CN117782132A

CN117782132A - Path planning method, device, equipment and medium based on traffic uncertainty

Info

Publication number: CN117782132A
Application number: CN202311823930.2A
Authority: CN
Inventors: 王晓林; 陈冰; 刘桂志; 李晓曦
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2023-12-27
Filing date: 2023-12-27
Publication date: 2024-03-29

Abstract

The application provides a path planning method, device, equipment and medium based on traffic uncertainty, which can be used in the technical field of path planning. The method comprises the steps of obtaining a first navigation inquiry request sent by an automatic driving vehicle, wherein the first navigation inquiry request comprises: navigation start position, navigation end position and request time; acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time; determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

Description

Path planning method, device, equipment and medium based on traffic uncertainty

Technical Field

The present disclosure relates to the field of path planning technologies, and in particular, to a method, an apparatus, a device, and a medium for path planning based on traffic uncertainty.

Background

With the rapid development of urban traffic, it is difficult to find free space to accommodate more traffic infrastructure in developed cities, and therefore developing an effective navigation system is a low cost option to alleviate traffic congestion. In a scenario where a plurality of vehicles carrying automatic driving techniques all travel along a predetermined route suggested by a navigation system, it is possible to accurately predict traffic congestion if the navigation system is able to know the predetermined route of each vehicle.

Existing path planning methods focus on solving traffic distribution problems or multi-agent routing problems, for example, by behavioral methods, where dynamic traffic distribution models can be used to represent interactions between travel selections and traffic flows; multi-agent based vehicle routing systems focus on how these agents perform communication between them to improve decisions; and calculating the probability of road traffic jam through route information sharing so as to facilitate the diversion of a driver.

However, the existing route planning method is based on the assumption that all the automatically driven vehicles travel along the route planned by the vehicle, and does not consider any traffic uncertainty in the route planning, such as traffic accidents or the situation that the route is changed due to destination change or temporary parking, so that traffic jam caused by the traffic uncertainty cannot be avoided.

Disclosure of Invention

The application provides a path planning method, device, equipment and medium based on traffic uncertainty, which are used for solving the problem that the conventional path planning method cannot avoid traffic jam caused by the traffic uncertainty.

In a first aspect, the present application provides a method for path planning based on traffic uncertainty, the method comprising:

acquiring a first navigation inquiry request sent by an automatic driving vehicle, wherein the first navigation inquiry request comprises: navigation start position, navigation end position and request time;

acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time;

and determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path.

Optionally, the determining the planned path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set includes:

Determining a plurality of candidate paths according to the navigation starting position and the navigation ending position, wherein each candidate path comprises at least one candidate road;

determining the current traffic flow of each candidate road according to the navigation query set;

determining first state information of each candidate road according to the traffic abnormality set, wherein the state information is used for indicating whether traffic abnormality exists or not and an accident period when the traffic abnormality exists;

and determining the planning path matched with the first navigation inquiry request from a plurality of candidate paths according to the current traffic flow, the first state information of the candidate roads and a passing duration set.

Optionally, the determining the planned path matched with the first navigation inquiry request from a plurality of candidate paths according to the current traffic flow, the first state information of the candidate roads and the passing duration set includes:

updating the passing duration sets of the candidate roads according to the current traffic flow and the first state information of the candidate roads to obtain a target passing duration set of each candidate road;

determining the target passing duration of each candidate path according to the target passing duration sets of the candidate roads;

And taking the candidate path with the shortest target passing duration in the plurality of candidate paths as the planning path.

Optionally, the determining the current traffic flow of each candidate road according to the navigation query set includes:

classifying a plurality of second navigation inquiry requests in the navigation inquiry set to obtain navigation inquiry information corresponding to each candidate road, wherein the navigation inquiry information is used for indicating the number of the second navigation inquiry requests corresponding to the candidate roads;

and determining the current traffic flow of each candidate road according to the navigation inquiry information of the candidate roads.

Optionally, the determining the first status information of each candidate road according to the traffic anomaly set includes:

judging whether each candidate road has traffic abnormality or not according to the occurrence positions of a plurality of traffic abnormalities in the traffic abnormality set and the position information of a plurality of candidate roads;

if yes, recording an accident period with traffic abnormality, and determining the first state information of the candidate road as an accident state;

if not, determining that the first state information of the candidate road is in a normal state.

Optionally, before the acquiring the first navigation inquiry request sent by the automatic driving vehicle, the method further includes:

Acquiring second navigation inquiry requests sent by a plurality of automatic driving vehicles in a driving state, wherein the navigation inquiry requests comprise geographic positions and inquiry moments;

updating a plurality of third navigation inquiry requests in the navigation inquiry set according to the plurality of second navigation inquiry requests, wherein the inquiry time of the third navigation inquiry requests is earlier than the inquiry time of the second navigation inquiry requests;

determining first passing time lengths of a plurality of candidate roads according to geographic positions and query time corresponding to a plurality of second navigation query requests and geographic positions and query time corresponding to a plurality of third navigation query requests in a navigation query set, and updating the passing time lengths in the passing time length set according to the first passing time lengths of the plurality of candidate roads;

and determining second state information of each candidate road according to the first passing time length of the candidate roads and the preset passing time length of the candidate roads, and updating the first state information in the traffic anomaly set according to the second state information.

