CN114861514A - Planning method and device for vehicle driving scheme and storage medium - Google Patents

Planning method and device for vehicle driving scheme and storage medium Download PDF

Info

Publication number
CN114861514A
CN114861514A CN202110150312.0A CN202110150312A CN114861514A CN 114861514 A CN114861514 A CN 114861514A CN 202110150312 A CN202110150312 A CN 202110150312A CN 114861514 A CN114861514 A CN 114861514A
Authority
CN
China
Prior art keywords
road
road section
time
traffic
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.)
Pending
Application number
CN202110150312.0A
Other languages
Chinese (zh)
Inventor
丁涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN202110150312.0A priority Critical patent/CN114861514A/en
Priority to PCT/CN2021/122425 priority patent/WO2022166239A1/en
Publication of CN114861514A publication Critical patent/CN114861514A/en
Pending legal-status Critical Current

Links

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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

A method, an apparatus and a storage medium for planning a driving scheme of a vehicle, wherein the method comprises: acquiring a navigation route from a starting point to a destination at a specified moment, wherein the navigation route comprises one or more road section units, and each road section unit in the one or more road section units is a road section between two road points; obtaining historical traffic data information of the navigation route; performing track cost evaluation on the road traffic model of each road section unit in the one or more road section units by taking time as a baseline based on the historical traffic data information to obtain an evaluation result meeting the planning requirement; determining travel time and arrival time respectively corresponding to the two waypoints of each road section unit according to the evaluation result meeting the planning requirement; and determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.

