Vehicle crossing passing method, intelligent driving domain controller, storage medium and program product

Abstract

The invention provides a vehicle intersection passing method and an intelligent driving domain controller, and the method comprises the steps: obtaining the map information of a target vehicle at a current position, the information of vehicles around the target vehicle, and the state information of a traffic signal lamp in front of the target vehicle, the vehicle information comprises one of no vehicle, temporary parking waiting, straight going and turning, and the state information of the traffic signal lamp in front of the target vehicle; the traffic signal lamp state information comprises first state information and second state information, the first state information is used for indicating vehicle passing, the second state information is used for indicating prohibition of vehicle passing, and the current position of the target vehicle is located at an intersection and does not pass through the intersection; according to the map information, the vehicle information and the traffic signal lamp state information, whether view shielding judgment needs to be executed or not is judged; if so, determining the view shielding condition of the target vehicle; and determining a safe driving strategy of the target vehicle according to the view shielding condition. According to the invention, the driving safety of the vehicle passing through the intersection can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safe driving, in particular to a vehicle intersection passing method, an intelligent driving domain controller, a storage medium and a program product. BACKGROUND

[0002] With the progress of artificial intelligence and sensor technology, vehicles can more accurately perceive the surrounding environment and make complex decisions, thus promoting the rapid development of autonomous driving technology. The unprotected left turn scenario refers to a scenario where there is no traffic light or other guiding sign at the intersection for vehicles to make a left turn. In the context of intelligent driving, vehicles passing through intersections with unprotected left turns face complex risks such as visual obstruction and interaction with multiple traffic participants. The existing technology has deficiencies in comprehensive evaluation of intersection safety passing, especially in dynamic risk identification for unprotected left turn / turning vehicles and turning lanes. When the ego vehicle is in a scenario where it can make an unprotected left turn at an intersection, vehicles on both sides of the ego vehicle's lane may obstruct the ego vehicle's view, making it difficult to determine whether there is an unprotected left turn vehicle approaching from the left side of the ego vehicle, and whether there is a vehicle approaching from the right side of the ego vehicle on the crossing lane. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a vehicle intersection passing method, an intelligent driving domain controller, a storage medium and a program product to provide a safe driving strategy when a vehicle passes through an intersection with an unprotected left turn, thereby improving the safety of intersection passing.

[0004] In a first aspect, the present application provides a vehicle intersection passing method, comprising: acquiring map information of a target vehicle at a current position, vehicle information around the target vehicle, and traffic signal light state information in front of the target vehicle, wherein the vehicle information includes one of no vehicle, temporary stop waiting, straight driving, and turning, the traffic signal light state information includes first state information and second state information, the first state information is used to indicate vehicle passage, and the second state information is used to indicate prohibition of vehicle passage, the current position of the target vehicle is located at an intersection, and the target vehicle has not passed through the intersection; determining whether to perform visual obstruction judgment according to the map information, the vehicle information, and the traffic signal light state information; if so, determining a visual obstruction condition of the target vehicle; and determining a safe driving strategy of the target vehicle according to the visual obstruction condition.

[0005] In the above scheme, by comprehensively acquiring map information, vehicle information and traffic signal light state information, the visual obstruction condition can be accurately judged, and a reasonable safe driving strategy can be formulated, thereby greatly reducing the risk of collision with other vehicles, reducing the judgment pressure of the driver in complex road conditions, and improving the overall driving experience.

[0006] As an optional mode, the judging whether the visual field shielding judgment needs to be performed according to the map information, the vehicle information and the traffic signal lamp state information comprises: determining that the target vehicle is located in the rightmost lane according to the map information, the vehicle information comprises first vehicle information of a lane on the left side of the target vehicle, the traffic signal lamp state information comprises a turning signal lamp of a turning lane in front of the target vehicle, and a turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle; if the first vehicle information is temporary parking and waiting, and the traffic signal lamp state information is any state, the visual field shielding judgment is performed, otherwise, the visual field shielding judgment is not performed, wherein the visual field shielding judgment comprises whether there is visual field shielding on the left side of the target vehicle.

[0007] When the target vehicle is located in the rightmost lane, the left side vehicle shields the visual field, and it is difficult to perceive potential dangers such as protecting the left turning vehicle. In the above scheme, the specific conditions for performing the visual field shielding judgment are determined, and the judgment is performed only when the left lane vehicle is temporarily parked and waiting and the traffic signal lamp state information is any state, thereby reducing unnecessary judgment process. The visual field shielding judgment is performed under the specific condition, potential visual field shielding problems can be found in time, risks can be identified in advance, and basis is provided for subsequent safe driving strategy, thereby effectively reducing traffic accidents caused by visual obstruction.

[0008] As an optional mode, the judging whether the visual field shielding judgment needs to be performed according to the map information, the vehicle information and the traffic signal lamp state information comprises: determining that the target vehicle is located in the rightmost lane according to the map information, the vehicle information comprises first vehicle information of a lane on the left side of the target vehicle, the traffic signal lamp state information comprises a turning signal lamp of a turning lane in front of the target vehicle, and a turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle; if the first vehicle information is temporary parking and waiting, and the traffic signal lamp state information is any state, the visual field shielding judgment is performed, otherwise, the visual field shielding judgment is not performed, wherein the visual field shielding judgment comprises whether there is visual field shielding on the left side of the target vehicle.

[0009] When the target vehicle is located in the middle lane, the target vehicle faces the problem of being blocked by the left and right vehicles, and it is difficult to detect potential dangers such as unprotected left-turn vehicles and right-turn vehicles on the turning lane. In the above scheme, the specific conditions for performing left and right visual field blocking judgment are clearly defined, unnecessary judgment processes are reduced, visual field blocking judgment is performed under specific conditions, potential visual field blocking problems can be found in time, risks can be identified in advance, and the basis for subsequent safe driving strategies is provided, thereby effectively reducing traffic accidents caused by blocked vision.

