Training method and device for positioning confidence prediction model for autonomous driving

Abstract

The present application discloses a method and device for training a positioning confidence prediction model for autonomous driving, the method comprising: obtaining inertial navigation RTK information and corresponding high-precision positioning information, the inertial navigation RTK information including inertial navigation RTK positioning information; determining the positioning error of the inertial navigation RTK positioning information based on the high-precision positioning information; determining the confidence of the inertial navigation RTK positioning information based on the positioning error of the inertial navigation RTK positioning information; and training a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model. The training method for a positioning confidence prediction model for autonomous driving in an embodiment of the present application converts the positioning error of the inertial navigation RTK positioning information into the corresponding positioning confidence, and uses this to train the positioning confidence prediction model, thereby improving the accuracy of the positioning confidence prediction and providing strong support for subsequent fusion positioning.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a training method and device for a positioning confidence prediction model for autonomous driving. Background Art

[0002] In order to achieve high-precision positioning of autonomous vehicles, it is often necessary to fuse the data of multiple sensors. When performing fusion positioning, it is necessary to know the positioning information and corresponding confidence of each sensor. The accuracy of the confidence will directly affect the accuracy of the fusion positioning.

[0003] A single RTK (Real-time kinematic) positioning state cannot meet the needs of autonomous driving. For example, on complex urban roads, large positioning errors may still occur even when the RTK positioning state is a fixed solution.

[0004] The existing solution directly models the system based on parameters such as RTK positioning status, which is relatively complex and cannot obtain accurate positioning reliability. Summary of the Invention

[0005] The embodiments of the present application provide a method and apparatus for training a positioning confidence prediction model for autonomous driving to improve the accuracy of positioning confidence prediction.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for training a positioning confidence prediction model for autonomous driving, wherein the method comprises:

[0008] Acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information;

[0009] Determine the positioning error of the inertial navigation RTK positioning information according to the high-precision positioning information;

[0010] Determining the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information;

[0011] The inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information are used to train a positioning confidence prediction model to obtain a trained positioning confidence prediction model.

[0012] Optionally, obtaining inertial navigation RTK information and corresponding high-precision positioning information includes:

[0013] Obtaining high-precision inertial navigation data and base station data corresponding to the inertial navigation RTK information;

[0014] Post-processing and solving the high-precision inertial navigation data and the base station data to obtain the high-precision positioning information.

[0015] Optionally, determining the confidence of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information includes:

[0016] If the positioning error of the inertial navigation RTK positioning information is not greater than a first preset error threshold, determining the confidence level of the inertial navigation RTK positioning information to be a first confidence level;

[0017] If the positioning error of the inertial navigation RTK positioning information is not less than a second preset error threshold, determining the confidence level of the inertial navigation RTK positioning information to be a second confidence level;

[0018] If the positioning error of the inertial navigation RTK positioning information is greater than the first preset error threshold and less than the second preset error threshold, determining that the confidence level of the inertial navigation RTK positioning information is a third confidence level;

[0019] The first preset error threshold is smaller than the second preset error threshold, the first confidence level is larger than the third confidence level, and the third confidence level is larger than the second confidence level.

[0020] Optionally, the inertial navigation RTK information further includes the absolute time of the inertial navigation RTK information, the RTK positioning status, the horizontal position precision factor, and the number of satellites. The training of the positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain the trained positioning confidence prediction model includes:

[0021] Based on the power-on time of the inertial navigation RTK, converting the absolute time of the inertial navigation RTK information into relative continuous time;

[0022] The relative continuous time of the inertial navigation RTK information, the RTK positioning state, the horizontal position precision factor, and the number of satellites are used as inputs of the positioning confidence prediction model, and the confidence of the inertial navigation RTK positioning information is used as a supervision signal to train the positioning confidence prediction model to obtain a trained positioning confidence prediction model.

[0023] Optionally, the location reliability prediction model adopts an LSTM long short-term memory network.