Description

Planning method and device for vehicle driving scheme and storage medium
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to a method and an apparatus for planning a vehicle driving scheme, and a storage medium.
Background
The unmanned vehicle is one of intelligent vehicles, also called as an automatic driving vehicle, and mainly achieves the purpose of unmanned driving by means of control equipment which is mainly a computer system in the vehicle. Unmanned vehicles can typically sense the surrounding environment and navigate without manual manipulation. As the in-vehicle terminal device, a control device for controlling unmanned driving is sometimes called an Electronic Control Unit (ECU), a Domain Control Unit (DCU), a Mobile Data Center (MDC), or the like. Before the unmanned vehicle automatically runs on the road, a route which can avoid obstacles and is in line with the dynamics of the vehicle can be planned by the control device, and the vehicle is controlled to run according to the planned track with high precision. It is somewhat similar to the brain issuing commands to get the hand to hold something, and how to do so is done by the hand itself.
When planning a route, a navigation route needs to be planned first, and the navigation route may be a route with a large span. For example, if a passenger needs to go home from an airport, open a map stored in the vehicle-mounted terminal, search for an airport to a home for 35 kilometers, the control device can plan several routes from the airport to the home to be displayed on the map of the vehicle-mounted terminal, and the routes are navigation routes. After the unmanned vehicle determines a navigation route from the routes to automatically drive on the road, avoidance needs to be carried out according to whether a vehicle needs to be carried out in front of the current route or not, and traffic lights need to be considered, and the unmanned vehicle accelerates when and decelerates when. Therefore, a short-term route is also required to be planned according to the current real-time driving situation, and the short-term route is often in the range of 100-200 meters. Since the unmanned vehicle is traveling while the other vehicles are also traveling, the previously planned short-term route may not always fit, which is dynamically adjusted every 0.1 second.
However, when the existing scheme is used for planning the navigation route, how to reasonably plan the driving scheme and improve the driving experience is a problem to be solved.
Disclosure of Invention
In order to solve the above problems, embodiments of the present application provide a method, an apparatus, and a storage medium for planning a vehicle driving scheme.
In a first aspect, an embodiment of the present application provides a method for planning a vehicle driving scheme, where the method includes: the method comprises the following steps: acquiring a navigation route from a starting point to a destination at a specified moment, wherein the navigation route comprises one or more road section units, and each road section unit in the one or more road section units is a road section between two road points; obtaining historical traffic data information of the navigation route; performing track cost evaluation on the road traffic model of each road section unit in the one or more road section units by taking time as a baseline based on the historical traffic data information to obtain an evaluation result meeting the planning requirement; determining travel time and arrival time respectively corresponding to the two waypoints of each road section unit according to the evaluation result meeting the planning requirement; and determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
Therefore, when the unmanned vehicle carries out automatic driving planning, the unmanned vehicle can be planned by combining with the historical passing experience of the current road to obtain the optimal driving track in the whole course, so that the unmanned vehicle can reach a specific destination within the planned time and obtain the optimal driving experience.
In a possible implementation manner, the determining, according to the travel time and the arrival time respectively corresponding to the two waypoints of each road segment unit, a driving scheme on the navigation route that meets the planning requirement includes: determining the running speed of the vehicle on each road section unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit; and determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit and the driving speed of the vehicle on each road section unit.
In one possible embodiment, the historical traffic data information of the navigation route includes one or more of the following items:
the vehicle control information, the travel information and the traffic participant information and the traffic information around the vehicle of the vehicle passing at a plurality of different moments in a historical time period on the one or more road section units.
In this way, the historical traffic data information is classified by taking time as a base line and taking the road section units with fixed lengths as statistical units, so that the classification statistics and the feature extraction of the data are conveniently carried out by taking time as a dimension.
In one possible embodiment, the one or more link units are obtained by dividing the navigation route according to link lengths, or the one or more link units are obtained by dividing the navigation route according to traffic flows or traffic elements.
Therefore, the historical traffic data information of each road section unit is obtained by taking the road section units with fixed lengths as statistical units, so that the classification statistics and the feature extraction of subsequent data are facilitated. And taking the road section units divided according to the traffic flow and the traffic elements as statistical units, and acquiring the historical traffic data information of each road section unit, so as to facilitate the classification statistics and feature extraction of subsequent data.
In a possible embodiment, the method further comprises establishing a road traffic model for each of the one or more road segment units according to the historical traffic data information.
In a possible embodiment, the building a road traffic model of each of the one or more road segment units according to the historical traffic data information includes: extracting one or more traffic characteristics on each road section unit from the historical traffic data information by taking time as a base line; and establishing a plurality of road traffic models with time as a base line on each road section unit according to one or more traffic characteristics on each road section unit.
In this way, the modeling element can be determined through the traffic characteristics with the time as the base line, and the road traffic model at different moments with the time as the base line can be determined based on the modeling element, so that the accuracy and the comprehensiveness of the road traffic model can be ensured.
In one possible embodiment, the building a plurality of road traffic models with time as a base line on each road segment unit according to one or more traffic characteristics on each road segment unit comprises: accumulating the one or more traffic characteristics on each road section unit, and establishing a plurality of road traffic models with time as a base line on each road section unit.
Therefore, the modeling element values can be determined by selecting a plurality of traffic characteristics as required by taking time as a base line, and the road traffic model at different moments can be determined based on the modeling element values, so that the accuracy and the comprehensiveness of the road traffic model can be ensured.
In a possible embodiment, the building a plurality of road traffic models with time as a base line on each road section unit according to one or more traffic characteristics on each road section unit comprises: and establishing a road traffic model with time as a base line by the one or more traffic characteristics on each road section unit through an RNN recurrent neural network.
In one possible embodiment, the method further comprises: establishing an evaluation system of the road traffic model according to the historical traffic data information, wherein the evaluation system of the road traffic model comprises track cost values corresponding to the one or more traffic characteristics at different moments; and setting track cost values corresponding to the one or more traffic characteristics at different moments, and establishing an evaluation system of the road traffic model.
Therefore, specific evaluation standards of the road passing model are established according to the passing characteristics, and the grade standards of the determined passing characteristics at different moments are used for evaluating the advantages and disadvantages of the driving scheme of the road passing model planning at different moments.
In one possible embodiment, the traffic characteristics include one or more of: a vehicle control feature, a trip feature, a traffic participant feature, a traffic feature, an arrival time feature, a traffic light wait time feature, and a green light transit time feature.
Therefore, comprehensive modeling data is covered through a plurality of different traffic characteristics, so that the accuracy and the comprehensiveness of the road traffic model can be ensured.
In a possible implementation manner, the performing, based on the historical traffic data information, a trajectory cost evaluation on the road traffic model of each road segment unit by taking time as a baseline to obtain an evaluation result meeting a planning requirement includes: according to the road traffic model evaluation system, calculating or weighting and summing track cost values corresponding to a plurality of traffic characteristics of each road traffic model by taking time as a base line to obtain a comprehensive track cost value of each road traffic model of each road section unit at different moments; and comparing the comprehensive track cost value by taking time as a base line to obtain an evaluation result meeting the planning requirement.
In this way, the track cost of the road traffic model at different moments with the time as the base line can be evaluated to obtain the road traffic model meeting the planning requirement.
In a possible implementation manner, the determining, according to the evaluation result meeting the planning requirement, the travel time and the arrival time corresponding to the two waypoints of each road segment unit includes: according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of the starting waypoint of each road section unit; according to the travel time of the starting waypoint and in combination with the road speed limit condition, appointing the arrival time of the terminating waypoint of each road section unit; and obtaining the travel time and the arrival time from the starting waypoint to the ending waypoint.
In this way, the track cost evaluation can be performed on the road traffic model with time as a base line at different moments based on traffic characteristics, so as to obtain the road traffic model meeting the planning requirements.
In a possible implementation manner, the determining, according to the evaluation result meeting the planning requirement, the travel time and the arrival time corresponding to the two waypoints of each road segment unit includes:
according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of each road section unit at the starting waypoint; calculating an interval of the arrival time of the termination waypoint of each road section unit according to the travel time of the starting waypoint of each road section unit and the road speed limit condition; planning the travel time of the next road section unit of each road section unit according to the interval of the arrival time of the termination road point of each road section unit; and taking the travel time of the next road section unit of each road section unit as the arrival time of each road section unit, and obtaining the travel time and the arrival time corresponding to two waypoints of each road section unit respectively.
In a possible implementation manner, the determining the driving speed of the vehicle on each road segment unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road segment unit includes: determining the running speed of the vehicle on each road section unit by using a speed optimization formula according to the travel time and the arrival time corresponding to the two road points of each road section unit, wherein the speed optimization formula is as follows:
Figure BDA0002932478770000031
wherein f is an optimization result of the optimization function, and the optimization objective is to minimize f when the unmanned vehicle speed planning is carried out; s i Representing the travel of the ith actual waypoint;
Figure BDA0002932478770000032
representing the ith planned waypoint journey; w is a s Representing a positional deviation weight;
Figure BDA0002932478770000033
representing an acceleration deviation weight;
Figure BDA0002932478770000034
represents the acceleration of the vehicle, with index i being the ith planned waypoint;
Figure BDA0002932478770000035
the deviation weight of the speed value representing the change of the vehicle in the acceleration;
Figure BDA0002932478770000036
the fast and slow values of the acceleration change are shown, and the subscript i → i +1 is the planned waypoint from the ith to the (i + 1) th; w is a t Representing a time of arrival deviation weight; t is t i Representing the predicted time to reach the terminal point when travelling from the ith waypoint;
Figure BDA0002932478770000037
represents the planned arrival time when traveling from the ith waypoint.
In one possible embodiment, determining the traveling speed of the vehicle on each road segment unit by using the speed optimization formula further includes:
set waypoint travel s i Speed of
Figure BDA0002932478770000038
Acceleration of a vehicle
Figure BDA0002932478770000039
Upper and lower limit values of (d);
set waypoint travel s i Speed of
Figure BDA00029324787700000310
Acceleration of a vehicle
Figure BDA00029324787700000311
The relationship constraint between (a) and (b) is:
Figure BDA0002932478770000041
wherein, Δ t is the difference between the travel time and the arrival time planned from the ith waypoint;
set speed
Figure BDA0002932478770000042
Acceleration of a vehicle
Figure BDA0002932478770000043
The relation between the two is restricted;
Figure BDA0002932478770000044
setting acceleration
Figure BDA0002932478770000045
And the fast and slow values of the acceleration change
Figure BDA0002932478770000046
The relationship constraint of (1) is:
Figure BDA0002932478770000047
therefore, the data information provided by the road traffic model meeting the planning requirement can be utilized, and the current environment information is combined to make a traffic target, wherein the traffic target reaches a certain waypoint before a certain moment, so that the optimal driving experience of the whole traffic process is obtained.
