Fusion positioning method, device and electronic equipment for autonomous driving vehicle

Abstract

The present application discloses a fusion positioning method, device and electronic equipment for an autonomous driving vehicle, the method comprising: when a high-precision positioning signal is unavailable, obtaining the fusion positioning position at the current moment, the track deduction position at the next moment and the corresponding lateral position error; using the lateral position error to correct the track deduction position at the next moment; compensating the corrected position at the next moment according to the fusion positioning position at the current moment, the track deduction position at the next moment and the corrected position at the next moment; obtaining preset vehicle speed error information, and determining the confidence of the compensated position at the next moment in combination with the time interval between the current moment and the next moment; inputting the compensated position at the next moment and the corresponding confidence as observation values ​​into a filter for fusion positioning. The present application corrects longitudinal positioning based on visual lateral positioning error, provides additional observation input to the filter, ensures the stability of the filter, and avoids positioning jumps.

Description

Technical Field

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

[0002] The development of computer vision technology allows autonomous vehicles to use more element information in images for positioning. For example, the visual SLAM (Simultaneous Localization And Mapping) method, which has been widely used in recent years, extracts feature points in the image and tracks the feature points to establish a point cloud map, and then relocates the vehicle based on the established point cloud map. Another example is positioning based on matching the semantic elements of the road surface in the image, such as lane lines, road arrows, stop lines, etc. with high-precision maps. Both positioning methods can compensate to a certain extent for the problem of large positioning errors caused by interference with high-precision positioning signals such as GNSS (Global Navigation Satellite System), and prevent large cumulative errors in self-vehicle positioning by providing effective observation information to the Kalman filter.

[0003] However, the above solutions have at least the following problems:

[0004] 1) Due to the influence of lighting, dynamic objects, etc., the feature point-based visual SLAM method can easily cause feature point tracking loss in actual mapping and positioning, resulting in the inability to output effective positioning information;

[0005] 2) Map storage and importing require a lot of resources. If the autonomous vehicle is traveling in a large area, the point cloud map of a large area will often have large errors, and the feature point matching calculation will have unpredictable delays. Therefore, due to the above two problems, the above visual SLAM method technology is only applicable to low-speed and closed scenes;

[0006] 3) Since there are few lane lines and stop lines on the road, and the lane lines can only provide correction information for lateral positioning errors, when the vehicle speed exceeds a certain threshold, a large jump will occur between two adjacent longitudinal positioning results, thereby affecting the stability of the positioning results output by the Kalman filter. Summary of the invention

[0007] The embodiments of the present application provide a fusion positioning method, device and electronic device for an autonomous driving vehicle to improve the stability of the autonomous driving vehicle's positioning and avoid positioning jumps.

[0008] The present application embodiment adopts the following technical solutions:

[0009] In a first aspect, an embodiment of the present application provides a fusion positioning method for an autonomous driving vehicle, wherein the method includes:

[0010] When the high-precision positioning signal is unavailable, obtain the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, wherein the visual lateral positioning error includes the lateral position error;

[0011] Correcting the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment;

[0012] According to the fused positioning position at the current moment, the track derivation position at the next moment and the corrected position at the next moment, compensating the corrected position at the next moment to obtain the compensated position at the next moment;

[0013] Acquire preset vehicle speed error information, and determine the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment;

[0014] The compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the automatic driving vehicle at the next moment.

[0015] Optionally, when the high-precision positioning signal is unavailable, before obtaining the fused positioning position of the autonomous driving vehicle at the current moment, and the track deduction position at the next moment and the corresponding visual lateral positioning error, the method further includes:

[0016] Determine whether the fused positioning position at the current moment enters a preset signal interference area;

[0017] If yes, determining that the high-precision positioning signal is in an unavailable state;

[0018] Otherwise, it is determined that the high-precision positioning signal is in an available state.