[0024] In a second aspect, an embodiment of the present application further provides a fusion positioning method for an autonomous driving vehicle, wherein the method includes:

[0025] Acquire current inertial navigation RTK information, where the current inertial navigation RTK information includes absolute time of current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision factor, and number of satellites;

[0026] Based on the current inertial navigation RTK information, using a positioning confidence prediction model to predict the confidence of the current inertial navigation RTK positioning information;

[0027] Performing fusion positioning based on the confidence of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle;

[0028] The positioning confidence prediction model is trained based on any of the aforementioned training methods for the positioning confidence prediction model for autonomous driving.

[0029] In a third aspect, an embodiment of the present application further provides a training device for a positioning confidence prediction model for autonomous driving, wherein the device comprises:

[0030] A first acquisition unit is configured to acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information;

[0031] A first determining unit is configured to determine a positioning error of the inertial navigation RTK positioning information based on the high-precision positioning information;

[0032] A second determining unit is configured to determine the confidence of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information;

[0033] The training unit is used to train a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model.

[0034] In a fourth aspect, an embodiment of the present application further provides a fusion positioning device for an autonomous driving vehicle, wherein the device includes:

[0035] A second acquisition unit is used to acquire current inertial navigation RTK information, where the current inertial navigation RTK information includes the absolute time of the current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision factor, and number of satellites;

[0036] A prediction unit, configured to predict the confidence of the current inertial navigation RTK positioning information using a positioning confidence prediction model based on the current inertial navigation RTK information;

[0037] a fusion positioning unit, configured to perform fusion positioning based on the confidence level of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle;

[0038] The positioning reliability prediction model is obtained by training based on the aforementioned training device for the positioning reliability prediction model for autonomous driving.

[0039] In a fifth aspect, an embodiment of the present application further provides an electronic device, including:

[0040] processor; and

[0041] A memory arranged to store computer-executable instructions, which, when executed, cause the processor to execute any of the aforementioned methods for training a positioning confidence prediction model for autonomous driving, or to execute the aforementioned fusion positioning method for an autonomous driving vehicle.

[0042] In a sixth 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 applications, the electronic device executes any of the aforementioned training methods for the positioning confidence prediction model for autonomous driving, or is used to execute the aforementioned fusion positioning method for the autonomous driving vehicle.

[0043] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the training method of the positioning confidence prediction model for autonomous driving in the embodiments of the present application first obtains inertial navigation RTK information and corresponding high-precision positioning information, and the inertial navigation RTK information includes inertial navigation RTK positioning information; then determines the positioning error of the inertial navigation RTK positioning information based on the high-precision positioning information; then determines the confidence of the inertial navigation RTK positioning information based on the positioning error of the inertial navigation RTK positioning information; finally, uses the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to train the positioning confidence prediction model to obtain the trained positioning confidence prediction model. The training method of the positioning confidence prediction model for autonomous driving in the embodiments of the present application converts the positioning error of the inertial navigation RTK positioning information into the corresponding positioning confidence, and uses this to train the positioning confidence prediction model, thereby improving the accuracy of the positioning confidence prediction and providing strong support for subsequent fusion positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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:

[0045] Figure 1 Schematic diagram of a flow chart of a method for training a positioning confidence prediction model for autonomous driving according to an embodiment of the present application;

[0046] Figure 2 This is a flow chart of a fusion positioning method for an autonomous driving vehicle in an embodiment of the present application;

[0047] Figure 3 Schematic diagram of the structure of a training device for a positioning confidence prediction model for autonomous driving according to an embodiment of the present application;

[0048] Figure 4 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;

[0049] Figure 5 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0050] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0051] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0052] The present application embodiment provides a method for training a positioning confidence prediction model for autonomous driving, such as Figure 1 As shown, a flow chart of a method for training a positioning confidence prediction model for autonomous driving in an embodiment of the present application is provided. The method includes at least the following steps S110 to S140:

[0053] Step S110: Acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information.

[0054] The positioning reliability prediction model trained in the embodiment of the present application is mainly used to predict the reliability of the positioning information output by the inertial navigation RTK. Inertial navigation RTK refers to the positioning information output after the IMU (Inertial Measurement Unit) positioning data collected by the inertial navigation device is integrated with the RTK real-time differential algorithm.