[0010] As an optional mode, the judging whether the visual field blocking judgment needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information comprises: determining that the target vehicle is located in the leftmost lane according to the map information, the vehicle information comprises second vehicle information of a right lane of the target vehicle, the traffic signal lamp state information comprises a turning signal lamp of a turning lane in front of the target vehicle, and a turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle; if the second vehicle information is temporarily stopped and waits, and the traffic signal lamp state information is the first state information, the visual field blocking judgment is performed, otherwise, the visual field blocking judgment is not performed, wherein the visual field blocking judgment comprises whether there is a visual field blocking on the right side of the target vehicle.

[0011] When the target vehicle is located in the leftmost lane, the target vehicle faces the problem of being blocked by the right vehicle, and it is difficult to detect potential dangers such as right-turn vehicles on the turning lane. In the above scheme, by clearly defining the specific conditions for performing visual field blocking judgment, the judgment is only performed when the vehicle in the right lane is temporarily stopped and waits and the traffic signal lamp state information is the first state information, unnecessary judgment processes are reduced, visual field blocking judgment is performed under this specific condition, potential visual field blocking problems can be found in time, risks can be identified in advance, and the basis for subsequent safe driving strategies is provided, thereby effectively reducing traffic accidents caused by blocked vision.

[0012] As an optional mode, after the map information of the target vehicle at the current position, the vehicle information around the target vehicle, and the traffic signal lamp state information in front of the target vehicle are acquired, the method further comprises: judging whether the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information, the turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle, if yes, determining whether there is a passing vehicle; and the determining the safe driving strategy of the target vehicle according to the visual field blocking condition comprises: determining the safe driving strategy of the target vehicle according to the visual field blocking condition and whether there is a passing vehicle.

[0013] In the intersection scenario, in addition to the problem of the vehicle's own visual obstruction, the passing vehicle on the turning lane in front of the target vehicle can also pose a threat to the safe driving of the target vehicle. In the above scheme, by adding a judgment link for the passing vehicle on the lane, the safe driving strategy is determined in combination with the visual obstruction, which reduces potential accidents caused by ignoring distant vehicles and can more accurately assess the overall safety risk to provide more comprehensive safety protection for the driver.

[0014] As an optional way, the judging whether to perform the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle according to the map information, the vehicle information, and the traffic signal light state information comprises: determining that the target vehicle is located on the rightmost lane according to the map information, and the traffic signal light state information comprises a turning signal light of the turning lane in front of the target vehicle; if the traffic signal light state information is the first state information, the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle is performed, otherwise, the judgment is not performed.

[0015] In the above scheme, in the case that the target vehicle is located on the rightmost lane, the judgment is performed according to the traffic signal light state information of the intersection lane, the monitoring of potential dangers is strengthened when the turning signal light allows the passing of the vehicle on the turning lane, and unnecessary judgment is reduced when the turning signal light prohibits the passing, which reduces the resource waste caused by invalid judgment and can also discover potential conflict vehicles in time to ensure the safety of driving.

[0016] As an optional way, the judging whether to perform the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle according to the map information, the vehicle information, and the traffic signal light state information comprises: determining that the target vehicle is located on the middle lane or the leftmost lane according to the map information, the vehicle information comprises second vehicle information of the right lane of the target vehicle, and the traffic signal light state information comprises a turning signal light of the turning lane in front of the target vehicle; if the traffic signal light state information is the first state information, and the second vehicle information is no vehicle, temporary parking for waiting or turning, the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle is performed, otherwise, the judgment is not performed.

[0017] In the above scheme, in the case that the target vehicle is located on the middle lane or the leftmost lane, the judgment is performed according to the traffic signal light state of the turning lane in combination with the vehicle information of the right lane, which improves the judgment efficiency and real-time performance and reduces the decision delay caused by redundant calculation.

[0018] As an optional mode, the method comprises: if it is judged that the visual field shielding judgment is not needed to be performed according to the map information, the vehicle information and the traffic signal lamp state information, it is judged whether the judgment of whether there is a passing vehicle in the turning lane in front of the target vehicle, the turning direction corresponding to the turning lane being the same as the straight direction of the target vehicle, is needed to be performed, and if it is needed, it is determined whether there is a passing vehicle; and the safety driving strategy of the target vehicle is determined according to the determination of whether there is a passing vehicle.

[0019] In the above scheme, in the intersection right-of-way conflict scene, even if the visual field is not shielded, the driving track of the vehicle on the turning lane may still cross the target vehicle (such as a "ghost probe" conflict). By judging whether the judgment of whether there is a passing vehicle in the turning lane in front of the target vehicle needs to be performed, the risk can be warned in advance, and the comprehensive coverage of the "dynamic risk source" is ensured.

[0020] As an optional mode, the safety driving strategy is determined by the following method: if one of the following conditions is met: there is a visual field shielding on the left side of the target vehicle, there is a visual field shielding on the right side of the target vehicle, and there is a passing vehicle in the turning lane in front of the target vehicle, it is determined that the safety driving strategy is deceleration one-gear passing; if two or more of the following conditions are met: there is a visual field shielding on the left side of the target vehicle, there is a visual field shielding on the right side of the target vehicle, and there is a passing vehicle in the turning lane in front of the target vehicle, it is determined that the safety driving strategy is deceleration two-gear passing; otherwise, it is determined that the safety driving strategy is maintaining the original vehicle speed passing.

