Road model generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a road model generation method and device, electronic equipment and a storage medium, and relates to the field of automatic driving, and the method comprises the steps: determining a target vehicle from a plurality of vehicles according to the driving directions of the plurality of vehicles in front of a current vehicle; recording driving track information of the target vehicle; determining a characteristic value of the driving track of the target vehicle based on the recorded driving track information; determining a characteristic value of the driving track of the reference vehicle from the characteristic values of the driving track of the target vehicle as a target characteristic value; and taking the target characteristic value as a parameter of a road model, and generating a target road model based on the target characteristic value. Therefore, the road model can be established based on the characteristic value of the driving track of the reference vehicle, the road model does not need to be established through lane line information acquired by a camera, and the situation that the reliability of the generated road model is reduced due to inaccurate lane line information is avoided.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, electronic device and storage medium for generating a road model. Background Art

[0002] Nowadays, the development of intelligent driving technology has a profound impact on transportation. The division of lane lines on the road and the establishment of road models are important steps in intelligent assisted driving, and are also important technical means to ensure that intelligent driving cars are both intelligent and safe.

[0003] In related technologies, lane line information of a road is often obtained through a camera. However, when the lane line information obtained by the camera is inaccurate or the lane lines on the road are blurred, the reliability of the established road model will be reduced. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present application provides a method, device, electronic device and storage medium for generating a road model.

[0005] According to a first aspect of an embodiment of the present application, a method for generating a road model is provided, the method comprising:

[0006] Determining a target vehicle from among the multiple vehicles according to the driving directions of the multiple vehicles in front of the current vehicle;

[0007] Recording the driving trajectory information of the target vehicle;

[0008] Determining a characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information;

[0009] Determining, from the characteristic values ​​of the driving trajectory of the target vehicle, a characteristic value of the driving trajectory of the reference vehicle as a target characteristic value;

[0010] The target feature value is used as a parameter of a road model, and a target road model is generated based on the target feature value.

[0011] Optionally, determining the target vehicle from the multiple vehicles according to the driving directions of the multiple vehicles in front of the current vehicle includes:

[0012] For any vehicle among the multiple vehicles, obtaining a moving speed of the vehicle, a lateral distance between the vehicle and the current vehicle, and a moving direction of the vehicle;

[0013] In the case that the movement speed is greater than a preset speed threshold, the lateral distance is less than a preset distance threshold, and the driving direction is the same as the driving direction of the current vehicle, the vehicle is determined as the target vehicle.

[0014] Optionally, when the number of the target vehicles is at least two, recording the driving trajectory information of the target vehicles includes:

[0015] Based on the lateral distances between the at least two target vehicles and the current vehicle, obtaining driving lane information of the at least two target vehicles;

[0016] generating confidences for the at least two target vehicles based on the driving lane information of the at least two target vehicles;

[0017] Based on the confidences of the at least two target vehicles, one target vehicle is selected from the target vehicles in descending order of confidence as the current vehicle to be stored, and the driving trajectory information of the vehicle to be stored is recorded.

[0018] Optionally, the recording of the driving trajectory information of the vehicle to be stored includes:

[0019] Based on the vehicle identification of the vehicle to be stored and the latest track point coordinates of the vehicle to be stored, generating current track information of the vehicle to be stored;

[0020] If the historical trajectory information of the vehicle to be stored is stored in the designated storage area, the current trajectory information is written into a storage bit of the designated storage area when the trajectory point coordinates in the current trajectory information and the trajectory point coordinates in the historical trajectory information meet preset requirements.

[0021] Optionally, the method further comprises:

[0022] If the historical track information of the vehicle to be stored is not stored in the designated storage area, then if there is an unused storage bit in the designated storage area, writing the current track information into the unused storage bit;

[0023] In the case where there is no unused storage bit in the designated storage area, the storage bit occupied by the failed target vehicle is determined from the used storage bits as a spare storage bit; the failed target vehicle is a target vehicle whose historical trajectory information stops updating within a preset time threshold;

[0024] The current track information is written into the spare storage location.

[0025] Optionally, the trajectory information of the vehicle to be stored in the designated storage area includes: the starting identifier of the starting storage bit, the ending identifier of the ending storage bit, and the number of storage bits in the continuous storage bits occupied by the trajectory information of the vehicle to be stored in the designated storage area; the characteristic value of the driving trajectory of the target vehicle is determined based on the recorded driving trajectory information, including:

[0026] For any of the target vehicles, obtaining the start identifier, the end identifier, and the number of storage locations stored in the storage location where the stored vehicle identifier matches the vehicle identifier of the target vehicle as the target start identifier, the target end identifier, and the target number M;

[0027] Determining a target storage bit interval based on a start storage bit indicated by the target start identifier and an end storage bit indicated by the target end identifier;

[0028] Acquire the coordinates of the track points in M ​​consecutive storage bits from the storage bits in the target storage bit interval;

[0029] A fitting calculation is performed based on the acquired coordinates of the M trajectory points to obtain a characteristic value of the driving trajectory of the target vehicle.

[0030] Optionally, the designated storage area is a ring storage area, and writing the current trajectory information into a storage bit of the designated storage area includes:

[0031] When the number of continuous historical trajectory information of the target vehicle stored in each storage bit in the annular storage area is equal to the total number of storage bits in the annular storage area, the current trajectory information is written into the starting storage bit of the annular storage area, and the starting identifier and the ending identifier stored in each storage bit are updated.

[0032] Optionally, the characteristic value includes a slope and a curvature, and determining the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value includes:

[0033] In a case where the current vehicle is in a road keeping state, for any of the target vehicles, determining a similarity between the driving trajectory of the target vehicle and an expected trajectory based on a slope and a curvature of the driving trajectory of the target vehicle;

[0034] Determine the target vehicle with the greatest corresponding similarity as the reference vehicle, and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value;

[0035] Alternatively, when the current vehicle is in a lane-changing state, based on the lateral distances between each target vehicle and the current vehicle, the target vehicle with the smallest corresponding lateral distance is determined as the reference vehicle; and the characteristic value of the driving trajectory of the reference vehicle is determined as the target characteristic value.

[0036] According to a second aspect of an embodiment of the present application, a device for generating a road model is provided, the device comprising:

[0037] A first determination module, configured to determine a target vehicle from a plurality of vehicles in front of a current vehicle according to the driving directions of the plurality of vehicles;

[0038] A first recording module, used to record the driving track information of the target vehicle;

[0039] A second determination module, used to determine a characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information;

[0040] A third determination module is used to determine the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value;

[0041] The first generating module is used to use the target feature value as a parameter of the road model and generate a target road model based on the target feature value.

