CN113326641B - Path planning method and device, computer equipment and storage medium - Google Patents
Path planning method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113326641B CN113326641B CN202110887080.7A CN202110887080A CN113326641B CN 113326641 B CN113326641 B CN 113326641B CN 202110887080 A CN202110887080 A CN 202110887080A CN 113326641 B CN113326641 B CN 113326641B
- Authority
- CN
- China
- Prior art keywords
- target
- path
- route
- determining
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013439 planning Methods 0.000 title claims abstract description 97
- 238000000034 method Methods 0.000 title claims abstract description 96
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000004088 simulation Methods 0.000 claims abstract description 247
- 230000000875 corresponding effect Effects 0.000 claims description 296
- 238000004590 computer program Methods 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 58
- 230000008569 process Effects 0.000 description 31
- 238000005516 engineering process Methods 0.000 description 23
- 238000004364 calculation method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 235000019788 craving Nutrition 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000008080 stochastic effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a path planning method, a path planning device, computer equipment and a storage medium, which are applied to the technical field of traffic. According to the method and the device, after the target traffic event and the respective path of each vehicle are determined, the simulation environment is built based on the target traffic event, the travel of each vehicle on the corresponding path is simulated, whether the vehicle completely runs the corresponding path in the simulation time period or not can be determined, the corresponding first passing time length can be determined, when the first passing time lengths meet the target condition, each path of the simulation is output as a path planning result, and the accuracy of the computer equipment in the simulation can be improved.
Description
Technical Field
The present application relates to the field of traffic technologies, and in particular, to a method and an apparatus for path planning, a computer device, and a storage medium.
Background
With the development of computer technology and traffic technology, traffic simulation is becoming an important tool in traffic engineering and other related fields. The traffic simulation refers to the study of traffic behaviors by using simulation technology, and is a technology for tracking and describing the change of traffic motion along with time and space.
At present, in the traffic simulation technology, a driving process of a vehicle under a set path can be simulated by using simulation software, but various influence factors are likely to occur in actual travel, so that the vehicle cannot complete a normal travel according to the set path, for example, a traffic accident occurs on the set path, a part of road sections on the set path is closed, and the accuracy of a computer device in simulation is low.
Disclosure of Invention
The embodiment of the application provides a path planning method, a path planning device, computer equipment and a storage medium, and can improve the accuracy of the computer equipment in simulation.
In one aspect, a method for path planning is provided, where the method includes:
acquiring a target traffic event and a plurality of paths corresponding to a plurality of vehicles, wherein the paths are paths for simulating the running of the corresponding vehicles in the simulation;
simulating the travel of the vehicles on the paths under the simulation environment based on the target traffic incident to obtain a plurality of simulation travel data of the vehicles, wherein the simulation travel data comprises the positions of the corresponding vehicles at any time in the simulation time period;
acquiring a plurality of first passing time lengths corresponding to the plurality of paths based on the plurality of simulation travel data, wherein the first passing time lengths are used for representing the average running time length spent by each vehicle passing through the corresponding path in the simulation;
and if the plurality of first passing time lengths meet the target condition, outputting the plurality of paths in the simulation.
In one possible embodiment, the obtaining, based on the plurality of simulation trip data, a plurality of first passage durations corresponding to the plurality of routes includes:
for any one of the plurality of routes, if at least one first target vehicle runs from the starting point to the end point of the route, determining a first average running time spent by the at least one first target vehicle on the route based on the simulated running data of the at least one first target vehicle; determining the first average running time length as a first passing time length corresponding to any one route;
if any first target vehicle does not travel from the starting point to the end point of any route, determining the road section passing time length corresponding to each of a plurality of road sections in any route based on the simulated travel data of at least one second target vehicle passing through any route; and determining the sum of the passage time lengths of the road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route.
In one possible embodiment, the determining, based on the simulated driving data of at least one second target vehicle passing through the any route, a link transit time length corresponding to each of a plurality of links in the any route includes:
for any road section in any path, if at least one second target vehicle runs from the starting point to the end point of the any road section, determining a second average running time spent by the at least one second target vehicle on the any road section based on the simulated running data of the at least one second target vehicle;
and determining the second average driving time length as the road section passing time length corresponding to any road section.
In one possible embodiment, the determining, based on the simulated driving data of at least one second target vehicle passing through the any route, a link transit time length corresponding to each of a plurality of links in the any route includes:
for any road section in any path, if any second target vehicle does not pass through any road section, determining the maximum speed limit of any road section;
and dividing the road length of any road section by the maximum speed limit to obtain a numerical value, and determining the road section passing time corresponding to any road section.
In one possible embodiment, the determining the maximum speed limit of any road segment includes:
and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
In one possible embodiment, the determining, based on the simulated driving data of at least one second target vehicle passing through the any route, a link transit time length corresponding to each of a plurality of links in the any route includes:
for any road section in any route, if at least one second target vehicle passes through a partial road section in any road section, determining a third average driving time spent by the at least one second target vehicle on the partial road section based on the simulated driving data of the at least one second target vehicle;
for another part of the road sections, acquiring a first target numerical value obtained by dividing the road length of the another part of the road sections by the maximum speed limit of the another part of the road sections;
and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
In one possible embodiment, the determining the first average travel time period that the at least one first target vehicle spends on the any one route based on the simulated travel data of the at least one first target vehicle includes:
determining at least one first time and at least one second time based on the simulated driving data of the at least one first target vehicle, wherein the first time is the time when the first target vehicle drives to the starting point of any path, and the second time is the time when the first target vehicle drives to the end point of any path;
for any one first target vehicle in the at least one first target vehicle, acquiring a difference value between a corresponding first moment and a corresponding second moment;
and determining the average value of at least one difference value corresponding to the at least one first target vehicle as the first average running time length.
In one possible embodiment, the target condition includes that a relative interval parameter of the first passage time periods is smaller than a target threshold value, the relative interval parameter being used to characterize a difference between respective passage time periods of different vehicles travelling on the same route.
In one possible embodiment, the obtaining of the relative interval parameter includes:
acquiring a plurality of shortest passing time lengths corresponding to the plurality of paths respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding paths;
obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths;
and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
In one possible embodiment, the method further comprises:
if the first passing time lengths do not meet the target condition, updating a second passing time length corresponding to each of the paths based on the first passing time lengths to obtain a second updated passing time length, wherein the second passing time length is used for representing the estimated travelling time length of the driver on the corresponding path based on the historical travel;
and distributing a plurality of paths corresponding to the next simulation for the plurality of vehicles based on the plurality of updated second passage time lengths.
In a possible implementation manner, the updating, based on the first passage durations, the second passage durations corresponding to the paths, and obtaining a plurality of updated second passage durations includes:
multiplying a first coefficient by a first passing time corresponding to any one path in the paths to obtain a third target numerical value;
multiplying a second coefficient by a second pass duration corresponding to any one of the paths to obtain a fourth target value, wherein the sum of the first coefficient and the second coefficient is 1;
and adding the third target value and the fourth target value to obtain an updated second passing time corresponding to any one path.
In one possible embodiment, the allocating, based on the updated second passage durations, a plurality of paths corresponding to a next simulation to the plurality of vehicles includes:
for any vehicle in the plurality of vehicles, determining at least one candidate route corresponding to the any vehicle, wherein the starting point and the end point of the candidate route are respectively matched with the starting point and the end point of the journey of the any vehicle;
determining at least one selection probability of the at least one candidate route based on the at least one updated second travel time corresponding to the at least one candidate route, the selection probability being used to characterize a likelihood that the any vehicle is expected to select the corresponding candidate route to complete the trip;
and sampling the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
In one possible embodiment, the determining at least one selection probability of the at least one candidate path based on the at least one updated second passage duration corresponding to the at least one candidate path includes:
for any candidate path in the at least one candidate path, determining a utility parameter of the any candidate path based on an updated second passing duration corresponding to the any candidate path, wherein the utility parameter is negatively correlated with the corresponding updated second passing duration;
acquiring a third sum value between at least one utility parameter corresponding to each of the at least one candidate path;
and determining the ratio of the utility parameter of any candidate path in the third sum as the selection probability of any candidate path.
In a possible implementation manner, the determining, based on the updated second passage duration corresponding to the any candidate path, a utility parameter of the any candidate path includes:
and determining the reciprocal of the updated second passing time length corresponding to any candidate path as the utility parameter of any candidate path.
In one aspect, a path planning apparatus is provided, the apparatus including:
the first acquisition module is used for acquiring a target traffic event and a plurality of paths corresponding to a plurality of vehicles, wherein the paths are paths for simulating driving of the corresponding vehicles in the simulation;
the simulation module is used for simulating the travel of the vehicles on the paths under the simulation environment based on the target traffic incident to obtain a plurality of simulation travel data of the vehicles, wherein the simulation travel data comprise the positions of the corresponding vehicles at any time in the simulation time period;
a second obtaining module, configured to obtain, based on the plurality of simulation trip data, a plurality of first passage durations corresponding to the plurality of routes, where the first passage durations are used to represent average traveling durations spent by vehicles passing through the corresponding routes during the simulation;
and the output module is used for outputting the plurality of paths in the simulation if the plurality of first passing time lengths meet the target condition.
In one possible implementation, the second obtaining module includes:
a first determining unit, configured to determine, for any one of the multiple routes, if at least one first target vehicle travels from a start point to an end point of the any one route, a first average travel time period that the at least one first target vehicle spends on the any one route based on simulated travel data of the at least one first target vehicle; determining the first average running time length as a first passing time length corresponding to any one route;
the second determining unit is used for determining the road section passing time length corresponding to each of the plurality of road sections in any route based on the simulated driving data of at least one second target vehicle passing through any route if any first target vehicle does not travel from the starting point to the end point of any route; and determining the sum of the passage time lengths of the road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route.
In one possible implementation, the second determining unit is configured to:
for any road section in any path, if at least one second target vehicle runs from the starting point to the end point of the any road section, determining a second average running time spent by the at least one second target vehicle on the any road section based on the simulated running data of the at least one second target vehicle;
and determining the second average driving time length as the road section passing time length corresponding to any road section.
In one possible implementation, the second determining unit includes:
the first determining subunit is used for determining the maximum speed limit of any road section if any second target vehicle passes through the road section for any road section in any path;
and the second determining subunit is used for dividing the road length of any road section by the value obtained by the maximum speed limit to determine the road section passing time length corresponding to any road section.
In one possible implementation, the first determining subunit is configured to:
and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
In one possible implementation, the second determining unit is configured to:
for any road section in any route, if at least one second target vehicle passes through a partial road section in any road section, determining a third average driving time spent by the at least one second target vehicle on the partial road section based on the simulated driving data of the at least one second target vehicle;
for another part of the road sections, acquiring a first target numerical value obtained by dividing the road length of the another part of the road sections by the maximum speed limit of the another part of the road sections;
and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
In one possible implementation, the first determining unit is configured to:
determining at least one first time and at least one second time based on the simulated driving data of the at least one first target vehicle, wherein the first time is the time when the first target vehicle drives to the starting point of any path, and the second time is the time when the first target vehicle drives to the end point of any path;
for any one first target vehicle in the at least one first target vehicle, acquiring a difference value between a corresponding first moment and a corresponding second moment;
and determining the average value of at least one difference value corresponding to the at least one first target vehicle as the first average running time length.
In one possible embodiment, the target condition includes that a relative interval parameter of the first passage time periods is smaller than a target threshold value, the relative interval parameter being used to characterize a difference between respective passage time periods of different vehicles travelling on the same route.
In one possible embodiment, the obtaining of the relative interval parameter includes:
acquiring a plurality of shortest passing time lengths corresponding to the plurality of paths respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding paths;
obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths;
and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
In one possible embodiment, the apparatus further comprises:
the updating module is used for updating a plurality of second passing time lengths corresponding to the paths respectively based on the first passing time lengths if the first passing time lengths do not accord with the target condition to obtain a plurality of updated second passing time lengths, and the second passing time lengths are used for representing the predicted travelling time lengths spent on the corresponding paths determined by the driver based on historical travel;
and the distribution module is used for distributing a plurality of paths corresponding to the next simulation to the plurality of vehicles based on the plurality of updated second passage durations.
In one possible implementation, the update module is configured to:
multiplying a first coefficient by a first passing time corresponding to any one path in the paths to obtain a third target numerical value;
multiplying a second coefficient by a second pass duration corresponding to any one of the paths to obtain a fourth target value, wherein the sum of the first coefficient and the second coefficient is 1;
and adding the third target value and the fourth target value to obtain an updated second passing time corresponding to any one path.
