An intersection passing decision method, device, medium and vehicle

Abstract

The application discloses a kind of intersection traffic decision method, device, medium and vehicle, belong to data processing technical field.The method mainly includes: under the condition that current vehicle cannot obtain intersection signal light state, determine reference vehicle on the same type lane as the current lane of current vehicle;The position information and speed information of reference vehicle are obtained, and whether reference vehicle intends to pass intersection stop line is judged according to the position information, speed information of reference vehicle, the position information of intersection stop line.This application can make the decision of whether the automatic driving vehicle passes under the condition that intersection traffic signal cannot be obtained, according to the driving state of surrounding reference vehicle, make the decision result safer and more accurate.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and in particular to a method, device, medium and vehicle for making traffic decisions at intersections. Background Technology

[0002] In actual driving, autonomous vehicles, intelligent driving vehicles, or assisted driving vehicles may encounter situations where their sensing devices are obstructed, or blocked by large vehicles ahead, preventing them from timely obtaining the status of traffic lights at intersections to make informed decisions. Current technologies address this issue by instructing the autonomous vehicle to stop regardless of its actual driving state, only re-establishing control after the vehicle can re-obtain the traffic light status. This method of decision-making at intersections where traffic light status is unavailable can easily cause traffic congestion, reduce driving efficiency, and in severe cases, potentially lead to traffic accidents. Summary of the Invention

[0003] To address the problem that existing technologies cannot make reasonable and reliable intersection traffic decisions when the status of intersection traffic lights cannot be obtained, this application mainly provides an intersection traffic decision-making method, device, medium, and vehicle.

[0004] Firstly, a method for making intersection traffic decisions is provided, comprising: determining a reference vehicle in a lane of the same type as the current vehicle's current driving lane when the current vehicle cannot obtain the status of the intersection traffic lights; wherein the same type of lane includes lanes with the same direction of travel and the same lane restriction requirements; obtaining the position information and speed information of the reference vehicle, and determining whether the reference vehicle intends to cross the intersection stop line based on the position information, speed information, and position information of the intersection stop line; wherein, if it is determined that the reference vehicle intends to cross the intersection stop line, the current vehicle's intersection traffic decision is determined to be a traffic decision; if it is determined that the reference vehicle cannot cross the intersection stop line, the current vehicle's intersection traffic decision is determined to be a stop decision.

[0005] Optionally, the braking distance between the reference vehicle and the intersection stop line is calculated based on the position information of the reference vehicle and the position information of the intersection stop line; the estimated braking acceleration information of the reference vehicle is calculated using the speed information and braking distance of the reference vehicle; the estimated braking acceleration information of the reference vehicle is compared with a preset acceleration threshold; if the estimated braking acceleration information is not less than the preset acceleration threshold, the reference vehicle is determined to make a braking decision; if the estimated braking acceleration information is less than the preset acceleration threshold, the reference vehicle is determined to make a passage decision.

[0006] Optionally, a vehicle located behind the current vehicle relative to the lane travel direction can be identified as a reference vehicle.

[0007] Optionally, vehicles in lanes adjacent to the current vehicle's lane can be designated as reference vehicles.

[0008] Optionally, multiple reference vehicles are identified in the same lane as the current vehicle's current driving lane type. The intersection passage intention of each reference vehicle is determined based on the motion state information of each reference vehicle, resulting in multiple intersection passage intentions of multiple reference vehicles. The intersection passage strategy is then determined based on the multiple intersection passage intentions.

[0009] Optionally, the number of intentions to pass through the current intersection and the number of intentions not to pass through the current intersection can be counted separately among multiple intersections, and the passage decision for the current intersection can be determined based on the number of intentions to pass through the intersection with the larger number.

[0010] Secondly, an intersection traffic decision-making device is provided, comprising: a reference vehicle acquisition module, used to determine a reference vehicle in a lane of the same type as the current vehicle's current driving lane when the current vehicle cannot obtain the intersection traffic light status, wherein the same type of lane includes lanes with the same lane travel direction and the same lane restriction requirements; and a decision module, used to acquire the position information and speed information of the reference vehicle, and determine whether the reference vehicle intends to cross the intersection stop line based on the position information, speed information, and position information of the intersection stop line, wherein if it is determined that the reference vehicle intends to cross the intersection stop line, the current vehicle's intersection traffic decision is determined to be a passage decision; if it is determined that the reference vehicle cannot cross the intersection stop line, the current vehicle's intersection traffic decision is determined to be a stop decision.