[0042] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including:

[0043] processor;

[0044] a memory for storing instructions executable by the processor;

[0045] The processor is configured to execute the instructions to implement a method for generating a road model as described in the first aspect of an embodiment of the present application.

[0046] According to the fourth aspect of the embodiment of the present application, a computer storage medium is provided. When the instructions in the computer storage medium are executed by the processor of an electronic device, the electronic device can execute the method for generating a road model described in the first aspect of the embodiment of the present application.

[0047] According to a fifth aspect of the present application, a vehicle is provided, comprising a device for generating a road model as described in the second aspect of the present application.

[0048] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0049] The present application determines a target vehicle from multiple vehicles according to the driving directions of multiple vehicles in front of the current vehicle; records the driving trajectory information of the target vehicle; determines the characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information; determines the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value; uses the target characteristic value as a parameter of the road model, and generates a target road model based on the target characteristic value. In this way, the characteristic value of the driving trajectory of the reference vehicle can be determined by judging the driving trajectory of the target vehicle, and then the target road model is established with the driving trajectory of the reference vehicle as a reference. In this way, the road model can be established based on the characteristic value of the driving trajectory of the reference vehicle, without the need to establish the road model through the lane line information obtained by the camera, thereby avoiding the situation where the reliability of the generated road model is reduced due to inaccurate lane line information. Therefore, the embodiment of the present application can provide a stable and reliable model basis for the autonomous driving vehicle traveling on the public road when the lane line information obtained by the camera is inaccurate or the lane line is blurred. In addition, since the driving trajectory information of the vehicle traveling in front of the current vehicle is recorded, the real-time performance of the road model can be improved to a certain extent, so that the road model can be updated according to the real-time status.

[0050] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] Figure 1 is a flowchart of a method for generating a road model according to an exemplary embodiment;

[0053] Figure 2 is a schematic diagram of a road model according to an exemplary embodiment;

[0054] Figure 3 is a schematic diagram of a ring storage area according to an exemplary embodiment;

[0055] Figure 4 is a flowchart of a method for storing current trajectory information according to an exemplary embodiment;

[0056] Figure 5 It is a block diagram of a device for generating a road model according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0058] Figure 1 is a flowchart of a method for generating a road model according to an exemplary embodiment. Figure 1 As shown, the following steps are included.

[0059] Step 101: Determine a target vehicle from among multiple vehicles according to the driving directions of the multiple vehicles in front of the current vehicle.

[0060] In an embodiment of the present application, the driving directions of multiple vehicles in front of the current vehicle can be judged by a forward camera and / or sensor to obtain the driving directions of multiple vehicles, and the vehicles in the multiple vehicles whose driving directions are in the same direction as the current vehicle are determined as target vehicles. Among them, the target vehicle is one or more vehicles in front of the current vehicle whose front direction is in the same direction as the current vehicle and are traveling. Exemplarily, the scene in front of the current vehicle can be photographed by a camera, and the driving direction of the vehicle in front can be judged based on the photographed picture, such as judging based on whether the front or rear of the vehicle is shown in the picture. The distance between the current vehicle and the moving target in front can also be measured by a millimeter-wave radar, and the driving direction of the current vehicle can be judged based on the distance value. In a possible implementation, before determining the target vehicle, all targets in front of the current vehicle can also be judged by a forward camera, and invalid targets such as pedestrians, obstacles, and stationary vehicles in front of the current vehicle can be screened out.

[0061] Step 102: Record the driving trajectory information of the target vehicle.

[0062] In an embodiment of the present application, the driving trajectory information may include the coordinates of the trajectory points of the target vehicle, and a continuous driving trajectory of the target vehicle may be obtained based on the coordinates of multiple trajectory points. Exemplarily, after determining the target vehicle, the position of the first trajectory point of the target vehicle may be obtained for the first time, and the position may be set as the origin coordinate of the target vehicle. In the subsequent process of obtaining the trajectory points of the target vehicle, the coordinates of the obtained trajectory points are all absolute coordinate values ​​with the first trajectory point as the origin. The coordinates of the trajectory points may be obtained by using a sensor to obtain the relative distance between the current vehicle and the target vehicle, and based on the coordinate conversion formula, the relative coordinates may be converted into absolute coordinates to obtain the coordinates corresponding to the trajectory points of the target vehicle.

[0063] Step 103: Determine a characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information.

[0064] In an embodiment of the present application, based on the coordinates of the trajectory points in the driving trajectory information of any target vehicle, the characteristic value of the driving trajectory of the target vehicle is calculated. The characteristic value may include the curvature and slope of the driving trajectory, which is used to characterize the degree of deviation of the driving trajectory of the target vehicle from a straight line and the degree of inclination.

[0065] Step 104: Determine a characteristic value of the driving trajectory of a reference vehicle from the characteristic values ​​of the driving trajectory of the target vehicle as a target characteristic value.

[0066] In the embodiment of the present application, the driving trajectory of the reference vehicle can be the optimal driving trajectory for establishing the road model, that is, the reference vehicle is determined based on the characteristic value of the driving trajectory, so the road model established based on the driving trajectory of the reference vehicle is more real and reliable. The optimal driving trajectory is determined from the driving trajectory of the target vehicle, and the characteristic value corresponding to the optimal driving trajectory is used as the target characteristic value.

[0067] Step 105: Use the target feature value as a parameter of a road model, and generate a target road model based on the target feature value.

[0068] In an embodiment of the present application, the target feature value may include a target slope and a target curvature. The target slope and the target curvature are used as parameters of the LR and RL lane lines of the road model to generate the lane lines on both sides of the current vehicle body. Then, based on the road width, the target slope and the target curvature are used as parameters of the LL and RR lane lines of the road model to generate the left adjacent lane line of the left lane line of the current vehicle and the right adjacent lane line of the right lane line of the current vehicle. Among them, LR represents the left lane line of the lane on the road (i.e., the lane on which the current vehicle is traveling), L2 represents the right lane line of the lane on the road (i.e., the lane on which the current vehicle is traveling), LL represents the left adjacent lane line based on the left lane line, and the right adjacent lane line based on the right lane line. Exemplarily, the road width can be 2.5 meters. The target road model generated based on the target feature value includes the following: Figure 2 The LR, RL, LL and RR lane lines are shown, and the three lanes are divided by the LR, RL, LL and RR lane lines.

