Method, device and electronic equipment for determining heading angle of autonomous vehicle

Abstract

The application discloses a heading angle determination method and device for an autonomous vehicle and electronic equipment, and the method comprises the following steps: acquiring a current vehicle tracking result, and determining whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result; if yes, acquiring a lane line detection result of a region where the target vehicle is located, including a lane line and no lane line; determining a surrounding vehicle detection result corresponding to the target vehicle, and determining an initial heading angle calculation strategy of the target vehicle according to the lane line detection result and the surrounding vehicle detection result, wherein the surrounding vehicle detection result includes a surrounding vehicle and no surrounding vehicle; and determining a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy of the target vehicle. The application can calculate a more reasonable and actual initial heading angle according to the lane line detection result and the surrounding vehicle condition, and improve the accuracy and rationality of the initial heading angle setting in different scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a heading angle determination method and device for an automatic driving vehicle and an electronic device. BACKGROUND

[0002] Currently, the tracking process at the roadside generally first detects a vehicle target in the road in 2D or 3D, and then matches and associates the detection results between different frames through a tracking matching algorithm, so as to ensure that the same target in different frames has a globally unique ID identifier according to the matching result, and to realize target tracking.

[0003] Based on the target tracking result, the historical trajectory of each tracking target can be obtained, and the heading angle of the target in the current frame can be further calculated through the historical trajectory, thereby providing data support for driving decisions and visual display at the vehicle end.

[0004] However, the calculation of the heading angle may deviate due to various situations, resulting in the inability to provide accurate data support for the vehicle end, and in a three-dimensional display scene, the vehicle suddenly changes from a certain driving angle to 0 degrees or suddenly recovers to a normal angle from a certain default angle, resulting in a turning situation of the displayed vehicle. SUMMARY

[0005] Embodiments of the present application provide a heading angle determination method, device and electronic device for an automatic driving vehicle, to improve the accuracy and rationality of the initial heading angle setting of the automatic driving vehicle.

[0006] Embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, the embodiments of the present application provide a heading angle determination method for an automatic driving vehicle, wherein the method comprises:

[0008] obtaining a current vehicle tracking result, and determining whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result;

[0009] In the case where there is a target vehicle triggering the initial heading angle calculation condition, obtaining a lane line detection result of a region where the target vehicle is located, the lane line detection result including lane lines and no lane lines;

[0010] determining a surrounding vehicle detection result corresponding to the target vehicle, and determining an initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result including surrounding vehicles and no surrounding vehicles;

[0011] determining a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle.

[0012] Optionally, the determining the initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result corresponding to the target vehicle comprises:

[0013] if the lane line detection result is that there is a lane line, determining the initial heading angle calculation strategy corresponding to the target vehicle according to the detected lane line;

[0014] if the lane line detection result is that there is no lane line, determining the initial heading angle calculation strategy corresponding to the target vehicle according to the surrounding vehicle detection result.

[0015] Optionally, the determining the initial heading angle calculation strategy corresponding to the target vehicle according to the surrounding vehicle detection result comprises:

[0016] if the surrounding vehicle detection result is that there is a surrounding vehicle, determining the initial heading angle calculation strategy corresponding to the target vehicle according to the detected surrounding vehicle;

[0017] if the surrounding vehicle detection result is that there is no surrounding vehicle, determining the reason why the target vehicle triggers the initial heading angle calculation condition, and determining the initial heading angle calculation strategy corresponding to the target vehicle according to the reason why the target vehicle triggers the initial heading angle calculation condition, wherein the reason why the target vehicle triggers the initial heading angle calculation condition comprises target tracking algorithm abnormality and target detection algorithm abnormality.

[0018] Optionally, the determining the reason why the target vehicle triggers the initial heading angle calculation condition comprises:

[0019] determining whether there is a lost vehicle according to the vehicle tracking result;

[0020] if there is a lost vehicle at present, and there is a lost vehicle in the lost vehicles which has a distance to the target vehicle satisfying a preset distance threshold, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target tracking algorithm abnormality;

[0021] otherwise, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target detection algorithm abnormality.

[0022] Optionally, the determining the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises:

[0023] if the lane line detection result is a lane line detection result, determining the positions of two lane line points according to the lane line detection result;

[0024] determining the current initial heading angle of the target vehicle according to the positions of the two lane line points.

[0025] Optionally, the determining the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises:

[0026] If the lane line detection result is a no-lane-line detection result and the surrounding vehicle detection result is a surrounding vehicle, a same-lane vehicle corresponding to the target vehicle is determined according to the distance between the surrounding vehicle and the target vehicle.