In a second aspect, embodiments of the present application provide an apparatus for planning a driving scheme of a vehicle, which may include a module for executing the corresponding module in any one of the above embodiments, where the module may be software, hardware, or both. Advantageous effects can be referred to the description in the first aspect. For example, the apparatus may comprise: the route determining module is used for acquiring a navigation route from a starting point to a destination at a specified moment, wherein the navigation route comprises one or more road section units, and each road section unit in the one or more road section units is a road section between two road points; the data acquisition module is used for acquiring historical traffic data information of the navigation route; the model evaluation module is used for evaluating the track cost of the road traffic model of each road section unit in the one or more road section units by taking time as a baseline based on the historical traffic data information to obtain an evaluation result meeting the planning requirement; the time planning module is used for determining travel time and arrival time respectively corresponding to the two waypoints of each road section unit according to the evaluation result meeting the planning requirement; and the scheme planning module is used for determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
In a third aspect, embodiments of the present application provide an electronic device, and beneficial effects may refer to the description in the first aspect. The electronic device comprises a memory and a processor; the processor is configured to execute the computer-executable instructions stored in the memory, and the processor executes the computer-executable instructions to perform the method for unmanned planning according to any of the above embodiments.
In a fourth aspect, embodiments of the present application provide a vehicle comprising the apparatus of the second or third aspect described above.
In a fifth aspect, embodiments of the present application provide a storage medium, and advantageous effects may be found in the description of the first aspect. The storage medium comprises a readable storage medium and a computer program stored in the readable storage medium, the computer program being configured to implement the method of unmanned planning according to any of the embodiments described above.
In a sixth aspect, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method of the above aspects.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments disclosed in the present application, the drawings required to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only embodiments disclosed in the present application, and other drawings can be obtained according to the drawings without creative efforts for those skilled in the art.
Fig. 1 is a schematic view of a scene in which an unmanned vehicle acquires a navigation route from a- > B from a high-precision map in a first scheme;
fig. 2 is a flowchart of a method for planning a vehicle driving scheme according to an embodiment of the present application;
fig. 3 is a flowchart of a method for planning a vehicle driving scenario according to an embodiment of the present application, where the time is used as a baseline to evaluate a trajectory cost;
fig. 4 is a flowchart of a method for planning a vehicle driving scheme according to an embodiment of the present application for constructing a road traffic model;
fig. 5 is a Time-Cost curve diagram of traveling from a starting point in a method for planning a vehicle driving scenario according to an embodiment of the present application;
fig. 6 is a scene graph cut by a fixed route from a starting point- > a terminal point according to a traffic situation when going out from the starting point in the planning method for a vehicle driving scheme provided in the embodiment of the present application;
fig. 7 is a functional block diagram of an apparatus for planning a driving scheme of a vehicle according to an embodiment of the present disclosure;
fig. 8 is a schematic view of an electronic device for planning a vehicle driving scheme according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.
The high-precision map is an electronic map with high precision and specially provided for automatic driving, the precision reaches centimeter level, and the precision is required to be at lane line level. The common data information of the high-precision map comprises lane lines, central lines, traffic lights, road signboards, stop lines, lane line types and the like.
In one possible solution, the planning module of the control device obtains a navigation route from the starting point to the end point based on a high-precision map. And generating track waypoints on the high-precision map according to the navigation route from the starting point to the end point to obtain one or more passing routes. The point set of the road points generated when the unmanned vehicle carries out navigation planning and path planning is composed of a plurality of road points, the road points can be traffic signs or moving barriers in front of driving, each road point represents a real road coordinate, and the road points in the point set are linked one by one to form one or a plurality of passing lines. The starting point, the end point, the destination point and the passing point on the navigation route may also include a point set at the waypoint.
The planning module can carry out cost evaluation on the moving track based on various constraint conditions, so that the moving track of the unmanned vehicle automatic driving can be planned according to the cost evaluation result. The constraint conditions may include collision-related constraints, comfort-related constraints, speed limit-related constraints, law compliance-related constraints, and the like. And accumulating the track cost of all the constraint conditions on one driving track, wherein the obtained numerical value is the comprehensive cost of the driving track. And sorting the different running tracks according to the magnitude of the comprehensive cost value, and selecting the running track corresponding to the minimum value of the comprehensive cost as the final short-term optimal running track according to the sorting.
The track cost corresponding to each constraint condition can be set respectively. For example: the trajectory Cost of the collision-related constraint is Cost1, and a larger value of Cost1 indicates that the probability of collision with the obstacle is higher on the travel trajectory, for example, Cost 1-6 indicates that the probability of collision with the obstacle is higher on the travel trajectory, and Cost 1-3 indicates that the probability of collision with the travel trajectory is smaller than that of the travel trajectory corresponding to Cost 1-6; for another example, the track Cost of the comfort-related constraint is Cost2, and a larger value of Cost2 indicates a lower comfort level for the passenger on the travel track, e.g., Cost2 ═ 6 indicates that the transition between waypoints and the change in speed in the travel track make the passenger feel extremely uncomfortable, and Cost2 ═ 0 indicates that the transition between waypoints and the change in speed in the travel track make the passenger feel comfortable; for another example, the trajectory Cost of the constraint related to the speed limitation is Cost3, and a larger value of Cost3 indicates that the speed-limited travel included in the action trajectory is more, for example, Cost3 indicates that the travel trajectory includes a motor travel with a speed limitation, and Cost3 indicates that the travel trajectory does not include a motor travel with a speed limitation, when Cost3 equals 5; for example, the trajectory Cost for legally complying with the relevant constraint is Cost4, a larger value of Cost4 indicates a higher possibility that the action trajectory violates the traffic regulation, Cost4 indicates that the running trajectory includes a maneuver that violates the traffic regulation, and Cost4 indicates that the running trajectory does not include a maneuver that violates the traffic regulation. It should be noted that the above description is illustrative and not restrictive.
In the scheme, the automatic driving planning scheme of the unmanned vehicle respectively formulates a whole-course track and a temporary track which need to be automatically driven through whole-course planning and local planning. Firstly, an unmanned vehicle makes a whole-course track from a starting point to a terminal point through a high-precision map and current traffic flow information; and then, local planning is carried out on the environment where the current unmanned vehicle is located through sensor data, a high-precision map, high-precision positioning and driving track prediction, and a currently ideal navigation route is formulated.
However, the unmanned vehicle which is automatically driven by the navigation route planned by the scheme can completely have different riding experiences and driving effects of passengers at different times and under different conditions even if the unmanned vehicle is on the same road segment and the same starting point and the same ending point.
Taking a certain road as an example, the road is provided with a plurality of traffic lights, and unmanned vehicles travel at different speeds at different moments, so that under different traffic environments, locally planned track waypoints are different every time, and the time for reaching each waypoint is different. Some unmanned vehicles can run fast all the time in a locally planned running track, but just each intersection can meet a red light, and the unmanned vehicles need to stop for several seconds and then start slowly to continue running. Due to frequent acceleration, deceleration, parking and waiting, the passenger experience of riding is very poor. Some unmanned vehicles can run stably all the time in a locally planned running track, and just each intersection meets a green light, so that the unmanned vehicles do not need to stop all the way and directly run stably, and riding experience brought by the unmanned vehicles is excellent.
The following describes a method for planning a vehicle driving scheme provided by an embodiment of the present application.
For a navigation route from a starting point to a destination at the current moment, when the driving track is planned, the planning requirement is to enable the unmanned vehicle to obtain the global optimal or better comprehensive travel effect in one or more aspects as far as possible: the system has the advantages of quickest arrival, least starting and stopping, least sudden braking, least traffic jam and the like, so that passengers on the vehicle can obtain driving experience which meets the planning requirements. The driving experience can be measured according to the indexes such as average braking acceleration and deceleration, braking acceleration times, turning amplitude, waiting time, average speed, avoidance times and the like.
The embodiment of the application discloses a planning method of a vehicle driving scheme, which can evaluate the track cost of each road section at different moments on each road section on a navigation route where an unmanned vehicle passes based on historical communication data information, and obtain the ideal travel time and the ideal arrival time of a road point on the road section according to the evaluation result; and obtaining a driving scheme meeting the planning requirement according to the ideal travel time and the ideal arrival time.
In most scenes, the ideal arrival time and the ideal departure time of a road point are the same, for example, passengers want to encounter a green light at each intersection, so that the passengers can directly and smoothly drive through the road without stopping the vehicle all the way. When planning the driving scheme, the speed is solved by taking time as one of the constraint conditions, and a series of driving schemes which can reach a specific destination on the road section within a specified time are obtained.
The historical traffic data information is a data and behavior set of a road section in historical traffic. For example, vehicle control information and travel information of the unmanned vehicle at the historical passing time on the road section, traffic information in the surrounding environment, traffic participant information and the like, and according to the information, the time of travel, where the vehicle is not blocked, the time of travel without encountering a large number of pedestrians and vehicles and the like can be known.
The unmanned vehicle can continuously collect historical traffic data information of the unmanned vehicle passing on the navigation route by itself in a sensor and a domain controller of the vehicle, wherein the historical traffic data information comprises vehicle control information, such as a throttle, a brake, a steering wheel, a steering lamp and the like, and environment information related to travel, traffic participants and the like; and establishing a set of road traffic model with time as a base line according to the historical traffic data information.
Modeling elements required for constructing the road traffic model relate to vehicle control information, travel information, traffic information in the surrounding environment, traffic participant information and the like of the unmanned vehicle at the historical traffic moment on the road section. Specifically, the vehicle control information of the unmanned vehicle comprises emergency braking times, emergency avoidance times, large-amplitude accelerator times, large-amplitude braking times and the like; the travel information comprises track speed change rate, track curvature, average vehicle speed, arrival time and the like; the traffic information in the surrounding environment comprises the times of the occurrence of the blocking obstacles and the times of the occurrence of the dangerous obstacles, the times of red light, the times of green light, the times of yellow light and the like; the traffic participant information includes the number of occurrences and waiting time of other traffic objects such as vehicles, pedestrians, and the like.
The emergency brake is an emergency brake phenomenon generated by suddenly stepping on the brake in order to avoid traffic participants, obstacles and the like in the driving process of the vehicle. The emergency avoidance is a sharp turning phenomenon caused by the fact that a steering wheel is hurled in order to avoid traffic participants, obstacles and the like in the driving process of a vehicle. The blocking obstacle is an obstacle causing a brake pause phenomenon of the unmanned vehicle and is called as a blocking obstacle of the unmanned vehicle. The dangerous barrier is a barrier which is too close to the unmanned vehicle or has a cross track with the unmanned vehicle and can cause the unmanned vehicle to take over emergently, brake, avoid and the like.
In the embodiment of the application, the road traffic model describes traffic information of a road section at different moments in a time period, and the traffic information may include one or more traffic characteristics of the current road section, and the traffic characteristics may show different characteristics along with time, so that the evaluation score of the track cost corresponding to the traffic characteristics is different along with the time. After the planning scheme of one road section is completed, the next road point can be used as a destination, the track cost of different moments is evaluated by utilizing a road traffic model of the next road section, the ideal travel time and the ideal arrival time of the next road point are calculated, and the driving scheme of the unmanned vehicle is planned again. And circulating the steps until the end point, and obtaining a driving scheme which meets the planning requirement on the whole course of the navigation route.
The unmanned vehicle running by using the running scheme planned by the evaluation result of the road traffic model can reach a specific destination within the planned time and obtain better driving experience.
Before the control device of the unmanned vehicle executes the planning method of the vehicle driving scheme provided by the embodiment of the application, a road traffic model and an evaluation system of the road traffic model are established according to historical traffic data information.
The method is described in detail below.