[0019] Optionally, when the high-precision positioning signal is unavailable, obtaining the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error includes:

[0020] Acquire a current road image corresponding to the autonomous driving vehicle;

[0021] Performing lane line recognition on the current road image using a preset lane line recognition algorithm to obtain a lane line recognition result;

[0022] Obtain local high-precision map data corresponding to the autonomous driving vehicle, and use the lane line data in the local high-precision map data and the lane line recognition result to determine the visual lateral positioning error.

[0023] Optionally, compensating the corrected position at the next moment according to the fused positioning position at the current moment, the track derivation position at the next moment, and the corrected position at the next moment to obtain the compensated position at the next moment includes:

[0024] Determine the distance between the fused positioning position at the current moment and the track derivation position at the next moment as a first distance, and determine the distance between the fused positioning position at the current moment and the corrected position at the next moment as a second distance;

[0025] determining a difference between the first distance and the second distance;

[0026] The corrected position at the next moment is compensated according to the difference between the first distance and the second distance to obtain the compensated position at the next moment.

[0027] Optionally, determining the distance between the fused positioning position at the current moment and the track derivation position at the next moment includes:

[0028] Obtaining information on the actual vehicle speed and the preset vehicle speed error at the current moment;

[0029] Compensating the actual vehicle speed at the current moment by using the preset vehicle speed error information to obtain the compensated vehicle speed at the current moment;

[0030] According to the compensated vehicle speed at the current moment and the time interval between the current moment and the next moment, the displacement between the current moment and the next moment is determined as the distance between the fused positioning position at the current moment and the track deduction position at the next moment.

[0031] Optionally, obtaining preset vehicle speed error information includes:

[0032] When the high-precision positioning signal is available, obtaining the actual speed of the autonomous driving vehicle and the fused speed output by the Kalman filter;

[0033] The preset vehicle speed error information is determined according to the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter.

[0034] Optionally, the visual lateral positioning error also includes a heading angle error, and the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into a Kalman filter for fusion positioning, and obtaining the fusion positioning result of the autonomous driving vehicle at the next moment includes:

[0035] Get the compensated vehicle speed at the next moment;

[0036] The compensated vehicle speed and the heading angle error at the next moment, together with the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment, are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the autonomous driving vehicle at the next moment.

[0037] In a second aspect, an embodiment of the present application further provides a fusion positioning device for an autonomous driving vehicle, wherein the device comprises:

[0038] An acquisition unit, used to acquire the fused positioning position of the autonomous driving vehicle at the current moment, the track deduction position at the next moment, and the corresponding visual lateral positioning error when the high-precision positioning signal is unavailable, wherein the visual lateral positioning error includes a lateral position error;

[0039] A correction unit, used to correct the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment;

[0040] a compensation unit, configured to compensate the corrected position at the next moment according to the fused positioning position at the current moment, the track derivation position at the next moment, and the corrected position at the next moment, so as to obtain the compensated position at the next moment;

[0041] A first determining unit, configured to obtain preset vehicle speed error information, and determine a confidence level corresponding to a compensated position at a next moment according to the preset vehicle speed error information and a time interval between the current moment and the next moment;

[0042] A fusion positioning unit is used to input the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into a Kalman filter for fusion positioning, so as to obtain a fusion positioning result of the autonomous driving vehicle at the next moment.

[0043] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0044] Processor; and

[0045] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.

[0046] 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.

