High-precision positioning information determination method, fusion positioning module and high-definition map engine

Abstract

The embodiment of the specification discloses a high-precision positioning information determination method, a fusion positioning module and a high-definition map engine. The scheme can include: acquiring sensor information collected by multiple different types of sensors loaded on a target vehicle respectively; from high-precision map data, acquiring first map information corresponding to an estimated position of the target vehicle and second map information within a preset distance range around the estimated position; based on at least one of the first map information and the second map information, correcting the sensor information collected by the different types of sensors respectively to obtain corrected sensor information; and fusing the corrected sensor information corresponding to the multiple different types of sensors with the high-precision map data to obtain fused high-precision positioning information of the target vehicle. Based on the scheme, the accuracy and robustness of the positioning system can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of map, in particular to a high-precision positioning information determination method, a fusion positioning module and a high-definition map engine. BACKGROUND

[0002] With the development of automatic driving technology, high-precision real-time positioning technology is becoming more and more important. How to provide high-quality pose information for automatic driving has become a major point in the field of automatic driving.

[0003] At present, the scheme of high-precision positioning has not reached a mature and stable state. Generally, data collected by various sensors can be used to obtain vehicle positioning by fusion. However, various sensors commonly used by vehicles have their own application limitations. For example, inertial measurement information will also drift when it is static, RTK (Real Time Kinematic) signal quality will decrease in places with obstructions, radar cannot provide effective information in places with few or no obvious features, and so on. It can be seen that due to the influence of various sensor information by external environment, it is difficult to keep the vehicle in a high-precision positioning state all the time. SUMMARY

[0004] The embodiments of the present specification provide a high-precision positioning information determination method, a fusion positioning module and a high-definition map engine to solve the problem that the existing high-precision positioning method cannot keep the vehicle in a high-precision positioning state.

[0005] To solve the above technical problems, the embodiments of the present specification are implemented as follows:

[0006] The high-precision positioning information determination method provided by the embodiments of the present specification comprises:

[0007] Respectively acquiring sensor information collected by multiple different types of sensors loaded on a target vehicle;

[0008] From high-precision map data, acquiring first map information corresponding to an estimated position of the target vehicle and second map information within a preset distance range around the estimated position; the first map information comprises at least one of lane attribute information and road attribute information; the second map information comprises building attribute information;

[0009] Based on at least one of the first map information and the second map information, respectively correcting the sensor information collected by the different types of sensors to obtain corrected sensor information;

[0010] Fusing the corrected sensor information corresponding to the multiple different types of sensors with the high-precision map data to obtain fused high-precision positioning information of the target vehicle.

[0011] The embodiment of the present specification provides a fusion positioning module, comprising:

[0012] A sensor information acquisition unit is configured to acquire sensor information collected by multiple different types of sensors mounted on a target vehicle respectively;

[0013] A high-precision map information acquisition unit is configured to acquire first map information corresponding to an estimated position of the target vehicle and second map information within a preset distance range around the estimated position from high-precision map data; the first map information comprises at least one of lane attribute information and road attribute information; and the second map information comprises building attribute information;

[0014] A correction unit is configured to correct sensor information collected by the different types of sensors based on at least one of the first map information and the second map information, to obtain corrected sensor information;

[0015] A data fusion unit is configured to fuse the corrected sensor information corresponding to the multiple different types of sensors with the high-precision map data, to obtain fused high-precision positioning information of the target vehicle.

[0016] The embodiment of the present specification provides a high-precision map engine, comprising:

[0017] The foregoing fusion positioning module;

[0018] An electronic horizon module is configured to receive external high-precision vehicle position information and match to a map, and provide a functional interface for automatic driving applications to make control and judgment;

[0019] and at least one of an automatic driving design running domain judgment module, a map updating module, a crowdsourcing preprocessing and feedback module, a path intersection correlation module, and a lane-level path planning module;

[0020] The automatic driving design running domain judgment module is configured to configure an automatic driving area and judgment requirements;

[0021] The map updating module is configured to obtain map data update information of a high-precision map based on vehicle position and planned path;

[0022] The crowdsourcing preprocessing and feedback module is configured to perform preprocessing such as filtering and fusion on UGC visual vector data, feedback to the cloud, and update a map data center;

[0023] The path intersection correlation module is configured to synchronize a global path planning result initiated by a user to an automatic driving system, and obtain a matching path of a navigation path on a high-precision map through cross correlation with the high-precision map.

