Fusion positioning method and device for autonomous vehicle, electronic equipment and computer program product

Abstract

The invention discloses a fusion positioning method and device for an automatic driving vehicle, electronic equipment and a computer program product. The method comprises the following steps: acquiring positioning data of a plurality of positioning information sources of the automatic driving vehicle; calculating an accumulated positioning error between any two positioning information sources in a preset sliding time window according to the positioning data of the plurality of positioning information sources; determining a current positioning information source according to an accumulated positioning error between any two positioning information sources in the preset sliding time window, wherein the current positioning information source is one of the plurality of positioning information sources; and performing fusion positioning according to the positioning data of the current positioning information source to obtain a fusion positioning result of the autonomous vehicle. Compared with the prior art, the positioning data of the multiple positioning information sources in the preset sliding time window are compared and analyzed, the accuracy of positioning error calculation of the positioning information sources is improved, the current positioning information source is further determined, fusion positioning is carried out, and the fusion positioning precision and stability are improved.

Description

Technical Field

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

[0002] In the positioning process of autonomous vehicles, the single-frame correction method is often used as a technical means to improve the accuracy of the vehicle's current position. Single-frame correction refers to a one-time correction of the vehicle's current position based on information from a single data frame (usually from positioning information sources such as GPS, IMU, LiDAR, etc.) during the autonomous driving process. However, although single-frame correction can achieve instant adjustment of the vehicle's position to a certain extent, its application is also accompanied by significant problems and challenges.

[0003] Specifically, this method is prone to misjudgment due to environmental noise, positioning information source errors or inaccurate data processing, that is, the real position information of the vehicle is incorrectly corrected. More importantly, frequent reliance on single-frame correction to update positioning information will cause the switching between positioning information sources to become too frequent. This instability not only exacerbates the volatility of positioning results, but also seriously affects the continuity and reliability of the autonomous driving system. Therefore, in the actual deployment and application of autonomous driving technology, how to overcome the positioning instability caused by single-frame correction has become a technical problem that needs to be solved urgently, and there is an urgent need to develop a more robust and efficient fusion positioning solution. Summary of the invention

[0004] The embodiments of the present application provide a fusion positioning method, device, electronic device, and computer program product for an autonomous driving vehicle to improve the fusion positioning accuracy and stability of the autonomous driving vehicle.

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

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

[0007] Obtaining positioning data of multiple positioning information sources of the autonomous driving vehicle;

[0008] Calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources;

[0009] Determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources;

[0010] The fusion positioning is performed based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

[0011] Optionally, the calculating, based on the positioning data of the plurality of positioning information sources, the cumulative positioning error between any two positioning information sources within a preset sliding time window comprises:

[0012] Obtaining the positioning data of multiple positioning information sources within a preset sliding time window of the cache;

[0013] Calculate multiple positioning errors between any two positioning information sources within the preset sliding time window based on the positioning data of the multiple positioning information sources within the preset sliding time window;

[0014] A weighted sum is performed on multiple positioning errors between any two positioning information sources within a preset sliding time window to obtain a cumulative positioning error between any two positioning information sources within the preset sliding time window.

[0015] Optionally, determining the current positioning information source according to the accumulated positioning error between any two positioning information sources within a preset sliding time window includes:

[0016] Determine the positioning status of each positioning information source according to the cumulative positioning error between any two positioning information sources within a preset sliding time window;

[0017] Determine a positioning information source in a normal state according to the positioning states of each positioning information source;

[0018] When there are at least two positioning information sources in a normal state, the current positioning information source is determined according to the accumulated positioning error between any two positioning information sources within a preset sliding time window.

[0019] Optionally, performing fusion positioning according to the positioning data of the current positioning information source to obtain a fusion positioning result of the autonomous driving vehicle includes:

[0020] Determining whether to trigger a switching optimization condition of the positioning information source according to the current positioning information source and the original positioning information source;

[0021] When the switching optimization condition of the positioning information source is triggered, the switching optimization strategy of the positioning information source is used to fuse the positioning data of the current positioning information source and the positioning data of the original positioning information source to obtain a fused positioning result of the autonomous driving vehicle.

