Vehicle driving control method and device

Abstract

The invention provides a vehicle driving control method and device. The method comprises: determining a distance from a vehicle to an intersection; when the distance is smaller than a first distance threshold value, camera image data and radar point cloud data are acquired; determining perception information according to the camera image data and the radar point cloud data; judging whether the vehicle needs to change lanes or not according to the sensing information; when it is determined that the vehicle needs to change lanes, lane changing path planning information is generated according to the navigation map information, the navigation positioning information and the sensing information, and the lane changing path planning information is used for controlling the vehicle to complete lane changing in front of the intersection. The method is used for achieving the effect of efficient and energy-saving lane-level lane-changing navigation by adopting a standard map.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle driving control method and device. Background Art

[0002] Intelligent driving vehicles integrate key technologies such as advanced sensor technology, data processing capabilities, artificial intelligence algorithms, and high-precision maps to achieve autonomous navigation and driving in different complex road environments.

[0003] Among the relevant intelligent driving technologies, vehicle lane changing, as a complex driving behavior, relies on the close collaboration of high-precision maps and multi-sensor fusion technology. Specifically, the intelligent driving system collects information about the surrounding environment in real time, and then uses high-precision map information to accurately match the perceived environmental data with the road model in the map, thereby achieving high-precision fusion positioning of the vehicle on the high-precision map. Based on this positioning result, the intelligent driving system makes a comprehensive judgment and decision on the vehicle's lane change based on the lane-level navigation information provided by the high-precision map, combined with traffic rules, vehicle status, and predicted behaviors of other traffic participants. Finally, according to the decision-making instructions, the vehicle is precisely controlled to perform lane change operations to ensure that the lane change process is completed safely and smoothly.

[0004] However, lane-level navigation cannot be achieved using the above method without a high-precision map. Summary of the invention

[0005] The present application provides a vehicle driving control method and device to solve the problem that lane-level navigation cannot be performed when there is no high-precision map.

[0006] In a first aspect, the present application provides a vehicle driving control method, comprising:

[0007] Determine the distance of the vehicle from the intersection;

[0008] When the distance is less than a first distance threshold, the camera image data and the radar point cloud data are obtained;

[0009] Determine perception information based on camera image data and radar point cloud data;

[0010] Determine whether the vehicle needs to change lanes based on the perceived information;

[0011] When it is determined that the vehicle needs to change lanes, lane change path planning information is generated based on the navigation map information, navigation positioning information and perception information. The lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

[0012] In some embodiments, lane change path planning information is generated based on navigation map information, navigation positioning information, and perception information, including:

[0013] Generate global positioning information based on navigation positioning information and perception information;

[0014] Generate local positioning information based on navigation map information and perception information;

[0015] Determine lane change information according to global navigation path information and navigation guidance prompt information in the navigation map information, as well as global positioning information, the lane change information including lane change speed and lane change angle;

[0016] The lane-level lane change path planning information is determined based on the perception information, local positioning information and lane change information.

[0017] In some embodiments, determining the distance of the vehicle from the intersection includes:

[0018] Predicting a first distance between the vehicle and the intersection based on navigation map information or navigation positioning information;

[0019] Determine perception information based on camera image data and radar point cloud data, the perception information including road topology;

[0020] According to the road topology, predict the second distance between the vehicle and the intersection;

[0021] According to whether there is an intersection in the road topology, the distance between the vehicle and the intersection is determined in the first distance and the second distance.

[0022] In some embodiments, according to whether there is an intersection in the road topology, determining the distance between the vehicle and the intersection in the first distance and the second distance includes:

[0023] When there is no intersection in the road topology, the first distance is determined to be the distance between the vehicle and the intersection;

[0024] When there is an intersection in the road topology, the absolute value of the difference between the first distance and the second distance is determined; when the absolute value of the difference is less than the second distance threshold, the second distance is determined to be the distance between the vehicle and the intersection; when the absolute value of the difference is greater than or equal to the second distance threshold, the first distance is determined to be the distance between the vehicle and the intersection.

[0025] In some embodiments, judging whether the vehicle needs to change lanes based on the perception information includes:

[0026] Determine the target lane according to the navigation guidance prompt information and perception information in the navigation map information;

[0027] Determine the current lane based on the perception information;

[0028] Determine whether the vehicle needs to change lanes based on the target lane and the current lane.

[0029] In some embodiments, determining the target lane according to the navigation guidance prompt information and the perception information in the navigation map information includes:

[0030] When the navigation guidance prompt information includes a recommended lane, determining the recommended lane as the target lane;

[0031] When the navigation guidance prompt information does not include a recommended lane, determining at least one passable lane based on the navigation guidance prompt information and the perception information;

[0032] According to the navigation guidance prompt information of the next intersection, a target lane is determined from at least one passable lane.