[0055] When training the positioning reliability prediction model, the embodiment of the present application needs to first obtain inertial navigation RTK information and corresponding high-precision positioning information. The inertial navigation RTK information can specifically include inertial navigation RTK positioning information, such as specific position and posture, etc., while the high-precision positioning information can be understood as positioning information collected based on high-precision inertial navigation equipment. The high-precision inertial navigation equipment is equipped with a high-precision closed-loop fiber optic gyroscope and acceleration sensor, and the positioning accuracy can reach the centimeter level or even the millimeter level. Therefore, it has higher positioning accuracy than general inertial navigation equipment.

[0056] Step S120: determining a positioning error of the inertial navigation RTK positioning information according to the high-precision positioning information.

[0057] Because high-precision positioning information is collected based on high-precision inertial navigation equipment, it is not affected by the quality of satellite positioning signals, resulting in reliable and highly accurate positioning results. Therefore, the positioning error of the corresponding inertial navigation RTK positioning information can be measured based on this high-precision positioning information. To facilitate subsequent processing, the collected inertial navigation RTK positioning information and the corresponding high-precision positioning information can be time-synchronized, for example, using interpolation methods.

[0058] Step S130 : determining the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information.

[0059] After obtaining the positioning error of the INS RTK positioning information, a conversion strategy is needed to convert the positioning error of the INS RTK positioning information into a corresponding confidence level. The larger the positioning error of the INS RTK positioning information, the lower the corresponding confidence level, and the smaller the positioning error, the higher the corresponding confidence level. Based on this, a conversion strategy can be used to convert the positioning error with a fluctuating range into a confidence level within a fixed range, facilitating subsequent model training and improving the model's generalization ability.

[0060] Step S140 : training a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model.

[0061] After obtaining the confidence level of the INS RTK positioning information, the positioning confidence prediction model can be trained by combining it with INS RTK information from other dimensions. These INS RTK information from other dimensions refers to information other than INS RTK positioning information that is closely related to the prediction of positioning confidence, such as RTK positioning status and number of satellites.

[0062] The training method of the positioning confidence prediction model for autonomous driving in the embodiments of the present application converts the positioning error of the inertial navigation RTK positioning information into the corresponding positioning confidence, and trains the positioning confidence prediction model with this, improving the accuracy of the positioning confidence prediction and providing strong support for subsequent integrated positioning.

[0063] In some embodiments of the present application, the obtaining of the inertial navigation RTK information and the corresponding high-precision positioning information includes: obtaining the high-precision inertial navigation data and base station data corresponding to the inertial navigation RTK information; performing post-processing calculation on the high-precision inertial navigation data and the base station data to obtain the high-precision positioning information.

[0064] In the embodiments of the present application, when obtaining the high-precision positioning information, high-precision inertial navigation data can be collected by using a high-precision inertial navigation device, and the corresponding base station data can be obtained based on a self-built base station. Then, by combining the high-precision inertial navigation data and the corresponding base station data, a custom differential algorithm is used for post-processing to calculate the high-precision positioning information.

[0065] In some embodiments of the present application, the determining of the confidence of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information includes: if the positioning error of the inertial navigation RTK positioning information is not greater than the first preset error threshold, determining the confidence of the inertial navigation RTK positioning information as the first confidence; if the positioning error of the inertial navigation RTK positioning information is not less than the second preset error threshold, determining the confidence of the inertial navigation RTK positioning information as the second confidence; if the positioning error of the inertial navigation RTK positioning information is greater than the first preset error threshold and less than the second preset error threshold, determining the confidence of the inertial navigation RTK positioning information as the third confidence; wherein, the first preset error threshold is less than the second preset error threshold, the first confidence is greater than the third confidence, and the third confidence is greater than the second confidence.

[0066] In the embodiments of the present application, when converting the positioning error Pos error of the inertial navigation RTK positioning information into the corresponding confidence a(t), the following method can be adopted: <0000​​​​​​​​​​Wherein, t is the time after the conversion based on the inertial navigation RTK power-on moment, the first preset error threshold < the second preset error threshold, and the first confidence level > the third confidence level > the second confidence level.

