Path planning method and device, equipment and storage medium

Abstract

The invention discloses a path planning method and device, equipment and a storage medium, and the method comprises the steps: determining a target position from a global path according to the current position of a vehicle in a vehicle driving process after the global path of the vehicle from a starting point to a destination is obtained; the predicted passing duration of each passing path is calculated according to the road condition information of the passing paths, the optimal passing path is obtained, the optimal passing path of the vehicle at the current position can be obtained according to the real-time road condition information, it is ensured that each local path is the optimal path in a real-time dynamic local path planning mode, and the traffic safety of the vehicle is improved. Therefore, the global path is gradually optimized, and the passing efficiency of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a path planning method, device, equipment and storage medium. Background Art

[0002] With the continuous research and application of technologies such as autonomous driving, on-board sensing, and vehicle positioning, the intelligent transportation system can provide users with traffic driving suggestions through path planning methods based on the traffic flow information of each section of the urban road, thereby reducing vehicle travel time and alleviating traffic congestion. In the vehicle path planning method in the prior art, the navigation route between the starting point and the destination is determined, and the location information of traffic events on the navigation route is obtained in real time. The vehicle navigation path is replanned according to the location information of the traffic event, thereby completing the path navigation. However, this solution only improves the travel efficiency for traffic events, which has certain limitations, and ignores the impact of changes in road conditions on the travel path on the vehicle travel time. Therefore, the generated path is often not the local optimal path, and fails to maximize the reduction of vehicle travel time, reducing the vehicle's travel efficiency. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a path planning method, device, equipment and storage medium, which can provide a local optimal path according to the vehicle's travel stage, thereby optimizing the global path and improving the vehicle's travel efficiency.

[0004] To achieve the above object, an embodiment of the present invention provides a path planning method, including:

[0005] Determine a target position from the global path according to the current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and at least two passing paths are included between the target position and the current position;

[0006] Calculating the estimated travel time of each travel path according to the traffic information of the travel path;

[0007] Determine the target travel path according to the estimated travel time of each travel path;

[0008] The global path is updated according to the target travel path, and the vehicle is instructed to travel until it is detected that the vehicle arrives at the destination.

[0009] As an improvement of the above solution, the road condition information includes the road section information of each road section in the passing path and the timing status of the traffic light at each intersection in the passing path; then, the estimated travel time of each passing path is calculated according to the road condition information of the passing path, including:

[0010] Calculate the travel time of the current road section according to the road section information;

[0011] Calculate the waiting time of the vehicle at each intersection according to the travel time of the road section and the timing status of the signal light;

[0012] The travel time of each road section and the waiting time at each intersection are accumulated to obtain the estimated travel time of the travel path.

[0013] As an improvement of the above solution, the calculation of the waiting time of the vehicle at each intersection according to the passage time of the road section and the timing status of the signal light includes:

[0014] Obtaining the initial timing state of the traffic light at each intersection in each of the passage paths when the vehicle is at the current position;

[0015] According to the road section passing time of the vehicle in each road section in the passing path and the initial timing state of the traffic light, predicting the timing state change information of the traffic light at the intersection corresponding to each road section when the vehicle passes through the road section;

[0016] The waiting time of the vehicle at each intersection when arriving at the intersection is determined according to the timing state change information and the signal light cycle.

[0017] As an improvement of the above solution, the road condition information also includes vehicle parking information of each road section; then, calculating the road section travel time of the current road section according to the road section information includes:

[0018] Calculating a congestion index of a current road section according to the vehicle parking information;

[0019] The road section travel time of the current road section is calculated according to the congestion degree index and the road section information.

[0020] As an improvement of the above solution, the road section information includes the road section length and the average travel speed; then, calculating the road section travel time of the current road section according to the congestion index and the road section information includes:

[0021] If the congestion index of the current road section is greater than a preset congestion threshold, the road section travel time of the current road section is calculated according to the road section length, the average travel speed and the congestion index;

[0022] If the congestion index of the current road section is less than or equal to the congestion threshold, the road section travel time of the current road section is calculated according to the road section length and the average travel speed.

[0023] As an improvement of the above solution, the step of calculating the congestion index of the current road section according to the vehicle parking information includes:

[0024] Obtaining the vehicle parking information of several target vehicles passing through the current road section on the current road section; wherein the vehicle parking information includes the parking duration and the number of parking times;

[0025] Obtaining a target number of parking times for each target vehicle whose parking time is greater than a preset parking time threshold;

[0026] The average value of the target parking times of all target vehicles is calculated as the congestion degree index of the current road section.

[0027] As an improvement of the above solution, determining a target position from the global path according to the current position of the vehicle includes:

[0028] Calculate the segment evaluation parameters for each segment in the global path;

[0029] Taking the road section where the current position of the vehicle is located as the starting road section, a plurality of continuous target road sections are determined from the global path according to the road section evaluation parameters; wherein the sum of the road section evaluation parameters of the plurality of target road sections is greater than a preset evaluation parameter threshold;

[0030] Any position of the last section among a plurality of continuous target sections is taken as the target position.