[0021] In the above scheme, the three risk factors of left side visual field shielding, right side visual field shielding and passing vehicle in the turning lane are combined to judge, forming a three-level strategy of deceleration one-gear, deceleration two-gear and maintaining the original speed, which improves the "one-size-fits-all" extensive decision-making, reduces the influence on the passing efficiency while reserving the safety margin.

[0022] In a second aspect, the present application provides an intelligent driving domain controller, comprising: a processor, a memory and a bus, wherein the processor and the memory complete mutual communication through the bus; the memory stores program instructions that can be executed by the processor, and the processor calling the program instructions can execute the method steps of the first aspect.

[0023] In a third aspect, the present application provides a computer readable storage medium, comprising: the computer readable storage medium stores computer instructions, and the computer instructions make the computer execute the method steps of the first aspect.

[0024] In a fourth aspect, the present application provides a computer program product, comprising computer program instructions, which are read and run by a processor and execute the method steps of the first aspect.

[0025] In a fifth aspect, the present application provides a vehicle comprising the intelligent driving domain controller of the second aspect.

[0026] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application as set forth in the description. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0028] Figure 1 The flowchart of the vehicle intersection passing method provided by the embodiments of the present application is shown in the figure; Figure 2 The position of the target vehicle at the intersection and the distribution of the surrounding vehicles provided by the embodiments of the present application are shown in the figure; Figure 3 The structure diagram of the intelligent driving domain controller provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] The embodiments of the technical solutions of the present application will be described in detail below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0030] It should be noted that all the technical and scientific terms used herein have the same meaning as that understood by the skilled person in the technical field of the present application; the terms used herein are only for the purpose of describing the specific embodiments, and are not intended to limit the present application; the terms in the specification and claims of the present application and the above description of drawings, "include" and "have", as well as any variation thereof, are intended to cover non-exclusive inclusion.

[0031] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0032] In the description of the embodiments of the present application, the term "and / or" is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0033] It can be understood that the vehicle intersection passing method provided by the embodiments of the present application can be applied to an intelligent driving domain controller. In order to facilitate understanding, the technical solutions provided by the embodiments of the present application are described below with the intelligent driving domain controller as an execution subject. The application scenarios of the vehicle intersection passing method provided by the embodiments of the present application are introduced.

[0034] Referring to Figure 1 , Figure 1 The flowchart of the vehicle intersection passing method provided by the embodiments of the present application, the method comprises the following steps: Step S10: Obtain the map information of the target vehicle at the current position, the vehicle information around the target vehicle, and the traffic signal lamp state information in front of the target vehicle, wherein the vehicle information comprises one of no vehicle, temporary stop waiting, straight driving, and turning, the traffic signal lamp state information comprises first state information and second state information, the first state information is used to indicate vehicle passing, and the second state information is used to indicate prohibiting vehicle passing, the current position of the target vehicle is located at the intersection, and the intersection has not been passed.

[0035] Referring to Figure 2 , Figure 2 The position of the target vehicle at the intersection and the distribution of the surrounding vehicles provided by the embodiments of the present application are shown in the figure, Figure 2 In the figure, is the middle lane, is the left lane, is the right lane, is the turning lane in front of the target vehicle, and it should be noted that, may represent one lane, or may represent multiple lanes, is the opposite lane, when the target vehicle drives along or or the lane to the intersection, due to the complexity of the traffic situation, there are many risk factors such as visual obstruction, vehicle intersection passing, etc., for example, there is a vehicle turning left or U-turning without protection at the position, There are vehicles turning right, etc., so it is necessary to obtain map information, vehicle information and traffic signal light state information for traffic risk judgment. Related information can be obtained through various sensors and communication devices equipped on the vehicle, for example, map information can be obtained through a high-precision map system, which can reflect the detailed layout of the intersection, such as the number of lanes, the direction of the lane, the shape of the intersection, etc.; vehicle information around the target vehicle can be obtained through the target vehicle's panoramic vision perception system, radar sensor, laser radar sensor, communication interface and motion state sensor, etc. With these vehicle-mounted environmental sensors, the target vehicle can detect the distance and relative speed of the surrounding vehicles; the traffic signal light state information in front of the target vehicle can be identified by the color of the traffic signal light through the camera and the car navigation map reading second information on the vehicle, or through data interaction with the communication system of the traffic signal light.

[0036] The traffic signal light state information includes first state information and second state information, the first state information is used to indicate that the vehicle is allowed to pass, for example, the green light is on or the yellow light is on; the second state information is used to indicate that the vehicle is prohibited to pass, for example, the red light is on.

[0037] Step S20: According to the map information, vehicle information and traffic signal light state information, it is judged whether the visual field shielding judgment needs to be performed.

[0038] The map information, vehicle information and traffic signal light state information are comprehensively considered to judge whether there is a possibility of visual field shielding, so as to decide whether the visual field shielding judgment needs to be performed. If the above factors can directly determine that there is no visual field shielding or indirectly determine that there is no potential traffic participant at the visual field shielding place, then the visual field shielding judgment does not need to be performed. For the former case, for example, the target vehicle is located in the leftmost lane, then the left side must not be shielded from the visual field, so the visual field shielding judgment does not need to be performed, and even if the target vehicle is located in the middle lane, but if there is no car on the left side, the visual field shielding judgment also does not need to be performed. For the latter case, for example, if the vehicle on the left lane of the target vehicle turns left, it indirectly reflects that there is no driving on the left side that is shielded, otherwise the vehicle on the left side will not turn left. The motion state of the vehicle on the left side indirectly eliminates the potential risk, so the visual field shielding judgment does not need to be performed.

