Positioning method, device, electronic device and storage medium for autonomous driving vehicle

Abstract

The present application discloses a positioning method, device, electronic device, and storage medium for an autonomous driving vehicle, the method comprising: obtaining the initial posture data of the vehicle, high-precision map data corresponding to the initial posture data, and road sign segmentation data; determining the angular change of the vehicle relative to the road surface based on the high-precision map data and the road sign segmentation data; constructing an optimization model based on the angular change of the vehicle relative to the road surface using the high-precision map data and the road sign segmentation data, and determining the relative deviation between the road sign segmentation data and the high-precision map data using the optimization model; determining the positioning result based on the relative deviation between the road sign segmentation data and the high-precision map data and the initial posture data. The present application determines the angular change of the vehicle relative to the road surface based on the high-precision map data, improves the calculation accuracy of the road sign segmentation data in the vehicle coordinate system, and uses the road sign segmentation data obtained based on visual technology to assist in positioning, thereby improving positioning accuracy.

Description

Technical Field

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

[0002] In the field of autonomous driving, the accuracy of data such as the position and posture of autonomous driving vehicles is crucial to the realization of autonomous driving functions. These data are prerequisites for the vehicle perception unit and control unit to make perception decisions. The accuracy of the position and posture of the autonomous driving vehicle in the lane during driving is related to the safe driving of the autonomous driving vehicle, so special attention needs to be paid.

[0003] With the rapid development of autonomous driving technology, a variety of positioning methods for autonomous driving vehicles have emerged, among which inertial navigation / satellite combined positioning and odometer (Odometry) are the most common. However, due to the influence of satellite availability, inertial navigation performance, odometer cumulative error, etc., the positioning accuracy of current positioning methods in scenes such as tunnels and urban canyons is still difficult to meet the needs of autonomous driving. Summary of the invention

[0004] The embodiments of the present application provide a positioning method, device, electronic device, and storage medium for an autonomous driving vehicle to improve the positioning accuracy of the autonomous driving vehicle.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a positioning method for an autonomous driving vehicle, wherein the method comprises:

[0007] Acquire initial posture data of the autonomous driving vehicle, as well as high-precision map data and road sign segmentation data corresponding to the initial posture data;

[0008] Determining a change in angle of the autonomous driving vehicle relative to a road surface based on the high-precision map data and the road surface marking segmentation data;

[0009] Based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and the road surface marking segmentation data, and a relative deviation between the road surface marking segmentation data and the high-precision map data is determined using the optimization model;

[0010] The positioning result of the autonomous driving vehicle is determined based on the relative deviation between the road marking segmentation data and the high-precision map data, as well as the initial posture data.

[0011] Optionally, determining the angle change of the autonomous driving vehicle relative to the road surface according to the high-precision map data and the road surface marking segmentation data includes:

[0012] Converting the high-precision map data and the road surface marking segmentation data into a vehicle coordinate system respectively to obtain the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the vehicle coordinate system;

[0013] Matching the high-precision map data in the vehicle coordinate system with the road surface marking segmentation data in the vehicle coordinate system;

[0014] The angle change of the autonomous driving vehicle relative to the road surface is determined based on the matching result.

[0015] Optionally, determining the angle change of the autonomous driving vehicle relative to the road surface according to the matching result includes:

[0016] Obtaining a lane line fitting equation in high-precision map data that matches the road surface marking segmentation data in the vehicle coordinate system;

[0017] Constructing a point-line error model according to the lane line points in the road surface marking segmentation data and the lane line fitting equation;

[0018] Based on the point-line error model, the angular change of the autonomous driving vehicle relative to the road surface is determined.

[0019] Optionally, the angle change of the autonomous driving vehicle relative to the road surface includes a pitch angle of the autonomous driving vehicle relative to the road surface, and constructing an optimization model based on the angle change of the autonomous driving vehicle relative to the road surface by using the high-precision map data and the road surface marking segmentation data includes:

[0020] Based on the camera parameters and the pitch angle of the autonomous driving vehicle relative to the road surface, the road surface marking segmentation data in the vehicle coordinate system is corrected to obtain the corrected road surface marking segmentation data in the vehicle coordinate system;

[0021] The optimization model is constructed based on the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the corrected vehicle coordinate system.