[0069] In summary, the present application determines the target vehicle from multiple vehicles according to the driving directions of multiple vehicles in front of the current vehicle; records the driving trajectory information of the target vehicle; determines the characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information; determines the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value; uses the target characteristic value as a parameter of the road model, and generates the target road model based on the target characteristic value. In this way, the characteristic value of the driving trajectory of the reference vehicle can be determined by judging the driving trajectory of the target vehicle, and then the target road model is established with the driving trajectory of the reference vehicle as a reference. In this way, a road model can be established based on the characteristic value of the driving trajectory of the reference vehicle, without the need to establish a road model through the lane line information obtained by the camera, thereby avoiding the situation where the reliability of the generated road model is reduced due to inaccurate lane line information. Therefore, the embodiment of the present application can provide a stable and reliable model basis for autonomous driving vehicles traveling on public roads when the lane line information obtained by the camera is inaccurate or the lane line is blurred. Furthermore, since the driving trajectory information of the vehicle traveling in front of the current vehicle is recorded, the real-time performance of the road model can be improved to a certain extent, so that the road model can be updated according to the real-time status.

[0070] Optionally, step 101 may include the following steps:

[0071] Step 1011: For any vehicle among the multiple vehicles, obtain the movement speed of the vehicle, the lateral distance between the vehicle and the current vehicle, and the driving direction of the vehicle.

[0072] In an embodiment of the present application, information of any vehicle in front of the current vehicle is acquired through a forward-facing camera or sensor to obtain the vehicle's movement speed, the lateral distance between the vehicle and the current vehicle, and the vehicle's travel direction. The lateral distance between the vehicle and the current vehicle may be the lateral distance between the center of the current vehicle and the center of the vehicle in front, or the distance between the center of the vehicle in front and the center line of the lane in which the current vehicle is traveling. Exemplarily, the vehicle's travel direction may be determined through a forward-facing camera, the vehicle's movement speed may be measured through a speed sensor, and the lateral distance between the vehicle and the current vehicle may be detected through a distance sensor.

[0073] Step 1012: When the movement speed is greater than a preset speed threshold, the lateral distance is less than a preset distance threshold, and the driving direction is the same as the driving direction of the current vehicle, determine the vehicle as the target vehicle.

[0074] In the embodiment of the present application, the target vehicle that meets the target driving state can be determined by judging the vehicle's moving speed, the lateral distance from the current vehicle, and the driving direction. When the moving speed is greater than a preset speed threshold, the lateral distance is less than a preset distance threshold, and the driving direction is the same as the driving direction of the current vehicle, the vehicle is judged to be a valid target that meets the target moving state, and is determined as the target vehicle. Among them, the preset speed threshold can be set according to demand. For example, in order to make the target vehicle always in front of the current vehicle, the preset speed threshold can be the driving speed of the current vehicle; the preset distance threshold can be set according to demand according to the road width. For example, since the reference significance of the target vehicles driving on the lane where the current vehicle is driving and the lanes on both sides is relatively large, the preset distance threshold can be set to be the same as the road width.

[0075] In an embodiment of the present application, by judging the vehicle's movement speed, lateral distance from the current vehicle, and driving direction, a target vehicle that is more meaningful for reference in establishing a road model can be determined. At the same time, since the vehicles in front of the current vehicle are screened, while ensuring the referenceability of the target vehicle, the amount of data that needs to be stored in the driving trajectory information of the target vehicle is reduced. Therefore, computing resources are saved to a certain extent in the subsequent calculation process based on the driving trajectory information.

[0076] Optionally, when the number of target vehicles is at least two, step 102 may include the following steps:

[0077] Step 1021: Acquire driving lane information of the at least two target vehicles based on the lateral distances between the at least two target vehicles and the current vehicle.

[0078] In the embodiment of the present application, the driving lane information of at least two target vehicles is judged in sequence, and for any target vehicle among the at least two target vehicles, the lateral distance between the target vehicle and the current vehicle is obtained, and the lane in which the target vehicle is traveling is judged based on the lateral distance and the first preset distance threshold, and the driving lane information is obtained. Among them, the first preset distance is obtained according to the road width, for example, the first preset distance can be equal to the road width, that is, when the lateral distance is less than the first preset distance, it indicates that the driving lane of the target vehicle is the same as the driving lane of the current vehicle or is beside the driving lane of the current vehicle, that is, an adjacent lane, and when the lateral distance is greater than the first preset distance, it indicates that the driving lane of the target vehicle is in the second adjacent lane of the driving lane of the current vehicle.

[0079] Step 1022: Generate confidence levels for the at least two target vehicles based on the driving lane information of the at least two target vehicles.

[0080] In the embodiment of the present application, after obtaining the driving lane information of at least two target vehicles, confidence is generated for at least two target vehicles based on the driving lane information. Since the target vehicle traveling on the driving lane of the current vehicle has a greater reference significance for the establishment of the road model, the confidence of the target vehicle in the same driving lane as the current vehicle is greater. In this way, in the subsequent process of storing the driving trajectory information, the driving trajectory information of the target vehicle with a large reference value can be stored preferentially. It can be understood that the confidence can be generated according to the size of the lateral distance between the target vehicle and the current vehicle, and a larger confidence can be generated for the target vehicle traveling on the driving lane of the current vehicle, and a smaller confidence can be generated for the target vehicle traveling on the lane adjacent to the driving lane of the current vehicle. In short, the confidence is used to characterize the reference value of the target vehicle.

[0081] Step 1023: Based on the confidences of the at least two target vehicles, one target vehicle is selected from the target vehicles in descending order of confidence as the current vehicle to be stored, and the driving trajectory information of the vehicle to be stored is recorded.

[0082] In the embodiment of the present application, the target vehicles are sorted according to the confidence level, and one target vehicle is selected from the target vehicles in descending order of confidence level as the current vehicle to be stored, and the driving track information of the vehicle to be stored is stored and recorded. That is, the driving track information of the target vehicle with a high confidence level is recorded first.

[0083] In an embodiment of the present application, by assigning confidence levels to target vehicles, target vehicles with high confidence levels can be processed first, and then the driving trajectory information of target vehicles with high reference values ​​can be stored first, which can improve the reliability and accuracy of the road model to a certain extent.

[0084] Optionally, step 1023 may include the following steps:

[0085] Step 1023a: Based on the vehicle identification of the vehicle to be stored and the latest track point coordinates of the vehicle to be stored, the current track information of the vehicle to be stored is generated.

