A passing decision method, device, vehicle, medium and equipment

Abstract

The application discloses a kind of intersection region-of-interest-based traffic decision method, device, medium, equipment and vehicle, belong to data processing technical field.The method mainly includes: at the intersection without traffic signal, according to the right-of-way information of the lane where the ego vehicle is to obtain the region-of-interest of the ego vehicle at the intersection;According to the feature of obstacle, the obstacle in the region-of-interest is filtered, and whether there is target vehicle in the region-of-interest is judged;And, under the condition that there is target vehicle in the region-of-interest, the decision of yielding at the intersection is made, under the condition that there is no target vehicle in the region-of-interest, the decision of passing through the intersection is made.The application can make the traffic decision made by the ego vehicle at the intersection more accurate under the condition of ensuring the traffic efficiency, and ensure the safety of ego vehicle.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, medium, equipment, and vehicle for traffic decision-making based on regions of interest at intersections. Background Technology

[0002] As residents' living standards gradually improve, the number of cars owned by residents also increases with the gradual improvement of economic level. Under these circumstances, the efficient operation of urban transportation has become an important factor in the rapid development of urban economy and the improvement of people's lifestyle. The key to urban transportation lies in the traffic capacity of these road nodes, namely intersections.

[0003] To ensure vehicles can pass through intersections quickly and safely with minimal congestion and delay, traffic decisions at intersections without traffic lights are typically made by predicting the order in which vehicles need to enter the intersection to determine their priority. However, this method is not applicable to intersections with predefined traffic sequences. Summary of the Invention

[0004] To address the problem that existing technologies are not applicable to intersections with prescribed traffic sequences when making decisions at intersections without traffic lights, this application mainly provides a method, device, medium, equipment, and vehicle for traffic decision-making based on the region of interest at the intersection.

[0005] Firstly, this application provides a method for making traffic decisions based on regions of interest (ROIs) at intersections, comprising: at an intersection without traffic lights, obtaining the region of interest of the vehicle at the intersection based on the right-of-way information of the lane in which the vehicle is located; filtering obstacles in the region of interest based on obstacle characteristics, and determining whether a target vehicle exists in the region of interest; and, if a target vehicle exists in the region of interest, making a decision to yield at the intersection, and if no target vehicle exists in the region of interest, making a decision to proceed through the intersection.

[0006] Optionally, if there is no right-of-way information in the lane where the vehicle is located, determine the yield lane for the vehicle and determine the region of interest outside the intersection based on the position of the driving lane; if there is a right-of-way in the lane where the vehicle is located, determine the yield lane for the vehicle and determine the region of interest outside the intersection and the region of interest inside the intersection based on the position of the yield lane and the intersection.

[0007] Optionally, the yielding lanes are filtered according to the permitted direction of travel and the permitted vehicle types to obtain target lanes where the direction of travel is entering the intersection and the permitted vehicle type is motor vehicles; a first boundary of the region of interest is obtained by extending a predetermined width threshold outward from the position of the two outermost lane lines of the target lanes, and a second boundary of the region of interest is obtained according to the position of the stop line of the intersection and a preset length threshold; the region of interest outside the intersection is determined using the first boundary and the second boundary.

[0008] Optionally, the predicted driving trajectory of the vehicle within the intersection can be obtained, and the area with a predetermined width obtained by extending the predicted driving trajectory to both sides can be used as the region of interest within the intersection.

[0009] Optionally, Frenet coordinate transformation is performed on the obstacles to obtain the effective obstacles; based on vehicle characteristics, the effective obstacles are filtered to obtain vehicle obstacles; based on the angle formed by the vehicle and the vehicle obstacles, the vehicle obstacles are filtered to obtain the target vehicle.

[0010] Optionally, obstacles can be filtered based on the directional angle formed by the vehicle's frontal orientation and that of the obstacle to obtain obstacles within an angle threshold; and the target vehicle can be obtained by filtering obstacles within an angle threshold based on the speed angle formed by the vehicle and the obstacle within the angle threshold.