[0022] Optionally, constructing an optimization model based on the angle change of the autonomous driving vehicle relative to the road surface by using the high-precision map data and the road surface marking segmentation data includes:

[0023] Determining road surface marking attributes of the road surface marking segmentation data;

[0024] Based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attributes of the road surface marking segmentation data, an optimization model corresponding to the road surface marking attributes is constructed using the high-precision map data and the road surface marking segmentation data.

[0025] Optionally, based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attributes of the road surface marking segmentation data, constructing an optimization model corresponding to the road surface marking attributes using the high-precision map data and the road surface marking segmentation data includes:

[0026] If the road surface marking attribute is a linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, a point-line error model is constructed using the high-precision map data and the road surface marking segmentation data;

[0027] If the road surface marking attribute is a non-linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, a 3D point-3D point error model is constructed using the high-precision map data and the road surface marking segmentation data.

[0028] Optionally, determining the positioning result of the autonomous driving vehicle according to the relative deviation between the road surface marking segmentation data and the high-precision map data, and the initial posture data includes:

[0029] According to the relative deviation between the road sign segmentation data and the high-precision map data, the initial posture data is corrected to obtain corrected posture data;

[0030] The positioning result of the autonomous driving vehicle is determined based on the corrected posture data.

[0031] In a second aspect, an embodiment of the present application further provides a positioning device for an autonomous driving vehicle, wherein the device comprises:

[0032] An acquisition unit, used to acquire initial posture data of the autonomous driving vehicle, and high-precision map data and road sign segmentation data corresponding to the initial posture data;

[0033] A first determination unit, configured to determine an angle change of the autonomous driving vehicle relative to a road surface according to the high-precision map data and the road surface marking segmentation data;

[0034] an optimization unit, configured to construct an optimization model using the high-precision map data and the road surface marking segmentation data based on an angle change of the autonomous driving vehicle relative to a road surface, and to determine a relative deviation between the road surface marking segmentation data and the high-precision map data using the optimization model;

[0035] The second determination unit is used to determine the positioning result of the autonomous driving vehicle according to the relative deviation between the road surface marking segmentation data and the high-precision map data, and the initial posture data.

[0036] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0037] Processor; and

[0038] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.

[0039] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes any of the aforementioned methods.

[0040] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the positioning method of the autonomous driving vehicle in the embodiments of the present application first obtains the initial posture data of the autonomous driving vehicle, as well as the high-precision map data and road sign segmentation data corresponding to the initial posture data; then, according to the high-precision map data and road sign segmentation data, the angle change of the autonomous driving vehicle relative to the road surface is determined; then, based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and road sign segmentation data, and the optimization model is used to determine the relative deviation between the road sign segmentation data and the high-precision map data; finally, according to the relative deviation between the road sign segmentation data and the high-precision map data, as well as the initial posture data, the positioning result of the autonomous driving vehicle is determined. The positioning method of the autonomous driving vehicle in the embodiments of the present application determines the angle change of the vehicle relative to the road surface based on the high-precision map data, improves the calculation accuracy of the road sign segmentation data in the vehicle coordinate system, and uses the road sign segmentation data obtained based on visual technology to assist in positioning, thereby improving the positioning accuracy of the vehicle in scenes such as urban canyons and tunnels. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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:

[0042] Figure 1 A schematic diagram of a flow chart of a positioning method for an autonomous driving vehicle in an embodiment of the present application;

[0043] Figure 2 This is a schematic diagram of the structure of a positioning device for an autonomous driving vehicle in an embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0046] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0047] The present application embodiment provides a method for positioning an autonomous driving vehicle, such as Figure 1 As shown, a flow chart of a positioning method for an autonomous driving vehicle in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S140:

[0048] Step S110, obtaining the initial posture data of the autonomous driving vehicle, as well as the high-precision map data and road sign segmentation data corresponding to the initial posture data.

[0049] The positioning method of the autonomous driving vehicle in the embodiment of the present application needs to obtain the initial posture data of the autonomous driving vehicle when positioning. The initial posture data can be calculated based on the data measured by the inertial navigation device on the vehicle. For example, the initial posture of the vehicle can be predicted by pre-integration or other methods based on the angular velocity and linear acceleration measured by the inertial navigation device. Of course, the initial posture of the vehicle can also be obtained by fusing the inertial navigation device with the GPS positioning signal or odometer data.