[0039] When the surrounding vehicles are temporarily stopped and waiting, the visual field shielding judgment needs to be performed in most cases, unless the traffic signal light state information can be known that there is no car at the visual field shielding place.

[0040] Step S30: If needed, the visual field shielding situation of the target vehicle is determined.

[0041] When it is determined that the visual field shielding judgment needs to be performed, the visual field shielding situation of the target vehicle is further determined through the sensors on the vehicle. The image information around the target vehicle can be obtained through the camera, and it is analyzed whether there is an obstacle (such as a temporarily parked vehicle) shielding the visual field of the target vehicle in the image. At the same time, the position and distance of the obstacle are detected by combining sensors such as radars, and the range and degree of visual field shielding are accurately judged. For example, it is determined whether there is visual field shielding on the left side of the target vehicle, whether there is visual field shielding on the right side of the target vehicle, and the like.

[0042] As an embodiment of determining the visual field shielding situation, the vehicle-mounted sensor can perceive the road structure of the intersection where the target vehicle is currently located, and compare it with the map output information. If the intelligent driving domain controller finds that the sensor perception is missing and there is a traffic participant within the sensor perception range of 60 m, it is judged that the visual field is shielded. It can be understood that those skilled in the art can adjust the perception range of the sensor to detect whether there is a traffic participant, and the present application does not make specific limitations thereto.

[0043] Step S40: determining the safe driving strategy of the target vehicle according to the visual field shielding situation.

[0044] According to different visual field shielding situations, different levels of safe driving strategies are determined. The safe driving strategy is used to pass through the intersection, and the visual field shielding situation can be divided into left visual field shielding and / or right visual field shielding. If there is only unilateral visual field shielding, a corresponding level of deceleration safe driving strategy is determined. If there is visual field shielding on both sides, a corresponding level of deceleration safe driving strategy is determined. The deceleration amplitude of the safe driving strategy with visual field shielding on both sides is larger than that of the safe driving strategy with unilateral visual field shielding. If there is no visual field shielding, it indicates that the visual field of the target vehicle is good, and the original vehicle speed can be maintained. By executing such a gradient deceleration strategy, the balance between safety and passing efficiency is considered, which can adapt to various complex intersection traffic scenes and has strong adaptability and universality.

[0045] In the above scheme, by comprehensively obtaining map information, vehicle information and traffic signal lamp state information, the visual field shielding situation can be accurately judged, and a reasonable safe driving strategy is formulated, which greatly reduces the risk of collision with other vehicles, reduces the judgment pressure of the driver in complex road conditions, and improves the overall driving experience.

[0046] In some embodiments, step S20 comprises: Step 1): according to the map information, it is determined that the target vehicle is located in the rightmost lane, the vehicle information includes the first vehicle information of the left lane of the target vehicle, and the traffic signal lamp state information includes the turning signal lamp of the turning lane in front of the target vehicle. The turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle.

[0047] The turning direction should refer to the driving direction of the vehicle after turning the lane, and the same hereinafter.

[0048] For example, it is determined that the target vehicle is located in the rightmost lane Figure 2 The vehicle information includes first vehicle information of the lane and The traffic signal light state information includes the turning signal light of the lane

[0049] Step 2): If the first vehicle information is temporary parking and waiting, and the traffic signal light state information is any state, perform the visual field obstruction judgment, otherwise, do not perform the visual field obstruction judgment, wherein the visual field obstruction judgment includes whether there is a visual field obstruction on the left side of the target vehicle.

[0050] Firstly, the positioning module of the vehicle determines that the target vehicle is currently located in the rightmost lane of the intersection in combination with the map information, such as Figure 2 The lane The sensor monitors the vehicle in the left lane such as lane in real time, which can be identified by a target detection algorithm (such as YOLO, BEV perception) to identify the motion state of the vehicle. For example, if it is detected that the vehicle in lane is stationary and the duration exceeds a preset threshold, such as 5 seconds, it is determined that the first vehicle information is temporary parking and waiting; if the vehicle speed is greater than 0 and the driving direction is the same as that of the target vehicle, it is determined that it is straight; if the turning indicator of the vehicle is turned on and the driving trajectory is offset, it is determined that it is turning; if the sensor does not detect the vehicle, it is determined that there is no vehicle.

[0051] Then, the condition judgment exists visual field obstruction judgment, when the first vehicle information is temporary parking and waiting, no matter whether the turning signal light is in the first state information or the second state information, the left visual field of the target vehicle may be obstructed, therefore, as long as the vehicle in the left lane is temporarily parked, the visual field obstruction judgment is triggered, ensuring full-scene risk coverage.

[0052] On the contrary, if the first vehicle information is straight or left turning, it indirectly indicates that there is no obstructed traffic participant on the left side, at this time, the left visual field obstruction judgment does not need to be performed, if the first vehicle information is no vehicle, there is no vehicle obstructing the visual field on the left side, naturally, the left visual field obstruction judgment does not need to be performed.

[0053] ​​When the target vehicle is in the rightmost lane, it faces the problem of obstructed view by vehicles on the left, making it difficult to detect potential dangers such as whether there is protection for vehicles turning left. In the above solution, by clearly defining the specific conditions for performing the view obstruction judgment, the judgment is only performed when vehicles in the left lane are temporarily stopped and the traffic light status information is in any state. This reduces unnecessary judgment processes. Performing the view obstruction judgment under this specific condition can promptly detect potential view obstruction problems, identify risks in advance, and provide a basis for subsequent safe driving strategies, effectively reducing traffic accidents caused by obstructed vision.