In one possible embodiment, the allocation module comprises:
a second determination sub-module configured to determine, for any vehicle of the plurality of vehicles, at least one candidate route corresponding to the any vehicle, where a start point and an end point of the candidate route are matched with a travel start point and a travel end point of the any vehicle, respectively;
a third determining sub-module, configured to determine, based on at least one updated second travel duration corresponding to the at least one candidate route, at least one selection probability of the at least one candidate route, where the selection probability is used to characterize a likelihood that the any vehicle is expected to select the corresponding candidate route to complete the trip;
and the sampling submodule is used for sampling the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
In one possible implementation, the third determining sub-module includes:
a third determining unit, configured to determine, for any candidate path in the at least one candidate path, a utility parameter of the any candidate path based on an updated second transit time length corresponding to the any candidate path, where the utility parameter is negatively correlated with the corresponding updated second transit time length;
the obtaining unit is used for obtaining a third sum value between at least one utility parameter corresponding to each of the at least one candidate path;
and a fourth determining unit, configured to determine, as the selection probability of any candidate path, a ratio of the utility parameter of any candidate path to the third sum.
In one possible implementation, the third determining unit is configured to:
and determining the reciprocal of the updated second passing time length corresponding to any candidate path as the utility parameter of any candidate path.
In one aspect, a computer device is provided, the computer device comprising one or more processors and one or more memories, the one or more memories having stored therein at least one computer program that is loaded by the one or more processors and executed to implement a path planning method as in any one of the possible implementations described above.
In one aspect, a storage medium is provided, in which at least one computer program is stored, the at least one computer program being loaded and executed by a processor to implement the path planning method according to any one of the above possible implementations.
In one aspect, a computer program product or computer program is provided that includes one or more program codes stored in a computer readable storage medium. The one or more program codes can be read by one or more processors of the computer device from a computer-readable storage medium, and the one or more processors execute the one or more program codes, so that the computer device can execute the path planning method of any of the above-described possible embodiments.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
the method comprises the steps of establishing a simulation environment based on a target traffic event after the target traffic event and the respective path of each vehicle are determined, simulating the travel of each vehicle on the corresponding path, determining the corresponding first passage time length no matter whether the vehicle completely runs the corresponding path in a simulation time period, outputting each path of the simulation as a path planning result when each first passage time length meets the target condition, namely supporting the flexible setting of different traffic events in the path planning process, establishing different simulation environments based on different traffic events, ensuring that the path planning result can be suitable for the traffic event, accurately deducing the influence of the traffic event on path selection, and not influencing the calculation of the first passage time length even if the vehicle cannot complete the travel under the influence of the traffic event, therefore, higher universality is achieved when whether a path planning result is output or not is judged based on the first passing time length, and the accuracy of the computer equipment in simulation is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to be able to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of an implementation environment of a path planning method according to an embodiment of the present application;
fig. 2 is a flowchart of a path planning method according to an embodiment of the present application;
fig. 3 is a flowchart of a path planning method according to an embodiment of the present application;
fig. 4 is a flowchart for acquiring a first passage duration according to an embodiment of the present application;
fig. 5 is a flowchart of a path planning method according to an embodiment of the present application;
FIG. 6 is a flow chart of path allocation for next simulation according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a path planning method according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a traffic simulation system according to an embodiment of the present application;
FIG. 9 is a schematic diagram of an interface for inputting a target traffic event according to an embodiment of the present disclosure;
fig. 10 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The terms "first," "second," and the like in this application are used for distinguishing between similar items and items that have substantially the same function or similar functionality, and it should be understood that "first," "second," and "nth" do not have any logical or temporal dependency or limitation on the number or order of execution.
The term "at least one" in this application means one or more, and the meaning of "a plurality" means two or more, for example, a plurality of first locations means two or more first locations.
Hereinafter, terms related to the embodiments of the present application will be explained.
Intelligent Transportation System (ITS): the Intelligent Transportation System is a comprehensive Transportation System which effectively and comprehensively applies advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operational research, artificial intelligence and the like) to Transportation, service control and vehicle manufacturing, strengthens the relation among vehicles, roads and users, and thus forms a comprehensive Transportation System which ensures safety, improves efficiency, improves environment and saves energy.
Intelligent Vehicle-road Cooperative Systems (IVICS): the vehicle-road cooperative system is a development direction of an Intelligent Transportation System (ITS). The vehicle-road cooperative system adopts the advanced wireless communication, new generation internet and other technologies, implements vehicle-vehicle and vehicle-road dynamic real-time information interaction in all directions, develops vehicle active safety control and road cooperative management on the basis of full-time dynamic traffic information acquisition and fusion, fully realizes effective cooperation of human and vehicle roads, ensures traffic safety, improves traffic efficiency, and thus forms a safe, efficient and environment-friendly road traffic system.
Electronic map (Electronic map): the digital map is a map which is stored and consulted in a digital mode by utilizing a computer technology, is a system for map making and application, is a map generated by the control of an electronic computer, is a screen map based on a digital cartographic technology, and is a visual real map. The method for storing information in electronic map generally uses vector image storage, and the map scale can be enlarged, reduced or rotated without affecting the display effect. Being able to visualize on a computer screen is a fundamental feature of electronic maps. The electronic map is characterized by at least comprising the following components: 1) the display can be accessed quickly; 2) animation can be realized; 3) map elements can be displayed hierarchically; 4) the map is three-dimensional and dynamic by using the virtual reality technology, so that the user has a sense of being personally on the scene; 5) the electronic map can be transmitted to other places by using a data transmission technology; 6) automatic measurement of length, angle, area, etc. on the map can be achieved.
Traffic Simulation (Traffic Simulation): the traffic simulation refers to the study of traffic behaviors by using simulation technology, and is a technology for tracking and describing the change of traffic motion along with time and space. It contains stochastic properties, can be microscopic or macroscopic, and involves mathematical models that describe the real-time motion of the transportation system over a period of time. According to the difference of the traffic simulation model in description degree of the research object, the traffic simulation model can be divided into microscopic simulation, mesoscopic simulation and macroscopic simulation, wherein the microscopic simulation has the highest detail description degree on elements and behaviors of a traffic system, for example, the description of the microscopic traffic simulation model on the traffic flow is based on a single vehicle, and the microscopic behaviors of the vehicle such as car following, overtaking, lane change and the like on a road can be truly reflected; for example, the description of the traffic flow by the mesoscopic traffic simulation model is often a queue formed by a plurality of vehicles, can describe the inflow and outflow behaviors of the queue at road sections and nodes, and can also approximately describe behaviors of vehicles such as lane change in a simple manner; macroscopic simulations describe the elements and behavior of the traffic system to a lesser extent, for example, traffic flow may be described by some aggregate macroscopic models of flow, speed, density relationships, etc., but not for detailed behavior such as lane changes of vehicles.
Traffic control simulation deduction: according to the setting of the user, various traffic events (i.e. traffic control events) are simulated based on the traffic simulation technology, so that the influence of various traffic events on the traffic system is deduced, for example, the traffic events include but are not limited to: speed limit events, road closure events, etc.
Path: the route refers to each road passing from a starting position of the vehicle to a target position, the starting point of the route is also the starting position (i.e., the starting point) of the vehicle, and the end point of the route is also the target position (i.e., the destination) of the vehicle. In other words, the path is composed of a plurality of roads in order, and can be described by a sequence of road IDs (Identification), along which the vehicle in the simulation will travel.
Path allocation: also known as path planning. Before each simulation begins, a path needs to be assigned to each vehicle in the current simulation through a path assignment algorithm. Therefore, it can be considered that the purpose of the route assignment algorithm is to predict the route that the driver will select in the real world as accurately as possible.
Driver (Driver): because each vehicle and the corresponding driver have a one-to-one correspondence relationship, and the position of each vehicle can reflect the position of the driver corresponding to the vehicle, each vehicle in the simulation can be considered as one driver.
Passage Time (Travel Time): refers to the length of time it takes for a vehicle to travel to traverse a road or a route. The selection of the path in the path allocation algorithm needs to be carried out according to the transit time.
Dijkstra algorithm (Dijkstra): the Dijkstra algorithm was proposed by dickstra, a netherlands computer scientist, in 1959, and is therefore also called the dickstra algorithm. The method is a shortest path algorithm from one vertex to the rest of the vertices, and solves the shortest path problem in the weighted graph. The dijkstra algorithm is mainly characterized in that a greedy algorithm strategy is adopted from a starting point, and adjacent nodes of vertexes which are nearest to the starting point and have not been visited are traversed each time until the nodes are expanded to a terminal point.
Craving algorithm (Yen): the Yen algorithm is the algorithm proposed by Yen in 1971, named after its name. The Yen algorithm is used for obtaining the shortest multiple paths, adopts the deviation path algorithm thought in the recurrence method, and is suitable for the directed acyclic graph structure of the non-negative weight edge. Since the Dijkstra algorithm can only obtain one shortest path, if multiple short paths are desired or there are multiple shortest paths, the Dijkstra algorithm cannot obtain the shortest paths, and the Yen algorithm is needed. The Yen algorithm firstly utilizes Dijkstra algorithm to obtain a first shortest path Q (1) from a source node to a destination node, when K-1 short paths are obtained, a deviation path algorithm thought in a recurrence method is adopted, when Q (i + 1) is obtained, all nodes except the destination node on Q (1) are regarded as deviation nodes, the shortest path between each deviation node and the destination node is calculated, then the deviation nodes and paths from the source node to the deviation nodes on Q (1) are spliced together to form a candidate path, so that the shortest deviation path is obtained, and the rest is carried out until the shortest paths from K (K is more than or equal to 2) are obtained, wherein i is an integer more than or equal to 1.
The embodiment of the application relates to mesoscopic simulation in traffic simulation, a path planning module is provided in two types of traffic simulation software, namely VISSIM and SUMO, and the path planning module does not support the function of estimating the passing time of a path according to an incomplete stroke (namely, a vehicle does not complete the stroke during simulation), namely the path planning module ignores the possibility of all incomplete strokes, and in order to ensure that the passing time of the path can be accurately estimated, the simulation is required to run for a long time to acquire enough passing time information to plan the path. For example, to estimate the length of time that each vehicle will experience when departing between 8:00 and 9:00, then to ensure that some vehicles that depart later (e.g., 8:55 departures) complete their journey, the simulation would need to run for 8:00 to 10:00 for a total of two hours, and thus the computational efficiency of the computer device in the simulation would be low.
In addition, if the traffic event to be deduced per se prolongs the transit time, for example, the speed-limiting event prolongs the transit time of the road section of the speed-limiting road section, or some traffic events (such as road closing events) can make the journey passing through the closed road section unfinishable, which can sharply increase the difficulty of calculating the transit time.
In addition, the path planning module does not have the function of predicting the change of the path selection of the vehicle in N (N is more than or equal to 1) days after the traffic incident occurs, the calculation result of the path planning module represents the path selected after the driver completely knows the influence of the traffic incident on the transit time, and the driver usually selects the path according to the experience effect in the real world, so the calculation accuracy of the computer device in the simulation is low.
In view of this, the present application provides a path planning method, which can be used in a phase of performing path allocation on vehicles in traffic simulation, and the method iteratively uses an observation simulation to evaluate a result of the path allocation, and optimizes an allocated path according to a simulation result until a target condition is met, and finally determines a path allocated to each vehicle. The method can be used for predicting the influence caused by the traffic condition of the traffic event, and traffic management departments can also utilize the method to conduct control deduction on traffic.
On one hand, the estimation algorithm of the passing time length can estimate the total passing time length of a path corresponding to the whole travel by using the incomplete travel in the simulated time period, namely, if the passing time length of each vehicle which starts between 8:00 and 9:00 needs to be estimated, the simulation between 8:00 and 9:00 only needs to be operated, the simulation with longer time does not need to be operated to ensure the completion of the travel of each vehicle, the required simulation time length can be reduced, and the calculation efficiency is greatly improved.
On the other hand, the influence of the management and control of the traffic incident on the passing time (namely the second passing time) perceived by the driver is estimated by using a weighted average method, so that the description of the change of the route every N days after the traffic incident occurs can be realized, the description that the driver does not know the relevant information when the traffic incident occurs right away can be better described, the driver completely knows the relevant information after the traffic incident occurs for several days, and the change of the route selected by the driver in the whole process can reflect the influence of the traffic incident on the route selection of the driver.
Hereinafter, an environment architecture according to an embodiment of the present application will be described.
Fig. 1 is a schematic diagram of an implementation environment of a path planning method according to an embodiment of the present application. Referring to fig. 1, the embodiment includes: a vehicle 101 and a computer device 102.
The vehicle 101 is configured to collect drive test data during actual driving and transmit the drive test data to the computer device 102. Optionally, the Vehicle 101 is equipped with functional modules such as an on-board sensor, a positioning component, a camera component, a controller, a data processor, and an automatic driving system, and the functional modules can implement exchange and sharing of traffic participants by modern Mobile communication and network technologies such as car networking, 5G (5 th Generation Mobile Networks, fifth Generation Mobile communication technology), and V2X (Vehicle To X, wireless communication technology for vehicles), so as To have functions of sensing perception, decision planning, control execution, and the like in a complex environment.