[0050] Since the initial pose data is easily affected by the inertial navigation performance, the quality of satellite positioning signals, etc., the positioning accuracy in some positioning scenarios is difficult to meet the needs of autonomous driving. Therefore, the embodiment of the present application needs to further correct the initial pose data. Here, it is necessary to first obtain the high-precision map data and road sign segmentation data corresponding to the initial pose data.

[0051] The information contained in the HD map data includes not only high-precision location coordinates, but also accurate road shapes, and the slope, curvature, heading, elevation, and roll data of each lane. In addition, the type of signs on each lane, the color of lane lines, the road divider, the arrows and text on the road signs, etc. will all be presented in the HD map. Therefore, HD map data can provide strong support for the positioning of autonomous driving vehicles. In order to improve the efficiency of subsequent matching and positioning, local HD map data within a small range can be obtained based on the initial posture data.

[0052] When obtaining road sign segmentation data, the road image captured by the vehicle-mounted camera can be obtained first, and then the road signs contained in the road image can be semantically segmented using a trained preset semantic segmentation model to obtain a road sign segmentation result. The preset semantic segmentation model can be trained based on a convolutional neural network in the prior art, for example, a U-NET or LaneNet model can be used. Of course, the specific form of the semantic segmentation model can be flexibly selected by those skilled in the art according to actual needs, and no specific limitation is made here.

[0053] Step S120: determining the angle change of the autonomous driving vehicle relative to the road surface based on the high-precision map data and the road marking segmentation data.

[0054] The positioning of autonomous vehicles is usually achieved based on the vehicle coordinate system, which is a Euclidean coordinate system with the vehicle itself as the origin, that is, a coordinate system based on "Euclidean geometry". Specifically, the vehicle coordinate system can be a body coordinate system with the center of the rear axle of the vehicle as the origin, the direction of the front of the vehicle as the positive direction of the x-axis, the left side of the vehicle as the positive direction of the y-axis, and the vertical direction upward as the positive direction of the z-axis (in accordance with the right-hand rule). Since the high-precision map data is data in the world coordinate system constructed with the ground as the 0 plane in a static state, and the 0 plane referenced by the constructed vehicle coordinate system will change during the movement of the vehicle, it is necessary to compensate for the deviation caused by this change.

[0055] Based on this, the embodiments of the present application can determine the angular change of the autonomous driving vehicle relative to the road surface according to the matching between the high-precision map data and the road surface marking segmentation data, thereby improving the calculation accuracy of the road surface marking segmentation data in the vehicle coordinate system.

[0056] Step S130, based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and the road surface marking segmentation data, and the relative deviation between the road surface marking segmentation data and the high-precision map data is determined using the optimization model.

[0057] After obtaining the angle change of the autonomous driving vehicle relative to the road surface, the calculation deviation of the road surface marking segmentation data in the vehicle coordinate system can be compensated based on this, and then an optimization model can be constructed according to the deviation between the compensated road surface marking segmentation data and the high-precision map data. The optimization model can, for example, be a nonlinear optimization model, which is solved using a certain solution algorithm such as the least squares method, so as to obtain the relative deviation between the optimized road surface marking segmentation data and the high-precision map data.

[0058] Step S140, determining the positioning result of the autonomous driving vehicle according to the relative deviation between the road marking segmentation data and the high-precision map data, and the initial posture data.

[0059] Based on the relative deviation between the road marking segmentation data and the high-precision map data, the initial posture data can be corrected to improve the accuracy of posture calculation and further improve the positioning accuracy of the autonomous driving vehicle.

[0060] The positioning method of the autonomous driving vehicle in the embodiment of the present application determines the angular change of the vehicle relative to the road surface based on high-precision map data, improves the calculation accuracy of the road surface marking segmentation data in the vehicle coordinate system, and uses the road surface marking segmentation data obtained based on vision technology to assist in positioning, thereby improving the vehicle's positioning accuracy in scenarios such as urban canyons and tunnels.

[0061] In some embodiments of the present application, determining the angular change of the autonomous driving vehicle relative to the road surface based on the high-precision map data and the road surface marking segmentation data includes: converting the high-precision map data and the road surface marking segmentation data into a vehicle coordinate system, respectively, to obtain the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the vehicle coordinate system; matching the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the vehicle coordinate system; and determining the angular change of the autonomous driving vehicle relative to the road surface based on the matching result.