[0033] In some embodiments, before determining the distance between the vehicle and the intersection, the method further includes:

[0034] Obtain navigation map information or navigation positioning information;

[0035] Determine the distance of the vehicle from the intersection, including:

[0036] Determine the distance between the vehicle and the intersection based on the navigation guidance prompt information or navigation positioning information in the navigation map information.

[0037] In some embodiments, after determining the distance between the vehicle and the intersection, the method further includes:

[0038] When the distance between the vehicle and the intersection is greater than or equal to a first distance threshold, the vehicle is controlled to travel in the current lane.

[0039] In a second aspect, the present application provides a vehicle driving control device, comprising:

[0040] A determination module, used to determine the distance between the vehicle and the intersection;

[0041] An acquisition module, used to acquire camera image data and radar point cloud data when the distance is less than a first distance threshold;

[0042] The determination module is also used to determine the perception information based on the camera image data and the radar point cloud data;

[0043] A judgment module, used to judge whether the vehicle needs to change lanes based on the perception information;

[0044] The generation module is used to determine that when a vehicle needs to change lanes, it generates lane change path planning information based on navigation map information, navigation positioning information and perception information. The lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

[0045] In a third aspect, the present application provides an intelligent driving system, including a map module, a perception module, a positioning module, a planning module and a control module;

[0046] A map module, used to obtain navigation map information and navigation positioning information from a standard map software development kit;

[0047] A perception module is used to determine perception information based on camera image data and radar point cloud data;

[0048] A positioning module, used to generate global positioning information and local positioning information based on navigation map information, navigation positioning information and perception information;

[0049] A planning module, used for generating lane change path planning information according to navigation map information, navigation positioning information, perception information, global positioning information and local positioning information;

[0050] The control module is used to control the vehicle to complete the lane change according to the lane change path planning information.

[0051] In a fourth aspect, the present application provides an electronic device, including: a memory and a processor;

[0052] The memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory to implement the vehicle driving control method in the first aspect and any one of the embodiments of the first aspect.

[0053] In a fifth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the vehicle driving control method in the first aspect and any one of the embodiments of the first aspect is implemented.

[0054] In a sixth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the vehicle driving control method in the first aspect and any one of the embodiments of the first aspect.

[0055] The vehicle driving control method and device provided in the present application determines the distance between the vehicle and the intersection, and when the distance is less than a first distance threshold, obtains camera image data and radar point cloud data; then determines perception information based on the camera image data and radar point cloud data, and determines whether the vehicle needs to change lanes based on the perception information; when it is determined that the vehicle needs to change lanes, generates lane change path planning information based on navigation map information, navigation positioning information and perception information, thereby controlling the vehicle to complete the lane change before the intersection. Due to the combination of navigation map information and navigation positioning information of standard navigation, as well as perception information, lane-level lane change navigation can be performed without relying on high-precision maps, reducing the cost of the intelligent driving system. In addition, the method of the present application obtains camera image data and radar point cloud data to determine perception information when the distance is less than the first distance threshold, without the need to determine the perception information in real time, reducing the amount of calculation and energy consumption, and achieving energy-saving effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 It is a structural schematic diagram of an intelligent driving system in the prior art;

[0058] Figure 2 A schematic diagram of a vehicle driving scenario provided in an embodiment of the present application;

[0059] Figure 3 A flow chart of a vehicle driving control method provided in one embodiment of the present application;

[0060] Figure 4 A schematic diagram of a lane-level lane change path planning provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of the distance between a vehicle and an intersection provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of the structure of a vehicle driving control device provided in one embodiment of the present application;

[0063] Figure 7 A schematic diagram of the structure of an intelligent driving system provided in one embodiment of the present application;

[0064] Figure 8 A schematic diagram of the structure of another intelligent driving system provided in one embodiment of the present application;

[0065] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0067] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances. For example, without departing from the scope of this document, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0068] 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 relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0069] Terminology explanation:

[0070] Car computer: The abbreviation of the in-vehicle infotainment product installed in the vehicle. The car computer can functionally realize information communication between people and vehicles, and between vehicles and the outside world (cars and cars).

[0071] Transformer: A neural network model based on attention mechanism.

[0072] SOME / IP: A service-oriented communication protocol, the full name of which is Scalable service-Oriented Middleware over IP.

