CN116524721A

CN116524721A - Vehicle intersection decision method, device, equipment and storage medium

Info

Publication number: CN116524721A
Application number: CN202310731737.XA
Authority: CN
Inventors: 王子嘉; 张天雷; 王晓东
Original assignee: Beijing Zhuxian Technology Co Ltd
Current assignee: Beijing Zhuxian Technology Co Ltd
Priority date: 2023-06-19
Filing date: 2023-06-19
Publication date: 2023-08-01

Abstract

The disclosure provides a vehicle intersection decision-making method, device, equipment and storage medium. The method comprises the following steps: and determining that the automatic driving vehicle enters the intersection and no indicator light signal is detected in response to the acquired environmental data, determining state information of the target vehicle and the target vehicle to be analyzed from the environmental data based on the set filtering rule, determining an expected meeting state of the automatic driving vehicle and the target vehicle based on the position relation between the first running track of the target vehicle and the second running track of the automatic driving vehicle and the shape parameter of the set part of the target vehicle, and determining the running strategy of the automatic driving vehicle based on the expected meeting state. The method solves the problem that the automatic driving vehicle lacks a stable and reliable decision method when passing through the intersection without the signal lamp, and ensures the running efficiency and the safety of the automatic driving vehicle when passing through the intersection.

Description

Vehicle intersection decision method, device, equipment and storage medium

Technical Field

The disclosure relates to the technical field of automatic driving, in particular to a vehicle intersection decision method, a device, equipment and a storage medium.

Background

With the generation of diversified traffic demands, automatic driving techniques are increasingly being used. An important difficulty in the application of autopilot technology is the travel at intersections. Because the road junction is the necessary place for people to drive vehicles, unmanned vehicles and people to collect, turn around and evacuate in urban road environment or in closed park, the factors influencing the safety of the vehicles are more, the decision difficulty is higher, and potential safety hazards easily occur. Especially for the crossing without signal lamp, the environment is more complex, and the safety and the efficiency of the automatic driving vehicle are greatly challenged.

In the prior art, the decision of the automatic driving vehicle when driving at the intersection is mainly judged by combining with the intersection signal lamp, and the decision of the automatic driving vehicle at the intersection without the signal lamp is a decision method based on learning, but the result stability of the method is insufficient, and the driving safety of the automatic driving vehicle cannot be ensured.

Disclosure of Invention

The disclosure provides a vehicle intersection decision method, device, equipment and storage medium, which are used for solving the problem that a stable and reliable decision method is lacking when an automatic driving vehicle passes through a traffic light-free intersection in the prior art.

In a first aspect, the present disclosure provides a vehicle intersection decision method, the vehicle intersection decision method comprising:

responding to the acquired environmental data, determining that the automatic driving vehicle enters the intersection and no indicator light signal is detected;

determining a target vehicle to be analyzed and state information of the target vehicle from environmental data based on a set filtering rule, wherein the state information comprises a first running track of the target vehicle and shape parameters of a set part;

determining an expected meeting state of the automatic driving vehicle and the target vehicle based on the position relation between the first driving track of the target vehicle and the second driving track of the automatic driving vehicle and the shape parameter of the set part of the target vehicle;

a driving strategy for the autonomous vehicle is determined based on the expected meeting status.

It can be seen that, by responding to the acquired environmental data, it is determined that the automatic driving vehicle enters the intersection and the indicator light signal is not detected, then based on the set filtering rule, state information of the target vehicle and the target vehicle to be analyzed is determined from the environmental data, then based on the first driving track of the target vehicle, the shape parameter of the set part and the position relation of the second driving track of the automatic driving vehicle, the expected meeting state of the automatic driving vehicle and the target vehicle is determined, and finally based on the expected meeting state, the driving strategy of the automatic driving vehicle is determined. Therefore, the target vehicle which influences the running of the unmanned vehicle can be effectively identified at the intersection without the indicator lamp, and whether the automatic driving vehicle needs to be decelerated, avoided or other running strategies can be determined according to the running state and the structural characteristics of the target vehicle, so that the unmanned vehicle can reliably and regularly ensure the running safety at the intersection without the indicator lamp, and the running strategy is determined by screening the target vehicle, so that the running safety of the vehicle is ensured, the influence of excessive environmental factors is avoided, and the running efficiency and the running safety of the automatic driving vehicle passing through the intersection are ensured.

Optionally, determining the expected meeting state of the autonomous vehicle and the target vehicle based on the positional relationship between the first driving track of the target vehicle and the second driving track of the autonomous vehicle and the shape parameter of the set part of the target vehicle includes: determining a target structure with the maximum width of the target vehicle as a set part based on the type of the target vehicle; taking a point on the first running track as a circle center, generating a track expansion circle corresponding to the first running track based on the width of the target structure and the set expansion width, wherein the set expansion width is determined based on the type of the target vehicle; and determining the expected meeting state based on the intersection point of the second running track and the track expansion circle.

Therefore, the expected meeting state is determined by combining the intersection point of the track expansion circle of the first running track and the second running track, so that the possible state of the automatic driving vehicle and the target vehicle during meeting can be determined graphically and accurately, the track expansion circle is determined by a plurality of parameters together, the structural characteristics of the target vehicle are fully considered, the accuracy of determining the possible state during meeting is further ensured, and the running strategy can be determined accurately according to the accuracy, so that the running safety of the automatic driving vehicle is ensured.

Optionally, determining the expected meeting state based on the intersection of the second travel track and the track expansion circle includes: determining an intersection point of the second travel track and the first travel track; determining a tangent point of the track expansion circle and the second running track; determining one point from the intersection point and the tangent point to the nearest point of the automatic driving vehicle as a conflict point; an expected meeting state is determined based on the target vehicle behavior state, the autonomous vehicle behavior state, and the conflict point.

Therefore, the conflict point is determined from a plurality of intersection points and tangent points, and the expected meeting state is determined based on the conflict point, so that the positions of the automatic driving vehicle and the target vehicle in the expected meeting state with the earliest occurrence time are determined, the most urgent danger is effectively avoided, and the running safety of the automatic driving vehicle is ensured.

Optionally, the target vehicle action state includes a first speed of the target vehicle, the autonomous vehicle action state includes a second speed of the autonomous vehicle, and determining the expected meeting state based on the target vehicle action state, the autonomous vehicle action state, and the conflict point includes: determining a first moment when the head of the autonomous vehicle reaches the point of conflict based on the second speed; determining a second moment when the head of the target vehicle reaches the conflict point and a third moment when the tail of the target vehicle reaches the conflict point based on the first speed; if the difference value between the second moment and the first moment is larger than the first time threshold, determining that the expected meeting state is that the automatic driving vehicle passes through the conflict point first and cannot collide with the target vehicle; or if the difference value between the first moment and the third moment is larger than the second time threshold value, determining that the expected meeting state is that the target vehicle passes through the conflict point first and cannot collide with the automatic driving vehicle; or if the difference between the first time and the second time is smaller than the first time threshold, determining that the expected passing state is that the target vehicle collides with the automatic driving vehicle.

Therefore, according to different target vehicles and running states of the automatic driving vehicle, different expected meeting states can be accurately determined, possible collision is avoided in advance, and running safety of the automatic driving vehicle is guaranteed.

Optionally, determining a driving strategy of the autonomous vehicle based on the expected meeting state includes: if the expected meeting state is that the automatic driving vehicle and the target vehicle cannot collide, determining that the driving strategy is to keep the current driving state; if the expected meeting state is that the target vehicle collides with the automatic driving vehicle, determining the driving strategy of the automatic driving vehicle based on the first speed and the first driving track of the target vehicle.