[0027] A heading angle of the same-lane vehicle is acquired, and the heading angle of the same-lane vehicle is taken as the current initial heading angle of the target vehicle.

[0028] Optionally, the determining the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises:

[0029] If the reason for the target vehicle triggering the initial heading angle calculation condition is a target tracking algorithm exception, a lost vehicle closest to the target vehicle is determined according to the distance between the lost vehicle and the target vehicle.

[0030] A heading angle of the lost vehicle closest to the target vehicle is acquired and taken as the current initial heading angle of the target vehicle.

[0031] Optionally, the determining the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises:

[0032] If the reason for the target vehicle triggering the initial heading angle calculation condition is a target detection algorithm exception, a lane line closest to the target vehicle is determined.

[0033] The current initial heading angle of the target vehicle is determined according to the positions of two lane line points on the lane line closest to the target vehicle.

[0034] In a second aspect, the embodiments of the present application further provide a heading angle determination apparatus of an autonomous vehicle, wherein the apparatus comprises:

[0035] A first acquisition unit is configured to acquire a current vehicle tracking result, and determine whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result.

[0036] A second acquisition unit is configured to acquire a lane line detection result of a region where the target vehicle is located if there is a target vehicle triggering the initial heading angle calculation condition, wherein the lane line detection result comprises a lane line and no lane line.

[0037] The first determination unit is configured to determine a surrounding vehicle detection result corresponding to the target vehicle, and determine an initial heading angle calculation strategy of the target vehicle according to the lane line detection result and the surrounding vehicle detection result.

[0038] The second determination unit is configured to determine a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy of the target vehicle.

[0039] In a third aspect, an electronic device is provided, including:

[0040] a processor; and

[0041] a memory arranged to store computer executable instructions that, when executed, cause the processor to perform any of the methods described above.

[0042] In a fourth aspect, a computer readable storage medium is provided, storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform any of the methods described above.

[0043] The above at least one technical solution adopted by the embodiments of the present application can achieve the following beneficial effects: The heading angle determination method of the autonomous vehicle according to the embodiments of the present application first acquires a current vehicle tracking result, and determines whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result. Then, in the case that there is a target vehicle triggering the initial heading angle calculation condition, a lane line detection result of a region where the target vehicle is located is acquired, the lane line detection result including a lane line and no lane line. Then, a surrounding vehicle detection result corresponding to the target vehicle is determined, and an initial heading angle calculation strategy of the target vehicle is determined according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result including a surrounding vehicle and no surrounding vehicle. Finally, a current initial heading angle of the target vehicle is determined according to the initial heading angle calculation strategy of the target vehicle. The heading angle determination method of the autonomous vehicle according to the embodiments of the present application can calculate a more reasonable and closer-to-true heading angle according to the lane line detection result and the surrounding vehicle condition when it is necessary to assign an initial heading angle to the autonomous vehicle, thereby solving the problem of large deviation of the initial heading angle setting of the vehicle in the process of being static or moving, and improving the accuracy and reasonableness of the initial heading angle setting. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0045] Figure 1 a flowchart of a method for determining a heading angle of an autonomous vehicle in an embodiment of the present application;

[0046] Figure 2 a structural diagram of a device for determining a heading angle of an autonomous vehicle in an embodiment of the present application;

[0047] Figure 3 a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be described below in conjunction with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0049] The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the drawings.

[0050] The main reasons for the deviation of the general heading angle calculation are as follows:

[0051] 1) Due to the abnormality of the target tracking algorithm, the missed detection of the detection algorithm, and the occlusion, etc., the target is lost in the tracking process, and when it appears again, it cannot be matched, thus a new ID identifier is assigned to the target. At this time, since the heading angle cannot be calculated, an initial heading angle can only be set;

[0052] 2) When the target just appears in the camera field of view, since there is not enough data to calculate the heading angle, a default initial heading angle can only be set;

[0053] 3) In the case of vehicle static, since the historical frame position is the same when the vehicle is static, the calculated heading angle is 0, but it is not actually 0.

[0054] The above situations will cause the deviation of the set heading angle from the actual situation to be large, and after the subsequent heading angle calculation is normal, the vehicle will suddenly change from a certain driving angle to 0 degrees or suddenly recover from a certain default angle to the normal angle, that is, the vehicle appears to be turning.