[0073] Intelligent driving technology is one of the core cutting-edge technologies in the current automotive field. Intelligent driving vehicles integrate advanced sensor technology, data processing capabilities, artificial intelligence algorithms, high-precision maps and other key technologies to achieve autonomous navigation and driving in different complex road environments. Among them, high-precision maps, as an important part of the intelligent driving system, provide vehicles with detailed road geometry information, traffic rules, traffic signs, obstacle distribution and other key data, which is the key basis for achieving accurate vehicle positioning, path planning and intelligent decision-making.

[0074] like Figure 1As shown in the figure, in the related technology, the intelligent driving system includes a map module, a perception module, a positioning module, a planning module and a control module. Among them, the map module integrates a high-precision map software development kit (SDK), which is used to provide high-precision map data of a preset range before and after the vehicle according to the latitude and longitude and navigation path of the vehicle in the positioning information. The perception module is used to receive sensor data such as cameras, radars, and lidars to achieve target detection (such as mobile devices, pedestrians, non-motor vehicles, etc.), semantic segmentation (obstacles, ground markings, lamp poles, signboards, passable spaces, etc.), lane line fitting, perception of obstacles and lane line relationships, target fusion and other tasks and output real-time perception results. The positioning module achieves high-precision fusion positioning by matching the lane line and pole sign information in the perception results with the lane line and pole sign information in the high-precision map, and completes the projection of the vehicle position on the high-precision map. The planning module is used to complete the selection of lane change positions and lanes based on high-precision fusion positioning information, high-precision map lane-level navigation data and chassis information, and at the same time perform obstacle avoidance planning in combination with real-time perception results. The control module outputs control instructions based on the planning results and the vehicle status information including chassis information obtained through the vehicle bus, thereby controlling the vehicle to change lanes.

[0075] However, the above lane-changing methods rely on high-precision maps for positioning and lane-changing decisions, and the coverage of high-precision maps is limited. Especially in remote areas, newly built roads or rapidly changing urban areas, the lack or lag of high-precision maps seriously affects the availability and reliability of intelligent driving systems. In addition, the update frequency of high-precision maps is difficult to meet the needs of rapidly changing road environments, resulting in limited functions of intelligent driving systems, and the high cost of high-precision maps also increases the cost of intelligent driving systems.

[0076] In response to the above problems, the present application proposes a vehicle driving control method and device. In this method, standard navigation is used for navigation planning and navigation positioning, and lane-level navigation is realized in combination with perception information, eliminating the dependence of intelligent driving on high-precision maps. In addition, in the method of the present application, perception information is obtained only when it is determined that the vehicle is within a preset distance of the intersection, without the need to obtain perception information in real time and perform lane change planning, which reduces the amount of calculation and energy consumption, and realizes efficient and energy-saving lane-level navigation using standard navigation.

[0077] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0078] Figure 2 FIG. 1 shows a schematic diagram of a vehicle driving scene provided by an embodiment of the present application. Figure 2As shown, the black triangle represents an intelligent driving vehicle. During the driving process, the distance between the vehicle and the intersection is determined in real time. Vehicle B is far away from the intersection and continues to drive in the current lane. Vehicle A is close to the intersection, so it is determined whether vehicle A needs to change lanes. The distance can be determined by the relationship between the distance and the preset threshold. Different preset thresholds can be set for roads of different grades according to needs. For example, the preset threshold can be set to 2 kilometers for expressways, and the preset threshold can be set to 1 kilometer for non-expressways. Alternatively, the preset threshold can be set to 600 meters for expressways, and the preset threshold can be set to 300 meters for non-expressways.

[0079] In this application, the electronic device is used as the execution subject to execute the vehicle driving control method of the following embodiment. Specifically, the execution subject can be a hardware device of the electronic device, or a software application that implements the following embodiment in the electronic device, or a computer-readable storage medium installed with the software application that implements the following embodiment, or a code that implements the software application of the following embodiment. The electronic device can be a vehicle terminal or an intelligent driving system installed in a vehicle.

[0080] Figure 3 FIG. 1 is a flow chart of a vehicle driving control method provided by an embodiment of the present application. Figure 3 As shown, with the electronic device as the execution subject, the method of this embodiment may include the following steps:

[0081] S101. Determine the distance between the vehicle and the intersection.

[0082] In this embodiment, the electronic device can determine the distance between the vehicle and the intersection through the navigation map information of the standard map. For example, if the navigation map information shows that the traffic light is 500 meters ahead and you need to go straight, then you can determine that the distance between the vehicle and the intersection is 500 meters. For another example, the electronic device can determine the distance between the vehicle and the intersection based on the longitude and latitude of the vehicle in the navigation positioning information and the longitude and latitude information of the intersection.