[0031] As an improvement of the above solution, the step of calculating the segment evaluation parameter of each segment in the global path includes:

[0032] Get the average travel time, congestion index and red light cycle of each road section in the global path;

[0033] The road section evaluation parameters of each road section are calculated according to the average travel time, congestion index and red light cycle.

[0034] To achieve the above object, an embodiment of the present invention further provides a path planning device, comprising:

[0035] A target position determination module, used to determine a target position from a global path according to a current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and there are at least two passing paths between the target position and the current position;

[0036] An estimated travel time calculation module, used to calculate the estimated travel time of each travel path according to the road condition information of the travel path;

[0037] A target travel path determination module is used to determine the target travel path according to the estimated travel time of each travel path;

[0038] The global path updating module is used to update the global path according to the target travel path and instruct the vehicle to pass until it is detected that the vehicle arrives at the destination.

[0039] To achieve the above objectives, an embodiment of the present invention further provides a path planning device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the path planning method as described in any of the above embodiments is implemented.

[0040] To achieve the above objectives, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the path planning method as described in any of the above embodiments.

[0041] Compared with the prior art, the path planning method, device, equipment and storage medium disclosed in the present invention, after obtaining the global path of the vehicle from the starting point to the destination, determine a target position from the global path according to the current position of the vehicle during the vehicle's driving process, calculate the estimated travel time of each travel path according to the road condition information of the travel path, and obtain the optimal travel path. It can obtain the optimal travel path of the vehicle at the current position according to the real-time road condition information, reduce the situation in which the path planning is inaccurate due to the increased variability in complex road conditions, and ensure that each local path is the optimal path through real-time dynamic local path planning, thereby gradually optimizing the global path and improving the vehicle's travel efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a path planning method provided by an embodiment of the present invention;

[0043] Figure 2 is a global path schematic diagram provided by an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of the timing status of traffic lights in a traffic path provided by an embodiment of the present invention;

[0045] Figure 4 is another flow chart of a path planning method provided by an embodiment of the present invention;

[0046] Figure 5 is a structural block diagram of a path planning device provided by an embodiment of the present invention;

[0047] Figure 6 It is a structural block diagram of an estimated travel time calculation module in a path planning device provided by an embodiment of the present invention;

[0048] Figure 7 is a structural block diagram of a target position determination module in a path planning device provided by an embodiment of the present invention;

[0049] Figure 8 It is a structural block diagram of a path planning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 , Figure 1 is a flow chart of a path planning method provided by an embodiment of the present invention, the path planning method comprising:

[0052] S1. Determine a target position from a global path according to a current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and there are at least two passing paths between the target position and the current position;

[0053] S2. Calculating the estimated travel time of each travel path according to the road condition information of the travel path;

[0054] S3, determining the target travel path according to the estimated travel time of each travel path;

[0055] S4. Update the global path according to the target travel path, and instruct the vehicle to pass until it is detected that the vehicle arrives at the destination.

[0056] It is worth noting that the path planning method described in the embodiment of the present invention is implemented by a cloud platform, and the cloud platform can obtain vehicle information (such as location, speed, etc.), map data and traffic light data. The cloud platform uses a vehicle-mounted positioning device to collect vehicle information; wherein, the vehicle information includes a timestamp, location longitude and latitude, vehicle speed, heading angle, vehicle unique identification number and other information. The cloud platform collects vehicle sensor information as raw data, such as vehicle sensors including but not limited to GPS (Global Positioning System), IMU (Inertial measurement unit), wheel speed meter, laser radar, and processes the raw data to generate C-V2X MAP (hereinafter referred to as MAP) data. C-V2X (Cellular Vehicle-to-Everything) technology is a dedicated wireless communication technology for the Internet of Vehicles that can ensure low latency and high reliability. MAP map data contains key information such as the upstream and downstream relationship between roads and intersections, the coordinates of the center point of the road, the width of the road, and the corresponding traffic light phase ID. The cloud platform can read the traffic light information at the intersection in real time, and the traffic light information includes: traffic light phase, traffic light state, duration, start time of the next cycle, duration of the next cycle and other key information.

[0057] Specifically, before step S1, the method further includes: generating a global path of the vehicle from the starting point to the destination according to the map data.

[0058] For example, within the area of ​​MAP map data, a starting point (the default is the current vehicle location, or the driver's custom location) and a destination are selected, and a directed graph is formed based on common path planning algorithms such as the Dijkstra algorithm, with the length of the current road section, the average speed, and the degree of congestion as weights, and the path with the shortest time and distance from the current location to the target location intersection is calculated as the vehicle's global path. Combined with MAP map data, the road network relationship of the global path can be obtained, such as Figure 2 As shown, the road network relationship of the global path includes several adjacent intersections, namely intersections A to T. Two adjacent intersections form a road section, such as intersection A and intersection E form section AE. Assuming that the starting point of the vehicle is located in section AE and the destination is intersection T, the shortest path (one of them) from the starting point (the origin in the figure) to point T is: vehicle-EFJKOPT.