Fig. 2 is a flowchart of a method for planning a vehicle driving scheme according to an embodiment of the present application, and as shown in fig. 2, a control device of an unmanned vehicle performs the following steps to plan the driving scheme:
s21, a navigation route from a starting point to a destination at a specified time is obtained, the navigation route including one or more link elements, each link element being a link between two waypoints on the navigation route.
Specifically, the control device of the unmanned vehicle may acquire a navigation route from a start point to a destination at the present time from a high-precision map, and segment the navigation route into a plurality of segments. And recording the road section between every two waypoints as a road section unit.
In one possible embodiment, the navigation route from the starting point to the destination may be divided into a plurality of segments according to segment lengths, and accordingly, two waypoints are the starting point and the ending point of both ends of the segment, and for example, the navigation route may be divided according to a segment length of 100 and 200 meters.
Alternatively, the navigation route from the start point to the destination may be divided into a plurality of segments according to traffic flow or traffic elements. For example, the navigation route may be divided into a plurality of road segments according to road points before and after the traffic light intersection, and accordingly, two road points may be positions where the traffic light intersections at both ends of the road segments are located, or the navigation route may be divided into a plurality of road segments according to road points before and after the road segments where traffic congestion often occurs, and accordingly, two road points may be starting points and ending points at both ends of the congested road segments; or the navigation route is divided into a plurality of road sections according to road points before and after the crossroad, and correspondingly, the two road points can be the positions of the crossroad at the two ends of the road section.
And S22, acquiring historical traffic data information on the current navigation route.
Specifically, the control device of the unmanned vehicle collects time-based historical traffic data information on each section of the current navigation route.
For example, the historical traffic data information at a certain time on each road section may include the vehicle control information and the trip information of the unmanned vehicle itself passing on the road section; the traffic information of other vehicles participating in the traffic, such as the running speed, the quantity and the like, can be included, the traffic information of other vehicles is recorded as the traffic participant information, and the traffic information of the road section at the moment, such as the traffic light time, the congestion time and the like, can also be included.
In one possible implementation, vehicle control information and travel information at a certain time may be collected by a sensor of the unmanned vehicle and a vehicle domain controller; the information of all traffic participants at a certain moment and the traffic information at a certain moment can be acquired through intelligent network connection or data stored in a cloud.
It is to be understood that the historical traffic data information based on time includes historical traffic data information at a plurality of times within a certain set period of time.
And S23, based on the historical traffic data information, performing track cost evaluation on the road traffic model of each road section by taking time as a baseline, and obtaining an evaluation result meeting the planning requirement. As shown in fig. 3, S23 is specifically realized by performing the following steps S231-S233.
S231, determining that the road traffic model of the unmanned vehicle is as follows:
Figure BDA0002932478770000081
formula (1) Key i→j Road traffic model, Key, from ith to jth road section n For the road traffic model of the nth section of road nm Is the mth traffic feature on the nth road segment. i. j and m are natural numbers.
And S232, according to the road traffic model evaluation system, summing track cost values corresponding to a plurality of traffic characteristics of the current road traffic model by taking time as a base line (the weight is 1), and obtaining a comprehensive track cost value of each road traffic model of each road section.
The evaluation formula corresponding to the road traffic model of the unmanned vehicle of formula (1) is:
Figure BDA0002932478770000082
cost in equation (2) i→j For the combined track Cost of the navigation route from the ith to the jth road segment, Cost i The track cost of a link starting from the ith waypoint. W 1 Pass feature key n1 Weight value of (1), cost nt1 Passing feature key representing nth road section at time t n1 Cost of trace of, W 2 Pass feature key n2 Weight value of (1), cost it2 Passing characteristic key for nth road section at t time n2 Track cost of (W) m Pass feature key nm Weight value of (1), cost ntm Characteristic key for representing nth road section passing at t time nm The track cost of (1). Formula (2) shows that the integrated track cost of the navigation route from the ith road point to the jth road point is the track cost accumulation of the road traffic models corresponding to the ith road section to the jth road section; and the value of the integrated track cost from the ith road section to the jth road section is the weighted sum of the track cost scores corresponding to all traffic characteristics on the route.
In a possible implementation manner, according to a road traffic model evaluation system, with time as a baseline, the vehicle control characteristics, the travel characteristics, the traffic participant characteristics and the track cost scores corresponding to the traffic characteristics at different moments on the current road section are weighted and summed with the time as the baseline, and the comprehensive track cost of the road traffic model of each road section with the time as the baseline is obtained.
In a possible implementation mode, a statistical threshold corresponding to the arrival time characteristic, a statistical threshold corresponding to the traffic light waiting time characteristic and a statistical threshold corresponding to the green light passing time characteristic can be obtained according to historical passing data information statistics; according to a road traffic model evaluation system, with time t as a base line, weighting and summing track cost values corresponding to statistical thresholds of the arrival time characteristic, traffic light waiting time characteristic and green light traffic time characteristic of t moment on each road section respectively to obtain the comprehensive track cost of the road traffic model.
And S233, evaluating the comprehensive track cost values of different moments on the current road section by taking time as a base line, and obtaining an evaluation result meeting the planning requirement.
The planning requirement is to enable the unmanned vehicle to obtain global optimal or superior comprehensive travel effects in one or more aspects as far as possible: the method has the advantages of quickest arrival, least start and stop, least emergency brake, least traffic jam and the like, so that passengers on the vehicle can obtain the driving experience meeting the planned requirements.
Whether the planning requirements are met or not can be evaluated through the score of the comprehensive track cost of the road traffic model.
In one possible implementation manner, the comprehensive track cost values of the road traffic model on the current road section at different times can be compared, and the time t corresponding to the larger comprehensive track cost value is taken as the evaluation result meeting the planning requirement.
For example: in an evaluation system of a road traffic model, the track cost scores of all traffic characteristics are set on the basis that the track cost scores are larger and more accord with planning requirements, and the time t corresponding to the larger comprehensive track cost value is an evaluation result which accords with the planning requirements.
In a possible implementation manner, the comprehensive track cost values of the road traffic model on the current road section at different times can be compared, and the time t corresponding to the smaller comprehensive track cost value is taken as the evaluation result meeting the planning requirement.
For example: in an evaluation system of a road traffic model, the track cost scores of all traffic characteristics are set on the basis that the smaller the track cost score is, the more the traffic characteristics meet the planning requirements, and the time t corresponding to the smaller comprehensive track cost value is the evaluation result meeting the planning requirements.
S24, obtaining the travel time and arrival time of each road section unit from the starting waypoint to the ending waypoint according to the evaluation result meeting the planning requirement;
specifically, the control device of the unmanned vehicle selects the time corresponding to the evaluation result meeting the planning requirement as the ideal travel time of the current waypoint by combining the current position and the current travel time. And meanwhile, the ideal arrival time of the next waypoint is obtained by planning by combining the current planning and road speed limit conditions of the unmanned vehicle.
In a possible implementation manner, time information corresponding to the route-to-route model can be obtained according to an evaluation result meeting the planning requirement, and the route time of the starting route point of each road section is determined; according to the travel time of the starting waypoint of each road section, the arrival time of the ending waypoint is appointed by combining the speed limit condition of the road; and obtaining the travel time and the arrival time from the starting waypoint to the ending waypoint.
In a possible implementation manner, according to an evaluation result meeting the planning requirement, time information corresponding to a road traffic model is obtained, and travel time of a starting waypoint of each road section is determined; calculating the interval of the arrival time of the termination waypoint of each road section according to the travel time of the start waypoint of each road section and by combining the road speed limit condition; planning travel time of the termination waypoints by taking the termination waypoint of the next road section of each road section as a destination according to the arrival time interval of the termination waypoints; and the travel time of the ending waypoint is the arrival time of each road section, and the travel time and the arrival time from the starting waypoint to the ending waypoint of each road section are obtained.
And S25, determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit. Specifically by performing the following steps S251-S252.
And S251, calculating according to the traveling time and the arrival time of the current road point by using the constraint conditions among the position, the speed and the time, and obtaining the traveling speed of the vehicle on the current road section.
And planning the corresponding speed of the path point of the track according to the traveling time of the current path point and the ideal arrival time of the next path point.
Specifically, the ideal arrival time is used as an input parameter and is input into a speed optimization formula, and when the track is generated, a reasonable corresponding speed of the track waypoint is planned, so that the purpose of reaching the target place by the ideal arrival time is achieved.
The speed optimization formula is as follows:
Figure BDA0002932478770000091
wherein f is an optimization result of the optimization function, and the optimization goal is to minimize f when the speed of the unmanned vehicle is planned; s i Representing the travel of the ith actual waypoint;
Figure BDA0002932478770000092
representing the planned waypoint journey of the ith; w is a s Representing a positional deviation weight;
Figure BDA0002932478770000093
representing an acceleration deviation weight;
Figure BDA0002932478770000094
represents the acceleration of the vehicle, with index i being the ith planned waypoint;
Figure BDA0002932478770000095
the deviation weight of the speed value representing the change of the vehicle in the acceleration;
Figure BDA0002932478770000096
the fast and slow values of the acceleration change are shown, and the subscript i → i +1 is the planned waypoint from the ith to the (i + 1) th; w is a t Representing a time of arrival deviation weight; t is t i Representing the predicted time to reach the terminal point when travelling from the ith waypoint;
Figure BDA0002932478770000097
represents the planned arrival time when traveling from the ith waypoint.
Setting the constraints of equation (3) includes:
setting a constraint of a position s of the starting point, derived from the planned starting point;
set waypoint travel s i Speed of
Figure BDA0002932478770000098
Acceleration of a vehicle
Figure BDA0002932478770000099
Upper and lower limit values of (d);
set waypoint travel s i Speed of
Figure BDA00029324787700000910
Acceleration of a vehicle
Figure BDA00029324787700000911
The relationship constraint between (a) and (b) is:
Figure BDA0002932478770000101
wherein, Δ t is the difference between the travel time and the arrival time planned from the ith waypoint;
set speed
Figure BDA0002932478770000102
Acceleration of a vehicle
Figure BDA0002932478770000103
The relation between the two is restricted;
Figure BDA0002932478770000104
setting acceleration
Figure BDA0002932478770000105
And the fast and slow values of the acceleration change
Figure BDA0002932478770000106
The relationship constraint of (1) is:
Figure BDA0002932478770000107
the constraints of equations (4) - (6) can make the s value at each time as close as possible to the position of the waypoint corresponding to the previously planned driving trajectory. And the acceleration and the value of the fast and slow value of the acceleration change are ensured to be as small as possible, and the driving comfort is ensured under the condition of the minimum arrival time error. In these constraints, a trade-off is performed, and finally, an optimization result of the driving speed is obtained.
And S252, planning on the navigation route according to the travel time, the arrival time and the running speed of each road section unit, and obtaining a running scheme meeting the planning requirement.
Specifically, the control device of the unmanned vehicle determines whether the terminal is reached, and if the determination result is "no", performs trajectory planning of the next route segment, and executes S24. If the judgment result is 'yes', planning on the navigation route according to the travel time, the arrival time and the travel speed of each road section to obtain a travel scheme meeting the planning requirement, and finishing the travel track planning of the unmanned vehicle.
The unmanned vehicle driving track planning method provided by the embodiment of the application is based on a road traffic model of the unmanned vehicle, the traffic time of a navigation route is optimized, the time is used as a constraint condition to participate in the planning of the driving track and the driving speed, and the triple constraint and planning of the position, the speed and the time are achieved. The method utilizes current and historical traffic experience to ensure that the unmanned vehicle has the optimal global situation during track planning, and the driving experience and traffic efficiency are greatly improved.
Before the planning method of the vehicle running scheme provided by the embodiment of the application is executed, a road traffic model is also established according to the historical traffic data information.
