Vehicle driving control method, electronic equipment and storage medium

Abstract

The invention discloses a vehicle driving control method, electronic equipment and a storage medium, and the method comprises the steps: obtaining map data of a lane where a vehicle is located, and obtaining a visual perception result of the vehicle; determining driving constraint information of the vehicle according to the visual perception result and the map data; and controlling the vehicle to pass through an intersection corresponding to the lane based on the driving constraint information. Due to the fact that the visual perception result of the vehicle can contain the ground elements on the ground surface nearby the vehicle, and various elements on the ground surface of the vehicle are recorded in the map data, the driving constraint information of the vehicle can be constructed according to the visual perception result and the map data, and the vehicle is controlled to pass through the corresponding intersection through the driving constraint information. The visual perception result of the environment nearby the vehicle can be acquired in real time, so that the visual perception result and the map data can be continuously utilized to constrain vehicle driving, complete continuous correction of the vehicle position, ensure that the vehicle correctly passes through the intersection, and improve the ability of the vehicle to automatically pass through the intersection.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle driving control method, electronic equipment and storage medium. Background Art

[0002] In the field of autonomous driving, vehicles passing through intersections is a relatively difficult scenario. Due to the complex driving conditions of vehicles at intersections, there are fewer features that can be used for vehicle driving control. At the same time, due to occlusion or multipath effects, the RTK (Real Time Kinematic) or GNSS (Global Navigation Satellite System) signals are poor, making vehicle driving control very difficult.

[0003] In related solutions, IMU (Inertial Measurement Unit) and wheel speedometer are used to collect vehicle data for dead reckoning to pass through intersections. However, this method is not effective in passing through intersections, and vehicles may go to the wrong lane or jump sideways after passing through intersections. Summary of the invention

[0004] The purpose of the present application is to propose a vehicle driving control method, device, electronic device and storage medium to address the deficiencies of the above-mentioned prior art, and this purpose is achieved through the following technical solutions.

[0005] The first aspect of the present application provides a vehicle driving control method, the method comprising:

[0006] Obtaining map data of the lane where the vehicle is located, and obtaining visual perception results of the vehicle;

[0007] Determining driving constraint information of the vehicle according to the visual perception result and the map data;

[0008] The vehicle is controlled to pass through an intersection corresponding to the lane based on the driving constraint information.

[0009] A second aspect of the present application provides a vehicle driving control device, the device comprising:

[0010] A data acquisition module, used to acquire map data of the lane where the vehicle is located and to acquire visual perception results of the vehicle;

[0011] A constraint module, used for determining driving constraint information of the vehicle according to the visual perception result and the map data;

[0012] A control module is used to control the vehicle to pass through the intersection corresponding to the lane based on the driving constraint information.

[0013] The third aspect of the present application proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in the first aspect above.

[0014] The fourth aspect of the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the steps of the method described in the first aspect above.

[0015] Based on the vehicle driving control method and device described in the first and second aspects above, the present application has at least the following beneficial effects or advantages:

[0016] When a vehicle passes through an intersection, by obtaining the map data of the lane where the vehicle is located and the visual perception results of the environment near the vehicle, since the visual perception results of the vehicle will include the ground elements on the surface near the vehicle, and the map data records various elements on the surface of the vehicle, the vehicle's driving constraint information can be constructed based on the visual perception results and map data, and the driving constraint information can be used to control the vehicle to pass the corresponding intersection. Since the visual perception results of the environment near the vehicle can be obtained in real time, the visual perception results and map data can be continuously used to constrain the vehicle's driving, complete the continuous correction of the vehicle's position, ensure that the vehicle passes through the intersection correctly, and improve the vehicle's ability to automatically pass through the intersection.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a schematic diagram of an intersection scene of vehicle visual perception according to an exemplary embodiment;

[0020] Figure 2 A schematic diagram of an intersection scene on a high-precision map according to an exemplary embodiment;

[0021] Figure 3 is a flow chart of an embodiment of a vehicle driving control method according to an exemplary embodiment;