[0011] Thirdly, a computer-readable storage medium is provided that stores computer instructions that are operated to execute the intersection traffic decision method in Scheme 1.

[0012] Fourthly, a vehicle is provided that is configured to execute the intersection traffic decision-making method in Scheme 1.

[0013] The beneficial effects of the technical solution of this application are as follows: This application designs an intersection traffic decision-making method, device, medium, and vehicle. This method can make intersection traffic decisions for autonomous vehicles based on the driving status of surrounding vehicles when the status of traffic lights at the intersection cannot be obtained. Since this intersection traffic decision is made with reference to the intersection passage intentions of vehicles in the same type of lane as the autonomous vehicle, it is more reasonable and reliable. Using the intersection traffic decision-making method of this application can effectively avoid traffic congestion caused by autonomous vehicles directly making a stop decision at the intersection due to the inability to obtain the traffic light status, thus ensuring traffic efficiency. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description exemplarily illustrate some embodiments of this application.

[0015] Figure 1 This is a schematic diagram of a specific implementation of an intersection traffic decision-making method according to this application; Figure 2 This is a schematic diagram of a specific embodiment of an intersection traffic decision device according to this application.

[0016] 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

[0017] 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.

[0018] 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.

[0019] 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.

[0020] Figure 1 This paper illustrates one embodiment of an intersection traffic decision-making method according to this application.

[0021] Figure 1The intersection traffic decision-making method includes step S101, where, when the current vehicle cannot obtain the intersection traffic light status, a reference vehicle is determined in a lane of the same type as the current vehicle's current driving lane. Lanes of the same type include lanes with the same travel direction and lane restrictions, such as lane turning requirements (e.g., left-turn lane, straight lane, right-turn lane, right-turn plus straight lane). For example, when the vehicle is traveling in a straight lane from east to west, a reference vehicle can be selected from other straight lanes also traveling from east to west. This reference vehicle can be located in the same straight lane as the vehicle, for example, in front of or behind the vehicle; or it can be located in a different straight lane, including a straight lane adjacent to or not adjacent to the vehicle's lane. Lanes include lanes with the same travel direction and lane restrictions, such as lane turning requirements (e.g., left-turn lane, straight lane, right-turn lane, right-turn plus straight lane). For example, when a vehicle is traveling in a straight lane from east to west, a reference vehicle can be selected from other straight lanes also traveling from east to west. This reference vehicle can be located in the same straight lane as the vehicle, such as in front of or behind it; or it can be located in a different straight lane, including either an adjacent lane or a non-adjacent lane. Since vehicles in the same type of lane generally make the same intersection passing decisions, selecting a vehicle in the same type of lane as the vehicle as a reference vehicle to determine the intersection passing strategy can yield reasonable and reliable passing decisions.

[0022] Step S102 involves acquiring the location and speed information of a reference vehicle, and determining whether the reference vehicle intends to cross the intersection stop line based on the location, speed, and stop line position information. If the reference vehicle intends to cross the stop line, the current vehicle's intersection passage decision is determined to be a passage decision; otherwise, if the reference vehicle cannot cross the stop line, the current vehicle's intersection passage decision is determined to be a stop decision. This implementation allows for intersection passage decisions by the autonomous vehicle based on the driving status of surrounding vehicles, even when the traffic light status is unavailable. Since this intersection passage decision is made by referencing the intersection passage intentions of vehicles in the same lane as the autonomous vehicle, it is more reasonable and reliable. Using the intersection passage decision method of this application effectively avoids traffic congestion caused by the autonomous vehicle directly making a stop decision due to the inability to obtain the traffic light status, ensuring traffic efficiency.

[0023] In one embodiment, when an autonomous vehicle approaches an intersection and cannot obtain the status of the traffic lights, it uses the autonomous vehicle's perception system or network equipment or other feasible methods to obtain obstacles around the vehicle, and filters out vehicle obstacles from the obstacles around the autonomous vehicle that can obtain its motion information. The direction of travel of the vehicle obstacle must be the same as the direction of travel of the autonomous vehicle, the distance between the vehicle obstacle and the stop line of the intersection is less than or equal to the distance between the autonomous vehicle and the stop line of the intersection, and the lane of the vehicle obstacle is on the left and right adjacent sides of the lane in which the autonomous vehicle is traveling.

[0024] In this specific embodiment, since vehicles in the same type of lane should generally make the same intersection passage decision, a vehicle in the same lane as the current vehicle and located after the current vehicle is selected as a reference vehicle. By judging the intersection passage intention of the reference vehicle, the vehicle's passage strategy can be determined, thus obtaining a reasonable and reliable intersection passage decision.