Therefore, the driving strategy is determined according to whether the target vehicle and the automatic driving vehicle collide, the driving state is maintained when collision danger does not occur, invalid adjustment is avoided, and the driving efficiency and the stability of the automatic driving vehicle are improved.

Optionally, if the meeting state is that the target vehicle collides with the automatic driving vehicle, determining the driving strategy of the automatic driving vehicle based on the first speed and the first driving track of the target vehicle includes: if the first speed is higher than the set first speed threshold, the running speed is adjusted based on the set deceleration parameter until the target vehicle passes through the conflict point and cannot collide with the automatic driving vehicle; if the first speed is lower than the set first speed threshold, determining a safe intersection time based on the distance between the target vehicle and the conflict point and the first speed; the travel speed is redetermined based on the location of the autonomous vehicle and the safe intersection time.

Therefore, collision risks in different scenes can be effectively avoided through different driving strategies, and the driving safety of the automatic driving vehicle is fully ensured.

Optionally, determining the target vehicle to be analyzed and the state information of the target vehicle from the environmental data based on the set filtering rule includes: filtering vehicles with the distance from the automatic driving vehicle being greater than a first set distance threshold; filtering vehicles located behind the autonomous vehicle identified in the environmental data based on the direction of travel of the autonomous vehicle; if the running direction of the automatic driving vehicle is straight, filtering vehicles which are identified in the environment data and have the same direction as the automatic driving vehicle; or if the running direction of the automatic driving vehicle is left-turning, filtering the vehicle which is identified in the environment data and is positioned on the right side of the automatic driving vehicle and is in the same direction and directly moving or turning right; or if the running direction of the automatic driving vehicle is right-turning, filtering the vehicle which is identified in the environment data and is positioned on the left side of the automatic driving vehicle and is in the same direction and is straight or turns left; determining a vehicle with an included angle between the filtered vehicle and the running direction of the automatic driving vehicle in a set angle range as a target vehicle to be analyzed; based on the environmental data, status information of the target vehicle is acquired.

Therefore, the target vehicle with safety risk for the running of the automatic driving vehicle can be accurately found out from the environmental data through different filtering rules, so that the data acquisition requirement is reduced based on the state information of the target vehicle for further analysis, the processing efficiency is improved, and meanwhile, the running safety of the automatic driving vehicle is ensured.

Optionally, determining the driving strategy of the autonomous vehicle based on the expected meeting state further comprises: determining that the driving strategy of the automatic driving vehicle is braked to a stop state when an obstacle with the speed smaller than a second speed threshold exists in the second driving track and the distance between the obstacle and the automatic driving vehicle is smaller than a second set distance threshold; obtaining a driving coverage corresponding to the second driving track based on the shape parameters of the automatic driving vehicle and the set vehicle body extension, and determining that the driving strategy of the automatic driving vehicle is braked to a stop state when the driving coverage is partially overlapped with the first driving track of the target vehicle; if the distance between the target vehicle and the automatic driving vehicle is smaller than the third set distance threshold value, determining that the driving strategy of the automatic driving vehicle is based on the set deceleration braking.

Therefore, the running safety of the automatic driving vehicle under different environments is effectively ensured by adopting the running strategy of decelerating, braking or stopping under different special conditions.

In a second aspect, the present disclosure provides a vehicle intersection decision making apparatus comprising:

the environment recognition module is used for responding to the acquired environment data, determining that the automatic driving vehicle enters the intersection and the indicator light signal is not detected;

the target identification module is used for determining a target vehicle to be analyzed and state information of the target vehicle from the environmental data based on a set filtering rule, wherein the state information comprises a first running track of the target vehicle and shape parameters of a set part;

the analysis module is used for determining the expected meeting state of the automatic driving vehicle and the target vehicle based on the position relation between the first driving track of the target vehicle and the second driving track of the automatic driving vehicle and the shape parameter of the set part of the target vehicle;

and the processing module is used for determining the driving strategy of the automatic driving vehicle based on the expected meeting state.

Optionally, the analysis module is specifically configured to determine, as the set location, a target structure with a maximum target vehicle width based on a type of the target vehicle; taking a point on the first running track as a circle center, generating a track expansion circle corresponding to the first running track based on the width of the target structure and the set expansion width, wherein the set expansion width is determined based on the type of the target vehicle; and determining the expected meeting state based on the intersection point of the second running track and the track expansion circle.

Optionally, the analysis module is specifically configured to determine an intersection point of the second travel track and the first travel track; determining a tangent point of the track expansion circle and the second running track; determining one point from the intersection point and the tangent point to the nearest point of the automatic driving vehicle as a conflict point; an expected meeting state is determined based on the target vehicle behavior state, the autonomous vehicle behavior state, and the conflict point.

Optionally, the analysis module is specifically configured to determine, if the target vehicle action state includes a first speed of the target vehicle, the autopilot vehicle action state includes a second speed of the autopilot vehicle, and determine, based on the second speed, a first moment when the head of the autopilot vehicle reaches the conflict point; determining a second moment when the head of the target vehicle reaches the conflict point and a third moment when the tail of the target vehicle reaches the conflict point based on the first speed; if the difference value between the second moment and the first moment is larger than the first time threshold, determining that the expected meeting state is that the automatic driving vehicle passes through the conflict point first and cannot collide with the target vehicle; or if the difference value between the first moment and the third moment is larger than the second time threshold value, determining that the expected meeting state is that the target vehicle passes through the conflict point first and cannot collide with the automatic driving vehicle; or if the difference between the first time and the second time is smaller than the first time threshold, determining that the expected passing state is that the target vehicle collides with the automatic driving vehicle.

Optionally, the processing module is specifically configured to determine that the driving policy is to keep the current driving state if the expected meeting state is that the automatic driving vehicle and the target vehicle cannot collide; if the expected meeting state is that the target vehicle collides with the automatic driving vehicle, determining the driving strategy of the automatic driving vehicle based on the first speed and the first driving track of the target vehicle.

Optionally, the processing module is specifically configured to adjust the running speed based on the set deceleration parameter if the first speed is higher than the set first speed threshold, until the target vehicle passes through the conflict point and does not collide with the autopilot vehicle; if the first speed is lower than the set first speed threshold, determining a safe intersection time based on the distance between the target vehicle and the conflict point and the first speed; the travel speed is redetermined based on the location of the autonomous vehicle and the safe intersection time.

Optionally, the target recognition module is specifically configured to filter a vehicle having a distance from the autonomous vehicle that is greater than a first set distance threshold; filtering vehicles located behind the autonomous vehicle identified in the environmental data based on the direction of travel of the autonomous vehicle; if the running direction of the automatic driving vehicle is straight, filtering vehicles which are identified in the environment data and have the same direction as the automatic driving vehicle; or if the running direction of the automatic driving vehicle is left-turning, filtering the vehicle which is identified in the environment data and is positioned on the right side of the automatic driving vehicle and is in the same direction and directly moving or turning right; or if the running direction of the automatic driving vehicle is right-turning, filtering the vehicle which is identified in the environment data and is positioned on the left side of the automatic driving vehicle and is in the same direction and is straight or turns left; determining a vehicle with an included angle between the filtered vehicle and the running direction of the automatic driving vehicle in a set angle range as a target vehicle to be analyzed; based on the environmental data, status information of the target vehicle is acquired.