[0055] Based on this, the embodiments of the present application provide a method for determining a heading angle of an autonomous vehicle, as shown in Figure 1As shown, a flowchart of a method for determining a heading angle of an autonomous vehicle is provided, which includes at least the following steps S110-S140:

[0056] In step S110, a current vehicle tracking result is obtained, and whether there is a target vehicle triggering an initial heading angle calculation condition is determined according to the vehicle tracking result.

[0057] The method for determining a heading angle of an autonomous vehicle can be executed by a roadside device, which can first obtain a current vehicle tracking result. The vehicle tracking result is mainly obtained according to a target tracking matching algorithm, which can include a tracking state of the target and a position of the target in each frame, etc.

[0058] For a target detected in a current frame, the tracking state of the target can include a tracking state and a new appearance state. If the tracking state of the current target is the tracking state, it means that the target can be continuously detected and has a continuous historical trajectory, and then the heading angle can be directly calculated according to the historical trajectory, without reassignment, so this condition does not trigger the initial heading angle calculation condition. If the tracking state of the current target is the new appearance state, it means that the detection frame of the target in the current frame cannot be matched with all detection frames of the previous frame, i.e., it can be a newly appearing target, and then a new initial heading angle needs to be assigned to the target, i.e., the initial heading angle calculation condition is triggered.

[0059] It should be noted that the tracking state of the target being the new appearance state does not mean that the target is detected for the first time. For example, the target can have appeared before and been continuously detected, but the detection frame of the target in the current frame cannot be matched with the detection frame of the previous frame due to errors in the tracking matching algorithm, missed detection by the detection algorithm, or the target being blocked, etc. In any case, the heading angle of the target cannot be calculated according to the historical trajectory, and thus a new initial heading angle needs to be assigned.

[0060] In step S120, in the case where there is a target vehicle triggering the initial heading angle calculation condition, a lane line detection result of a region where the target vehicle is located is obtained, which includes lane lines and no lane lines.

[0061] If there is a target vehicle triggering the initial heading angle calculation condition among the detected targets, the lane line detection result of the region where the target vehicle is located can be further obtained, i.e., whether there is a lane line near the target vehicle is detected. The region where the target vehicle is located mainly refers to whether there is a lane line near the current position of the target vehicle, i.e., whether the target vehicle is driving in a road region with lane lines. The lane line detection result can provide a reference for setting the initial heading angle of the target vehicle.

[0062] In step S130, a surrounding vehicle detection result corresponding to the target vehicle is determined, and an initial heading angle calculation strategy corresponding to the target vehicle is determined according to the lane line detection result and the surrounding vehicle detection result. The surrounding vehicle detection result includes a surrounding vehicle or no surrounding vehicle.

[0063] When the initial heading angle of the target vehicle cannot be determined based on the lane line detection result, a surrounding vehicle detection result corresponding to the target vehicle can be further determined. The surrounding vehicle detection result can be obtained according to a vehicle tracking result. The vehicle tracking result includes the positions of all vehicles detected in the current frame. By comparing the position of the target vehicle with the positions of all vehicles, it can be determined whether there are other vehicles around the target vehicle. Of course, the specific range of the surrounding vehicle can be flexibly set according to actual conditions, and is not limited herein.

[0064] The surrounding vehicle detection result can also provide a reference for setting the initial heading angle of the target vehicle. Therefore, the initial heading angle calculation strategy corresponding to the target vehicle can be determined by combining different lane line detection results and different surrounding vehicle detection results.

[0065] In step S140, the current initial heading angle of the target vehicle is determined according to the initial heading angle calculation strategy corresponding to the target vehicle.

[0066] After the initial heading angle calculation strategy of the target vehicle in the corresponding scene is determined, the current initial heading angle of the target vehicle can be calculated by using the initial heading angle calculation strategy. Thus, the target vehicle has a more realistic and reasonable initial heading angle in the current frame.

[0067] The method for determining the heading angle of the autonomous vehicle according to the embodiments of the present application can calculate a more reasonable and more realistic heading angle according to the lane line detection result and the surrounding vehicle condition when the initial heading angle of the autonomous vehicle needs to be determined. The problem of large deviation of the initial heading angle of the vehicle in the process of being static or moving is solved, and the accuracy and reasonableness of the initial heading angle setting are improved.

[0068] In some embodiments of the present application, the initial heading angle calculation strategy corresponding to the target vehicle is determined according to the lane line detection result and the surrounding vehicle detection result corresponding to the target vehicle. If the lane line detection result is a lane line, the corresponding initial heading angle calculation strategy is determined according to the detected lane line. If the lane line detection result is no lane line, the corresponding initial heading angle calculation strategy is determined according to the surrounding vehicle detection result.

