CN115092180A

CN115092180A - Vehicle meeting method and device, computer equipment and storage medium

Info

Publication number: CN115092180A
Application number: CN202210763340.4A
Authority: CN
Inventors: 林腾波; 卢天明; 李伟明
Original assignee: Guangzhou Weride Technology Co Ltd
Current assignee: Guangzhou Weride Technology Co Ltd
Priority date: 2022-06-30
Filing date: 2022-06-30
Publication date: 2022-09-23

Abstract

The application relates to the technical field of automatic driving, and discloses a vehicle meeting method, a device, computer equipment and a storage medium, wherein the method comprises the steps of detecting whether an incoming vehicle exists in front of an automatic driving main vehicle or not and whether obstacles occupy lanes or not on the basis of map information of the automatic driving main vehicle, positioning information of the automatic driving main vehicle and obstacle information; judging and researching the space overlapping condition of a driving area of the main vehicle and a driving area of an oncoming vehicle when an obstacle occupies the lane and the oncoming vehicle is in front of the automatic driving main vehicle; deciding the passing priority based on the judging and researching result; and deciding a motion plan of the automatic driving main vehicle based on the passing priority. The method and the device have the effects of deciding the meeting according to the characteristics of the actual meeting scene and improving the comfort and the safety of the meeting.

Description

Vehicle meeting method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to a vehicle meeting method and apparatus, a computer device, and a storage medium.

Background

As the application fields of the autonomous vehicles are increasingly expanded, driving scenes to be processed are also gradually increased. The narrow road meeting scenario is one of the most complex scenarios in the automatic driving decision planning algorithm of level L4.

Particularly, when the main vehicle normally runs in the main vehicle lane, the opposite lane is occupied by an illegal parking vehicle, and the opposite vehicle is in a reverse lane for avoiding the illegal parking vehicle, so that the conventional automatic driving meeting strategy easily causes the main vehicle to be stuck and causes safety accidents, and the comfort and the safety of the meeting strategy are poor.

Disclosure of Invention

In order to improve the comfort and safety of vehicle meeting, the application provides a vehicle meeting method, a device, computer equipment and a storage medium.

In a first aspect, the present application provides a vehicle meeting method.

The application is realized by the following technical scheme:

a vehicle meeting method comprises the following steps,

detecting whether a vehicle comes in front of the automatic driving main vehicle and whether obstacles occupy lanes or not on the basis of map information of the automatic driving main vehicle, positioning information of the automatic driving main vehicle and obstacle information;

judging and researching the space overlapping condition of the driving area of the main vehicle and the driving area of the coming vehicle when the obstacle occupies the lane of the opposite lane and the coming vehicle is in front of the automatic driving main vehicle;

deciding the passing priority based on the judging and researching result;

and deciding a motion plan of the automatic driving main vehicle based on the passing priority.

The present application may be further configured in a preferred example to: the step of deciding the traffic priority based on the result of the research comprises,

acquiring the speed of a coming vehicle, the speed of an automatically driven main vehicle, the running track of the coming vehicle and the overlapping space of the running area of the main vehicle and the running area of the coming vehicle, and establishing an avoidance cost function;

and respectively calculating the main vehicle avoidance cost and the coming vehicle avoidance cost according to the avoidance cost function, and deciding that the corresponding avoidance cost in the two vehicles is high in traffic priority.

The present application may be further configured in a preferred example to: the avoidance cost function comprises a vehicle deceleration limiting factor and a remaining selection difficulty factor.

The present application may be further configured in a preferred example to: the avoidance cost function also comprises a road weight factor;

and mapping the road weight factor into a first constant term of the avoidance cost function based on a preset road weight mapping rule.

The present application may be further configured in a preferred example to: the avoidance cost function further comprises a vehicle type factor;

and mapping the vehicle type factor into a second constant item of the avoidance cost function based on a preset vehicle type mapping rule.