Optionally, the processing module further includes determining that the driving strategy of the autonomous vehicle is braking to a stopped state when an obstacle with a speed less than a second speed threshold exists in the second driving track and a distance from the autonomous vehicle is less than a second set distance threshold; obtaining a driving coverage corresponding to the second driving track based on the shape parameters of the automatic driving vehicle and the set vehicle body extension, and determining that the driving strategy of the automatic driving vehicle is braked to a stop state when the driving coverage is partially overlapped with the first driving track of the target vehicle; if the distance between the target vehicle and the automatic driving vehicle is smaller than the third set distance threshold value, determining that the driving strategy of the automatic driving vehicle is based on the set deceleration braking.

In a third aspect, the present disclosure also provides a control apparatus including:

at least one processor;

and a memory communicatively coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor to cause the control device to perform a vehicle intersection decision method as corresponds to any embodiment of the first aspect of the present disclosure.

In a fourth aspect, the present disclosure also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement a vehicle intersection decision method as in any one of the first aspects of the present disclosure.

In a fifth aspect, the present disclosure also provides a computer program product containing computer-executable instructions for implementing the vehicle intersection decision method according to any embodiment corresponding to the first aspect of the present disclosure when executed by a processor.

Drawings

Fig. 1 is an application scenario diagram of a vehicle intersection decision method provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart of a vehicle intersection decision making method provided by one embodiment of the present disclosure;

FIG. 3a is a flow chart of a vehicle intersection decision making method provided by yet another embodiment of the present disclosure;

FIG. 3b is a flow chart of a method of determining an expected meeting status provided in the embodiment of FIG. 3 a;

FIG. 3c is a schematic diagram of the relationship between the tangent points, the intersecting points and the conflict points provided in the embodiment shown in FIG. 3 a;

FIG. 3d is a flowchart of a method for determining an expected meeting state based on a conflict point and a vehicle driving state provided in the embodiment of FIG. 3 a;

FIG. 3e is a flow chart of a method of driving strategy determination provided in the embodiment of FIG. 3 a;

FIG. 4a is a flow chart of a vehicle intersection decision making method provided by yet another embodiment of the present disclosure;

FIG. 4b is a schematic view of a scenario in which an obstacle is present on the second driving track provided in the embodiment shown in FIG. 4 a;

FIG. 4c is a schematic view of a scenario in which the coverage area of the autonomous vehicle provided in the embodiment shown in FIG. 4a coincides with the first travel track;

fig. 5 is a schematic structural diagram of a vehicle intersection decision making device according to another embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a control apparatus according to still another embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present application. Rather, they are merely examples of apparatus and methods consistent with aspects of embodiments of the present application as detailed in the accompanying claims.

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

With the generation of diversified traffic demands, automatic driving techniques are increasingly being used. The automatic driving vehicle based on the automatic driving technology can gradually execute application tasks such as downloading people, carrying cargo and the like in various environments. In these application tasks, how an autonomous vehicle travels through an intersection is an important difficulty. Because the road junction is the necessary place for people to drive vehicles, automatic driving vehicles and people to collect, turn around and evacuate in urban road environment or in closed park, the factors influencing the safety of the vehicles are more, the decision difficulty is higher, and potential safety hazards easily occur.

Especially for the crossing without signal lamp, because the signal lamp is not used for limiting the movement of the vehicle and the pedestrian in other directions except the running direction of the automatic driving vehicle, the environment facing the automatic driving vehicle is complex during running, the safety of unmanned measurement cannot be ensured at the crossing with signal lamp and the like, and great challenges are brought to the safe and efficient passing of the automatic driving vehicle.

In the prior art, decision of an automatic driving vehicle when driving at an intersection is mainly based on intersection signal lamps for judgment, and when the intersection signal lamps are in a state capable of driving, the driving strategy of the automatic driving vehicle can be determined by combining the vehicle states at two sides of the position. For intersections without signal lamps, the decision of the driving strategy is a decision method based on learning, and the driving strategy under different environments needs to be learned through training, but the result stability of the method is insufficient, and in practical application, if the environment which does not exist during learning exists, the reliability of the decision of an automatic driving vehicle cannot be ensured, and the driving safety cannot be ensured.

In order to solve the above problems, the embodiments of the present application provide a vehicle intersection decision method, which identifies a specific target vehicle needing to be noticed based on environmental data and a preset filtering rule, and then determines a driving strategy according to the state of the target vehicle and the driving state of the target vehicle, adapts to different complex environments, and ensures the driving safety and reliability of an automatic driving vehicle.

Fig. 1 is an application scenario diagram of a vehicle intersection decision method provided in an embodiment of the present application. As shown in fig. 1, in the intersection decision making process, the autonomous vehicle 100 confirms entry into an intersection by recognizing the environmental data, then recognizes the target vehicle 110, determines whether collision with the target vehicle 110 will occur or not according to the first travel track 111 of the target vehicle 110 and the second travel track 101 of the target vehicle, and further determines the travel strategy of the autonomous vehicle passing through the intersection.

It should be noted that, in the scenario shown in fig. 1, the autonomous vehicle and the target vehicle are only illustrated as an example, but the embodiment of the present application is not limited thereto, that is, the number of autonomous vehicles and the target vehicles may be arbitrary.

The vehicle intersection decision-making method provided by the application is described in detail below through specific embodiments. It should be noted that the following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

Fig. 2 is a flowchart of a vehicle intersection decision making method according to an embodiment of the present application. As shown in fig. 2, including but not limited to the following steps:

step S201, responding to the acquired environmental data, determining that the automatic driving vehicle enters the intersection and no indicator light signal is detected.

Specifically, an autonomous vehicle may collect environmental data around the vehicle in real time. The environmental data may be image data collected by an image sensor (such as a camera), GPS positioning data collected by a positioning sensor, distance data from surrounding objects collected by an infrared sensor or an ultrasonic sensor to an autonomous vehicle, etc., through which the determination of the location of the vehicle and the relative location to surrounding objects (such as vehicles, lanes, pedestrians, etc.) is performed.

According to different data types, the coverage range (or distance) of the environmental data is different, and the environmental data generally needs to cover more than twenty meters around the vehicle or more, so that when dangerous objects (such as children and animals sitting on the ground) exist on the running path of the automatic driving vehicle, braking measures can be timely taken, and running safety is guaranteed.

The autonomous vehicle needs to determine that itself is at the intersection by the environmental data to switch to the determination logic for entering the intersection (to determine whether the indicator light signal is detected).

If the indicator light signal can be detected, traveling can be performed using a traveling strategy based on the indicator light signal in the related art.

However, if the pilot signal is not detected by the autonomous vehicle, a subsequent decision is required in combination with other environmental data.

The identification and judgment of the intersection can have different judgment modes corresponding to different types of environment data. For example, corresponding to the GPS positioning data, the location of the autonomous vehicle may be combined with the positioning software or map data in the map software (e.g., identifying an intersection where the location of the vehicle is located in the map may be completed); corresponding image data can be identified directly according to the shot surrounding environment image (if the ground accords with the intersection feature, the identification can be completed); the corresponding distance data can be identified according to the obtained road surface characteristics (if the road surface meets the intersection characteristics, the identification can be completed), other existing intersection identification judging methods can be adopted, or a combination of a plurality of modes can be adopted.

Step S202, determining the target vehicle to be analyzed and the state information of the target vehicle from the environment data based on the set filtering rules.

Wherein the state information includes a first travel track of the target vehicle and a shape parameter of the set portion.

Specifically, since the intersection has no indicator light signal, when the autonomous vehicle passes through the intersection, vehicles, pedestrians, and the like traveling in different directions may exist around the autonomous vehicle (while if the intersection has the indicator light signal, the autonomous vehicle generally has only vehicles around the intersection, and the traveling direction is the same as or opposite to that of the autonomous vehicle, and the vehicle generally traveling track different from the traveling direction of the autonomous vehicle does not intersect with the autonomous vehicle), so that it is necessary to find data that may affect the traveling safety of the vehicle from the surrounding vehicles and pedestrians according to the collected environmental data.