Optionally, the type of the vehicle 101 includes a conventional automobile, a smart car, an unmanned vehicle, an electric vehicle, a bicycle, a motorcycle, etc., and the vehicle 101 may be operated by a driver by manual driving or may be driven by an automatic driving system to realize unmanned driving.
The vehicle 101 and the computer device 102 can be directly or indirectly connected through wired or wireless communication, for example, the vehicle 101 and the computer device 102 are wirelessly connected through a vehicle network, and the embodiment of the present application is not limited herein.
The computer device 102 is configured to perform a traffic control simulation deduction on one or more traffic events by applying a traffic simulation technique based on drive test data collected by the vehicle 101 or raw data set by a technician. Optionally, the computer device 102 comprises at least one of a server, a plurality of servers, a cloud computing platform, or a virtualization center. Optionally, the computer device 102 undertakes primary computational work and the vehicle 101 undertakes secondary computational work; alternatively, the computer device 102 undertakes secondary computing work and the vehicle 101 undertakes primary computing work; alternatively, the vehicle 101 and the computer device 102 may both employ a distributed computing architecture for coordinated computing.
Optionally, the computer device 102 is an independent physical server, or a server cluster or distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, web service, cloud communication, middleware service, domain name service, security service, CDN (Content Delivery Network), big data and artificial intelligence platform, and the like.
Those skilled in the art will appreciate that the number of vehicles 101 may be greater or fewer. For example, the number of the vehicles 101 may be only one, or the number of the vehicles 101 may be several tens or hundreds, or more. The number of vehicles 101 and the type of equipment are not limited in the embodiment of the present application.
Fig. 2 is a flowchart of a path planning method according to an embodiment of the present application. Referring to fig. 2, the embodiment is applied to a computer apparatus, and includes the following steps.
201. The computer equipment acquires a target traffic event and a plurality of paths corresponding to a plurality of vehicles, wherein the paths are paths which correspond to the vehicles in the simulation and are used for simulating the running.
In some embodiments, the computer device obtains vehicle trip information and a target traffic event, wherein the vehicle trip information is used for describing trip related information of each vehicle, and the target traffic event is used for describing a traffic event to be deduced in the simulation, for example, the target traffic event may be a speed limit event, a road closure event and the like.
Wherein the vehicle trip information at least includes: the vehicle trip information may be drive test data extracted from real traffic sensors of the plurality of vehicles, or may be set data customized by a user, and the source of the vehicle trip information is not specifically limited in the embodiments of the present application.
Wherein the target traffic event comprises at least: the target traffic event can be set individually by a user, and the source of the target traffic event is not specifically limited in the embodiment of the application.
In some embodiments, the computer device obtains an end-point pair composed of a starting position and a target position of a travel of each vehicle based on vehicle travel information input by a user, deduplicates a plurality of end-point pairs of respective travels of the plurality of vehicles to obtain at least one end-point pair different from each other, and then calls a path planning algorithm to predict at least one candidate path for each end-point pair on the basis of an electronic map. Optionally, the path planning algorithm may be Dijkstra algorithm, which may calculate the shortest candidate path, or the path planning algorithm may also be Yen algorithm, which may calculate the shortest candidate paths, or the path planning algorithm may also be Astar algorithm (i.e., a × algorithm, a heuristic search algorithm), which may also be used to calculate the shortest candidate path. In some embodiments, since the candidate route from the travel start point to the travel end point is constituted by a plurality of links, the corresponding candidate route may be represented by a sequence of IDs of the plurality of links in the traveling order of the vehicle.
For example, a greedy algorithm strategy is adopted from a starting position, namely a trip starting point, and the shortest candidate path between the current starting point and the current ending point pair can be output after traversing the adjacent nodes of the vertex which is closest to the starting point and has not been visited until the adjacent nodes extend to the ending point.
Schematically, for any starting and ending point pair, a Yen algorithm is adopted to calculate the shortest K (K is more than or equal to 2) candidate paths, firstly, a Dijkstra algorithm is adopted to obtain the shortest 1 st candidate path Q (1) from a starting position, namely a starting point of a travel to a target position, namely an end point of the travel, when the next K-1 candidate paths are obtained, the concept of the off-path algorithm in the recurrence method is adopted, for example, when Q (i + 1) is obtained, wherein i is an integer greater than or equal to 1, all nodes except the end of travel on Q (1) are regarded as deviated nodes, and the shortest path between each deviated node to the end of travel is calculated, then the path from the travel starting point to the deviated node on the Q (1) is spliced together to form a candidate path, and obtaining the shortest deviation path by analogy until obtaining the shortest K candidate paths.
Note that the "node" referred to in the Dijkstra algorithm or the Yen algorithm refers to a position point including a route start point, a route end point, a link node, or other nodes in the electronic map, where the link node refers to a start point of any link, an end point of any link, an intersection (such as an intersection, a t-junction, or the like) between any two different links, and the other node refers to a position point such as a building or a building group that can be parked on the electronic map, and this is not particularly limited in the embodiment of the present application.
In some embodiments, when predicting at least one candidate route for each starting and ending point pair based on the route planning algorithm, a target traffic event input by a user may be further considered, and if the target traffic event is a road closure event, when generating a candidate route based on the route planning algorithm, all closed sections indicated by the road closure event may be removed to ensure that no vehicle passes through the closed sections in subsequent simulation.
In some embodiments, the above operation may not be performed, and if the influence of the road closure event is not considered when the candidate path is generated based on the path planning algorithm, if a vehicle needs to pass through the closed road section in the subsequent simulation, the condition that the vehicle stops at the starting point of the closed road section is simulated.
In some embodiments, if the simulation is the first simulation, after at least one candidate path is obtained for each starting and ending point pair, for any vehicle matched with the current starting and ending point pair, one path may be randomly selected from the at least one candidate path as a path corresponding to the vehicle, or weighted random sampling may be performed from the at least one candidate path according to the selection frequency of the driver for each candidate path in the real world, so as to obtain a path corresponding to the vehicle.
In some embodiments, if the simulation is not the first simulation, for any vehicle matching the current starting and ending point pair, based on the selection probability output for each path in the previous simulation, weighted random sampling may be performed on multiple paths corresponding to the current starting and ending point pair in the previous simulation, so as to obtain a path corresponding to the vehicle in the current simulation.
Note that the meaning of "match" in "any vehicle that matches the current starting and ending point pair means: the vehicle has a trip start point that is the same as the start point of the start-stop point pair and a trip end point that is the same as the end point of the start-stop point pair.
202. And the computer equipment simulates the travel of the vehicles on the paths under the simulation environment based on the target traffic incident to obtain a plurality of simulation travel data of the vehicles, wherein the simulation travel data comprises the positions of the corresponding vehicles at any time in the simulation time period.
In some embodiments, for each vehicle of the plurality of vehicles, the computer device may simulate the own vehicle to depart from the trip start point at the corresponding departure time and to travel according to the corresponding path until the travel is to the trip end point or the simulation is finished, using the simulation software or a preset traffic flow model. The simulation process is performed based on a simulation environment of a target traffic event, for example, when the target traffic event is a speed limit event, the speed of a vehicle passing through a speed limit road section needs to be less than or equal to the constraint of the speed limit event, for example, when the target traffic event is a road closure event, if the closed road section is removed when the candidate route is generated in step 201, it can be ensured that no vehicle passes through the speed limit road section, and if the closed road section is not removed when the candidate route is generated in step 201, all vehicles passing through the speed limit road section need to be controlled to stop at the starting point of the closed road section until the simulation is finished.
In the embodiment of the application, after the departure time period of the vehicle is set, the simulation does not need to be stopped after waiting for all or most of the trips of the vehicle departing in the departure time period to be ended, but the simulation can be operated only in the departure time period, namely, the simulation is ended at the same time when the departure time period is ended, for example, if the departure time period is 8:00 to 9:00, the running of each vehicle in the range of 8:00 to 9:00 only needs to be simulated, the simulation operation does not need to be prolonged to 8:00 to 10:00 to wait for all the trips to be ended, and therefore the calculation efficiency of the computer device in the simulation can be improved.
After the simulation is finished, the computer device can acquire the simulation travel data of each vehicle according to the simulation result, and the simulation travel data can comprise a plurality of timestamps and a plurality of position coordinates which are respectively in one-to-one correspondence with the timestamps, so that the position of the vehicle under any timestamp can be represented.
203. And the computer equipment acquires a plurality of first passing time lengths corresponding to the plurality of paths based on the plurality of simulation travel data, wherein the first passing time lengths are used for representing the average running time length spent by each vehicle passing through the corresponding path in the simulation midway.
In some embodiments, for each of the multiple routes, the first passage duration corresponding to the route may be obtained according to the simulation journey data of each vehicle passing through the route in the simulation, and optionally, the following situations are discussed.
1) If all the road sections of the route completely traveled by the vehicles exist, the average traveling time length of each vehicle can be directly used as the first passing time length corresponding to the route.
2) Under the condition that the condition 1) is not satisfied, the first passing time length of the route can be regarded as the sum value of the passage time lengths of the road sections contained in the route, so that the passage time length of each road section is calculated independently for each road section. For each road segment, there are three cases: 2a) if the vehicles completely drive through the road section, the average driving time of each vehicle can be directly used as the road section passing time corresponding to the road section; 2b) under the condition that the condition 2 a) is not met, if vehicles pass through a part of road sections in the road section, for the part of road sections, the average running time of each vehicle is used as a part of value of the road section passing time, for another part of road sections, the road length is directly divided by the maximum speed limit to be used as another part of value of the road section passing time, and the two are added to obtain the road section passing time corresponding to the road section; 2c) under the condition that the conditions 2 a) and 2 b) are not met, namely no vehicle passes through the road section, the road section passing time length is directly obtained by dividing the road length by the maximum speed limit.
Various possible calculation manners of the first transit time duration will be described in detail in the next embodiment, and are not described herein.
In the process, the corresponding first passing time length is obtained for each route, and even for a vehicle which does not complete all routes, the first passing time length of each route through which an incomplete route passes at present can be calculated by using the simulation route data of the vehicle, so that the limitation that the route is required to be simulated for a longer time to avoid the incomplete route during route planning is broken, and the calculation efficiency of computer equipment during simulation is improved.
204. And if the first passing time lengths meet the target condition, the computer equipment outputs the paths in the simulation.
In some embodiments, the computer device may obtain the relative interval parameters of the plurality of first passage durations when determining whether the plurality of first passage durations meet the target condition; and if the relative interval parameter of the first passing time lengths is smaller than a target threshold value, determining that the first passing time lengths meet the target condition, wherein the relative interval parameter is used for representing the difference between the respective passing time lengths of different vehicles running on the same path.
In other words, the target condition is that relative interval parameters of a plurality of first passing time periods corresponding to the plurality of paths are smaller than a target threshold. When the relative interval parameter is smaller than the target threshold, the difference between the passage time lengths spent by different vehicles driving on the same path is considered to be small, namely the balance state is reached, so that the first passage time lengths are determined to meet the target condition, the paths in the simulation are output, and the target threshold is any value larger than or equal to 0.
It should be noted that the manner of obtaining the relative interval parameter will be described in the following embodiments, and details are not described in the embodiments of the present application.
In the process, the relative interval parameters are obtained, when the relative interval parameters are smaller than the target threshold value, the first passing time lengths are determined to meet the target condition, the paths of the simulation are output, the iterative simulation of the path planning is stopped under the condition that the difference between the passing time lengths spent by different vehicles in running on the same path reaches the equilibrium state, and the paths determined in the simulation are output, so that the accuracy of the path planning can be improved.
All the above optional technical solutions can be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
The method provided by the embodiment of the application establishes the simulation environment based on the target traffic event after determining the target traffic event and the respective path of each vehicle, simulates the travel of each vehicle on the corresponding path, can determine the corresponding first passing time regardless of whether the vehicle completely runs the corresponding path in the simulation time period, outputs each path of the simulation as a path planning result when each first passing time meets the target condition, namely supports the flexible setting of different traffic events in the path planning process, establishes different simulation environments based on different traffic events, ensures that the path planning result can adapt to the traffic event, can accurately deduce the influence of the traffic event on the path selection, and cannot complete the travel even if the vehicle is influenced by the traffic event, the calculation of the first passing time length still cannot be influenced, so that the method has higher universality when judging whether to output a path planning result or not based on the first passing time length, and the accuracy of the computer equipment in simulation is improved.
Fig. 3 is a flowchart of a path planning method according to an embodiment of the present application. Referring to fig. 3, the embodiment is applied to a computer device, and is described by taking the computer device as a server as an example, and the embodiment includes the following steps.
301. The server acquires the vehicle journey information and the target traffic event input by the user.
In some embodiments, the computer device obtains vehicle trip information and a target traffic event, wherein the vehicle trip information is used for describing trip related information of each vehicle, and the target traffic event is used for describing a traffic event to be deduced in the simulation, for example, the target traffic event may be a speed limit event, a road closure event and the like.