[0024] The lane-level path planning module is configured to output a lane-level local path planning for a certain length range in front of the vehicle according to a result of navigation path matching and route correction.

[0025] At least the following beneficial effects can be achieved by one embodiment of the present specification: by using high-precision map data to correct the data generated by each sensor for calculating the pose, and then using the corrected data for data fusion, the accuracy and robustness of the positioning system can be significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present specification, and other drawings can be obtained by those skilled in the art without creative labor.

[0027] Figure 1 is a whole scheme flow diagram of a high-precision positioning information determination method provided by an embodiment of the present specification;

[0028] Figure 2 is a flowchart of a high-precision positioning information determination method provided by an embodiment of the present specification;

[0029] Figure 3 is a schematic diagram of a fusion positioning module provided by an embodiment of the present specification;

[0030] Figure 4 is a structural schematic diagram of a high-precision map engine provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0031] With the development of automatic driving technology, high-precision real-time positioning technology is becoming increasingly important. How to provide high-quality pose information for automatic driving has become a major point in the field of automatic driving.

[0032] Currently, the scheme of high-precision positioning has not reached a mature and stable state. In the whole process of high-precision positioning, various sensors generate data for calculating the pose, and the fusion algorithm uses these data for fusion to generate high-precision position. Various sensors commonly used by vehicles have their own application limitations. In the process of actual application, various sensors may have inaccurate data. For example, inertial measurement (IMU) data will drift when stationary, real-time kinematic (RTK) carrier phase difference signals will have poor signal quality in places with obstructions, and radar cannot provide effective information in places with few or no features.

[0033] In the embodiments of the present specification, the errors of the sensors can be corrected using a high-precision map, and the corrected data is used for fusion, greatly improving the accuracy and robustness of the positioning system. Since the high-precision map can be unaffected by any external environment, the positioning system can still maintain high-precision positioning when the signal quality of other sensors is poor.

[0034] In order to make the purposes, technical solutions, and advantages of one or more embodiments of the present specification clearer, the technical solutions of one or more embodiments of the present specification will be described clearly and completely below in conjunction with specific embodiments of the present specification and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of one or more embodiments of the present specification.

[0035] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.

[0036] The technical solutions provided by the embodiments of the present specification will be described in detail below in conjunction with the drawings.

[0037] Figure 1 The overall scheme flowchart of a high-precision positioning information determination method in the embodiments of the present specification.

[0038] As shown in Figure 1 , high-precision map data can be used to calibrate sensor data such as IMU, RTK, odometry sensor data (visual odometry data or radar odometry data), vehicle speed data, etc., to obtain calibrated pose information and its precision factor information; then, the calibrated pose information and its precision factor information are input into the back-end fusion algorithm for information fusion to obtain the fusion positioning result.

[0039] Based on Figure 1 the scheme, before fusing external sensor data such as RTK, IMU, vehicle body signal, camera, etc., high-precision map data is used for calibration, the pose deviation of high-precision map data and the actual scene perceived by the sensor is estimated dynamically, and the data of the sensor is corrected by using the constraint of high-precision map. Accordingly, position information highly consistent with the high-precision map can be provided for use in autonomous driving and intelligent cockpit, etc.

[0040] Next, a high-precision positioning information determination method provided by the embodiment of the present specification will be specifically described in combination with the accompanying drawings.

[0041] Figure 2 A flowchart of a high-precision positioning information determination method provided by the embodiment of the present specification.

[0042] From the perspective of program, the execution subject of the flow can be a program loaded on an application server. It can be understood that the method can be executed by any device, equipment, platform, device cluster with computing and processing capability.

[0043] As Figure 2 shown, the flow can include the following steps:

[0044] Step 202: respectively acquiring sensor information collected by multiple different types of sensors loaded on a target vehicle.