[0069] In the embodiments of the present application, when determining the initial heading angle calculation strategy of the target vehicle, the lane line detection result can be used for judgment first. If a lane line is detected at the position of the target vehicle, it indicates that the target vehicle is currently driving in a lane line region, and thus the initial heading angle of the target vehicle can be set by referring to the lane line in the region.

[0070] If no lane line is detected at the position of the target vehicle, it indicates that the target vehicle is currently driving in a lane line free region, such as the middle region of an intersection or other lane line free road section. In this case, the initial heading angle calculation strategy of the target vehicle needs to be further determined in combination with the surrounding vehicle detection result corresponding to the target vehicle.

[0071] In some embodiments of the present application, the determination of the initial heading angle calculation strategy corresponding to the surrounding vehicle detection result comprises: if the surrounding vehicle detection result is that there is a surrounding vehicle, determining the initial heading angle calculation strategy corresponding to the detected surrounding vehicle; if the surrounding vehicle detection result is that there is no surrounding vehicle, determining the reason why the target vehicle triggers the initial heading angle calculation condition, and determining the initial heading angle calculation strategy corresponding to the reason why the target vehicle triggers the initial heading angle calculation condition, wherein the reason why the target vehicle triggers the initial heading angle calculation condition comprises target tracking algorithm abnormality and target detection algorithm abnormality.

[0072] When determining the initial heading angle calculation strategy corresponding to the surrounding vehicle detection result, if other vehicles are detected around the target vehicle, these vehicles are likely to block the target vehicle because they are very close to the target vehicle and usually travel with or even parallel to the target vehicle. The driving conditions of these vehicles can provide certain reference for setting the heading angle of the target vehicle.

[0073] If no other vehicles are detected around the target vehicle, it indicates that the target vehicle is currently driving in a lane line free region and is not blocked by other vehicles. In this case, the reason why the target vehicle triggers the initial heading angle calculation condition in the lane line free region and without being blocked by other vehicles needs to be further determined, such as tracking algorithm abnormality or detection algorithm missing detection, etc. Different initial heading angle calculation strategies can be adopted according to different reasons why the initial heading angle calculation condition is triggered.

[0074] In some embodiments of the present application, the determining the reason why the target vehicle triggers the initial heading angle calculation condition comprises: determining whether there is a lost vehicle currently according to the vehicle tracking result; in the case that there is a lost vehicle currently and there is a lost vehicle in the lost vehicles that has a distance to the target vehicle satisfying a preset distance threshold, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target tracking algorithm abnormality; otherwise, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target detection algorithm abnormality.

[0075] As mentioned above, the reasons why the target vehicle triggers the initial heading angle calculation condition mainly include tracking target tracking algorithm abnormality and detection algorithm abnormality. The tracking algorithm abnormality refers to the case that the tracking algorithm does not match the detection box of the current frame corresponding to the same target with the detection box of the last frame, resulting in that the target corresponding to the detection box of the last frame is marked as lost. Therefore, whether there is a lost vehicle currently can be determined according to the target tracking state in the vehicle tracking result. If there is a lost vehicle currently, it is further needed to confirm whether the lost vehicle is caused by tracking algorithm matching abnormality.

[0076] Specifically, the position of the lost vehicle in the current frame can be compared with the position of the target vehicle detected in the current frame to determine the distance between the lost vehicle and the target vehicle. If there is a vehicle in the lost vehicles that has a distance to the target vehicle less than a preset distance threshold, it means that there is a vehicle in the lost vehicles that probably corresponds to the same target as the target vehicle detected in the current frame, but is not matched successfully due to tracking algorithm abnormality. That is, it can be considered that the vehicle is marked as a lost state due to tracking algorithm matching abnormality at this time, and thus the initial heading angle needs to be assigned again in the current frame.

[0077] The detection algorithm abnormality refers to the case without historical tracking information. In the case that there is no lost target currently or the distance between the lost target and the target vehicle is too large, it can be considered that the detection algorithm has an abnormality of missing detection, and thus the target vehicle in the current frame is considered as a newly appeared target and needs to be assigned with an initial heading angle again.

[0078] In some embodiments of the present application, the determining the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the lane line detection result is a lane line detection result, determining the positions of two lane line points according to the lane line detection result; and determining the current initial heading angle of the target vehicle according to the positions of the two lane line points.