[0025] In one embodiment, the passage decisions of one or more obstacle vehicles that meet certain conditions at the intersection are analyzed. When the statistical result of the passage decisions of one or more obstacle vehicles at the intersection is to pass through the intersection, the autonomous vehicle's decision is also to pass through the intersection. When the statistical result of the passage decisions of one or more obstacle vehicles at the intersection is to stop at the intersection, the autonomous vehicle's decision is also to stop.

[0026] exist Figure 1 In the illustrated implementation, the traffic decision-making method mainly includes step S101: when the current vehicle cannot obtain the traffic light status at the intersection, a reference vehicle is determined in a lane of the same type as the current vehicle's current lane. Lanes of the same type include those with the same travel direction and lane restriction requirements. This step forms the basis for the vehicle's decision-making based on the driving status of surrounding vehicles. Furthermore, by selecting vehicles that meet the criteria, the resulting decision is more consistent with the actual application scenario, making the decision more accurate and reliable.

[0027] In one implementation instance, the surrounding obstacles obtained by the vehicle are filtered to identify reference vehicles that are located on the road, are of vehicle type, and are located behind or at the same level as the vehicle and in a lane adjacent to the lane the vehicle is currently traveling in. In other words, vehicles in the same lane as the vehicle's current lane and not located before the vehicle's current position are selected as reference vehicles.

[0028] Furthermore, vehicles with speeds closer to the autonomous vehicle can be selected as reference vehicles, thereby reducing the computational load of the decision-making process while ensuring the accuracy of the autonomous vehicle's decisions.

[0029] Furthermore, multiple reference vehicles that meet the criteria are selected to ensure the accuracy of the decision-making results and avoid erroneous decision-making errors.

[0030] In one specific embodiment of this application, step S102 includes determining a vehicle located behind the current vehicle relative to the lane travel direction as a reference vehicle. When a large vehicle in front of the vehicle obstructs the view of the traffic light status at the intersection, vehicles located behind the vehicle are less likely to be obstructed because they are farther away from the large vehicle. Therefore, vehicles meeting the criteria behind the vehicle can be used as reference vehicles to make intersection passage decisions.

[0031] In a specific embodiment of this application, surrounding obstacles are acquired through the vehicle's own sensing devices. These obstacles are then filtered by geographical location, category, lane position, and vehicle orientation angle to identify vehicles located behind the current vehicle relative to the lane travel direction and traveling in the same type of lane as the current vehicle's current lane as reference vehicles. This specific embodiment reduces the computational load in the decision-making process by filtering surrounding obstacles.

[0032] It should be noted that the order of filtering by geographic location, category, lane location, and vehicle orientation angle can be adjusted or reduced according to the actual situation, and this application does not impose specific restrictions.

[0033] The system filters obstacles based on their geographical location to identify those located within the lane. It also filters out obstacles not in the lane, further reducing computational load in the decision-making process. Specifically, it filters the surrounding obstacles acquired by the autonomous vehicle to obtain those suitable for Frenet coordinate system transformation and acquires their motion and location information.

[0034] Obstacles in the lane are categorized based on vehicle characteristics to identify vehicle-type obstacles. This ability to filter out obstacles that are classified as vehicle-type leads to more accurate and correct decision-making. Specifically, obstacles of vehicle type are identified by filtering from surrounding obstacles or lane obstacles based on their outline information. Alternatively, the visual perception system of the autonomous vehicle acquires outline information of obstacles around the vehicle, and based on preset outline information for different vehicle quantities, obstacles of vehicle type are compared and filtered from these surrounding obstacles or lane obstacles.