[0071] In actual application scenarios, the above-mentioned first preset error threshold and second preset error threshold can be flexibly set according to the requirements of autonomous driving. For example, the first preset error threshold can be set to 0.2m, and the second preset error threshold can be set to 0.6m. When the positioning error Pos error of the inertial navigation RTK positioning information is less than or equal to 0.2m, it means that the positioning error is very small and the accuracy is very high, so a higher confidence level can be assigned, for example, a value of 1; when the positioning error Pos error of the inertial navigation RTK positioning information is greater than or equal to 0.6m, it means that the positioning error is large and the accuracy is very low, so a lower confidence level can be assigned, for example, a value of 0.

[0072] For the inertial navigation RTK positioning information between the two, the corresponding confidence value can be determined between {0, 1} using methods such as linear interpolation according to the size of the positioning error. The linear interpolation method here can be expressed as:

[0073] a(t)=1-(Pos error-0.2) / (0.6-0.2)

[0074] It can be seen that after the above transformation, the confidence a(t) of the final inertial navigation RTK positioning information is a value distributed between {0,1}. The larger the value, the higher the corresponding confidence.

[0075] Of course, it should be noted that the above transformation strategy is merely an exemplary description, and those skilled in the art can flexibly define other forms of transformation strategies according to actual needs, which are not specifically limited here.

[0076] In some embodiments of the present application, the inertial navigation RTK information also includes the absolute time, RTK positioning status, horizontal position precision factor, and number of satellites of the inertial navigation RTK information. The using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to train the positioning confidence prediction model to obtain the trained positioning confidence prediction model includes: converting the absolute time of the inertial navigation RTK information into relative continuous time based on the power-on time of the inertial navigation RTK; using the relative continuous time, the RTK positioning status, the horizontal position precision factor, and the number of satellites of the inertial navigation RTK information as inputs of the positioning confidence prediction model, and using the confidence of the inertial navigation RTK positioning information as a supervision signal to train the positioning confidence prediction model to obtain the trained positioning confidence prediction model.

[0077] The inertial navigation RTK information in the embodiment of the present application specifically also includes parameters such as the absolute time of the inertial navigation RTK information, RTK positioning status, horizontal position precision factor (HDOP) and the number of satellites. These parameters are all related to the confidence level of the inertial navigation RTK positioning information. Therefore, when training the positioning confidence prediction model, training can be based on these parameters.

[0078] Since the timestamp provided by the inertial navigation RTK is absolute time, in order to facilitate model training, the embodiment of the present application can use the power-on time of the inertial navigation RTK as a reference to convert the absolute time in the inertial navigation RTK information into relative continuous time, and then input it into the positioning confidence prediction model together with the RTK positioning status, HDOP and number of satellites. The confidence of the inertial navigation RTK positioning information is used as output to train the positioning confidence prediction model. When the prediction accuracy of the model meets the preset accuracy requirement, the training is terminated, and the trained positioning confidence prediction model is output.

[0079] In some embodiments of the present application, the location reliability prediction model adopts an LSTM long short-term memory network.

[0080] The positioning reliability prediction model of the embodiment of the present application can be trained using the structure of an LSTM (Long Short-Term Memory) long short-term memory network. LSTM is a special recurrent neural network that has the ability to learn long-term dependencies. The ability of LSTM to remember information for a long time is actually its own attribute, not an ability acquired through learning or training. The RTK positioning status, horizontal position precision factor, number of satellites, etc. in the embodiment of the present application are parameters related to time series, so the use of an LSTM network structure for training is more in line with the needs of actual scenarios.

[0081] Of course, it should be noted that in addition to using LSTM networks to train the location confidence prediction model, traditional BP (Back Propagation) neural networks can also be used for training. Those skilled in the art can flexibly choose according to actual needs, and they are not listed here one by one.