[0079] For a lane line scene, that is, a lane line is detected near the target vehicle position, it indicates that the target vehicle is currently driving in a lane line area, and for the autonomous vehicle, the real heading angle is basically consistent with the heading angle of the lane line where it is currently located or has a small deviation, so the heading angle of the lane line where the target vehicle is located can be assigned to the target vehicle as the initial heading angle of the target vehicle.

[0080] For the calculation of the lane line heading angle, the positions of the two lane line points closest to the target vehicle position can be selected to calculate the lane line heading angle. Of course, based on the detected target vehicle position, it can be converted to the world coordinate system and matched with the high-precision map, so as to obtain the lane line data of the target vehicle position from the lane line data provided by the high-precision map, and then the lane line heading angle of the target vehicle position can be obtained.

[0081] In some embodiments of the present application, the initial heading angle of the target vehicle is determined according to the initial heading angle calculation strategy corresponding to the target vehicle, which includes: if the lane line detection result is a no-lane line detection result, and the surrounding vehicle detection result is a surrounding vehicle, the same lane vehicle corresponding to the target vehicle is determined according to the distance between the surrounding vehicle and the target vehicle; the heading angle of the same lane vehicle is obtained, and the heading angle of the same lane vehicle is taken as the initial heading angle of the target vehicle.

[0082] For a no-lane line scene, that is, no lane line is detected near the target vehicle position, it indicates that the target vehicle is currently driving in a no-lane line area, such as the middle area of an intersection or other no-lane line road section, at this time, the initial heading angle calculation strategy can be further determined in combination with the detection results of different surrounding vehicles.

[0083] If there are surrounding vehicles in the scene, i.e. other vehicles are detected within a certain distance around the target vehicle, since these vehicles are close to the target vehicle and since each road-side camera is usually mainly responsible for monitoring the road in the same driving direction, these surrounding vehicles detected from the road image are very likely to be vehicles traveling with the target vehicle, i.e. the heading angles are relatively close or have a small deviation, so the heading angles of these surrounding vehicles can provide a great reference for the setting of the initial heading angle of the target vehicle. Of course, in order to improve the accuracy and reasonableness of the setting of the initial heading angle as much as possible, a relatively more optimal surrounding vehicle can be determined based on the distance between the surrounding vehicle and the target vehicle, for example, the vehicle closest to the target vehicle, which is usually the vehicle traveling with the target vehicle, can be selected, and the heading angle of the vehicle traveling with the target vehicle can be directly assigned to the target vehicle. If the determined vehicle traveling with the target vehicle is also a vehicle that needs to be re-assigned an initial heading angle, the heading angle of the second closest vehicle can be selected to be assigned to the target vehicle.

[0084] For distance calculation, the positions of the detection boxes of each vehicle detected in the image can be first converted to the world coordinate system through a transformation relationship calibrated in advance, and then the position coordinates in the world coordinate system are used to calculate the distance, so as to avoid the error based on image position calculation and ensure the calculation accuracy.

[0085] In some embodiments of the present application, the determination of the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the reason for triggering the initial heading angle calculation condition of the target vehicle is target tracking algorithm anomaly, determining the lost vehicle closest to the target vehicle according to the distance between the lost vehicle and the target vehicle; obtaining the heading angle of the lost vehicle closest to the target vehicle and taking it as the current initial heading angle of the target vehicle.

[0086] For the case where no lane line and other vehicle are detected around the target vehicle, it is indicated that the target vehicle is very likely to travel in an area without lane line and occlusion. There are mainly two reasons for the target vehicle to need to re-set the initial heading angle in this scenario, i.e. target tracking algorithm anomaly and target detection algorithm anomaly.

[0087] If it is judged that the reason why the target vehicle triggers the initial heading angle calculation condition is that the target tracking algorithm is abnormal, it indicates that there is a lost vehicle close to the target vehicle at present, and the lost vehicle closest to the target vehicle can be selected at this time. Since the vehicle tracking result contains the detection box position of each detected target, the predicted box position of the lost target in the current frame can be predicted through Kalman filtering, and the lost vehicle closest to the target vehicle can be determined by matching the predicted box position of the lost target in the current frame with the detection box position of the target vehicle. Here, the positions are also converted to the world coordinate system before comparison.

[0088] After determining the lost vehicle closest to the target vehicle, it is highly probable that the position of the lost vehicle in the current frame is the detection box position of the target vehicle in the current frame, that is, the lost vehicle and the target vehicle are the same target, but the target is not matched due to abnormal tracking algorithm. Therefore, the heading angle of the lost vehicle can be directly assigned to the target vehicle. Since the historical trajectory of the lost vehicle before being lost can be determined, the corresponding heading angle can also be calculated, and the heading angle change after being just lost will not be too large. Therefore, the heading angle of the lost vehicle can be obtained according to the historical tracking data.