[0011] Secondly, this application provides a traffic decision-making device based on a region of interest (ROI) at an intersection, comprising: an ROI acquisition module, used to obtain the ROI of the vehicle at the intersection based on the right-of-way information of the lane in which the vehicle is located at an intersection without traffic lights; a target vehicle screening module, used to screen obstacles in the ROI based on obstacle characteristics and determine whether a target vehicle exists in the ROI; and a decision module, used to make a decision to yield at the intersection if a target vehicle exists in the ROI, and a decision to proceed at the intersection if no target vehicle exists in the ROI.

[0012] Thirdly, this application provides a vehicle configured to perform a traffic decision-making device based on the region of interest at an intersection, as described in the second aspect of this application and any embodiment thereof.

[0013] Fourthly, this application provides a computer-readable storage medium storing computer instructions that are operated to perform a traffic decision method based on the region of interest at an intersection as described in the first aspect of this application and any embodiment thereof.

[0014] Fifthly, embodiments of this application provide a computer device including a processor and a memory, the memory storing computer instructions, which, when executed by the processor, implement the traffic decision-making method based on the region of interest at an intersection as described in the first aspect of this application and any of its embodiments.

[0015] The beneficial effects of the technical solution of this application are: by determining the area of ​​interest at intersections with specified right-of-way information, the passage order of vehicles at intersections can be guaranteed, further ensuring traffic efficiency, making the passage decisions made by vehicles at intersections more accurate, and ensuring traffic safety. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of a specific implementation of a traffic decision-making method based on a region of interest at an intersection, as described in this application.

[0018] Figure 2 This is a schematic diagram of a specific implementation of a traffic decision-making method based on the region of interest at an intersection, without a right-of-way marker, according to this application.

[0019] Figure 3 This is a schematic diagram of a specific implementation of a traffic decision-making method based on a region of interest at an intersection, with a subsequent right-of-way indicator, according to this application.

[0020] Figure 4 This is a schematic diagram of a specific implementation of a traffic decision-making device based on a region of interest at an intersection, as described in this application.

[0021] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0022] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0023] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0024] To ensure smooth traffic flow at intersections, vehicles entering the intersection are typically assigned priority based on their arrival time, with earlier arrivals receiving higher priority. Traffic trajectories are then planned accordingly, and lower-priority vehicles must avoid the trajectories of higher-priority vehicles. However, this method results in lower-quality decision-making at intersections because lower-priority vehicles are limited to avoiding the predetermined trajectories of higher-priority vehicles, leading to poor flexibility and comprehensiveness. Furthermore, it is unsuitable for intersections with fixed traffic sequences.

[0025] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other to form new embodiments. The same or similar ideas or processes described in one embodiment may not be repeated in other embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0026] Figure 1 This paper illustrates one implementation of a traffic decision-making method based on a region of interest at an intersection, as described in this application.

[0027] Figure 1 The traffic decision-making method shown includes: step S101, at an intersection without traffic lights, obtaining the region of interest of the vehicle at the intersection based on the right-of-way information of the lane in which the vehicle is located;

[0028] Step S102: Filter obstacles within the region of interest based on obstacle characteristics, and determine whether a target vehicle exists within the region of interest; and,

[0029] Step S103: If the target vehicle exists in the area of ​​interest, make a decision to yield at the intersection; if the target vehicle does not exist in the area of ​​interest, make a decision to proceed at the intersection.

[0030] This specific implementation method, while ensuring traffic efficiency, makes the vehicle's traffic decisions at the intersection more accurate, thus ensuring the vehicle's safety and is applicable to intersections with prescribed traffic sequences.

[0031] Specifically, at intersections without traffic lights but with designated right-of-way, vehicles must decide whether to proceed based on the right-of-way of their lane. When a vehicle has the right-of-way, it can proceed without considering the traffic conditions of other vehicles at the intersection. When a vehicle does not have the right-of-way or has a rear right-of-way, it must decide whether to proceed according to the prescribed driving order. For example, if a vehicle does not have the right-of-way, it must yield to vehicles outside the intersection on its right; if a vehicle has a rear right-of-way, it must yield to vehicles outside the intersection on both its left and right sides, and also to vehicles already inside the intersection.

[0032] Before yielding to vehicles in a designated area, you need to determine the area of ​​interest that you need to yield to based on the right-of-way of your lane. Then, within the area of ​​interest, you need to filter for target vehicles according to certain requirements. If there is a target vehicle in the area of ​​interest, you will make a yielding decision. If there is no target vehicle in the area of ​​interest, you will make a passing decision.