[0083] Optionally, the electronic device may first obtain navigation map information or navigation positioning information, and then determine the distance between the vehicle and the intersection based on the navigation guidance prompt information or navigation positioning information in the navigation map information.

[0084] The navigation map information may include global navigation path information and navigation guidance prompt information. The global navigation path information includes the distance between the current position of the vehicle and the intersection ahead. For example, on the display page of the global navigation path information, a bubble pops up at the intersection and displays "1 km", indicating that the distance between the current position of the vehicle and the intersection is 1 km.

[0085] The navigation guidance prompt information can be in text form or in voice broadcast form. For example, displaying on the vehicle display screen or voice broadcasting "turn left at the intersection 800 meters ahead" can determine that the distance between the vehicle and the intersection is 800 meters.

[0086] S102: When the distance is less than a first distance threshold, obtain camera image data and radar point cloud data.

[0087] In this embodiment, the camera and the radar are both deployed on the vehicle to obtain information about the vehicle's surrounding environment. The first distance threshold can be set according to the road grade or according to demand, which is not limited here.

[0088] S103: Determine perception information based on the camera image data and the radar point cloud data.

[0089] In this embodiment, the electronic device can extract feature data from the camera image data and convert the feature data into an image under a bird's-eye view, extract geometric features from the radar point cloud data and project the geometric features into a height map under a bird's-eye view, and fuse the image under the bird's-eye view and the height map under the bird's-eye view to form a bird's-eye view of the vehicle's surroundings.

[0090] The self-attention mechanism of the Transformer model is used to extract and fuse features of multimodal data in the bird's-eye view space. The Transformer can capture long-range dependencies in the input sequence, thereby modeling in space and time to improve the accuracy and robustness of perception.

[0091] Through the multi-layer Transformer encoder-decoder structure, the image in the bird's-eye view space is feature extracted and context information is integrated to output the fused feature map.

[0092] The feature map output by the Transformer is further converted into an occupancy probability map in three-dimensional space through the occupancy network. The occupancy probability map is projected in 3D to generate perception information of the road environment around the vehicle. The perception information includes the precise position and shape information of elements such as 3D road topology, moving targets, and obstacles. The 3D road topology can include road edge lines, lanes, lane lines, lane center lines, intersections, road entrance lines, stop lines, crosswalks, road arrows, traffic lights, traffic signs, etc. Moving targets include vehicles, non-motor vehicles, and pedestrians.

[0093] S104. Determine whether the vehicle needs to change lanes based on the perception information.

[0094] In this embodiment, lane changing is a preparation for smoothly passing through the intersection. Therefore, the current lane of the vehicle is determined through perception information, and then the lane of the vehicle when passing through the intersection, that is, the target lane, is determined in combination with the global navigation path information or the navigation guidance prompt information to determine whether the vehicle needs to change lanes.

[0095] For example, if the perception information determines that the vehicle is in the straight lane, and the navigation guidance prompt information is "turn left at the intersection ahead", then the target lane is the left turn lane. In this way, it can be determined that the vehicle needs to change lanes.

[0096] S105: When it is determined that the vehicle needs to change lanes, generate lane change path planning information based on the navigation map information, navigation positioning information and perception information.

[0097] Among them, the lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

[0098] In this embodiment, the navigation map information includes global navigation path information, navigation guidance prompt information and navigation status information.

[0099] The global navigation path information is generated when the navigation path is turned on or updated on the standard navigation map. The navigation path consists of several sections arranged in sequence according to the navigation direction. Each section includes section identification, shape points that make up the section, the corresponding navigation action when exiting the section, the section length, the road grade corresponding to the section, the road type corresponding to the section and other road attribute information.

[0100] Navigation guidance prompt information is generated when navigation triggers guidance prompt. In the navigation state, the standard map sends navigation guidance prompt information within the preset distance ahead to the electronic device at a frequency of 1Hz. Navigation guidance prompt information includes guidance action information, intersection lane information, confusing intersections and complex intersections, etc. Among them, the guidance action information can include information about the two guidance points ahead, specifically including the distance between the vehicle and the guidance point and the type of guidance action. The guidance action type is left turn, right turn, straight ahead, etc. The intersection lane information includes information such as the distance between the vehicle and the intersection, the number of intersection lanes, the direction of traffic of the intersection lanes, the left and right extended lanes, and the recommended lanes.

[0101] The navigation status information is generated when the navigation status changes, for example, when the road condition changes.

[0102] In the navigation state, the standard map sends navigation positioning information to the electronic device at a frequency of 1Hz. The navigation positioning information includes the latitude and longitude of the vehicle's current position, the vehicle's heading, the road binding status, the identification of the road section where the vehicle is located, and the distance of the vehicle's position relative to the starting point of the road section.