[0022] Optionally, the determining whether to trigger a switching optimization condition of a positioning information source according to the current positioning information source and the original positioning information source includes:

[0023] If the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, determining a switching optimization condition for triggering the positioning information source;

[0024] Otherwise, it is determined that the switching optimization condition of the positioning information source is not triggered.

[0025] Optionally, the determining whether to trigger a switching optimization condition of a positioning information source according to the current positioning information source and the original positioning information source includes:

[0026] When the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or when the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, determining a positioning error between positioning data of the current positioning information source and positioning data of the original positioning information source;

[0027] If the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source is less than a preset positioning error threshold, determining a switching optimization condition for triggering the positioning information source;

[0028] Otherwise, it is determined that the switching optimization condition of the positioning information source is not triggered.

[0029] Optionally, in the case of triggering the switching optimization condition of the positioning information source, using the switching optimization strategy of the positioning information source to fuse the positioning data of the current positioning information source and the positioning data of the original positioning information source to obtain the fused positioning result of the autonomous driving vehicle includes:

[0030] Calculating a weight coefficient of the current positioning information source according to a positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source;

[0031] Calculating a weight coefficient of the original positioning information source according to a weight coefficient of the current positioning information source;

[0032] The fusion positioning is performed according to the positioning data and the corresponding weight coefficient of the current positioning information source, and the positioning data and the corresponding weight coefficient of the original positioning information source to obtain a fusion positioning result of the autonomous driving vehicle.

[0033] In a second aspect, an embodiment of the present application further provides a fusion positioning device for an autonomous driving vehicle, wherein the fusion positioning device for an autonomous driving vehicle includes:

[0034] An acquisition unit, used to acquire positioning data of multiple positioning information sources of the autonomous driving vehicle;

[0035] A calculation unit, used to calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources;

[0036] a determining unit, configured to determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources;

[0037] The fusion positioning unit is used to perform fusion positioning according to the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

[0038] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0039] A processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to perform any of the aforementioned fusion positioning methods for the autonomous driving vehicle.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any of the aforementioned fusion positioning methods for autonomous driving vehicles.

[0041] 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 positioning data of multiple positioning information sources of the autonomous driving vehicle; then, based on the positioning data of multiple positioning information sources, calculates the cumulative positioning error between any two positioning information sources within a preset sliding time window; then, the current positioning information source is determined based on the cumulative positioning error between any two positioning information sources within the preset sliding time window, and the current positioning information source is one of the multiple positioning information sources; finally, fusion positioning is performed based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle. The fusion positioning method of the autonomous driving vehicle in the embodiments of the present application improves the accuracy of the positioning error calculation of the positioning information source by comparing and analyzing the positioning data of multiple positioning information sources within a preset sliding time window, and further determines the currently used positioning information source and performs fusion positioning, thereby improving the fusion positioning accuracy and stability of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] 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:

[0043] 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;

[0044] Figure 2 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;

[0045] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0046] 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.

[0047] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0048] 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 fusion positioning method for the autonomous driving vehicle at least includes the following steps S110 to S140:

[0049] Step S110, obtaining positioning data of multiple positioning information sources of the autonomous driving vehicle.

[0050] When performing fusion positioning of an autonomous vehicle, the embodiment of the present application needs to first obtain positioning data collected by multiple positioning information sources on the autonomous vehicle. The multiple positioning information sources here may include different sensors or positioning modules on the autonomous vehicle, for example, laser SLAM, visual SLAM, RTK positioning, and fusion positioning, etc. The specific positioning information sources included can be flexibly set by those skilled in the art according to actual needs, and are not specifically limited here.

[0051] Step S120, calculating the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources.

[0052] The positioning data collected by multiple positioning information sources are time stamped and then the cumulative positioning errors are calculated between the positioning data collected by multiple positioning information sources within the set sliding time window, for example, the cumulative positioning errors of the positioning data of laser SLAM and the positioning data of visual SLAM, the cumulative positioning errors of the positioning data of laser SLAM and RTK positioning data, the cumulative positioning errors of the positioning data of laser SLAM and fused positioning data LOC, etc. The size of the sliding time window can be flexibly set according to actual needs and is not specifically limited here.