[0045] In the embodiment of the present specification, the corrected sensor data can be data collected by sensors loaded on a vehicle. Optionally, the sensors can include satellite positioning devices (such as GPS devices, RTK devices, etc.), inertial measurement devices (Inertial Measurement Unit, IMU), vehicle speed detection devices, radars or visual odometry, etc.

[0046] Step 204: acquiring, from high-precision map data, first map information corresponding to a predicted position of the target vehicle and second map information within a preset distance range around the predicted position.

[0047] The first map information can include road attribute information or lane attribute information; the second map information can include building attribute information. In the embodiment of the present specification, the building can be a fixed object on the ground surface, and can include naturally formed and artificially constructed, for example, the building can include buildings, road signs, trees, etc. The building attribute information acquired from the high-precision map data can specifically include coordinate information, size information, etc. of the building.

[0048] In practical applications, the vehicle can be repositioned according to a preset cycle as time passes or the vehicle moves. For example, the vehicle can be repositioned at certain time intervals, or after moving a certain distance. Furthermore, each repositioning can be based on the previous repositioning result; more specifically, it can be based on the prediction of the current vehicle position from the previous repositioning. (See this specification.) Figure 2 The technical solution corresponds to a single vehicle positioning process.

[0049] In the embodiments of this specification, when using high-precision map data to correct sensor data, it is first necessary to acquire the corresponding high-precision map data. Specifically, the corresponding high-precision map data can be acquired based on the estimated position of the target vehicle during the previous positioning.

[0050] In addition, when acquiring high-precision map data, high-precision data corresponding to the estimated location of the vehicle (referred to as first map information in the embodiments of this specification) can be obtained, such as data related to the lane, including lane width, road width, road slope, road curvature, lane speed limit, road speed limit, etc., and not limited to these. Furthermore, when acquiring high-precision map data, high-precision data within a certain distance range around the vehicle can also be obtained (referred to as second map information in the embodiments of this specification), such as road sign information, building information, etc.

[0051] Step 206: Based on at least one of the first map information and the second map information, the sensor information collected by the different types of sensors is corrected to obtain the corrected sensor information.

[0052] In the embodiments of this specification, the specific items of the high-precision map data required for calibration of different sensors may vary. In practical applications, the calibration of sensor information can be achieved by using only the first map information, only the second map information, or both the first and second map information. For example, the calibration can refer to the first map information corresponding to the estimated position of the target vehicle, such as road attribute information; or it can refer to the attribute information (e.g., coordinate information) of various terrain features around the target vehicle; or it can refer to both the first map information corresponding to the estimated position of the target vehicle and the attribute information of various terrain features around the target vehicle.

[0053] In addition, the sensor information can include sensing data, and can also include an accuracy factor. In actual application, the correction of the sensor information can include correction of the sensing data itself, or can include correction of the accuracy factor of the sensing data. Alternatively, the sensing data in the sensor information can be corrected based on at least one of the first map information and the second map information, and the sensing data specifically includes at least one of satellite positioning data, inertial measurement data, radar mileage data, visual mileage data, or vehicle speed data. In addition, the accuracy factor in the sensor information can be corrected based on the first map information.

[0054] Step 208: Fuse the corrected sensor information corresponding to the plurality of different types of sensors with the high-precision map data to obtain fused high-precision positioning information of the target vehicle.

[0055] In the embodiments of the present specification, after the high-precision map data is used to correct each type of sensor, the pose and accuracy information can be input to a back-end fusion algorithm (such as an Extended Kalman Filter (EKF)). The fusion algorithm applies appropriate data to its own state equation and observation equation as needed, and generates a fused positioning result.

[0056] In the embodiments of the present specification, by closely combining the high-precision map and fully utilizing the data advantages of the high-precision map, only low-cost sensors commonly used in traditional vehicles can be used to achieve a positioning scheme that is highly compatible with the high-precision map. The hardware cost is low, the real-time performance is good, and it is easy to mass-produce. For positioning schemes using more rich and high-cost sensors, the accuracy can also be improved and the use scenarios can be expanded.