[0103] When an electronic device obtains navigation map information and navigation positioning information, it can convert the navigation map information and navigation positioning information into a standard map data format for use. On the one hand, the conversion of the data format can isolate the impact of changes in the external map data format on the navigation planning and positioning inside the electronic device. For example, changes in the external map data format caused by navigation map version upgrades, changes in navigation map providers, etc. On the other hand, the internal data format of the electronic device is convenient for use by various modules inside the electronic device, and facilitates rapid retrieval of key data information.

[0104] In this embodiment, when the electronic device determines that the vehicle needs to change lanes, it plans a lane change path by combining navigation map information, navigation positioning information and perception information.

[0105] The vehicle driving control method provided in this embodiment determines the distance between the vehicle and the intersection, and when the distance is less than a first distance threshold, obtains vehicle sensor information and determines perception information, and then determines whether the vehicle needs to change lanes based on the perception information. When it is determined that the vehicle needs to change lanes, lane change planning is performed in combination with navigation map information, navigation positioning information and perception information, thereby achieving the effect of lane-level lane change navigation using a standard map, avoiding inaccurate planning due to low accuracy of the standard map or loss of vehicle information, and obtaining sensor information only when it is determined that the distance between the vehicle and the intersection is less than a threshold, without the need to obtain and process sensor information in real time, thereby reducing the computational complexity and energy consumption of the electronic device.

[0106] In some embodiments, after step S101, the electronic device may also control the vehicle to travel in the current lane when the distance between the vehicle and the intersection is greater than or equal to a first distance threshold.

[0107] Specifically, when the distance between the vehicle and the intersection is greater than or equal to a first distance threshold, the vehicle travels in the current lane to reduce energy consumption.

[0108] In some embodiments, generating lane change path planning information according to the navigation map information, the navigation positioning information and the perception information in step S105 may include the following steps:

[0109] S1051. Generate global positioning information based on navigation positioning information and perception information.

[0110] S1052: Generate local positioning information based on the navigation map information and perception information.

[0111] S1053: Determine lane change information based on the global navigation path information and navigation guidance prompt information in the navigation map information, as well as the global positioning information.

[0112] The lane change information includes lane change speed and lane change angle.

[0113] S1054. Determine lane-level lane change path planning information based on the perception information, local positioning information, and lane change information.

[0114] In this embodiment, after the electronic device obtains the navigation map information, navigation positioning information and perception information, it determines the position of the vehicle in the global coordinate system map according to the navigation positioning information and the perception information, that is, generates global positioning information, and constructs a local coordinate system with the current position of the vehicle as the origin according to the navigation map information and the perception information. It also integrates the vehicle driving state information such as the inertial measurement unit information and the wheel speed information based on the Kalman filter, solves the vehicle posture, and obtains continuous and stable local positioning information.

[0115] The electronic device calculates the lane change information based on the global navigation path information, navigation guidance prompt information, and global positioning information in the navigation map information. The lane change information includes the lane change timing, lane change speed, and lane change angle. Then, based on the road topology, local positioning information, and lane change information in the perception information, the detailed lane-level lane change path information (such as Figure 4 The system can realize the navigation lane change planning and replace the lane-level navigation of the high-precision map.

[0116] In some embodiments, step S101 may include the following steps:

[0117] S1011. Predict a first distance between the vehicle and the intersection based on the navigation map information or the navigation positioning information.

[0118] S1012. Determine perception information based on camera image data and radar point cloud data.

[0119] Among them, the perception information includes road topology.

[0120] Step S1012 and Figure 3 The implementation of step S103 in the embodiment is similar and will not be described in detail in this embodiment.

[0121] S1013. Predict a second distance between the vehicle and the intersection based on the road topology.

[0122] S1014. Determine the distance between the vehicle and the intersection from the first distance and the second distance according to whether there is an intersection in the road topology.

[0123] Figure 5 This is a schematic diagram of the distance between a vehicle and an intersection provided in this embodiment. Figure 5As shown, the first distance is the distance between the vehicle and the intersection predicted based on the navigation map information or the navigation positioning information, and the second distance is the distance between the vehicle and the intersection predicted in the perception information. The first distance may be greater than the second distance, or may be less than the second distance. This embodiment determines the distance between the vehicle and the intersection based on whether there is an intersection in the perception information and the absolute value of the difference between the first distance and the second distance.

[0124] Optionally, step S1014 includes:

[0125] When there is no intersection in the road topology, the first distance is determined to be the distance between the vehicle and the intersection.

