set can be selected for route replanning, such as 20% or 30% of the vehicle set. The selection proportion can be determined according to the actual application situation. In addition, priority can also be given to selecting vehicles that are closest to the starting point of road sections with high congestion rates, vehicles with the longest remaining travel time, or vehicles with low time sensitivity for route replanning.

[0117] Furthermore, in addition to setting a preset load threshold, a comprehensive judgment can be made by combining the rate of decline in road carrying capacity within a future time window, or the overall risk of the sub-network composed of upstream and downstream road segments. The specific method for determining path replanning is determined according to the actual application situation, and this invention does not limit it here.

[0118] In this embodiment of the invention, the system does not wait for actual road congestion before implementing detours, but rather intervenes in future traffic flow in advance, thereby reducing the possibility of a continuous increase in local road load. As the system periodically performs dynamic replanning, traffic flow can be more evenly distributed throughout the road network, effectively reducing the problem of homogenized vehicle route planning and minimizing the phenomenon of concentrated load on local roads.

[0119] In practical applications, the number of vehicles on the roads involved in the target planned path will decrease each time a vehicle completes route planning. Therefore, after completing route planning for the target vehicle, that is, after generating the corresponding target planned path for the target vehicle, it is necessary to update the road carrying capacity within the corresponding time window to ensure the accuracy of route planning for other vehicles in the future.

[0120] Based on this, in a specific embodiment provided by the present invention, the method further includes: updating the road carrying capacity within each time window based on the capacity deduction factor when generating the target planning path.

[0121] Among them, the capacity deduction factor refers to the factor used to update the road carrying capacity.

[0122] Specifically, after completing the route planning for the target vehicle, the road carrying capacity within the corresponding time window is updated based on the capacity deduction factor, which is to subtract the capacity deduction factor from the road carrying capacity within the corresponding time window.

[0123] In practical applications, different capacity reduction factors can be preset according to vehicle type. For example, the capacity reduction factor for semi-trailers is "3", the capacity reduction factor for buses is "2", and the capacity reduction factor for cars is "1". A capacity reduction factor of "1" means that the road carrying capacity is updated according to "-1", which means that the number of vehicles on the road in the corresponding time window is reduced by one.

[0124] This invention enables the determination of a target node from multiple candidate roads based on the target vehicle's time windows on each candidate road and the estimated travel time from each candidate node to the destination. By incorporating the target vehicle's time windows on multiple candidate roads—that is, by combining the predicted state of the target vehicle traveling to candidate roads within a future time period—and determining the time differences in vehicle arrival at candidate nodes through these time windows, the accuracy of target node determination is improved. Using the same method, multiple target nodes are identified during the target vehicle's journey. After identifying these multiple target nodes, a target planning path for the target vehicle is generated based on the start point, destination, and multiple target nodes, further improving the accuracy of the generated target planning path and reducing the likelihood of traffic congestion. This proactive intervention in future traffic flow reduces the possibility of a sustained increase in local road load.

[0125] The following is in conjunction with the appendix Figure 3 The path planning method provided in the embodiments of the present invention will be further explained and described. Figure 3 A flowchart of a path planning method provided in an embodiment of the present invention is shown below. Figure 3As shown, this embodiment of the invention uses road topology network, real-time traffic data, and road attribute data (i.e., road attribute parameter set) as data inputs for modeling. It should be noted that this data modeling is pre-modeled and does not need to be executed every time path planning is performed. To describe the road capacity state at different future times, the future time range is discretized to construct a road time-series capacity model. The road time-series capacity model includes a pre-defined sequence of time windows and a sequence of carrying capacity for each road. Specifically, for each candidate road of the current target node, the expected arrival time of the target vehicle from the starting point to the candidate road is determined based on the expected travel time of the target vehicle on each historical target road corresponding to each historical target node; that is, the sum of the expected travel times of the target vehicle on multiple historical target roads. The set of time windows occupied by the target vehicle on the candidate roads is queried based on the expected arrival time. For each time window, the road load cost of the candidate road within the time window is determined based on the road carrying capacity of the candidate road within the time window to assess the road load risk of the candidate road within the time window. Furthermore, the road distance cost is determined based on the road length of the candidate roads, the estimated travel time cost is determined based on the estimated travel time of the target vehicle traversing the candidate roads, and the road load cost is determined based on the road carrying capacity and road infrastructure capacity. These costs are then weighted to determine the dynamic weight of the candidate roads within the time window. Further, the estimated travel time of the target vehicle from a candidate node on a candidate road to its destination is determined. Based on the determined dynamic weights of the candidate roads, the dynamic weights of each historical target road in the planned path, and the estimated travel time of the target vehicle from the candidate node to its destination, the path cost of the candidate node is determined. Then, the path costs of all candidate nodes are compared, and the candidate node with the lowest path cost is selected as the next target node. Using the same method, subsequent target nodes are determined until the next node of the target node is the destination of the target vehicle, thus completing the path planning for the target vehicle. Based on the target vehicle's starting point, destination, and the determined multiple target nodes, the target planned path for the target vehicle is generated.