[0035] The system filters vehicle obstacles based on their lane location and position within the lane, identifying obstacles in lanes adjacent to the current vehicle's lane but not preceding it. This specific embodiment ensures that the decision-making results regarding the filtered obstacles are more similar to the autonomous vehicle's scenario, making the vehicle's decisions more accurate and reliable. First, based on the autonomous vehicle's location information, the location information of surrounding obstacles, and the lane location information, obstacles adjacent to the autonomous vehicle's driving lane are filtered from the surrounding obstacles or vehicle obstacles obtained by the autonomous vehicle. That is, the autonomous vehicle's driving lane is determined based on the autonomous vehicle's location information and the lane location information. The lanes of surrounding obstacles are determined based on the location information of surrounding obstacles and the lane location information. Finally, based on the autonomous vehicle's driving lane, the lanes of surrounding obstacles, and the positional relationships between lanes, obstacles adjacent to the vehicle's driving lane are filtered. Then, based on the location information and lane information of the autonomous vehicle, the location information of obstacles adjacent to the vehicle's driving lane, and the location information between the obstacle and the stop line at the intersection, obstacles are selected from those adjacent to the autonomous vehicle's driving lane or from obstacles within the vehicle itself, ensuring that the distance between these obstacles and the stop line is no greater than the distance between the vehicle and the stop line. That is, after selecting obstacles on both sides of the lane the autonomous vehicle is traveling in, the location information of these obstacles is obtained. Based on the obtained obstacle location information and the stop line location information, the distance between the obtained obstacle and the stop line is calculated; similarly, based on the autonomous vehicle's location information and the stop line location information, the distance between the autonomous vehicle and the stop line is calculated. The distance between the obstacle and the stop line is compared to the distance between the autonomous vehicle and the stop line. When the distance between the obstacle and the stop line is smaller than or equal to the distance between the autonomous vehicle and the stop line, the obstacle is the desired obstacle.

[0036] The orientation angle between the current vehicle and the obstacle is calculated. If the orientation angle is less than a preset angle threshold, the corresponding obstacle is identified as a vehicle traveling in the same direction, and this vehicle is used as a reference vehicle. This specific embodiment can filter out obstacles traveling in the same direction as the vehicle, thereby ensuring the correctness of the vehicle's decisions. Specifically, based on the orientation of the obstacle obtained by the autonomous vehicle and the orientation of the autonomous vehicle, the orientation angle between the autonomous vehicle and the obstacle is calculated. When this orientation angle is less than an angle threshold, the orientation of the obstacle is the same as the orientation of the autonomous vehicle. If the orientation angle is less than a preset angle threshold, the corresponding obstacle is identified as a vehicle traveling in the same direction, and this vehicle is used as a reference vehicle. Preferably, the angle threshold is 90 degrees. That is, the above method can obtain vehicles traveling in the same direction as the vehicle.

[0037] Furthermore, the obstacle screening process in this application includes, but is not limited to, screening based on geographical location, category, lane position, and vehicle orientation angle. For example, it can screen out reference vehicles that are more similar to the autonomous vehicle in terms of model, location, and motion state.

[0038] In one specific embodiment of this application, vehicles in lanes adjacent to the current vehicle's lane are identified as reference vehicles. Since vehicles in adjacent lanes are closer to the current vehicle, their information is easier to obtain, and vehicles in adjacent lanes of the same type typically have more consistent intersection passing strategies, thus providing greater reference value and leading to more reasonable and reliable intersection passing decisions.

[0039] exist Figure 1 In the illustrated embodiment, the traffic decision-making method mainly includes step S102: acquiring the location and speed information of a reference vehicle, and determining whether the reference vehicle intends to cross the intersection stop line based on the location, speed, and stop line information. If the reference vehicle intends to cross the stop line, the current vehicle's traffic decision is determined to be a passage decision; otherwise, if the reference vehicle cannot cross the stop line, the current vehicle's traffic decision is determined to be a stop decision. This step enables the autonomous vehicle to make a traffic decision based on the surrounding vehicles' driving status even when the traffic light status is unavailable. This reduces traffic congestion and improves traffic efficiency while ensuring the safety of the autonomous vehicle.

[0040] In one specific embodiment of this application, the location and speed information of a reference vehicle are obtained, and based on the location, speed, and stop line location information of the reference vehicle, it is determined whether the reference vehicle can cross the stop line. If the reference vehicle can cross the stop line, a passage decision is issued to the current vehicle; if the reference vehicle cannot cross the stop line, a stop decision is issued to the current vehicle. This step ensures the accuracy of the decision, reduces traffic congestion, and improves traffic efficiency.

[0041] Specifically, if the calculation shows that the reference vehicle can stop within the stop line with a comfortable braking acceleration, then the decision made by the reference vehicle at the intersection is determined to be a braking decision, and the autonomous vehicle is given the same braking decision as the reference vehicle. If the calculation shows that the reference vehicle cannot stop within the stop line with a comfortable braking acceleration, then the decision made by the reference vehicle at the intersection is determined to be a proceeding decision, and the autonomous vehicle is given the same proceeding decision as the reference vehicle. Whether the reference vehicle can stop within the stop line with a comfortable braking acceleration is determined using a preset acceleration threshold.