[0033] exist Figure 1 The illustrated implementation of the intersection region of interest (ROI) decision-making method includes step S101: at an intersection without traffic lights, the ROI of the vehicle at the intersection is obtained based on the right-of-way information of the lane in which the vehicle is located. This step reduces the number of obstacles that need to be screened by delineating the region, thereby reducing the computational load when making intersection decisions. It is also applicable to ROI decisions at intersections with limited traffic order.

[0034] Specifically, at intersections without traffic lights but with defined right-of-way information, the prescribed driving order is determined based on the right-of-way information of the lane in which the vehicle is located, and the area information that the vehicle needs to yield to is obtained. Within this yielding area, calculations are performed to determine the region of interest (ROI) for the vehicle. The ROI refers to the area with higher traffic priority than the vehicle itself.

[0035] For example, such as Figure 2 When the lane in which the vehicle is located has no right-of-way information, the vehicle needs to yield to vehicles in the area outside the intersection to its right. After determining the area outside the intersection where the vehicle needs to yield, the region of interest for the vehicle is filtered based on factors such as the lane's permitted direction of travel. Figure 2 The shaded area where car A is located is the region of interest for car A.

[0036] In one specific embodiment of this application, step S101 includes: determining the yield lane of the vehicle when there is no right-of-way information in the lane where the vehicle is located, and determining the region of interest outside the intersection based on the position of the driving lane; determining the yield lane of the vehicle when there is a right-of-way in the lane where the vehicle is located, and determining the region of interest outside the intersection and the region of interest inside the intersection based on the position of the yield lane and the intersection. This specific embodiment can accurately and efficiently calculate the region of interest, reduce the number of obstacles that need to be considered, and lay the foundation for reducing the amount of computation in the decision-making process.

[0037] Specifically, when the right-of-way information for the lane where the vehicle is located indicates no right-of-way, it needs to yield to vehicles outside the intersection on the right side of its direction of travel. When the right-of-way information for the lane where the vehicle is located indicates a rear right-of-way, it needs to yield to vehicles outside the intersection on the right side of its direction of travel, vehicles outside the intersection on the left side of its direction of travel, and vehicles within the intersection. However, these areas also include non-motorized vehicles, pedestrians, and vehicles exiting the intersection. Filtering these data during data selection would result in a large data volume and require significant computational power. Therefore, obtaining all lanes within the yielding area and the lane information for each lane, and filtering the yielding lanes based on the types of vehicles allowed to pass through the lane and the permitted directions of travel, reduces the computational load in the decision-making process while ensuring decision accuracy.

[0038] In one specific embodiment of this application, step S101 includes: filtering the yielding lanes according to their permitted direction of travel and permitted vehicle types to obtain target lanes where the direction of travel is entering the intersection and the permitted vehicle type is motor vehicles; extending a predetermined width threshold outward from the positions of the two outermost lane lines of the target lanes to obtain a first boundary of the region of interest; and obtaining a second boundary of the region of interest based on the position of the stop line at the intersection and a preset length threshold; and using the first and second boundaries to determine the region of interest outside the intersection. This specific embodiment can accurately filter and obtain the region of interest outside the intersection, reducing the amount of computation and ensuring the smoothness of traffic at the intersection.

[0039] Specifically, based on the permitted driving direction and permitted vehicle types of the lanes, target lanes are selected where the driving direction is towards entering the intersection and the permitted vehicle type is motor vehicles. The width of the region of interest (ROI) outside the intersection is obtained by extending outwards from the positions of the two outermost lane lines of the target lanes by a predetermined width threshold. The ROI outside the intersection is then defined based on the position of the stop line in the yield zone, a preset length threshold for the ROI outside the intersection, and the width of the ROI outside the intersection. When the yield zone is outside the intersection, all lanes within the yield zone and lane information for each lane are acquired. Lanes where the permitted vehicle type is non-motorized vehicles and pedestrians are excluded, as are lanes where the permitted driving direction is towards U-turns and exiting the intersection. The two outermost lane lines of the remaining lanes where the driving direction is towards entering the intersection and the permitted vehicle type are motor vehicles are used as the basis for extending the width of the ROI. The width of the ROI outside the intersection is obtained by extending outwards from the two outermost lane lines by a predetermined width threshold. Starting from the position of the stop line at the intersection of the yield zone, the region of interest of the vehicle outside the intersection is defined according to the preset length threshold and width of the region of interest outside the intersection.