The present application may be further configured in a preferred example to: the step of judging the spatial overlapping condition of the main vehicle driving area and the coming vehicle driving area comprises the steps of,

acquiring the width of the bodies, the lane width, the width of the occupied barrier and a preset safe distance of the main vehicle and the coming vehicle based on the driving track of the main vehicle and the driving track of the coming vehicle, and calculating the width of the residual space of the transverse interval of the tracks;

if the width of the residual space of the track transverse interval is greater than or equal to 0, the main vehicle running area and the coming vehicle running area have no overlapped space;

and if the width of the residual space of the track transverse interval is less than 0, the driving area of the main vehicle and the driving area of the coming vehicle have an overlapping space.

The present application may be further configured in a preferred example to: if the driving area of the main vehicle and the driving area of the coming vehicle have overlapping space and the automatic driving main vehicle has high priority, the step of deciding the motion planning of the automatic driving main vehicle comprises the following steps,

and optimizing the running track of the coming vehicle, and enabling the automatic driving main vehicle to pass through the overlapping space according to the running track of the main vehicle.

The present application may be further configured in a preferred example to: if the driving area of the main vehicle and the driving area of the coming vehicle have an overlapping space and the automatically-driven main vehicle has a low priority, the step of deciding the motion plan of the automatically-driven main vehicle comprises the steps of,

and based on the positioning information of the automatic driving main vehicle and the driving track of the main vehicle, enabling the automatic driving main vehicle to stop at any optional position in front of the overlapping space from the current position.

when the opposite lane and the main lane have no avoidance space, the main lane backs up to avoid.

The present application may be further configured in a preferred example to: if the running area of the main vehicle and the running area of the coming vehicle have no overlapping space and the main vehicle is decided to have no priority for passing, the step of deciding the motion planning of the automatic driving main vehicle comprises the following steps,

enabling an automatic driving main vehicle to run according to the main vehicle running track;

or detecting whether the driving of the coming vehicle conforms to the driving track of the coming vehicle on the basis of the driving track of the coming vehicle and roadside boundary information in the map information;

and when the running of the coming vehicle is not consistent with the running track of the coming vehicle and the coming vehicle encroaches on the running track of the main vehicle, the automatically-driven main vehicle is avoided.

when the opposite lane and the main lane have no avoidance space, the main lane is backed to avoid or an opposite vehicle is backed to avoid.

The present application may be further configured in a preferred example to: the generating step of the host vehicle running track and the coming vehicle running track comprises,

acquiring roadside boundary information and lane information according to the map information, and generating a main vehicle track reference line and an incoming vehicle track reference line by combining the positioning information and the obstacle information;

and predicting the running track of the main vehicle based on the reference line of the track of the main vehicle, and predicting the running track of the coming vehicle based on the reference line of the track of the coming vehicle.

In a second aspect, the present application provides a vehicle crossing device.

The application is realized by the following technical scheme:

a vehicle meeting device comprises a vehicle body,

the meeting scene recognition module is used for detecting whether an incoming vehicle exists in front of the automatic driving main vehicle and whether obstacles occupy lanes or not on the basis of map information of the automatic driving main vehicle, positioning information of the automatic driving main vehicle and obstacle information;

the meeting vehicle judging and researching module is used for judging and researching the space overlapping condition of the driving area of the main vehicle and the driving area of the coming vehicle when the opposite lane has the obstacle to occupy the lane and the coming vehicle is in front of the main vehicle for automatic driving;

the priority module is used for deciding the passing priority based on the judging and researching result;

and the motion planning module is used for deciding the motion planning of the automatic driving main vehicle based on the passing priority.

In a third aspect, the present application provides a computer device.

The application is realized by the following technical scheme:

a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any of the above-mentioned vehicle crossing methods when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium.

The application is realized by the following technical scheme:

a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of any of the above-mentioned vehicle crossing methods.