[0047] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the fusion positioning method of the autonomous driving vehicle in the embodiments of the present application first obtains the fusion positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error when the high-precision positioning signal is unavailable, and the visual lateral positioning error includes the lateral position error; then the track deduction position at the next moment is corrected using the lateral position error to obtain the corrected position at the next moment; then, according to the fusion positioning position at the current moment, the track deduction position at the next moment and the corrected position at the next moment, the corrected position at the next moment is compensated to obtain the compensated position at the next moment; then, the preset vehicle speed error information is obtained, and according to the preset vehicle speed error information and the time interval between the current moment and the next moment, the confidence corresponding to the compensated position at the next moment is determined; finally, the compensated position at the next moment and the confidence corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the autonomous driving vehicle at the next moment. The fusion positioning method of the autonomous driving vehicle in the embodiment of the present application corrects the longitudinal positioning based on the visual lateral positioning error. When the high-precision positioning signal is interfered with, it can provide additional observation input to the filter, thereby ensuring the stability of the filter, reducing the cumulative positioning error, and avoiding the occurrence of positioning jumps. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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:

[0049] Figure 1 A schematic diagram of a flow chart of a fusion positioning method for an autonomous driving vehicle in an embodiment of the present application;

[0050] Figure 2 This is a schematic diagram of compensating for a corrected position in an embodiment of the present application;

[0051] Figure 3 This is a schematic diagram of the structure of a fusion positioning device for an autonomous driving vehicle in an embodiment of the present application;

[0052] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0053] 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.

[0054] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0055] The present application embodiment provides a fusion positioning method for an autonomous driving vehicle, such as Figure 1 As shown, a flow chart of a fusion 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 S150:

[0056] Step S110, when the high-precision positioning signal is unavailable, obtain the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, wherein the visual lateral positioning error includes the lateral position error.

[0057] The fusion positioning method for the autonomous driving vehicle in the embodiment of the present application is mainly used in scenarios where the quality of high-precision positioning information, such as GNSS signals, is poor. When the high-precision positioning signal is interfered with and is unavailable, the embodiment of the present application needs to use visual technology to achieve the fusion positioning of the autonomous driving vehicle to ensure that the vehicle can maintain stable driving within a certain period of time.

[0058] Specifically, it is necessary to first obtain the fused positioning position of the autonomous driving vehicle at the current moment. The fused positioning position here can be regarded as a relatively accurate position after the fusion processing has been completed at the current moment. Since lane keeping is often required in autonomous driving scenarios, that is, to ensure that the vehicle travels on the center line of the lane, the fused positioning position at the current moment can be regarded as a position on the center line of the lane.

[0059] In addition, in order to realize the vehicle positioning at the next moment, it is also necessary to obtain the vehicle's track deduction position at the next moment and the corresponding visual lateral positioning error. The track deduction position is the position of the vehicle at the next moment predicted based on the vehicle's position at the current moment combined with the vehicle's speed information, etc. The visual lateral positioning error refers to the vehicle's lateral posture deviation, which may specifically include the vehicle's position deviation and angle deviation relative to the lane centerline.

[0060] Step S120, using the lateral position error to correct the track deduction position at the next moment to obtain the corrected position at the next moment.

[0061] Since the track deduced position at the next moment is only the result of preliminary prediction and has a certain positioning error, it is necessary to correct the lateral positioning error of the track deduced position in combination with the lateral position error in the visual lateral positioning error to obtain the corrected position at the next moment.

[0062] Step S130, compensating the corrected position at the next moment according to the fused positioning position at the current moment, the track deduction position at the next moment and the corrected position at the next moment to obtain the compensated position at the next moment.

[0063] The above steps only complete the correction of the lateral position error of the track deduction position at the next moment, but in the actual positioning scenario, the corrected position at the next moment may also have a longitudinal position error, that is, a position error generated in the direction of vehicle travel. Therefore, the embodiment of the present application is based on the fused positioning position at the current moment, the track deduction position at the next moment, and the corrected position at the next moment after correcting the visual lateral positioning error, and further compensates and corrects the longitudinal positioning error of the corrected position at the next moment, thereby obtaining the compensated position at the next moment.

[0064] Step S140, obtaining preset vehicle speed error information, and determining the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment.