[0089] In some embodiments of the present application, the initial heading angle of the target vehicle is determined according to the initial heading angle calculation strategy corresponding to the target vehicle, which includes: if the reason why the target vehicle triggers the initial heading angle calculation condition is that the target detection algorithm is abnormal, determining the lane line closest to the target; and determining the current initial heading angle of the target vehicle according to the positions of two lane line points on the lane line closest to the target.

[0090] If it is judged that the reason why the target vehicle triggers the initial heading angle calculation condition is that the target detection algorithm is abnormal, it indicates that the target detection algorithm has missed detection, but the detection algorithm will not miss detection for a long time, but only miss detection for one or two frames occasionally, for example, when the vehicle just drives out of the stop line. Therefore, the lane line closest to the target vehicle can be detected when the vehicle is still away from the lane line area, and the heading angle can be calculated according to the positions of the two lane line points closest to the target vehicle on the lane line, as the initial heading angle of the target vehicle.

[0091] The present application also provides a heading angle determination device 200 for an autonomous vehicle, as shown in Figure 2 The structure schematic diagram of the heading angle determination device for the autonomous vehicle in the present application is provided, and the device at least includes a first acquisition unit 210, a second acquisition unit 220, a first determination unit 230, and a second determination unit 240, wherein:

[0092] The first obtaining unit 210 is configured to obtain a current vehicle tracking result, and determine whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result.

[0093] The second obtaining unit 220 is configured to, in a case where there is the target vehicle triggering the initial heading angle calculation condition, obtain a lane line detection result of a region where the target vehicle is located, the lane line detection result including a lane line and no lane line.

[0094] The first determining unit 230 is configured to determine a surrounding vehicle detection result corresponding to the target vehicle, and determine an initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result including a surrounding vehicle and no surrounding vehicle.

[0095] The second determining unit 240 is configured to determine a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle.

[0096] In some embodiments of the present application, the first determining unit 230 is specifically configured to: if the lane line detection result is a lane line, determine a corresponding initial heading angle calculation strategy according to the detected lane line; and if the lane line detection result is no lane line, determine a corresponding initial heading angle calculation strategy according to the surrounding vehicle detection result.

[0097] In some embodiments of the present application, the first determining unit 230 is specifically configured to: if the surrounding vehicle detection result is a surrounding vehicle, determine a corresponding initial heading angle calculation strategy according to the detected surrounding vehicle; and if the surrounding vehicle detection result is no surrounding vehicle, determine a reason why the target vehicle triggers the initial heading angle calculation condition, and determine a corresponding initial heading angle calculation strategy according to the reason why the target vehicle triggers the initial heading angle calculation condition, the reason why the target vehicle triggers the initial heading angle calculation condition including a target tracking algorithm exception and a target detection algorithm exception.

[0098] In some embodiments of the present application, the first determining unit 230 is specifically configured to: determine whether there is a lost vehicle currently according to the vehicle tracking result; in a case where there is a lost vehicle currently, and there is a lost vehicle in the lost vehicle and a distance between the lost vehicle and the target vehicle satisfies a preset distance threshold, determine that a reason why the target vehicle triggers the initial heading angle calculation condition is a target tracking algorithm exception; otherwise, determine that the reason why the target vehicle triggers the initial heading angle calculation condition is a target detection algorithm exception.

[0099] In some embodiments of the present application, the second determining unit 240 is specifically configured to: if the lane line detection result is a lane line detection result, determine the positions of two lane line points according to the lane line detection result; and determine the initial heading angle of the target vehicle according to the positions of the two lane line points.

[0100] In some embodiments of the present application, the second determining unit 240 is specifically configured to: if the lane line detection result is a lane line detection result, determine the positions of two lane line points according to the lane line detection result; and determine the initial heading angle of the target vehicle according to the positions of the two lane line points.

[0101] In some embodiments of the present application, the second determining unit 240 is specifically configured to: if the lane line detection result is a lane line detection result, determine the positions of two lane line points according to the lane line detection result; and determine the initial heading angle of the target vehicle according to the positions of the two lane line points.

[0102] In some embodiments of the present application, the second determining unit 240 is specifically configured to: if the lane line detection result is a lane line detection result, determine the positions of two lane line points according to the lane line detection result; and determine the initial heading angle of the target vehicle according to the positions of the two lane line points.