[0053] Compared with the existing single-frame correction scheme, the cumulative positioning error calculated based on the preset sliding time window can solve the problem of low reliability of single-frame data leading to reduced accuracy and stability of positioning results.

[0054] It should be noted that, since the positioning data has not been fused at the current moment, the fused positioning data used to calculate the positioning error can be understood as the fused positioning result of the previous moment.

[0055] Step S130: determining a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of a plurality of positioning information sources.

[0056] Based on the above steps, the cumulative positioning error between any two positioning information sources within the preset sliding time window can be obtained. A certain voting strategy can be adopted to select the current main positioning information source. The voting strategy here is mainly designed comprehensively from the positioning error size, the confidence or positioning status of the positioning information source, and the priority of the use of the set positioning information source. The priority of the use of the positioning information source can be set to RTK> laser SLAM> visual SLAM> dead reckoning DR.

[0057] For example, if the positioning confidence output by laser SLAM and the positioning confidence output by visual SLAM are both higher than the corresponding confidence threshold, but the RTK positioning state is in a non-differential state, the positioning error between the positioning data output by laser SLAM and the positioning data output by visual SLAM is also less than the error threshold, and the error with the fused positioning result is also less than the threshold, it can be considered that laser SLAM and visual SLAM are both relatively reliable positioning information sources, but because the use priority of laser SLAM is higher than that of visual SLAM, laser SLAM can ultimately be used as the current positioning information source.

[0058] Step S140, performing fusion positioning based on the positioning data of the current positioning information source to obtain a fusion positioning result of the autonomous driving vehicle.

[0059] After the current positioning information source is determined, the positioning data collected by the current positioning information source can be used as the main observation information source to participate in the fusion positioning. Here, the role played by each positioning information source to be fused in the fusion process can be adjusted by the size of the fusion weight. Of course, the actual positioning information source used for fusion may also be a single positioning information source.

[0060] The fusion positioning method for the autonomous driving vehicle in the embodiment of the present application improves the accuracy of the positioning error calculation of the positioning information source by comparing and analyzing the positioning data of multiple positioning information sources within a preset sliding time window, further determines the currently used positioning information source and performs fusion positioning, thereby improving the fusion positioning accuracy and stability of the autonomous driving vehicle.

[0061] In some embodiments of the present application, the calculation of the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources includes: obtaining the positioning data of multiple positioning information sources within the cached preset sliding time window; calculating multiple positioning errors between any two positioning information sources within the preset sliding time window based on the positioning data of multiple positioning information sources within the preset sliding time window; and performing weighted summation of the multiple positioning errors between any two positioning information sources within the preset sliding time window to obtain the cumulative positioning error between any two positioning information sources within the preset sliding time window.

[0062] The embodiment of the present application can dynamically cache the positioning data of each positioning information source within a period of time based on the sliding time window, for example, it can cache the laser SLAM positioning data, visual SLAM positioning data, RTK positioning data and fusion positioning data within 3 seconds in real time. Based on the positioning data of each positioning information source cached in the sliding time window, after performing timestamp synchronization processing, the positioning errors are calculated for the positioning data of each two positioning information sources at the same time, so that multiple positioning errors of the two positioning information sources in the sliding time window can be obtained.

[0063] The weighted sum of multiple positioning errors of the two positioning information sources obtained above within the sliding time window is performed to obtain the final cumulative positioning error. The size of the weight is mainly related to the distance from the current time. The closer the distance to the current time, the larger the weight corresponding to the positioning error can be set.

[0064] As another implementation, when calculating the cumulative positioning error based on multiple positioning errors in a sliding time window, you can also choose to select a portion of representative data frames to participate in the calculation. For example, you can select the positioning error of the current frame in the sliding time window, the positioning error of the earliest frame, and the positioning error of the middle frame, and perform weighted summation on the positioning errors of these three frames to obtain a comprehensive positioning error.