[0065] The compensated position at the next moment obtained in the above steps is not necessarily reliable. Its credibility is mainly affected by the speed error. For example, if the speed error is larger and the time interval is longer, the resulting track deduction position error will also be larger, resulting in a lower confidence level of the compensated position obtained based on this. Therefore, the embodiment of the present application determines the speed error information of the vehicle in advance, and then uses the preset speed error information, combined with the time interval between the current moment and the next moment, to determine the confidence level of the compensated position at the next moment obtained in the above steps.

[0066] Step S150, input the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into the Kalman filter for fusion positioning, and obtain the fusion positioning result of the automatic driving vehicle at the next moment.

[0067] Based on the compensated position at the next moment and the corresponding confidence level obtained in the above steps, the two can be input into the Kalman filter or extended Kalman filter as additional observation information for fusion positioning processing. Due to the introduction of additional observation information, the Kalman filter can output a more stable fusion positioning result, thereby realizing stable positioning of the autonomous driving vehicle when the GNSS and other positioning signals are interfered with, and avoiding the occurrence of positioning jumps.

[0068] The fusion positioning method of the autonomous driving vehicle in the embodiment of the present application corrects the longitudinal positioning based on the visual lateral positioning error. When the high-precision positioning signal is interfered with, it can provide additional observation input to the filter, thereby ensuring the stability of the filter, reducing the cumulative positioning error, and avoiding the occurrence of positioning jumps.

[0069] In one embodiment of the present application, when the high-precision positioning signal is in an unavailable state, before obtaining the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, the method also includes: determining whether the fused positioning position at the current moment enters a preset signal interference area; if so, determining that the high-precision positioning signal is in an unavailable state; otherwise, determining that the high-precision positioning signal is in an available state.

[0070] When determining whether a high-precision positioning signal is in an unavailable state, the embodiment of the present application can determine in advance the location area where the high-precision positioning signal is easily interfered with or has poor quality. For example, when an autonomous driving vehicle enters a round bridge, tunnel, etc., the GNSS positioning signal is more easily interfered with. At this time, the GNSS positioning signal is in an unavailable state, and other positioning technologies such as vision are needed to assist in positioning.

[0071] Based on this, the embodiments of the present application can use these areas where actual signals are interfered with as the basis for determining whether the GNSS positioning signal is in an unavailable state. For example, the entry and exit points of the signal interference area can be set in advance on the map. When the current position of the autonomous driving vehicle is between the entry and exit points of the signal interference area, it can be considered that the GNSS positioning signal at this time is in an unavailable state. Compared with the method of judging the signal quality based on the state of the GNSS positioning signal itself, this method can prevent errors caused by relying solely on the GNSS signal itself, and is more accurate and reliable.

[0072] In one embodiment of the present application, when the high-precision positioning signal is unavailable, obtaining the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error includes: obtaining a current road image corresponding to the autonomous driving vehicle; performing lane line recognition on the current road image using a preset lane line recognition algorithm to obtain a lane line recognition result; obtaining local high-precision map data corresponding to the autonomous driving vehicle, and determining the visual lateral positioning error using the lane line data in the local high-precision map data and the lane line recognition result.

[0073] When obtaining the visual lateral positioning error corresponding to the track deduction position at the next moment, the embodiment of the present application can first obtain the current road image corresponding to the autonomous driving vehicle, and then use a preset lane line recognition algorithm to identify the lane lines in the current road image to obtain a lane line recognition result. The preset lane line recognition algorithm can be trained based on an existing convolutional neural network model such as LaneNet. Of course, those skilled in the art can also flexibly select other models according to actual needs, which is not specifically limited here.

[0074] Afterwards, the local high-precision map data corresponding to the autonomous driving vehicle can be obtained in combination with the current positioning of the autonomous driving vehicle. The local high-precision map data provides high-precision lane structured information. Therefore, the lane lines identified by the lane line recognition model can be compared with the corresponding lane lines in the local high-precision map data, including the calculation of position deviation and angle deviation, so as to obtain the lateral positioning error of the visual positioning algorithm.