[0059] Specifically, in step S1, a target position is determined from a global path according to a current position of the vehicle, and at least two passing paths are included between the target position and the current position.

[0060] For example, according to the road network relationship between the current position of the vehicle and the global path, a target position is found in the global path. This target position needs to be at a certain distance from the current position of the vehicle, and this distance needs to satisfy that there are at least two passing paths from the current position to the target position, so that the best passing path can be determined from at least two passing paths. Figure 3 As shown in the figure, assuming that the target location is intersection K at this time, multiple paths from the current location of the vehicle to the target location are replanned based on the intersection node information and upstream and downstream relationships. The replanned paths are non-shortest paths and only contain possible directed path information. For example, three paths from the current location of the vehicle to the target location are replanned, namely: vehicle-EFJK, vehicle-EIJK, and vehicle-EFGK.

[0061] It is worth noting that when the vehicle is driving, the cloud platform can trigger local path planning at fixed time intervals, at which time the current position of the vehicle is obtained and step S1 is executed. The fixed time interval can be determined by the red light cycle of the road where the vehicle is located. For example, if the red light cycle of the road where the vehicle is located is 40s, the cloud platform triggers local path planning every 40s. Alternatively, the fixed time interval can be customized by the cloud platform, such as triggering local path planning every 30s.

[0062] Specifically, in step S2, the road condition information includes the road section information of each road section in the travel path and the traffic light information of each intersection in the travel path; then, calculating the estimated travel time of each travel path according to the road condition information of the travel path includes:

[0063] S21, calculating the road section travel time of the current road section according to the road section information;

[0064] S22, calculating the waiting time of the vehicle at each intersection according to the road section travel time and the traffic light information;

[0065] S23, accumulating the travel time of each road section and the waiting time at each intersection to obtain the estimated travel time of the travel path.

[0066] Specifically, in step S11, the road section information includes the road section length and the average speed. The average speed can be determined by the vehicle speed in the historical time period, such as the average speed of vehicles passing through the road section in each time period (such as 1h) a week ago, thereby obtaining the average speed of the road section in different time periods. When the real-time congestion level of the road section is not considered, the road section travel time of the road section can be obtained according to the road section length and the average speed. For example, if the length of road section EF is 300m and the average speed is 45km / h, about 12.5m / s, the road section travel time of road section EF is 300 / 12.5=24s.

[0067] Furthermore, when considering the real-time congestion level of a road section, the road condition information also includes vehicle parking information for each road section; then, calculating the road section travel time of the current road section based on the road section information includes: calculating the congestion level index of the current road section based on the vehicle parking information; and calculating the road section travel time of the current road section based on the congestion level index and the road section information.

[0068] Exemplarily, the congestion index is used to reflect the congestion level of this road section, which is calculated by the average number of times vehicles stop in this road section. The larger the congestion index, the more congested this road section is, and the more vehicles are waiting to pass. Conversely, the smaller the congestion index, the smoother this road section is. In the embodiment of the present invention, the actual road section travel time through this road section is determined in combination with the congestion index. The road section information of different road sections in the three passing paths and the parameter examples of the congestion index can be referred to Table 2.

[0069] Table 1 Parameter examples of road section information and congestion index

[0070] Road Section Section length (m) Average traffic speed Congestion Index Vehicle-E 150 35km / h, about 9.7m / s 1.1 EF 300 45km / h, about 12.5m / s 0.9 FG 400 30km / h, about 8.3m / s 1.4 GK 400 50km / h, about 13.9m / s 0.7 EI 400 40km / h, about 11m / s 1.2 IJ 400 35km / h, about 9.7m / s 1.2 JK 400 45km / h, about 12.5m / s 1.2 FJ 400 30km / h, about 8.3m / s 1.4

[0071] Specifically, if the congestion index of the current road section is greater than a preset congestion threshold, the road section travel time of the current road section is calculated based on the road section length, the average travel speed and the congestion index; if the congestion index of the current road section is less than or equal to the congestion threshold, the road section travel time of the current road section is calculated based on the road section length and the average travel speed.

[0072] Exemplarily, the congestion threshold is 1, or it can be other values. If the congestion index of the current road section is greater than 1, it means that there is a possibility of congestion on this road section, then the corresponding travel time will be longer, and it is necessary to multiply the congestion index on the basis of the original travel time; if the congestion index of road section FG is 1.4, then the travel time of road section FG is (400 / 8.3)*1.4=67.5s. If the congestion index of the current road section is less than or equal to 1, it means that there will be basically no congestion on this road, then when calculating the travel time, there is no need to multiply the congestion index; if the congestion index of road section EF is 0.9, then the travel time of road section EF is 300 / 12.5=24s.