[0022] Figure 4A schematic diagram of a map element matching method according to an exemplary embodiment;

[0023] Figure 5 is a schematic diagram of lane line semantic association according to an exemplary embodiment;

[0024] Figure 6 A schematic diagram of a vehicle turning left through an intersection according to an exemplary embodiment;

[0025] Figure 7 is a schematic structural diagram of a vehicle driving control device according to an exemplary embodiment;

[0026] Figure 8 is a schematic diagram of a hardware structure of an electronic device according to an exemplary embodiment;

[0027] Fig. 9 The figure is a schematic diagram of the structure of a storage medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] 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.

[0029] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0030] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0031] In the field of autonomous driving, when a vehicle is driving on urban roads, the satellite positioning signal is blocked by buildings. The satellite positioning signal is even weaker when driving in urban tunnels or under elevated roads. If the satellite positioning signal is missing when passing through relatively large intersections, it will affect the vehicle's ability to automatically pass through the intersection.

[0032] In a prior art prior to the present application, the vehicle is controlled to pass through the intersection by performing track calculation using the vehicle operation data collected by the IMU or the wheel speed meter.

[0033] However, this method is less effective at passing intersections, as vehicles may go into the wrong lane or bounce left or right after turning left or right.

[0034] In view of this, the present application proposes a driving control method for a vehicle when passing through an intersection, so as to improve the vehicle's ability to correctly pass through an intersection under automatic driving conditions.

[0035] See also Figure 1 The intersection scene of vehicle visual perception shown in the figure can provide geometric information of ground elements such as lane lines, stop lines, crosswalk lines, surface arrows, and guide lines in the middle of the intersection. Figure 1 It can be seen that the small rectangular box represents the arrow on the ground, the three dotted lines in the middle of the intersection represent the guide line, the multiple parallel solid lines represent the lane lines, and the solid line connecting the endpoints of the multiple parallel lines represents the stop line. Figure 2 The high-precision map shown in the figure provides the intersection scene. The high-precision map can provide map elements such as lane lines, stop lines, surface arrows, and guide lines. Figure 2 It can be seen that the black rectangular frame represents the surface arrow, the black horizontal line represents the stop line, the gray line perpendicular to the black horizontal line represents the lane line, and the dotted line in the middle of the intersection represents the guide line.

[0036] It can be seen that the vehicle is aligned with the map through the vehicle's visual perception and map data, and the vehicle is constantly constrained to travel through the intersection. That is, when the vehicle passes through the intersection, by obtaining the visual perception results of the visual images of the surrounding environment collected by the vehicle, and the map data of the lane where the vehicle is located, since the visual perception results of the vehicle will include the ground elements on the surface near the vehicle, and the map data records various elements on the surface of the vehicle, the vehicle's driving constraint information can be constructed based on the visual perception results and map data, and the driving constraint information can be used to control the vehicle to pass through the corresponding intersection. Since the visual perception results of the environment near the vehicle can be obtained in real time, the visual perception results and map data can be continuously used to constrain the vehicle's travel, complete the continuous correction of the vehicle's position, ensure that the vehicle passes through the intersection correctly, and improve the vehicle's ability to automatically pass through the intersection.

[0037] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The several specific embodiments listed can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0038] Figure 3 The flowchart of a vehicle driving control method according to an exemplary embodiment is shown, and the method includes the following steps:

[0039] Step 301: Obtain the visual perception result of the vehicle.

[0040] Among them, the vehicle will collect visual images of the surrounding environment during driving. The visual image is a bird's-eye view (BEV, Birds Eye Views) synthesized from images of the surrounding environment collected by visual sensors installed at multiple positions of the vehicle. By perceiving and identifying the visual image, various ground elements contained in the image can be obtained, indicating the ground elements on the surface that the vehicle can observe.

[0041] In an embodiment of the present application, the visual perception results obtained are divided into two situations. One situation is that the visual perception results contain ground element information, and the ground elements indicated by the ground element information are surface features of the same type of map elements existing in the map data; the other situation is that the visual perception result is empty, indicating that no valid ground element information is obtained in the visual recognition.