[0054] In some embodiments, step S20 includes: Step 1): Based on the map information, determine that the target vehicle is located in the middle lane. The vehicle information includes the first vehicle information in the left lane and the second vehicle information in the right lane. The traffic light status information includes the turn signal light of the turning lane in front of the target vehicle. The turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle.

[0055] by Figure 2 For example, determine if the target vehicle is located in the middle lane. Vehicle information includes lane First vehicle information and lane The second vehicle information, traffic light status information includes lane information. The turn signal lights.

[0056] Step 2): If the first vehicle information is temporary stop waiting and the traffic light status information is in any state, then perform the view occlusion judgment; otherwise, do not perform the view occlusion judgment. The view occlusion judgment includes whether there is view occlusion on the left side of the target vehicle.

[0057] The principle for determining whether to perform left-side visual field occlusion detection is the same as in the aforementioned embodiments, and will not be repeated here.

[0058] Step 3): If the second vehicle information is temporary stop waiting and the traffic light status information is the first status information, then perform the view occlusion judgment; otherwise, do not perform it. The view occlusion judgment includes whether there is view occlusion on the right side of the target vehicle.

[0059] When the second vehicle's information indicates a temporary stop and the traffic light status is in the first state, a right-side view obstruction judgment is performed. Lane Temporarily parked vehicles in the lane When a turn signal indicates that a vehicle is to proceed, it may obstruct the target vehicle's view of oncoming traffic from the right-hand intersecting lane (such as lane markings). Observe the right-turning vehicle. If the lane... When the turn signal indicates that vehicles are prohibited from passing, vehicles in the right-hand intersecting lane are usually prohibited from passing, and the risk is low, so the judgment is only triggered when the light is green.

[0060] Conversely, in the following scenarios, it is not necessary to perform right-side view occlusion judgment: the second vehicle information is that it is going straight and the traffic light status information is in the first state; the second vehicle information is that it is going straight and the traffic light status information is in the second state; the second vehicle information is that it is turning right and the traffic light status information is in the first state; the second vehicle information is that it is turning right and the traffic light status information is in the second state; the second vehicle information is that there is no vehicle and the traffic light status information is in the first state; the second vehicle information is that there is no vehicle and the traffic light status information is in the second state.

[0061] When a target vehicle is in the middle lane, it faces the problem of obstructed vision by vehicles on the left and right, making it difficult to detect potential dangers such as unprotected left-turning vehicles and right-turning vehicles in the turning lane. In the above solution, the specific conditions for performing left-side and right-side vision obstruction judgments are clearly defined, reducing unnecessary judgment procedures. Performing vision obstruction judgments under specific conditions can promptly detect potential vision obstruction problems, identify risks in advance, and provide a basis for subsequent safe driving strategies, effectively reducing traffic accidents caused by obstructed vision.

[0062] In some embodiments, step S20 includes: Step 1): Based on the map information, determine that the target vehicle is located in the leftmost lane. The vehicle information includes the second vehicle information in the right lane of the target vehicle. The traffic light status information includes the turn signal light of the turning lane in front of the target vehicle. The turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle.

[0063] by Figure 2 For example, determine if the target vehicle is located in the leftmost lane. Vehicle information includes lane and lane The second vehicle information, traffic light status information includes lane information. The turn signal lights.

[0064] Step 2): If the second vehicle information is temporary stop waiting and the traffic light status information is the first status information, then perform the view occlusion judgment; otherwise, do not perform the view occlusion judgment. The view occlusion judgment includes whether there is view occlusion on the right side of the target vehicle.

[0065] The principle for determining whether to perform right-side visual field occlusion detection is the same as in the aforementioned embodiments, and will not be repeated here.

[0066] When the target vehicle is in the leftmost lane, it faces the problem of obstructed vision by vehicles on the right, making it difficult to detect potential dangers such as vehicles turning right in the turning lane. In the above solution, by clearly defining the specific conditions for performing vision obstruction judgment, the judgment is only performed when vehicles in the right lane are temporarily stopped and the traffic light status information is in the first state information. This reduces unnecessary judgment processes. Performing vision obstruction judgment under this specific condition can promptly detect potential vision obstruction problems, identify risks in advance, and provide a basis for subsequent safe driving strategies, effectively reducing traffic accidents caused by obstructed vision.

[0067] In some embodiments, after step S10, the method further includes: Step S50: Based on map information, vehicle information and traffic light status information, determine whether it is necessary to determine whether there are vehicles in the turning lane in front of the target vehicle. The turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle. Step S60: If necessary, determine whether there are any vehicles passing through.

[0068] Step S70: Determine the safe driving strategy of the target vehicle based on the obstruction of the field of vision, including: determining the safe driving strategy of the target vehicle based on the obstruction of the field of vision and whether there are oncoming vehicles.

[0069] by Figure 2 For example, a lane is the turning lane in front of the target vehicle, where the turning direction of the turning lane is the same as the straight-going direction of the target vehicle. After step S10, the visual obstruction judgment (steps S20-S30) and the judgment of whether there are passing vehicles are performed simultaneously. Based on the risk supplementary decision of the turning lane, the influence of the turning lane risk is superimposed on the safe driving strategy made based on the visual obstruction situation, forming a fusion strategy of "obstruction risk + turning lane risk".

[0070] When the traffic light status information for the turning lane is in the first state, in most cases it is necessary to determine whether there are vehicles passing through the turning lane, because vehicles are allowed to pass at this time. In addition to indirectly determining that there are no right-turning vehicles in the turning lane through the surrounding vehicle information, even if the traffic light status information for the turning lane is in the first state, it is not necessary to determine whether there are vehicles passing through the turning lane. This improves driving safety while taking into account traffic efficiency.