[0057] It should be understood that in the method described in one or more embodiments of the present specification, the order of some steps can be adjusted according to actual needs, or some steps can be omitted.

[0058] Based on the method of Figure 2 The embodiments of the present specification also provide some specific implementations of the method, which are described below.

[0059] In one or more embodiments, the satellite positioning information collected by the satellite positioning device can be corrected before data fusion positioning. The satellite positioning information can be GPS information, RTK information, etc. In actual application, the latitude and longitude data is obtained by receiving information from the satellite and parsing by a chip, and then the high-precision map data is used to calibrate the parsed latitude and longitude data and its accuracy factor, so as to maintain a better positioning state.

[0060] In one aspect, the satellite positioning data itself can be corrected based on the high-precision map information.

[0061] Specifically, the sensing data can include satellite positioning information of the target vehicle collected by a satellite positioning device; and the second map information can specifically include attribute information of a ground object. First, satellite positioning information of the target vehicle collected by a satellite positioning device can be acquired; and surrounding ground object information of the target vehicle and relative coordinate information of the surrounding ground object relative to the target vehicle collected by a vector camera can be acquired. Then, candidate ground object information within a preset distance range around an estimated position of the target vehicle in a high-precision map can be acquired; the estimated position is determined based on the satellite positioning information of the target vehicle; and a target ground object matching the surrounding ground object collected by the vector camera can be determined from the candidate ground objects. Subsequently, the satellite positioning information of the target vehicle can be corrected based on absolute coordinate information of the target ground object and the relative coordinate information of the target ground object relative to the target vehicle, to obtain corrected satellite positioning information.

[0062] In actual application, a camera loaded on a vehicle performs environment perception, uses a perception algorithm to identify lane lines, signs and other vector information as camera data from identified image information. A relatively accurate vehicle position can be obtained through a rough position provided by RTK and fusion of vehicle body data (for example, vehicle speed, angular velocity and other signals provided by the vehicle body) and visual mileage collected by the camera. High-precision lane line information and sign information and other vector information can be collected in a high-precision map through the relatively accurate vehicle position. The camera data and the collected high-precision map information are compared, including comparison of lane line types, lane line colors, sign types and other information, and a matching result information with the highest probability is calculated using a probability model. After the best matching result information is provided, point column coordinates of a relative position of each vector (for example, lane lines, signs and the like) relative to the vehicle in the camera data are extracted, and then absolute coordinates of each vector (for example, lane lines, signs and the like) in the high-precision map are taken out, and the two groups of coordinate data are matched to calculate a corrected high-precision position. In the above manner, the positioning system can always maintain a stable high-precision positioning state.

[0063] In another aspect, the precision factor of the satellite positioning data can also be corrected based on the high-precision map information.

[0064] Specifically, the first map information can specifically include lane attribute information. First, satellite positioning information of the target vehicle collected by a satellite positioning device can be acquired; and surrounding ground object information of the target vehicle collected by a vector camera and relative coordinate information of the surrounding ground object relative to the target vehicle can be acquired; then, lane attribute information corresponding to an estimated position of the target vehicle in a high-precision map can be acquired, the lane attribute information including at least one of lane width information and lane position information, the lane position information being used to indicate whether a target lane is adjacent to a road boundary; subsequently, whether a preset positioning accuracy adjustment condition is satisfied can be determined according to the lane attribute information, to obtain a first determination result; and if the first determination result indicates that the preset positioning accuracy adjustment condition is satisfied, an accuracy factor of the satellite positioning information of the target vehicle is adjusted according to a positioning accuracy adjustment strategy corresponding to the preset positioning accuracy adjustment condition.

[0065] Optionally, the determining whether the preset positioning accuracy adjustment condition is satisfied according to the lane attribute information to obtain the first determination result can specifically include: determining whether the lane width of the lane where the target vehicle is located is less than a first preset threshold and the accuracy factor of the satellite positioning information of the target vehicle is greater than a second preset threshold to obtain a second determination result. Correspondingly, the adjusting the accuracy factor of the satellite positioning information of the target vehicle according to the positioning accuracy adjustment strategy corresponding to the preset positioning accuracy adjustment condition if the first determination result indicates that the preset positioning accuracy adjustment condition is satisfied can specifically include: if the second determination result indicates that the lane width of the lane where the target vehicle is located is less than the first preset threshold and the accuracy factor of the satellite positioning information of the target vehicle is greater than the second preset threshold, the accuracy factor of the satellite positioning information of the target vehicle is reduced according to a preset accuracy factor reduction scheme.