Wherein the vehicle trip information at least includes: the vehicle trip information may be drive test data extracted from real traffic sensors of the plurality of vehicles, or may be set data customized by a user, and the source of the vehicle trip information is not specifically limited in the embodiments of the present application.
Wherein the target traffic event comprises at least: the target traffic event can be set individually by a user, and the source of the target traffic event is not specifically limited in the embodiment of the application.
302. And the server acquires a plurality of paths corresponding to a plurality of vehicles participating in the simulation on the basis of the vehicle travel information, wherein the paths are paths corresponding to the vehicles in the simulation for simulating the running.
In some embodiments, the computer device obtains an end-point pair composed of a starting position and a target position of a travel of each vehicle based on vehicle travel information input by a user, deduplicates a plurality of end-point pairs of respective travels of the plurality of vehicles to obtain at least one end-point pair different from each other, and then calls a path planning algorithm to predict at least one candidate path for each end-point pair on the basis of an electronic map. Optionally, the path planning algorithm may be Dijkstra algorithm, which may calculate the shortest candidate path, or the path planning algorithm may also be Yen algorithm, which may calculate the shortest candidate paths, or the path planning algorithm may also be Astar algorithm (i.e., a × algorithm, a heuristic search algorithm), which may also be used to calculate the shortest candidate path. In some embodiments, since the candidate route from the travel start point to the travel end point is constituted by a plurality of links, the corresponding candidate route may be represented by a sequence of IDs of the plurality of links in the traveling order of the vehicle.
For example, a greedy algorithm strategy is adopted from a starting position, namely a trip starting point, and the shortest candidate path between the current starting point and the current ending point pair can be output after traversing the adjacent nodes of the vertex which is closest to the starting point and has not been visited until the adjacent nodes extend to the ending point.
Schematically, for any starting and ending point pair, a Yen algorithm is adopted to calculate the shortest K (K is more than or equal to 2) candidate paths, firstly, a Dijkstra algorithm is adopted to obtain the shortest 1 st candidate path Q (1) from a starting position, namely a starting point of a travel to a target position, namely an end point of the travel, when the next K-1 candidate paths are obtained, the concept of the off-path algorithm in the recurrence method is adopted, for example, when Q (i + 1) is obtained, wherein i is an integer greater than or equal to 1, all nodes except the end of travel on Q (1) are regarded as deviated nodes, and the shortest path between each deviated node to the end of travel is calculated, then the path from the travel starting point to the deviated node on the Q (1) is spliced together to form a candidate path, and obtaining the shortest deviation path by analogy until obtaining the shortest K candidate paths.
Note that the "node" referred to in the Dijkstra algorithm or the Yen algorithm refers to a position point including a route start point, a route end point, a link node, or other nodes in the electronic map, where the link node refers to a start point of any link, an end point of any link, an intersection (such as an intersection, a t-junction, or the like) between any two different links, and the other node refers to a position point such as a building or a building group that can be parked on the electronic map, and this is not particularly limited in the embodiment of the present application.
In some embodiments, when predicting at least one candidate route for each starting and ending point pair based on the route planning algorithm, a target traffic event input by a user may be further considered, and if the target traffic event is a road closure event, when generating a candidate route based on the route planning algorithm, all closed sections indicated by the road closure event may be removed to ensure that no vehicle passes through the closed sections in subsequent simulation.
In some embodiments, the above operation may not be performed, and if the influence of the road closure event is not considered when the candidate path is generated based on the path planning algorithm, if a vehicle needs to pass through the closed road section in the subsequent simulation, the condition that the vehicle stops at the starting point of the closed road section is simulated.
In some embodiments, if the simulation is the first simulation, after at least one candidate path is obtained for each starting and ending point pair, for any vehicle matched with the current starting and ending point pair, one path may be randomly selected from the at least one candidate path as a path corresponding to the vehicle, or weighted random sampling may be performed from the at least one candidate path according to the selection frequency of the driver for each candidate path in the real world, so as to obtain a path corresponding to the vehicle.
In some embodiments, if the simulation is not the first simulation, for any vehicle matching the current starting and ending point pair, based on the selection probability output for each path in the previous simulation, weighted random sampling may be performed on multiple paths corresponding to the current starting and ending point pair in the previous simulation, so as to obtain a path corresponding to the vehicle in the current simulation.
Note that the meaning of "match" in "any vehicle that matches the current starting and ending point pair means: the vehicle has a trip start point that is the same as the start point of the start-stop point pair and a trip end point that is the same as the end point of the start-stop point pair.
303. And the server simulates the routes of the vehicles on the multiple paths under the simulation environment based on the target traffic incident to obtain multiple simulation route data of the vehicles, wherein the simulation route data comprises the positions of the corresponding vehicles at any time in the time period of the current simulation.
Step 303 is similar to step 202, and is not described herein.
304. The server obtains a plurality of first passing time lengths corresponding to the paths based on the plurality of simulation travel data, wherein the first passing time lengths are used for representing the average running time length spent by each vehicle passing through the corresponding path in the simulation.
In the process, the corresponding first passing time length is obtained for each route, and even for a vehicle which does not complete all routes, the first passing time length of each route through which an incomplete route passes at present can be calculated by using the simulation route data of the vehicle, so that the limitation that the route is required to be simulated for a longer time to avoid the incomplete route during route planning is broken, and the calculation efficiency of computer equipment during simulation is improved.
Fig. 4 is a flowchart for acquiring a first passage time according to an embodiment of the present application, and as shown in fig. 4, a process of acquiring the first passage time corresponding to any one of the routes will be described below, and details will be described below.
3041. If at least one first target vehicle runs from the starting point to the end point of any one route, the server determines a first average running time length spent by the at least one first target vehicle on any one route based on the simulated running data of the at least one first target vehicle; and determining the first average running time length as a first passing time length corresponding to any one route.
In the above process, if there is at least one first target vehicle traveling from the start point to the end point of the any route, which means that there is at least one first target vehicle completely passing through each road segment in the any route, the first average traveling time period of all the complete trips may be directly used as the first passing time period of the any route.
In some embodiments, the server may perform the following operation when acquiring the first average travel time.
3041A, the server determines at least one first time and at least one second time based on the simulated travel data of the at least one first target vehicle.
The first target vehicle refers to a vehicle that completely travels from a starting point of any one route to an end point of the first route, and it should be noted that if a certain vehicle only passes through a certain road segment in any one route, the vehicle does not belong to the first target vehicle (but belongs to the second target vehicle).
The first time is a time when the first target vehicle travels to the starting point of the any route, that is, the first time represents a starting time when the first target vehicle travels into the any route; the second time is a time when the first target vehicle travels to the end point of the any one route, that is, the second time represents a departure time when the first target vehicle exits the any one route.
In some embodiments, the server may select each vehicle corresponding to the arbitrary route from the plurality of vehicles as the at least one first target vehicle. Next, for each first target vehicle, since the simulated travel data of the first target vehicle is composed of a series of time stamps and a corresponding series of position coordinates, it is possible to select a first position coordinate closest to the start point of any one of the routes from the series of position coordinates, determine a time stamp corresponding to the first position coordinate as a first time, select a second position coordinate closest to the end point of any one of the routes from the series of position coordinates, and determine a time stamp corresponding to the second position coordinate as a second time. The server can determine a corresponding first time and second time for each first target vehicle, and the above operations are repeatedly performed, so that at least one first time and at least one second time can be determined for the at least one first target vehicle.
3041B, the server obtains a difference between the corresponding first time and second time for any one of the at least one first target vehicle.
In the process, the server obtains, for each first target vehicle, a difference value between a first time and a second time corresponding to the first target vehicle, and repeatedly executes the above operations, so that for the at least one first target vehicle, the corresponding at least one difference value can be determined.
3041C, the server determines an average of at least one difference corresponding to the at least one first target vehicle as the first average length of travel.
In some embodiments, the server averages at least one difference corresponding to the at least one first target vehicle, and determines the average as the first average travel time period of the any one route.
In the above steps 3041A-3041C, a possible implementation of how to determine the first average traveling time period of any one route is shown, and optionally, when the first average traveling time period of any one route is obtained, since each first target vehicle adopts any one route as the route for traveling in simulation, the departure time of each first target vehicle may be directly obtained as the first time of each first target vehicle, the arrival time of each first target vehicle may be obtained as the second time of each first target vehicle, and the average value of the difference between the first time and the second time of each first target vehicle may be further used as the first average traveling time period.
In some embodiments, after obtaining the first average travel time period of any one route, the first average travel time period of any one route may be determined as the first passage time period of any one route, so that the first passage time period may reflect an average travel time period of each vehicle passing through any one route completely.
3042. If any first target vehicle does not travel from the starting point to the end point of any route, the server determines the road section passing time length corresponding to each of the plurality of road sections in any route based on the simulation travel data of at least one second target vehicle passing through any route; and determining the sum of the passage time lengths of the road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route.
The second target vehicle refers to a vehicle which does not travel completely from the starting point of any route to the end point of the first route but passes through a part of road section in any route, that is, the traveling route of the second target vehicle in the simulation has a superposed part with any route but does not belong to the first target vehicle, optionally, the superposed part may be one or more road sections in any route or a part of road section in any route, and the embodiment of the present application does not specifically limit the superposed part.
In the above process, if no vehicle completely passes through any route, it indicates that no vehicle runs from the starting point of any route to the end point of any route in the simulation, that is, no vehicle in the plurality of vehicles belongs to the first target vehicle, at this time, the server cannot calculate the first passing time length according to the first average running time length of each first target vehicle. In this case, the server may calculate respective passage time lengths of the road segments in a segmented manner for the plurality of road segments in the any route, and add the passage time lengths of the road segments to obtain the first passage time length of the any route.
In the following, how to obtain the link transit time of any link in any route will be described for any link in any route, and the following cases can be classified for discussion.
3042A, if there is at least one second target vehicle traveling from the start point to the end point of the any road segment, the server determines a second average traveling time period spent by the at least one second target vehicle on the any road segment based on the simulated traveling data of the at least one second target vehicle; and determining the second average driving time length as the road section passing time length corresponding to any road section.
In some embodiments, if there is at least one second target vehicle traveling from the start point to the end point of the any road segment, which represents that there is at least one second target vehicle completely passing through the any road segment in the any route, at this time, the second average traveling time length of the at least one second target vehicle on the any road segment may be directly taken as the road segment passing time length of the any road segment.
In some embodiments, the server may determine, based on the simulated driving data of the at least one second target vehicle, at least one third time and at least one fourth time, where the third time is a time when the second target vehicle drives to the start of the any road segment, i.e., represents a start time when the second target vehicle drives into the any road segment, and the fourth time is a time when the second target vehicle drives to the end of the any road segment, i.e., represents a departure time when the second target vehicle drives out of the any road segment.
In some embodiments, the server may select, from the plurality of vehicles, each vehicle in the road ID sequence of the corresponding path that includes the road ID of the any road segment as the at least one second target vehicle, for example, the road ID of the any road segment is 0025, and then the server may traverse the road ID sequence of the path corresponding to each vehicle in the plurality of vehicles and determine, as the at least one second target vehicle, each vehicle corresponding to the path including the "0025" element in the road ID sequence.
In some embodiments, after the at least one second target vehicle is determined, for each second target vehicle, since the simulated travel data of the second target vehicle is composed of a series of time stamps and a corresponding series of position coordinates, a third position coordinate closest to the start point of any one road segment may be selected from the series of position coordinates, a time stamp corresponding to the third position coordinate may be determined as the third time, and similarly, a fourth position coordinate closest to the end point of any one road segment may be selected from the series of position coordinates, and a time stamp corresponding to the fourth position coordinate may be determined as the fourth time. The server can determine a corresponding third time and a corresponding fourth time for each second target vehicle, and the above operations are repeatedly performed, so that at least one third time and at least one fourth time can be determined for the at least one second target vehicle.
In some embodiments, the server obtains, for each second target vehicle, a difference between a third time and a fourth time corresponding to the second target vehicle, and repeats the above operations, so that, for the at least one second target vehicle, the corresponding at least one difference can be determined. Further, at least one difference value corresponding to the at least one second target vehicle is averaged, and the average value is determined as a second average running time of any one road section, so that the second average running time of any one road section is determined as the road section passing time of any one road section, and the road section passing time can reflect the average running time of each vehicle passing through any one road section completely.
In the above process, even if the first target vehicle does not completely pass through the local route, if the second target vehicle completely passes through a certain link in the local route, the second average traveling time period of the second target vehicle may be obtained for the local link as the link passage time period of the local link. Further, the road section passing time length of each road section of the composite route is obtained, and the road section passing time lengths of the road sections are added to obtain the first passing time length of the route.
Illustratively, assuming that the road ID sequence of the current route is { road1, road2, road3}, in the case that the first target vehicle does not completely pass through { road1, road2, road3}, if the second target vehicle completely passes through a first road segment road1 in the current route, the second target vehicle completely passes through a second road segment road2 in the current route, and the second target vehicle completely passes through a third road segment road3 in the current route, the road segment passing time lengths are respectively obtained for the road segments 1, 2 and road3, and the road segment passing time lengths of the road segments 1, road segments 2 and road segment 3 are added to obtain the first passing time length of the current route.