[0126] When there is an intersection in the road topology, the absolute value of the difference between the first distance and the second distance is determined; when the absolute value of the difference is less than the second distance threshold, the second distance is determined to be the distance between the vehicle and the intersection; when the absolute value of the difference is greater than or equal to the second distance threshold, the first distance is determined to be the distance between the vehicle and the intersection.

[0127] Specifically, when the absolute value of the difference is greater than or equal to the second distance threshold, in order to prevent erroneous correction, the electronic device does not perform correction processing and determines the first distance as the distance between the vehicle and the intersection.

[0128] In this embodiment, the electronic device uses the navigation guidance prompt information or navigation positioning information in the navigation map information provided by the standard map as the data source, and combines the 3D road topology information in the perception information to perform necessary deviation correction processing on the distance between the vehicle and the intersection. Based on the information provided by the standard map, the global positioning can be matched with the navigation map information, which facilitates the use of effective navigation map information when the electronic device performs navigation planning. At the same time, it can also avoid the situation where the vehicle presents different positions in different systems, reducing the risk of missing the intersection due to the low positioning accuracy of the standard map.

[0129] In some embodiments, step S104 includes the following steps:

[0130] S1041. Determine a target lane according to navigation guidance prompt information and perception information in the navigation map information.

[0131] For example, if the navigation guidance prompt is "...please take the leftmost lane", the target lane is the leftmost lane. For another example, if the navigation guidance prompt is "go straight ahead", and the perception information determines that there are multiple straight lanes ahead, then one straight lane needs to be determined as the target lane from the multiple straight lanes.

[0132] S1042. Determine the current lane based on the perception information.

[0133] Specifically, the perception information includes lane information such as lanes, lane lines, and lane center lines, based on which the vehicle's current lane can be determined.

[0134] S1043. Determine whether the vehicle needs to change lanes based on the target lane and the current lane.

[0135] Specifically, when the target lane and the current lane are different lanes, it can be determined that the vehicle needs to change lanes, otherwise it is determined that the vehicle does not need to change lanes.

[0136] Optionally, step S1041 includes: when the navigation guidance prompt information includes a recommended lane, determining the recommended lane as the target lane. When the navigation guidance prompt information does not include a recommended lane, determining at least one passable lane according to the navigation guidance prompt information and the perception information; and determining the target lane from at least one passable lane according to the navigation guidance prompt information of the next intersection.

[0137] Specifically, when the navigation guidance prompt information does not include a recommended lane, the electronic device can determine the target lane based on the guidance prompt information of the two guidance points ahead and the intersection lane information, thereby achieving the effect of the vehicle passing through the first intersection while efficiently passing through the second intersection.

[0138] For example, the navigation guidance prompt information is "go straight at the current intersection, turn right after 800 meters", where there are two guidance points, namely "current intersection" and "after 800 meters". In this case, the electronic device determines at least one straight lane based on "go straight at the current intersection" and the number of straight lanes at the current intersection.

[0139] When there is only one straight lane, the straight lane is determined as the target lane. When there are multiple straight lanes, the electronic device selects the right lane among the multiple straight lanes as the target lane according to "turn right after 800 meters".

[0140] It can be understood that when there are multiple passable lanes, when the second guidance is a right turn, the rightmost passable lane is determined as the target lane; when the second guidance is a left turn or a U-turn, the leftmost passable lane is determined as the target lane; when the second guidance is straight ahead, if the passable lanes are odd-numbered, the middlemost passable lane is determined as the target lane; if the passable lanes are even-numbered, the passable lane with less traffic in the two middle lanes is determined as the target lane.

[0141] In this embodiment, when there are multiple passable lanes for the vehicle to pass through the current intersection, the target lane is determined according to the guidance action information of the two guidance points, so that the vehicle can pass through the current intersection smoothly and pass through the next intersection more efficiently.

[0142] Figure 6 FIG. 1 shows a schematic diagram of the structure of a vehicle driving control device provided by an embodiment of the present application. Figure 6As shown, the vehicle driving control device 10 of this embodiment is used to implement the operation corresponding to the electronic device in any of the above method embodiments. The vehicle driving control device 10 of this embodiment includes:

[0143] A determination module 11, for determining the distance between the vehicle and the intersection;

[0144] An acquisition module 12, used to acquire camera image data and radar point cloud data when the distance is less than a first distance threshold;

[0145] The determination module 11 is further used to determine the perception information based on the camera image data and the radar point cloud data;

[0146] A judgment module 13 is used to judge whether the vehicle needs to change lanes according to the perception information;

[0147] The generation module 14 is used to generate lane change path planning information based on navigation map information, navigation positioning information and perception information when determining that the vehicle needs to change lanes. The lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

[0148] The vehicle driving control device 10 provided in this embodiment can execute the above method embodiment. Its specific implementation principle and technical effects can be found in the above method embodiment, and this embodiment will not be repeated here.