[0126] After completing the route planning for the target vehicle, the road carrying capacity within the corresponding time window is updated based on the capacity deduction factor. Specifically, the road carrying capacity within the corresponding time window is subtracted from the capacity deduction factor.

[0127] Furthermore, the system continuously monitors the remaining carrying capacity of each road within future time windows and determines the corresponding road load cost. When it detects that the road load cost of a certain road exceeds a preset load threshold within a future time window, the system sets the dynamic weight of that road within the corresponding time window to the maximum value and selects a portion of vehicles from the set of vehicles passing through that road during that time window for dynamic replanning. Specifically, the system uses the current position of the vehicle as the new path starting point, re-executes the above path planning method, recalculates the dynamic weight of the road based on the updated future road load state, and thus generates a new target planning path.

[0128] This invention enables the determination of a target node from multiple candidate roads based on the target vehicle's time windows on each candidate road and the estimated travel time from each candidate node to the destination. By incorporating the target vehicle's time windows on multiple candidate roads—that is, by combining the predicted state of the target vehicle traveling to candidate roads within a future time period—and determining the time differences in vehicle arrival at candidate nodes through these time windows, the accuracy of target node determination is improved. Using the same method, multiple target nodes are identified during the target vehicle's journey. After identifying these multiple target nodes, a target planning path for the target vehicle is generated based on the start point, destination, and multiple target nodes, further improving the accuracy of the generated target planning path and reducing the likelihood of traffic congestion. This proactive intervention in future traffic flow reduces the possibility of a sustained increase in local road load.

[0129] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0130] Secondly, embodiments of the present invention provide a path planning device.

[0131] See Figure 4 , Figure 4 This is a block diagram of a path planning device provided in an embodiment of the present invention. The device includes:

[0132] The node determination module 402 is configured to determine a target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from each candidate node on the multiple candidate roads to the destination, wherein the path of the target vehicle from the starting point to each candidate node includes at least one planned historical target node; the target node is determined as a new historical target node, and the step of determining a target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from each candidate node on the multiple candidate roads to the destination is continued to be executed, thus determining a new target node;

[0133] The path generation module 404 is configured to generate a target planning path for the target vehicle based on the starting point, the ending point, and a plurality of determined target nodes, when the next node after the new target node is the destination.

[0134] Optionally, the node determination module 402 is further configured to:

[0135] For each candidate road, the dynamic weight of the target vehicle traveling on the candidate road is determined based on the set of time windows corresponding to the expected arrival time of the target vehicle from the starting point to the candidate road;

[0136] The path cost of the candidate node is determined based on the dynamic weight of the candidate road, the dynamic weight of the historical target road corresponding to the at least one historical target node, and the estimated travel time of the target vehicle from the candidate node of the candidate road to the destination.

[0137] The target node is determined from the plurality of candidate nodes based on the path cost of the plurality of candidate nodes.

[0138] Optionally, the node determination module 402 is further configured to:

[0139] For each time window in the set of time windows, the road load cost of the candidate road within the time window is determined based on the road carrying capacity of the candidate road within the time window.

[0140] The dynamic weight of the candidate road within the time window is determined based on the road length of the candidate road, the estimated travel time of the target vehicle on the candidate road, and the road load cost.

[0141] The dynamic weight of the candidate road is determined based on its dynamic weight within each time window.

[0142] Optionally, the node determination module 402 is further configured to:

[0143] Determine the ratio between the road carrying capacity of the candidate road and the road infrastructure capacity of the candidate road within the time window;

[0144] The road load cost of the candidate road within the time window is determined based on the ratio.