[0042] The ground elements indicated by the valid ground element information refer to ground elements used to construct the driving constraint information of the vehicle in combination with the map data. If the visual perception result is empty, it means that there is no valid ground element information in the visual recognition result of the visual image.

[0043] Optionally, the valid ground elements included in the visual perception result may be any one or more combinations of ground features such as ground arrows, stop lines, guide lines, and lane lines. For example, assuming that the visual recognition result of the visual image includes a stop line, a traffic light pole, and a front vehicle, then the valid ground element is the stop line, and the traffic light pole and the front vehicle are not valid ground elements.

[0044] It is understandable that during the driving process of the vehicle, these effective ground features will not all appear in the visual image, but will change as the vehicle drives to different positions at the intersection. For example, when the vehicle starts to pass through the intersection, there may be ground arrows, lane lines, and stop lines behind the rear of the vehicle appearing in the visual image; when the vehicle passes through the middle of the intersection, there may be guide lines and ground arrows appearing in the visual image; after the vehicle passes through the middle of the intersection, there may be lane lines on the target lane, stop lines in front of the front of the vehicle, and ground arrows appearing in the visual image.

[0045] Taking the example that effective ground elements include four features: surface arrows, stop lines, guide lines, and lane lines, in an optional implementation, in the process of obtaining visual perception results, first identify all candidate ground elements contained in the visual image of the vehicle. Then, if the candidate ground elements include the element of a surface arrow, since the angle at which the vehicle collects environmental images is constantly changing, the shape of the perceived surface arrow will inevitably not conform to the actual shape. There will be inaccuracies in matching the shape of the surface arrow with the shape of the surface arrow in the map. Therefore, the center point of the area where the surface arrow is located in the visual image and the confidence of the center point can be obtained as the perception data of the surface arrow to improve the matching accuracy of the surface arrow. Specifically, the coordinates of the center point of the rectangular box in the area where the surface arrow is located can be fitted as ground element information.

[0046] If the candidate ground features include stop lines, there may be multiple stop lines in the visual image. In order to accurately constrain the vehicle, the target stop line closest to the vehicle is obtained, and multiple stop line sampling points and confidence levels are obtained based on the target stop line, so that the multiple stop line sampling points and confidence levels are used as the ground feature information of the stop line.

[0047] If the candidate ground features include guide lines, such features are mostly arcs in the middle of the intersection and are difficult to identify. In order to achieve accurate vehicle constraints, when the confidence of the obtained guide line is higher than the preset confidence, multiple guide line sampling points and confidences are obtained based on the guide line, and the multiple guide line sampling points and confidences are used as the ground feature information of the guide line.

[0048] If the candidate ground features include lane lines, multiple lane lines may appear in the visual image. In order to accurately constrain the vehicle, a set of target lane lines closest to the vehicle is obtained, and multiple lane line sampling points and confidence levels are obtained based on the target lane lines, so that the multiple lane line sampling points and confidence levels are used as the ground feature information of the lane lines.

[0049] It should be noted that for elements such as stop lines, guide lines and lane lines, when obtaining sampling points and confidence, sampling points can be obtained by uniformly sampling on the lines of perception output. For confidence, the confidence of the nearest neighbor point can be used for interpolation calculation.

[0050] Based on the above description, it can be known that the ground element information included in the visual perception result includes the perception point, element type, and confidence of the ground element. In addition, the ground arrow element includes a single perception point, and other element types include multiple perception points.

[0051] Step 302: Obtain map data of the lane where the vehicle is located, and determine the vehicle's driving constraint information based on the visual perception result and the acquired map data.

[0052] The map data of the lane where the vehicle is located describes the positions and shapes of all elements on the surface of the intersection corresponding to the lane and other lanes corresponding to the intersection, so it contains the description data of all map elements on the surface of the intersection. When the vehicle arrives at the intersection for initialization, the satellite positioning signal received at this time is still available, and the lane where the vehicle is located is located according to the satellite positioning signal, so as to obtain the map data of the lane.