To sum up, compare with prior art, the beneficial effect that technical scheme that this application provided brought includes at least:

detecting whether an incoming vehicle exists in front of the automatically-driven main vehicle and whether obstacles occupy the lane of an opposite lane or not based on map information of the automatically-driven main vehicle, positioning information of the automatically-driven main vehicle and obstacle information so as to identify a vehicle crossing scene; judging whether an overlapping space exists in a driving area of the main vehicle and a driving area of an incoming vehicle or not when obstacles occupy the lane and the incoming vehicle comes in front of the main vehicle in the opposite lane and automatically driving the main vehicle, and predicting the collision probability of the main vehicle and the incoming vehicle according to the overlapping space; and based on the judgment and research result, the passing priority is decided, and then the motion plan of the automatic driving main vehicle is decided, so that the vehicle meeting is decided according to the characteristics of the actual vehicle meeting scene, the applicability and the reasonability of the vehicle meeting strategy are improved, the automatic driving main vehicle can safely, comfortably and quickly pass through a vehicle meeting area, and the smoothness of automatic driving and the riding comfort are guaranteed.

Drawings

Fig. 1 is a schematic flowchart of a vehicle meeting method according to an exemplary embodiment of the present disclosure.

Fig. 2 is a flowchart of a method for vehicle crossing according to another exemplary embodiment of the present application, which is used for judging whether there is an overlapping space in a main vehicle driving area and an incoming vehicle driving area based on a predicted driving trajectory of a trajectory reference line.

Fig. 3 is a flowchart of a vehicle crossing method for judging whether there is an overlapping space between a main vehicle driving area and an oncoming vehicle driving area according to another exemplary embodiment of the present application.

Fig. 4 is a vehicle-meeting schematic diagram of a vehicle-meeting method according to an exemplary embodiment of the present application.

Fig. 5 is a block diagram of a vehicle meeting device according to an exemplary embodiment of the present disclosure.

Detailed Description

The specific embodiments are only for explaining the present application and are not limiting to the present application, and those skilled in the art can make modifications to the embodiments without inventive contribution as required after reading the present specification, but all the embodiments are protected by patent law within the scope of the claims of the present application.

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship, unless otherwise specified.

The embodiments of the present application will be described in further detail with reference to the drawings attached hereto.

Referring to fig. 1, an embodiment of the present application provides a vehicle meeting method, and main steps of the method are described as follows.

S1, detecting whether an incoming vehicle exists in front of the automatic driving main vehicle and whether obstacles occupy the lane in the opposite lane or not based on the map information of the automatic driving main vehicle, the positioning information of the automatic driving main vehicle and the obstacle information;

s2, judging and researching the space overlapping condition of the main vehicle driving area and the coming vehicle driving area when the opposite lane has the obstacle to occupy the lane and the automatic driving main vehicle has the coming vehicle in front;

s3, deciding the passing priority based on the judging and researching result;

and S4, deciding the motion plan of the automatic driving main vehicle based on the pass priority.

Specifically, the map information comprises roadside boundary information and lane information, the positioning information of the autonomous driving main vehicle comprises real-time speed information and real-time position information of the autonomous driving main vehicle, the obstacle information comprises static obstacle information and dynamic obstacle information, the dynamic obstacle information comprises positioning information of an incoming vehicle, and the positioning information of the incoming vehicle comprises real-time speed information and real-time position information of the incoming vehicle.

Whether the opposite lane is occupied by the obstacle can be sensed based on the static obstacle information. Based on the roadside boundary information, the lane information, the speed information and the position information of the vehicle, whether the lane where the main vehicle is located has a reverse vehicle can be judged.

When the opposite lane has obstacles to occupy the lane and the automatic driving main vehicle has a coming vehicle in front of the main vehicle, judging and researching the space overlapping condition of the driving area of the main vehicle and the driving area of the coming vehicle.

For example, it is judged whether or not there is an overlapping space in the host vehicle travel area and the incoming vehicle travel area based on machine learning. And (3) inputting a large number of learning examples of road condition meeting strategies for training by adopting a support vector machine algorithm, so that the trained support vector machine can automatically output the judgment and research result whether the driving area of the main vehicle and the driving area of the coming vehicle have overlapped spaces.

The spatial overlapping condition includes non-overlapping and overlapping.

If there is no overlap, the master is decided to be side-by-side without priority for passing, at this time, no one is supposed to pass preferentially, or the master is set to be high priority but the priority is equivalent to the priority for passing of the coming vehicle.