[0073] Furthermore, the calculation of the congestion index of the current road section based on the vehicle parking information includes: obtaining vehicle parking information of several target vehicles passing through the current road section; wherein the vehicle parking information includes parking duration and number of parking times; obtaining the target number of parking times for each target vehicle whose parking duration is greater than a preset parking duration threshold; and calculating the average of the target number of parking times for all target vehicles as the congestion index of the current road section.

[0074] For example, the traffic participant data is obtained based on the real-time traffic flow data of the cloud platform, the number of vehicle stops is detected, and the target number of stops greater than the stop time threshold (such as 10s) is screened out. When a vehicle is driving at an intersection with traffic lights, the driving speed will be affected by some vehicles, and there will be a phenomenon of stop-and-go. Only when the vehicle is stopped for a certain period of time will it be considered that the vehicle is truly stopped on the road section waiting for passage. The stop time threshold can be determined based on actual experience. Assume that vehicle A enters a road section and the current traffic light is red, then the vehicle will inevitably stop at a certain position. If the parking time is greater than the parking time threshold, the target number of stops will be recorded as 1; when the traffic light turns green, the vehicle starts to move. If it does not pass the intersection within a green light cycle, then the vehicle will inevitably stop on the road section. The parking time is greater than the parking time threshold, then the target number of stops is +1. The target number of stops for vehicle A when passing through this road section is calculated, and the average number of target stops for several vehicles (such as 100 vehicles) within a time period (such as the current time is 13:00, then the half hour from 12:30 to 13:00 is counted), and the average value is used as the congestion index of this road section.

[0075] Specifically, in step S22, after calculating the passage time of the road section, the waiting time of the vehicle at each intersection is calculated based on the passage time of the road section and the timing status of the traffic light, including: obtaining the initial timing status of the traffic light at each intersection in each passage path when the vehicle is at the current position; predicting the timing status change information of the traffic light at the intersection corresponding to the vehicle when passing each road section based on the passage time of the vehicle in each road section in the passage path and the initial timing status of the traffic light; determining the waiting time of the vehicle at the intersection when arriving at each intersection based on the timing status change information and the traffic light cycle.

[0076] For example, see Figure 3 , Figure 3 : is a schematic diagram of the timing states of traffic lights in the passage path provided by an embodiment of the present invention. Assuming that a traffic light cycle is 80 seconds, including a green light of 37 seconds, a yellow light of 3 seconds, and a red light of 40 seconds, when the vehicle is at the current position (i.e., position A in the figure), the initial timing states of the traffic lights at intersections E, F, G, I, and J in the three passage paths are as follows: Figure 3 As shown, the initial timing state of intersection E satisfies: it is green light, and there are 15s left in the countdown of the green light. Since the vehicle is at position A at this time, when the vehicle arrives at intersection E, it has passed the section passage time of section AE. At this time, the timing state of the signal light at intersection E will change, and the timing state of the signal lights at other intersections will also change. Therefore, according to the section passage time of the vehicle in each section and the initial timing state of the signal light, the timing state change information of the signal light at the intersection corresponding to the vehicle passing through each section can be predicted, and then the intersection waiting time of the vehicle when arriving at each intersection is determined according to the timing state change information and the signal light cycle. Take the path of vehicle-EFJK as an example. The speed of the vehicle at the current position (section AE) is 40km / h, about 11m / s, and the section length of the vehicle from intersection E is 150m. The estimated passage time of the passage path "vehicle-EFJK" is calculated as follows:

[0077] ① When a vehicle passes through intersection E to intersection F and turns left, it needs to observe the green light countdown before it can pass. The time required for the vehicle to reach intersection E is calculated as: 150 / 11≈13.6 seconds, but considering the congestion index and average speed of section AE, the actual processing requires (150 / 9.7)*1.1≈17.01 seconds, and the initial timing state of intersection E satisfies: the current green light remaining time is 15 seconds. Therefore, the vehicle can only pass through intersection E after driving on section AE for 15 seconds and waiting for the next green light cycle. Therefore, it can be predicted that the timing state change information of the signal light at intersection E when the vehicle passes through section AE satisfies: green light-red light-yellow light-green light. Then when the first green light ends, the vehicle has traveled a distance of (9.7*15) / 1.1≈132m, and there is about 18m left to the intersection. When the next green light cycle comes, the vehicle can pass normally, and the passing time is (18 / 9.7)*1.1≈2.04 seconds. At this time, the waiting time for the yellow light and the red light needs to be added, that is, the waiting time for intersection E is 43s (yellow light 3s + red light 40s), then the driving time required to pass through intersection E is 15+2.04+3+40=60.04 seconds; among which, "15+2.04" is the vehicle's passing time on section AE, and "3+40" is the waiting time at intersection E.