[0086] In the embodiment of the present application, the current relative distance between the current vehicle and the vehicle to be stored can be collected by a camera and converted into the coordinates of the track point as the coordinates of the latest track point, and the vehicle to be stored is assigned a vehicle identification, which is a unique identification corresponding to the vehicle to be stored. The corresponding vehicle to be stored can be found according to the vehicle identification. Based on the coordinates of the track point and the vehicle identification, the current track information of the vehicle to be stored is generated.

[0087] Step 1023b: If the historical trajectory information of the vehicle to be stored is stored in the designated storage area, then when the trajectory point coordinates in the current trajectory information and the trajectory point coordinates in the historical trajectory information meet preset requirements, the current trajectory information is written into a storage bit in the designated storage area.

[0088] In the embodiment of the present application, the designated storage area may be a storage queue for temporarily storing the driving trajectory information of the target vehicle. The designated storage area may contain multiple storage bits. If the designated storage area stores the historical trajectory information of the vehicle to be stored, that is, the designated storage area has stored the driving trajectory information of the vehicle to be stored, and the vehicle to be stored is not a new target vehicle, then it is determined whether the distance between the trajectory point coordinates in the current trajectory information and the last stored trajectory point coordinates in the historical trajectory information of the target vehicle stored in the designated storage area meets the preset requirements. If it meets the preset requirements, the current trajectory information is written into a storage bit in the designated storage area; if it does not meet the preset requirements, the current trajectory information is not stored. Among them, writing into a storage bit in the designated storage area may be writing the storage bit in the order of the storage sequence of the designated storage area. The preset requirement may be that the distance between the last stored trajectory point coordinates in the historical trajectory information of the target vehicle is greater than the preset distance threshold. Exemplarily, the last stored trajectory point coordinates in the designated storage area may be obtained, and the longitudinal distance between the trajectory coordinates and the trajectory point coordinates in the current trajectory information may be calculated. If the longitudinal distance meets the preset distance threshold, it indicates that the current trajectory information meets the storage standard and needs to be stored. The preset distance threshold can be set according to the speed of the target vehicle. For example, when the target vehicle's moving speed is greater than 120 km / h, the preset distance threshold is 3 m. When the target vehicle's moving speed is less than 120 km / h, the preset distance threshold is 2 m.

[0089] It can be understood that the historical trajectory information is the driving trajectory information that has been stored in the designated storage area, and the current trajectory information is the driving trajectory information obtained at the current moment that has not yet been stored in the designated storage area. In other words, assuming that the current trajectory information of the target vehicle is obtained at the current moment and the current trajectory information is stored in the designated storage area, the current trajectory information at this time is the historical trajectory information for the next moment, and the new current trajectory information is obtained at the next moment of the current moment.

[0090] In a possible implementation, while continuously storing the collected trajectory point coordinates of the same target vehicle, the trajectory point coordinates of the target vehicle at the current moment and the historical trajectory point coordinates of the target vehicle stored in a designated storage area at the previous moment are obtained, and when the longitudinal distance between the two trajectory point coordinates is greater than 2m, the current trajectory information at the current moment is stored, otherwise, the current trajectory information is not stored.

[0091] In an embodiment of the present application, by judging the coordinates of the trajectory points in the current trajectory information and the coordinates of the trajectory points in the historical trajectory information, only the current trajectory information that meets the storage requirements can be stored, which saves storage resources to a certain extent and also makes the driving trajectory information stored in the designated storage area more valuable for reference.

[0092] Optionally, step 1023 may further include the following steps:

[0093] Step 1023c: If the historical trajectory information of the vehicle to be stored is not stored in the designated storage area, then if there is an unused storage bit in the designated storage area, write the current trajectory information into the unused storage bit.

[0094] In the embodiment of the present application, if the historical track information of the vehicle to be stored is not stored in the designated storage area, that is, the designated storage area does not contain the driving track information of the vehicle to be stored, and the vehicle to be stored is a new target vehicle, it is determined whether there is an unused storage bit in the designated storage area, that is, an empty storage bit. If there is an unused storage bit, the current track information is written into the unused storage bit. It is understandable that writing into the unused storage bit can be traversing from the starting storage bit of the designated storage area, and when an empty storage bit is found, the current track information is written into the empty storage bit.

[0095] Step 1023d: When there are no unused storage bits in the designated storage area, determine the storage bits occupied by the failed target vehicle from the used storage bits as spare storage bits; the failed target vehicle is a target vehicle whose historical trajectory information stops updating within a preset time threshold.

[0096] In an embodiment of the present application, when there are no unused storage bits in the designated storage area, that is, all storage bits in the designated storage area store driving trajectory information of one or more target vehicles, this indicates that there are no free storage bits in the designated storage area that can be written to, and therefore it is necessary to make a judgment based on the storage situation in the designated storage area to decide whether to store the current trajectory information.

[0097] In a possible implementation, one or more target vehicles stored in the designated storage area can be obtained according to the vehicle identification stored in all storage bits in the designated storage area, and based on the current track information of the target vehicle collected multiple times by the camera and the sensor within the preset time threshold or the preset number of collections, it is determined whether the designated storage area contains a target vehicle whose historical track information stops updating within the preset time threshold. For example, if there is a target vehicle in the designated storage area, and the new current track information of the target vehicle is not obtained by the camera or the sensor within 2 minutes, it can be considered that the target vehicle has been lost. The situation where the target vehicle has been lost may be as follows: it is not in front of the current vehicle, or it is in front of the current vehicle but its driving state does not meet the target driving state, and it is not the target vehicle. Among them, the preset time threshold can be set according to the needs. Or, if there is a target vehicle in the designated storage area, after the camera or the sensor collects the driving track information 60 times, the 60 driving track information does not contain the current track information of the target vehicle, then it can be considered that the target vehicle has been lost. Among them, the preset number of collections can be set according to the needs, such as the same as the number of storage bits in the designated storage area.

[0098] In the case where the historical track information of the failed target vehicle is stored in the designated storage area, the storage location occupied by the failed target vehicle in the designated storage area may be determined as a spare storage location.

[0099] Step 1023e: write the current trajectory information into the spare storage location.