If the master vehicle is overlapped, the priority of the master vehicle is decided according to the degree of the overlapping and the like, and then the priority driving strategy corresponding to the master vehicle is decided.

And finally, deciding the motion plan of the automatic driving main vehicle based on the passing priority. If so, the automatic driving main vehicle is enabled to preferentially pass through the overlapping space according to the running track of the main vehicle; or the automatically-driven main vehicle is enabled to avoid the coming vehicle so as to decide that the coming vehicle preferentially passes through the overlapping space.

Further, based on the result of the investigation, the step of deciding the traffic priority comprises,

and respectively calculating the main vehicle avoidance cost and the coming vehicle avoidance cost according to the avoidance cost function, and deciding that the corresponding avoidance cost of the two vehicles is high in traffic priority.

The avoidance cost function includes a vehicle deceleration limit factor, and a remaining selection difficulty factor. Specifically, the deceleration limiting factor refers to a required deceleration when the vehicle decelerates from the current position and the current speed to the overlapping space, and for simplicity, the speed when the vehicle travels to the overlapping space may be set to 0, and then the corresponding calculation formula is: f (x) Vi ² (2S), wherein f (x) indicates the cost value of the vehicle, Vi indicates the running speed information of the vehicle at the current time, and S indicates the distance from the current position to the overlapping space. The larger the calculation result is, the higher the cost is, so that the calculation result is passed with high priority.

The remaining selection difficulty factor is used for measuring whether the opposite vehicle passes through the meeting area except for avoiding the automatic driving main vehicle or not, and f (x) Vi ² the/2S-C, C indicates the difficulty of selecting the remaining opposite cars; if the opposite vehicle cannot pass or other choices are very reverse to the reasonability of the vehicle, namely the opposite vehicle is difficult to pass through the meeting area, the remaining selection difficulty of the opposite vehicle is higher, and the avoidance cost value calculated by the remaining selection difficulty factor is smaller; otherwise, the avoidance cost value calculated by the remaining selection difficulty factors is larger.

In this embodiment, if the remaining selection difficulty factors of different driving scenarios are different, the value calculated according to the remaining selection difficulty factors is in a positive correlation with the driving scenario that meets the driving rationality of the oncoming vehicle, that is, the driving scenario that meets the driving rationality of the oncoming vehicle, the value calculated by the remaining selection difficulty factors is larger, and vice versa.

For example, referring to fig. 4, if there are 2 lanes in my lane, 1 lane in the opposite lane, and the host vehicle is in the left lane, it is determined by the remaining selection difficulty factor that the opposite vehicle has another way to pass through the meeting area, that is, the opposite vehicle has the remaining lane to be selected, and the avoidance cost value of the host vehicle calculated based on the remaining selection difficulty factor is smaller than the avoidance cost value of the opposite vehicle, the opposite vehicle preferentially passes through, the host vehicle needs to avoid, and the host vehicle changes the lane from the current lane to the right lane. For another example, 2 lanes are provided for our and 1 lane is provided for the opposite vehicle, the opposite vehicle has to go backwards because the lane is blocked, in this case, the scheme makes the main vehicle give up the middle lane to the opposite vehicle, and the corresponding C value of the main vehicle is larger, namely the main vehicle gives up the middle lane.

For another example, the meeting area is a scene of a long and narrow single lane, the oncoming vehicle has already entered the long and narrow single lane, the main vehicle has not entered or has just entered, and although the oncoming vehicle travels in the reverse direction, backing the vehicle back and avoiding the oncoming vehicle is also difficult, so C at this time is also relatively large, i.e., the main vehicle needs to avoid the oncoming vehicle.

Further, the avoidance cost function also comprises a road weight factor;

and mapping the road weight factor into a first constant item of an avoidance cost function based on a preset road weight mapping rule.

Specifically, considering the influence of the road right on the vehicle-meeting strategy, the function expression of the constructed avoidance cost function comprises f (x) Vi ² and/2S-C + A, wherein f (x) refers to the cost value of the vehicle, Vi refers to the running speed information of the vehicle at the current moment, S refers to the distance from the current position to the overlapped space, C refers to the residual selection difficulty factor, and A refers to a first constant item obtained through the mapping of a preset road weight mapping rule.