[0103] It can be understood that the above-mentioned heading angle determination device of the autonomous vehicle can realize each step of the heading angle determination method of the autonomous vehicle provided in the foregoing embodiments, and the related explanations about the heading angle determination method of the autonomous vehicle are all applicable to the heading angle determination device of the autonomous vehicle, which will not be repeated here.

[0104] Figure 3 FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 3 At the hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The memory can include a memory such as a random-access memory (RAM), and can also include a non-volatile memory such as at least one disk memory. Of course, the electronic device can also include other hardware required by the business.

[0105] The processor, the network interface and the memory can be connected with each other through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 222>Only one bidirectional arrow is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0106] The memory is used to store programs. Specifically, the program can include program code including computer operation instructions. The memory can include an internal memory and a non-volatile memory, and provide instructions and data for the processor.

[0107] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs, and forms a heading angle determination device of an autonomous vehicle at a logical level. The processor executes the program stored in the memory, and is specifically used for executing the following operations:

[0108] Obtain a current vehicle tracking result, and determine whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result;

[0109] In the case where there is a target vehicle triggering the initial heading angle calculation condition, obtain a lane line detection result of a region where the target vehicle is located, the lane line detection result including a lane line and no lane line;

[0110] Determine a surrounding vehicle detection result corresponding to the target vehicle, and determine an initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result including a surrounding vehicle and no surrounding vehicle;

[0111] Determine a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle.

[0112] The above as described in the present application Figure 1The method performed by the heading angle determination apparatus of the autonomous vehicle disclosed in the embodiments can be applied in a processor or implemented by the processor. The processor can be an integrated circuit chip with processing capability. In the implementation process, each step of the above method can be completed by integrated logic circuits in hardware or instructions in software form in the processor. The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or 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. Each method, step and logic block disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

[0113] The electronic device can further execute Figure 1 the method performed by the heading angle determination apparatus of the autonomous vehicle in the embodiments, and implement the functions of the heading angle determination apparatus of the autonomous vehicle in the Figure 1 embodiments. The embodiments of the present application will not be described here.

[0114] The embodiments of the present application further propose a computer readable storage medium storing one or more programs, the one or more programs including instructions capable of causing an electronic device including a plurality of applications to execute Figure 1 the method performed by the heading angle determination apparatus of the autonomous vehicle in the embodiments, and specifically for executing

[0115] obtaining a current vehicle tracking result, and determining whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result;

[0116] In the case where the target vehicle exists to trigger the initial heading angle calculation condition, a lane line detection result of a region where the target vehicle is located is acquired, the lane line detection result including lane lines and no lane lines;

[0117] A surrounding vehicle detection result corresponding to the target vehicle is determined, and an initial heading angle calculation strategy corresponding to the target vehicle is determined according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result including surrounding vehicles and no surrounding vehicles;

[0118] A current initial heading angle of the target vehicle is determined according to the initial heading angle calculation strategy corresponding to the target vehicle.

[0119] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0121] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0122] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 ​

[0123] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0124] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory is an example of computer readable storage media.

[0125] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0126] It should also be noted that the terms "comprising", "comprises", "including", "includes" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article or apparatus that includes the recited element.

[0127] ​​Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code thereon for use by or in connection with an instruction execution system. For the purposes of this description, a computer-usable or computer readable storage medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. The computer-usable or computer readable program code can be downloaded from an Internet website, server, or other remote source via a network or a data stream communication path. From the Internet website, server, or other remote source, the code can be downloaded into the instruction execution system, apparatus, or device where execution of the same can take place. The present application is directed to any number and type of computer-usable storage media, apparatuses, and devices self-evidently known to one of ordinary skill in the art.

[0128] The foregoing is merely illustrative of the principles of the application, and various modifications can be made by those skilled in the art. The present application is intended to embrace all such modifications and changes and aspects falling within the spirit and scope of the application.