Specifically, after collecting historical traffic data information and selecting a traffic characteristic key and a threshold value, the control device of the unmanned vehicle selects a modeling formula and establishes a series of time-based road traffic models for the current road section. For example, modeling the cumulative sum of the multiple traffic characteristics may be selected, and the road traffic model obtained is:
Figure BDA0002932478770000108
in formula (7), Key all Road traffic models, keys, for planning routes n The length is a road passing model of the nth road section, and the length is the number of the road sections obtained by dividing the whole road.
A plurality of different traffic characteristics can be extracted for modeling through historical traffic data information.
Illustratively, the corresponding vehicle control features and travel features can be extracted by collecting historical traffic data information of the vehicle passing on a certain planned route, and the traffic participant features and the traffic features can also be extracted by data stored in an intelligent internet and a cloud terminal.
In one possible implementation, as shown in fig. 4, the building of the road traffic model according to the historical traffic data information includes the following steps:
and S41, extracting one or more traffic characteristics on each road section from the historical traffic data information by taking time as a base line.
Optionally, extracting traffic characteristics on each road section unit from data information of historical traffic experience by taking time as a base line; the traffic characteristics include vehicle control characteristics, trip characteristics, traffic participant characteristics, traffic characteristics, arrival time characteristics, red-green light wait time characteristics, and green light transit time characteristics.
And S42, accumulating the one or more traffic characteristics on each road section unit, and establishing a plurality of road traffic models with time as a base line on each road section.
Optionally, taking time as a baseline, selecting one or more traffic characteristics from the vehicle control characteristics, the travel characteristics, the traffic participant characteristics, the traffic characteristics, the arrival time characteristics, the traffic light waiting time characteristics and the green light traffic time characteristics on each road section unit as modeling elements to accumulate the traffic characteristics, and generating a road traffic model taking time as a baseline.
Alternatively, the road traffic model may be obtained by modeling using a Recurrent Neural Network (RNN).
According to the planning method of the vehicle running scheme provided by the embodiment of the application, a road traffic model is modeled by adopting a plurality of different traffic characteristics, and data corresponding to the plurality of different traffic characteristics cover comprehensive historical traffic data information, so that the accuracy of the road traffic model can be ensured; according to the accurate road traffic model, the driving scheme is evaluated and planned, so that the unmanned vehicle can achieve a good traffic effect when driving, and passengers who go out of the unmanned vehicle can obtain satisfactory driving experience.
Before the planning method of the vehicle running scheme provided by the embodiment of the application is executed, an evaluation system of a road traffic model is established according to the historical traffic data information.
A road traffic model assessment system may be established by formulating trajectory cost scoring criteria for traffic characteristics and thresholds. And establishing a track cost scoring standard aiming at the traffic characteristics and the threshold according to a plurality of different traffic characteristics and thresholds.
Before the road traffic model is manufactured, the traffic characteristics required by the road traffic model of the road section and the statistical threshold corresponding to the traffic characteristics are selected according to data corresponding to a plurality of different traffic characteristics and by combining with the real law.
After historical traffic data information is collected and traffic characteristics and threshold values are selected, a modeling formula is selected, and a series of time-based road traffic models are established by taking the current road point as a starting point. For example, the sum of the track costs corresponding to the traffic characteristics may be selected for evaluation, and the evaluation formula corresponding to the road traffic model of formula (7) is:
Figure BDA0002932478770000111
in the formula (8), Cost all Cost of the composite trajectory for planning a route, Cost n The length is the track cost of the nth road segment, and the length is the number of road segments obtained by segmenting the whole road.
In one possible implementation, one or more traffic characteristics may be extracted from historical traffic data information; and setting track cost scores corresponding to one or more traffic characteristics by taking the time as a baseline, and establishing an evaluation system of the road traffic model.
When an evaluation system of a road traffic model is established, the track cost scores of all traffic characteristics are set on the basis that the track cost scores are smaller and more accord with planning requirements. Or the larger the track cost score is, the more in accordance with the planning requirement, the track cost score of each passing characteristic is set as a principle.
In one possible implementation, traffic characteristics may be extracted from historical traffic data information, including vehicle control characteristics, travel characteristics, traffic participant characteristics and traffic characteristics, arrival time characteristics, traffic light wait time characteristics, and green light traffic time characteristics of the unmanned vehicle. And setting corresponding track cost scores of the vehicle control characteristic, the travel characteristic, the traffic participant characteristic, the traffic characteristic, the arrival time characteristic, the traffic light waiting time characteristic and the green light passing time characteristic at different moments by taking the time as a base line, and establishing an evaluation system of the road passing model.
For example, the threshold of the arrival time is analyzed by combining the historical traffic data information, the threshold1 of the traffic characteristic, which is the arrival time characteristic, is obtained as 5min, the route cost corresponding to the traffic characteristic exceeds threshold1 plus two points in the plan, and is not divided below threshold 1. .
And analyzing the threshold of the traffic light waiting time characteristic by combining historical traffic data information, and obtaining the threshold2 of the traffic light waiting time, which is the traffic characteristic, of 2min, wherein the threshold2 plus 3 points is exceeded in the planning of the track cost corresponding to the traffic characteristic, and the threshold is lower than the threshold2 without adding points.
And analyzing the threshold of the green light passing time characteristic by combining historical passing data information, and obtaining the threshold of the passing characteristic, namely the green light passing time, which is 7min, wherein the threshold exceeds 3 plus 2 points in the planning of the track cost corresponding to the passing characteristic and is not plus less than 3 points in the planning of the track cost corresponding to the passing characteristic.
By using the planning method of the vehicle running scheme provided by the embodiment of the application, the road traffic model of the unmanned vehicle is manufactured, and the running track of the unmanned vehicle is planned. The method comprises the following specific steps:
s501, selecting related modeling elements as passing characteristics (key) of a road passing model of the unmanned vehicle, setting evaluation scores (Value) of corresponding track costs (cost) for the passing characteristics, and setting related thresholds (threshold) for the passing characteristics of certain specific modeling elements. As shown in table 1, the modeling elements participating in the modeling of the road traffic model for the unmanned vehicle include vehicle control features and environmental features.
TABLE 1
Figure BDA0002932478770000121
For example, the traffic characteristics of the vehicle control characteristics in table 1 include "emergency avoidance" with an estimated score of "+ 5" for the corresponding trajectory cost; during local planning, if the fact that the unmanned vehicle has already presented an emergency avoidance at the current road point according to the historical traffic data information is known, the track cost of the road traffic model of the current road section is added with 5 points, if the unmanned vehicle presents multiple emergency avoidance at the road point, the track cost of the road traffic model of the road section is added with 5m points, and m is the number of times of presenting the emergency avoidance.
The passage characteristics of the vehicle control features in table 1 include a "time of arrival" feature, which corresponds to an assessment score of "> threshold + 2"; during local planning, if the time of the unmanned vehicle reaching the current target road point is calculated to exceed a threshold (threshold) according to the historical traffic data information and the planned speed information, the track cost of the road traffic model of the current road section is added by 2 points. If the threshold (threshold) of the arrival time is set to be 2 minutes, if the time when the unmanned vehicle arrives at the current target road point according to the current speed exceeds the specified arrival time by more than 2 minutes, the track cost of the current road traffic model is added by 2 minutes, and the track cost is not added when the track cost is lower than the threshold.
The traffic characteristics of the environmental information in table 1 include a "red light" characteristic, which corresponds to an evaluation score of "+ 3"; in the local planning, if the unmanned vehicle encounters 1 red light before reaching the target waypoint, the track cost of the road traffic model is added by 3 points. If the unmanned vehicle encounters a plurality of red lights before reaching the target waypoint, the track cost of the road traffic model of the road section is added with 3 x m, and m is the number of the red lights.
The traffic characteristics of other vehicle control information and environmental information and their evaluation scores are also shown in table 1, and the evaluation scores for specific track costs are similar to the above examples and are not illustrated.
The traffic characteristics and the evaluation scores thereof of other relevant elements may be added according to the planning scheme in table 1, and the cost calculation algorithm of the specific road traffic model is similar to the above example, or a trajectory cost algorithm of the corresponding road traffic model, which can be obtained by a person skilled in the art according to the above example in combination with common knowledge, is also within the scope of the present application.
And S502, establishing a simple road traffic model of the unmanned vehicle by combining the modeling equation of the formula (6) according to the traffic characteristics of the relevant modeling elements and the evaluation scores of the corresponding track costs. Illustratively, the road traffic model is modeled with the traffic time characteristic and the waiting time characteristic as modeled element values, and the road traffic model of the current unmanned vehicle is evaluated as:
Figure BDA0002932478770000131
cost in formula (9) i→j Cost for the composite track of the planned route from the ith to the jth road section n The track cost corresponding to the nth road segment. W 1 Weight value representing a characteristic of transit time, Cost nt1 Indicating the passage of the nth link at time tCost of trace of time, W 2 Weight value representing a characteristic of latency, Cost nt2 And representing the track cost corresponding to the nth section waiting time characteristic at the time t, wherein the waiting time characteristic comprises red light waiting time and/or congestion waiting time. Formula (9) shows a road traffic model evaluation formula of a route from the ith to the jth waypoints, and is a track cost accumulation of road traffic models of the respective road sections corresponding to the ith to jth road sections; the value of the comprehensive track cost of the route from the ith road section to the jth road section is the accumulation of the track cost of each road section corresponding to the ith road section to the jth road section; and similarly, the value of the comprehensive track cost of the route from the ith road section to the jth road section is the weighted sum of the track cost scores corresponding to the transit time characteristic and the waiting time characteristic on the planned route.
S503, modeling is carried out according to the morning of 7: 50-8: 50, and the track Cost of the road traffic model from the ith road section to the jth road section at different travel times is calculated according to a formula (9) i→j . According to historical traffic data information, the condition that the traffic jam is serious in the morning from 8:00 to 8:30 in the morning is known, and the weight value W of the waiting time characteristic 2 The value is large, and the waiting time track Cost is caused by serious traffic congestion nt2 Is relatively large.
Fig. 5 is a Time-Cost graph of travel from the beginning of a planned route. As shown in fig. 5, the horizontal axis represents a Time axis (Time), and the vertical axis represents a track Cost axis (Cost). Calculating the track Cost of the road traffic model when the travel time is 7:50 i→j Is 15; when the travel time is 8:00, calculating the track Cost of the road traffic model i→j Is 20; when the travel time is 8:10, calculating the track Cost of the road traffic model i→j Is 32; when the travel time is 8:20, calculating the track Cost of the road traffic model i→j Is 46; when the travel time is 8:30, calculating the track Cost of the road traffic model i→j Is 35; when the travel time is 8:40, calculating the track Cost of the road traffic model i→j Is 20; when the travel time is 8:50, calculating a road passing modelTrajectory Cost of type Cost i→j Is 18.
Analyzing the Time-Cost graph shown in fig. 5 can obtain the track Cost of the road traffic model when the travel Time is 7:50 i→j The riding experience and the driving effect of passengers are optimal; when the travel time is 8:20, the track Cost of the road traffic model i→j The maximum is the ride experience and the driving effect of the passengers.
S504, it is determined that the unmanned vehicle users 7:50 start traveling from the starting point, the fixed routes of the starting point- > the end point are divided into three road sections according to the traffic conditions. As shown in fig. 6, the three links are respectively a start point- > D1 of waypoint 1, a waypoint 1- > D2 of waypoint 2, and a waypoint 2- > D3 of an end point.
Specifically, the waypoint 1 is before the traffic light intersection, and D1 represents a first road segment from the starting point to the front of the traffic light intersection; the waypoint 2 is behind the traffic light intersection, and D2 represents a second road section from the front of the traffic light intersection to the back of the traffic light intersection; d3 denotes a third road segment from behind the traffic light intersection to the end point.