In this embodiment, when the driving direction of the vehicle is consistent with the passing direction of the road, it is determined that the vehicle has the right of way; and when the driving direction of the vehicle is inconsistent with the passing direction of the road, judging that the vehicle has no right of way.

According to a preset road right mapping rule, if the value of the first constant item A obtained by mapping is 1 when the road right exists, and if the value of the first constant item A obtained by mapping is 0 when the road right does not exist.

Further, the avoidance cost function also comprises a vehicle type factor;

and mapping the vehicle model factor into a second constant term of the avoidance cost function based on a preset vehicle model mapping rule.

Specifically, the avoidance of the structure is carried out in consideration of the influence of the vehicle type on the vehicle meeting strategyThe functional expression of the cost function includes f (x) Vi ² The method comprises the following steps of/2S-C + A + B, wherein f (x) refers to the cost value of a vehicle, Vi refers to the running speed information of the vehicle at the current moment, S refers to the distance from the current position of the vehicle to an overlapping space, C refers to a residual selection difficulty factor, A refers to a first constant item obtained through mapping of a preset road right mapping rule, and B refers to a second constant item obtained through mapping of a preset vehicle type mapping rule corresponding to a coming vehicle.

In this embodiment, the preset vehicle type may be a specific vehicle type, such as a large car, a bus, an ambulance, and the like.

According to a preset vehicle type mapping rule, the specific vehicle type corresponds to a preset constant value, for example, the value of a second constant item B obtained by mapping a large vehicle is 0.6, the value of a second constant item B obtained by mapping a bus is 0.3, and the value of a second constant item B obtained by mapping an ambulance is 0.

Further, the avoidance cost function of the coming vehicle may be the same as or different from the avoidance cost function of the host vehicle, for example, when the avoidance cost function of the host vehicle is f (x) Vi ² at/2S-C, the avoidance cost function of the coming vehicle is f (x) Vi ² /2S-C+A。

If the calculation result of the avoidance cost function is large, the avoidance cost function passes preferentially; and if the calculation result of the avoidance cost function is small, the avoidance is defaulted.

By constructing an avoidance cost function, respectively calculating the avoidance cost of the main vehicle and the avoidance cost of the coming vehicle based on the avoidance cost function so as to obtain corresponding avoidance costs, wherein the avoidance costs are used for deciding that the passing priority with large corresponding avoidance costs in the two vehicles is high, so that the avoidance costs are accurately measured according to deceleration factors of the main vehicle and the coming vehicle, and the passing priority is decided; meanwhile, the influence of factors such as road right and vehicle type on the vehicle meeting decision is considered, so that the calculation result of the avoidance cost function is more accurate.

Referring to fig. 2, further, when there is an obstacle occupying the oncoming lane and there is a coming vehicle ahead of the host vehicle by the autonomous driving at S2, the step of judging a spatial overlap of the traveling area of the host vehicle and the traveling area of the coming vehicle includes,

s21, when the opposite lane has obstacles occupying the lane and the automatic driving main car has a coming car in front, according to the map information, obtaining the roadside boundary information and the lane information, and combining the positioning information and the obstacle information to generate a main car track reference line and an coming car track reference line;

s22, predicting the running track of the main vehicle based on the reference line of the main vehicle track, and predicting the running track of the coming vehicle based on the reference line of the coming vehicle track;

and S23, judging whether the main vehicle running area and the coming vehicle running area have overlapping space or not based on the main vehicle running track and the coming vehicle running track.

Specifically, roadside boundary information and lane information are obtained according to map information, positioning information and obstacle information are combined, and a main vehicle track reference line and an incoming vehicle track reference line are generated according to a main vehicle track reference line and a QP algorithm or a graph search algorithm.