[0065] Here, we take the calculation of the cumulative positioning error between the laser SLAM positioning data and the fused positioning data LOC as an example, which can be expressed as follows:

[0066] dp_multi_lidar_slam-loc=k1*dp_3s_lidar_slam-loc+k2*dp_1s_lidar_slam-loc+k3*dp_0s_lidar_slam-loc;

[0067] Among them, k1, k2, and k3 are weight coefficients, k1<k2<k3, and k1+k2+k3=1. The inter-frame coefficient dp_xs_slam-loc represents the positioning error between the laser SLAM positioning data and the fused positioning data at the previous x seconds. 0 seconds is the current time. The closer to the current time, the larger the corresponding weight coefficient.

[0068] Through the processing of the above-mentioned multi-frame sliding time window data, a more accurate basis is provided for the selection of the current positioning data source, thereby improving the fusion positioning accuracy and stability of the autonomous driving vehicle.

[0069] In some embodiments of the present application, determining the current positioning information source based on the cumulative positioning error between any two positioning information sources within a preset sliding time window includes: determining the positioning status of each positioning information source based on the cumulative positioning error between any two positioning information sources within the preset sliding time window; determining a positioning information source in a normal state based on the positioning status of each positioning information source; when there are at least two positioning information sources in a normal state, determining the current positioning information source based on the cumulative positioning error between any two positioning information sources within the preset sliding time window.

[0070] In actual scenarios, multiple positioning information sources on an autonomous driving vehicle are not always in a normal or valid state. Although some positioning information sources can report information reflecting their own state, such as positioning status or confidence, this information is not always reliable. Therefore, when determining the current positioning information source, the embodiment of the present application can further identify whether the positioning status of multiple positioning information sources is normal based on the cumulative positioning error between any two positioning information sources calculated in the above embodiment within a preset sliding time window.

[0071] Specifically, the cumulative positioning errors between any two positioning information sources in the preset sliding time window can be compared with each other, and can also be compared with the positioning error threshold. For example, if the comparison finds that the cumulative positioning error between the laser SLAM positioning data and the visual SLAM exceeds the positioning error threshold, it means that at least one of the positioning data sources in the laser SLAM positioning data and the visual SLAM may be abnormal. Further combining the size of the cumulative positioning error between the laser SLAM positioning data and the RTK positioning data and the fused positioning data can assist in judging whether the laser SLAM positioning data is normal, or combining the size of the cumulative positioning error between the visual SLAM positioning data and the RTK positioning data and the fused positioning data can assist in judging whether the visual SLAM positioning data is normal. How to compare and judge specifically, technicians in this field can flexibly set according to actual conditions, and no specific limitation is made here.

[0072] If there is an abnormal positioning information source among the multiple positioning information sources, the abnormal positioning information source is downgraded and does not participate in the subsequent voting and selection of positioning information sources, that is, voting and selection are performed only for normal positioning information sources.

[0073] In some embodiments of the present application, the performing fusion positioning based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle includes: determining whether to trigger the switching optimization condition of the positioning information source based on the current positioning information source and the original positioning information source; when the switching optimization condition of the positioning information source is triggered, using the switching optimization strategy of the positioning information source to perform fusion positioning on the positioning data of the current positioning information source and the positioning data of the original positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

[0074] The current positioning information source can be understood as the main positioning information source used for fusion positioning. Since the process of the above embodiment is carried out in real time, with changes in the environment, the sensor itself, etc., the selected current positioning information source may be different from the original positioning information source, that is, the main positioning information source being used. At this time, the problem of switching the positioning information source will be involved, and the positioning jump that may be caused by the switching needs to be considered.

[0075] Based on this, the embodiment of the present application can first determine the specific types of the current positioning information source and the original positioning information source and whether the two are the same, and then determine whether the switching of the positioning information source occurs and whether optimization processing after the switching is required. If the switching of the positioning information source occurs and optimization processing after the switching is required, the switching optimization strategy of the positioning information source can be used to optimize the fusion positioning of the positioning data of the current positioning information source and the positioning data of the original positioning information source, thereby avoiding the problem of positioning jumps caused by direct fusion after switching and improving the smoothness of the fusion positioning trajectory.