[0075] In one embodiment of the present application, compensating the corrected position at the next moment according to the fused positioning position at the current moment, the track deduction position at the next moment and the corrected position at the next moment to obtain the compensated position at the next moment includes: determining the distance between the fused positioning position at the current moment and the track deduction position at the next moment as the first distance, and determining the distance between the fused positioning position at the current moment and the corrected position at the next moment as the second distance; determining the difference between the first distance and the second distance; and compensating the corrected position at the next moment according to the difference between the first distance and the second distance to obtain the compensated position at the next moment.

[0076] In order to facilitate the understanding of the embodiments of the present application, Figure 2 As shown, a schematic diagram of compensating the corrected position in an embodiment of the present application is provided. Here, it mainly involves the fusion positioning position P at the current moment. k (marked as position point A), the next moment's track deduction position P k+1 predict(marked as position point B) and the corrected position P at the next moment k+1 vision (Marked as position point C) There are three position points. Since the fused positioning position at the current moment is the positioning result after Kalman filter fusion processing, position point A is located on the center line of the lane, and the corrected position at the next moment has been corrected for the lateral position error, so position point C is also located on the center line of the lane. Then, these three position points A, B, and C will form a right triangle after connecting each other, among which the line connecting position point A to position point C and the line connecting position point B to position point C are two right-angled sides, and the line connecting position point A to position point B is the hypotenuse.

[0077] According to the Pythagorean theorem, the hypotenuse is always greater than the right angle side, so the line P from point A to point B is k P k+1 predict will always be greater than the line P from point A to point C k P k+1 vision , that is, the first distance of the embodiment of the present application is greater than the second distance, then the difference between the two will always be greater than 0, so the compensation value of the longitudinal positioning error is a positive value. When the visual lateral positioning error is larger, that is, the distance from position point B to position point C is larger, then the hypotenuse will also be larger, which will lead to a larger compensation value obtained by the above calculation, that is, a larger longitudinal positioning error.

[0078] Therefore, the embodiment of the present application estimates the longitudinal positioning error through the visual lateral positioning error, and compensates for the longitudinal positioning error according to the estimated value, thereby avoiding the occurrence of positioning jumps due to the loss or interference of high-precision positioning signals such as GNSS, and improving the positioning stability of the autonomous driving vehicle.

[0079] In one embodiment of the present application, determining the distance between the fused positioning position at the current moment and the track deduction position at the next moment includes: obtaining the actual vehicle speed at the current moment and preset vehicle speed error information; using the preset vehicle speed error information to compensate the actual vehicle speed at the current moment to obtain the compensated vehicle speed at the current moment; and determining the displacement between the current moment and the next moment based on the compensated vehicle speed at the current moment and the time interval between the current moment and the next moment as the distance between the fused positioning position at the current moment and the track deduction position at the next moment.

[0080] When determining the distance between the fused positioning position at the current moment and the track deduction position at the next moment, the embodiment of the present application may use a track deduction algorithm for calculation. The track deduction algorithm mainly predicts the position of the vehicle at the next moment based on the vehicle position and speed information at the current moment. Since there is a certain error in the vehicle speed, the speed error information determined in advance may be used to perform error compensation on the actual vehicle speed at the current moment to obtain the compensated vehicle speed, and then the distance between the fused positioning position at the current moment and the track deduction position at the next moment is calculated in combination with the time interval between the two moments.

[0081] In one embodiment of the present application, obtaining the preset vehicle speed error information includes: when a high-precision positioning signal is available, obtaining the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter; and determining the preset vehicle speed error information based on the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter.

[0082] When determining the preset vehicle speed error information, the embodiment of the present application can determine it when the GNSS positioning signal is in an available state. First, the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter at the corresponding moment are obtained. The actual vehicle speed refers to the actual chassis speed obtained. The fused speed output by the Kalman filter can be regarded as a relatively accurate speed. Therefore, by comparing the actual vehicle speed with the fused speed, the speed error corresponding to the actual vehicle speed can be obtained. Since the actual vehicle speed may fluctuate within a certain range, the speed error calculated here can be a speed error interval. Using the error interval instead of an error value can provide a basis for calculating the confidence level of the position.