Generating a main vehicle track reference line based on the lane where the main vehicle is located, the position information and a QP algorithm or a graph search algorithm; according to the main vehicle track reference line and the QP algorithm or the graph search algorithm, the lane where the coming vehicle is located, the dynamic barrier information and the static barrier information are combined to generate a coming vehicle track reference line which avoids the static barrier so as to generate the main vehicle track reference line and the coming vehicle track reference line which are used as the driving assistance of the main vehicle or the coming vehicle, for example, the main vehicle is driven to the right by taking the main vehicle track reference line as the reference, or the coming vehicle is driven to the right by taking the coming vehicle track reference line as the reference so as to ensure the safety interval when meeting, so that the main vehicle or the coming vehicle can drive more safely.

The method and the device can predict the running track of the main vehicle or the running track of the coming vehicle based on the track reference line, and are used for judging and researching whether the running area of the main vehicle and the running area of the coming vehicle have an overlapping space.

Referring to fig. 3, further, the step of determining whether there is an overlapping space in the host driving area and the incoming driving area based on the host driving trajectory and the incoming driving trajectory S23 includes,

s231, acquiring the body widths, lane widths, barrier occupying widths and preset safe distances of the main vehicle and the coming vehicle based on the driving track of the main vehicle and the driving track of the coming vehicle, and calculating the width of the residual space of the transverse distance of the track;

s2321, if the width of the residual space of the transverse track interval is greater than or equal to 0, the running area of the main vehicle and the running area of the coming vehicle have no overlapping space;

s2322, if the width of the residual space of the track transverse spacing is smaller than 0, the driving area of the main vehicle and the driving area of the coming vehicle have an overlapping space.

Specifically, the method comprises the steps of obtaining the lane width of a main vehicle, the width of an opposite lane, the width of an obstacle occupying lane, the width of a body of the main vehicle, the width of a body of an oncoming vehicle and a preset safety distance;

if the remaining space width is equal to (main vehicle lane width + opposite lane width) - (obstacle occupying lane width + main vehicle body width + coming vehicle body width + safety distance) > (0), the main vehicle driving area and the coming vehicle driving area are considered to have no overlapping space;

if the remaining space width is (main vehicle lane width + opposite lane width) - (obstacle occupying lane width + main vehicle body width + safe distance) <0, then the main vehicle driving area and the vehicle driving area are considered to have an overlapping space.

And finally, deciding the motion plan of the automatic driving main vehicle based on the passing priority.

a) If the driving area of the main vehicle and the driving area of the coming vehicle have overlapping space and the automatic driving main vehicle has high driving priority, the step of deciding the motion plan of the automatic driving main vehicle comprises the following steps,

optimizing the running track of the coming vehicle and enabling the automatic driving main vehicle to pass through the overlapping space according to the running track of the main vehicle.

Or when the opposite lane and the main lane have no avoidance space, the main lane waits for the opposite vehicle to back up and avoid.

Specifically, if the overlapping space exists and the host vehicle has a high driving priority, when the driving track of the coming vehicle is optimized, the predicted driving track of the opposite coming vehicle is cut off to the front of the overlapping space, and the host vehicle is enabled to pass through the overlapping space according to the driving track of the host vehicle.

b) If the running area of the main vehicle and the running area of the coming vehicle have an overlapping space and the automatic driving main vehicle has low running priority, the automatic driving main vehicle is stopped by the side from the current position to any optional position in front of the overlapping space based on the positioning information of the automatic driving main vehicle and the running track of the main vehicle.

Or when the opposite lane and the main lane have no avoidance space, the main lane backs up for avoidance or the opposite vehicle backs up for avoidance.

Specifically, if the overlapping space exists and the main vehicle has a low priority, the main vehicle is enabled to stop at the position of the nearest boundary line of the overlapping space, or the main vehicle is enabled to stop at the side directly according to the positioning information and the driving track of the main vehicle, or the main vehicle is enabled to back up and avoid when the opposite lane and the main vehicle lane have no avoidance space.

1/C) if the running area of the main vehicle and the running area of the coming vehicle have no overlapping space, namely the main vehicle has no priority of passing along the same direction, the step of deciding the motion planning of the automatic driving main vehicle comprises the step of enabling the automatic driving main vehicle to run according to the running track of the main vehicle;

or detecting whether the driving of the coming vehicle conforms to the driving track of the coming vehicle or not based on the driving track of the coming vehicle and roadside boundary information in the map information;

and when the running track of the coming vehicle is not consistent with the running track of the coming vehicle and the coming vehicle encroaches on the running track of the main vehicle, the automatically-driven main vehicle is avoided.