[0053] In an optional embodiment, for the process of determining the driving constraint information of the vehicle based on the visual perception result and the map data, based on the visual perception result containing ground element information, the map elements matching the ground elements represented by the ground element information are determined in the map data, and the ground element information and the map data of the matched map elements are used to determine the driving constraint information of the vehicle; based on the visual perception result being empty, the driving constraint information of the vehicle is determined using the map data.

[0054] The driving constraint information of the vehicle is used to indicate the execution state of the vehicle. Optionally, the driving constraint information may include the vehicle position and the vehicle orientation angle.

[0055] It is understandable that when the visual perception result is empty, it means that the map data cannot be used to match the ground features. Specifically, the map data can be used to constrain vehicle driving through the track calculation method, or the execution state of the vehicle can be kept unchanged.

[0056] In an optional embodiment, the process of determining in map data a map element that matches a ground element represented by ground element information is performed by obtaining in the map data a map element of the same element type as the ground element in the visual perception result, and determining the matching map element based on the distance between the ground element and the obtained map element.

[0057] As mentioned above, the ground feature information contained in the visual perception result includes a single perception point for surface arrows and multiple perception points for ground features of other feature types. Based on this, when matching map features for ground features in the visual perception result, if the ground feature information includes a single perception point, the map feature closest to the single perception point can be obtained from the acquired map features as the matching map feature; if the ground feature information includes multiple perception points, the matching map feature can be determined based on the distance between each perception point and the acquired map feature.

[0058] Among them, after matching the ground features with the map features, the perceived features can be aligned with the features on the map.

[0059] That is to say, when matching map features, it can be regarded as basic point-line matching and point-point matching, see Figure 4 As shown, point-to-point matching refers to the matching method adopted when both ground features and map features are represented by single points. For example, if the feature type of the ground feature is a surface arrow, the distance between a single perception point representing the surface arrow and the map feature point representing the surface arrow is calculated. Point-to-line matching refers to the matching method adopted when the ground feature is represented by multiple points and the map feature is represented by a line. The distance from each perception point to the line is calculated for matching. For example, if the feature type of the ground feature is a lane line, the distance between each perception point representing the lane line and the map feature line representing the lane line is calculated.

[0060] It should be noted that since the coordinates of the perception points representing the ground elements in the visual perception results are all expressed in the vehicle coordinate system, before matching the map elements, the coordinates of the perception points contained in the ground element information need to be converted to the map coordinate system. The conversion formula (1) is as follows:

[0061]

[0062] Among them, p p2m represents the expression of the perception point in the map coordinate system, p p2v represents the expression of the perception point in the vehicle coordinate system, p v2m represents the position of the vehicle in the map coordinate system, and yaw represents the orientation angle of the vehicle in the map coordinate system. It is worth noting that when performing coordinate conversion, p v2m and yaw use the vehicle position and orientation angle in the map coordinate system obtained from the previous prediction.

[0063] In one possible implementation, in the process of determining matching map elements based on the distance between each perception point and the acquired map elements, in order to improve the matching accuracy, a target map element whose distance to each perception point is less than a preset threshold can be obtained from the acquired map elements, and the target map element can be used as the matching map element.

[0064] If there is no target map element whose distance to each perception point is less than the preset threshold, and the distance to each perception point is greater than the preset threshold and the ground element is a lane line, a semantically related lane line is determined among the lane lines of the target lane contained in the map data as the matching map element.

[0065] The traffic flow direction of the target lane is consistent with the direction of the vehicle after passing through the intersection. At some large intersections, when the vehicle passes through the middle of the intersection and perceives the lane lines and other features of the target lane, it is easy to have a large deviation from the map, resulting in the failure to match the corresponding map elements in the map. At this time, drawing on human driving experience, the lane semantic association is constructed to ensure that the corresponding map elements are matched.