In a second aspect, the present application provides a traffic uncertainty-based path planning apparatus, the apparatus comprising:

The system comprises an acquisition module, a first navigation inquiry module and a second navigation inquiry module, wherein the acquisition module is used for acquiring a first navigation inquiry request sent by an automatic driving vehicle, and the first navigation inquiry request comprises: navigation start position, navigation end position and request time;

the acquisition module is further used for acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time;

and the processing module is used for determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path.

Optionally, the processing module is further configured to determine a plurality of candidate paths according to the navigation start position and the navigation end position, where each candidate path includes at least one candidate road;

the processing module is further used for determining the current traffic flow of each candidate road according to the navigation query set;

the processing module is further used for determining first state information of each candidate road according to the traffic abnormality set, wherein the state information is used for indicating whether traffic abnormality exists or not and an accident period when the traffic abnormality exists;

The processing module is further configured to determine, from a plurality of candidate paths, the planned path that matches the first navigation query request according to the current traffic flow, first status information of the plurality of candidate roads, and a set of passing durations.

Optionally, the processing module is further configured to update the set of passing duration of the plurality of candidate roads according to the current traffic flow and the first state information of the plurality of candidate roads, so as to obtain a set of target passing duration of each candidate road;

the processing module is further used for determining the target passing duration of each candidate path according to the target passing duration sets of the candidate roads;

the processing module is further configured to use a candidate path with a shortest target passing duration among the multiple candidate paths as the planned path.

Optionally, the processing module is further configured to perform classification processing on the plurality of second navigation query requests in the navigation query set to obtain navigation query information corresponding to each candidate road, where the navigation query information is used to indicate the number of second navigation query requests corresponding to the candidate roads;

the processing module is further used for determining the current traffic flow of each candidate road according to navigation query information of the candidate roads.

Optionally, the apparatus further includes: a judging module;

the judging module is used for judging whether each candidate road has traffic abnormality according to the occurrence positions of a plurality of traffic abnormalities in the traffic abnormality set and the position information of a plurality of candidate roads;

the processing module is further used for recording an accident period with traffic abnormality when the traffic abnormality exists on the candidate road, and determining the first state information of the candidate road as an accident state;

and the processing module is further used for determining that the first state information of the candidate road is in a normal state when the candidate road is free from traffic abnormality.

Optionally, the acquiring module is further configured to acquire second navigation query requests sent by a plurality of autonomous vehicles in a driving state, where the navigation query requests include a geographic location and a query time;

the processing module is further configured to update a plurality of third navigation query requests in the navigation query set according to a plurality of second navigation query requests, where a query time of the third navigation query requests is earlier than a query time of the second navigation query requests;

the processing module is further configured to determine a first passing duration of the plurality of candidate roads according to geographic positions and query times corresponding to the plurality of second navigation query requests and geographic positions and query times corresponding to the plurality of third navigation query requests in the navigation query set, and update the passing duration in the passing duration set according to the first passing duration of the plurality of candidate roads;

The processing module is further configured to determine second status information of each candidate road according to a first passing duration of the plurality of candidate roads and a preset passing duration of the plurality of candidate roads, and update the first status information in the traffic anomaly set according to the second status information.

In a third aspect, the present application provides a traffic uncertainty-based path planning apparatus, comprising:

a memory;

a processor;

wherein the memory stores computer-executable instructions;

the processor executes the computer-executable instructions stored by the memory to implement the traffic uncertainty-based path planning method as described above in the first aspect and the various possible implementations of the first aspect.

In a fourth aspect, the present application provides a computer storage medium having stored thereon a computer program for execution by a processor to implement the traffic uncertainty based path planning method as described in the first aspect and the various possible implementations of the first aspect.

According to the traffic uncertainty-based path planning method, the first navigation inquiry request sent by the automatic driving vehicle is obtained, and the first navigation inquiry request comprises the following steps: navigation start position, navigation end position and request time; acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time; determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic view of a first scenario of a traffic uncertainty-based path planning method provided in the present application;

FIG. 2 is a flowchart I of a traffic uncertainty-based path planning method provided by the present application;

FIG. 3 is a second flowchart of a traffic uncertainty-based path planning method provided by the present application;

FIG. 4 is a third flowchart of a traffic uncertainty-based path planning method provided by the present application;

FIG. 5 (a) is a schematic diagram I of matching a planned path based on a navigation query request according to the present embodiment;

FIG. 5 (b) is a second schematic diagram of matching a planned path based on a navigation query request according to the present embodiment;

fig. 5 (c) is a schematic diagram III of matching a planned path based on a navigation query request provided in the present embodiment;

fig. 6 is a schematic structural diagram of a route planning device based on traffic uncertainty provided in the present application;

fig. 7 is a schematic structural diagram of a path planning device based on traffic uncertainty provided by the application.

Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.

In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

With the rapid development of urban traffic, it is difficult to find free space to accommodate more traffic infrastructure in developed cities, and therefore developing an effective navigation system is a low cost option to alleviate traffic congestion. In large cities where the road network is complex, coordination and management of vehicles is critical to reducing traffic congestion, which may also reduce driving time, pollution and noise. Developing an efficient navigation system is a low cost option to alleviate traffic congestion, as compared to the high cost of building more traffic infrastructure in developed cities. Today car navigation devices and navigation service providers can identify the shortest or fastest route, for example, based on current or historical traffic information of the vehicle. Each driver is unaware of the traffic conditions he will be facing along the shortest or fastest route and traffic jams may still occur because each vehicle is unaware of the routes of the other vehicles.

In order to solve the problems, the application provides a path planning method based on traffic uncertainty. Fig. 1 is a schematic view of a scenario of a traffic uncertainty-based path planning method provided in the present application. It should be noted that fig. 1 is only an example of an application scenario in which the traffic uncertainty-based path planning method of the present application may be applied, so as to help those skilled in the art understand the technical content of the present application, and does not mean that the embodiments of the present application may not be used in other devices, systems, environments, or scenarios.

When a traffic accident occurs on one side, setting the weight of the side as a large constant before the traffic accident ending time; that is, the pass duration through that side may be long. The ratio of the pre-planned schedule R to the navigation query U is small because the present embodiment provides a scenario in which the autopilot technology is mature and most vehicles follow the instructions of the navigation system.

As shown in fig. 1, the traffic uncertainty-based path planning method provided by the application is implemented through a time tableAnd evaluating the recent traffic condition of the edge. To consider assessing recent traffic conditions in the event of traffic uncertainty, a schedule b is maintained for edge E E _e . Two types of bar lines are used in the timetable. The first class represents the time period of the vehicle entering the edge e and the vehicle exiting the edge e; the second category refers to the start time and end time of a traffic accident. From the overlapping of these bar lines, the traffic condition of the corresponding edge at any point in time can be interpreted. The insertion and removal of the bar lines is performed by the proposed algorithm; the proposed algorithm cannot modify the striping of vehicles that do not follow the proposed algorithm instructions. Moreover, since the traffic accident cannot be predicted in advance, the bar line of the traffic accident is not listed in the timetable until after the traffic accident occurs.

As shown in fig. 1, when the second traffic accident bar is just inserted into the schedule, there are 5 vehicle bars and 2 traffic accident bars. As the number of vehicles increases, the length of the bar line increases. The first line of traffic accident does not overlap any line of vehicles, as the proposed algorithm has eliminated the overlap to reduce the pass duration. The lines of the vehicle 4 and the vehicle 5 overlap with the line of the traffic accident 2 because no traffic accident is observed when indicating the two vehicles. Once the traffic accident 2 is observed, a new path is arranged for two vehicles whose passing time length overlaps with the traffic accident 2 to reduce the passing time length.

The application provides a path planning method based on traffic uncertainty, which comprises the steps of obtaining a navigation inquiry request sent by an automatic driving vehicle, and obtaining a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request moment according to the request moment corresponding to the navigation inquiry request; determining a planning path matched with the navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormal set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Fig. 2 is a flowchart one of a traffic uncertainty-based path planning method according to an embodiment of the present application. As shown in fig. 2, the route planning method based on traffic uncertainty provided in this embodiment includes:

S101, acquiring a first navigation inquiry request sent by an automatic driving vehicle, wherein the first navigation inquiry request comprises: navigation start position, navigation end position, and request time.

The first navigation inquiry request is used for indicating a path planning of the automatic driving vehicle from a navigation starting position to a navigation ending position, and the request time is a corresponding time when the automatic driving vehicle sends the first navigation inquiry request.

S102, acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time.

And taking all possible roads between the navigation starting position and the navigation ending position in the first navigation inquiry request corresponding to the request time as candidate roads according to the request time, and acquiring a passing duration set of a plurality of candidate roads. The weighted directed graph g= (V, E) is formed by a set of top v= { V ₁ ,v ₂ ,…,v _|V| Sum of a set of edges e= { E ₁ ,e ₂ ,…,e _|E| }. The number of top points is |V| and the number of edges is |E|. The vertices represent intersections and the edges represent lanes of the road. For each edge e _i A weight is defined: w (w) _i ∈{x|x∈Q,x>0, calculated from the V-K velocity-density relationship as follows:

wherein the method comprises the steps ofThe number of vehicles on edge e when vehicle q enters e; s is(s) _e Is the speed limit of e; n is n _e The number of vehicles on e; l (L) _v Is the length of the vehicle; l (L) _e Is the length of the edge; g is the distance between two vehicles; k is a user-defined constant, s herein _e 、l _v G is predefined and K is set to 1. Calculating the traffic condition of the vehicle q as +.>The pass duration of pass edge e.