[0082] In some embodiments of the present application, inertial navigation RTK information and corresponding high-precision positioning information can be collected separately in different road scenarios in the city, and then different positioning confidence prediction models can be trained separately according to the differences in road scenarios to meet the accuracy requirements of positioning confidence prediction in different road scenarios.

[0083] The present application also provides a fusion positioning method for an autonomous driving vehicle, such as Figure 2As shown, a flow chart of a fusion positioning method for an autonomous driving vehicle in an embodiment of the present application is provided, wherein the method includes at least the following steps S210 to S230:

[0084] Step S210, obtaining current inertial navigation RTK information, where the current inertial navigation RTK information includes the absolute time of the current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision coefficient, and number of satellites;

[0085] Step S220, based on the current inertial navigation RTK information, using a positioning confidence prediction model to predict the confidence of the current inertial navigation RTK positioning information;

[0086] Step S230, performing fusion positioning based on the confidence level of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle;

[0087] The positioning confidence prediction model is trained based on any of the aforementioned training methods for positioning confidence prediction models for autonomous driving.

[0088] In the real-time positioning scenario of an autonomous vehicle, the current INS RTK information can be obtained first, which can also include the absolute time of current INS RTK information acquisition, the corresponding INS RTK positioning information, RTK positioning status, HDOP, and number of satellites.

[0089] Then, the positioning confidence prediction model trained in the above embodiment is used to predict the confidence of the inertial navigation RTK positioning information output by the current inertial navigation RTK device. The higher the confidence, the higher the accuracy of the current inertial navigation RTK positioning information, and vice versa.

[0090] Finally, the confidence of the current inertial navigation RTK positioning information can be used as observation information and input into the Kalman filter or extended Kalman filter together with the positioning data of other sensors such as IMU positioning data and wheel speed data for fusion positioning, thereby obtaining the fusion positioning result of the autonomous driving vehicle.

[0091] The embodiment of the present application also provides a training device 300 for a positioning confidence prediction model for autonomous driving, such as Figure 3 As shown, a schematic diagram of the structure of a training device for a positioning confidence prediction model for autonomous driving according to an embodiment of the present application is provided. The device 300 includes: a first acquisition unit 310, a first determination unit 320, a second determination unit 330, and a training unit 340, wherein:

[0092] A first acquisition unit 310 is configured to acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information;

[0093] A first determining unit 320 is configured to determine a positioning error of the inertial navigation RTK positioning information based on the high-precision positioning information;

[0094] A second determining unit 330 is configured to determine the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information;

[0095] The training unit 340 is configured to train a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model.

[0096] In some embodiments of the present application, the first acquisition unit 310 is specifically used to: acquire high-precision inertial navigation data and base station data corresponding to the inertial navigation RTK information; and perform post-processing and solving on the high-precision inertial navigation data and the base station data to obtain the high-precision positioning information.

[0097] In some embodiments of the present application, the second determination unit 330 is specifically used to: if the positioning error of the inertial navigation RTK positioning information is not greater than the first preset error threshold, determine that the confidence of the inertial navigation RTK positioning information is the first confidence; if the positioning error of the inertial navigation RTK positioning information is not less than the second preset error threshold, determine that the confidence of the inertial navigation RTK positioning information is the second confidence; if the positioning error of the inertial navigation RTK positioning information is greater than the first preset error threshold and less than the second preset error threshold, determine that the confidence of the inertial navigation RTK positioning information is the third confidence; wherein, the first preset error threshold is less than the second preset error threshold, the first confidence is greater than the third confidence, and the third confidence is greater than the second confidence.

[0098] In some embodiments of the present application, the inertial navigation RTK information also includes the absolute time, RTK positioning status, horizontal position precision factor and number of satellites of the inertial navigation RTK information. The training unit 340 is specifically used to: convert the absolute time of the inertial navigation RTK information into relative continuous time based on the power-on time of the inertial navigation RTK; use the relative continuous time, the RTK positioning status, the horizontal position precision factor and the number of satellites of the inertial navigation RTK information as inputs of the positioning confidence prediction model, use the confidence of the inertial navigation RTK positioning information as a supervision signal, train the positioning confidence prediction model, and obtain a trained positioning confidence prediction model.