[0066] In specific implementation, the perception data that the ground element obtained from the visual image is the lane line can be obtained, and by further distinguishing whether the lane line is an edge lane line or a middle lane line, the lane line belonging to the edge is semantically associated with the lane line representing the edge in the map, and then the lane line belonging to the middle is semantically associated with the lane line located in the middle of the map.

[0067] See also Figure 5 In the two deviation situations shown, the deviations between the lane lines of the target lane perceived by the vehicle's visual image and the lane lines of the target lane represented in the map are relatively large. The solid line represents the lane lines at the edge of the road, and the dotted line represents the lane lines in the middle of the road. The lane lines at the edge of the road are semantically associated according to the direction of the arrows, and the lane lines in the middle of the road are semantically associated.

[0068] In one possible implementation, in the process of determining the driving constraint information of the vehicle using ground element information and map data of matched map elements, the target weight of the ground element represented by the ground element information in the visual perception result can be determined, and then the vehicle position and the heading angle of the vehicle head can be predicted based on the ground element information, the target weight, and the map data of the matched map elements and used as the driving constraint information.

[0069] Among them, the ground features and the matched map features should be aligned in theory, but in practical applications, there is a certain gap between the two. Therefore, the vehicle can be constrained to pass through the intersection by predicting the vehicle position and vehicle head orientation angle that can minimize the gap between the two. The target weight can reflect the degree of influence of the ground feature information on the vehicle's driving constraint information. The vehicle position and vehicle head orientation angle predicted by using weights are more accurate.

[0070] In a specific embodiment, in the process of determining the target weight of the ground element represented by the ground element information in the visual perception result, the distance weight is determined according to the distance between the ground element and the vehicle, and the element weight corresponding to the element type of the ground element is obtained. Then, the target weight is obtained based on the distance weight, the element weight and the confidence contained in the ground element information.

[0071] Among them, the farther the ground element is from the vehicle, the smaller the distance weight is, which means that the perception result of the ground element is better near the vehicle. The corresponding distance weight can be set in advance for different distance ranges. And because there are two representations of ground elements, one is a single perception point representation, and the other is a multiple perception point representation, each perception point has a corresponding confidence level, so the target weight contains the weight value of each perception point.

[0072] Specifically, the weight value calculation formula of each perception point is as follows:

[0073] w=w confidence *w dis *w element (2)

[0074] Among them, w confidence represents the confidence of the perception point, w dis represents the distance weight, w element It is worth noting that the values ​​of confidence, distance weight and element weight are all between 0 and 1.

[0075] In a specific embodiment, the prediction process of the vehicle position and the vehicle head orientation angle can be performed by substituting the perception points, target weights, and map data of the matched map elements contained in the ground element information into a preset cost function, and then differentiating the cost function to obtain the vehicle position and vehicle head orientation angle that minimizes the cost value of the cost function.

[0076] The cost function is as follows:

[0077]

[0078] Among them, w pp The weight of the perception point representing the ground element represented by a single perception point, p p02m The ground element is the expression of a single perception point in the map coordinate system. Specifically, the expression of a single perception point in the vehicle coordinate system is substituted into the above formula (1). The vehicle position p in formula (1) is v2m and the vehicle heading angle yaw as the unknown to be predicted, p m0 represents the map element point that matches a single perception point in the map, w plThe weight of each perception point representing the ground element represented by multiple perception points, p p12m The expression of each perception point of the ground element in the map coordinate system is represented by substituting the expression of a single perception point in the vehicle coordinate system into the above formula (1). The vehicle position p in formula (1) is v2m and the vehicle heading angle yaw as the unknown to be predicted, p m1 Indicates the first endpoint of the map element line that the perception point matches in the map, p m2 Indicates the second endpoint of the map element line that the perception point matches in the map.

[0079] Step 303: Control the vehicle to pass through the intersection corresponding to the lane based on the driving constraint information.

[0080] Based on the description of step 302 above, it can be seen that in the cost function, the vehicle position p v2m and the vehicle orientation angle yaw as the predicted driving constraint information. Each time the vehicle obtains a frame of visual image, the cost function can be used to realize the vehicle position p v2m and the prediction of the vehicle's heading angle yaw, so that the predicted p v2m And yaw continuously completes the correction of the vehicle position.