It can be appreciated that the navigation query set u= { U ₁ ,u ₂ ,…,u _|U| }. The number of queries is |U|. Query u _i The e U consists of three attributes:is u _i A requested navigation start position; />Is the destination, i.e. navigation end position Is request u _i Corresponding request time. A vehicle may request many queries, but it has at most one query at a time. By putting->And->Stored in vertices or edges, < >>And->May be anywhere on the map.

In order to realize the path planning based on the traffic uncertainty, traffic anomalies are taken into consideration, a traffic anomaly set corresponding to the request moment is acquired according to the request, and the traffic anomalies are marked to the side. Each edge e has a group of traffic anomaliesWherein->Is the traffic anomaly that occurs at edge e. The number of traffic anomalies on edge e is |A ^e | a. The invention relates to a method for producing a fibre-reinforced plastic composite. Traffic abnormality->Is a time period +.>Wherein->Is->Start time of- >Is->End time of (2). Multiple traffic anomalies may occur on one edge, but at most one traffic anomaly occurs at the same time. Using a= { a ¹ ,a ² ,…,a ^|E| All A is represented by } ^e Is a union of (a) and (b). A set of pre-planned schedules r= { R ₁ ,r ₂ ,…,r _|R| Used to demonstrate the functionality of a navigation algorithm that takes into account manually driven vehicles. Scheduling r of advance planning _i Consists of two attributes:>is the start time for traversing the next edge;is an ordered list of edges, which is a subset of E, with +.>Representation of->Is equal to r _i The edge that the associated vehicle passes by. />The number of edges in (a) is |r _i | a. The invention relates to a method for producing a fibre-reinforced plastic composite. One element of R is associated with a car.

And S103, determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path.

The planned path matched with the first navigation inquiry request is an optimal path planning based on the condition of traffic uncertainty, and the planned path is used for avoiding that an automatic driving vehicle enters a road with traffic accidents or other traffic abnormal conditions in a future period after the request time by planning a reasonable path so as to reduce the total passing time from a navigation starting position to a navigation ending position.

The output of the problem is a set of scheduling schedules s= { S ₁ ,s ₂ ,…,s _|U| (s is therein _i Representing query u _i E scheduling of U. Scheduling s _i Is an ordered list of edgess _i The element in (a) is queried by request u _i Is traversed in a sequential order. />Is a connection->Edge (request u) _i Is a position of (2); />Is a connection->Edge (u) _i Is the destination of (1); />Is s _i Is a number of sides of the pattern.

The goal of this path planning problem is to reduce the total pass duration of all schedules. Will ct(s) _i ) Defined as schedule s _i The calculation formula of the total passing time length is as follows:

wherein the method comprises the steps ofExpressed by query u _i Edge e of (2) _j Is calculated from the V-K velocity-density relationship equation. The total transit time of all schedules is therefore +.>

According to the traffic uncertainty-based path planning method, a first navigation inquiry request sent by an automatic driving vehicle is obtained, and the first navigation inquiry request comprises: navigation start position, navigation end position and request time; acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time; determining a planning path matched with the first navigation inquiry request according to the navigation starting position, the navigation ending position, the navigation inquiry set, the traffic abnormality set and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

Fig. 3 is a second flowchart of a traffic uncertainty-based path planning method according to an embodiment of the present application. The present embodiment is a detailed description of a route planning method based on traffic uncertainty based on the embodiment of fig. 2. As shown in fig. 3, the route planning method based on traffic uncertainty provided in this embodiment includes:

s201, acquiring a plurality of second navigation inquiry requests sent by the automatic driving vehicles in a driving state, wherein the second navigation inquiry requests comprise geographic positions and inquiry moments.

The query time of the second navigation query request is earlier than the query time of the first navigation query request, and the geographic position of the second navigation query request refers to the position of the automatic driving vehicle at the query time of the second navigation query request.

S202, updating a plurality of third navigation inquiry requests in the navigation inquiry set according to the plurality of second navigation inquiry requests.

The query time of the third navigation query request is earlier than the query time of the second navigation query request, and the third navigation query request comprises a geographic position and a query time. The reason why the update processing is performed on the third navigation inquiry request in the navigation inquiry set according to the second navigation inquiry request is that since the navigation inquiry set is maintained by the data structure of the queue, the inquiry request with the earlier inquiry time is updated by the inquiry request with the later inquiry time.