And judging whether surrounding vehicles and pedestrians influence the running safety of the vehicles or not, namely, judging whether the surrounding vehicles and pedestrians are filtering rules. Wherein, when a pedestrian is present around the automatic driving vehicle (for example, the distance between the pedestrian and the running track of the automatic driving vehicle is smaller than the set safe distance value), the automatic driving vehicle can stop directly or decelerate according to the set deceleration without further analysis (because the action of the pedestrian is difficult to predict, it is preferable to decelerate directly to stop or decelerate until the distance between the pedestrian and the running track reaches the set safe distance value for ensuring safety).

If other vehicles exist around the automatic driving vehicle, the filtering can be performed according to factors such as distance between the other vehicles and the automatic driving vehicle (for example, the vehicle with too far distance can be directly excluded), relative driving speed (for example, the vehicle with too slow relative driving speed can not meet after the automatic driving vehicle passes through the intersection), relative driving direction (for example, the relative driving direction is inconsistent, so that the other vehicles are far away from the automatic driving vehicle, and the vehicle can be directly excluded).

The vehicles left after filtering, i.e. the vehicles which may have an influence on the driving safety of the autonomous vehicle, i.e. the target vehicles, require further analysis of such vehicles to ensure the safety of the autonomous vehicle.

For further analysis, it is necessary to collect state information of the target vehicle. The status information may be generally determined by integrating image data and distance data, and the like, and includes a vehicle type (different types such as a large truck, a tricycle, and a sedan, because of different predicted deceleration distances and different shape characteristics), a vehicle shape parameter (different set positions corresponding to the shape parameter according to different types of target vehicles, generally, one of the positions having the largest width of the target vehicle is selected as the set position, and the width of the set position is the corresponding shape parameter), a travel speed, a relative position with respect to the autonomous vehicle, and a predicted travel track (i.e., a first travel track), and the like.

The first driving track can be determined according to the continuously collected position, driving speed and driving direction of the target vehicle, and the determining method can directly refer to the related technology and is not limited herein.

Step S203, determining an expected meeting state of the autonomous vehicle and the target vehicle based on the positional relationship between the first driving track of the target vehicle and the second driving track of the autonomous vehicle, and the shape parameter of the set portion of the target vehicle.

Specifically, since the target vehicle has different vehicle types and different size and shape characteristics, different results are generated by analyzing the state of the target vehicle when the target vehicle meets the automatic driving vehicle (if the target vehicle is a long truck, whether the target vehicle collides with the automatic driving vehicle when the target vehicle meets the automatic driving vehicle or not is analyzed, and the running speed, the vehicle length, the width and the like of the target vehicle need to be considered at the same time, but if the target vehicle is a mini electric vehicle, only the lower width can be considered regardless of the length of the target vehicle, because the length of the target vehicle is short, the influence on the analysis result is not great), therefore, a set position for analyzing the meeting vehicle needs to be selected based on different vehicle types, and whether the collision occurs or not is judged based on the shape parameters of the set position.

Since the target vehicle and the autonomous vehicle are usually in a high-speed driving state at the intersection, when analyzing the meeting state, a shape model (such as a cuboid model including the target vehicle) of the target vehicle is generated mainly by selecting a set part (such as a part with the largest width), then the position and the movement track of the shape model are analyzed to be not crossed with the movement track (such as a second driving track) of the (shape model of the) autonomous vehicle, and if the crossing exists, when any one of the two vehicles moves to the intersection, the shape models of the two vehicles are not partially overlapped (such as the expected meeting state, if the overlapping exists, the two vehicles can be considered to collide, and the specific structures of the two vehicles are not overlapped, so that the calculated amount is too large on one hand, and the influence on the result is not great on the other hand).

By analyzing based on the shape parameters of the set portion, the calculation amount can be significantly reduced while ensuring the effect and reliability of the analysis, compared to analyzing using a vehicle model configured in advance or collecting detailed parameters of the target vehicle in the related art.

Step S204, determining a driving strategy of the automatic driving vehicle based on the expected meeting state.

Specifically, if the expected meeting state is that two vehicles cannot collide, the driving strategy may be to keep the current driving state.

If the expected meeting state is that two vehicles possibly collide, different driving strategies need to be determined according to the specific meeting state. If two vehicles pass through the intersection in front of and behind each other, the driving strategy can be set to be decelerating until the expected meeting state is changed into a state that the two vehicles cannot collide; if two vehicles pass through the intersection at the same time, the driving strategy can be set to be braked to a parking state.

In some embodiments, in a specific emergency, other driving strategies may be adopted, for example, the target vehicle is in continuous deceleration driving, and the driving strategy may be acceleration passing within a set speed range; if the target vehicle is traveling continuously under acceleration, the driving strategy may be deceleration, fine-tuning the driving route so that the target vehicle passes preferentially through the intersection (but a deceleration strategy is generally preferred), and so on.

According to the vehicle intersection decision-making method, the automatic driving vehicle is determined to enter the intersection by responding to the acquired environmental data, the indicator light signal is not detected, the state information of the target vehicle and the target vehicle to be analyzed is determined from the environmental data based on the set filtering rule, the expected meeting state of the automatic driving vehicle and the target vehicle is determined based on the first running track of the target vehicle, the shape parameter of the set part and the position relation of the second running track of the automatic driving vehicle, and finally the running strategy of the automatic driving vehicle is determined based on the expected meeting state. Therefore, the target vehicle which influences the running of the unmanned vehicle can be effectively identified at the intersection without the indicator lamp, and whether the automatic driving vehicle needs to be decelerated, avoided or other running strategies can be determined according to the running state and the structural characteristics of the target vehicle, so that the unmanned vehicle can reliably and regularly ensure the running safety at the intersection without the indicator lamp, and the running strategy is determined by screening the target vehicle, so that the running safety of the vehicle is ensured, the influence of excessive environmental factors is avoided, and the running efficiency of the vehicle passing through the intersection is ensured.

Fig. 3a is a flowchart of a vehicle intersection decision making method according to another embodiment of the present application. As shown in fig. 3a, the vehicle intersection decision method includes:

step S301, in response to the acquired environmental data, it is determined that the autonomous vehicle enters the intersection and no indicator light signal is detected.

Step S302, determining the target vehicle to be analyzed and the state information of the target vehicle from the environment data based on the set filtering rules.

Wherein the status information includes a first travel track and shape parameters of the target vehicle.

Specifically, the steps S301 to S302 are the same as the corresponding steps in the embodiment shown in fig. 2, and are not repeated here.

Step S303, determining a target structure with the largest target vehicle width as a set location based on the type of the target vehicle.

Specifically, in order to determine the expected meeting state of the target vehicle and the autonomous vehicle, it is necessary to determine whether an intersection exists between the two based on the shape parameter of the target vehicle and the first travel track, and the second travel track of the autonomous vehicle.

For the target vehicles, if all the size data are directly used, the calculation amount is large, and the adjustability of the target vehicles in the running process is different (for example, the heavy truck usually keeps the first running track unchanged when no dangerous condition is encountered, so that the predictability is high, while the small tricycle can see that the potential dangerous condition accelerates preferentially or changes the first running track, so that the predictability is low), the direct use of the size data calculates whether collision occurs, and the difference from the actual situation can exist (particularly, for the vehicle with flexible control, the vehicle can accelerate and change the first running track under the condition that the first running track and the second running track are not predicted to intersect, so that the changed first running track and the second running track intersect, and the collision risk is caused).