[0100] In the embodiment of the present application, the current trajectory information is written into the spare storage position by traversing from the starting storage position of the designated storage area, and when the first spare storage position is traversed, the current trajectory information is written into the spare storage position, wherein the original trajectory information in the spare storage position may be cleared and then the current trajectory information is written, or the current trajectory information may be directly written to overwrite the original trajectory information. The writing into the spare storage position may also be, when there are multiple consecutive spare storage positions in the designated storage area, writing the current trajectory information into the starting spare storage position of any consecutive spare storage position.

[0101] In a possible implementation, if the historical track information of multiple failed target vehicles is stored in the designated storage area, the spare storage position of the failed target vehicle with the least number of corresponding spare storage positions may be preferentially selected for storage.

[0102] When the historical trajectory information of the failed target vehicle is not stored in the designated storage area, that is, when there is no failed target vehicle, it is considered that more driving trajectory information of valid target vehicles has been stored for subsequent reference, and the storage of the current trajectory information is abandoned.

[0103] In the embodiment of the present application, by judging whether there are unused storage bits in the designated storage area, the storage space in the designated storage area can be reasonably utilized, ensuring that the storage bits in the designated storage area are utilized to the maximum extent, and at the same time, as much driving trajectory information as possible can be stored in the storage bits for subsequent use. Furthermore, by determining the spare storage bits of the failed target vehicles in the designated storage area, the storage bits of the failed target vehicles with lower reference value in the designated storage area can be reused to release a certain amount of storage space, thereby ensuring the real-time and effectiveness of the driving trajectory information in the designated storage area.

[0104] Optionally, the trajectory information of the vehicle to be stored in the designated storage area includes: a start identifier of a starting storage position, an end identifier of an ending storage position, and the number of storage positions in the continuous storage positions occupied by the trajectory information of the vehicle to be stored in the designated storage area.

[0105] In the embodiment of the present application, the trajectory information may include a vehicle identifier, trajectory point coordinates, a starting identifier of a starting storage position, an ending identifier of an ending storage position, and the number of storage positions. The starting storage position is the first storage position in the continuous storage positions occupied by the trajectory information of the vehicle to be stored in the designated storage area, and is also the storage position where the trajectory information corresponding to this section of the driving trajectory of the target vehicle collected is first written to the designated storage area. Correspondingly, the ending storage position is the last storage position in the continuous storage positions occupied by the trajectory information of the vehicle to be stored in the designated storage area, and is also the storage position where the trajectory information corresponding to this section of the driving trajectory of the target vehicle collected is last written to the designated storage area. The number of storage positions is the number of storage positions between the starting storage position and the ending storage position. In other words, all the storage positions contained between the starting storage position and the ending storage position store the driving trajectory information of the same target vehicle, and the trajectory point coordinates in the driving trajectory information are obtained by continuous acquisition by the camera and the sensor. And since all the storage positions contained between the starting storage position and the ending storage position store the driving trajectory information of the same target vehicle, the number of storage positions is the same as the number of continuous trajectory point coordinates collected for the same target vehicle. The start storage position and the end storage position may be marked by a pointer, and the marked pointer information is used as the start mark and the end mark.

[0106] It can be understood that, when the current trajectory information of the target vehicle is written into a storage bit in a designated storage area, if the previous storage bit of the storage bit stores the historical trajectory information of the same target vehicle, then the end identifier of the end storage bit in the historical trajectory information stored in the previous storage bit and each continuous and adjacent storage bit before the previous storage bit storing the historical trajectory information of the same target vehicle and the number of storage bits are updated. For example: if the trajectory information stored in 3 continuous storage bits adjacent to the storage bit before the storage bit is the same as the target vehicle, and the starting storage bit indicated by the starting identifier stored in these 3 storage bits is 1, the ending storage bit indicated by the ending identifier is 3, and the number of storage bits is 3, then after the current trajectory information of the target vehicle is stored in the storage bit, the starting storage bit indicated by the starting identifier stored in the storage bit and the previous 3 storage bits is 1, the ending storage bit indicated by the ending identifier is 4, and the number of storage bits is 4.

[0107] Accordingly, step 103 may include the following steps:

[0108] Step 1031: For any of the target vehicles, obtain the start identifier, end identifier and number of storage locations stored in the storage location where the stored vehicle identifier matches the vehicle identifier of the target vehicle as the target start identifier, target end identifier and target number M.

[0109] In an embodiment of the present application, for any target vehicle, based on its vehicle identification, the vehicle identifications stored in each storage position of the designated storage area can be traversed to search for the vehicle identification stored in the storage position that is identical to the vehicle identification of the target vehicle. When the same vehicle identification is found, the start identification, end identification and number of storage positions stored in the storage position that is identical to the vehicle identification of the target vehicle are used as the target start identification, target end identification and target number M.

[0110] Step 1032: Determine a target storage bit interval based on the start storage bit indicated by the target start identifier and the end storage bit indicated by the target end identifier.

[0111] In the embodiment of the present application, the starting storage position indicated by the target starting mark and the ending storage position indicated by the target ending mark are determined from the designated storage area, and the starting storage position, the ending storage position, and each storage position between the starting storage position and the ending storage position are determined as the target storage interval. The target storage interval stores the driving trajectory information of the same target vehicle, and the target storage interval includes M storage positions.

[0112] Step 1033: Obtain the coordinates of the track points in M ​​consecutive storage bits from the storage bits in the target storage bit interval.

[0113] In the embodiment of the present application, the coordinates of M trajectory points stored in the M storage bits are read sequentially from the target storage bit interval.

[0114] Step 1034: Perform fitting calculation based on the acquired coordinates of the M trajectory points to obtain characteristic values ​​of the driving trajectory of the target vehicle.

[0115] In the embodiment of the present application, a quadratic fitting calculation is performed based on the obtained coordinates of the M trajectory points to obtain the quadratic coefficient of the fitted driving trajectory of the target vehicle to obtain the slope and curvature of the fitted driving trajectory. For example: the fitting calculation obtains y=C0+1x 2 +2x, where C1 can represent the slope and C2 can represent the curvature.

[0116] In the embodiment of the present application, since the designated storage area can store multiple continuous historical tracks and information of the same target vehicle, that is, the same target vehicle can correspond to multiple target storage intervals, when the first target storage interval is determined during the traversal process, the end storage position can be determined based on the end mark of the target storage interval, and the traversal can be continued with the end storage position as the starting point to determine whether there is a next target storage interval in the designated storage area. In this way, the traversal time can be reduced to a certain extent and the traversal efficiency can be improved. In the case where the designated storage area contains multiple target storage bit intervals, that is, the designated storage area stores multiple continuous historical track information of the same target vehicle, the track point coordinates in the multiple target storage bit intervals are acquired in turn to obtain multiple groups of track point coordinates, wherein one group of track point coordinates represents a section of the target vehicle's driving track. Fitting calculations are performed on the multiple groups of track point coordinates respectively to obtain the characteristic values ​​of multiple driving tracks.