[0078] ② When the vehicle passes through intersection F to intersection J, it turns right and can pass without observing the green light countdown. However, considering the problem of vehicles at the intersection, it is necessary to determine whether it is necessary to wait for the right turn: according to the traffic data information issued by the traffic platform, find out whether there is a dedicated right-turn lane on the section of road. If so, further determine whether there is a dedicated right-turn control light and the countdown of the right-turn control light to determine whether it is possible to pass within the green light cycle; if there is no dedicated right-turn lane, find out whether there is a vehicle occupying the lane that can turn right on the section of road. If so, it is necessary to wait for the lane to be within the green light cycle before passing; if not, it can pass directly.

[0079] Assuming that waiting is required, the vehicle needs to wait for the green light before passing through intersection F to intersection J. The initial timing state of intersection F satisfies: the remaining time of the current red light is 15 seconds. The time required from intersection E to intersection F is: (300 / 12.5) = 24s; 60.04s is rounded up to 61s, so the traffic light state of intersection F after 61+24s is: (61+24)%(37+3+40)=5, that is, when the vehicle passes through section EF and arrives at intersection F, after a signal light cycle (37+3+40), 5 seconds have passed since the original light state of intersection F. Therefore, it can be predicted that when the vehicle passes through section EF, the timing state change information of the traffic light at intersection F satisfies: red light-yellow light-green light-red light. At this time, intersection F has changed from the original countdown of 15s (refer to Figure 3, when the vehicle is still on section AE, the traffic light at intersection F is red, and the red light countdown is 15s, which changes to 10s. It is not within the green light time, and there are still 10s before the green light turns on. It needs to wait for 10s before passing. That is, the waiting time at intersection F is 10s. Then the time required for the vehicle to travel from intersection E to intersection J is: (300 / 12.5)+(400 / 8.3)*1.4+10≈101.47s; among which, "(300 / 12.5)" is the section travel time of section EF, "(400 / 8.3)*1.4" is the section travel time of section FJ, and "10" is the waiting time at intersection F.

[0080] Assuming that there is no need to wait, that is, the waiting time at intersection F is 0, the time required for a vehicle to travel from intersection F to intersection J is: (300 / 12.5)+(400 / 8.3)*1.4≈91.47s.

[0081] ③ The vehicle passes through intersection J to intersection K and needs to turn left. Intersection J waits and calculates as needed. The initial timing state of intersection J satisfies: the current green light remaining time is 5 seconds. 60.04s is rounded up to 61s, and 101.47s is rounded up to 102s. Then the signal light state of intersection J after 61+102s is: 163%(37+3+40)=3, which means 3 seconds have passed since the original light state of intersection J. Therefore, it can be predicted that the timing state change information of the signal light of intersection J when the vehicle passes through section FJ satisfies: green light-red light-yellow light-green light-red light-yellow light-green light. At this time, the green light countdown at intersection J changes from 5s to 2s, and the light is still green, so you can pass directly without waiting. That is, the waiting time at intersection J is 0, and the driving time from intersection J to intersection K is: (400 / 12.5)*1.2=38.4 seconds.

[0082] Specifically, in step S23, the travel time of each section and the waiting time at each intersection are accumulated to obtain the estimated travel time of the travel path. For example, the estimated travel time of the travel path "vehicle-EFJK" is: 60.04+101.47+38.4=199.91 seconds; similarly, the same calculation method is used for other travel paths, and the calculation results are as follows: the estimated travel time of the travel path "vehicle-EIJK" is 204.52 seconds; the estimated travel time of the travel path "vehicle-EFGK" is 190.65 seconds.

[0083] Specifically, in step S3, the target communication path is determined according to the estimated travel time of each travel path. Exemplarily, as calculated in step S23, the path with the shortest estimated travel time is selected as the target communication path, namely "vehicle-EFGK".

[0084] Specifically, in step S4, the global path is updated according to the target travel path, and the vehicle is instructed to pass until it is detected that the vehicle has arrived at the destination.

[0085] Exemplarily, since the cloud platform can trigger local path planning at fixed time intervals, each time the local path planning is triggered, steps S1 to S3 need to be executed to obtain a target travel path. For example, when the target communication path is vehicle-EFGK, the optimal global path at this time is updated to: vehicle-EFGKOPT. After a fixed time interval, assuming that the vehicle travels to section EF (not reaching the target location intersection K selected in step S1), steps S1 to S3 are repeated, and a target location is selected again according to the global path "vehicle-EFGKOPT", and the target communication path when the vehicle is located at section EF is continued to be calculated until it is detected that the vehicle has arrived at the destination.

[0086] In an embodiment of the present invention, a target position is determined from the global path according to the current position of the vehicle, and the estimated travel time of each travel path is calculated according to the road condition information of the travel path to obtain the optimal travel path. The optimal travel path of the vehicle at the current position can be obtained according to the real-time road condition information, thereby reducing the situation in which the path planning is inaccurate due to the increased variability in complex road conditions. Through real-time dynamic local path planning, it is ensured that each local path is the optimal path, thereby gradually optimizing the global path and improving the travel efficiency of the vehicle.