[0076] In some embodiments of the present application, determining whether to trigger the switching optimization condition of the positioning information source based on the current positioning information source and the original positioning information source includes: if the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, then determining that the switching optimization condition of the positioning information source is triggered; otherwise, determining that the switching optimization condition of the positioning information source is not triggered.

[0077] The embodiment of the present application determines the switching optimization conditions of the positioning information source. On the one hand, it requires that the current positioning information source and the original positioning information source are different. On the other hand, it limits the types of positioning information sources before and after the switching. That is, it designs a switching optimization strategy mainly for the situation where the two positioning information sources, laser SLAM and RTK positioning, are interchangeable.

[0078] In some embodiments of the present application, determining whether to trigger the switching optimization condition of the positioning information source based on the current positioning information source and the original positioning information source includes: when the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or when the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, determining the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source; if the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source is less than a preset positioning error threshold, determining that the switching optimization condition of the positioning information source is triggered; otherwise, determining that the switching optimization condition of the positioning information source is not triggered.

[0079] In order to further improve the effect of the optimization of the switching of the positioning information source, when it is determined based on the above-mentioned embodiment that the two positioning information sources of laser SLAM and RTK positioning are interchangeable, the positioning error between the two positioning information sources can be further constrained, and the positioning error can be decomposed into lateral error and longitudinal error, and it is determined whether the lateral error between the laser SLAM positioning data and the RTK positioning data is less than the lateral error threshold, and whether the longitudinal error is less than the longitudinal error threshold. If both are less than, it is considered that the switching optimization condition is met. Otherwise, if the positioning error between the laser SLAM positioning data and the RTK positioning data does not meet the above threshold requirements, the subsequent optimization fusion strategy may introduce additional errors, resulting in the fusion positioning accuracy and stability being affected.

[0080] In some embodiments of the present application, when the switching optimization condition of the positioning information source is triggered, the positioning data of the current positioning information source and the positioning data of the original positioning information source are fused and positioned using the switching optimization strategy of the positioning information source to obtain a fused positioning result of the autonomous driving vehicle, including: calculating the weight coefficient of the current positioning information source according to the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source; calculating the weight coefficient of the original positioning information source according to the weight coefficient of the current positioning information source; and performing fused positioning according to the positioning data and the corresponding weight coefficient of the current positioning information source, as well as the positioning data and the corresponding weight coefficient of the original positioning information source, to obtain a fused positioning result of the autonomous driving vehicle.

[0081] To facilitate understanding of the embodiments of the present application, the specific implementation of the switching optimization strategy is represented as follows:

[0082] Case 1)

[0083] if(slam_flag==0)slam_tmp_k=(α / lidar_rtk);

[0084] if(slam_tmp_k>1.0)slam_tmp_k=1.0;

[0085] rtk_tmp_k=1.0-slam_tmp_k;

[0086] Case 2)

[0087] if(slam_flag==1)rtk_tmp_k=(β / lidar_rtk);

[0088] if(rtk_tmp_k>1.0)rtk_tmp_k=1.0;

[0089] slam_tmp_k=1.0-rtk_tmp_k;

[0090] Among them, slam_flag==0 indicates that the current positioning information source is RTK, slam_flag==1 indicates that the current positioning information source is laser SLAM, slam_tmp_k and rtk_tmp_k are the fusion weight coefficients of laser SLAM and RTK respectively, lidar_rtk is the positioning error between laser SLAM positioning data and RTK positioning data, α and β are custom coefficients, which can be set according to the lateral error threshold in the aforementioned embodiment, for example, can be set to less than 1 / 2 of the lateral error threshold. Of course, the specific setting can be flexibly set by those skilled in the art according to actual needs, and is not specifically limited here.