3042B, if there is no second target vehicle passing through the any road section, the server determines the maximum speed limit of the any road section; and dividing the road length of any road section by the maximum speed limit to obtain a numerical value, and determining the road section passing time corresponding to any road section.
In the above process, no second target vehicle passes through any section, which means that no second target vehicle passes through any section in the simulation, and this means that no second target vehicle completely travels from the start point of any section to the end point of any section, and no second target vehicle passes through any section in any section. For any of the road segments, because of the lack of the simulated travel data of the second target vehicle passing through the any of the road segments, the maximum speed limit for the any of the road segments can be used to estimate the road segment transit time for the any of the road segments, since if there are fewer vehicles (even no vehicles) traveling on the local road segment, the vehicles can travel on the local road segment at a speed that does not exceed the maximum speed limit.
In some embodiments, when the server determines the maximum speed limit of any road segment, since the any road segment usually has an existing speed limit value and, in the case of being subjected to the regulation of the speed limit event, if the any road segment is included in the speed limit road segment, there is also a speed limit value of the speed limit event, the server may perform the following operations: and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
In some embodiments, after determining the maximum speed limit of any road section, the server divides the road length of any road section by the maximum speed limit of any road section to obtain the road section passing time length of any road section.
In the above process, even if no first target vehicle completely passes through the route, no second target vehicle passes through any road segment in the route, that is, no vehicle passes through any road segment in the simulation, the road length and the maximum speed limit of any road segment may be used to estimate the road segment passing time of any road segment, and for other road segments in the route, if a second target vehicle completely passes through other road segments, an operation similar to the above step 3042A may be performed, if a second target vehicle passes through a part of the other road segments, an operation similar to the following step 3042C may be performed, and if no second target vehicle passes through other road segments, an operation similar to the above step 3042B may be performed.
In other embodiments, in addition to using the road length and the maximum speed limit of any one of the road sections to estimate the road section passing time length of any one of the road sections, the road length and the historical average speed of any one of the road sections may be used to estimate the road section passing time length of any one of the road sections, where the historical average speed is an average speed of each vehicle passing through any one of the road sections in the historical simulation, that is, the server determines the road length and the historical average speed of any one of the road sections, and divides the road length by the historical average speed to obtain the road section passing time length of any one of the road sections.
Illustratively, assuming that the road ID sequence of the current route is { road1, road2, road3}, in the case where there is no first target vehicle passing through { road1, road2, road3} completely, if there is a second target vehicle passing through the first road segment road1 in the current route completely, but there is no second target vehicle passing through the second road segment road2 and the third road segment road3 in the current route completely, the road segment transit time length of the road segment 1 may be obtained using operations similar to the above step 3042A for the road segment 1, the road segment transit time lengths of the road segments 2 and 3 for the road segment 2 and the road segment 3 using operations similar to the above step 3042B, and the road segment 1, the road segment 2 and the road segment 3 are added to obtain the first transit time length of the current route.
3042C, if there is at least one second target vehicle passing through a part of the road section, the server determines a third average driving time length spent by the at least one second target vehicle on the part of the road section based on the simulated driving data of the at least one second target vehicle; for another part of road sections in any road section, acquiring a first target numerical value obtained by dividing the road length of the another part of road sections by the maximum speed limit of the another part of road sections; and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
In the above process, if there is a second target vehicle passing through the any link but not completely passing through the any link (i.e., the second target vehicle does not travel from the start point to the end point of the any link, which may be the case where there is a jump to 3042A) for the any link, in other words, there is a partial link in which the second target vehicle passes through the any link, the any link may be segmented and divided into a partial link on which the second target vehicle travels and another partial link on which the second target vehicle does not travel, and then, for the partial link, a third average travel time period of each second target vehicle on the partial link may be acquired, and for the another partial link, a first target value may be estimated using a road length and a maximum speed limit of the another partial link, and a second target value obtained by adding the third average travel time period and the first target value may be acquired, and determining the road section passing time of any road section.
In some embodiments, for the partial road segment in the any one road segment, the server may determine at least one fifth time and at least one sixth time based on the simulated driving data of the at least one second target vehicle, where the fifth time is a time when the second target vehicle drives to the start point of the partial road segment, i.e., represents a start time when the second target vehicle drives into the partial road segment, and the sixth time is a time when the second target vehicle drives to the end point of the partial road segment, i.e., represents a departure time when the second target vehicle drives out of the partial road segment.
In some embodiments, for each second target vehicle, the server in determining the fifth time and the sixth time may perform the following: since the simulated travel data of the second target vehicle is composed of a series of time stamps and a corresponding series of position coordinates, it is possible to select a fifth position coordinate closest to the start point of the partial link from the series of position coordinates, determine a time stamp corresponding to the fifth position coordinate as a fifth time, select a sixth position coordinate closest to the end point of the partial link from the series of position coordinates, and determine a time stamp corresponding to the sixth position coordinate as a sixth time. The server may determine a corresponding fifth time and sixth time for each second target vehicle, and repeat the above operations, so that at least one fifth time and at least one sixth time can be determined for the at least one second target vehicle.
In some embodiments, the server obtains, for each second target vehicle, a difference between a fifth time and a sixth time corresponding to the second target vehicle, and repeats the above operations, so that, for the at least one second target vehicle, the corresponding at least one difference can be determined. Further, at least one difference value corresponding to the at least one second target vehicle is averaged, and the average value is determined as the third average travel time length of the partial road section.
In some embodiments, for another portion of the road segment, since no second target vehicle is passing through the another portion of the road segment, the server may estimate the road segment transit time for the another portion of the road segment using the maximum speed limit for the another portion of the road segment, since if there are fewer vehicles (or even no vehicles) traveling on the portion of the road segment, the vehicles may travel on the portion of the road segment using a speed that does not exceed the maximum speed limit.
In some embodiments, when the server determines the maximum speed limit of the other part of the road segment, since the other part of the road segment usually has an existing speed limit value and, in the case of being subjected to the regulation of the speed limit event, if the other part of the road segment is included in the speed limit road segment, there is also a speed limit value of the speed limit event, the server may perform the following operations: and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises the other section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of the other section as the maximum speed limit. After determining the maximum speed limit of the other part of the road section, the server divides the road length of the other part of the road section by the maximum speed limit of the other part of the road section to obtain a first target value.
In other embodiments, in addition to using the road length and the maximum speed limit of the another part of the road section to estimate the first target value of the another part of the road section, the road length and the historical average speed of the another part of the road section may be used to estimate the road section passing time of the another part of the road section, where the historical average speed refers to the average speed of each vehicle passing through the another part of the road section in the historical simulation, that is, the server determines the road length and the historical average speed of the another part of the road section, and divides the road length by the historical average speed to obtain the first target value of the another part of the road section.
Further, after the third average driving time length of the section of road segment and the first target value of the other section of road segment are obtained, a second target value obtained by adding the third average driving time length and the first target value may be determined as the road segment passing time length of any one section of road segment.
In the above process, even if no first target vehicle completely passes through the local route, if there is a part of the route section where the second target vehicle passes through any one of the route sections in the local route, the segment calculation may be performed on the local route section, for the section where there are second target vehicles passing through, a third average traveling time period is obtained, which represents the divided average traveling time period for each of the second target vehicles traveling to the section, for another portion of the road segment where no second target vehicle is present, the road length may be divided by the maximum speed limit to obtain a first target value, this first target value represents the expected length of travel for each vehicle to travel to the other portion of the road segment, and then, determining the section passing time length of any section according to a second target value obtained by adding the third average driving time length and the first target value.
Illustratively, assuming that the road ID sequence of the current route is { road1, road2, road3}, if there is no first target vehicle passing through { road1, road2, road3} in its entirety, if there is a partial road segment where a second target vehicle passes through the first road segment road1, and there is no second target vehicle passing through the second road segment road2 and the third road segment road3 in the present route, this situation usually occurs when a "traffic accident" or a "road closure" occurs at a certain position (which may be the end point of the partial road segment) in the road 1. Then the link transit time length can be divided into two parts of the sum value for the road load 1, one part is the third average travel time length of the road load in the road load 1, and the other part is the first target value obtained by dividing the road length of the road load in the road load 1 by the maximum speed limit. For the road2 and the road3, similar operations as the above step 3042B can be used to obtain the road segment passing time lengths of the road2 and the road3, and the road segment passing time lengths of the road1, the road2 and the road3 are added to obtain the first passing time length of the current route.
In the above step 3041 and 3042, in the simulation operation process, it is not necessary to wait for all vehicles to complete the journey to collect enough passage time information, but the simulation may be operated only for the departure time period to be studied, even if the journey of some vehicles is not finished, that is, an incomplete journey occurs, the first passage time of the corresponding path may be estimated by using the processing involved in the above steps 3042A-C, so as to improve the calculation efficiency of the computer in the simulation.
305. If the relative interval parameters of the first passing time lengths are smaller than the target threshold value, the server determines that the first passing time lengths meet the target condition, and outputs the paths in the simulation.
Wherein the relative interval parameter is used to characterize the difference between the respective passage lengths of different vehicles travelling on the same route.
The target condition is that relative interval parameters of a plurality of first passing time lengths corresponding to the paths are smaller than a target threshold value. The target threshold is any value greater than or equal to 0.
In some embodiments, after obtaining the first transit time length of each route through step 304, the server may obtain a plurality of first transit time lengths for the plurality of routes, so as to obtain the relative interval parameters of the plurality of first transit time lengths. When the relative interval parameter is smaller than the target threshold value, the difference between the passage time lengths spent by different vehicles driving on the same path is considered to be small, namely the balance state is reached, so that the plurality of first passage time lengths are determined to meet the target condition, and the plurality of paths in the simulation are output.
In some embodiments, the obtaining of the relative interval parameter comprises: acquiring a plurality of shortest passing time lengths corresponding to the plurality of routes respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding routes; obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths; and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
In the above process, for each route, since the first passing time length only reflects the average traveling time length spent by each vehicle passing through the route, the minimum value of each passing time length can be determined from each passing time length spent by each vehicle passing through the route as the shortest passing time length of the route, then the shortest passing time lengths of all routes are summed to obtain the second sum value, then, for each route, the first passing time length of the route and the shortest passing time length of the route are subtracted to obtain a target difference value, the above operations are repeatedly performed, a plurality of target difference values can be obtained for the plurality of routes, the target difference values of all routes are summed to obtain the first sum value, and the first sum value is divided by the second sum value, so that the relative interval parameters of all routes can be obtained.
The relative interval parameter is expressed by RG, assuming that there are n (n ≧ 1) paths in total,representing a first transit time period for a jth route, j being an integer greater than or equal to 1 and less than or equal to n,representing the shortest transit time, the expression of the relative interval parameter is as follows:
wherein,it is indicated that the target difference value,a first sum value is represented that is a sum of,representing a second sum value.
In step 305, by obtaining the relative interval parameter, determining that the first passage durations meet the target condition when the relative interval parameter is smaller than the target threshold, and outputting the plurality of paths of the simulation, where the difference between the passage durations taken by different vehicles driving on the same path reaches a balanced state, stopping the iterative simulation of the path planning, and outputting the plurality of paths determined in the simulation, the accuracy of the path planning can be improved.
All the above optional technical solutions can be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
The method provided by the embodiment of the application establishes the simulation environment based on the target traffic event after determining the target traffic event and the respective path of each vehicle, simulates the travel of each vehicle on the corresponding path, can determine the corresponding first passing time regardless of whether the vehicle completely runs the corresponding path in the simulation time period, outputs each path of the simulation as a path planning result when each first passing time meets the target condition, namely supports the flexible setting of different traffic events in the path planning process, establishes different simulation environments based on different traffic events, ensures that the path planning result can adapt to the traffic event, can accurately deduce the influence of the traffic event on the path selection, and cannot complete the travel even if the vehicle is influenced by the traffic event, the calculation of the first passing time length still cannot be influenced, so that the method has higher universality when judging whether to output a path planning result or not based on the first passing time length, and the accuracy of the computer equipment in simulation is improved.
In the above embodiment, the operation performed by the server to output the multiple paths when the multiple first passage time lengths meet the target condition is shown, while in the embodiment of the present application, fig. 5 is a flowchart of a path planning method provided in the embodiment of the present application, and as shown in fig. 5, it is shown that if the multiple first passage time lengths do not meet the target condition, the server may perform the following operation.
501. The server acquires the vehicle journey information and the target traffic event input by the user.
Step 501 is similar to step 301, and is not described herein.
502. And the server acquires a plurality of paths corresponding to a plurality of vehicles participating in the simulation on the basis of the vehicle travel information, wherein the paths are paths corresponding to the vehicles in the simulation for simulating the running.
Step 502 is similar to step 302 and will not be described herein.