[0087] Furthermore, step S1 specifically includes:

[0088] S11, calculating the section evaluation parameters of each section in the global path;

[0089] S12, taking the road section where the current position of the vehicle is located as the starting road section, determining a plurality of continuous target road sections from the global path according to the road section evaluation parameters; wherein the sum of the road section evaluation parameters of the plurality of target road sections is greater than a preset evaluation parameter threshold;

[0090] S13. Taking any position of the last section among a plurality of continuous target sections as the target position.

[0091] Specifically, the calculation of the section evaluation parameters of each section in the global path includes: obtaining the average travel time, congestion index and red light cycle of each section in the global path; and calculating the section evaluation parameters of each section based on the average travel time, congestion index and red light cycle.

[0092] Exemplarily, assuming that the route passes through the following 10 road sections, the average travel time, congestion index and red light cycle of each road section can be found in Table 2.

[0093] Table 2 Examples of average travel time, congestion index and red light cycle for sections 1-10

[0094]

[0095]

[0096] Exemplarily, the calculation formula of the road section evaluation parameter C satisfies:

[0097] C=(t / avgT)*(i / avgI)*(r / avgR);

[0098] Among them, t is the average travel time, which is the ratio of the length of the section and the average travel speed of this section; avgT is the average travel time of all sections in the path; i is the congestion index; avgI is the average value of the congestion index; r is the red light cycle; avgR is the average value of the red light cycle of all sections in the path.

[0099] It is worth noting that the selection of several (assuming N) target sections is negatively correlated with the average travel time of the current road, the congestion index, and the red light cycle of the current intersection. The higher the average travel time, the higher the congestion index, and the longer the red light cycle, the smaller N should be. For example, the value of N satisfies the last intersection where the coefficient C is greater than 4.

[0100] For example, usually, the more complex the road section, the greater the variability. According to the calculation formula of the section evaluation parameter, it can be seen that the value of the section evaluation parameter depends on the average travel time at the intersection, the average red light cycle at the intersection, and the average congestion index at the intersection, and is positively correlated with these three items. Therefore, in the case of complex sections, reducing the sections that need to be dynamically calculated also reduces this variability. The value of 4 is currently selected, and it can also be adjusted to 5 or other values, but it is not recommended to be too large, so as to avoid increased variability and inaccurate path planning; it is also not recommended to be too small, otherwise there will only be one communication path, and the meaning of subsequent calculation of the best travel path is lost. As shown in Table 1: when the vehicle is located at section 1, 1.273+0.797+0.579+0.729+0.877=4.255, when the sum is 0.877, i.e. the 5th section, it is greater than 4, then the value of N can be 5, and the several consecutive target sections are in the range of 1-5; when the vehicle is located at section 4, 0.729+0.877+3.189=4.795, when the sum is 3.189, i.e. the 3rd section, it is greater than 4, then the value of N is 3, and the several consecutive target sections are in the range of 4-6.

[0101] In an embodiment of the present invention, the red light cycle of each intersection is calculated by counting the average traffic speed, congestion index and traffic light information of the road section, thereby generating the number of road sections to be planned for the local path, thereby reducing the situation in which the path planning is inaccurate due to increased variability in complex road conditions.

[0102] See also Figure 4 , Figure 4 It is another flow chart of a path planning method provided by an embodiment of the present invention. The cloud platform can obtain the road network relationship of the global path based on the vehicle position and map data. During the vehicle driving process, the cloud platform determines a target position from the global path according to the current position of the vehicle and the number N of sections of the local path to be planned, so that there are at least two to-be-selected travel paths from the current position of the vehicle to the target position. The cloud platform calculates the travel time of at least two travel paths according to the congestion index, average travel speed, right turn auxiliary light data and signal light information of each section in each travel path, and selects the shortest travel time as the target travel path. This target travel path is the local optimal path. Finally, the global path is updated according to the target travel path, and the N sections previously selected are replaced with this target travel path.

[0103] Compared with the prior art, the path planning method disclosed in the embodiment of the present invention determines a target position from the global path according to the current position of the vehicle, and calculates the estimated travel time of each travel path according to the road condition information of the travel path to obtain the optimal travel path. The optimal travel path of the vehicle at the current position can be obtained according to the real-time road condition information, which reduces the situation that the variability increases in complex road conditions and causes inaccurate path planning. Through the real-time dynamic local path planning method, it is ensured that each local path is the optimal path, thereby gradually optimizing the global path and improving the vehicle's travel efficiency. In addition, by counting the average travel speed of the road section, the congestion index, the intersection distance and the traffic light information and other factors that can affect the vehicle's travel time, the time required to pass the road section is calculated, which solves the problem that the path is not the optimal path due to the calculation based on a single dimension but ignoring other factors. In addition, through the real-time dynamic local path planning method, it is ensured that each local path is the optimal path, and the global path is calculated progressively, which solves the problem that the final global path cannot actually reach the optimal path because the real-time changing factors are ignored when the path is globally calculated at the beginning.