[0083] The embodiment of the present application can specifically adopt two methods when calculating the vehicle speed error. One method can be an absolute error, that is, the actual vehicle speed is directly subtracted from the corresponding fused speed. The other method is a proportional error, that is, the actual vehicle speed is subtracted from the corresponding fused speed and then divided by the fused speed. Of course, those skilled in the art can adaptively select which method to use to calculate the vehicle speed error according to the actual situation of the vehicle, and no specific limitation is made here.

[0084] In one embodiment of the present application, the visual lateral positioning error also includes a heading angle error, and the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the autonomous driving vehicle at the next moment, including: obtaining the compensated vehicle speed at the next moment; inputting the compensated vehicle speed at the next moment and the heading angle error, together with the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the autonomous driving vehicle at the next moment.

[0085] The visual lateral positioning error of the embodiment of the present application includes not only the lateral position error but also the heading angle error. In order to provide more observation information to the Kalman filter, the embodiment of the present application can input the heading angle error and the compensated vehicle speed as additional observation values ​​into the Kalman filter for fusion positioning, thereby further improving the positioning stability of the Kalman filter.

[0086] The fusion positioning method for the autonomous driving vehicle of the present application further corrects the longitudinal position using the correction result of the visual lateral positioning error, and calculates the confidence using the vehicle speed error information. When the GNSS signal is interfered with (regardless of the duration), the longitudinally corrected position and the corresponding confidence are input into the Kalman filter as additional observation information for fusion positioning, thereby ensuring the positioning stability of the Kalman filter, reducing the cumulative error, and preventing positioning jumps.

[0087] The present application also provides a fusion positioning device 300 for an autonomous driving vehicle, such as Figure 3 As shown, a schematic diagram of the structure of a fusion positioning device for an autonomous driving vehicle in an embodiment of the present application is provided, wherein the device at least includes: an acquisition unit 310, a correction unit 320, a compensation unit 330, a first determination unit 340, and a fusion positioning unit 350, wherein:

[0088] The acquisition unit 310 is used to acquire the fused positioning position of the autonomous driving vehicle at the current moment, the track deduction position at the next moment, and the corresponding visual lateral positioning error when the high-precision positioning signal is unavailable, wherein the visual lateral positioning error includes a lateral position error;

[0089] A correction unit 320, configured to correct the track derivation position at the next moment by using the lateral position error to obtain a corrected position at the next moment;

[0090] The compensation unit 330 is used to compensate the corrected position at the next moment according to the fused positioning position at the current moment, the track derivation position at the next moment and the corrected position at the next moment to obtain the compensated position at the next moment;

[0091] A first determining unit 340 is used to obtain preset vehicle speed error information, and determine the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment;

[0092] The fusion positioning unit 350 is used to input the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into the Kalman filter for fusion positioning, so as to obtain the fusion positioning result of the autonomous driving vehicle at the next moment.

[0093] In one embodiment of the present application, the device also includes: a second determination unit, used to determine whether the fused positioning position at the current moment enters a preset signal interference area; if so, determine that the high-precision positioning signal is in an unavailable state; otherwise, determine that the high-precision positioning signal is in an available state.

[0094] In one embodiment of the present application, the acquisition unit 310 is specifically used to: acquire a current road image corresponding to the autonomous driving vehicle; perform lane line recognition on the current road image using a preset lane line recognition algorithm to obtain a lane line recognition result; acquire local high-precision map data corresponding to the autonomous driving vehicle, and use the lane line data in the local high-precision map data and the lane line recognition result to determine the visual lateral positioning error.