[0145] Optionally, the device further includes a replanning module configured to:

[0146] If the road load cost exceeds a preset load threshold, select some vehicles from among the multiple vehicles in the target area where the target vehicle is located for route replanning, and generate new target planned routes for the selected vehicles.

[0147] Optionally, the device further includes a capacity update module configured to:

[0148] When generating the target planning path, the road carrying capacity within each time window is updated based on the capacity deduction factor.

[0149] Optionally, the device further includes a window determination module configured to:

[0150] For each candidate road, the estimated arrival time of the target vehicle from the starting point to the candidate road is determined based on the estimated travel time of the target vehicle on the historical target road corresponding to each historical target node.

[0151] Based on the estimated arrival time and the estimated travel time of the target vehicle through the candidate road, the estimated departure time of the target vehicle from the candidate road is determined;

[0152] The time window for the target vehicle on the candidate road is determined based on the estimated arrival time and the estimated departure time.

[0153] Optionally, the window determination module is further configured to:

[0154] Based on the estimated arrival time and the estimated departure time, the time interval for the target vehicle to occupy the candidate road is determined;

[0155] The time windows in the preset time window sequence that overlap with the occupied time interval are determined as the time windows of the target vehicle on the candidate road.

[0156] The path planning apparatus provided by the present invention includes: a node determination module, configured to determine a target node from multiple candidate nodes based on the time windows of a target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination, wherein the path of the target vehicle from the starting point to the multiple candidate nodes includes at least one planned historical target node; determine the target node as a new historical target node, and continue to execute the step of determining a new target node based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on the multiple candidate roads to the destination; and a path generation module, configured to generate a target planned path for the target vehicle based on the starting point, the destination, and the determined multiple target nodes when the next node of the new target node is the destination.

[0157] This invention enables the determination of a target node from multiple candidate roads based on the target vehicle's time windows in multiple candidate roads and the estimated travel time from each candidate node to the destination. By incorporating the target vehicle's time windows in the candidate road selection process—that is, by combining the predicted state of the target vehicle traveling to the candidate roads within a future time period—and determining the time differences in vehicle arrival at candidate nodes through these time windows, the accuracy of target node determination is improved. Using the same method, multiple target nodes are determined during the target vehicle's journey. After determining these multiple target nodes, a target planning path for the target vehicle is generated based on the start point, destination, and multiple target nodes, further improving the accuracy of the generated target planning path and reducing the likelihood of traffic congestion.

[0158] The apparatus provided in the embodiments of the present invention has functions or includes modules that can be used to perform the methods described in the first aspect of the method embodiments above. The specific implementation and technical effects can be referred to the description of the method embodiments above. For the sake of brevity, they will not be repeated here.

[0159] It should be noted that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by this invention; however, this does not mean that other units are absent from this embodiment.

[0160] See Figure 5 This invention provides an electronic device comprising:

[0161] One or more processors 501;

[0162] The memory 502 stores one or more programs, which, when executed by one or more processors, enable the one or more processors to implement the path planning method described above.

[0163] One or more I / O interfaces 503 are connected between the processor and the memory and configured to enable information exchange between the processor and the memory.

[0164] Among them, processor 501 is a device with data processing capabilities, including but not limited to central processing unit (CPU); memory 502 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); I / O interface (read-write interface) 503 is connected between processor 501 and memory 502, and can realize information interaction between processor 501 and memory 502, including but not limited to data bus (Bus).

[0165] In some embodiments, the processor 501, memory 502, and I / O interface 503 are interconnected via a bus, and thus connected to other components of the computing device.

[0166] This embodiment also provides a computer-readable medium storing a computer program thereon. When the program is executed by a processor, it implements the path planning method provided in this embodiment. To avoid repetition, the specific steps of the path planning method will not be described again here.

[0167] This invention also provides a computer program product, including computer-readable code, which, when run in a processor of an electronic device, executes the path planning method described above.

[0168] Those skilled in the art will understand that all or some of the steps, systems, or apparatuses in the methods, systems, and apparatuses described above can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0169] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0170] Those skilled in the art will understand that although some embodiments described herein include certain features that are included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this embodiment and form different embodiments.