[0062] When determining the angular change of the vehicle relative to the road surface, the embodiment of the present application can first uniformly convert the high-precision map data and the road surface marking segmentation data into the vehicle coordinate system. Since the vehicle coordinate system can essentially be regarded as a local world coordinate system established with the vehicle itself as the origin, and the high-precision map data is located in the global world coordinate system, the conversion of the high-precision map data to the vehicle coordinate system can be regarded as a rigid transformation. The road surface marking segmentation data is located in the image coordinate system, so its conversion to the vehicle coordinate system is a perspective transformation, which can be performed based on camera parameters.

[0063] After obtaining the high-precision map data and road marking segmentation data in the vehicle coordinate system, the road marking segmentation data is represented by a point cloud in the vehicle coordinate system to facilitate subsequent processing. After that, the road marking data in the high-precision map data in the vehicle coordinate system can be matched with the road marking segmentation data. Taking the lane line as an example, the specific matching dimensions may include the lane line fitting equation, lane line attributes, and the geometric relationship between lane lines. The lane line attributes may specifically include the lane line color such as white or yellow, and the lane line type such as solid line or dotted line, single line or double line, etc. The geometric relationship between lane lines may include, for example, the relative position relationship between multiple lane lines segmented in the image. If the parameters of the lane line fitting equation are the same or similar, the lane line color and type are the same, and the lane line geometric relationship is also the same, then it can be considered that the lane line is matched.

[0064] In actual scenarios, due to the influence of some external factors, the high-precision map data and the road surface marking segmentation data will not be completely matched. Therefore, the matching result of the embodiment of the present application can be understood as the degree of deviation in position and posture between the road surface marking segmentation data in the vehicle coordinate system and the matching high-precision map data, which can be used to calculate the angular deviation of the vehicle relative to the road surface.

[0065] In some embodiments of the present application, determining the angular change of the autonomous driving vehicle relative to the road surface based on the matching results includes: obtaining a lane line fitting equation in high-precision map data that matches the road surface marking segmentation data in the vehicle coordinate system; constructing a point-line error model based on the lane line points in the road surface marking segmentation data and the lane line fitting equation; and determining the angular change of the autonomous driving vehicle relative to the road surface based on the point-line error model.

[0066] After matching the high-precision map data with the road surface marking segmentation data, the embodiment of the present application can find the high-precision map data that best matches the road surface marking segmentation data, and then obtain the matching lane line fitting equation from the high-precision map data. Then, a point-line error model is constructed based on the lane line points in the road surface marking segmentation data and the lane line fitting equation, and optimization is performed using a nonlinear optimization method. The quantity to be optimized is mainly the angular change of the vehicle relative to the road surface, such as the pitch angle, so that the optimized angular change of the vehicle relative to the road surface can be obtained.

[0067] In some embodiments of the present application, the angular change of the autonomous driving vehicle relative to the road surface includes the pitch angle of the autonomous driving vehicle relative to the road surface, and constructing an optimization model based on the angular change of the autonomous driving vehicle relative to the road surface using the high-precision map data and the road surface marking segmentation data includes: correcting the road surface marking segmentation data in the vehicle coordinate system based on camera parameters and the pitch angle of the autonomous driving vehicle relative to the road surface to obtain corrected road surface marking segmentation data in the vehicle coordinate system; and constructing the optimization model based on the high-precision map data in the vehicle coordinate system and the corrected road surface marking segmentation data in the vehicle coordinate system.

[0068] After obtaining the angular change of the vehicle relative to the road surface, the embodiment of the present application can take the ground as the 0 plane and combine the internal and external parameters of the camera to reconvert the road surface marking segmentation data to the vehicle coordinate system. Since the angular deviation of the vehicle relative to the road surface is corrected, the road surface marking segmentation data obtained after the conversion has higher accuracy than that before the correction, which also improves the calculation accuracy of the road surface marking segmentation data in the vehicle coordinate system.

[0069] Based on the road marking segmentation data in the corrected vehicle coordinate system and the high-precision map data that has been converted to the vehicle coordinate system in the aforementioned embodiment, a nonlinear optimization model can be constructed to obtain more accurate optimization results.

[0070] In some embodiments of the present application, constructing an optimization model based on the angle change of the autonomous driving vehicle relative to the road surface using the high-precision map data and the road surface marking segmentation data includes: determining road surface marking attributes of the road surface marking segmentation data; based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attributes of the road surface marking segmentation data, constructing an optimization model corresponding to the road surface marking attributes using the high-precision map data and the road surface marking segmentation data.