[0081] It should be noted that see Figure 6 As shown in the figure, in a relatively large intersection scenario, when a vehicle drives to the center of the intersection, due to the limitation of perception distance, the vehicle may not perceive any valid ground elements. At this time, the visual perception result is empty, and the dead reckoning method can be used to constrain the vehicle.

[0082] At this point, the above Figure 3 In the control process shown, when a vehicle passes through an intersection, the map data of the lane where the vehicle is located and the visual perception results of the environment near the vehicle are obtained. Since the visual perception results of the vehicle will include ground elements on the surface near the vehicle, and the map data records various elements on the surface of the vehicle, the driving constraint information of the vehicle can be constructed based on the visual perception results and map data, and the driving constraint information is used to control the vehicle to pass the corresponding intersection. Since the visual perception results of the environment near the vehicle can be obtained in real time, the visual perception results and map data can be continuously used to constrain the vehicle's driving, complete the continuous correction of the vehicle's position, ensure that the vehicle passes through the intersection correctly, and improve the vehicle's ability to automatically pass through the intersection.

[0083] The execution subject of the embodiment of the present application may be an application, service, instance, software-based functional module, virtual machine (VM), container or cloud server, etc., or a hardware device (such as a server or terminal device) or hardware chip (such as CPU, GPU, FPGA, NPU, AI acceleration card or DPU) with data processing function. The device for realizing vehicle driving control can be deployed on the computing device of the application party providing the corresponding service or on the cloud computing platform providing computing power, storage and network resources. The mode of providing services to the outside world by the cloud computing platform may be IaaS (Infrastructure as a Service), PaaS (Platform as a Service), SaaS (Software as a Service) or DaaS (Data as a Service). Taking the platform providing SaaS software as a service (Software as a Service) as an example, the cloud computing platform can use its own computing resources to provide the training of the vehicle driving control model or the functional execution of the vehicle driving control module, and the specific application architecture can be built according to the service requirements. For example, the platform can provide construction services based on the above model to application parties or individuals using platform resources, and further call the above model and implement online or offline vehicle driving control functions based on vehicle driving control requests submitted by relevant clients or servers and other devices.

[0084] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0085] Corresponding to the above-mentioned embodiments of the vehicle driving control method, the present application also provides embodiments of a vehicle driving control device.

[0086] Figure 7 FIG. 1 is a schematic diagram of a vehicle driving control device according to an exemplary embodiment. The device is used to execute the vehicle driving control method provided in any of the above embodiments. Figure 7 As shown, the vehicle driving control device includes:

[0087] The data acquisition module 710 is used to acquire the map data of the lane where the vehicle is located and obtain the visual perception result of the vehicle;

[0088] A constraint module 720, configured to determine driving constraint information of the vehicle according to the visual perception result and the map data;

[0089] The control module 730 is used to control the vehicle to pass through the intersection corresponding to the lane based on the driving constraint information.

[0090] In one possible implementation, the constraint module 720 is specifically used to determine, in the map data, map elements that match the ground elements represented by the ground element information based on the visual perception result containing ground element information, and to determine the driving constraint information of the vehicle using the ground element information and the map data of the matched map elements; and to determine the driving constraint information of the vehicle using the map data based on the visual perception result being empty.

[0091] In one possible implementation, the constraint module 720 is specifically used to obtain a map element of the same element type as the ground element in the map data during the process of determining in the map data a map element that matches the ground element represented by the ground element information; and determine the matching map element based on the distance between the ground element and the obtained map element.

[0092] In one possible implementation, the constraint module 720 is specifically used to, in the process of determining the matching map elements according to the distance between the ground element and the acquired map element, obtain the map element closest to the single perception point from the acquired map elements as the matching map element according to the ground element information containing a single perception point; and determine the matching map element according to the distance between each perception point and the acquired map element according to the ground element information containing multiple perception points.