[0149] Figure 7 This is a schematic diagram of the structure of an intelligent driving system provided in one embodiment of the present application. Figure 7 As shown, the intelligent driving system 20 provided in this embodiment includes a map module 21, a perception module 22, a positioning module 23, a planning module 24 and a control module 25.

[0150] A map module 21, used to obtain navigation map information and navigation positioning information from a standard map software development kit (SDK);

[0151] A perception module 22, used to determine perception information based on camera image data and radar point cloud data;

[0152] A positioning module 23, used to generate global positioning information and local positioning information according to navigation map information, navigation positioning information and perception information;

[0153] A planning module 24, for generating lane change path planning information according to navigation map information, navigation positioning information, perception information, global positioning information and local positioning information;

[0154] The control module 25 is used to control the vehicle to complete the lane change according to the lane change path planning information.

[0155] It should be noted that in this embodiment, the standard map SDK can be integrated into the vehicle's built-in navigation map, which provides navigation map information and navigation positioning information, thereby reusing the vehicle's existing resources to reduce the cost of each vehicle.

[0156] Specifically, the vehicle computer can send navigation map information and navigation positioning information to the intelligent driving system via Ethernet, and the modules of the intelligent driving system can communicate with each other using SOME / IP.

[0157] like Figure 8 As shown, the standard map SDK can also be integrated into the map module of the intelligent driving system. The map module obtains navigation map information and navigation positioning information from the standard map SDK through an interface without directly communicating with the vehicle computer, thereby solving the problem of direct dependence of the intelligent driving system on the vehicle computer.

[0158] In addition, the map provider's standard map SDK communicates with the navigation map SDK in the car computer via Ethernet to synchronize necessary information, such as the navigation route selected by the user on the car computer, the car computer navigation location information and other basic navigation information. The standard map SDK combines local map data and cloud map data to provide the map module with all the map information required for intelligent driving.

[0159] The intelligent driving system 20 provided in this embodiment can execute the above method embodiments. Its specific implementation principles and technical effects can be found in the above method embodiments, and this embodiment will not be repeated here.

[0160] Fig. 9 FIG. 1 shows a hardware structure diagram of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 30 is used to implement the operations corresponding to the electronic device in any of the above method embodiments. The electronic device 30 of this embodiment may include: a memory 31, a processor 32 and a communication interface 34.

[0161] The memory 31 is used to store computer programs. The memory 31 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a disk, or an optical disk.

[0162] The processor 32 is used to execute the computer program stored in the memory to implement the method in the above embodiment. For details, please refer to the relevant description in the above method embodiment. The processor 32 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. 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 the invention can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0163] Optionally, the memory 31 may be independent or integrated with the processor 32 .

[0164] When the memory 31 is a device independent of the processor 32, the electronic device 30 may further include a bus 33. The bus 33 is used to connect the memory 31 and the processor 32. The bus 33 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0165] The communication interface 34 may be connected to the processor 32 via the bus 33. The processor 32 may control the communication interface 34 to implement the functions of receiving and sending signals.

[0166] The electronic device 30 provided in this embodiment can be used to execute the above-mentioned vehicle driving control method. Its implementation method and technical effect are similar, and this embodiment will not be repeated here.

[0167] The present application also provides a computer-readable storage medium, in which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, it is used to implement the methods provided in the various embodiments described above.

[0168] Among them, the computer-readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can be located in an application-specific integrated circuit (ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the computer-readable storage medium can also exist in a communication device as discrete components.

[0169] Specifically, the computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium may be any available medium that can be accessed by a general or special-purpose computer.

[0170] The present application also provides a computer program product, which includes a computer program / instruction, and the computer program / instruction is stored in a computer-readable storage medium. At least one processor of the device can read the computer program / instruction from the computer-readable storage medium, and at least one processor executes the computer program / instruction so that the device implements the methods provided in the various embodiments described above.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0172] Among them, each module can be physically separated, for example, installed in different locations of a device, or installed on different devices, or distributed on multiple network units, or distributed on multiple processors. Each module can also be integrated together, for example, installed in the same device, or integrated in a set of codes. Each module can exist in the form of hardware, or can also exist in the form of software, or can also be implemented in the form of software plus hardware. The present application can select some or all of the modules according to actual needs to achieve the purpose of the present embodiment.