[0117] In the embodiment of the present application, the storage bit storing the track information of the target vehicle can be determined from multiple storage bits through the vehicle identification, thereby improving the search efficiency. At the same time, the track point coordinates corresponding to the continuous driving track of the target vehicle in the specified storage area can be determined through the start identification and the end identification, thereby reducing the traversal time to a certain extent and improving the traversal efficiency.

[0118] Optionally, the designated storage area is a ring storage area, wherein the ring storage area may be a closed loop storage space, such as a ring buffer (Ring Buffer), such as Figure 3 As shown, Figure 3 The illustrated annular storage area comprises 10 storage locations.

[0119] Accordingly, after writing the current trajectory information into a storage bit of the designated storage area, the embodiment of the present application further includes the following steps:

[0120] Step 201: When the number of continuous historical trajectory information of the target vehicle stored in each storage bit in the annular storage area is equal to the total number of storage bits in the annular storage area, the current trajectory information is written into the starting storage bit of the annular storage area, and the starting identifier and the ending identifier stored in each storage bit are updated.

[0121] In the embodiment of the present application, when the number of continuous historical trajectory information of the target vehicle stored in each storage bit in the annular storage area is equal to the total number of storage bits in the annular storage area, it indicates that there are no unused storage bits in the annular buffer and each storage bit of the annular buffer stores a continuous historical trajectory information of the same target vehicle. Then the current trajectory information is written into the starting storage bit of the annular storage area, that is, the historical trajectory information first written into the annular storage area is overwritten. At this time, the storage bit first written into the annular storage area in the annular buffer is the second storage bit of the annular storage area, then the starting identifier and the ending identifier stored in each storage bit need to be updated, and the number of storage bits remains unchanged. Exemplarily, the starting identifier can be moved back one storage bit, and the starting storage bit indicated by the starting identifier is the second storage bit of the annular storage area, and the ending identifier can be moved back one storage bit, and the ending storage bit indicated by the ending identifier is the starting storage bit of the annular storage area. For example, if the storage capacity of the circular buffer is 60 storage bits, each storage bit of the circular buffer stores historical trajectory information of the first target vehicle. At this time, it is necessary to store the current trajectory information of the first target vehicle, and the current trajectory information is written into the starting storage bit of the circular buffer, that is, the first storage bit, and the starting mark and the ending mark in the historical trajectory information stored in each storage bit of the circular buffer are updated. Before the update, the starting storage bit indicated by the starting mark is the first storage bit, and the ending storage bit indicated by the ending mark is the 60th storage bit. After the update, the starting storage bit indicated by the starting mark is the second storage bit, and the ending storage bit indicated by the ending mark is the first storage bit.

[0122] In the embodiment of the present application, based on the closed-loop characteristics of the annular storage area, the historical trajectory information stored in the annular storage area can be updated in real time, thereby ensuring real-time performance to a certain extent.

[0123] Optionally, the characteristic value includes a slope and a curvature.

[0124] Accordingly, step 104 may include the following steps:

[0125] Step 1041: When the current vehicle is in a road keeping state, for any target vehicle, determine the similarity between the driving trajectory of the target vehicle and the expected trajectory based on the slope and curvature of the driving trajectory of the target vehicle.

[0126] In the embodiment of the present application, it can be determined whether the current vehicle is in a road keeping state or a lane changing state according to the steering wheel angle of the current vehicle. When the current vehicle is in a road keeping state, a target vehicle whose driving trajectory is closest to the target trajectory is selected as a reference vehicle. For any target vehicle, since the more similar the driving trajectory of the target vehicle is to a straight line, the more reference value it has, the expected trajectory can be a straight line with a slope and a curvature of 0, and the obtained variance value can characterize the similarity between the driving trajectory of the target vehicle and the straight line. Exemplarily, an average value can be calculated based on the slope and curvature of the driving trajectory of the target vehicle and the slope and curvature of the expected trajectory, and then a variance calculation is performed based on the slope, curvature and the average value obtained of the driving trajectory of the target vehicle, and the obtained variance value characterizes the similarity between the driving trajectory of the target vehicle and the expected trajectory. Among them, the smaller the variance value, the greater the similarity between the driving trajectory of the target vehicle and the expected trajectory.

[0127] In order to improve the accuracy of the calculation, the fitted driving trajectory can be divided into segments, and the slope and curvature of each segment of the driving trajectory can be determined based on the segmented driving trajectory. Based on the slope and curvature of each segment of the driving trajectory, an average value can be calculated, and then the variance is calculated based on the slope, curvature and the average value of the target vehicle's driving trajectory to obtain the variance value.

[0128] Step 1042: determine the target vehicle with the greatest corresponding similarity as the reference vehicle, and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value.

[0129] In an embodiment of the present application, if the similarity between the driving trajectory corresponding to the target vehicle and the expected trajectory is the greatest, indicating that the road model established based on the driving trajectory of the target vehicle as a reference is optimal, the target vehicle is determined as the reference vehicle, and the characteristic value of the driving trajectory of the reference vehicle is determined as the target characteristic value.

[0130] In the case that there are multiple continuous storage bits in the designated storage area storing historical trajectory information corresponding to the same target vehicle, it is characterized that a target vehicle corresponds to multiple continuous driving trajectories, and variance calculations are performed on each driving trajectory to obtain variance values ​​corresponding to each driving trajectory. The similarity between the driving trajectory of the target vehicle and the expected trajectory is determined based on each variance value, and the target vehicle corresponding to the driving trajectory with the greatest similarity is determined as the reference vehicle, and the characteristic value of the driving trajectory with the greatest similarity is used as the target characteristic value.

[0131] Alternatively, in step 1043, when the current vehicle is in a lane-changing state, based on the lateral distances between each target vehicle and the current vehicle, determine the target vehicle with the smallest corresponding lateral distance as the reference vehicle; and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value.