503. And the server simulates the routes of the vehicles on the multiple paths under the simulation environment based on the target traffic incident to obtain multiple simulation route data of the vehicles, wherein the simulation route data comprises the positions of the corresponding vehicles at any time in the time period of the current simulation.
Step 503 is similar to step 303 and will not be described herein.
504. The server obtains a plurality of first passing time lengths corresponding to the paths based on the plurality of simulation travel data, wherein the first passing time lengths are used for representing the average running time length spent by each vehicle passing through the corresponding path in the simulation.
Step 504 is similar to step 304 and will not be described herein.
505. If the relative interval parameters of the first passing time lengths are larger than or equal to the target threshold, the server determines that the first passing time lengths do not meet the target condition.
Wherein the relative interval parameter is used to characterize the difference between the respective passage lengths of different vehicles travelling on the same route.
The target condition is that relative interval parameters of a plurality of first passing time lengths corresponding to the paths are smaller than a target threshold value. The target threshold is any value greater than or equal to 0.
In some embodiments, after obtaining the first transit time length of each route through step 504, the server may obtain a plurality of first transit time lengths for the plurality of routes, so as to obtain the relative interval parameters of the plurality of first transit time lengths. When the relative interval parameter is greater than or equal to the target threshold, it may be considered that the difference between the passage time lengths taken by different vehicles to travel on the same route is large, that is, the equilibrium state is not reached, so that it is determined that the plurality of first passage time lengths do not meet the target condition, and the following step 506 is performed.
It should be noted that the process of acquiring the relative interval parameter in step 505 is similar to the process of acquiring the relative interval parameter in step 305, and is not described herein again.
506. If the first passing time lengths do not meet the target condition, the server updates second passing time lengths corresponding to the paths respectively based on the first passing time lengths to obtain updated second passing time lengths, and the second passing time lengths are used for representing the predicted travelling time lengths spent on the corresponding paths determined by the driver based on the historical travel.
The first passage time length and the second passage time length are different in that the first passage time length is used for representing the average travelling time length spent by each vehicle passing through the corresponding path in the simulation, namely representing the actual passage time length of each path, and the second passage time length is used for representing the travelling time length predicted to be spent on the corresponding path by the driver based on the historical travel, namely representing the perceived passage time length of each path (in other words, the elapsed path time length considered by the driver according to the experience effect accumulated in the historical simulation).
In some embodiments, the server may perform the following operations when updating the second passage duration: multiplying a first coefficient by a first passing time corresponding to any one of the paths to obtain a third target numerical value; multiplying a second coefficient by a second passing time length corresponding to any one path to obtain a fourth target numerical value, wherein the sum of the first coefficient and the second coefficient is 1; and adding the third target value and the fourth target value to obtain the updated second traffic duration corresponding to any one path.
Optionally, for any of the paths, toRepresents the first passing time of the simulation of this time, namely the t time,indicates the corresponding second of the any pathThe two-pass duration, which represents the perceived pass duration that has been calculated in the history simulation,the updated second communication time length is represented, and then the updated second communication time lengthThe expression of (a) is as follows:
wherein,which is indicative of the first coefficient of the signal,which is indicative of the second coefficient of the signal,a third target value is represented which is,representing a fourth target value.
In other words, since the path is redistributed to each vehicle and the next simulation is started under the condition that the target condition is not met, the iterative simulation process can be considered to be performed on each vehicle, the iteration is stopped until a plurality of first passing time lengths under a certain simulation meet the target condition, and each path corresponding to each vehicle during the last simulation is output as the final path planning result. Thus, the t-th simulation in the iterative process may be considered to be the simulation on the t-th day after the occurrence of the target traffic event, and thenCan be regarded as the fact of the corresponding path at the t th day after the target traffic incident occursThe length of the time of the cross-pass,the perceived transit time of the corresponding route on the tth day after the occurrence of the target traffic event can be considered,can be regarded as the perceived passage time of the corresponding path at the t +1 th day after the target traffic event occurs, andthen represents the weight taken by the historical perceived transit time.
In the process, for each path, the updated second passing time of the simulation can be obtained by performing weighted summation on the first passing time of the simulation and the second passing time of the historical simulation, so that the updated second passing time can fully integrate the perceived passing time (second passing time) of the historical travel and the actual passing time (first passing time) of the simulation, and the method is favorable for guiding and predicting path allocation in the next simulation.
In some embodiments, in addition to performing weighted average on the second passing time length calculated in the last simulation and the first passing time length of the current simulation to obtain the updated second passing time length, a weighted average may be performed on an average value of two second passing time lengths calculated in the previous simulations and the second passing time length of the current simulation to obtain the updated second passing time length, or a weighted average may be performed on an average value of each second passing time length calculated in all previous historical simulations and the second passing time length of the current simulation to obtain the updated second passing time length, which is not specifically limited in this embodiment of the present application.
507. And the server distributes a plurality of paths corresponding to the next simulation to the plurality of vehicles based on the plurality of updated second passage time lengths.
In some embodiments, when allocating the next simulated path to each vehicle, the server may determine, for each candidate path, a selection probability of the candidate path based on the updated second travel time length corresponding to the candidate path, for at least one candidate path corresponding to each start-end point pair, by taking the start-end point pair as a unit, and perform weighted random sampling on the selection probabilities of the candidate paths from the candidate paths corresponding to the start-end point pair to obtain the next simulated path of each vehicle for each vehicle matched with the start-end point pair, which is described in detail below.
Fig. 6 is a flowchart of path allocation at the next simulation according to an embodiment of the present application, and as shown in fig. 6, the server may perform the following operations for any vehicle in the plurality of vehicles.
5071. The server determines at least one candidate route corresponding to the any vehicle, and the starting point and the end point of the candidate route are respectively matched with the starting point and the end point of the journey of the any vehicle.
Wherein the starting point and the end point of the candidate route are respectively matched with the travel starting point and the travel end point of any vehicle, and the steps are as follows: the distance between the starting point of the candidate route and the travel starting point of any vehicle is smaller than a first distance threshold, and the distance between the end point of the candidate route and the travel end point of any vehicle is smaller than a second distance threshold, wherein the first distance threshold and the second distance threshold are any numerical values larger than or equal to 0.
In some embodiments, for each vehicle, the server may determine, according to the starting point and the ending point of the travel of the vehicle, a starting point and an ending point pair corresponding to the vehicle, and take each route corresponding to the starting point and the ending point pair as the at least one candidate route.
In some embodiments, for each vehicle, the server may also predict the at least one candidate path based on the call path planning algorithm in step 201, for example, using Dijkstra algorithm or Yen algorithm to predict the at least one candidate path, which is not described herein.
5072. The server determines at least one selection probability of the at least one candidate route based on the at least one updated second travel time corresponding to the at least one candidate route, wherein the selection probability is used for representing the possibility that any vehicle is expected to select the corresponding candidate route to complete the travel.
In some embodiments, for any candidate path of the at least one candidate path, the server may determine a utility parameter of the any candidate path based on the updated second transit time length corresponding to the any candidate path, the utility parameter being negatively correlated with the corresponding updated second transit time length; acquiring a third sum value between at least one utility parameter corresponding to each of the at least one candidate path; and determining the ratio of the utility parameter of any candidate path in the third sum as the selection probability of any candidate path. The utility parameter is used for representing the vehicle driving efficiency when the driver selects the corresponding candidate route, and the utility parameter of the same candidate route can be generally in negative correlation with the updated second passing time length, that is, the longer the updated second passing time length of the same candidate route is, the smaller the utility parameter of the candidate route is, the shorter the updated second passing time length of the same candidate route is, and the larger the utility parameter of the candidate route is.
In some embodiments, the server may determine the inverse of the corresponding updated second passage time length of the any one candidate path as the utility parameter of the any one candidate path. That is, toIndicating the updated second transit time of the jth candidate route calculated in step 506 above,representing the utility parameter of the jth candidate path, j being an integer greater than or equal to 1 and less than or equal to n, n being any integer greater than 1 or equal to 1 (n represents the total number of candidate paths), then the utility parameter of the jth candidate pathCan be expressed as:
further, after obtaining each utility parameter of each candidate path, summing each utility parameter to obtain a third sum, and a ratio of the utility parameter of each candidate path in the third sum is a selection probability of each candidate path. In other words, the selection probability of the jth candidate pathCan be expressed as:
wherein,a utility parameter representing the jth candidate path, j is an integer greater than or equal to 1 and less than or equal to n, n is any integer greater than 1 or equal to 1 (n represents the total number of candidate paths),and a utility parameter representing the ith candidate path, wherein i is an integer which is greater than or equal to 1 and less than or equal to n.
5073. And the server samples the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
In some embodiments, for each vehicle, the server may perform weighted random sampling on the at least one candidate path based on the at least one selection probability, so that a path corresponding to the vehicle in the next simulation can be sampled.
In the aforementioned step 5071-5073, it is shown how, in the case that the plurality of first passage time lengths do not meet the target condition, the server may perform the next simulation by re-allocating the route to each vehicle in the next simulation based on the updated second passage time length, and the next simulation may be executed by returning to the step 503 after the route allocation is completed. The server performs the above operations repeatedly for multiple times, which may be regarded as gradually deducing the change of the route selected by the driver in multiple days after the target traffic event occurs, for example, the route at the first iteration represents the route selected by the driver on the first day after the target traffic event occurs, and so on.
All the above optional technical solutions can be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
The method provided by the embodiment of the application establishes the simulation environment based on the target traffic event after determining the target traffic event and the respective path of each vehicle, simulates the travel of each vehicle on the corresponding path, can determine the corresponding first passing time regardless of whether the vehicle completely runs the corresponding path in the simulation time period, outputs each path of the simulation as a path planning result when each first passing time meets the target condition, namely supports the flexible setting of different traffic events in the path planning process, establishes different simulation environments based on different traffic events, ensures that the path planning result can adapt to the traffic event, can accurately deduce the influence of the traffic event on the path selection, and cannot complete the travel even if the vehicle is influenced by the traffic event, the calculation of the first passing time length still cannot be influenced, so that the method has higher universality when judging whether to output a path planning result or not based on the first passing time length, and the accuracy of the computer equipment in simulation is improved.
Fig. 7 is a schematic diagram of a path planning method provided in an embodiment of the present application, as shown in 700, which includes the following steps.
Step one, generating a candidate route according to a starting point and a destination point of a vehicle and a map.
And step two, running simulation.
It should be noted that the simulation is a part of the path planning process, and is performed again after the final output of the path planning result in order to evaluate the path allocated in the simulation, and the simulation is performed again based on the path determined by the path planning result.
And step three, estimating the first passing time of each path.
And step four, judging whether convergence is achieved (namely whether the target condition is met), if the convergence is achieved, outputting a plurality of paths of the simulation as a path planning result, exiting the process, and if the convergence is not achieved, executing the step five.
And step five, updating the second passage time length perceived by the driver.
And step six, selecting a path of next simulation according to the updated second passage time length.
And step seven, recording the currently allocated path of the next simulation, and returning to the step two.
In the path planning process, the input includes vehicle travel information and a target traffic event, the output includes a path corresponding to each vehicle, the path of each vehicle may be composed of a plurality of road segments in sequence, that is, may be described by a road ID sequence, and a path corresponding to any day (iteration number represents days) after the target traffic event occurs may also be flexibly output according to the needs of a user.
In the embodiment of the application, a vehicle path allocation mode is provided, and the vehicle path allocation mode can be used in traffic control simulation deduction and can efficiently output the change rule of the path selected by a driver within a day after a target traffic event occurs.
Fig. 8 is a schematic diagram of a traffic simulation system according to an embodiment of the present application, and as shown in 800, in the traffic simulation system or the traffic simulation platform, a front end may receive two types of information input by a user, where one type of information is vehicle travel information including a departure position, a target position, a departure time, and the like of each vehicle, and the other type of information is a target traffic event including a road segment where the event occurs, an event type, a duration, and the like. The two types of information are input into a path planning module, the path planning method provided by the embodiment of the application is executed in the path planning module, the path corresponding to each vehicle can be output, further, simulation is carried out based on the path corresponding to each vehicle, an event simulation result of a target traffic event can be obtained, and the event simulation result can be output to the front end to be visually displayed.
Fig. 9 is a schematic interface diagram of inputting a target traffic event according to an embodiment of the present application, and as shown in fig. 9, in a configuration interface 900 of a traffic simulation platform, an event simulation function may be provided, based on which a simulation environment can be triggered and executed based on a certain target traffic event, and driving of each vehicle is simulated, so as to deduce a possible influence of the target traffic event. An add event function option 910 may be provided in the configuration interface 900, an event configuration window 920 may be displayed in the configuration interface 900 in response to a user's trigger operation on the add event function option 910, and an event type edit area 921, an event start time edit area 922, an event duration edit area 923, a maximum speed edit area 924, and an event-influenced distance edit area 925 may be provided in the event configuration window 920, as shown in fig. 9, assuming that the event type of the current target traffic event is "traffic accident", the event start time thereof may be XXXX month XX day 20:07:00 in XXXX year, the event duration may be 50 minutes, the maximum speed may be 10km/h, and the event-influenced distance may be 100 meters. After the target traffic event is input based on the configuration interface 900, the subsequent processes of path planning, simulation deduction and the like can be triggered and executed.