[0104] See also Figure 5 , Figure 5 is a structural block diagram of a path planning device 100 provided in an embodiment of the present invention, wherein the path planning device 100 comprises:

[0105] A target position determination module 11 is used to determine a target position from a global path according to a current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and there are at least two passing paths between the target position and the current position;

[0106] An estimated travel time calculation module 12 is used to calculate the estimated travel time of each travel path according to the road condition information of the travel path;

[0107] A target travel path determination module 13 is used to determine the target travel path according to the estimated travel time of each travel path;

[0108] The global path updating module 14 is used to update the global path according to the target travel path and instruct the vehicle to pass until it is detected that the vehicle arrives at the destination.

[0109] Specifically, the road condition information includes the road section information of each road section in the passage path and the timing status of the traffic lights at each intersection in the passage path; then, refer to Figure 6 The estimated travel time calculation module 12 includes:

[0110] A road section travel time calculation unit 121, used to calculate the road section travel time of the current road section according to the road section information;

[0111] The intersection waiting time calculation unit 122 is used to calculate the intersection waiting time of the vehicle at each intersection according to the passage time of the road section and the timing status of the signal light;

[0112] The estimated travel time calculation unit 123 is used to accumulate the section travel time of each road section and the intersection waiting time of each intersection to obtain the estimated travel time of the travel path.

[0113] Specifically, the intersection waiting time calculation unit 122 is specifically used to: obtain the initial timing state of the traffic light at each intersection in each of the passage paths when the vehicle is at the current position; predict the timing state change information of the traffic light at the intersection corresponding to the vehicle when passing through each section according to the section passing time of the vehicle in each section of the passage path and the initial timing state of the traffic light; determine the intersection waiting time when the vehicle arrives at each intersection according to the timing state change information and the traffic light cycle.

[0114] Specifically, the road condition information also includes vehicle parking information for each road section; then, the road section travel time calculation unit 121 is used to: calculate the congestion index of the current road section according to the vehicle parking information; calculate the road section travel time of the current road section according to the congestion index and the road section information.

[0115] Specifically, the road section information includes the road section length and the average travel speed; then, calculating the road section travel time of the current road section according to the congestion index and the road section information includes: if the congestion index of the current road section is greater than a preset congestion threshold, calculating the road section travel time of the current road section according to the road section length, the average travel speed and the congestion index; if the congestion index of the current road section is less than or equal to the congestion threshold, calculating the road section travel time of the current road section according to the road section length and the average travel speed.

[0116] Specifically, the calculation of the congestion index of the current road section based on the vehicle parking information includes: obtaining vehicle parking information of several target vehicles passing through the current road section; wherein the vehicle parking information includes parking duration and number of parking times; obtaining the target number of parking times for each target vehicle whose parking duration is greater than a preset parking duration threshold; and calculating the average of the target number of parking times for all target vehicles as the congestion index of the current road section.

[0117] Specifically, see Figure 7 , the target location determination module 11 includes:

[0118] A road segment evaluation parameter calculation unit 111, used to calculate a road segment evaluation parameter of each road segment in the global path;

[0119] The target road section determination unit 112 is used to determine a plurality of continuous target road sections from the global path according to the road section evaluation parameter, taking the road section where the current position of the vehicle is located as the starting road section; wherein the sum of the road section evaluation parameters of the plurality of target road sections is greater than a preset evaluation parameter threshold;

[0120] The target position determination unit 113 is configured to take any position of the last section among a plurality of consecutive target sections as the target position.

[0121] Specifically, the section evaluation parameter calculation unit 111 is used to: obtain the average travel time, congestion index and red light cycle of each section in the global path; calculate the section evaluation parameters of each section based on the average travel time, congestion index and red light cycle.

[0122] It is worth noting that the working process of each module in the path planning device 100 described in the embodiment of the present invention can refer to the working process of the path planning method described in the above embodiment, and will not be repeated here.

[0123] Compared with the prior art, the path planning device 100 disclosed in the embodiment of the present invention determines a target position from the global path according to the current position of the vehicle, and calculates the estimated travel time of each travel path according to the road condition information of the travel path to obtain the optimal travel path. The optimal travel path of the vehicle at the current position can be obtained according to the real-time road condition information, which reduces the situation that the variability increases in complex road conditions and causes inaccurate path planning. Through the real-time dynamic local path planning method, it is ensured that each local path is the optimal path, thereby gradually optimizing the global path and improving the vehicle's travel efficiency. In addition, by counting the average travel speed of the road section, the congestion index, the intersection distance and the traffic light information and other factors that can affect the vehicle's travel time, the time required to pass the road section is calculated, which solves the problem that the path is not the optimal path due to the calculation based on a single dimension but ignoring other factors. In addition, through the real-time dynamic local path planning method, it is ensured that each local path is the optimal path, and the global path is calculated progressively, which solves the problem that the final global path cannot actually reach the optimal path because the real-time changing factors are ignored when the path is globally calculated at the beginning.