[0171] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A path planning method, characterized in that, include: Based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from the candidate nodes of the multiple candidate roads to the destination, the target node is determined among the multiple candidate nodes. The path of the target vehicle from the starting point to the multiple candidate nodes includes at least one historical target node that has been planned. The target node is determined as a new historical target node, and the process of determining the target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from the candidate nodes of the multiple candidate roads to the destination is continued, thus determining a new target node. If the next node after the new target node is the destination, a target planning path for the target vehicle is generated based on the starting point, the destination, and the determined multiple target nodes.

2. The method as described in claim 1, characterized in that, Based on the target vehicle's time windows on multiple candidate roads and the estimated travel time of the target vehicle from candidate nodes on each of the multiple candidate roads to its destination, the target node is determined from the multiple candidate nodes, including: For each candidate road, the dynamic weight of the target vehicle traveling on the candidate road is determined based on the set of time windows corresponding to the expected arrival time of the target vehicle from the starting point to the candidate road; The path cost of the candidate node is determined based on the dynamic weight of the candidate road, the dynamic weight of the historical target road corresponding to the at least one historical target node, and the estimated travel time of the target vehicle from the candidate node of the candidate road to the destination. The target node is determined from the plurality of candidate nodes based on the path cost of the plurality of candidate nodes.

3. The method as described in claim 2, characterized in that, Based on the set of time windows corresponding to the estimated arrival time of the target vehicle from the starting point to the candidate road, the dynamic weight of the target vehicle's passage through the candidate road is determined, including: For each time window in the set of time windows, the road load cost of the candidate road within the time window is determined based on the road carrying capacity of the candidate road within the time window. The dynamic weight of the candidate road within the time window is determined based on the road length of the candidate road, the estimated travel time of the target vehicle on the candidate road, and the road load cost. The dynamic weight of the candidate road is determined based on its dynamic weight within each time window.

4. The method as described in claim 3, characterized in that, Based on the road carrying capacity of the candidate roads within the time window, determine the road load cost of the candidate roads within the time window, including: Determine the ratio between the road carrying capacity of the candidate road and the road infrastructure capacity of the candidate road within the time window; The road load cost of the candidate road within the time window is determined based on the ratio.

5. The method as described in claim 3, characterized in that, The method further includes: If the road load cost exceeds a preset load threshold, select some vehicles from among the multiple vehicles in the target area where the target vehicle is located for route replanning, and generate new target planned routes for the selected vehicles.

6. The method as described in claim 3 or 5, characterized in that, The method further includes: When generating the target planning path, the road carrying capacity within each time window is updated based on the capacity deduction factor.

7. The method as described in claim 1, characterized in that, The method further includes: For each candidate road, the estimated arrival time of the target vehicle from the starting point to the candidate road is determined based on the estimated travel time of the target vehicle on the historical target road corresponding to each historical target node. Based on the estimated arrival time and the estimated travel time of the target vehicle through the candidate road, the estimated departure time of the target vehicle from the candidate road is determined; The time window for the target vehicle on the candidate road is determined based on the estimated arrival time and the estimated departure time.

8. The method as described in claim 7, characterized in that, Determining the time window for the target vehicle on the candidate road based on the estimated arrival time and the estimated departure time includes: Based on the estimated arrival time and the estimated departure time, the time interval for the target vehicle to occupy the candidate road is determined; The time windows in the preset time window sequence that overlap with the occupied time interval are determined as the time windows of the target vehicle on the candidate road.

9. A path planning device, characterized in that, include: The node determination module is configured to determine a target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from each candidate node on the multiple candidate roads to the destination, wherein the path of the target vehicle from the starting point to each candidate node includes at least one planned historical target node; the target node is determined as a new historical target node, and the step of determining a target node from multiple candidate nodes based on the time windows of the target vehicle on multiple candidate roads and the estimated travel time of the target vehicle from each candidate node on the multiple candidate roads to the destination is continued to determine a new target node; The path generation module is configured to generate a target planning path for the target vehicle based on the starting point, the ending point, and a plurality of determined target nodes, when the next node after the new target node is the destination.

10. An electronic device, characterized in that, include: One or more processors; A memory having stored one or more programs thereon, which, when executed by the one or more processors, cause the one or more processors to implement the method according to any one of claims 1-8; One or more I / O interfaces are connected between the processor and the memory and configured to enable information interaction between the processor and the memory.