[0132] In an embodiment of the present application, when the current vehicle is in a lane-changing state, that is, the current vehicle needs to move from the current lane to an adjacent lane, the target vehicle with the smallest lateral distance to the current vehicle is determined as a reference vehicle based on the lateral distance between each target vehicle and the current vehicle. The essence of the judgment based on the lateral distance is to determine whether there is a target vehicle in the lane in which the current vehicle is traveling or whether there is a target vehicle in a lane adjacent to the lane in which the current vehicle is traveling, such as the current lane, the left lane of the current lane, or the right lane. The closer the lane in which the target vehicle is traveling is to the lane in which the current vehicle is traveling, the greater the reference value for the current vehicle. Therefore, based on the size of the lateral distance, the target vehicle with the smallest lateral distance is selected as the reference vehicle.

[0133] In an embodiment of the present application, by judging the driving state of the current vehicle, different reference vehicles can be selected for the current vehicle in different driving states, thereby establishing a road model that conforms to the driving state of the current vehicle, thereby improving the flexibility of road model establishment and at the same time improving the reliability and accuracy of the road model to a certain extent.

[0134] For example, Figure 4 A flowchart of a method for storing current trajectory information is shown. Figure 4 As shown, in the process of storing the current trajectory information of the vehicle to be stored, it is first determined whether the historical trajectory information of the vehicle to be stored is stored in the designated storage area. If so, it is determined whether the trajectory point coordinates in the current trajectory information and the trajectory point coordinates in the historical trajectory information meet the preset requirements. If they meet the preset requirements, the current trajectory information is written into the designated storage area. If they do not meet the preset requirements, the current trajectory information is not stored; if not, it is determined whether there are unused storage bits in the designated storage area. If there are unused storage bits, the current trajectory information is written into the unused storage bits. If there are no unused storage bits, it is determined whether the used storage bits include the storage bits occupied by the failed target vehicle. If they include the storage bits occupied by the failed target vehicle, the current trajectory information is written into the storage bits occupied by the failed target vehicle. If they do not include the storage bits occupied by the failed target vehicle, the current trajectory information is not stored.

[0135] Figure 5 is a block diagram of a device for generating a road model according to an exemplary embodiment. Figure 5 , the device comprises:

[0136] The first determination module 301 is used to determine a target vehicle from a plurality of vehicles in front of a current vehicle according to the driving directions of the plurality of vehicles.

[0137] The first recording module 302 is used to record the driving track information of the target vehicle.

[0138] The second determination module 303 is used to determine the characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information.

[0139] The third determination module 304 is used to determine the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value.

[0140] The first generating module 305 is configured to use the target feature value as a parameter of a road model and generate a target road model based on the target feature value.

[0141] Optionally, the first determining module 301 may include:

[0142] The first acquisition module is used to acquire, for any vehicle among the multiple vehicles, a moving speed of the vehicle, a lateral distance between the vehicle and the current vehicle, and a driving direction of the vehicle.

[0143] The first determination submodule is used to determine the vehicle as the target vehicle when the movement speed is greater than a preset speed threshold, the lateral distance is less than a preset distance threshold, and the driving direction is the same as the driving direction of the current vehicle.

[0144] Optionally, when the number of the target vehicles is at least two, the first recording module 302 may include:

[0145] The second acquisition module is used to acquire the driving lane information of the at least two target vehicles based on the lateral distance between the at least two target vehicles and the current vehicle.

[0146] The first generating submodule is used to generate confidence for the at least two target vehicles based on the driving lane information of the at least two target vehicles.

[0147] The first recording submodule is used to select a target vehicle from the target vehicles as the current vehicle to be stored based on the confidences of the at least two target vehicles and in descending order of confidence, and record the driving trajectory information of the vehicle to be stored.

[0148] Optionally, the first recording submodule may include:

[0149] The second generating submodule is used to generate the current track information of the vehicle to be stored based on the vehicle identification of the vehicle to be stored and the latest track point coordinates of the vehicle to be stored.

[0150] The first writing module is used to write the current trajectory information into a storage bit of the designated storage area if the historical trajectory information of the vehicle to be stored is stored in the designated storage area and if the trajectory point coordinates in the current trajectory information and the trajectory point coordinates in the historical trajectory information meet preset requirements.

[0151] Optionally, the first recording submodule may further include:

[0152] The second writing module is used for writing the current trajectory information into an unused storage bit if the historical trajectory information of the vehicle to be stored is not stored in the designated storage area and if there is an unused storage bit in the designated storage area.

[0153] The second determination submodule is used to determine the storage position occupied by the failed target vehicle from the used storage positions as a spare storage position when there is no unused storage position in the designated storage area; the failed target vehicle is a target vehicle whose historical trajectory information stops updating within a preset time threshold.

[0154] The third writing module is used to write the current track information into the spare storage location.

[0155] Optionally, the track information of the vehicle to be stored in the designated storage area includes: the start identifier of the start storage bit, the end identifier of the end storage bit and the number of storage bits in the continuous storage bits occupied by the track information of the vehicle to be stored in the designated storage area; the second determination module 303 may include:

[0156] The third acquisition module is used to obtain, for any of the target vehicles, the start identifier, end identifier and number of storage locations stored in the storage location where the stored vehicle identifier matches the vehicle identifier of the target vehicle as the target start identifier, target end identifier and target number M.

[0157] The third determination submodule is used to determine a target storage bit interval based on the start storage bit indicated by the target start identifier and the end storage bit indicated by the target end identifier.

[0158] The fourth acquisition module is used to acquire the coordinates of the track points in M ​​consecutive storage bits from the storage bits in the target storage bit interval.

[0159] The first calculation module is used to perform fitting calculation based on the acquired coordinates of the M trajectory points to obtain the characteristic value of the driving trajectory of the target vehicle.

[0160] Optionally, the designated storage area is a ring storage area, and the first writing module may include:

[0161] The first updating module is used to write the current trajectory information into the starting storage bit of the annular storage area when the number of continuous historical trajectory information of the target vehicle stored in each storage bit in the annular storage area is equal to the total number of storage bits in the annular storage area, and update the starting identifier and the ending identifier stored in each storage bit.

[0162] Optionally, the characteristic value includes a slope and a curvature, and the third determination module 304 may include:

[0163] The second calculation module is used to determine, for any of the target vehicles, the similarity between the driving trajectory of the target vehicle and the expected trajectory based on the slope and curvature of the driving trajectory of the target vehicle when the current vehicle is in a road keeping state.

[0164] The fourth determination submodule is used to determine the corresponding target vehicle with the greatest similarity as the reference vehicle, and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value.