S203, determining first passing time lengths of the candidate roads according to the geographic positions and the query time corresponding to the second navigation query requests and the geographic positions and the query time corresponding to the third navigation query requests in the navigation query set, and updating the passing time lengths in the passing time length set according to the first passing time lengths of the candidate roads.

The geographic positions corresponding to the plurality of second navigation inquiry requests are, for example, the next intersection along the planned path corresponding to the third navigation inquiry request, and the relative distance of the plurality of candidate roads can be determined according to the geographic positions corresponding to the plurality of second navigation inquiry requests and the geographic positions corresponding to the plurality of third navigation inquiry requests, and the first passing duration of the plurality of candidate roads can be determined according to the relative distance of the plurality of candidate roads, the inquiry time corresponding to the plurality of second navigation inquiry requests and the inquiry time corresponding to the plurality of third navigation inquiry requests. And updating the passing time periods in the passing time period set according to a plurality of first passing time periods when the automatic driving vehicle passes through a plurality of candidate roads before the first navigation inquiry request, wherein the updated passing time periods refer to those passing time periods which are influenced by the first passing time periods in the passing time period set, such as the time period increase caused by traffic abnormality and change along with the first passing time period.

S204, determining second state information of each candidate road according to the first passing time length of the plurality of candidate roads and the preset passing time length of the plurality of candidate roads, and updating the first state information in the traffic anomaly set according to the second state information.

The preset passing time is, for example, a time required for automatically driving the vehicle to pass through the candidate road under an ideal traffic condition, and the first state information is used for indicating initial state information of the candidate road in a traffic anomaly set.

It can be understood that according to the first passing time length of the candidate roads, that is, the time length actually used when the vehicle is automatically driven to pass through the candidate roads under the traffic conditions corresponding to the second navigation inquiry request and the third navigation inquiry request, the second state information of each candidate road, that is, the latest state information of the candidate road, can be determined according to the first passing time length and the preset passing time length, and the first state information in the traffic anomaly set is updated according to the second state information.

S205, acquiring a first navigation inquiry request sent by an automatic driving vehicle, wherein the first navigation inquiry request comprises: navigation start position, navigation end position, and request time.

Step S205 is similar to step S101 described above, and will not be described again.

S206, acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time.

Step S206 is similar to step S102 described above, and will not be described again.

S207, determining a plurality of candidate paths according to the navigation starting position and the navigation ending position.

The navigation start position and the navigation end position corresponding to the first navigation inquiry request can be used as vertexes in the weighted directed graph corresponding to the road network, all edges which can be connected with the navigation start position and the navigation end position, namely candidate roads, are obtained from the weighted directed graph of the road network, a plurality of candidate roads are combined to obtain a limited set, and the set formed by the candidate roads is used as a plurality of candidate paths corresponding to the first navigation inquiry request.

S208, determining the current traffic flow of each candidate road according to the navigation query set.

Because each navigation inquiry request comprises the corresponding inquiry time and only one inquiry request is allowed to exist in one vehicle at the same inquiry time, one navigation inquiry request corresponds to one automatic driving vehicle, and therefore the current traffic flow of each candidate road can be determined according to the navigation inquiry set.

S209, according to the traffic abnormal set, determining first state information of each candidate road.

The traffic anomaly set comprises the occurrence positions of a plurality of traffic anomalies and the position information of a plurality of candidate roads, so that the first state information of each candidate road can be obtained according to the traffic anomaly set, and the first state information is used for indicating whether each candidate road is in a normal traffic state or not.

S210, determining a planning path matched with the first navigation inquiry request from the plurality of candidate paths according to the current traffic flow, the first state information of the plurality of candidate roads and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path.

The method comprises the steps that according to a passing duration set, the passing duration of each candidate road in a plurality of candidate paths can be obtained, the planned path matched with a first navigation inquiry request is not necessarily the path with the shortest total passing duration in the plurality of candidate paths, because the planned path determined from the plurality of candidate paths is the optimal path selected based on traffic uncertainty through the current traffic flow of each candidate road in the plurality of candidate paths, the first state information of each candidate road and the passing duration of each candidate road, and the planned path is controlled to run according to the planned path, so that the total passing duration of the automatic driving vehicle passing through the planned path is shortest.

According to the route planning method based on traffic uncertainty, a plurality of second navigation inquiry requests sent by the automatic driving vehicles in a driving state are obtained, and a plurality of third navigation inquiry requests in a navigation inquiry set are updated according to the plurality of second navigation inquiry requests; determining a first passing duration of a plurality of candidate roads according to geographic positions and query moments corresponding to a plurality of second navigation query requests and geographic positions and query moments corresponding to a plurality of third navigation query requests in a navigation query set, and updating the passing duration in the passing duration set according to the first passing duration; determining second state information of each candidate road according to the first passing time length of the candidate roads and the preset passing time length of the candidate roads, and updating the first state information in the traffic anomaly set according to the second state information; acquiring a first navigation inquiry request sent by an automatic driving vehicle, and acquiring a navigation inquiry set, a traffic abnormality set and a passing duration set of a plurality of candidate roads corresponding to the request time according to the request time; determining a plurality of candidate paths according to the navigation starting position and the navigation ending position; determining the current traffic flow of each candidate road according to the navigation query set; determining first state information of each candidate road according to the traffic anomaly set; determining a planning path matched with the first navigation inquiry request from a plurality of candidate paths according to the current traffic flow, the first state information of the candidate paths and the passing duration set, and controlling the automatic driving vehicle to run according to the planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