[0071] When constructing an optimization model, the embodiments of the present application may further combine the different attributes of road surface markings to construct different optimization models respectively, and finally optimize together with different optimization models, so as to improve the optimization efficiency and optimization effect. Road surface marking attributes can, for example, divide road surface markings into linear road surface markings and non-linear road surface markings. Linear road surface markings may include lane lines and stop lines, etc., and non-linear road surface markings may include arrows, etc. The road surface marking attributes can be obtained from the semantic segmentation results of the road surface markings. Of course, those skilled in the art can flexibly set the specific attributes of road surface markings according to actual needs, and no specific limitation is made here.

[0072] In some embodiments of the present application, the optimization model corresponding to the road surface marking attribute is constructed using the high-precision map data and the road surface marking segmentation data based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attribute of the road surface marking segmentation data, including: if the road surface marking attribute is a linear road surface marking, then based on the angle change of the autonomous driving vehicle relative to the road surface, a point-line error model is constructed using the high-precision map data and the road surface marking segmentation data; if the road surface marking attribute is a non-linear road surface marking, then based on the angle change of the autonomous driving vehicle relative to the road surface, a 3D point-3D point error model is constructed using the high-precision map data and the road surface marking segmentation data.

[0073] If it is a linear road marking such as a lane line or a stop line, a point-line error model can be constructed based on the matching lane line pair or stop line pair. If it is a non-linear road marking such as an arrow, a 3D point-3D point error model can be constructed based on the matching arrow point pair. The matching algorithm between 3D points and 3D points can be implemented through point cloud registration methods such as ICP (Iterative Closest Point). Finally, the point-line error model and the 3D point-3D point error model are combined for joint optimization, and the relative deviation between the road marking segmentation data and the high-precision map data in the vehicle coordinate system is obtained by solving the least squares method and other nonlinear optimization models.

[0074] In some embodiments of the present application, determining the positioning result of the autonomous driving vehicle based on the relative deviation between the road surface marking segmentation data and the high-precision map data, and the initial pose data includes: correcting the initial pose data based on the relative deviation between the road surface marking segmentation data and the high-precision map data to obtain corrected pose data; and determining the positioning result of the autonomous driving vehicle based on the corrected pose data.

[0075] The initial pose data can be corrected based on the relative deviation between the road sign segmentation data and the high-precision map data. The corrected pose data has higher positioning accuracy. Therefore, the corrected pose data can be directly used as the final positioning result of the autonomous driving vehicle. Of course, it can also be further combined with the positioning data of other sensors and fused using the Kalman filter or extended Kalman filter to output the final positioning result.

[0076] In summary, the positioning method of the autonomous driving vehicle of the present application has achieved at least the following technical effects:

[0077] 1) The road sign segmentation data obtained based on visual semantic segmentation can assist inertial navigation equipment and other positioning solutions in scenes such as urban canyons and tunnels, thereby improving positioning accuracy;

[0078] 2) The angle change of the vehicle relative to the road surface is calculated based on high-precision map data, which improves the calculation accuracy of the road surface marking segmentation data in the vehicle coordinate system;

[0079] 3) Different error optimization models are constructed according to road signs with different attributes, and all error optimization models are jointly optimized to improve the optimization efficiency and effect.

[0080] The present application also provides a positioning device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a schematic diagram of the structure of a positioning device for an autonomous driving vehicle in an embodiment of the present application is provided, wherein the device 200 includes: an acquisition unit 210, a first determination unit 220, an optimization unit 230, and a second determination unit 240, wherein:

[0081] An acquisition unit 210 is used to acquire initial posture data of the autonomous driving vehicle, as well as high-precision map data and road sign segmentation data corresponding to the initial posture data;

[0082] A first determination unit 220, configured to determine an angle change of the autonomous driving vehicle relative to a road surface according to the high-precision map data and the road surface marking segmentation data;

[0083] The optimization unit 230 is used to construct an optimization model using the high-precision map data and the road surface marking segmentation data based on the angle change of the autonomous driving vehicle relative to the road surface, and determine the relative deviation between the road surface marking segmentation data and the high-precision map data using the optimization model;

[0084] The second determination unit 240 is used to determine the positioning result of the autonomous driving vehicle according to the relative deviation between the road marking segmentation data and the high-precision map data, and the initial posture data.