[0165] Alternatively, the fifth determination submodule is used to determine, when the current vehicle is in a lane-changing state, a target vehicle with the smallest corresponding lateral distance based on the lateral distance between each target vehicle and the current vehicle, as the reference vehicle; and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value.

[0166] The present application provides a device for generating a road model, which determines a target vehicle from multiple vehicles according to the driving directions of multiple vehicles in front of the current vehicle; records the driving trajectory information of the target vehicle; determines the characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information; determines the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value; uses the target characteristic value as a parameter of the road model, and generates the target road model based on the target characteristic value. In this way, a road model can be established based on the characteristic value of the driving trajectory of the reference vehicle, without the need to establish a road model through the lane line information obtained by the camera, thereby avoiding the situation where the reliability of the generated road model is reduced due to inaccurate lane line information. Therefore, the embodiment of the present application can provide a stable and reliable model basis for an autonomous driving vehicle traveling on a public road when the lane line information obtained by the camera is inaccurate or the lane line is blurred. In addition, since the driving trajectory information of the vehicle traveling in front of the current vehicle is recorded, the real-time performance of the road model can be improved to a certain extent, so that the road model can be updated according to the real-time status.

[0167] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0168] A third embodiment of the present application relates to an electronic device, the electronic device comprising:

[0169] processor;

[0170] a memory for storing instructions executable by the processor;

[0171] The processor is configured to execute the instructions to implement the method for generating a road model as described above.

[0172] A fourth embodiment of the present application provides a computer storage medium. When instructions in the computer storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a method for generating a road model as described above.

[0173] A fifth embodiment of the present application provides a vehicle, which includes a device for generating a road model as described above.

[0174] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0175] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0176] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for generating a road model, characterized in that: The method comprises: Determining a target vehicle from among the multiple vehicles according to the driving directions of the multiple vehicles in front of the current vehicle; Recording the driving trajectory information of the target vehicle; Determining a characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information; Determining, from the characteristic values ​​of the driving trajectory of the target vehicle, a characteristic value of the driving trajectory of the reference vehicle as a target characteristic value; The target feature value is used as a parameter of a road model, and a target road model is generated based on the target feature value.

2. The method according to claim 1, characterized in that The step of determining a target vehicle from a plurality of vehicles in front of a current vehicle according to their driving directions comprises: For any vehicle among the multiple vehicles, obtaining a moving speed of the vehicle, a lateral distance between the vehicle and the current vehicle, and a moving direction of the vehicle; In the case that the movement speed is greater than a preset speed threshold, the lateral distance is less than a preset distance threshold, and the driving direction is the same as the driving direction of the current vehicle, the vehicle is determined as the target vehicle.

3. The method according to claim 2, characterized in that When the number of the target vehicles is at least two, recording the driving trajectory information of the target vehicles includes: Based on the lateral distances between the at least two target vehicles and the current vehicle, obtaining driving lane information of the at least two target vehicles; generating confidences for the at least two target vehicles based on the driving lane information of the at least two target vehicles; Based on the confidences of the at least two target vehicles, one target vehicle is selected from the target vehicles in descending order of confidence as the current vehicle to be stored, and the driving trajectory information of the vehicle to be stored is recorded.

4. The method according to claim 3, characterized in that The recording of the driving trajectory information of the vehicle to be stored includes: Based on the vehicle identification of the vehicle to be stored and the latest track point coordinates of the vehicle to be stored, generating current track information of the vehicle to be stored; If the historical trajectory information of the vehicle to be stored is stored in the designated storage area, the current trajectory information is written into a storage bit of the designated storage area when the trajectory point coordinates in the current trajectory information and the trajectory point coordinates in the historical trajectory information meet preset requirements.

5. The method according to claim 4, characterized in that The method further comprises: If the historical track information of the vehicle to be stored is not stored in the designated storage area, then if there is an unused storage bit in the designated storage area, writing the current track information into the unused storage bit; In the case where there is no unused storage bit in the designated storage area, the storage bit occupied by the failed target vehicle is determined from the used storage bits as a spare storage bit; the failed target vehicle is a target vehicle whose historical trajectory information stops updating within a preset time threshold; The current track information is written into the spare storage location.

6. The method according to claim 4 or 5, characterized in that: The track information of the vehicle to be stored in the designated storage area includes: the start identifier of the start storage bit, the end identifier of the end storage bit and the number of storage bits in the continuous storage bits occupied by the track information of the vehicle to be stored in the designated storage area; the characteristic value of the driving track of the target vehicle is determined based on the recorded driving track information, including: For any of the target vehicles, obtaining the start identifier, the end identifier, and the number of storage locations stored in the storage location where the stored vehicle identifier matches the vehicle identifier of the target vehicle as the target start identifier, the target end identifier, and the target number M; Determining a target storage bit interval based on a start storage bit indicated by the target start identifier and an end storage bit indicated by the target end identifier; Acquire the coordinates of the track points in M ​​consecutive storage bits from the storage bits in the target storage bit interval; A fitting calculation is performed based on the acquired coordinates of the M trajectory points to obtain a characteristic value of the driving trajectory of the target vehicle.

7. The method according to claim 1, characterized in that The characteristic value includes a slope and a curvature, and determining the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value includes: In a case where the current vehicle is in a road keeping state, for any of the target vehicles, determining a similarity between the driving trajectory of the target vehicle and an expected trajectory based on a slope and a curvature of the driving trajectory of the target vehicle; Determine the target vehicle with the greatest corresponding similarity as the reference vehicle, and determine the characteristic value of the driving trajectory of the reference vehicle as the target characteristic value; Alternatively, when the current vehicle is in a lane-changing state, based on the lateral distances between each target vehicle and the current vehicle, the target vehicle with the smallest corresponding lateral distance is determined as the reference vehicle; and the characteristic value of the driving trajectory of the reference vehicle is determined as the target characteristic value.

8. A device for generating a road model, characterized in that: The device comprises: A first determination module, configured to determine a target vehicle from a plurality of vehicles in front of a current vehicle according to the driving directions of the plurality of vehicles; A first recording module, used to record the driving track information of the target vehicle; A second determination module, used to determine a characteristic value of the driving trajectory of the target vehicle based on the recorded driving trajectory information; A third determination module is used to determine the characteristic value of the driving trajectory of the reference vehicle from the characteristic value of the driving trajectory of the target vehicle as the target characteristic value; The first generating module is used to use the target feature value as a parameter of the road model and generate a target road model based on the target feature value.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement a method for generating a road model as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a method for generating a road model as described in any one of claims 1 to 7.

Images