Therefore, by determining the maximum width, setting the expansion width according to the maximum width, and determining whether an intersection point exists after the combination of the expansion width and the first travel track, the condition that the first travel track changes can be fully considered, the safety of the vehicle meeting process is ensured to the greatest extent, and the safety of the automatic driving vehicle when passing through an intersection is further ensured.

The corresponding relation between the type of the specific target vehicle and the target structure can be configured according to actual conditions, for example, a truck can select a container part as the target structure and the width of the container part as the maximum width; the car can select the head part as a target structure (because the width of the car is generally consistent from front to back), and the width of the head part is used as the maximum width; the tricycle can select the tail part as the target structure (usually the tail part is provided with two wheels which are the parts with the largest width), and the motorcycle can select the head part as the target structure.

Step S304, a track expansion circle corresponding to the first running track is generated by taking a point on the first running track as a circle center and based on the width of the target structure and the set expansion width.

Wherein the set expansion width is determined based on the type of the target vehicle.

Specifically, since there is often no intersection between the first travel track and the second travel track, when the first travel track is close to the second travel track, the target vehicle based on the first travel track and the autonomous vehicle based on the second travel track collide (i.e., a very common scratch accident), and at this time, the judgment cannot be performed through the intersection between the first travel track and the second travel track.

Therefore, by generating a plurality of track expansion circles corresponding to the first travel track (each point on the first travel track corresponds to the center of one track expansion circle), when the second travel track is tangent to any track expansion circle, it can be considered that the target vehicle and the automatic driving vehicle may have a collision condition.

The diameter of the trajectory expansion circle is determined based on the width of the target structure (i.e., the width of the target vehicle) and the set expansion width.

Setting the inflated width typically includes the width of the autonomous vehicle itself and the width of the target vehicle.

In some embodiments, the expansion width is set to be the sum of the product of the width of the target vehicle and the expansion coefficient and the width of the autonomous vehicle itself. At this time, the expansion coefficient is determined according to the type of the target vehicle, and the larger the expansion coefficient is (for example, the minimum expansion coefficient is 1.2, the larger the expansion coefficient corresponds to a large truck, the maximum expansion coefficient is 3, and the expansion coefficient corresponds to a motorcycle), by setting the expansion coefficient, the distance allowance in the expected meeting state is increased, thereby fully considering the change of the first running track of the target vehicle when the target vehicle is possibly close to the automatic driving vehicle, ensuring that the target vehicle cannot collide with the automatic driving vehicle even if the target vehicle adjusts the first running track after the second running track is not tangential to any track expansion circle, if the second running track is not tangential to any track expansion circle (otherwise, the first running track and the second running track may not intersect, but the target vehicle suddenly adjusts the running track in the running process, so that the first running track and the second running track intersect, if the first running track and the second running track intersect according to the original running strategy, if the first running track expansion circle are analyzed, the target vehicle can leave more safety allowance even if the target vehicle adjusts the running track.

And step S305, determining the expected meeting state based on the intersection point of the second running track and the track expansion circle.

Specifically, since the second travel track and the first travel track are necessarily tangent to or intersect with a certain track expansion circle when they intersect, the expected meeting state can be analyzed based on the intersection of the second travel track and any track expansion circle.

Further, as shown in fig. 3b, a flowchart of a method for determining an expected meeting state includes the following specific steps:

step S3051, determining an intersection point of the second travel track and the first travel track.

Specifically, in one case, the second running track and the first running track intersect, and then the corresponding intersection point is directly determined.

Step S3052, determining a tangent point of the trajectory expansion circle and the second travel trajectory.

Specifically, when the second running track intersects with the first running track, the second running track is necessarily tangent to any track expansion circle, and then a tangent point is necessarily present. There may be one or more points of intersection (where there are multiple points of intersection, this is typically included as shown in fig. 3 c).

In another case, the second travel track does not intersect the first travel track, but the second travel track is also tangent to a track expansion circle, and the tangent point can be determined as well.

In step S3053, one of the intersection point and the tangent point, which is closest to the autonomous vehicle, is determined as a conflict point.

Specifically, if there is both the intersection point and the tangent point, one of the points closest to the autonomous vehicle is determined as the conflict point, and if there is only the tangent point, the tangent point is determined as the conflict point.

For example, as shown in fig. 3c, the relationship between the intersection points, the intersection points and the conflict points is schematically shown, where the intersection point 340 exists between the second running track 310 of the autonomous vehicle 300 and the first running track 330 of the target vehicle 320, and the intersection point 360 exists between the second running track 310 and the corresponding track expansion circle 350 of the first running track 330 (two tangent points 360 are respectively tangent to the left side and the right side of the head of the target vehicle 320 in the drawing), and the closest one tangent point 360 to the autonomous vehicle 300 is determined as the conflict point based on the distances between the intersection point 340, the tangent point 360 and the autonomous vehicle.

Step S3054, determining an expected meeting state based on the target vehicle action state, the autonomous vehicle action state, and the conflict point.

Specifically, the expected meeting state of the target vehicle and the automatic driving vehicle can be determined according to which vehicle arrives at the conflict point first, passes through the conflict point first, and whether the two vehicles collide when arriving at the conflict point.

In some embodiments, as shown in fig. 3d, a flowchart of a method for determining an expected meeting state based on a conflict point and a vehicle driving state includes the following specific steps:

and A1, determining a first moment when the head of the automatic driving vehicle reaches a conflict point based on the second speed.

Wherein the target vehicle behavior state comprises a first speed of the target vehicle and the autonomous vehicle behavior state comprises a second speed of the autonomous vehicle.

In particular, the size data and the second speed of the autonomous vehicle can be determined directly, so that the time when the autonomous vehicle (head part) reaches the conflict point, i.e. the first moment, can be determined first.

And A2, determining a second moment when the head of the target vehicle reaches the conflict point and a third moment when the tail of the target vehicle reaches the conflict point based on the first speed.

Specifically, a first speed at which the target vehicle moves may be determined based on the continuously acquired environmental data. The second moment when the head of the target vehicle reaches the conflict point and the third moment when the tail of the target vehicle reaches the conflict point can be determined according to the length of the target vehicle.

And A3, if the difference value between the second moment and the first moment is larger than the first time threshold, determining that the expected meeting state is that the automatic driving vehicle passes through the conflict point first and cannot collide with the target vehicle.

Specifically, if the second moment is smaller than the first moment and there is a certain difference (i.e., a first time threshold, for example, 3 seconds), when the autopilot vehicle passes through the conflict point, the head of the target vehicle is further a certain distance (combined with the first speed, usually more than 20 meters) from the conflict point, and at this time, the target vehicle and the autopilot vehicle will not collide.

And A4, if the difference value between the first moment and the third moment is larger than the second time threshold value, determining that the expected meeting state is that the target vehicle passes through the conflict point first and the automatic driving vehicle cannot collide.

Specifically, the third time is smaller than the first time, and a certain difference (i.e., a second time threshold, for example, 2 seconds) exists, when the target vehicle passes through the conflict point, the head of the automatic driving vehicle is further away from the conflict point (combined with the second speed, usually more than 10 meters), and at this time, the target vehicle and the automatic driving vehicle will not collide.

And step A5, if the difference value between the first moment and the second moment is smaller than the first time threshold value, determining that the expected passing state is that the target vehicle collides with the automatic driving vehicle.