[0040] For example, such as Figure 2 When there is no right-of-way information in the lane where vehicle A is located, the shaded area where vehicle A is located is designated as the region of interest outside the intersection. For example... Figure 3 When there is right-of-way information in the lane where the vehicle is located, the shaded areas where vehicle A and vehicle C are located are designated as regions of interest outside the intersection.

[0041] In one specific embodiment of this application, step S101 includes acquiring the predicted driving trajectory of the vehicle within the intersection, and defining the area extending to both sides of the predicted driving trajectory to obtain a predetermined width as the region of interest within the intersection. This specific embodiment can accurately filter out the region of interest within the intersection, reduce the amount of computation, and ensure the smoothness of traffic flow at the intersection.

[0042] Specifically, based on the predicted driving direction of vehicles exiting the lane or vehicles currently traveling within the intersection, the vehicle's current position is used as the starting point of the predicted driving trajectory. Connecting the starting point of the predicted driving trajectory to the intersection stop line of the lane the vehicle needs to enter yields the predicted driving trajectory of the vehicle in the predicted driving direction. Based on the virtual predicted trajectory and a predetermined expansion threshold, the region of interest (ROI) of the vehicle within the intersection is obtained.

[0043] For example, such as Figure 3 When the yield zone is within the intersection, the predicted driving trajectory of the vehicle is trajectory a. Extending the predicted driving trajectory a to both sides by a predetermined width yields... Figure 3 The area enclosed by the dashed line is designated as the region of interest within the intersection.

[0044] exist Figure 1 In the specific implementation shown, the traffic decision-making method based on the region of interest at an intersection further includes step S102, which involves filtering obstacles within the region of interest based on obstacle characteristics and determining whether a target vehicle exists within the region of interest. This step ensures the accuracy of the decision and reduces the computational load during the decision-making process.

[0045] In one specific embodiment of this application, step S102 includes performing Frenet coordinate transformation on the obstacles to obtain valid obstacles; filtering the valid obstacles based on vehicle characteristics to obtain vehicle obstacles; and filtering the vehicle obstacles based on the angle formed by the vehicle and the vehicle obstacles to obtain the target vehicle. This specific implementation can accurately filter and obtain the target vehicle, ensuring the accuracy of the decision result.

[0046] Specifically, within the region of interest, valid obstacle information is traversed, and targets that can be transformed into the Frenet coordinate system are filtered out to eliminate virtual obstacles, resulting in valid obstacles. Virtual obstacles include traffic cones and false obstacles fitted from predicted trajectories. Then, these valid obstacles are traversed, and pedestrians and non-motorized vehicles are removed based on obstacle characteristics to obtain vehicle obstacles. The filtered vehicle obstacles are then subjected to angle filtering to obtain the target vehicles. Angle filtering includes filtering the angle between the vehicle's frontal orientation and the driver's frontal orientation, and filtering the velocity angle between the vehicle's speed direction and the driver's speed direction.

[0047] In one specific embodiment of this application, step S102 includes: filtering vehicle obstacles based on the directional angle formed by the vehicle's frontal orientation and that of the obstacle to obtain obstacles within an angle threshold; and filtering obstacles within the angle threshold to obtain a target vehicle based on the speed angle formed by the vehicle and the obstacle within the angle threshold. This specific implementation ensures that the filtered obstacles meet the requirements, further guaranteeing the accuracy and correctness of the decision on whether to yield based on the target vehicle within the region of interest.

[0048] For example, when the region of interest is outside the intersection to the right of the vehicle, the system iterates through the obstacles within that region, filtering for obstacles whose facing angle is between 0 and 90° and the vehicle's facing angle. This filters out vehicles making U-turns within the intersection or those entering the intersection, thus obtaining obstacles within an angle threshold. Then, the system iterates through the obstacles within the angle threshold within the region of interest, filtering for obstacles whose speed direction is between 0 and 90° and the vehicle's angle, thus filtering out stationary vehicles to obtain the target vehicle.