Fig. 10 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present application, please refer to fig. 10, where the apparatus includes:
a first obtaining module 1001, configured to obtain a target traffic event and multiple paths corresponding to multiple vehicles, where the paths are paths where the corresponding vehicles in the simulation run in the current simulation;
the simulation module 1002 is configured to simulate the routes of the multiple vehicles on the multiple paths in a simulation environment based on the target traffic event to obtain multiple pieces of simulated route data of the multiple vehicles, where the simulated route data includes positions of the corresponding vehicles at any time within the current simulation time period;
a second obtaining module 1003, configured to obtain, based on the plurality of simulation trip data, a plurality of first passage durations corresponding to the plurality of routes, where the first passage durations are used to represent average traveling durations spent by vehicles passing through the corresponding routes in the middle of the simulation;
an output module 1004, configured to output the multiple paths in the current simulation if the multiple first passing durations meet a target condition.
The device provided by the embodiment of the application establishes the simulation environment based on the target traffic event after determining the target traffic event and the respective path of each vehicle, simulates the travel of each vehicle on the corresponding path, can determine the corresponding first passing time regardless of whether the vehicle completely runs the corresponding path in the simulation time period, outputs each path of the simulation as a path planning result when each first passing time meets the target condition, namely supports the flexible setting of different traffic events in the path planning process, establishes different simulation environments based on different traffic events, ensures that the path planning result can adapt to the traffic event, can accurately deduce the influence of the traffic event on the path selection, and cannot complete the travel even if the vehicle is influenced by the traffic event, the calculation of the first passing time length still cannot be influenced, so that the method has higher universality when judging whether to output a path planning result or not based on the first passing time length, and the accuracy of the computer equipment in simulation is improved.
In a possible implementation, based on the apparatus composition of fig. 10, the second obtaining module 1003 includes:
a first determining unit, configured to determine, for any one of the plurality of routes, if there is at least one first target vehicle traveling from a start point to an end point of the any one route, a first average traveling time period that the at least one first target vehicle spends on the any one route based on the simulated traveling data of the at least one first target vehicle; determining the first average running time length as a first passing time length corresponding to any one route;
the second determining unit is used for determining the road section passing time length corresponding to each of the plurality of road sections in any route based on the simulated driving data of at least one second target vehicle passing through any route if any first target vehicle does not travel from the starting point to the end point of any route; and determining the sum of the passage time lengths of the road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route.
In one possible embodiment, the second determination unit is configured to:
for any road section in any path, if at least one second target vehicle runs from the starting point to the end point of the any road section, determining a second average running time spent by the at least one second target vehicle on the any road section based on the simulated running data of the at least one second target vehicle;
and determining the second average driving time length as the road section passing time length corresponding to any road section.
In a possible implementation, based on the apparatus composition of fig. 10, the second determining unit includes:
the first determining subunit is used for determining the maximum speed limit of any road section if any second target vehicle passes through the road section for any road section in any path;
and the second determining subunit is used for dividing the road length of any road section by the value obtained by the maximum speed limit to determine the road section passing time length corresponding to any road section.
In one possible embodiment, the first determining subunit is configured to:
and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
In one possible embodiment, the second determination unit is configured to:
for any road section in any route, if at least one second target vehicle passes through a partial road section in any road section, determining a third average driving time spent by the at least one second target vehicle on the partial road section based on the simulated driving data of the at least one second target vehicle;
for another part of road sections in any road section, acquiring a first target numerical value obtained by dividing the road length of the another part of road sections by the maximum speed limit of the another part of road sections;
and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
In one possible embodiment, the first determination unit is configured to:
determining at least one first time and at least one second time based on the simulated running data of the at least one first target vehicle, wherein the first time is the time when the first target vehicle runs to the starting point of any one route, and the second time is the time when the first target vehicle runs to the end point of any one route;
for any one first target vehicle in the at least one first target vehicle, acquiring a difference value between a corresponding first moment and a corresponding second moment;
and determining the average value of at least one difference value corresponding to the at least one first target vehicle as the first average running time length.
In one possible embodiment, the target condition comprises a relative interval parameter of the first transit time periods being smaller than a target threshold value, the relative interval parameter being indicative of a difference between respective transit time periods of different vehicles travelling on the same route.
In one possible embodiment, the obtaining of the relative interval parameter includes:
acquiring a plurality of shortest passing time lengths corresponding to the plurality of routes respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding routes;
obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths;
and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
In a possible embodiment, based on the apparatus composition of fig. 10, the apparatus further comprises:
the updating module is used for updating a plurality of second passing time lengths corresponding to the paths respectively based on the first passing time lengths if the first passing time lengths do not accord with the target condition to obtain a plurality of updated second passing time lengths, and the second passing time lengths are used for representing the predicted travelling time lengths spent on the corresponding paths determined by the driver based on historical travel;
and the distribution module is used for distributing a plurality of paths corresponding to the next simulation to the plurality of vehicles based on the plurality of updated second traffic duration.
In one possible embodiment, the update module is configured to:
multiplying a first coefficient by a first passing time corresponding to any one of the paths to obtain a third target numerical value;
multiplying a second coefficient by a second passing time length corresponding to any one path to obtain a fourth target numerical value, wherein the sum of the first coefficient and the second coefficient is 1;
and adding the third target value and the fourth target value to obtain the updated second traffic duration corresponding to any one path.
In a possible implementation, based on the apparatus composition of fig. 10, the allocation module includes:
a second determination sub-module configured to determine, for any one of the plurality of vehicles, at least one candidate route corresponding to the any one vehicle, the start point and the end point of the candidate route being matched with the trip start point and the trip end point of the any one vehicle, respectively;
a third determining submodule, configured to determine, based on at least one updated second travel time corresponding to the at least one candidate route, at least one selection probability of the at least one candidate route, where the selection probability is used to characterize a possibility that the any vehicle is expected to select the corresponding candidate route to complete the trip;
and the sampling submodule is used for sampling the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
In one possible implementation, based on the apparatus components of fig. 10, the third determining submodule includes:
a third determining unit, configured to determine, for any candidate path in the at least one candidate path, a utility parameter of the any candidate path based on an updated second transit time length corresponding to the any candidate path, where the utility parameter is negatively correlated with the corresponding updated second transit time length;
the obtaining unit is used for obtaining a third sum value between at least one utility parameter corresponding to each of the at least one candidate path;
and a fourth determining unit, configured to determine, as the selection probability of any candidate path, a ratio of the utility parameter of the any candidate path to the third sum.
In one possible embodiment, the third determination unit is configured to:
and determining the reciprocal of the updated second passing time length corresponding to any candidate path as the utility parameter of any candidate path.
All the above optional technical solutions can be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
It should be noted that: the path planning apparatus provided in the above embodiment is only illustrated by dividing the functional modules when planning a path, and in practical applications, the function distribution can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the path planning apparatus and the path planning method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the path planning method embodiments and are not described herein again.
Fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application, where the computer device 1100 may generate a relatively large difference due to a difference in configuration or performance, and the computer device 1100 includes one or more processors (CPUs) 1101 and one or more memories 1102, where the memories 1102 store at least one computer program, and the at least one computer program is loaded and executed by the one or more processors 1101 to implement the path planning method provided in the foregoing embodiments. Optionally, the computer device 1100 further has components such as a wired or wireless network interface, a keyboard, an input/output interface, and the like, so as to perform input/output, and the computer device 1100 further includes other components for implementing device functions, which are not described herein again.
In an exemplary embodiment, a computer-readable storage medium, such as a memory including at least one computer program, which is executable by a processor in a terminal to perform the path planning method in the above embodiments, is also provided. For example, the computer-readable storage medium includes a ROM (Read-Only Memory), a RAM (Random-Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product or computer program is also provided, comprising one or more program codes, the one or more program codes being stored in a computer readable storage medium. The one or more program codes can be read by one or more processors of the computer device from a computer-readable storage medium, and the one or more processors execute the one or more program codes, so that the computer device can execute to complete the path planning method in the above-described embodiments.
Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments can be implemented by hardware, or can be implemented by a program instructing relevant hardware, and optionally, the program is stored in a computer readable storage medium, and optionally, the above mentioned storage medium is a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (27)
1. A method of path planning, the method comprising:
acquiring a target traffic event and a plurality of paths corresponding to a plurality of vehicles, wherein the paths are paths for simulating the running of the corresponding vehicles in the simulation;
simulating the travel of the vehicles on the paths under the simulation environment based on the target traffic incident to obtain a plurality of simulated driving data of the vehicles, wherein the simulated driving data comprises the positions of the corresponding vehicles at any time in the time period of the simulation;
for any one of the plurality of routes, if at least one first target vehicle runs from the starting point to the end point of the route, determining a first average running time spent by the at least one first target vehicle on the route based on the simulated running data of the at least one first target vehicle; determining the first average running time length as a first passing time length corresponding to any one route;
if any first target vehicle does not travel from the starting point to the end point of any route, determining the road section passing time length corresponding to each of a plurality of road sections in any route based on the simulated travel data of at least one second target vehicle passing through any route; determining a sum value of passage time lengths of road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route;
if a plurality of first passing time lengths corresponding to the plurality of paths meet a target condition, outputting the plurality of paths in the simulation, wherein the target condition comprises that relative interval parameters of the plurality of first passing time lengths are smaller than a target threshold value, and the relative interval parameters are used for representing the difference between the respective passing time lengths of different vehicles running on the same path.
2. The method according to claim 1, wherein the determining a link transit time length corresponding to each of a plurality of links in the any route based on the simulated travel data of at least one second target vehicle passing through the any route comprises:
for any road section in any path, if at least one second target vehicle runs from the starting point to the end point of the any road section, determining a second average running time spent by the at least one second target vehicle on the any road section based on the simulated running data of the at least one second target vehicle;
and determining the second average driving time length as the road section passing time length corresponding to any road section.
3. The method according to claim 1, wherein the determining a link transit time length corresponding to each of a plurality of links in the any route based on the simulated travel data of at least one second target vehicle passing through the any route comprises:
for any road section in any path, if any second target vehicle does not pass through any road section, determining the maximum speed limit of any road section;
and dividing the road length of any road section by the maximum speed limit to obtain a numerical value, and determining the road section passing time corresponding to any road section.
4. The method of claim 3, wherein the determining the maximum speed limit for any of the road segments comprises:
and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
5. The method according to claim 1, wherein the determining a link transit time length corresponding to each of a plurality of links in the any route based on the simulated travel data of at least one second target vehicle passing through the any route comprises:
for any road section in any route, if at least one second target vehicle passes through a partial road section in any road section, determining a third average driving time spent by the at least one second target vehicle on the partial road section based on the simulated driving data of the at least one second target vehicle;
for another part of the road sections, acquiring a first target numerical value obtained by dividing the road length of the another part of the road sections by the maximum speed limit of the another part of the road sections;
and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
6. The method of claim 1, wherein the determining a first average travel length that the at least one first target vehicle spends on the either path based on the simulated travel data of the at least one first target vehicle comprises:
determining at least one first time and at least one second time based on the simulated driving data of the at least one first target vehicle, wherein the first time is the time when the first target vehicle drives to the starting point of any path, and the second time is the time when the first target vehicle drives to the end point of any path;
for any one first target vehicle in the at least one first target vehicle, acquiring a difference value between a corresponding first moment and a corresponding second moment;
and determining the average value of at least one difference value corresponding to the at least one first target vehicle as the first average running time length.
7. The method of claim 1, wherein the obtaining of the relative interval parameter comprises:
acquiring a plurality of shortest passing time lengths corresponding to the plurality of paths respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding paths;
obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths;
and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
8. The method of claim 1, further comprising:
if the first passing time lengths do not meet the target condition, updating a second passing time length corresponding to each of the paths based on the first passing time lengths to obtain a second updated passing time length, wherein the second passing time length is used for representing the estimated travelling time length of the driver on the corresponding path based on the historical travel;
and distributing a plurality of paths corresponding to the next simulation for the plurality of vehicles based on the plurality of updated second passage time lengths.
9. The method of claim 8, wherein the updating the plurality of second passage durations corresponding to the plurality of paths based on the plurality of first passage durations comprises:
multiplying a first coefficient by a first passing time corresponding to any one path in the paths to obtain a third target numerical value;
multiplying a second coefficient by a second pass duration corresponding to any one of the paths to obtain a fourth target value, wherein the sum of the first coefficient and the second coefficient is 1;
and adding the third target value and the fourth target value to obtain an updated second passing time corresponding to any one path.