Fig. 4 is a flowchart III of a traffic uncertainty-based path planning method according to an embodiment of the present application. The present embodiment is a detailed description of determining a planned path matching the first navigation inquiry request according to the navigation start position, the navigation end position, the navigation inquiry set, the traffic anomaly set, and the passing duration set based on the embodiment of fig. 3. As shown in fig. 4, the route planning method based on traffic uncertainty provided in this embodiment includes:

s301, determining a plurality of candidate paths according to the navigation starting position and the navigation ending position.

Step S301 is similar to step S207 described above, and will not be described again.

S302, classifying the plurality of second navigation inquiry requests in the navigation inquiry set to obtain navigation inquiry information corresponding to each candidate road.

The second navigation inquiry requests refer to inquiry requests with inquiry time earlier than that of the first navigation inquiry requests, and the geographic position and inquiry time corresponding to each second navigation inquiry request are different, so that all second navigation inquiry requests in the navigation inquiry set are classified according to the geographic position and inquiry time, and navigation inquiry information corresponding to each candidate road, namely the information of the corresponding candidate road which is driven when a plurality of automatic driving vehicles send the corresponding second navigation inquiry requests, can be obtained.

S303, determining the current traffic flow of each candidate road according to navigation query information of a plurality of candidate roads.

The navigation inquiry information of the plurality of candidate roads is obtained according to the second navigation inquiry request, and the second navigation inquiry request is an inquiry request with the inquiry time earlier than that of the first navigation inquiry request, so that the information of the corresponding candidate roads driven when the plurality of automatic driving vehicles send the corresponding second navigation inquiry request can be obtained according to the navigation inquiry information of the plurality of candidate roads, and the current traffic flow of each candidate road is further obtained.

S304, judging whether each candidate road has traffic abnormality according to the occurrence positions of a plurality of traffic abnormalities in the traffic abnormality set and the position information of a plurality of candidate roads, and if so, executing step S305; if not, step S306 is performed.

The traffic abnormality determination method comprises the steps of determining the road range of all candidate roads according to the position information of the candidate roads, and determining whether the occurrence positions of the traffic abnormalities in the traffic abnormality set are located in the road range area of the candidate roads or not, so that the traffic abnormality condition of each candidate road can be determined.

It can be understood that when traffic abnormality exists in the candidate road, an abnormal accident period, namely, the starting time and the ending time of the accident, needs to be recorded, and the first state information of the corresponding candidate road is determined to be the accident state; and when the traffic abnormality does not exist in the candidate road, setting the first state information of the candidate road to be a normal state.

S305, recording an accident period in which traffic abnormality exists, and determining first state information of the candidate road as an accident state.

S306, determining that the first state information of the candidate road is in a normal state.

S307, updating the passing duration sets of the candidate roads according to the current traffic flow and the first state information of the candidate roads to obtain the target passing duration set of each candidate road.

When the current traffic flow exceeds a preset traffic flow threshold, and when the first state information of the candidate roads is an accident state, updating the passing time lengths of all the candidate roads in the candidate paths to obtain an updated target passing time length set.

S308, determining the target passing duration of each candidate path according to the target passing duration sets of the candidate roads.

The target passing duration refers to the total passing duration required by the automatic driving vehicle to pass through all candidate roads in the candidate path, namely the target passing duration refers to the sum of the passing durations of each candidate road after being updated.

S309, taking the candidate path with the shortest target passing duration in the plurality of candidate paths as the planning path.

The method comprises the steps of selecting a candidate path with the shortest target passing duration from a set of updated target passing durations, namely taking the optimal path of an automatic driving vehicle reaching a navigation ending position under the current traffic condition as a planning path of the automatic driving vehicle after considering the factors of traffic uncertainty, so as to improve the total passing duration of the vehicle and relieve traffic anomalies such as traffic jams.

Fig. 5 (a) is a schematic diagram one of matching a planned path based on a navigation query request according to the present embodiment, for indicating a matching result of path planning according to the navigation query request in the prior art, where traffic uncertainty is not considered; fig. 5 (b) is a schematic diagram two of matching a planned path based on a navigation query request provided in the present embodiment, which is used to indicate that when no traffic abnormality occurs, the path planning method based on traffic uncertainty provided in the present application will guide a vehicle to bypass a road where traffic jam is about to occur; fig. 5 (c) is a schematic diagram three of matching a planned path based on a navigation query request provided in this embodiment, which is used to indicate a method for determining a planned path matching a navigation query request from a plurality of candidate paths according to the path planning method based on traffic uncertainty provided in this application when traffic anomalies occur.