[0091] The present application also provides a fusion positioning device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a schematic diagram of the structure of a fusion positioning device of an autonomous driving vehicle in an embodiment of the present application is provided. The fusion positioning device 200 of the autonomous driving vehicle includes: an acquisition unit 210, a calculation unit 220, a determination unit 230 and a fusion positioning unit 240, wherein:

[0092] An acquisition unit 210 is used to acquire positioning data of multiple positioning information sources of the autonomous driving vehicle;

[0093] A calculation unit 220, configured to calculate a cumulative positioning error between any two positioning information sources within a preset sliding time window based on positioning data of multiple positioning information sources;

[0094] A determination unit 230, configured to determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources;

[0095] The fusion positioning unit 240 is used to perform fusion positioning according to the positioning data of the current positioning information source to obtain a fusion positioning result of the autonomous driving vehicle.

[0096] In some embodiments of the present application, the calculation unit 220 is specifically used to: obtain the positioning data of multiple positioning information sources within the preset sliding time window of the cache; calculate multiple positioning errors between any two positioning information sources within the preset sliding time window based on the positioning data of multiple positioning information sources within the preset sliding time window; perform weighted summation of the multiple positioning errors between any two positioning information sources within the preset sliding time window to obtain the cumulative positioning error between any two positioning information sources within the preset sliding time window.

[0097] In some embodiments of the present application, the determination unit 230 is specifically used to: determine the positioning status of each positioning information source based on the cumulative positioning error between any two positioning information sources within a preset sliding time window; determine the positioning information source in a normal state based on the positioning status of each positioning information source; when there are at least two positioning information sources in a normal state, determine the current positioning information source based on the cumulative positioning error between any two positioning information sources within a preset sliding time window.

[0098] In some embodiments of the present application, the fusion positioning unit is specifically used to: determine whether to trigger the switching optimization condition of the positioning information source based on the current positioning information source and the original positioning information source; when the switching optimization condition of the positioning information source is triggered, use the switching optimization strategy of the positioning information source to fuse the positioning data of the current positioning information source and the positioning data of the original positioning information source to obtain a fusion positioning result of the autonomous driving vehicle.

[0099] In some embodiments of the present application, the fused positioning unit 240 is specifically used to: if the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, then determine the switching optimization conditions that trigger the positioning information source; otherwise, determine that the switching optimization conditions that do not trigger the positioning information source.

[0100] In some embodiments of the present application, the fused positioning unit 240 is specifically used to: determine the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source when the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or when the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning; if the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source is less than a preset positioning error threshold, determine to trigger the switching optimization condition of the positioning information source; otherwise, determine that the switching optimization condition of the positioning information source is not triggered.

[0101] In some embodiments of the present application, the fusion positioning unit 240 is specifically used to: calculate the weight coefficient of the current positioning information source according to the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source; calculate the weight coefficient of the original positioning information source according to the weight coefficient of the current positioning information source; perform fusion positioning according to the positioning data and the corresponding weight coefficient of the current positioning information source, and the positioning data and the corresponding weight coefficient of the original positioning information source, to obtain a fusion positioning result of the autonomous driving vehicle.

[0102] 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.

[0103] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3At 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.

[0104] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] 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.

[0106] 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:

[0107] Obtaining positioning data of multiple positioning information sources of the autonomous driving vehicle;

[0108] Calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources;

[0109] Determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources;

[0110] The fusion positioning is performed based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

[0111] 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.

[0112] The present application also provides a computer program product, 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:

[0113] Obtaining positioning data of multiple positioning information sources of the autonomous driving vehicle;

[0114] Calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources;

[0115] Determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources;

[0116] The fusion positioning is performed based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

[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 A step that specifies a function 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 fusion positioning method of the autonomous driving vehicle includes: Obtaining positioning data of multiple positioning information sources of the autonomous driving vehicle; Calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources; Determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources; The fusion positioning is performed based on the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

2. The fusion positioning method for an autonomous driving vehicle according to claim 1, wherein: The step of calculating the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of the plurality of positioning information sources comprises: Obtaining the positioning data of multiple positioning information sources within a preset sliding time window of the cache; Calculate multiple positioning errors between any two positioning information sources within the preset sliding time window based on the positioning data of the multiple positioning information sources within the preset sliding time window; A weighted sum is performed on multiple positioning errors between any two positioning information sources within a preset sliding time window to obtain a cumulative positioning error between any two positioning information sources within the preset sliding time window.