[0071] After the conditions for determining whether there are vehicles passing through are triggered, the camera identifies whether the vehicle has started moving after the stop line of the turning lane (e.g., brake lights are off, tires are turning). The radar can also be used to verify whether there is a moving target in the same direction as the turning lane. Finally, the system makes a comprehensive judgment to determine whether there are "vehicles passing through" or "no vehicles passing through".

[0072] In the intersection scene, in addition to the problem of the vehicle's own visual obstruction, the passing vehicle on the turning lane in front of the target vehicle can also pose a threat to the safe driving of the target vehicle. In the above scheme, by adding a judgment link of the passing vehicle on the lane, the safe driving strategy is determined in combination with the visual obstruction, which reduces the potential accidents caused by ignoring the distant vehicle, and can more accurately evaluate the overall safety risk and provide more comprehensive safety protection for the driver.

[0073] In some embodiments, step S50 comprises: Step 1): According to the map information, it is determined that the target vehicle is located in the rightmost lane, and the traffic signal light state information includes the turning signal light of the turning lane in front of the target vehicle.

[0074] Step 2): If the traffic signal light state information is the first state information, the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle is performed, otherwise, it is not performed.

[0075] When the target vehicle is located in the rightmost lane, the triggering condition of the judgment of whether there is a passing vehicle on the turning lane is the traffic signal light state information of the turning lane, and the judgment is performed only when the first state information is executed, and the judgment is not performed when the second state information is executed.

[0076] In the above scheme, when the target vehicle is located in the rightmost lane, the judgment is performed according to the traffic signal light state information of the turning lane, the monitoring of potential dangers is strengthened when the turning signal light allows the passing of the vehicle on the turning lane, and unnecessary judgment is reduced when the turning signal light prohibits the passing, which reduces the resource waste caused by invalid judgment, and can also discover potential conflict vehicles in time, thereby ensuring the safety of driving.

[0077] In some embodiments, step S50 comprises: Step 1): According to the map information, it is determined that the target vehicle is located in the middle lane or the leftmost lane, the vehicle information includes the second vehicle information of the right lane of the target vehicle, and the traffic signal light state information includes the turning signal light of the turning lane in front of the target vehicle.

[0078] Step 2): If the traffic signal light state information is the first state information, and the second vehicle information is no vehicle, or temporary parking and waiting, or turning, the judgment of whether there is a passing vehicle on the turning lane in front of the target vehicle is performed, otherwise, it is not performed.

[0079] In the case that the target vehicle is located in the middle lane or the leftmost lane, the triggering condition of the turning lane with or without passing vehicle judgment is the traffic signal light state information of the turning lane and the vehicle information of the right lane. If the turning lane is indirectly determined to have no passing vehicle according to the vehicle information of the right lane, the turning lane with or without passing vehicle judgment does not need to be performed even if the traffic signal light state information of the turning lane is the first state information, which is beneficial to save computing power and improve decision efficiency. When the second vehicle information of the right lane is straight driving, it indirectly implies that the turning lane has no passing vehicle, and the turning lane with or without passing vehicle judgment does not need to be performed.

[0080] In the above scheme, in the case that the target vehicle is located in the middle lane or the leftmost lane, the turning lane with or without passing vehicle judgment is determined according to the traffic signal light state of the turning lane and the vehicle information of the right lane, which improves the judgment efficiency and real-time performance and reduces the decision delay caused by redundant calculation.

[0081] In some embodiments, the method comprises: Step S80: If it is determined according to the map information, the vehicle information and the traffic signal light state information that the visual field shielding judgment does not need to be performed, it is determined whether the turning lane with or without passing vehicle judgment in front of the target vehicle needs to be performed, the turning direction corresponding to the turning lane is the same as the straight driving direction of the target vehicle, and if so, the passing vehicle is determined. Step S90: The safe driving strategy of the target vehicle is determined according to the passing vehicle.

[0082] In this embodiment, the turning lane with or without passing vehicle judgment is also performed when the visual field shielding judgment does not need to be performed, a “turning lane risk completion in the visual field shielding-free scene” mechanism is constructed, and the problem of “only focusing on shielding risk and ignoring dynamic threat of the turning lane” in the traditional scheme is solved.

[0083] In the above scheme, in the intersection right-of-way conflict scene, even if the visual field is not shielded, the driving track of the vehicle on the turning lane may still cross the target vehicle (such as “ghost probe” conflict). By determining whether the turning lane with or without passing vehicle judgment in front of the target vehicle needs to be performed, such risks can be warned in advance to ensure comprehensive coverage of “dynamic risk sources”.

[0084] In some embodiments, the safe driving strategy is determined by the following method: If one of the following conditions is met, the safe driving strategy is determined to be one-gear deceleration passing: the target vehicle left side exists a visual field obstruction, the target vehicle right side exists a visual field obstruction, and there is a passing vehicle on the turning lane in front of the target vehicle; if two or more of the following conditions are met, the safe driving strategy is determined to be two-gear deceleration passing: the target vehicle left side exists a visual field obstruction, the target vehicle right side exists a visual field obstruction, and there is a passing vehicle on the turning lane in front of the target vehicle; otherwise, the safe driving strategy is determined to be maintaining the original vehicle speed passing.

[0085] Based on the three risk factors of left side visual field obstruction, right side visual field obstruction, and turning lane passing vehicle, a hierarchical response of safe driving strategy is formed, from the original speed passing without risk, to one-gear deceleration passing with single risk, to the highest level of safe driving strategy with multiple risks, through the combination of risk quantification and grading, the accurate response to complex scenarios is realized, the driving safety is ensured, and the passing efficiency is considered, which provides a risk response framework for intelligent driving system.