[0042] In one specific embodiment of this application, step S102 includes: calculating the braking distance between the reference vehicle and the intersection stop line based on the position information of the reference vehicle and the position information of the intersection stop line; calculating the estimated braking acceleration information of the reference vehicle using the speed information of the reference vehicle and the braking distance; comparing the estimated braking acceleration information of the reference vehicle with a preset acceleration threshold; determining that the reference vehicle should make a braking decision if the estimated braking acceleration information is not less than the preset acceleration threshold; and determining that the reference vehicle should make a passage decision if the estimated braking acceleration information is less than the preset acceleration threshold. This specific embodiment can ensure the accuracy of the decision, enabling autonomous vehicles to make decisions that are more in line with actual scenarios and ensuring the flexibility of the decision-making.

[0043] Specifically, the distance between the reference vehicle and the intersection stop line is calculated based on the position information of the reference vehicle and the position information of the intersection stop line. Then, based on the speed information of the reference vehicle and the distance between the reference vehicle and the intersection stop line, the formula V is used. 2The estimated braking acceleration of the reference vehicle is calculated using / 2S, where V is the speed of the reference vehicle and S is the distance between the reference vehicle and the stop line at the intersection. Based on a preset acceleration threshold, it is determined whether the reference vehicle can pass through the intersection with good comfort. When the estimated braking acceleration of the reference vehicle is not less than the preset acceleration threshold, the reference vehicle can pass through the intersection with good comfort, and the decision is to proceed. When the estimated braking acceleration of the reference vehicle is less than the preset acceleration threshold, the reference vehicle cannot pass through the intersection with good comfort, and the decision is to stop. The acceleration threshold can be selected according to actual conditions, such as different road surface materials or weather conditions. For example, in some embodiments, the acceleration threshold can be set to -6 m / s². 2 -7m / s 2 or -8m / s 2 .

[0044] In one embodiment of this application, multiple reference vehicles are determined in a lane of the same type as the current driving lane of the current vehicle. The intersection passage intention of each reference vehicle is determined based on the motion state information of each reference vehicle, resulting in multiple intersection passage intentions of multiple reference vehicles. The intersection passage strategy is determined based on the multiple intersection passage intentions, which can improve the reliability of intersection passage decision-making.

[0045] In one embodiment of this application, the number of intentions to pass through the current intersection and the number of no intentions to pass through the current intersection are counted among multiple intersection passing intentions, and the current intersection passage decision is determined based on the intersection passing intentions with the larger number.

[0046] Specifically, the estimated braking acceleration information of multiple reference vehicles is compared with a preset acceleration threshold to obtain the passage decision results of multiple reference vehicles at the intersection. These passage decision results are categorized into passage and stopping outcomes, and the number of decision results in each category is counted. The autonomous vehicle's decision is based on the category with the most passing decisions. That is, when the number of passing decisions is high, the autonomous vehicle's decision is to pass; when the number of stopping decisions is high, the autonomous vehicle's decision is to stop. The preset acceleration threshold can be adjusted according to different usage scenarios, and this application does not impose specific limitations on the setting of the acceleration threshold.

[0047] Figure 2 An embodiment of a traffic decision-making device according to this application is shown.

[0048] exist Figure 2In the embodiment shown, the traffic decision device mainly includes: a reference vehicle acquisition module 201, which is used to determine a reference vehicle in the adjacent lane of the current vehicle's current lane that is traveling in the same direction as the current vehicle and whose position is not in front of the current vehicle when the current vehicle cannot obtain the traffic light status at the intersection. The decision module 202 is used to obtain the position and speed information of the reference vehicle, and to determine whether the reference vehicle can cross the intersection stop line based on the position, speed and position information of the reference vehicle and the stop line of the intersection. If the reference vehicle can cross the intersection stop line, a passage decision is issued to the current vehicle; if the reference vehicle cannot cross the intersection stop line, a stop decision is issued to the current vehicle.

[0049] The passage decision-making device provided in this application can be used to execute the passage decision-making method described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0050] In another embodiment of this application, a computer-readable storage medium stores computer instructions that are operated to perform the passage decision-making method described in the above embodiments.

[0051] In one specific embodiment of this application, the functional modules in the passage decision method of this application may be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0052] 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.

[0053] 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.

[0054] In another embodiment of this application, a vehicle is provided, wherein the vehicle includes the intersection traffic decision method of any embodiment. Optionally, the vehicle includes a processor and a memory, the processor and memory being coupled, and the vehicle is used to implement the appendix to this specification. Figure 1 The passage decision method in the embodiments.