[0085] In some embodiments of the present application, the first determination unit 220 is specifically used to: convert the high-precision map data and the road surface marking segmentation data into a vehicle coordinate system, respectively, to obtain the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the vehicle coordinate system; match the high-precision map data in the vehicle coordinate system with the road surface marking segmentation data in the vehicle coordinate system; and determine the angle change of the autonomous driving vehicle relative to the road surface based on the matching result.

[0086] In some embodiments of the present application, the first determination unit 220 is specifically used to: obtain the lane line fitting equation in the high-precision map data that matches the road surface marking segmentation data in the vehicle coordinate system; construct a point-line error model based on the lane line points in the road surface marking segmentation data and the lane line fitting equation; and determine the angle change of the autonomous driving vehicle relative to the road surface based on the point-line error model.

[0087] In some embodiments of the present application, the angular change of the autonomous driving vehicle relative to the road surface includes the pitch angle of the autonomous driving vehicle relative to the road surface, and the optimization unit 230 is specifically used to: correct the road surface marking segmentation data in the vehicle coordinate system based on camera parameters and the pitch angle of the autonomous driving vehicle relative to the road surface to obtain the corrected road surface marking segmentation data in the vehicle coordinate system; and construct the optimization model according to the high-precision map data in the vehicle coordinate system and the corrected road surface marking segmentation data in the vehicle coordinate system.

[0088] In some embodiments of the present application, the optimization unit 230 is specifically used to: determine the road surface marking attributes of the road surface marking segmentation data; based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attributes of the road surface marking segmentation data, use the high-precision map data and the road surface marking segmentation data to construct an optimization model corresponding to the road surface marking attributes.

[0089] In some embodiments of the present application, the optimization unit 230 is specifically used to: if the road surface marking attribute is a linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, construct a point-line error model using the high-precision map data and the road surface marking segmentation data; if the road surface marking attribute is a non-linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, construct a 3D point-3D point error model using the high-precision map data and the road surface marking segmentation data.

[0090] In some embodiments of the present application, the second determination unit 240 is specifically used to: correct the initial posture data according to the relative deviation between the road marking segmentation data and the high-precision map data to obtain corrected posture data; and determine the positioning result of the autonomous driving vehicle according to the corrected posture data.

[0091] It can be understood that the positioning device of the above-mentioned autonomous driving vehicle can implement the various steps of the positioning method of the autonomous driving vehicle provided in the aforementioned embodiments. The relevant explanations about the positioning method of the autonomous driving vehicle are applicable to the positioning device of the autonomous driving vehicle and will not be repeated here.

[0092] Figure 3This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0093] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0094] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0095] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a positioning device for the autonomous driving vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0096] Acquire initial posture data of the autonomous driving vehicle, as well as high-precision map data and road sign segmentation data corresponding to the initial posture data;

[0097] Determining a change in angle of the autonomous driving vehicle relative to a road surface based on the high-precision map data and the road surface marking segmentation data;

[0098] Based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and the road surface marking segmentation data, and a relative deviation between the road surface marking segmentation data and the high-precision map data is determined using the optimization model;

[0099] The positioning result of the autonomous driving vehicle is determined based on the relative deviation between the road marking segmentation data and the high-precision map data, as well as the initial posture data.

[0100] The above application Figure 1 The method performed by the positioning device of the autonomous driving vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor 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 the processor or instructions in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed 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 the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0101] The electronic device may also perform Figure 1 A method for executing a positioning device of an autonomous driving vehicle in a vehicle positioning system Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0102] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method performed by the positioning device of the autonomous driving vehicle in the illustrated embodiment is specifically used to perform:

[0103] Acquire initial posture data of the autonomous driving vehicle, as well as high-precision map data and road sign segmentation data corresponding to the initial posture data;

[0104] Determining a change in angle of the autonomous driving vehicle relative to a road surface based on the high-precision map data and the road surface marking segmentation data;

[0105] Based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and the road surface marking segmentation data, and a relative deviation between the road surface marking segmentation data and the high-precision map data is determined using the optimization model;

[0106] The positioning result of the autonomous driving vehicle is determined based on the relative deviation between the road marking segmentation data and the high-precision map data, as well as the initial posture data.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0112] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0113] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0114] 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.