[0086] As an implementation manner, the one-gear deceleration can be a speed reduction of 5km / h, and the two-gear deceleration can be a speed reduction of 10km / h, and those skilled in the art can adjust the speed setting according to experience, which is not limited in the present application.

[0087] In the above scheme, the three risk factors of left side visual field obstruction, right side visual field obstruction, and turning lane passing vehicle are combined to form three-level strategies of one-gear deceleration, two-gear deceleration, and maintaining the original speed, which improves the extensive decision-making of “one-size-fits-all”, and reduces the impact on passing efficiency while reserving safety margin.

[0088] The present application provides a device for executing a vehicle intersection passing method, comprising: The acquisition module is configured to acquire map information of a target vehicle at a current position, vehicle information around the target vehicle, and traffic signal light state information in front of the target vehicle, wherein the vehicle information includes one of no vehicle, temporary stop waiting, straight driving, and turning, the traffic signal light state information includes first state information and second state information, the first state information is used to indicate vehicle passing, the second state information is used to indicate prohibition of vehicle passing, the current position of the target vehicle is located at an intersection, and the intersection has not been passed.

[0089] The judgment module is configured to judge whether the visual field obstruction judgment needs to be performed according to the map information, the vehicle information, and the traffic signal light state information.

[0090] The determination of visual field obstruction module is configured to determine the visual field obstruction of the target vehicle if needed.

[0091] The safe driving strategy determination module is configured to determine the safe driving strategy of the target vehicle according to the visual field obstruction.

[0092] It should be understood that the device corresponds to the vehicle intersection passing method embodiments described above, and can perform each step involved in the above method embodiments. The specific functions of the device can be referred to the description above, and the detailed description is appropriately omitted here to avoid repetition. The device includes at least one software function module that can be stored in the memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0093] The present application provides a computer readable storage medium, comprising: the computer readable storage medium stores computer instructions, and the computer instructions make the computer execute the method steps of the first aspect.

[0094] The present application provides a computer program product, comprising computer program instructions, which are read and run by a processor to execute the methods provided by each of the method embodiments.

[0095] The present application provides an intelligent driving domain controller, comprising: a processor, a memory and a bus, wherein the processor and the memory complete mutual communication through the bus; the memory stores program instructions executable by the processor, and the processor calling the program instructions can execute the methods provided by each of the method embodiments.

[0096] Figure 3 The intelligent driving domain controller structure diagram provided for the embodiments of the present application is shown in FIG. 1. Figure 3 As shown in FIG. 1, the intelligent driving domain controller comprises: a processor 301, a memory 302 and a bus 303; wherein the processor 301 and the memory 302 complete mutual communication through the bus 303; the memory 302 stores program instructions executable by the processor 301, and the processor 301 calling the program instructions can execute the methods provided by each of the method embodiments.

[0097] The processor 301 includes one or more (only one is shown in the figure), which can be an integrated circuit chip with processing capability of signals. The processor 301 described above can be a general-purpose processor, including a central processing unit (CPU), a micro controller unit (MCU), a network processor (NP) or other conventional processors; it can also be a special-purpose processor, including a neural-network processing unit (NPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. And when the processor 301 is multiple, part of them can be general-purpose processors, and the other part can be special-purpose processors.

[0098] The memory 302 includes one or more (only one is shown in the figure), which can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) and the like. The processor 301 and other possible components can access, read and / or write data in the memory 302.

[0099] In particular, one or more computer program instructions can be stored in the memory 302, and the processor 301 can read and run these computer program instructions to implement the weak password scanning behavior identification method provided by the embodiments of the present application.

[0100] The bus 303 includes one or more (only one is shown in the figure) and can be used for direct or indirect communication with other devices to interact with data. The bus 303 can include devices for wired or wireless communication, such as optical fiber, serial peripheral interface (SPI) module, inter-integrated circuit (I2C), etc., and can also include devices for wireless communication, such as Bluetooth module, Wi-Fi module, mobile communication module (such as 4G, 3G module) and the like.

[0101] It can be understood that, Figure 3 The structure shown is only schematic, and the intelligent driving domain controller can also include more or fewer components than Figure 3 shown, or have a different structure from Figure 3 shown. Figure 3 The components shown in the above can be implemented in hardware, software or a combination thereof. The intelligent driving domain controller can be a physical device such as a switch, router, server, PC, etc., or a virtual device such as a virtual machine, virtual container, etc. Moreover, the intelligent driving domain controller is not limited to a single device, but can also be a combination of multiple devices or an integrated environment formed by a large number of devices.

[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interface, device or unit, and can be electrical, mechanical or other forms.

[0103] In addition, the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0104] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0105] The application also provides a vehicle comprising the intelligent driving domain controller described in the foregoing embodiments.

[0106] The above only is the embodiment of the application, and does not use to limit the protection scope of the application, for the person skilled in the art, the application can have various changes and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A vehicle intersection passing method, characterized by, The method comprises the following steps: acquiring map information of a target vehicle at a current position, vehicle information around the target vehicle, and traffic signal lamp state information in front of the target vehicle, wherein the vehicle information comprises one of no vehicle, temporary stop and waiting, straight driving, and turning, the traffic signal lamp state information comprises first state information and second state information, the first state information is used for indicating vehicle passing, the second state information is used for indicating vehicle prohibition, the current position of the target vehicle is located at an intersection, and the intersection has not been passed; judging whether a visual field shielding judgment needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information; if the visual field shielding judgment needs to be performed, determining a visual field shielding condition of the target vehicle; determining a safe driving strategy of the target vehicle according to the visual field shielding condition.