Specifically, if the first moment is greater than the second moment and the difference is smaller, the head of the target vehicle passes through the conflict point, but the tail of the target vehicle does not pass through the conflict point, and the automatic driving vehicle also reaches the conflict point, the situation that the automatic driving vehicle overtakes the target vehicle can occur; if the first moment is smaller than the second moment and the difference is smaller, the head of the automatic driving vehicle passes through the conflict point, but the tail of the vehicle does not necessarily pass through the conflict point, and the head of the target vehicle also reaches the conflict point, the situation that the target vehicle is in rear-end collision with the automatic driving vehicle can occur. In both cases, a situation occurs in which the target vehicle collides with the automatically driven vehicle.

Steps A3 to A5 are optional steps parallel to each other, and a person skilled in the art may choose to execute the corresponding steps according to the actual situation.

And step S306, if the expected meeting state is that the automatic driving vehicle and the target vehicle cannot collide, determining the driving strategy to keep the current driving state.

Specifically, if the autonomous vehicle and the target vehicle do not collide, the current running state (including the second speed and the second running track) of the autonomous vehicle can be ensured to be safe, so that the current running state can be kept to continue running.

Step S307, if the expected meeting state is that the target vehicle collides with the automatic driving vehicle, the driving strategy of the automatic driving vehicle is determined based on the first speed and the first driving track of the target vehicle.

Specifically, in the case of a possible collision, the driving strategy of the autonomous vehicle needs to be adjusted, and different adjustment modes may be available according to different first speeds of the target vehicle.

Further, as shown in fig. 3e, the method is a flow chart of a method for determining a driving strategy, and the specific steps include:

in step S3071, if the first speed is higher than the set first speed threshold, the driving speed is adjusted based on the set deceleration parameter until the target vehicle passes through the collision point and no collision occurs with the autonomous vehicle.

Specifically, if the first speed is not very low (the first speed threshold is low, such as 20 km/h), the autonomous vehicle should be directly decelerated or stopped to ensure the driving safety. The specific deceleration can be performed according to the set deceleration parameters (such as the speed of deceleration, the time of deceleration and the like) so as to ensure the stability and safety of the measurement running.

In step S3072, if the first speed is lower than the set first speed threshold, a safe meeting time is determined based on the distance between the target vehicle and the conflict point and the first speed.

Specifically, if the first speed is low (e.g., the target vehicle is passing through the intersection at a very low speed), the autonomous vehicle may choose to slow down, stop for waiting, and also readjust the driving speed, and directly exit the intersection in advance without waiting for the target vehicle.

The specific method for adjusting the running speed may be based on the difference between the second time (which may be determined by the distance between the target vehicle and the conflict point and the first speed) and the set safety time threshold (for example, 3 seconds), as the safe intersection time.

Step S3073, redetermining the running speed based on the location of the autonomous vehicle and the safe intersection time.

Specifically, the method aims at that the automatic driving vehicle passes through the conflict point at the safe meeting time, and the running speed of the automatic driving vehicle is determined again, so that the situation that the automatic driving vehicle collides with the target vehicle can be avoided, and the running safety is ensured.

According to the vehicle intersection decision-making method, after the target vehicle is determined according to the environmental data, the track expansion circle is generated according to the state information of the target vehicle, then the expected meeting state is determined according to the relation between the second running track of the automatic driving vehicle and the track expansion circle, and the running strategy is determined based on the expected meeting state. Therefore, the automatic driving vehicle can be prevented from colliding with the target vehicle when passing through the intersection position, so that the safety of the automatic driving vehicle when passing through the intersection is ensured, and the safety and reliability of the automatic driving vehicle are improved.

Fig. 4a is a flowchart of a vehicle intersection decision making method according to still another embodiment of the present application. As shown in fig. 4a, the vehicle intersection decision method provided in this embodiment includes the following steps:

step S401, responding to the acquired environmental data, determining that the automatic driving vehicle enters the intersection and no indicator light signal is detected.

Specifically, the content of this step is the same as that of step S201 in the embodiment shown in fig. 2, and will not be described here again.

Step S402, a vehicle with a distance from the automatic driving vehicle being greater than a first set distance threshold is filtered.

Specifically, after determining that an autonomous vehicle enters an intersection, vehicles that are present in the environment are first detected based on the environmental data, and then vehicles that do not create a hazard therein, such as vehicles that are too far from the autonomous vehicle (beyond a first set distance threshold, such as one hundred meters), are filtered.

Step S403, filtering the vehicles located behind the autonomous vehicle identified in the environmental data based on the traveling direction of the autonomous vehicle.

Specifically, when passing through an intersection, a vehicle behind an autonomous vehicle generally follows the travel track of the autonomous vehicle, and thus it is not generally necessary to consider the collision with the autonomous vehicle.

Step S404, if the driving direction of the autonomous vehicle is straight, the vehicle identified in the environmental data and the autonomous vehicle are filtered.

Specifically, if the autonomous vehicle passes through the intersection in a straight line, the vehicles running in the same direction or in opposite directions and located on different lanes need not be considered, because the running tracks of the vehicles and the autonomous vehicle are parallel to each other at this time, and the situation of collision is not generally considered.

In step S405, if the driving direction of the autonomous vehicle is left-turning, the vehicle or right-turning vehicle that is located on the right side of the autonomous vehicle and is traveling straight in the same direction and is identified in the environmental data is filtered.

Specifically, for example, when an autonomous vehicle turns left, the right-hand straight-going vehicle and the right-hand turning vehicle do not intersect with the driving track, so that the consideration is not needed.

In step S406, if the driving direction of the autonomous vehicle is right-handed, the vehicle or left-handed vehicle located on the left side of the autonomous vehicle and identified in the environmental data is filtered.

Specifically, the straight left-turn vehicle and the track of the left-turn vehicle do not intersect with each other, and therefore, the left-turn vehicle and the track of the left-turn vehicle do not need to be considered, as in the case of left-turn of the automated driving vehicle.

Steps S404 to S406 are optional steps parallel to each other, and a person skilled in the art may select the corresponding steps to execute according to the actual situation.

And step S407, determining the vehicle with the included angle with the running direction of the automatic driving vehicle in the filtered vehicle being in the set angle range as the target vehicle to be analyzed.

Specifically, the relation between the running direction of the filtered vehicle and the running direction of the automatic driving vehicle needs to be considered, for example, the included angle between the running directions of the two vehicles is larger than a right angle (larger than 90 degrees or smaller than minus 90 degrees), which means that the two vehicles gradually deviate from each other, so that the collision condition does not need to be considered, but if the included angle between the running directions of the two sides is a right angle or smaller than a right angle (i.e. a set angle range), the collision risk may exist, so that the vehicle needs to be considered as the target vehicle for further analysis.

Step S408, based on the environmental data, status information of the target vehicle is acquired.

Specifically, after the target vehicle is determined, specific state information of the target vehicle, such as shape parameters, etc., needs to be acquired, and for the filtered vehicle, the information does not need to be acquired, so that the data processing amount is reduced, and the processing efficiency is improved.

Step S409, determining an expected meeting state of the autonomous vehicle and the target vehicle based on the positional relationship between the first travel track of the target vehicle and the second travel track of the autonomous vehicle, and the shape parameter of the set portion of the target vehicle.

Specifically, the content of the steps is the same as that of the corresponding steps in the embodiments shown in fig. 2 and fig. 3a, and the details are not repeated here.

Step S410, determining a driving strategy of the autonomous vehicle based on the expected meeting state.

Specifically, after determining the expected meeting state, the driving strategy of the autonomous vehicle may be further determined.

In some embodiments, if an obstacle having a speed less than the second speed threshold exists in the second travel track and the distance from the autonomous vehicle is less than the second set distance threshold, determining that the travel strategy of the autonomous vehicle is braked to a stop state.