[0115] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0116] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A positioning method for an autonomous driving vehicle, wherein: The method comprises: Acquire initial posture data of the autonomous driving vehicle, as well as high-precision map data and road sign segmentation data corresponding to the initial posture data; Determining a change in angle of the autonomous driving vehicle relative to a road surface based on the high-precision map data and the road surface marking segmentation data; Based on the angle change of the autonomous driving vehicle relative to the road surface, an optimization model is constructed using the high-precision map data and the road surface marking segmentation data, and a relative deviation between the road surface marking segmentation data and the high-precision map data is determined using the optimization model; The positioning result of the autonomous driving vehicle is determined based on the relative deviation between the road marking segmentation data and the high-precision map data, as well as the initial posture data.

2. The method of claim 1, wherein: The determining, based on the high-precision map data and the road sign segmentation data, the angle change of the autonomous driving vehicle relative to the road surface comprises: Converting the high-precision map data and the road surface marking segmentation data into a vehicle coordinate system respectively to obtain the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the vehicle coordinate system; Matching the high-precision map data in the vehicle coordinate system with the road surface marking segmentation data in the vehicle coordinate system; The angle change of the autonomous driving vehicle relative to the road surface is determined based on the matching result.

3. The method of claim 2, wherein: Determining the angle change of the autonomous driving vehicle relative to the road surface according to the matching result includes: Obtaining a lane line fitting equation in high-precision map data that matches the road surface marking segmentation data in the vehicle coordinate system; Constructing a point-line error model according to the lane line points in the road surface marking segmentation data and the lane line fitting equation; Based on the point-line error model, the angular change of the autonomous driving vehicle relative to the road surface is determined.

4. The method of claim 2, wherein: The angle change of the autonomous driving vehicle relative to the road surface includes a pitch angle of the autonomous driving vehicle relative to the road surface, and constructing an optimization model based on the angle change of the autonomous driving vehicle relative to the road surface by using the high-precision map data and the road surface marking segmentation data includes: Based on the camera parameters and the pitch angle of the autonomous driving vehicle relative to the road surface, the road surface marking segmentation data in the vehicle coordinate system is corrected to obtain the corrected road surface marking segmentation data in the vehicle coordinate system; The optimization model is constructed based on the high-precision map data in the vehicle coordinate system and the road surface marking segmentation data in the corrected vehicle coordinate system.

5. The method of claim 1, wherein: The constructing of the optimization model based on the angle change of the autonomous driving vehicle relative to the road surface using the high-precision map data and the road surface marking segmentation data comprises: Determining road surface marking attributes of the road surface marking segmentation data; Based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attributes of the road surface marking segmentation data, an optimization model corresponding to the road surface marking attributes is constructed using the high-precision map data and the road surface marking segmentation data.

6. The method of claim 5, wherein: The constructing of an optimization model corresponding to the road surface marking attribute by using the high-precision map data and the road surface marking segmentation data based on the angle change of the autonomous driving vehicle relative to the road surface and the road surface marking attribute of the road surface marking segmentation data comprises: If the road surface marking attribute is a linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, a point-line error model is constructed using the high-precision map data and the road surface marking segmentation data; If the road surface marking attribute is a non-linear road surface marking, based on the angle change of the autonomous driving vehicle relative to the road surface, a 3D point-3D point error model is constructed using the high-precision map data and the road surface marking segmentation data.

7. The method of claim 1, wherein: Determining the positioning result of the autonomous driving vehicle according to the relative deviation between the road sign segmentation data and the high-precision map data, and the initial posture data includes: According to the relative deviation between the road sign segmentation data and the high-precision map data, the initial posture data is corrected to obtain corrected posture data; The positioning result of the autonomous driving vehicle is determined based on the corrected posture data.

8. A positioning device for an autonomous driving vehicle, wherein: The device comprises: An acquisition unit, used to acquire initial posture data of the autonomous driving vehicle, and high-precision map data and road sign segmentation data corresponding to the initial posture data; A first determination unit, configured to determine an angle change of the autonomous driving vehicle relative to a road surface according to the high-precision map data and the road surface marking segmentation data; an optimization unit, configured to construct an optimization model using the high-precision map data and the road surface marking segmentation data based on an angle change of the autonomous driving vehicle relative to a road surface, and to determine a relative deviation between the road surface marking segmentation data and the high-precision map data using the optimization model; The second determination unit is used to determine the positioning result of the autonomous driving vehicle according to the relative deviation between the road surface marking segmentation data and the high-precision map data, and the initial posture data.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.

Images