Claims

1. A method of determining a heading angle of an autonomous vehicle, wherein, The method comprises: acquiring a current vehicle tracking result, and determining whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result; in the case that there is a target vehicle triggering the initial heading angle calculation condition, acquiring a lane line detection result of a region where the target vehicle is located, the lane line detection result comprising lane lines and no lane lines; determining a surrounding vehicle detection result corresponding to the target vehicle, and determining an initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result comprising surrounding vehicles and no surrounding vehicles; determining a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle; the determination of the initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result comprises: if the lane line detection result is lane lines, determining a corresponding initial heading angle calculation strategy according to the detected lane lines; if the lane line detection result is no lane lines, determining a corresponding initial heading angle calculation strategy according to the surrounding vehicle detection result; the determination of the corresponding initial heading angle calculation strategy according to the surrounding vehicle detection result comprises: if the surrounding vehicle detection result is surrounding vehicles, determining a corresponding initial heading angle calculation strategy according to the detected surrounding vehicles; if the surrounding vehicle detection result is no surrounding vehicles, determining a reason why the target vehicle triggers the initial heading angle calculation condition, and determining a corresponding initial heading angle calculation strategy according to the reason why the target vehicle triggers the initial heading angle calculation condition, the reason why the target vehicle triggers the initial heading angle calculation condition comprising target tracking algorithm abnormality and target detection algorithm abnormality.

2. The method of claim 1, wherein, the determination of the reason why the target vehicle triggers the initial heading angle calculation condition comprises: determining whether there is a lost vehicle at present according to the vehicle tracking result; in the case that there is a lost vehicle at present, and there is a lost vehicle in the lost vehicles which has a distance from the target vehicle satisfying a preset distance threshold, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target tracking algorithm abnormality; otherwise, determining that the reason why the target vehicle triggers the initial heading angle calculation condition is target detection algorithm abnormality.

3. The method of claim 1, wherein, the determination of the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the lane line detection result is a lane line detection result, determining the positions of two lane line points according to the lane line detection result; determining the current initial heading angle of the target vehicle according to the positions of the two lane line points.

4. The method of claim 1, wherein, the determination of the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the lane line detection result is a no lane line detection result, and the surrounding vehicle detection result is surrounding vehicles, determining a same-row vehicle corresponding to the target vehicle according to the distance between the surrounding vehicles and the target vehicle; obtain the heading angle of the same-vehicle, and take the heading angle of the same-vehicle as the current initial heading angle of the target vehicle.

5. The method of claim 1, wherein, The determining of the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the target vehicle triggers the initial heading angle calculation condition due to target tracking algorithm abnormality, determining a lost vehicle closest to the target vehicle according to the distance between the lost vehicle and the target vehicle; obtain the heading angle of the lost vehicle closest to the target vehicle, and take the heading angle as the current initial heading angle of the target vehicle.

6. The method of claim 1, wherein, The determining of the current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle comprises: if the target vehicle triggers the initial heading angle calculation condition due to target detection algorithm abnormality, determining a lane line closest to the target vehicle; determine the current initial heading angle of the target vehicle according to the positions of two lane line points on the lane line closest to the target vehicle.

7. A yaw angle determination device of an autonomous vehicle, wherein, The apparatus comprises: a first obtaining unit, configured to obtain a current vehicle tracking result, and determine whether there is a target vehicle triggering an initial heading angle calculation condition according to the vehicle tracking result; a second obtaining unit, configured to, if there is a target vehicle triggering the initial heading angle calculation condition, obtain a lane line detection result of a region where the target vehicle is located, the lane line detection result comprising a lane line and no lane line; a first determining unit, configured to determine a surrounding vehicle detection result corresponding to the target vehicle, and determine an initial heading angle calculation strategy corresponding to the target vehicle according to the lane line detection result and the surrounding vehicle detection result, the surrounding vehicle detection result comprising a surrounding vehicle and no surrounding vehicle; a second determining unit, configured to determine a current initial heading angle of the target vehicle according to the initial heading angle calculation strategy corresponding to the target vehicle; The first determining unit is specifically configured to: if the lane line detection result is a lane line, determine the corresponding initial heading angle calculation strategy according to the detected lane line; if the lane line detection result is no lane line, determine the corresponding initial heading angle calculation strategy according to the surrounding vehicle detection result; The first determining unit is specifically configured to: if the surrounding vehicle detection result is a surrounding vehicle, determine the corresponding initial heading angle calculation strategy according to the detected surrounding vehicle; if the surrounding vehicle detection result is no surrounding vehicle, determine the reason why the target vehicle triggers the initial heading angle calculation condition, and determine the corresponding initial heading angle calculation strategy according to the reason why the target vehicle triggers the initial heading angle calculation condition, the reason why the target vehicle triggers the initial heading angle calculation condition comprising target tracking algorithm abnormality and target detection algorithm abnormality. 8.An electronic device comprising: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any of claims 1-6.

9. A computer readable storage medium storing one or more programs, which when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform any of the methods of claims 1-6.

Images