[0124] See also Figure 8 , Figure 8 2 is a structural block diagram of a path planning device 200 provided in an embodiment of the present invention, wherein the path planning device 200 includes a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned path planning method embodiments are implemented, such as steps S1 to S4.

[0125] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the path planning device 200.

[0126] The path planning device 200 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will appreciate that the schematic diagram is merely an example of the path planning device 200 and does not constitute a limitation on the path planning device 200. The path planning device 200 may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the path planning device 200 may also include input and output devices, network access devices, buses, etc.

[0127] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the path planning device 200, and uses various interfaces and lines to connect various parts of the entire path planning device 200.

[0128] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the path planning device 200 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0129] Wherein, if the module / unit integrated in the path planning device 200 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor 21. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0130] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A path planning method, characterized in that: include: Determine a target position from the global path according to the current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and at least two passing paths are included between the target position and the current position; Calculating the estimated travel time of each travel path according to the traffic information of the travel path; Determine the target travel path according to the estimated travel time of each travel path; The global path is updated according to the target travel path, and the vehicle is instructed to travel until it is detected that the vehicle arrives at the destination.

2. The path planning method according to claim 1, characterized in that: The traffic condition information includes the section information of each section in the travel path and the timing status of the traffic light at each intersection in the travel path; then, calculating the estimated travel time of each travel path according to the traffic condition information of the travel path includes: Calculate the travel time of the current road section according to the road section information; Calculate the waiting time of the vehicle at each intersection according to the travel time of the road section and the timing status of the signal light; The travel time of each road section and the waiting time at each intersection are accumulated to obtain the estimated travel time of the travel path.

3. The path planning method according to claim 2, characterized in that: The step of calculating the waiting time of the vehicle at each intersection according to the passage time of the road section and the timing status of the signal light comprises: Obtaining the initial timing state of the traffic light at each intersection in each of the passage paths when the vehicle is at the current position; According to the road section passing time of the vehicle in each road section in the passing path and the initial timing state of the traffic light, predicting the timing state change information of the traffic light at the intersection corresponding to each road section when the vehicle passes through the road section; The waiting time of the vehicle at each intersection when arriving at the intersection is determined according to the timing state change information and the signal light cycle.

4. The path planning method according to claim 2, characterized in that: The road condition information also includes vehicle parking information for each road section; then, calculating the road section travel time of the current road section according to the road section information includes: Calculating a congestion index of a current road section according to the vehicle parking information; The road section travel time of the current road section is calculated according to the congestion degree index and the road section information.

5. The path planning method according to claim 4, characterized in that: The road section information includes the road section length and the average travel speed; then, calculating the road section travel time of the current road section according to the congestion index and the road section information includes: If the congestion index of the current road section is greater than a preset congestion threshold, the road section travel time of the current road section is calculated according to the road section length, the average travel speed and the congestion index; If the congestion index of the current road section is less than or equal to the congestion threshold, the road section travel time of the current road section is calculated according to the road section length and the average travel speed.

6. The path planning method according to claim 4, characterized in that: The calculating the congestion index of the current road section according to the vehicle parking information includes: Obtaining the vehicle parking information of several target vehicles passing through the current road section on the current road section; wherein the vehicle parking information includes the parking duration and the number of parking times; Obtaining a target number of parking times for each target vehicle whose parking time is greater than a preset parking time threshold; The average value of the target parking times of all target vehicles is calculated as the congestion degree index of the current road section.

7. The path planning method according to claim 1, characterized in that: Determining a target position from a global path according to a current position of the vehicle includes: Calculate the segment evaluation parameters for each segment in the global path; Taking the road section where the current position of the vehicle is located as the starting road section, a plurality of continuous target road sections are determined from the global path according to the road section evaluation parameters; wherein the sum of the road section evaluation parameters of the plurality of target road sections is greater than a preset evaluation parameter threshold; Any position of the last section among a plurality of continuous target sections is taken as the target position.

8. The path planning method according to claim 7, characterized in that: The calculating of the segment evaluation parameters of each segment in the global path includes: Get the average travel time, congestion index and red light cycle of each road section in the global path; The road section evaluation parameters of each road section are calculated according to the average travel time, congestion index and red light cycle.

9. A path planning device, characterized in that: include: A target position determination module, used to determine a target position from a global path according to a current position of the vehicle; wherein the global path includes path information of the vehicle from a starting point to a destination, and there are at least two passing paths between the target position and the current position; An estimated travel time calculation module, used to calculate the estimated travel time of each travel path according to the road condition information of the travel path; A target travel path determination module is used to determine the target travel path according to the estimated travel time of each travel path; The global path updating module is used to update the global path according to the target travel path and instruct the vehicle to pass until it is detected that the vehicle arrives at the destination.

10. A path planning device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the path planning method according to any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the path planning method according to any one of claims 1 to 8.

Images