[0173] It should be understood that, although the various steps in the flowcharts in the above-described embodiments are sequentially displayed according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily to be carried out sequentially, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the above embodiments can still be modified, or some or all of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle driving control method, characterized in that: The method comprises: Determine the distance of the vehicle from the intersection; When the distance is less than a first distance threshold, acquiring camera image data and radar point cloud data; Determining perception information according to the camera image data and the radar point cloud data; Determining whether the vehicle needs to change lanes based on the perception information; When it is determined that the vehicle needs to change lanes, lane change path planning information is generated based on the navigation map information, the navigation positioning information and the perception information. The lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

2. The method according to claim 1, characterized in that Generate lane change path planning information according to the navigation map information, the navigation positioning information and the perception information, including: Generate global positioning information according to the navigation positioning information and the perception information; generating local positioning information according to the navigation map information and the perception information; Determining lane change information according to the global navigation path information and navigation guidance prompt information in the navigation map information and the global positioning information, wherein the lane change information includes a lane change speed and a lane change angle; Determine lane-level lane change path planning information based on the perception information, the local positioning information, and the lane change information.

3. The method according to claim 1 or 2, characterized in that: Determine the distance of the vehicle from the intersection, including: Predicting a first distance between the vehicle and the intersection based on navigation map information or navigation positioning information; Determining perception information based on the camera image data and the radar point cloud data, wherein the perception information includes road topology; Predicting a second distance between the vehicle and the intersection based on the road topology; According to whether there is an intersection in the road topology, the distance between the vehicle and the intersection is determined in the first distance and the second distance.

4. The method according to claim 3, characterized in that: Determining the distance between the vehicle and the intersection from the first distance and the second distance according to whether there is an intersection in the road topology includes: When there is no intersection in the road topology, determining the first distance as the distance between the vehicle and the intersection; When there is an intersection in the road topology, the absolute value of the difference between the first distance and the second distance is determined; when the absolute value of the difference is less than the second distance threshold, the second distance is determined to be the distance between the vehicle and the intersection; when the absolute value of the difference is greater than or equal to the second distance threshold, the first distance is determined to be the distance between the vehicle and the intersection.

5. The method according to claim 1 or 2, characterized in that: Judging whether the vehicle needs to change lanes based on the perception information includes: Determining a target lane according to the navigation guidance prompt information in the navigation map information and the perception information; Determine a current lane according to the perception information; According to the target lane and the current lane, it is determined whether the vehicle needs to change lanes.

6. The method according to claim 5, characterized in that Determining a target lane according to navigation guidance prompt information in the navigation map information and the perception information includes: When the navigation guidance prompt information includes a recommended lane, determining the recommended lane as a target lane; When the navigation guidance prompt information does not include a recommended lane, determining at least one drivable lane according to the navigation guidance prompt information and the perception information; According to the navigation guidance prompt information of the next intersection, a target lane is determined from the at least one drivable lane.

7. The method according to claim 1 or 2, characterized in that: Before determining the distance of the vehicle from the intersection, it also includes: Obtain navigation map information or navigation positioning information; Determine the distance of the vehicle from the intersection, including: The distance between the vehicle and the intersection is determined according to the navigation guidance prompt information or the navigation positioning information in the navigation map information.

8. The method according to claim 1 or 2, characterized in that: After determining the distance of the vehicle from the intersection, it also includes: When the distance between the vehicle and the intersection is greater than or equal to the first distance threshold, the vehicle is controlled to travel in the current lane.

9. A vehicle driving control device, characterized in that: include: A determination module, used to determine the distance between the vehicle and the intersection; An acquisition module, used for acquiring camera image data and radar point cloud data when the distance is less than a first distance threshold; The determination module is further used to determine the perception information according to the camera image data and the radar point cloud data; A judgment module, used for judging whether the vehicle needs to change lanes according to the perception information; The generation module is used to generate lane change path planning information based on navigation map information, navigation positioning information and the perception information when determining that the vehicle needs to change lanes. The lane change path planning information is used to control the vehicle to complete the lane change before the intersection.

10. An intelligent driving system, characterized in that: Includes map module, perception module, positioning module, planning module and control module; The map module is used to obtain navigation map information and navigation positioning information from a standard map software development kit; The perception module is used to determine perception information based on camera image data and radar point cloud data; The positioning module is used to generate global positioning information and local positioning information according to the navigation map information, the navigation positioning information and the perception information; The planning module is used to generate lane change path planning information according to the navigation map information, the navigation positioning information, the perception information, the global positioning information and the local positioning information; The control module is used to control the vehicle to complete lane change according to the lane change path planning information.

11. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to implement the vehicle driving control method as described in any one of claims 1-8.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the vehicle driving control method as described in any one of claims 1-8.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the vehicle driving control method according to any one of claims 1 to 8 is implemented.

Images