[0055] 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.

[0056] 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.

[0057] 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 method for traffic decision-making at intersections, characterized in that, include: When the current vehicle cannot obtain the traffic light status at the intersection, a reference vehicle is determined in a lane of the same type as the current vehicle's current driving lane. The same type of lane includes lanes with the same traffic direction and the same lane restriction requirements. The location and speed information of the reference vehicle are obtained, and the location information of the reference vehicle, speed information, and the location information of the intersection stop line are used to determine whether the reference vehicle intends to pass through the intersection stop line. If it is determined that the reference vehicle intends to pass through the intersection stop line, the intersection passage decision of the current vehicle is determined to be a passage decision. If it is determined that the reference vehicle cannot pass the stop line at the intersection, the current vehicle's intersection passage decision is determined to be a stop decision; The process of acquiring the position and speed information of the reference vehicle, and determining whether the reference vehicle intends to cross the intersection stop line based on the position and speed information of the reference vehicle and the position information of the intersection stop line, includes: The braking distance between the reference vehicle and the intersection stop line is calculated based on the position information of the reference vehicle and the position information of the intersection stop line. The estimated braking acceleration information of the reference vehicle is calculated using the speed information of the reference vehicle and the braking distance. The estimated braking acceleration information of the reference vehicle is compared with a preset acceleration threshold. If the estimated braking acceleration information is not less than the preset acceleration threshold, it is determined that the reference vehicle will make a braking decision. If the estimated braking acceleration information is less than the preset acceleration threshold, the reference vehicle is determined to make a passage decision.

2. The intersection traffic decision-making method according to claim 1, characterized in that, The step of determining a reference vehicle in a lane of the same type as the current vehicle's current driving lane further includes: The vehicle located behind the current vehicle relative to the lane travel direction is identified as the reference vehicle.

3. The intersection traffic decision-making method according to claim 1, characterized in that, The step of determining a reference vehicle in a lane of the same type as the current vehicle's current driving lane further includes: The vehicle in the lane adjacent to the lane where the current vehicle is located is identified as the reference vehicle.

4. The intersection traffic decision-making method according to claim 1, characterized in that, include: Multiple reference vehicles are identified in the same lane as the current vehicle's current driving lane. The intersection passage intention of each reference vehicle is determined based on the motion state information of each reference vehicle, resulting in multiple intersection passage intentions of the multiple reference vehicles. An intersection passage strategy is determined based on the multiple intersection passage intentions.

5. The intersection traffic decision-making method according to claim 4, characterized in that, The process of determining the intersection passage strategy based on multiple intersection passage intentions includes: The number of intentions to pass through the current intersection and the number of intentions not to pass through the current intersection are counted separately. The passage decision for the current intersection is determined based on the number of intentions to pass through the intersection with the larger number of intentions.

6. A traffic decision-making device for intersections, characterized in that, include: The reference vehicle acquisition module is used to determine a reference vehicle in a lane of the same type as the current vehicle's current driving lane when the current vehicle cannot obtain the traffic light status at the intersection. The lane of the same type includes lanes with the same direction of travel and the same lane restriction requirements. The decision-making module is used to acquire the position and speed information of the reference vehicle, and determine whether the reference vehicle intends to cross the intersection stop line based on the position, speed, and position information of the intersection stop line. If the reference vehicle is determined to intend to cross the intersection stop line, the current vehicle's intersection passage decision is determined to be a passage decision; if the reference vehicle is determined to be unable to cross the intersection stop line, the current vehicle's intersection passage decision is determined to be a stop decision. The decision-making module further includes: A braking distance calculation module is used to calculate the braking distance between the reference vehicle and the intersection stop line based on the position information of the reference vehicle and the position information of the intersection stop line. The estimated braking acceleration information calculation module is used to calculate the estimated braking acceleration information of the reference vehicle using the speed information of the reference vehicle and the braking distance. The judgment module is used to compare the estimated braking acceleration information of the reference vehicle with a preset acceleration threshold. If the estimated braking acceleration information is not less than the preset acceleration threshold, the module determines that the reference vehicle should make a braking decision; if the estimated braking acceleration information is less than the preset acceleration threshold, the module determines that the reference vehicle should make a passage decision.

7. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the intersection traffic decision method as described in any one of claims 1-5.

8. A vehicle, characterized in that, The vehicle includes the intersection traffic decision-making device as described in claim 6.

Images