As shown in fig. 5 (a), 5 (b) and 5 (c), the road network has seven intersections (vertices) and eighteen directed edges (roads). The number next to an edge is the length of time that the edge was passed without traffic congestion. It will be appreciated that if the number of vehicles on the edge exceeds 10, traffic congestion may occur. In this case, there are 11 queries, ten queries from A to G are named Q _AG1 -Q _AG10 A query from B to G is named Q _BG 。Q _BG Starting at 00:05, while other queries start at 00:00. Suppose a traffic accident occurs at 00:15 between E and G.

As shown in fig. 5 (a), for the path planning method based on dynamic update in the prior art, no recent traffic state evaluation is required. First, the method suggests that the path A-C-E-G be Q _AG1 -Q _AG10 Since no traffic accident occurs at this time. The method is Q _BG Paths B-C-E-G are proposed because it is not known that traffic congestion can occur at edges between 00:20C and E. When Q is _AG1 -Q _AG10 When 00:15 reaches the point C, the method observes that the traffic accident occurs at the edge EG, and the traffic accident is Q _AG1 -Q _AG10 Paths C-D-F-G are proposed. When Q is _BG When the point C is reached, the method recommends Q _BG The C-E-F-G path is followed because of Q _BG Traffic congestion occurs at the entry side CD (number of vehicles exceeding 10). Thus Q _AG1 ～Q _AG10 The passage time period of (2) is 95 seconds,

Q _BG for 135 seconds.

Fig. 5 (b) and 5 (c) discuss the effects of the traffic uncertainty-based path planning method provided by the embodiments of the present application. Initially, the system is unaware that a traffic accident occurred at 00:15; thus, the proposed algorithm is Q _AG1 -Q _AG10 Suggesting paths A-C-E-G as Q _BG Paths B-D-F-G are proposed to avoid any potential traffic congestion. When Q is _AG1 -Q _AG10 When C is reached, as shown in FIG. 5 (C), the proposed algorithm observes the traffic accident and is Q _AG1 -Q _AG10 Paths C-D-F-G are proposed because of Q _AG1 -Q _AG10 Will not encounter Q on this path _BG . Compared to the results of fig. 5 (a), the method proposed by the embodiment of the present application may save 48% of the total pass duration for QBG.

According to the route planning method based on traffic uncertainty, a plurality of candidate routes are determined according to the navigation starting position and the navigation ending position; classifying a plurality of second navigation inquiry requests in the navigation inquiry set to obtain navigation inquiry information corresponding to each candidate road; determining the current traffic flow of each candidate road according to navigation query information of a plurality of candidate roads; judging whether each candidate road has traffic abnormality according to the occurrence positions of a plurality of traffic abnormalities in the traffic abnormality set and the position information of a plurality of candidate roads, recording an accident period when the traffic abnormality exists in the candidate roads, and determining the first state information of the candidate roads as an accident state; when traffic abnormality does not exist in the candidate road, determining that the first state information of the candidate road is in a normal state; updating the passing duration sets of the candidate roads according to the current traffic flow and the first state information of the candidate roads to obtain a target passing duration set of each candidate road; determining the target passing duration of each candidate path according to the target passing duration sets of the candidate roads; taking a candidate path with the shortest target passing duration in the plurality of candidate paths as a planning path; the method realizes that the traffic jam road section caused by the uncertainty of traffic is avoided in the path planning, thereby reducing the total passing time of the automatic driving vehicle.

Fig. 6 is a schematic structural diagram of a path planning device based on traffic uncertainty provided by the application.

As shown in fig. 6, the route planning device 400 based on traffic uncertainty provided in this embodiment includes:

the obtaining module 401 is configured to obtain a first navigation query request sent by an autopilot vehicle, where the first navigation query request includes: navigation start position, navigation end position and request time;

the obtaining module 401 is further configured to obtain, according to the request time, a navigation query set, a traffic anomaly set, and a set of passing durations of a plurality of candidate roads, which correspond to the request time;

the processing module 402 is configured to determine a planned path matching the first navigation inquiry request according to the navigation start position, the navigation end position, the navigation inquiry set, the traffic abnormality set, and the passing duration set, and control the autonomous vehicle to travel according to the planned path.

Optionally, the processing module 402 is further configured to determine a plurality of candidate paths according to the navigation start position and the navigation end position, where each candidate path includes at least one candidate road;

the processing module 402 is further configured to determine, according to the navigation query set, a current traffic flow of each candidate road;

The processing module 402 is further configured to determine first status information of each candidate road according to the traffic anomaly set, where the status information is used to indicate whether there is a traffic anomaly and an accident period when there is a traffic anomaly;

the processing module 402 is further configured to determine, from a plurality of candidate paths, the planned path that matches the first navigation query request according to the current traffic flow, first status information of the plurality of candidate roads, and a set of passing durations.