S505, taking 7:50 as a starting point for travel time, calculating according to the speed limit of the road section and the track planning condition of the unmanned vehicle, obtaining that the time range of reaching the waypoint 1 is 8:10-8:30, and calculating the track Cost of D1 according to the road traffic model of the unmanned vehicle within the range of 8:10-8:30 1 The ideal travel time point of the obtained waypoint 1 is 8:20, and the obtained waypoint can meet a green light, so that the vehicle can run smoothly without stopping; taking the time 8:20 as a constraint condition of speed track optimization, substituting the constraint condition into equations (3) - (5) to solve the speed, and obtaining a driving scheme which is started at the speed of 7:50 and reaches the waypoint 1 at the speed of 8:20 and meets the planning requirement.
S506, going out along the route of the waypoint 1-the waypoint 2, continuously and circularly solving the ideal arrival time according to the road traffic model of the unmanned vehicle, and carrying out speed solution.
Specifically, whether the unmanned vehicle reaches the end point is judged, if the judgment result is 'no', 8:20 is taken as the travel time of the waypoint 1, the time range of reaching the waypoint 2 is obtained by calculation according to the road speed limit and the unmanned vehicle track planning conditionAt 8:25-8:35, calculating the track Cost of the D2 road section according to the road traffic model of the unmanned vehicle 2 According to the track Cost 2 The travel time point of the ideal waypoint 2 obtained from the minimum value of the time points is 8:30, and the vehicle can run and pass through the ideal waypoint directly and stably without stopping; taking the arrival time 8:20 as a constraint condition for speed track optimization, substituting equations (3) - (5) to solve the speed, and obtaining a driving scheme meeting the planning requirement when the arrival time reaches the waypoint 2 at 8: 30.
And S507, repeating the step S506, planning the track of the next road section until the unmanned vehicle is finally judged to reach the terminal point, and canceling the track planning. And finishing the planning of the unmanned vehicle driving scheme.
According to the embodiment, the driving scheme is planned according to the road traffic model based on the unmanned vehicle, when the unmanned vehicle is planned based on the model, the model data can be fully utilized to avoid the waiting time of red light and the waiting of congested road sections, and the traffic efficiency and the driving experience are improved.
The embodiment of the present application further provides a device for planning a vehicle driving scheme, where the device may be deployed or integrated on a vehicle, is a part of a vehicle-mounted system, may be a vehicle-mounted control unit, such as an ECU, a DCU or an MDC, and may also be a semiconductor chip disposed in the vehicle-mounted system.
As shown in fig. 7, the apparatus obtains a navigation route from a starting point to a destination at a specified time by a route determination module 71, the navigation route including one or more link units, each of the one or more link units being a link between two waypoints; acquiring historical traffic data information of the navigation route through a data acquisition module 72; performing track cost evaluation on the road traffic model of each road section unit in one or more road section units by using time as a baseline through a model evaluation module 73 based on the history traffic data information to obtain an evaluation result meeting the planning requirement; determining travel time and arrival time respectively corresponding to two waypoints of each road section unit by the time planning module 74 according to the evaluation result meeting the planning requirement; and a driving scheme meeting the planning requirement on the navigation route is determined by the scheme planning module 75 according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
In an apparatus for planning a driving scheme of a vehicle provided in an embodiment of the present application, a time planning module includes: a speed calculation unit and a scheme planning unit; the device determines the running speed of a vehicle on each road section unit through a speed calculation unit according to the travel time and the arrival time respectively corresponding to two waypoints of each road section unit; and determining a driving scheme meeting the planning requirement on the navigation route by the scheme planning unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit and the driving speed of the vehicle on each road section unit.
Optionally, the historical traffic data information of the navigation route includes one or more of the following items: the vehicle control information, the travel information and the information of the traffic participants and the traffic information around the vehicle are used for the vehicle to pass at a plurality of different moments in a historical time period on one or a plurality of road section units.
In the apparatus for planning a driving scheme of a vehicle provided by an embodiment of the present application, one or more road segment units are obtained by dividing a navigation route according to a road segment length, or one or more road segment units are obtained by dividing a navigation route according to a traffic flow or a traffic element.
The device for planning the vehicle driving scheme further comprises a model building module, and the model building module is used for building a road traffic model of each road section unit in one or more road section units according to the historical traffic data information.
Optionally, the model building module comprises a used feature extraction unit, which extracts one or more traffic features on each road segment unit from the historical traffic data information by taking time as a baseline; and establishing a plurality of road traffic models with time as a base line on each road section unit according to one or more traffic characteristics on each road section unit through the modeling unit.
Optionally, the modeling subunit accumulates the one or more traffic characteristics on each road segment unit, and establishes a plurality of road traffic models with time as a baseline on each road segment unit.
Optionally, the modeling subunit is configured to establish a time-based road traffic model from the one or more traffic characteristics on each road segment unit through the RNN recurrent neural network.
In the device for planning the vehicle running scheme provided by the embodiment of the application, the device further comprises an evaluation system establishing module, an evaluation system of a road traffic model is established through the evaluation system establishing module according to the historical traffic data information, and the evaluation system of the road traffic model comprises track cost values corresponding to one or more traffic characteristics at different moments; and setting track cost scores corresponding to one or more traffic characteristics at different moments, and establishing an evaluation system of the road traffic model.
Optionally, the traffic characteristics include one or more of: a vehicle control feature, a trip feature, a traffic participant feature, a traffic feature, an arrival time feature, a traffic light wait time feature, and a green light transit time feature.
Optionally, the model evaluation module includes a calculation unit and an evaluation unit; according to the device, a calculation unit sums track cost values corresponding to a plurality of traffic characteristics of each road traffic model by taking time as a base line or weighting and summing according to a road traffic model evaluation system to obtain a comprehensive track cost value of each road traffic model of each road section unit at different moments; and the evaluation unit is used for comparing the comprehensive track cost value by taking time as a base line to obtain an evaluation result meeting the planning requirement.
In the device for planning the vehicle driving scheme provided by the embodiment of the application, the passing time planning module of the device obtains time information corresponding to the road passing model of each road section unit according to the evaluation result meeting the planning requirement, and determines the travel time of the starting waypoint of each road section unit; according to the travel time of the starting waypoint of each road section unit, the arrival time of the ending waypoint of each road section unit is appointed by combining the road speed limit condition; and obtaining the travel time and the arrival time from the starting waypoint to the ending waypoint.
Optionally, the device obtains time information corresponding to the road traffic model of each road section unit through a time planning module according to an evaluation result meeting the planning requirement, and determines the travel time of each road section unit at the starting waypoint; calculating an interval of the arrival time of the termination waypoint of each road section unit according to the travel time of the starting waypoint of each road section unit and the road speed limit condition; planning the travel time of the next road section unit of each road section unit according to the interval of the arrival time of the termination road point of each road section unit; and taking the travel time of the next road section unit of each road section unit as the arrival time of each road section unit, and obtaining the travel time and the arrival time corresponding to two waypoints of each road section unit respectively.
In an apparatus for planning a driving scheme of a vehicle provided in an embodiment of the present application, a speed calculation unit is configured to:
determining the running speed of the vehicle on each road section unit by using a speed optimization formula according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit, wherein the speed optimization formula is as shown in a formula (3):
Figure BDA0002932478770000151
wherein f is an optimization result of the optimization function, and the optimization goal is to minimize f when the speed of the unmanned vehicle is planned; s i Representing the travel of the ith actual waypoint;
Figure BDA0002932478770000152
representing the planned waypoint journey of the ith; w is a s Representing a positional deviation weight;
Figure BDA0002932478770000153
representing an acceleration deviation weight;
Figure BDA0002932478770000161
represents the acceleration of the vehicle, with index i being the ith planned waypoint;
Figure BDA0002932478770000162
the deviation weight of the speed value representing the change of the vehicle in the acceleration;
Figure BDA0002932478770000163
the fast and slow values of the acceleration change are shown, and the subscript i → i +1 is the planned waypoint from the ith to the (i + 1) th; w is a t Representing a time of arrival deviation weight; t is t i Representing the predicted time to reach the terminal point when travelling from the ith waypoint;
Figure BDA0002932478770000164
represents the planned arrival time when traveling from the ith waypoint.
Optionally, the speed calculating unit is further configured to:
set waypoint travel s i Speed of
Figure BDA0002932478770000165
Acceleration of a vehicle
Figure BDA0002932478770000166
Upper and lower limit values of (d);
set waypoint travel s i Speed of
Figure BDA0002932478770000167
Acceleration of a vehicle
Figure BDA0002932478770000168
Is constrained as in equation (4):
Figure BDA0002932478770000169
wherein, Δ t is the difference between the travel time and the arrival time planned from the ith waypoint;
set speed
Figure BDA00029324787700001610
Acceleration of a vehicle
Figure BDA00029324787700001611
The relationship between (A) and (B) is constrained by the following formula (5):
Figure BDA00029324787700001612
setting acceleration
Figure BDA00029324787700001613
And the fast and slow values of the acceleration change
Figure BDA00029324787700001614
Is constrained as in equation (6):
Figure BDA00029324787700001615
as shown in fig. 8, an embodiment of the present application provides an electronic device 1100, which includes a processor 1101 and a memory 1102; the processor 1101 is configured to execute the computer executable instructions stored in the memory 1102, and the processor 1101 executes the computer executable instructions to perform the method for unmanned planning according to any of the above embodiments.
The embodiment of the present application provides a storage medium 1103, which includes a readable storage medium and a computer program stored in the readable storage medium, where the computer program is used to implement the method for unmanned planning according to any one of the above embodiments.
The embodiment of the present application further provides a vehicle, where at least one device for planning a vehicle driving scheme is deployed or integrated, where the device is a part of an on-board system, and may be an on-board control unit, such as an ECU, a DCU, or an MDC, and may also be a semiconductor chip disposed in the on-board system. The vehicle can be driven according to a driving scheme planned by the device according to the method of any one of the above embodiments; the device at least comprises: the route determining module is used for acquiring a navigation route from a starting point to a destination at a specified moment, and the navigation route comprises one or more road section units, wherein each road section unit in the one or more road section units is a road section between two road points; the data acquisition module is used for acquiring historical traffic data information of the navigation route; the model evaluation module is used for evaluating the track cost of the road traffic model of each road section unit in one or more road section units by taking time as a baseline based on historical traffic data information to obtain an evaluation result meeting the planning requirement; the time planning module is used for determining travel time and arrival time respectively corresponding to two waypoints of each road section unit according to an evaluation result meeting the planning requirement; and the scheme planning module is used for determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
Moreover, various aspects or features of embodiments of the application may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term "article of manufacture" as used herein is intended to encompass a computer program accessible from any computer-readable device, carrier, or media. For example, computer-readable media can include but are not limited to magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips, etc.), optical disks (e.g., Compact Disk (CD), Digital Versatile Disk (DVD), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROM), card, stick, or key drive, etc.). In addition, various storage media described herein can represent one or more devices and/or other machine-readable media for storing information. The term "machine-readable medium" can include, without being limited to, wireless channels and various other media capable of storing, containing, and/or carrying instruction(s) and/or data.
It should be understood that, in various embodiments of the present application, the sequence numbers of the above-mentioned processes do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application, which essentially or partly contribute to the prior art, may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or an access network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other media capable of storing program codes.
The above description is only a specific implementation of the embodiments of the present application, but the scope of the embodiments of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present application, and all the changes or substitutions should be covered by the scope of the embodiments of the present application.