[0093] In one possible implementation, the constraint module 720 is specifically used to, in the process of determining the matching map element according to the distance between each perception point and the acquired map element, use the target map element as the matching map element based on the existence of a target map element in the acquired map elements whose distance to each perception point is less than a preset threshold; based on the distance of each perception point being greater than a preset threshold and the ground element being a lane line, determine a semantically associated lane line in the lane lines of the target lane contained in the map data as the matching map element; the traffic flow direction of the target lane is consistent with the driving direction of the vehicle after passing through the intersection.

[0094] In one possible implementation, the constraint module 720 is specifically used to determine the target weight of the ground element represented by the ground element information when determining the driving constraint information of the vehicle using the ground element information and the map data of the matched map elements; and predict the vehicle position and the vehicle head orientation angle based on the ground element information, the target weight, and the map data of the matched map elements as the driving constraint information.

[0095] In one possible implementation, the constraint module 720 is specifically used to determine the distance weight according to the distance between the ground element and the vehicle in the process of determining the target weight of the ground element represented by the ground element information; obtain the element weight corresponding to the element type of the ground element; and obtain the target weight according to the distance weight, the element weight and the confidence contained in the ground element information.

[0096] In one possible implementation, the constraint module 720 is specifically used to substitute the perception points contained in the ground element information, the target weight, and the map data of the matched map elements into a preset cost function during the process of predicting the vehicle position and the vehicle head orientation angle based on the ground element information, the target weight, and the map data of the matched map elements; and to obtain the vehicle position and the vehicle head orientation angle that minimize the cost value of the cost function by deriving the cost function.

[0097] In a possible implementation, the data acquisition module 710 is specifically used to identify candidate ground elements contained in the visual image of the vehicle during the process of acquiring the visual perception result of the vehicle; based on the candidate ground elements containing a surface arrow, obtain the center point of the area where the surface arrow is located in the visual image and the confidence of the center point as the ground element information of the surface arrow; based on the candidate ground elements containing a stop line, obtain a target stop line closest to the vehicle, obtain multiple stop line sampling points and confidences based on the target stop line, and use the multiple stop line sampling points and confidences as the ground element information of the stop line; based on the candidate ground elements containing a guide line, based on the confidence of the guide line being higher than a preset confidence, obtain multiple guide line sampling points and confidences based on the guide line, and use the multiple guide line sampling points and confidences as the ground element information of the guide line; based on the candidate ground elements containing a lane line, obtain a group of target lane lines closest to the vehicle, obtain multiple lane line sampling points and confidences based on the target lane line, and use the multiple lane line sampling points and confidences as the ground element information of the lane line.

[0098] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0099] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0100] The embodiment of the present application also provides an electronic device corresponding to the vehicle driving control method provided in the above embodiment to execute the above vehicle driving control method.

[0101] Figure 8 6 is a hardware structure diagram of an electronic device according to an exemplary embodiment, the electronic device includes: a communication interface 601, a processor 602, a memory 603 and a bus 604; wherein the communication interface 601, the processor 602 and the memory 603 communicate with each other through the bus 604. The processor 602 can execute the vehicle driving control method described above by reading and executing the machine executable instructions corresponding to the control logic of the vehicle driving control method in the memory 603. The specific content of the method is referred to the above embodiment, which will not be repeated here.

[0102] The memory 603 mentioned in this application can be any electronic, magnetic, optical or other physical storage device, and can contain storage information, such as executable instructions, data, etc. Specifically, the memory 603 can be RAM (Random Access Memory), flash memory, storage drive (such as hard disk drive), any type of storage disk (such as optical disk, DVD, etc.), or similar storage medium, or a combination thereof. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 601 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0103] The bus 604 may be an ISA bus, a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 603 is used to store programs, and the processor 602 executes the programs after receiving execution instructions.

[0104] Processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in processor 602 or an instruction in software form. The above-mentioned processor 602 can be a general-purpose processor, including a network processor (Network Processor, referred to as NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined to execute.