10. The method of claim 8, wherein the assigning the plurality of vehicles a plurality of paths for a next simulation based on the plurality of updated second passage durations comprises:
for any vehicle in the plurality of vehicles, determining at least one candidate route corresponding to the any vehicle, wherein the starting point and the end point of the candidate route are respectively matched with the starting point and the end point of the journey of the any vehicle;
determining at least one selection probability of the at least one candidate route based on the at least one updated second travel time corresponding to the at least one candidate route, the selection probability being used to characterize a likelihood that the any vehicle is expected to select the corresponding candidate route to complete the trip;
and sampling the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
11. The method of claim 10, wherein determining at least one selection probability for the at least one candidate path based on the at least one updated second travel time duration for the at least one candidate path comprises:
for any candidate path in the at least one candidate path, determining a utility parameter of the any candidate path based on an updated second passing duration corresponding to the any candidate path, wherein the utility parameter is negatively correlated with the corresponding updated second passing duration;
acquiring a third sum value between at least one utility parameter corresponding to each of the at least one candidate path;
and determining the ratio of the utility parameter of any candidate path in the third sum as the selection probability of any candidate path.
12. The method according to claim 11, wherein the determining the utility parameter of any candidate path based on the updated second passage duration corresponding to the any candidate path comprises:
and determining the reciprocal of the updated second passing time length corresponding to any candidate path as the utility parameter of any candidate path.
13. A path planning apparatus, the apparatus comprising:
the first acquisition module is used for acquiring a target traffic event and a plurality of paths corresponding to a plurality of vehicles, wherein the paths are paths for simulating driving of the corresponding vehicles in the simulation;
the simulation module is used for simulating the travel of the vehicles on the paths under the simulation environment based on the target traffic incident to obtain a plurality of simulated driving data of the vehicles, wherein the simulated driving data comprises the positions of the corresponding vehicles at any time in the time period of the current simulation;
the second acquisition module comprises a first determination unit and a second determination unit;
the first determining unit is configured to determine, for any one of the plurality of routes, if at least one first target vehicle travels from a start point to an end point of the any one route, a first average travel time period that the at least one first target vehicle spends on the any one route based on the simulated travel data of the at least one first target vehicle; determining the first average running time length as a first passing time length corresponding to any one route;
the second determining unit is used for determining the road section passing time length corresponding to each of the plurality of road sections in any route based on the simulated driving data of at least one second target vehicle passing through any route if any first target vehicle does not travel from the starting point to the end point of any route; determining a sum value of passage time lengths of road sections corresponding to the plurality of road sections as a first passage time length corresponding to any one route;
and the output module is used for outputting the plurality of paths in the simulation if the plurality of first passing time lengths corresponding to the plurality of paths meet a target condition, wherein the target condition comprises that relative interval parameters of the plurality of first passing time lengths are smaller than a target threshold value, and the relative interval parameters are used for representing the difference between the respective passing time lengths of different vehicles running on the same path.
14. The apparatus of claim 13, wherein the second determining unit is configured to:
for any road section in any path, if at least one second target vehicle runs from the starting point to the end point of the any road section, determining a second average running time spent by the at least one second target vehicle on the any road section based on the simulated running data of the at least one second target vehicle;
and determining the second average driving time length as the road section passing time length corresponding to any road section.
15. The apparatus of claim 13, wherein the second determining unit comprises:
the first determining subunit is used for determining the maximum speed limit of any road section if any second target vehicle passes through the road section for any road section in any path;
and the second determining subunit is used for dividing the road length of any road section by the value obtained by the maximum speed limit to determine the road section passing time length corresponding to any road section.
16. The apparatus of claim 15, wherein the first determining subunit is configured to:
and if the target traffic event is a speed-limiting event and the speed-limiting section of the speed-limiting event comprises any section, determining the minimum value between the speed-limiting value of the speed-limiting event and the existing speed-limiting value of any section as the maximum speed limit.
17. The apparatus of claim 13, wherein the second determining unit is configured to:
for any road section in any route, if at least one second target vehicle passes through a partial road section in any road section, determining a third average driving time spent by the at least one second target vehicle on the partial road section based on the simulated driving data of the at least one second target vehicle;
for another part of the road sections, acquiring a first target numerical value obtained by dividing the road length of the another part of the road sections by the maximum speed limit of the another part of the road sections;
and determining the section passing time length corresponding to any section according to a second target value obtained by adding the third average driving time length and the first target value.
18. The apparatus of claim 13, wherein the first determining unit is configured to:
determining at least one first time and at least one second time based on the simulated driving data of the at least one first target vehicle, wherein the first time is the time when the first target vehicle drives to the starting point of any path, and the second time is the time when the first target vehicle drives to the end point of any path;
for any one first target vehicle in the at least one first target vehicle, acquiring a difference value between a corresponding first moment and a corresponding second moment;
and determining the average value of at least one difference value corresponding to the at least one first target vehicle as the first average running time length.
19. The apparatus of claim 13, wherein the obtaining of the relative interval parameter comprises:
acquiring a plurality of shortest passing time lengths corresponding to the plurality of paths respectively, wherein the shortest passing time length is the minimum value of the passing time lengths spent by vehicles passing through the corresponding paths;
obtaining a plurality of target difference values between the first passing time lengths and the corresponding shortest passing time lengths;
and dividing the first sum of the target difference values by the second sum of the shortest passing time lengths to obtain the relative interval parameter.
20. The apparatus of claim 13, further comprising:
the updating module is used for updating a plurality of second passing time lengths corresponding to the paths respectively based on the first passing time lengths if the first passing time lengths do not accord with the target condition to obtain a plurality of updated second passing time lengths, and the second passing time lengths are used for representing the predicted travelling time lengths spent on the corresponding paths determined by the driver based on historical travel;
and the distribution module is used for distributing a plurality of paths corresponding to the next simulation to the plurality of vehicles based on the plurality of updated second passage durations.
21. The apparatus of claim 20, wherein the update module is configured to:
multiplying a first coefficient by a first passing time corresponding to any one path in the paths to obtain a third target numerical value;
multiplying a second coefficient by a second pass duration corresponding to any one of the paths to obtain a fourth target value, wherein the sum of the first coefficient and the second coefficient is 1;
and adding the third target value and the fourth target value to obtain an updated second passing time corresponding to any one path.
22. The apparatus of claim 20, wherein the assignment module comprises:
a second determination sub-module configured to determine, for any vehicle of the plurality of vehicles, at least one candidate route corresponding to the any vehicle, where a start point and an end point of the candidate route are matched with a travel start point and a travel end point of the any vehicle, respectively;
a third determining sub-module, configured to determine, based on at least one updated second travel duration corresponding to the at least one candidate route, at least one selection probability of the at least one candidate route, where the selection probability is used to characterize a likelihood that the any vehicle is expected to select the corresponding candidate route to complete the trip;
and the sampling submodule is used for sampling the at least one candidate path based on the at least one selection probability to obtain a path corresponding to the next simulation of any vehicle.
23. The apparatus of claim 22, wherein the third determination submodule comprises:
a third determining unit, configured to determine, for any candidate path in the at least one candidate path, a utility parameter of the any candidate path based on an updated second transit time length corresponding to the any candidate path, where the utility parameter is negatively correlated with the corresponding updated second transit time length;
the obtaining unit is used for obtaining a third sum value between at least one utility parameter corresponding to each of the at least one candidate path;
and a fourth determining unit, configured to determine, as the selection probability of any candidate path, a ratio of the utility parameter of any candidate path to the third sum.
24. The apparatus of claim 23, wherein the third determining unit is configured to:
and determining the reciprocal of the updated second passing time length corresponding to any candidate path as the utility parameter of any candidate path.
25. A computer device, characterized in that the computer device comprises one or more processors and one or more memories in which at least one computer program is stored, the at least one computer program being loaded and executed by the one or more processors to implement the path planning method according to any one of claims 1 to 12.
26. A storage medium having stored therein at least one computer program which is loaded and executed by a processor to implement a path planning method according to any one of claims 1 to 12.
27. A computer program product, characterized in that the computer program product comprises at least one computer program which is loaded and executed by a processor to implement the path planning method according to any of claims 1 to 12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110887080.7A CN113326641B (en) | 2021-08-03 | 2021-08-03 | Path planning method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110887080.7A CN113326641B (en) | 2021-08-03 | 2021-08-03 | Path planning method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113326641A CN113326641A (en) | 2021-08-31 |
CN113326641B true CN113326641B (en) | 2021-12-14 |
Family
ID=77426994
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110887080.7A Active CN113326641B (en) | 2021-08-03 | 2021-08-03 | Path planning method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113326641B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114137973B (en) * | 2021-11-26 | 2024-05-07 | 湖北亿纬动力有限公司 | Path planning method, device, equipment and storage medium |
CN115049167B (en) * | 2022-08-16 | 2022-11-08 | 北京市城市规划设计研究院 | Traffic situation prediction method, device, equipment and storage medium |
CN115482660A (en) * | 2022-09-02 | 2022-12-16 | 江苏中寰卫星导航通信有限公司 | Path determining method, device, equipment and storage medium |
CN116595808B (en) * | 2023-07-17 | 2023-09-08 | 中国人民解放军国防科技大学 | Event pyramid model construction and multi-granularity space-time visualization method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104567897A (en) * | 2013-10-16 | 2015-04-29 | 大陆汽车投资(上海)有限公司 | Road condition forecast combined path planning method and navigation device |
CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
CN112686441A (en) * | 2020-12-28 | 2021-04-20 | 燕山大学 | Electric automobile charging navigation and path selection method based on traffic balance |
CN113011676A (en) * | 2021-04-02 | 2021-06-22 | 银隆新能源股份有限公司 | Route determination method, device and system, nonvolatile storage medium and processor |
CN113111514A (en) * | 2021-04-12 | 2021-07-13 | 清华大学深圳国际研究生院 | Vehicle microscopic driving scene simulation method and computer readable storage medium |
-
2021
- 2021-08-03 CN CN202110887080.7A patent/CN113326641B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104567897A (en) * | 2013-10-16 | 2015-04-29 | 大陆汽车投资(上海)有限公司 | Road condition forecast combined path planning method and navigation device |
CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
CN112686441A (en) * | 2020-12-28 | 2021-04-20 | 燕山大学 | Electric automobile charging navigation and path selection method based on traffic balance |
CN113011676A (en) * | 2021-04-02 | 2021-06-22 | 银隆新能源股份有限公司 | Route determination method, device and system, nonvolatile storage medium and processor |
CN113111514A (en) * | 2021-04-12 | 2021-07-13 | 清华大学深圳国际研究生院 | Vehicle microscopic driving scene simulation method and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN113326641A (en) | 2021-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113326641B (en) | Path planning method and device, computer equipment and storage medium | |
CN107111794B (en) | Predicting and exploiting variability of travel time in a mapping service | |
JP7163099B2 (en) | ENERGY MANAGEMENT DEVICE, MODEL MANAGEMENT METHOD AND COMPUTER PROGRAM | |
De Palma et al. | METROPOLIS: Modular system for dynamic traffic simulation | |
Ukkusuri et al. | A-rescue: An agent based regional evacuation simulator coupled with user enriched behavior | |
CN111158401B (en) | Distributed unmanned aerial vehicle path planning system and method for encouraging space-time data exploration | |
CN111612122A (en) | Method and device for predicting real-time demand and electronic equipment | |
CN111656735A (en) | Testing embedded systems and applications using hardware-in-the-loop service (HILAAS) | |
CN111667693B (en) | Method, apparatus, device and medium for determining estimated time of arrival | |
CN117094631B (en) | Goods transportation management method and system based on Internet of things | |
US20220164913A1 (en) | Systems and methods for utilizing models to determine real time estimated times of arrival for scheduled appointments | |
CN115311860B (en) | Online federal learning method of traffic flow prediction model | |
Afian et al. | Inferring unmet demand from taxi probe data | |
CN109284891B (en) | Charging pile maintenance scheduling method based on time-space index | |
CN115049167B (en) | Traffic situation prediction method, device, equipment and storage medium | |
Kammoun et al. | An adaptive vehicle guidance system instigated from ant colony behavior | |
Wilbur et al. | An online approach to solve the dynamic vehicle routing problem with stochastic trip requests for paratransit services | |
Fanti et al. | Modeling virtual sensors for electric vehicles charge services | |
Abidin et al. | Towards improved vehicle arrival time prediction in public transportation: integrating SUMO and Kalman filter models | |
JP2023155476A (en) | Information processing system, information processing apparatus, information processing method, and information processing program | |
Kluge et al. | On the computation of the energy-optimal route dependent on the traffic load in Ingolstadt | |
Luo et al. | ACP based large-scale coordinated route planning: from perspective of Cyber-Physical-Social Systems | |
JP2020027023A (en) | Information processing apparatus, information processing method and computer program | |
Tsai et al. | An IoT based parking recommendation system considering distance and parking lot flow | |
Panovski et al. | Real-time public transportation prediction with machine learning algorithms |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40050091 Country of ref document: HK |