Specifically, if there are pedestrians, obstacles (such as roadblocks, broken stones, etc.), small animals (the moving speed is lower than the second speed threshold, such as 5m/s, and the small animals are bumped into the second driving track without decelerating the vehicle) and the like in the range of a distance (i.e., a second set distance threshold, such as 50 meters) which is closer to the vehicle, the vehicle must be braked to a parking state until the pedestrians and the small animals leave the second driving track, or the second driving track is planned again.

As shown in fig. 4b, which is a schematic view of a scenario in which an obstacle exists on the second driving track, when an obstacle 410 exists on the driving track of the autonomous vehicle 400, the autonomous vehicle needs to be braked and stopped in time.

In some embodiments, the driving coverage corresponding to the second driving track is obtained based on the shape parameter of the autonomous vehicle and the set vehicle body extension, and when the driving coverage partially overlaps with the first driving track of the target vehicle, the driving strategy of the autonomous vehicle is determined to be braked to a stop state.

Specifically, if the head of the automatic driving vehicle extends forward by a set vehicle body extension amount (for example, 3 meters) under the condition that the track expansion circles of the automatic driving vehicle and the target vehicle are not intersected or tangent, a driving coverage area (for safe driving) corresponding to the second driving track can be obtained, and then whether the second driving track is overlapped with the first driving track or the track expansion circle of the target vehicle is judged based on the driving coverage area, so that whether a sufficient safety distance exists when the vehicle is expected to meet is judged, and the driving safety of the automatic driving vehicle is ensured to the greatest extent.

As shown in fig. 4c, which is a schematic view of a scenario where the driving coverage of the autonomous vehicle coincides with the first driving track, the driving coverage 440 obtained by extending the driving track of the autonomous vehicle 400 coincides with the first driving track corresponding track expansion circle 430 of the target vehicle 420, and the autonomous vehicle needs to be braked and stopped in time at this time.

In some embodiments, if the distance between the target vehicle and the autonomous vehicle is less than a third set distance threshold, determining the driving strategy of the autonomous vehicle is based on the set deceleration brake.

Specifically, when the distance between the target vehicle and the automatic driving vehicle is relatively short (i.e., less than the third set distance, e.g., less than 20 meters), the distance between the target vehicle and the automatic driving vehicle is relatively short regardless of the expected meeting state, and the relative safety is relatively low regardless of the adjustment, so that the automatic driving vehicle needs to be directly decelerated and braked to ensure the safety.

According to the vehicle intersection decision-making method, after the environmental data are acquired, vehicles which do not affect the running safety of the automatic driving vehicle are filtered according to different rules, so that target vehicles which need to be further analyzed are obtained, and then the running strategy is determined according to the expected meeting state of the target vehicles and the automatic driving vehicle. Therefore, the target vehicles are screened, only the specific state information of the target vehicles is acquired, the information processing amount is reduced, the processing efficiency is improved, and meanwhile, the running safety of the automatic driving vehicle is ensured.

Fig. 5 is a schematic structural diagram of a vehicle intersection decision device according to an embodiment of the present application. As shown in fig. 5, the vehicle intersection decision making apparatus 500 includes: an environment recognition module 510, an object recognition module 520, an analysis module 530, and a processing module 540. Wherein:

the environment recognition module 510 is used for responding to the acquired environment data, determining that the automatic driving vehicle enters the intersection and no indicator light signal is detected;

the target recognition module 520 is configured to determine, based on a set filtering rule, a target vehicle to be analyzed and state information of the target vehicle from the environmental data, where the state information includes a first driving track of the target vehicle and a shape parameter of a set portion;

an analysis module 530, configured to determine an expected meeting state of the autonomous vehicle and the target vehicle based on a positional relationship between the first driving track of the target vehicle and the second driving track of the autonomous vehicle, and a shape parameter of a set portion of the target vehicle;

a processing module 540 for determining a driving strategy for the autonomous vehicle based on the expected meeting status.

Optionally, the analysis module 530 is specifically configured to determine, as the set location, a target structure with a maximum width of the target vehicle based on the type of the target vehicle; taking a point on the first running track as a circle center, generating a track expansion circle corresponding to the first running track based on the width of the target structure and the set expansion width, wherein the set expansion width is determined based on the type of the target vehicle; and determining the expected meeting state based on the intersection point of the second running track and the track expansion circle.

Optionally, the analysis module 530 is specifically configured to determine an intersection point of the second travel track and the first travel track; determining a tangent point of the track expansion circle and the second running track; determining one point from the intersection point and the tangent point to the nearest point of the automatic driving vehicle as a conflict point; an expected meeting state is determined based on the target vehicle behavior state, the autonomous vehicle behavior state, and the conflict point.

Optionally, the analysis module 530 is specifically configured to determine, if the target vehicle action state includes a first speed of the target vehicle, the autopilot vehicle action state includes a second speed of the autopilot vehicle, and determine, based on the second speed, a first moment when the head of the autopilot vehicle reaches the conflict point; determining a second moment when the head of the target vehicle reaches the conflict point and a third moment when the tail of the target vehicle reaches the conflict point based on the first speed; if the difference value between the second moment and the first moment is larger than the first time threshold, determining that the expected meeting state is that the automatic driving vehicle passes through the conflict point first and cannot collide with the target vehicle; or if the difference value between the first moment and the third moment is larger than the second time threshold value, determining that the expected meeting state is that the target vehicle passes through the conflict point first and cannot collide with the automatic driving vehicle; or if the difference between the first time and the second time is smaller than the first time threshold, determining that the expected passing state is that the target vehicle collides with the automatic driving vehicle.

Optionally, the processing module 540 is specifically configured to determine that the driving strategy is to maintain the current driving state if the expected meeting state is that the autonomous vehicle will not collide with the target vehicle; if the expected meeting state is that the target vehicle collides with the automatic driving vehicle, determining the driving strategy of the automatic driving vehicle based on the first speed and the first driving track of the target vehicle.

Optionally, the processing module 540 is specifically configured to, if the first speed is higher than the set first speed threshold, adjust the running speed based on the set deceleration parameter until the target vehicle passes through the conflict point and does not collide with the autopilot vehicle; if the first speed is lower than the set first speed threshold, determining a safe intersection time based on the distance between the target vehicle and the conflict point and the first speed; the travel speed is redetermined based on the location of the autonomous vehicle and the safe intersection time.

Optionally, the target recognition module 520 is specifically configured to filter vehicles having a distance to the autonomous vehicle greater than the first set distance threshold; filtering vehicles located behind the autonomous vehicle identified in the environmental data based on the direction of travel of the autonomous vehicle; if the running direction of the automatic driving vehicle is straight, filtering vehicles which are identified in the environment data and have the same direction as the automatic driving vehicle; or if the running direction of the automatic driving vehicle is left-turning, filtering the vehicle which is identified in the environment data and is positioned on the right side of the automatic driving vehicle and is in the same direction and directly moving or turning right; or if the running direction of the automatic driving vehicle is right-turning, filtering the vehicle which is identified in the environment data and is positioned on the left side of the automatic driving vehicle and is in the same direction and is straight or turns left; determining a vehicle with an included angle between the filtered vehicle and the running direction of the automatic driving vehicle in a set angle range as a target vehicle to be analyzed; based on the environmental data, status information of the target vehicle is acquired.