Optionally, the processing module 402 is further configured to update the set of passing durations of the plurality of candidate roads according to the current traffic flow and the first status information of the plurality of candidate roads, to obtain a set of target passing durations of each candidate road;

the processing module 402 is further configured to determine a target passing duration of each candidate path according to a target passing duration set of the plurality of candidate roads;

the processing module 402 is further configured to use a candidate path with a shortest target passing duration of the multiple candidate paths as the planned path.

Optionally, the processing module 402 is further configured to perform a classification process on the plurality of second navigation query requests in the navigation query set to obtain navigation query information corresponding to each candidate road, where the navigation query information is used to indicate the number of second navigation query requests corresponding to the candidate road;

The processing module 402 is further configured to determine a current traffic flow of each candidate road according to navigation query information of the plurality of candidate roads.

Optionally, the apparatus further includes: a judgment module 403;

the judging module 403 is configured to judge whether each candidate road has a traffic abnormality according to the occurrence positions of a plurality of traffic abnormalities in the traffic abnormality set and the position information of a plurality of candidate roads;

the processing module 402 is further configured to record an accident period when traffic abnormality exists on each candidate road, and determine that the first state information of the candidate road is an accident state;

the processing module 402 is further configured to determine that the first status information of each candidate road is a normal status when there is no traffic abnormality in the candidate road.

Optionally, the obtaining module 401 is further configured to obtain second navigation query requests sent by a plurality of autonomous vehicles in a driving state, where the navigation query requests include a geographic location and a query time;

the processing module 402 is further configured to update a plurality of third navigation query requests in the navigation query set according to a plurality of second navigation query requests, where a query time of the third navigation query requests is earlier than a query time of the second navigation query requests;

The processing module 402 is further configured to determine a first passing duration of the plurality of candidate roads according to the geographic locations and the query times corresponding to the plurality of second navigation query requests and the geographic locations and the query times corresponding to the plurality of third navigation query requests in the navigation query set, and update the passing durations in the passing duration set according to the first passing durations of the plurality of candidate roads;

the processing module 402 is further configured to determine second status information of each candidate road according to a first passing duration of the plurality of candidate roads and a preset passing duration of the plurality of candidate roads, and update the first status information in the traffic anomaly set according to the second status information.

Fig. 7 is a schematic structural diagram of a path planning device based on traffic uncertainty provided by the application. As shown in fig. 7, the present application provides a traffic uncertainty-based path planning apparatus 500, which includes: a receiver 501, a transmitter 502, a processor 503 and a memory 504.

A receiver 501 for receiving instructions and data;

a transmitter 502 for transmitting instructions and data;

Memory 504 for storing computer-executable instructions;

a processor 503 for executing computer-executable instructions stored in a memory 504 to implement the steps executed by the traffic uncertainty-based path planning method in the above-described embodiment. Reference may be made in particular to the description of the related embodiments of the method of path planning based on traffic uncertainty described above.

Alternatively, the memory 504 may be separate or integrated with the processor 503.

When the memory 504 is provided separately, the electronic device further comprises a bus for connecting the memory 504 and the processor 503.

The application also provides a computer storage medium, in which computer execution instructions are stored, which when executed by a processor, implement the traffic uncertainty-based path planning method as executed by the traffic uncertainty-based path planning device.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the 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. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method of path planning based on traffic uncertainty, the method comprising:

2. The method of claim 1, wherein the determining a planned path matching the first navigation query request based on the navigation start position, navigation end position, navigation query set, traffic anomaly set, and the pass duration set comprises:

3. The method of claim 2, wherein the determining the planned path from a plurality of candidate paths that matches the first navigation query request based on the current traffic flow, first status information for a plurality of candidate roads, and a set of pass durations comprises:

4. The method of claim 2, wherein determining the current traffic flow for each candidate link from the navigation query set comprises:

5. The method of claim 2, wherein determining the first status information for each candidate link based on the traffic anomaly set comprises:

6. The method of claim 1, wherein prior to the obtaining the first navigation query request sent by the autonomous vehicle, the method further comprises:

7. A traffic uncertainty-based path planning apparatus, the apparatus comprising:

8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,

the processing module is further configured to determine a plurality of candidate paths according to the navigation start position and the navigation end position, where each candidate path includes at least one candidate road;

9. A traffic uncertainty-based path planning apparatus, comprising:

a memory;

a processor;

wherein the memory stores computer-executable instructions;

the processor executes computer-executable instructions stored by the memory to implement the traffic uncertainty-based path planning method of any of claims 1-6.

10. A computer storage medium having stored therein computer executable instructions which when executed by a processor are for implementing the traffic uncertainty based path planning method according to any of claims 1-6.