[0095] In one embodiment of the present application, the compensation unit 330 is specifically used to: determine the distance between the fused positioning position at the current moment and the track deduction position at the next moment as the first distance, and determine the distance between the fused positioning position at the current moment and the corrected position at the next moment as the second distance; determine the difference between the first distance and the second distance; and compensate the corrected position at the next moment according to the difference between the first distance and the second distance to obtain the compensated position at the next moment.

[0096] In one embodiment of the present application, the compensation unit 330 is specifically used to: obtain the actual vehicle speed at the current moment and the preset vehicle speed error information; use the preset vehicle speed error information to compensate the actual vehicle speed at the current moment to obtain the compensated vehicle speed at the current moment; determine the displacement between the current moment and the next moment according to the compensated vehicle speed at the current moment and the time interval between the current moment and the next moment, as the distance between the fused positioning position at the current moment and the track deduction position at the next moment.

[0097] In one embodiment of the present application, the first determination unit 340 is specifically used to: obtain the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter when the high-precision positioning signal is available; and determine the preset vehicle speed error information based on the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter.

[0098] In one embodiment of the present application, the visual lateral positioning error also includes a heading angle error, and the fusion positioning unit 350 is specifically used to: obtain the compensated vehicle speed at the next moment; input the compensated vehicle speed at the next moment and the heading angle error, together with the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into the Kalman filter for fusion positioning, to obtain the fusion positioning result of the autonomous driving vehicle at the next moment.

[0099] It can be understood that the above-mentioned fusion positioning device of the autonomous driving vehicle can implement the various steps of the fusion positioning method of the autonomous driving vehicle provided in the aforementioned embodiments. The relevant explanations on the fusion positioning method of the autonomous driving vehicle are applicable to the fusion positioning device of the autonomous driving vehicle and will not be repeated here.

[0100] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 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.

[0101] 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 4 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.

[0102] 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.

[0103] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a fusion 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:

[0104] When the high-precision positioning signal is unavailable, obtain the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, wherein the visual lateral positioning error includes the lateral position error;

[0105] Correcting the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment;

[0106] According to the fused positioning position at the current moment, the track derivation position at the next moment and the corrected position at the next moment, compensating the corrected position at the next moment to obtain the compensated position at the next moment;

[0107] Acquire preset vehicle speed error information, and determine the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment;

[0108] The compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the automatic driving vehicle at the next moment.

[0109] The above application Figure 1The method performed by the fusion 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 an instruction in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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 may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a 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.

[0110] The electronic device may also perform Figure 1 A method for executing a fusion positioning device of an autonomous driving vehicle in a Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0111] 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 fusion positioning device of the autonomous driving vehicle in the illustrated embodiment is specifically used to perform:

[0112] When the high-precision positioning signal is unavailable, obtain the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, wherein the visual lateral positioning error includes the lateral position error;

[0113] Correcting the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment;

[0114] According to the fused positioning position at the current moment, the track derivation position at the next moment and the corrected position at the next moment, compensating the corrected position at the next moment to obtain the compensated position at the next moment;

[0115] Acquire preset vehicle speed error information, and determine the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment;

[0116] The compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the automatic driving vehicle at the next moment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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 fusion positioning method for an autonomous driving vehicle, wherein: The method comprises: When the high-precision positioning signal is unavailable, obtain the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error, wherein the visual lateral positioning error includes the lateral position error; Correcting the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment; According to the fused positioning position at the current moment, the track derivation position at the next moment and the corrected position at the next moment, compensating the corrected position at the next moment to obtain the compensated position at the next moment; Acquire preset vehicle speed error information, and determine the confidence corresponding to the compensated position at the next moment according to the preset vehicle speed error information and the time interval between the current moment and the next moment; The compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the automatic driving vehicle at the next moment.