Claims (33)

1. A method of planning a driving scheme for a vehicle, the method comprising:
acquiring a navigation route from a starting point to a destination at a specified moment, wherein the navigation route comprises one or more road section units, and each road section unit in the one or more road section units is a road section between two waypoints on the navigation route;
obtaining historical traffic data information of the navigation route;
performing track cost evaluation on the road traffic model of each road section unit in the one or more road section units by taking time as a baseline based on the historical traffic data information to obtain an evaluation result meeting the planning requirement;
determining travel time and arrival time respectively corresponding to the two waypoints of each road section unit according to the evaluation result meeting the planning requirement;
and determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
2. The method according to claim 1, wherein the determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road segment unit comprises:
determining the running speed of the vehicle on each road section unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit;
and determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit and the driving speed of the vehicle on each road section unit.
3. The method of claim 1, wherein the historical traffic data information of the navigation route includes one or more of:
the vehicle control information, the travel information and the traffic participant information and the traffic information around the vehicle of the vehicle passing at a plurality of different moments in a historical time period on the one or more road section units.
4. The method according to claim 1, wherein the one or more link units are obtained by dividing the navigation route by link length or the one or more link units are obtained by dividing the navigation route by traffic flow or traffic element.
5. The method according to claims 1-3, further comprising establishing a road traffic model for each of the one or more road segment units based on the historical traffic data information.
6. The method of claim 5, wherein the establishing a road traffic model for each of the one or more road segment units according to the historical traffic data information comprises:
extracting one or more traffic characteristics on each road section unit from the historical traffic data information by taking time as a base line;
and establishing a plurality of road traffic models with time as a base line on each road section unit according to one or more traffic characteristics on each road section unit.
7. The method of claim 6, wherein the building a plurality of time-based road traffic models on each road segment unit according to one or more traffic characteristics on each road segment unit comprises: accumulating the one or more traffic characteristics on each road section unit, and establishing a plurality of road traffic models with time as a base line on each road section unit.
8. The method of claim 6, wherein the building a plurality of time-based road traffic models on each road segment unit according to one or more traffic characteristics on each road segment unit comprises:
and establishing a road traffic model with time as a base line by the one or more traffic characteristics on each road section unit through an RNN recurrent neural network.
9. The method according to any one of claims 6-8, further comprising: establishing an evaluation system of the road traffic model according to the historical traffic data information, wherein the evaluation system of the road traffic model comprises track cost values corresponding to the one or more traffic characteristics at different moments; and setting track cost values corresponding to the one or more traffic characteristics at different moments, and establishing an evaluation system of the road traffic model.
10. The method of any of claims 6-9, wherein the traffic characteristics include one or more of: a vehicle control feature, a trip feature, a traffic participant feature, a traffic feature, an arrival time feature, a traffic light wait time feature, and a green light transit time feature.
11. The method of claim 9, wherein the performing track cost evaluation on the road traffic model of each road segment unit based on the historical traffic data information by taking time as a baseline obtains an evaluation result meeting the planning requirement, and comprises:
according to the road traffic model evaluation system, summing track cost values corresponding to a plurality of traffic characteristics of each road traffic model by taking time as a base line or weighting and summing the track cost values to obtain a comprehensive track cost value of each road traffic model of each road section unit at different moments;
and comparing the comprehensive track cost value by taking time as a base line to obtain an evaluation result meeting the planning requirement.
12. The method according to any one of claims 1 to 2, wherein the two waypoints of each road segment unit are a start waypoint and an end waypoint, respectively, and the determining the travel time and the arrival time corresponding to the two waypoints of each road segment unit according to the evaluation result meeting the planning requirement comprises:
according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of the starting waypoint of each road section unit;
and according to the travel time of the starting waypoint and the road speed limit condition, appointing the arrival time of the ending waypoint of each road section unit.
13. The method according to any one of claims 1 to 2, wherein the two waypoints of each road segment unit are a start waypoint and an end waypoint, respectively, and the determining the travel time and the arrival time corresponding to the two waypoints of each road segment unit according to the evaluation result meeting the planning requirement comprises:
according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of each road section unit at the starting waypoint;
calculating an arrival time interval of the termination waypoint of each road section unit according to the travel time of the starting waypoint of each road section unit and the road speed limit condition;
planning the travel time of the next road section unit of each road section unit according to the interval of the arrival time of the termination road point of each road section unit;
and taking the travel time of the next road section unit of each road section unit as the arrival time of each road section unit, and obtaining the travel time and the arrival time corresponding to two waypoints of each road section unit respectively.
14. The method according to claim 2, wherein the determining the driving speed of the vehicle on each road segment unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road segment unit comprises:
determining the running speed of the vehicle on each road section unit by using a speed optimization formula according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit, wherein the speed optimization formula is as follows:
Figure RE-FDA0003053449020000021
wherein f is an optimization result of the optimization function, and the optimization goal is to minimize f when the speed of the unmanned vehicle is planned; s i Representing the travel of the ith actual waypoint;
Figure RE-FDA0003053449020000022
representing the planned waypoint journey of the ith; w is a s Representing a positional deviation weight;
Figure RE-FDA0003053449020000023
representing an acceleration deviation weight;
Figure RE-FDA0003053449020000024
represents the acceleration of the vehicle, with index i being the ith planned waypoint;
Figure RE-FDA0003053449020000025
deviation weight of fast and slow values representing the acceleration change of the vehicle;
Figure RE-FDA0003053449020000026
the fast and slow values of the acceleration change are shown, and the subscript i → i +1 is the planned waypoint from the ith to the (i + 1) th; w is a t Representing a time of arrival deviation weight; t is t i Representing the predicted time to reach the terminal point when travelling from the ith waypoint;
Figure RE-FDA0003053449020000031
represents the planned arrival time when traveling from the ith waypoint.
15. The method of claim 14, wherein said determining a travel speed of said vehicle on said each road segment unit using said speed optimization formula further comprises:
set waypoint travel s i Speed of
Figure RE-FDA0003053449020000032
Acceleration of a vehicle
Figure RE-FDA0003053449020000033
Upper and lower limit values of (d);
set waypoint travel s i Speed of
Figure RE-FDA0003053449020000034
Acceleration of a vehicle
Figure RE-FDA0003053449020000035
The relationship constraint between (a) and (b) is:
Figure RE-FDA0003053449020000036
wherein, Δ t is the difference between the travel time and the arrival time planned from the ith waypoint;
set speed
Figure RE-FDA0003053449020000037
Acceleration of a vehicle
Figure RE-FDA0003053449020000038
A relationship constraint between;
Figure RE-FDA0003053449020000039
setting acceleration
Figure RE-FDA00030534490200000310
And the fast and slow values of the acceleration change
Figure RE-FDA00030534490200000311
The relationship constraint of (1) is:
Figure RE-FDA00030534490200000312
16. an apparatus for planning a driving scheme of a vehicle, the apparatus comprising:
the route determining module is used for acquiring a navigation route from a starting point to a destination at a specified moment, wherein the navigation route comprises one or more road section units, and each road section unit in the one or more road section units is a road section between two road points;
the data acquisition module is used for acquiring historical traffic data information of the navigation route;
the model evaluation module is used for evaluating the track cost of the road traffic model of each road section unit in the one or more road section units by taking time as a baseline based on the historical traffic data information to obtain an evaluation result meeting the planning requirement;
the time planning module is used for determining travel time and arrival time respectively corresponding to the two waypoints of each road section unit according to the evaluation result meeting the planning requirement; and
and the scheme planning module is used for determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit.
17. The apparatus of claim 16, wherein the time planning module comprises:
the speed calculation unit is used for determining the running speed of the vehicle on each road section unit according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit; and
and the scheme planning unit is used for determining a driving scheme meeting the planning requirement on the navigation route according to the travel time and the arrival time respectively corresponding to the two waypoints of each road section unit and the driving speed of the vehicle on each road section unit.
18. The apparatus of claim 16, wherein the historical traffic data information of the navigation route includes one or more of:
the vehicle control information, the travel information and the traffic participant information and the traffic information around the vehicle of the vehicle passing at a plurality of different moments in a historical time period on the one or more road section units.
19. The apparatus of claim 16, wherein the one or more link units are obtained by dividing the navigation route by link length or are obtained by dividing the navigation route by traffic flow or traffic element.
20. The apparatus of one of claims 16 to 18, further comprising a build model module for: and establishing a road traffic model of each road section unit in the one or more road section units according to the historical traffic data information.
21. The apparatus of claim 20, wherein the build model module comprises:
the characteristic extraction unit is used for extracting one or more traffic characteristics on each road section unit from the historical traffic data information by taking time as a base line; and
and the modeling unit is used for establishing a plurality of road traffic models taking time as a base line on each road section unit according to one or more traffic characteristics on each road section unit.
22. The apparatus of claim 21, wherein the modeling unit is configured to accumulate the one or more traffic characteristics for each of the road segment units to create a plurality of time-based road traffic models for each of the road segment units.
23. The apparatus of claim 21, wherein the modeling unit is configured to build a time-based road traffic model from the one or more traffic characteristics on each road segment unit through an RNN recurrent neural network.
24. The device according to any one of claims 21 to 23, further comprising an evaluation system establishing module, configured to establish an evaluation system of the road traffic model according to the historical traffic data information, wherein the evaluation system of the road traffic model comprises track cost scores corresponding to the one or more traffic characteristics at different times; and setting track cost values corresponding to the one or more traffic characteristics at different moments, and establishing an evaluation system of the road traffic model.
25. The apparatus of any one of claims 21-23, wherein the traffic characteristics include one or more of: a vehicle control feature, a trip feature, a traffic participant feature, a traffic feature, an arrival time feature, a traffic light wait time feature, and a green light transit time feature.
26. The apparatus of claim 24, wherein the model evaluation module is configured to:
the calculation unit is used for summing track cost values corresponding to a plurality of traffic characteristics of each road traffic model by taking time as a base line or weighting and summing according to the road traffic model evaluation system to obtain a comprehensive track cost value of each road traffic model of each road section unit at different moments; and
and the evaluation unit is used for comparing the comprehensive track cost value by taking time as a base line to obtain an evaluation result meeting the planning requirement.
27. The apparatus according to one of claims 16-17, wherein the time planning module is configured to:
according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of the starting waypoint of each road section unit;
and according to the travel time of the starting waypoint and the road speed limit condition, appointing the arrival time of the ending waypoint of each road section unit.
28. The apparatus according to any one of claims 16-17, wherein the two waypoints per segment unit are a start waypoint and an end waypoint, respectively, and the time planning module is configured to:
according to the evaluation result meeting the planning requirement, obtaining time information corresponding to the road traffic model of each road section unit, and determining the travel time of each road section unit at the starting waypoint; calculating an interval of the arrival time of the termination waypoint of each road section unit according to the travel time of the starting waypoint of each road section unit and the road speed limit condition; planning the travel time of the next road section unit of each road section unit according to the interval of the arrival time of the termination road point of each road section unit; and taking the travel time of the next road section unit of each road section unit as the arrival time of each road section unit, and obtaining the travel time and the arrival time corresponding to two waypoints of each road section unit respectively.
29. The apparatus of claim 17, wherein the speed calculation unit is configured to:
Figure RE-FDA0003053449020000041
wherein f is an optimization result of the optimization function, and the optimization goal is to minimize f when the speed of the unmanned vehicle is planned; s i Representing the travel of the ith actual waypoint;
Figure RE-FDA0003053449020000051
representing the planned waypoint journey of the ith; w is a s Representing a positional deviation weight;
Figure RE-FDA0003053449020000052
representing an acceleration deviation weight;
Figure RE-FDA0003053449020000053
represents the acceleration of the vehicle, with index i being the ith planned waypoint;
Figure RE-FDA0003053449020000054
deviation weight of fast and slow values representing the acceleration change of the vehicle;
Figure RE-FDA0003053449020000055
the fast and slow values of the acceleration change are shown, and the subscript i → i +1 is the planned waypoint from the ith to the (i + 1) th; w is a t Representing a time of arrival deviation weight; t is t i Representing the predicted time to reach the terminal point when travelling from the ith waypoint;
Figure RE-FDA0003053449020000056
represents the planned arrival time when traveling from the ith waypoint.
30. The apparatus of claim 29, wherein the speed calculation unit is further configured to:
set waypoint travel s i Speed of
Figure RE-FDA0003053449020000057
Acceleration of a vehicle
Figure RE-FDA0003053449020000058
Upper and lower limit values of (d);
set waypoint travel s i Speed of
Figure RE-FDA0003053449020000059
Acceleration of a vehicle
Figure RE-FDA00030534490200000510
The relationship constraint between (a) and (b) is:
Figure RE-FDA00030534490200000511
wherein, Δ t is the difference between the travel time and the arrival time planned from the ith waypoint;
set speed
Figure RE-FDA00030534490200000512
Acceleration of a vehicle
Figure RE-FDA00030534490200000513
The relation between the two is restricted;
Figure RE-FDA00030534490200000514
setting acceleration
Figure RE-FDA00030534490200000515
And the fast and slow values of the acceleration change
Figure RE-FDA00030534490200000516
The relationship constraint of (1) is:
Figure RE-FDA00030534490200000517
31. an electronic device comprising a memory and a processor; the processor is configured to execute computer-executable instructions stored in the memory, and the processor executes the computer-executable instructions to perform the method of planning a vehicle driving scenario of any of claims 1-15.
32. A vehicle, characterized in that the vehicle comprises a device according to any one of claims 16 to 31 for planning a driving scheme for the vehicle.
33. A storage medium comprising a readable storage medium and a computer program stored in the readable storage medium for implementing the method of planning a vehicle driving scenario of any of claims 1-15.
CN202110150312.0A 2021-02-03 2021-02-03 Planning method and device for vehicle driving scheme and storage medium Pending CN114861514A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202110150312.0A CN114861514A (en) 2021-02-03 2021-02-03 Planning method and device for vehicle driving scheme and storage medium
PCT/CN2021/122425 WO2022166239A1 (en) 2021-02-03 2021-09-30 Vehicle travel scheme planning method and apparatus, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110150312.0A CN114861514A (en) 2021-02-03 2021-02-03 Planning method and device for vehicle driving scheme and storage medium