Specifically, if no overlapping space exists, the decision is that no priority is given, namely the main vehicle and the coming vehicle can pass side by side, and whether the running of the coming vehicle accords with the running track of the coming vehicle is detected; when the coming vehicle does not conform to the running track of the coming vehicle and the coming vehicle passes along the edge intentionally, the decision-making main vehicle runs on the right according to the running track of the main vehicle and the coming vehicle runs on the right according to the running track of the coming vehicle; when the coming vehicle does not conform to the running track of the coming vehicle and the coming vehicle passes along the road without intention, the main vehicle is decided to adopt an avoidance strategy so as to ensure the safe distance between the coming vehicle and the coming vehicle when the road condition meets the vehicle and further improve the safety of the coming vehicle.

In conclusion, whether an incoming vehicle exists in front of the automatically-driven main vehicle and whether obstacles occupy lanes in the opposite lane or not are detected based on the map information of the automatically-driven main vehicle, the positioning information of the automatically-driven main vehicle and the obstacle information so as to identify a vehicle crossing scene; judging whether an overlapping space exists in a driving area of the main vehicle and a driving area of an incoming vehicle or not when obstacles occupy the lane and the incoming vehicle comes in front of the main vehicle in the opposite lane and automatically driving the main vehicle, and predicting the collision probability of the main vehicle and the incoming vehicle according to the overlapping space; and deciding the passing priority based on the judging and researching result, and further deciding the motion plan of the automatic driving main vehicle so as to decide the vehicle crossing according to the characteristics of the actual vehicle crossing scene, improve the comfort of the vehicle crossing strategy, facilitate the main vehicle to safely and quickly pass through the vehicle crossing area, and improve the safety of the automatic driving main vehicle in vehicle crossing.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments 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.

Referring to fig. 5, an embodiment of the present application further provides a vehicle meeting device, where the vehicle meeting device corresponds to one vehicle meeting method in the foregoing embodiment. The vehicle meeting device comprises a vehicle meeting device,

the meeting vehicle judging and researching module is used for judging and researching whether a running area of the main vehicle and a running area of an oncoming vehicle have an overlapping space when a barrier occupies a lane in an opposite lane and the oncoming vehicle exists in front of the main vehicle in automatic driving;

Wherein the car-meeting judging and researching module comprises,

the track reference line unit is used for acquiring roadside boundary information and lane information according to map information when an obstacle occupies a lane and a coming vehicle comes in front of the automatic driving main vehicle, and generating a main vehicle track reference line and a coming vehicle track reference line by combining positioning information and the obstacle information;

a travel track unit for predicting a travel track of the host vehicle or a travel track of the incoming vehicle based on the track reference line;

and the overlapping space judging and researching unit is used for judging and researching whether the overlapping space exists in the main vehicle running area and the coming vehicle running area or not based on the main vehicle running track and the coming vehicle running track.

The motion planning module comprises a motion planning module and a motion planning module,

and the high-priority planning unit is used for optimizing the driving track of the coming vehicle and enabling the automatically-driven main vehicle to pass through the overlapping space according to the driving track of the main vehicle when the driving area of the main vehicle and the driving area of the coming vehicle have the overlapping space and the automatic-driven main vehicle has high driving priority.

And the low-priority planning unit is used for enabling the automatic driving main vehicle to stop from the current position to any optional position in front of the overlapping space in an edge-by-edge mode based on the positioning information of the automatic driving main vehicle and the driving track of the main vehicle when the driving area of the main vehicle and the driving area of the coming vehicle have the overlapping space and the automatic driving main vehicle has low driving priority.

The crossless passing planning unit is used for enabling the automatic driving main vehicle to run according to the running track of the main vehicle when the running area of the main vehicle and the running area of the coming vehicle have no overlapped space; or whether the coming vehicle running accords with the running track of the coming vehicle or not is determined based on the running track of the coming vehicle and roadside boundary information in the map information, and when the coming vehicle running does not accord with the running track of the coming vehicle and the coming vehicle invades the running track of the main vehicle, the automatic driving main vehicle is avoided.