2. The method of claim 1, wherein: Before obtaining the fused positioning position of the autonomous driving vehicle at the current moment, and the track deduction position and the corresponding visual lateral positioning error at the next moment when the high-precision positioning signal is unavailable, the method further includes: Determine whether the fused positioning position at the current moment enters a preset signal interference area; If yes, determining that the high-precision positioning signal is in an unavailable state; Otherwise, it is determined that the high-precision positioning signal is in an available state.

3. The method of claim 1, wherein: When the high-precision positioning signal is unavailable, obtaining the fused positioning position of the autonomous driving vehicle at the current moment, as well as the track deduction position at the next moment and the corresponding visual lateral positioning error includes: Acquire a current road image corresponding to the autonomous driving vehicle; Performing lane line recognition on the current road image using a preset lane line recognition algorithm to obtain a lane line recognition result; Obtain local high-precision map data corresponding to the autonomous driving vehicle, and use the lane line data in the local high-precision map data and the lane line recognition result to determine the visual lateral positioning error.

4. The method of claim 1, wherein: The compensating the corrected position at the next moment according to the fused positioning position at the current moment, the track derivation position at the next moment, and the corrected position at the next moment to obtain the compensated position at the next moment includes: Determine the distance between the fused positioning position at the current moment and the track derivation position at the next moment as a first distance, and determine the distance between the fused positioning position at the current moment and the corrected position at the next moment as a second distance; determining a difference between the first distance and the second distance; The corrected position at the next moment is compensated according to the difference between the first distance and the second distance to obtain the compensated position at the next moment.

5. The method of claim 4, wherein: Determining the distance between the fused positioning position at the current moment and the track derivation position at the next moment includes: Obtaining information on the actual vehicle speed and the preset vehicle speed error at the current moment; Compensating the actual vehicle speed at the current moment by using the preset vehicle speed error information to obtain the compensated vehicle speed at the current moment; According to the compensated vehicle speed at the current moment and the time interval between the current moment and the next moment, the displacement between the current moment and the next moment is determined as the distance between the fused positioning position at the current moment and the track deduction position at the next moment.

6. The method of claim 1, wherein: The obtaining of preset vehicle speed error information comprises: When the high-precision positioning signal is available, obtaining the actual speed of the autonomous driving vehicle and the fused speed output by the Kalman filter; The preset vehicle speed error information is determined according to the actual vehicle speed of the autonomous driving vehicle and the fused speed output by the Kalman filter.

7. The method of claim 1, wherein: The visual lateral positioning error also includes a heading angle error. The compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment are input as observation information into a Kalman filter for fusion positioning. The fusion positioning result of the autonomous driving vehicle at the next moment is obtained, which includes: Get the compensated vehicle speed at the next moment; The compensated vehicle speed and the heading angle error at the next moment, together with the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment, are input as observation information into the Kalman filter for fusion positioning to obtain the fusion positioning result of the autonomous driving vehicle at the next moment.

8. A fusion positioning device for an autonomous driving vehicle, wherein: The device comprises: An acquisition unit, used to acquire the fused positioning position of the autonomous driving vehicle at the current moment, the track deduction position at the next moment, and the corresponding visual lateral positioning error when the high-precision positioning signal is unavailable, wherein the visual lateral positioning error includes a lateral position error; A correction unit, used to correct the track deduction position at the next moment by using the lateral position error to obtain the corrected position at the next moment; a compensation unit, configured to compensate the corrected position at the next moment according to the fused positioning position at the current moment, the track derivation position at the next moment, and the corrected position at the next moment, so as to obtain the compensated position at the next moment; A first determining unit, configured to obtain preset vehicle speed error information, and determine a confidence level corresponding to a compensated position at a next moment according to the preset vehicle speed error information and a time interval between the current moment and the next moment; A fusion positioning unit is used to input the compensated position at the next moment and the confidence level corresponding to the compensated position at the next moment as observation information into a Kalman filter for fusion positioning, so as to obtain a fusion positioning result of the autonomous driving vehicle at the next moment.

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