Publications (1)

Publication Number Publication Date
CN114861514A true CN114861514A (en) 2022-08-05

Family

ID=82623494

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110150312.0A Pending CN114861514A (en) 2021-02-03 2021-02-03 Planning method and device for vehicle driving scheme and storage medium

Country Status (2)

Country Link
CN (1) CN114861514A (en)
WO (1) WO2022166239A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116030636A (en) * 2023-03-28 2023-04-28 北京清研宏达信息科技有限公司 Method and system for dynamically planning bus speed

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115310723A (en) * 2022-10-09 2022-11-08 深圳市城市交通规划设计研究中心股份有限公司 Vehicle navigation optimization method based on data encryption, electronic equipment and storage medium
CN116434529B (en) * 2022-12-12 2023-10-24 交通运输部规划研究院 Inter-city highway freight characteristic analysis method and device and electronic equipment
CN116295684B (en) * 2023-03-07 2023-11-24 智能网联汽车(山东)协同创新研究院有限公司 Automobile instantaneous oil consumption monitoring system under intelligent networking environment
CN116858259B (en) * 2023-06-02 2024-02-06 速度科技股份有限公司 Intelligent driving path planning system based on vehicle-road cooperation
CN117196266B (en) * 2023-11-07 2024-01-23 成都工业职业技术学院 Unmanned shared automobile area scheduling method and device based on neural network
CN118010059A (en) * 2024-04-08 2024-05-10 逸航汽车零部件无锡有限公司 Path planning system and method based on personalized comfort control

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103245347B (en) * 2012-02-13 2015-11-25 腾讯科技（深圳）有限公司 Based on intelligent navigation method and the system of road condition predicting
TW201614195A (en) * 2014-10-02 2016-04-16 Inst Information Industry Route planning system, route planning method and traffic information update method
CN110553656A (en) * 2018-05-31 2019-12-10 上海博泰悦臻网络技术服务有限公司 road condition planning method and system for vehicle machine
CN110375760A (en) * 2019-07-29 2019-10-25 北京百度网讯科技有限公司 Route determination method, apparatus, equipment and medium
CN111256723B (en) * 2020-03-05 2022-02-11 新石器慧通（北京）科技有限公司 Unmanned vehicle navigation method and device, detection device and unmanned vehicle
CN112161636B (en) * 2020-08-28 2022-07-29 深圳市跨越新科技有限公司 Truck route planning method and system based on one-way simulation

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116030636A (en) * 2023-03-28 2023-04-28 北京清研宏达信息科技有限公司 Method and system for dynamically planning bus speed

Also Published As

Publication number Publication date
WO2022166239A1 (en) 2022-08-11

Similar Documents

Publication Publication Date Title
CN114861514A (en) Planning method and device for vehicle driving scheme and storage medium
CN110298122B (en) Unmanned vehicle urban intersection left-turn decision-making method based on conflict resolution
CN108848462B (en) Real-time vehicle track prediction method suitable for signal control intersection
US10829116B2 (en) Affecting functions of a vehicle based on function-related information about its environment
CN110488802A (en) A kind of automatic driving vehicle dynamic behaviour decision-making technique netted under connection environment
Kang et al. Game theoretical approach to model decision making for merging maneuvers at freeway on-ramps
CN109643118B (en) Influencing a function of a vehicle based on function-related information about the environment of the vehicle
KR20190030199A (en) Supervision of vehicles
US20180004210A1 (en) Affecting Functions of a Vehicle Based on Function-Related Information about its Environment
CN108431549A (en) The housebroken system of constraint with application
CN110383008A (en) Navigation based on movable vehicle
CN106428009A (en) Vehicle trajectory determination
CN106114507A (en) Local path planning method and device for intelligent vehicle
CN107851373A (en) Scene apparatus for evaluating, driving assist system, scene appraisal procedure
CN107851372A (en) Driving plan device, driving assist system, driving plan method
CN107851375A (en) Driving plan device, driving assist system, driving plan method
CN109615887A (en) Wisdom traffic network system signal guidance method
CN107851376A (en) Scene apparatus for evaluating, driving assist system, scene appraisal procedure
CN112767683B (en) Path induction method based on feedback mechanism
CN108171967A (en) A kind of traffic control method and device
CN113743469A (en) Automatic driving decision-making method fusing multi-source data and comprehensive multi-dimensional indexes
CN112833903A (en) Trajectory prediction method, apparatus, device and computer readable storage medium
Chen et al. Towards human-like speed control in autonomous vehicles: A mountainous freeway case
Geng et al. Human-driver speed profile modeling for autonomous vehicle's velocity strategy on curvy paths
Bakibillah et al. Sustainable eco-driving strategy at signalized intersections from driving data

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