[0049] When the region of interest (ROI) is outside the intersection to the right of the vehicle, outside the intersection to the left of the vehicle, and inside the intersection, the obstacles within the ROI of the left-front intersection are traversed, and obstacles with the vehicle's heading angle between -90° and 0° are filtered out to obtain obstacles within the angle threshold. The same process is repeated within the ROI of the left-front intersection, filtering out obstacles with the vehicle's speed direction angle between -90° and 0° to obtain the target vehicle. The same process is repeated within the ROI of the right-front intersection, filtering out obstacles with the vehicle's heading angle between 0° and 90° to obtain obstacles within the angle threshold. Finally, the ROI of the intersection itself is traversed, filtering out obstacles with the vehicle's heading angle between -45° and -180° and between 45° and 180° to obtain obstacles within the angle threshold. Iterate through obstacles within the angle threshold of the region of interest in the intersection, and filter out obstacles whose angle between the vehicle's speed direction and the vehicle's own direction is in the range of -45° to -180° and 45° to 180° to obtain the target vehicle. The angle mentioned above is a vector angle, and the angle is positive when rotating counterclockwise and negative when rotating clockwise.

[0050] exist Figure 1 In the specific embodiment shown, the traffic decision-making method based on the region of interest at an intersection further includes step S103: if a target vehicle exists within the region of interest, a yield decision is made at the intersection; if no target vehicle exists within the region of interest, a passage decision is made at the intersection. This specific embodiment, while ensuring traffic efficiency, makes the passage decisions made by the vehicle at the intersection more accurate, ensuring the vehicle's safety, and is applicable to intersections with prescribed traffic sequences.

[0051] Furthermore, when the vehicle's lane has no right-of-way information or has a subsequent right-of-way, the region of interest (ROI) of the vehicle at the intersection is calculated, and the vehicle's decision at the intersection is made based on whether a target vehicle exists within the ROI. When the vehicle's lane has a right-of-way, the vehicle's decision to proceed at the current intersection is determined to be to proceed.

[0052] Figure 4 This paper illustrates a specific implementation of a traffic decision-making device based on a region of interest at an intersection, as described in this application.

[0053] exist Figure 4 In the specific implementation shown, the traffic decision-making device based on the region of interest at the intersection mainly includes: a region of interest acquisition module 401, which is used to obtain the region of interest of the vehicle at the intersection based on the right-of-way information of the lane in which the vehicle is located at an intersection without traffic lights;

[0054] The target vehicle filtering module 402 is used to filter obstacles within the region of interest based on obstacle characteristics and determine whether a target vehicle exists within the region of interest; and,

[0055] The decision module 403 is used to make a yield decision at the intersection when a target vehicle is present in the area of ​​interest, and to make a pass decision at the intersection when no target vehicle is present in the area of ​​interest.

[0056] In one specific embodiment of this application, the functional modules of the traffic decision-making device based on the region of interest at an intersection can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0057] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0058] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0059] The traffic decision-making device based on the region of interest at an intersection provided in this application can be used to execute the traffic decision-making method based on the region of interest at an intersection described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0060] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that are operated to perform the traffic decision-making method based on the region of interest at an intersection as described in the above embodiments.

[0061] In another specific embodiment of this application, a computer device is provided, wherein the computer device includes the traffic decision-making method based on the region of interest at an intersection described in any embodiment. Optionally, the device is used to implement the appendix to this application specification. Figure 1 The traffic decision-making method based on the region of interest at the intersection is described in the embodiments.

[0062] In another specific embodiment of this application, a vehicle is provided, wherein the vehicle includes the traffic decision-making method based on the region of interest at an intersection as described in any embodiment. Optionally, the vehicle includes a processor and a memory, coupled together, and the vehicle is used to implement the appendix to this specification. Figure 1 The traffic decision-making method based on the region of interest at the intersection is described in the embodiments.