[0099] In some embodiments of the present application, the location reliability prediction model adopts an LSTM long short-term memory network.

[0100] It can be understood that the above-mentioned training device for the position confidence prediction model for autonomous driving can implement the various steps of the training method for the position confidence prediction model for autonomous driving provided in the aforementioned embodiment. The relevant explanations on the training method for the position confidence prediction model for autonomous driving are applicable to the training device for the position confidence prediction model for autonomous driving and will not be repeated here.

[0101] The embodiment of the present application also provides a fusion positioning device 400 for an autonomous driving vehicle, such as Figure 4 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. The device 400 includes: a second acquisition unit 410, a prediction unit 420, and a fusion positioning unit 430, wherein:

[0102] The second acquisition unit 410 is configured to acquire current inertial navigation RTK information, where the current inertial navigation RTK information includes the absolute time of the current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision factor, and number of satellites;

[0103] The prediction unit 420 is configured to predict the confidence of the current inertial navigation RTK positioning information based on the current inertial navigation RTK information using a positioning confidence prediction model;

[0104] A fusion positioning unit 430 is configured to perform fusion positioning based on the confidence level of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle;

[0105] The positioning reliability prediction model is obtained by training based on the aforementioned training device for the positioning reliability prediction model for autonomous driving.

[0106] 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.

[0107] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 5 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0108] The processor, network interface, and memory can be interconnected via 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 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0109] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0110] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a training device for the position confidence prediction model for autonomous driving at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0111] Acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information;

[0112] Determine the positioning error of the inertial navigation RTK positioning information according to the high-precision positioning information;

[0113] Determining the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information;

[0114] The inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information are used to train a positioning confidence prediction model to obtain a trained positioning confidence prediction model.

[0115] The above application Figure 1The method performed by the training device for a position confidence prediction model for autonomous driving disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. 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 gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0116] The electronic device may also perform Figure 1 A method for executing a training device for a positioning confidence prediction model for autonomous driving, and implementing a training device for a positioning confidence prediction model for autonomous driving in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0117] The embodiment of 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, can enable the electronic device to execute Figure 1 The method executed by the training device for the position confidence prediction model for autonomous driving in the illustrated embodiment is specifically used to perform:

[0118] Acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information;

[0119] Determine the positioning error of the inertial navigation RTK positioning information according to the high-precision positioning information;

[0120] Determining the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information;

[0121] The inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information are used to train a positioning confidence prediction model to obtain a trained positioning confidence prediction model.

[0122] It should be noted that the electronic device of the embodiment of the present application can also be used to perform Figure 2 The method performed by the fusion positioning device of the autonomous driving vehicle disclosed in the illustrated embodiment will not be described in detail.

[0123] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0124] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 flowcharts and / or block diagrams. 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.

[0125] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0127] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0128] 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. Memory is an example of a computer-readable medium.

[0129] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0130] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0131] 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 take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The foregoing is merely 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 modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A training method for a position confidence prediction model for autonomous driving, wherein: The method comprises: Acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information; Determine the positioning error of the inertial navigation RTK positioning information according to the high-precision positioning information; Determining the confidence level of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information; Training a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model; The inertial navigation RTK information also includes the absolute time of the inertial navigation RTK information, the RTK positioning status, the horizontal position precision factor, and the number of satellites. The training of the positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain the trained positioning confidence prediction model includes: Based on the power-on time of the inertial navigation RTK, the absolute time of the inertial navigation RTK information is converted into relative continuous time; The relative continuous time of the inertial navigation RTK information, the RTK positioning state, the horizontal position precision factor, and the number of satellites are used as inputs of the positioning confidence prediction model, and the confidence of the inertial navigation RTK positioning information is used as a supervision signal to train the positioning confidence prediction model to obtain a trained positioning confidence prediction model.

2. The method according to claim 1, wherein: The acquisition of inertial navigation RTK information and corresponding high-precision positioning information includes: Obtaining high-precision inertial navigation data and base station data corresponding to the inertial navigation RTK information; Post-processing and solving the high-precision inertial navigation data and the base station data to obtain the high-precision positioning information.