3. The fusion positioning method for an autonomous driving vehicle according to claim 1, wherein: The step of determining the current positioning information source according to the accumulated positioning error between any two positioning information sources within a preset sliding time window comprises: Determine the positioning status of each positioning information source according to the cumulative positioning error between any two positioning information sources within a preset sliding time window; Determine a positioning information source in a normal state according to the positioning states of each positioning information source; When there are at least two positioning information sources in a normal state, the current positioning information source is determined according to the accumulated positioning error between any two positioning information sources within a preset sliding time window.

4. The fusion positioning method for an autonomous driving vehicle according to claim 1, wherein: The fusion positioning is performed according to the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle, including: Determining whether to trigger a switching optimization condition of the positioning information source according to the current positioning information source and the original positioning information source; When the switching optimization condition of the positioning information source is triggered, the switching optimization strategy of the positioning information source is used to fuse the positioning data of the current positioning information source and the positioning data of the original positioning information source to obtain a fused positioning result of the autonomous driving vehicle.

5. The fusion positioning method for an autonomous driving vehicle according to claim 4, wherein: The determining, according to the current positioning information source and the original positioning information source, whether to trigger the switching optimization condition of the positioning information source comprises: If the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, determining a switching optimization condition for triggering the positioning information source; Otherwise, it is determined that the switching optimization condition of the positioning information source is not triggered.

6. The fusion positioning method for an autonomous driving vehicle according to claim 5, wherein: The determining, according to the current positioning information source and the original positioning information source, whether to trigger the switching optimization condition of the positioning information source comprises: When the current positioning information source is laser SLAM positioning and the original positioning information source is RTK positioning, or when the current positioning information source is RTK positioning and the original positioning information source is laser SLAM positioning, determining a positioning error between positioning data of the current positioning information source and positioning data of the original positioning information source; If the positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source is less than a preset positioning error threshold, determining a switching optimization condition for triggering the positioning information source; Otherwise, it is determined that the switching optimization condition of the positioning information source is not triggered.

7. The fusion positioning method for an autonomous driving vehicle according to claim 4, wherein: In the case of triggering the switching optimization condition of the positioning information source, the positioning data of the current positioning information source and the positioning data of the original positioning information source are fused and positioned by using the switching optimization strategy of the positioning information source to obtain the fused positioning result of the autonomous driving vehicle, including: Calculating a weight coefficient of the current positioning information source according to a positioning error between the positioning data of the current positioning information source and the positioning data of the original positioning information source; Calculating a weight coefficient of the original positioning information source according to a weight coefficient of the current positioning information source; The fusion positioning is performed according to the positioning data and the corresponding weight coefficient of the current positioning information source, and the positioning data and the corresponding weight coefficient of the original positioning information source to obtain a fusion positioning result of the autonomous driving vehicle.

8. A fusion positioning device for an autonomous driving vehicle, wherein: The fusion positioning device of the autonomous driving vehicle includes: An acquisition unit, used to acquire positioning data of multiple positioning information sources of the autonomous driving vehicle; A calculation unit, used to calculate the cumulative positioning error between any two positioning information sources within a preset sliding time window based on the positioning data of multiple positioning information sources; a determining unit, configured to determine a current positioning information source according to a cumulative positioning error between any two positioning information sources within a preset sliding time window, wherein the current positioning information source is one of the multiple positioning information sources; The fusion positioning unit is used to perform fusion positioning according to the positioning data of the current positioning information source to obtain the fusion positioning result of the autonomous driving vehicle.

9. An electronic device, comprising: processor; And a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the fusion positioning method for the autonomous driving vehicle of any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, which, when executed by a processor, implements the fusion positioning method of the autonomous driving vehicle described in any one of claims 1 to 7.

Images