[0063] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0064] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0065] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A traffic decision-making method based on regions of interest at intersections, characterized in that, include: At an intersection without traffic lights, the region of interest of the vehicle at the intersection is obtained based on the right-of-way information of the lane in which the vehicle is located; The obstacles in the region of interest are filtered based on their characteristics, and it is determined whether a target vehicle exists in the region of interest. as well as, If the target vehicle is present in the area of ​​interest, a decision is made to yield at the intersection; if the target vehicle is not present in the area of ​​interest, a decision is made to proceed at the intersection. The step of obtaining the region of interest of the vehicle at the intersection based on the priority information of the lane in which the vehicle is located includes: If there is no right-of-way information in the lane where the vehicle is located, determine the yield lane of the vehicle and determine the area of ​​interest outside the intersection based on the position of the driving lane; Given that the lane in which the vehicle is located has a right-of-way, the yield lane of the vehicle is determined, and based on the position of the yield lane and the intersection, a region of interest outside the intersection and a region of interest inside the intersection are determined; wherein, the process of determining the region of interest outside the intersection includes: The yield lanes are filtered according to the permitted direction of travel and the permitted vehicle types to obtain the target lanes where the direction of travel is entering the intersection and the permitted vehicle type is motor vehicles. The first boundary of the region of interest is obtained by extending a predetermined width threshold outward from the positions of the two outermost lane lines of the target lane, and the second boundary of the region of interest is obtained based on the position of the stop line of the intersection and a preset length threshold. The region of interest outside the intersection is determined using the first boundary and the second boundary.

2. The traffic decision-making method based on the region of interest at an intersection according to claim 1, characterized in that, The process of determining the region of interest within the intersection includes: The predicted driving trajectory of the vehicle within the intersection is obtained, and the area with a predetermined width extended to both sides of the predicted driving trajectory is taken as the region of interest within the intersection.

3. The traffic decision-making method based on the region of interest at an intersection according to claim 1, characterized in that, The step of filtering obstacles within the region of interest based on obstacle characteristics and determining whether a target vehicle exists within the region of interest includes: Perform Frenet coordinate transformation on the obstacles to obtain the valid obstacles among the obstacles; Based on vehicle characteristics, the effective obstacles are screened to obtain vehicle obstacles; Based on the angle formed by the vehicle and the vehicle obstacle, the vehicle obstacle is screened to obtain the target vehicle.

4. The traffic decision-making method based on the region of interest at an intersection according to claim 3, characterized in that, The step of filtering vehicle obstacles based on the angle formed by the vehicle and the vehicle obstacle to obtain the target vehicle includes: Based on the directional angle formed by the frontal orientation of the vehicle and the vehicle obstacle, the vehicle obstacle is screened to obtain obstacles within the angle threshold. The target vehicle is obtained by filtering obstacles within the angle threshold based on the speed angle between the vehicle and the obstacles within the angle threshold.

5. A traffic decision-making device based on a region of interest at an intersection, characterized in that, include: The region of interest acquisition module is used to obtain the region of interest of the vehicle at the intersection without traffic lights, based on the right-of-way information of the lane in which the vehicle is located. The target vehicle filtering module is used to filter obstacles in the region of interest based on obstacle characteristics and determine whether a target vehicle exists in the region of interest. as well as, The decision module is used to make a decision to yield at the intersection when the target vehicle is present in the area of ​​interest, and to make a decision to proceed at the intersection when the target vehicle is not present in the area of ​​interest. The step of obtaining the region of interest of the vehicle at the intersection based on the priority information of the lane in which the vehicle is located includes: If there is no right-of-way information in the lane where the vehicle is located, determine the yield lane of the vehicle and determine the area of ​​interest outside the intersection based on the position of the driving lane; Given that the lane in which the vehicle is located has a right-of-way, the yield lane of the vehicle is determined, and based on the position of the yield lane and the intersection, a region of interest outside the intersection and a region of interest inside the intersection are determined; wherein, the process of determining the region of interest outside the intersection includes: The yield lanes are filtered according to the permitted direction of travel and the permitted vehicle types to obtain the target lanes where the direction of travel is entering the intersection and the permitted vehicle type is motor vehicles. The first boundary of the region of interest is obtained by extending a predetermined width threshold outward from the positions of the two outermost lane lines of the target lane, and the second boundary of the region of interest is obtained based on the position of the stop line of the intersection and a preset length threshold. The region of interest outside the intersection is determined using the first boundary and the second boundary.

6. A vehicle, characterized in that, The vehicle includes the traffic decision-making device based on the region of interest at the intersection as described in claim 5.

7. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the traffic decision-making method based on the region of interest at the intersection as described in any one of claims 1-4.

8. A computer device comprising a processor and a memory, the memory storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the traffic decision-making method based on the region of interest at an intersection as described in any one of claims 1-4.

Images