3. The method according to claim 1, wherein: Determining the confidence of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information includes: If the positioning error of the inertial navigation RTK positioning information is not greater than a first preset error threshold, determining the confidence level of the inertial navigation RTK positioning information to be a first confidence level; If the positioning error of the inertial navigation RTK positioning information is not less than a second preset error threshold, determining the confidence level of the inertial navigation RTK positioning information to be a second confidence level; If the positioning error of the inertial navigation RTK positioning information is greater than the first preset error threshold and less than the second preset error threshold, determining that the confidence level of the inertial navigation RTK positioning information is a third confidence level; The first preset error threshold is smaller than the second preset error threshold, the first confidence level is larger than the third confidence level, and the third confidence level is larger than the second confidence level.

4. The method according to any one of claims 1 to 3, wherein: The location reliability prediction model adopts LSTM long short-term memory network.

5. A fusion positioning method for an autonomous driving vehicle, wherein: The method comprises: Acquire current inertial navigation RTK information, where the current inertial navigation RTK information includes absolute time of current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision factor, and number of satellites; Based on the current inertial navigation RTK information, using a positioning confidence prediction model to predict the confidence of the current inertial navigation RTK positioning information; Performing fusion positioning based on the confidence of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle; The positioning confidence prediction model is trained based on the training method of the positioning confidence prediction model for autonomous driving according to any one of claims 1 to 4.

6. A training device for a positioning confidence prediction model for autonomous driving, wherein: The device comprises: A first acquisition unit is configured to acquire inertial navigation RTK information and corresponding high-precision positioning information, wherein the inertial navigation RTK information includes inertial navigation RTK positioning information; A first determining unit is configured to determine a positioning error of the inertial navigation RTK positioning information based on the high-precision positioning information; A second determining unit is configured to determine the confidence of the inertial navigation RTK positioning information according to the positioning error of the inertial navigation RTK positioning information; A training unit, configured to train a positioning confidence prediction model using the inertial navigation RTK information and the confidence of the inertial navigation RTK positioning information to obtain a trained positioning confidence prediction model; The inertial navigation RTK information also includes the absolute time, RTK positioning status, horizontal position precision factor and number of satellites of the inertial navigation RTK information. The training unit is specifically used for: Based on the power-on time of the inertial navigation RTK, the absolute time of the inertial navigation RTK information is converted into relative continuous time; The relative continuous time of the inertial navigation RTK information, the RTK positioning state, the horizontal position precision factor, and the number of satellites are used as inputs of the positioning confidence prediction model, and the confidence of the inertial navigation RTK positioning information is used as a supervision signal to train the positioning confidence prediction model to obtain a trained positioning confidence prediction model.

7. A fusion positioning device for an autonomous driving vehicle, wherein: The device comprises: A second acquisition unit is used to acquire current inertial navigation RTK information, where the current inertial navigation RTK information includes the absolute time of the current inertial navigation RTK information, inertial navigation RTK positioning information, RTK positioning status, horizontal position precision factor, and number of satellites; A prediction unit, configured to predict the confidence of the current inertial navigation RTK positioning information using a positioning confidence prediction model based on the current inertial navigation RTK information; a fusion positioning unit, configured to perform fusion positioning based on the confidence level of the current inertial navigation RTK positioning information to obtain a fusion positioning result of the autonomous driving vehicle; The positioning reliability prediction model is obtained by training based on the training device for the positioning reliability prediction model for autonomous driving according to claim 6.

8. An electronic device comprising: processor; as well as A memory arranged to store computer-executable instructions, which, when executed, cause the processor to execute the method for training a positioning confidence prediction model for autonomous driving as described in any one of claims 1 to 4, or the method for executing the fusion positioning method for an autonomous driving vehicle as described in claim 5.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device comprising a plurality of applications, enables the electronic device to execute the training method for a positioning confidence prediction model for autonomous driving as described in any one of claims 1 to 4, or to execute the fusion positioning method for an autonomous driving vehicle as described in claim 5.

Images