[0105] The electronic device provided in the embodiment of the present application and the vehicle driving control method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0106] The present application also provides a computer-readable storage medium corresponding to the vehicle driving control method provided in the above embodiment. Fig. 9 As shown, the computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the vehicle driving control method provided by any of the aforementioned embodiments will be executed.

[0107] It should be noted that examples of the computer-readable storage medium may also 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 erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0108] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the vehicle driving control method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0109] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A vehicle driving control method, characterized in that: The method comprises: Obtaining map data of the lane where the vehicle is located, and obtaining visual perception results of the vehicle; Determining driving constraint information of the vehicle according to the visual perception result and the map data; The vehicle is controlled to pass through an intersection corresponding to the lane based on the driving constraint information.

2. The method according to claim 1, characterized in that The determining, according to the visual perception result and the map data, the driving constraint information of the vehicle comprises: According to the visual perception result including ground element information, determining in the map data a map element that matches the ground element represented by the ground element information, and determining the driving constraint information of the vehicle by using the ground element information and the map data of the matched map element; According to the visual perception result being empty, the driving constraint information of the vehicle is determined using the map data.

3. The method according to claim 1, characterized in that The determining, in the map data, a map element that matches the ground element represented by the ground element information comprises: Acquire a map element of the same element type as the ground element in the map data; According to the distance between the ground element and the acquired map element, a matching map element is determined.

4. The method according to claim 3, characterized in that The determining of the matching map element according to the distance between the ground element and the acquired map element comprises: According to the ground element information including a single perception point, a map element closest to the single perception point is obtained from the obtained map elements as a matching map element; The ground element information includes a plurality of perception points, and the matching map element is determined according to the distance between each perception point and the acquired map element.

5. The method according to claim 4, characterized in that The step of determining the matching map element according to the distance between each perception point and the acquired map element comprises: According to the existence of a target map element in the acquired map elements whose distance from each perception point is less than a preset threshold, the target map element is used as a matching map element; According to the fact that the distance of each perception point is greater than a preset threshold and the ground element is a lane line, a semantically associated lane line is determined as a matching map element among the lane lines of the target lane contained in the map data; the traffic flow direction of the target lane is consistent with the driving direction of the vehicle after passing through the intersection.

6. The method according to claim 2, characterized in that The determining the driving constraint information of the vehicle by using the ground element information and the map data of the matched map elements includes: Determining a target weight of a ground element represented by the ground element information; According to the ground element information, the target weight, and the map data of the matched map elements, the vehicle position and the vehicle head orientation angle are predicted and used as driving constraint information.

7. The method according to claim 6, characterized in that The determining the target weight of the ground element represented by the ground element information includes: Determining a distance weight according to the distance between the ground element and the vehicle; Obtaining an element weight corresponding to the element type of the ground element; The target weight is obtained according to the distance weight, the element weight and the confidence contained in the ground element information.

8. The method according to claim 1, characterized in that The obtaining of the visual perception result of the vehicle includes: identifying candidate ground features contained in a visual image of the vehicle; According to the candidate ground element including a ground arrow, obtaining the center point of the area where the ground arrow is located in the visual image and the confidence of the center point as ground element information of the ground arrow; According to the candidate ground elements including a stop line, a target stop line closest to the vehicle is obtained, a plurality of stop line sampling points and confidences are obtained according to the target stop line, and the plurality of stop line sampling points and confidences are used as ground element information of the stop line; According to the candidate ground element including a guide line, according to the confidence of the guide line being higher than a preset confidence, according to the guide line, a plurality of guide line sampling points and confidences are obtained, and the plurality of guide line sampling points and confidences are used as ground element information of the guide line; According to the candidate ground elements including lane lines, a group of target lane lines closest to the vehicle are obtained, a plurality of lane line sampling points and confidences are obtained according to the target lane lines, and the plurality of lane line sampling points and confidences are used as ground element information of the lane lines.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the program to implement the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the steps of the method according to any one of claims 1 to 8.

Images