2. The method of claim 1, wherein, The judging whether the visual field shielding judgment needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information comprises: determining, according to the map information, that the target vehicle is located at a rightmost lane, the vehicle information comprises first vehicle information of a lane left to the target vehicle, and the traffic signal lamp state information comprises a turning signal lamp of a turning lane in front of the target vehicle, the turning lane corresponds to a same turning direction as a straight driving direction of the target vehicle; if the first vehicle information is temporary stop and waiting, and the traffic signal lamp state information is any state, performing the visual field shielding judgment, otherwise, not performing the visual field shielding judgment, wherein the visual field shielding judgment comprises whether there is visual field shielding on the left side of the target vehicle.

3. The method of claim 1, wherein, The judging whether the visual field shielding judgment needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information comprises: determining, according to the map information, that the target vehicle is located at a middle lane, the vehicle information comprises first vehicle information of a lane left to the target vehicle and second vehicle information of a lane right to the target vehicle, and the traffic signal lamp state information comprises a turning signal lamp of a turning lane in front of the target vehicle, the turning lane corresponds to a same turning direction as a straight driving direction of the target vehicle; if the first vehicle information is temporary stop and waiting, and the traffic signal lamp state information is any state, performing the visual field shielding judgment, otherwise, not performing the visual field shielding judgment, wherein the visual field shielding judgment comprises whether there is visual field shielding on the left side of the target vehicle; if the second vehicle information is temporary stop and waiting, and the traffic signal lamp state information is the first state information, performing the visual field shielding judgment, otherwise, not performing, wherein the visual field shielding judgment comprises whether there is visual field shielding on the right side of the target vehicle.

4. The method of claim 1, wherein, The judging whether the visual field shielding judgment needs to be performed according to the map information, the vehicle information, and the traffic signal lamp state information comprises: According to the map information, it is determined that the target vehicle is located in the leftmost lane, the vehicle information comprises second vehicle information of a lane on the right side of the target vehicle, and the traffic signal light state information comprises a turning signal light of a turning lane in front of the target vehicle, and a turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle; If the second vehicle information is temporary parking and waiting, and the traffic signal light state information is the first state information, the visual field shielding judgment is performed, otherwise, the visual field shielding judgment is not performed, wherein the visual field shielding judgment comprises whether there is visual field shielding on the right side of the target vehicle.

5. The method of claim 1, wherein, After the map information of the target vehicle at the current position, the vehicle information around the target vehicle, and the traffic signal light state information in front of the target vehicle are obtained, the method further comprises: According to the map information, the vehicle information, and the traffic signal light state information, it is judged whether the judgment of whether there is a passing vehicle in a turning lane in front of the target vehicle needs to be performed, the turning direction corresponding to the turning lane is the same as the straight direction of the target vehicle, if so, it is determined whether there is a passing vehicle; The safety driving strategy of the target vehicle is determined according to the visual field shielding condition and the presence or absence of the passing vehicle. The safety driving strategy of the target vehicle is determined according to the visual field shielding condition and the presence or absence of the passing vehicle.

6. The method of claim 5, wherein, According to the map information, it is determined that the target vehicle is located in the leftmost lane, the traffic signal light state information comprises a turning signal light of a turning lane in front of the target vehicle, and a turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle; If the traffic signal light state information is the first state information, the judgment of whether there is a passing vehicle in a turning lane in front of the target vehicle is performed, otherwise, the judgment is not performed. According to the map information, it is determined that the target vehicle is located in the leftmost lane, the vehicle information comprises second vehicle information of a lane on the right side of the target vehicle, and the traffic signal light state information comprises a turning signal light of a turning lane in front of the target vehicle; 7. The method of claim 5, wherein, If the traffic signal light state information is the first state information, and the second vehicle information is no vehicle, temporary parking and waiting, or turning, the judgment of whether there is a passing vehicle in a turning lane in front of the target vehicle is performed, otherwise, the judgment is not performed. The method comprises: If it is judged according to the map information, the vehicle information, and the traffic signal light state information that the visual field shielding judgment does not need to be performed, it is judged whether the judgment of whether there is a passing vehicle in a turning lane in front of the target vehicle needs to be performed, the turning direction corresponding to the turning lane is the same as a straight direction of the target vehicle, if so, it is determined whether there is a passing vehicle; 8. The method of claim 1, wherein, The safety driving strategy of the target vehicle is determined according to the presence or absence of the passing vehicle. ​ ​ 9. The method according to any one of claims 1 to 8, characterized in that, The safe driving strategy is determined by the following method: if one of the following conditions is met: there is a visual field obstruction on the left side of the target vehicle, there is a visual field obstruction on the right side of the target vehicle, and there is a passing vehicle on the turning lane in front of the target vehicle, the safe driving strategy is determined to be deceleration one-gear passing; if two or more of the following conditions are met: there is a visual field obstruction on the left side of the target vehicle, there is a visual field obstruction on the right side of the target vehicle, and there is a passing vehicle on the turning lane in front of the target vehicle, the safe driving strategy is determined to be deceleration two-gear passing; otherwise, the safe driving strategy is determined to be maintaining the original vehicle speed passing.

10. An intelligent driving domain controller, characterized by, comprising: a processor, a memory and a bus, wherein the processor and the memory communicate with each other through the bus; the memory stores program instructions executable by the processor, and the processor calling the program instructions can execute the method of any one of claims 1-9.

11. A computer-readable storage medium, characterized in that, comprising: the computer readable storage medium stores computer instructions, and the computer instructions make the computer execute the method of any one of claims 1-9.

12. A computer program product, characterised in that, comprising computer program instructions, which are read and run by the processor, and execute the method of any one of claims 1-9.

13. A vehicle characterized by comprising: comprising the intelligent driving domain controller of claim 10.

Images