Optionally, the processing module 540 further includes determining that the driving strategy of the autonomous vehicle is braking to a stopped state when there is an obstacle in the second driving track having a speed less than the second speed threshold and a distance from the autonomous vehicle is less than the second set distance threshold; obtaining a driving coverage corresponding to the second driving track based on the shape parameters of the automatic driving vehicle and the set vehicle body extension, and determining that the driving strategy of the automatic driving vehicle is braked to a stop state when the driving coverage is partially overlapped with the first driving track of the target vehicle; if the distance between the target vehicle and the automatic driving vehicle is smaller than the third set distance threshold value, determining that the driving strategy of the automatic driving vehicle is based on the set deceleration braking.

In this embodiment, the vehicle intersection decision device can ensure that the unmanned vehicle can ensure the running safety of the unmanned vehicle at the intersection without the indicator light through the combination of the modules, and ensure the running safety of the vehicle without being influenced by excessive environmental factors and the running efficiency of the vehicle passing through the intersection through screening the target vehicle and determining the running strategy according to the target vehicle.

Fig. 6 is a schematic structural diagram of a control device according to an embodiment of the present application, as shown in fig. 6, the control device 600 includes: a memory 610 and a processor 620.

Wherein the memory 610 stores a computer program executable by the at least one processor 620. The computer program is executed by the at least one processor 620 to cause the control apparatus to implement the vehicle intersection decision making method as provided in any of the embodiments above.

Wherein the memory 610 and the processor 620 may be connected by a bus 630.

The relevant descriptions and effects corresponding to the relevant description and effects corresponding to the method embodiments may be understood, and are not repeated herein.

An embodiment of the present application provides a computer readable storage medium having stored thereon a computer program that is executed by a processor to implement the vehicle intersection decision making method of any of the embodiments described above.

The computer readable storage medium may be, among other things, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

One embodiment of the present application provides a computer program product containing computer-executable instructions for implementing the vehicle intersection decision method of any of the embodiments as corresponds to fig. 2 to 4a when executed by a processor.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.

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

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

Claims

1. A vehicle intersection decision method, characterized in that the vehicle intersection decision method comprises:

Determining an expected meeting state of the automatic driving vehicle and a target vehicle based on the position relation between the first driving track of the target vehicle and the second driving track of the automatic driving vehicle and the shape parameter of the set part of the target vehicle;

a driving strategy of the autonomous vehicle is determined based on the expected meeting status.

2. The vehicle intersection decision making method according to claim 1, wherein the determining the expected meeting state of the autonomous vehicle and the target vehicle based on the positional relationship between the first travel locus of the target vehicle and the second travel locus of the autonomous vehicle, the shape parameter of the set portion of the target vehicle, comprises:

determining a target structure with the maximum width of the target vehicle as the set part based on the type of the target vehicle;

generating a track expansion circle corresponding to the first running track by taking a point on the first running track as a circle center and based on the width of the target structure and a set expansion width, wherein the set expansion width is determined based on the type of the target vehicle;

and determining the expected meeting state based on the intersection point of the second running track and the track expansion circle.

3. The vehicle intersection decision method of claim 2, wherein the determining the expected meeting state based on the intersection of the second travel trajectory and the trajectory expansion circle comprises:

determining an intersection point of the second travel track and the first travel track;

determining a tangent point of the track expansion circle and the second running track;

determining one point from the intersection point and the tangent point to the nearest point of the automatic driving vehicle as a conflict point;

the expected meeting state is determined based on a target vehicle behavior state, an autonomous vehicle behavior state, and the conflict point.

4. The vehicle intersection decision making method according to claim 3, wherein the target vehicle action state includes a first speed of a target vehicle, the autonomous vehicle action state includes a second speed of an autonomous vehicle,

the determining the expected meeting state based on the target vehicle behavior state, the autonomous vehicle behavior state, and the conflict point comprises:

determining a first moment when the head of the autonomous vehicle reaches the conflict point based on the second speed;

determining a second moment when the head of the target vehicle reaches the conflict point and a third moment when the tail of the target vehicle reaches the conflict point based on the first speed;

If the difference value between the second moment and the first moment is larger than a first time threshold value, determining that the expected meeting state is that the automatic driving vehicle passes through the conflict point first and cannot collide with the target vehicle; or alternatively, the process may be performed,

if the difference value between the first moment and the third moment is larger than a second time threshold value, determining that the expected meeting state is that the target vehicle passes through the conflict point first and cannot collide with the automatic driving vehicle; or alternatively, the process may be performed,

if the difference between the first time and the second time is smaller than the first time threshold, determining that the expected passing state is that the target vehicle collides with the automatic driving vehicle.

5. The vehicle intersection decision making method according to claim 3, wherein the determining a driving strategy of an autonomous vehicle based on the expected meeting state includes:

if the expected meeting state is that the automatic driving vehicle and the target vehicle cannot collide, determining that the driving strategy is to keep the current driving state;

if the expected meeting state is that the target vehicle collides with the automatic driving vehicle, determining the driving strategy of the automatic driving vehicle based on the first speed and the first driving track of the target vehicle.

6. The vehicle intersection decision making method according to claim 5, wherein if the meeting state is expected to be a collision of the target vehicle with the automatically driven vehicle, determining the driving strategy of the automatically driven vehicle based on the first speed and the first driving trajectory of the target vehicle includes:

If the first speed is higher than the set first speed threshold, the running speed is adjusted based on the set deceleration parameter until the target vehicle passes through the conflict point and cannot collide with the automatic driving vehicle;

if the first speed is lower than a set first speed threshold, determining a safe intersection time based on the distance between the target vehicle and the conflict point and the first speed;

the travel speed is redetermined based on the location of the autonomous vehicle and the safe intersection time.

7. The vehicle intersection decision method according to any one of claims 1 to 6, wherein the determining, based on the set filtering rule, the target vehicle and the state information of the target vehicle to be analyzed from the environmental data includes:

filtering vehicles with the distance from the automatic driving vehicle being greater than a first set distance threshold;

filtering vehicles located behind the autonomous vehicle identified in the environmental data based on the direction of travel of the autonomous vehicle;

if the running direction of the automatic driving vehicle is straight, filtering vehicles which are identified in the environment data and have the same direction as the automatic driving vehicle; or alternatively, the process may be performed,

if the running direction of the automatic driving vehicle is left-turning, filtering the vehicles which are identified in the environment data and are positioned on the right side of the automatic driving vehicle and move straight in the same direction or turn right; or alternatively, the process may be performed,

If the running direction of the automatic driving vehicle is right-turning, filtering the vehicle which is identified in the environment data and is positioned on the left side of the automatic driving vehicle and is in the same direction and is straight or turns left;

determining a vehicle with an included angle between the filtered vehicle and the running direction of the automatic driving vehicle in a set angle range as a target vehicle to be analyzed;

and acquiring state information of the target vehicle based on the environment data.

8. The vehicle intersection decision making method according to any one of claims 1 to 6, characterized in that determining a driving strategy of an autonomous vehicle based on the expected meeting state, further comprises:

determining that the driving strategy of the automatic driving vehicle is braked to a stop state when an obstacle with the speed smaller than a second speed threshold exists in the second driving track and the distance between the obstacle and the automatic driving vehicle is smaller than a second set distance threshold;

obtaining a driving coverage corresponding to the second driving track based on the shape parameters of the automatic driving vehicle and the set vehicle body extension, and determining that the driving strategy of the automatic driving vehicle is braked to a stop state when the driving coverage is partially overlapped with the first driving track of the target vehicle;

If the distance between the target vehicle and the automatic driving vehicle is smaller than the third set distance threshold value, determining that the driving strategy of the automatic driving vehicle is based on the set deceleration braking.

9. A vehicle intersection decision making apparatus, comprising:

10. A control apparatus, characterized by comprising:

at least one processor;

and a memory communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor to cause the control device to perform the vehicle intersection decision method of any one of claims 1 to 8.