For specific definition of a vehicle crossing device, reference may be made to the above definition of a vehicle crossing method, which is not described herein again. The modules in the vehicle meeting device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement any one of the above-mentioned vehicle crossing methods.

In one embodiment, a computer-readable storage medium is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

s3, deciding the passing priority based on the judging and researching result;

and S4, deciding the motion plan of the automatic driving main vehicle based on the passing priority.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Sync link (Syn1/Chlink) DRAM (SLDRAM), Rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It should be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is only used for illustration, and in practical applications, the above functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the system may be divided into different functional units or modules to implement all or part of the above described functions.

Claims

1. A vehicle meeting method is characterized by comprising the following steps,

detecting whether an incoming vehicle exists in front of the automatic driving main vehicle and whether obstacles occupy the lane of an opposite lane or not based on map information of the automatic driving main vehicle, positioning information of the automatic driving main vehicle and obstacle information;

deciding the passing priority based on the judging and researching result;

2. The vehicle crossing method according to claim 1, wherein the step of deciding the priority of passage based on the result of the research includes,

and respectively calculating the main vehicle avoidance cost and the incoming vehicle avoidance cost according to the avoidance cost function, and deciding that the corresponding avoidance cost of the two vehicles is high in passing priority.

3. A vehicle crossing method according to claim 2, wherein the avoidance cost function includes a vehicle deceleration limit factor and a remaining selection difficulty factor.

4. A vehicle crossing method according to claim 2, wherein the avoidance cost function further includes a road weight factor;

5. The vehicle crossing method according to claim 2, wherein the avoidance cost function further comprises a vehicle type factor;

6. The vehicle crossing method according to any one of claims 1 to 5, wherein the step of judging a spatial overlap condition of a host vehicle traveling region and an oncoming vehicle traveling region comprises,

acquiring the body widths, lane widths, barrier occupying widths and preset safe distances of the main vehicle and the coming vehicle based on the driving track of the main vehicle and the driving track of the coming vehicle, and calculating the width of the residual space of the track transverse spacing;

7. A method for meeting vehicles according to claim 6, wherein said step of deciding the movement plan of an autonomous host vehicle comprises, if there is an overlapping space between the driving area of the host vehicle and the driving area of the incoming vehicle and the autonomous host vehicle is of high driving priority,

8. A method for meeting vehicles according to claim 6, wherein said step of deciding the movement plan of an autonomous host vehicle comprises, if there is an overlapping space in the driving area of the host vehicle and the driving area of the incoming vehicle and the autonomous host vehicle is of low priority for driving,

and based on the positioning information of the automatic driving main vehicle and the driving track of the main vehicle, the automatic driving main vehicle is enabled to stop from the current position to any optional position in front of the overlapping space.

9. A method for meeting vehicles according to claim 8, wherein said step of deciding the movement plan of an autonomous host vehicle comprises, if there is an overlapping space in the driving area of the host vehicle and the driving area of the incoming vehicle and the autonomous host vehicle is of low priority for driving,

10. A vehicle meeting method according to claim 6,

if the running area of the main vehicle and the running area of the coming vehicle have no overlapping space and the main vehicle is decided to have no priority for passing, the step of deciding the motion planning of the automatic driving main vehicle comprises the following steps,

or detecting whether the coming vehicle running conforms to the coming vehicle running track or not based on the coming vehicle running track and roadside boundary information in the map information;

11. The vehicle crossing method according to claim 2, wherein the generating of the host vehicle running locus and the incoming vehicle running locus includes,

12. A vehicle meeting device is characterized by comprising,

the meeting scene recognition module is used for detecting whether an incoming vehicle exists in front of the automatic driving main vehicle and whether obstacles occupy the lane of an opposite lane or not based on map information of the automatic driving main vehicle, positioning information of the automatic driving main vehicle and obstacle information;

13. A computer device comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to perform the steps of the method of any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 11.