[0066] For example, when a vehicle travels on a road with a width of only 4 meters, the RTK gives relatively accurate position information, but due to external reasons, the position accuracy data value of the RTK signal is very large, exceeding 4 meters. In such a situation, through the lane information of the high-precision map, the accuracy factor can be corrected and reasonably reduced.

[0067] Optionally, the determining whether the preset positioning accuracy adjustment condition is met according to the lane attribute information to obtain a first determination result can specifically include: determining whether the lane where the target vehicle is located is adjacent to a road boundary and the accuracy factor of the satellite positioning information of the target vehicle is less than a third preset threshold to obtain a third determination result. Correspondingly, if the first determination result indicates that the preset positioning accuracy adjustment condition is met, the accuracy factor of the satellite positioning information of the target vehicle is adjusted according to a positioning accuracy adjustment strategy corresponding to the preset positioning accuracy adjustment condition, which can specifically include: if the third determination result indicates that the lane where the target vehicle is located is adjacent to a road boundary and the accuracy factor of the satellite positioning information of the target vehicle is less than a third preset threshold, the accuracy factor of the satellite positioning information of the target vehicle is amplified according to a preset accuracy factor amplification scheme.

[0068] For example, when the vehicle normally travels in a lane adjacent to a road boundary, the RTK signal can deviate outside the lane, but at this time, the accuracy data value given by the RTK signal is very small, and it is considered that the vehicle is located outside the road boundary. In such a case, through the lane information of the high-precision map, the accuracy factor can also be corrected and reasonably amplified.

[0069] It can be understood that the above-mentioned examples of correcting the satellite positioning information (including the positioning data itself and the accuracy factor thereof) are only for the purpose of illustration and do not constitute a limitation on the application range of the technical solutions of the present application. In actual applications, there can be other examples.

[0070] In one or more embodiments, the inertial measurement information collected by the inertial measurement device can be corrected before data fusion positioning.

[0071] The inertial measurement device, also known as an inertial measurement unit or an inertial sensor, is mainly used to detect and measure acceleration and rotational motion. The most basic inertial sensors include accelerometers and angular rate sensors (gyroscopes). The error of the inertial sensor will increase with time, so the inertial sensor can only be relied on for a short time. In an autonomous vehicle, the inertial sensor is usually used together with GNSS (Global Navigation Satellite System), which is called integrated inertial navigation.

[0072] Specifically, first, the inertial measurement information of the target vehicle collected by the inertial measurement unit can be acquired, and the inertial measurement information can include acceleration and angular velocity; and the road attribute information corresponding to the estimated position of the target vehicle in the high-precision map can be acquired; then, the inertial measurement information range of the target vehicle can be determined according to the road attribute information; and then, the inertial measurement information collected by the inertial measurement unit is corrected according to the inertial measurement information range to obtain corrected inertial measurement information.

[0073] The road attribute information can specifically include road slope information. That is, the first map information corresponding to the estimated position of the target vehicle and the second map information within a preset distance range around the estimated position are acquired from the high-precision map data, specifically, the road slope information of the road to which the estimated position of the target vehicle in the high-precision map belongs can be acquired. The correction of the sensor information collected by the different types of sensors based on at least one of the first map information and the second map information to obtain corrected sensor information can specifically include: determining a theoretical acceleration range of the target vehicle based on the road slope information; and correcting the acceleration collected by the inertial measurement unit according to the theoretical acceleration range.

[0074] For example, due to external factors such as road undulation, the motion state of the vehicle changes dramatically, at this time, the IMU swings and shakes with the body, the acceleration information of the IMU changes dramatically, and then the predicted speed and position of the vehicle will mutate seriously. In this case, using the slope data in the high-precision map can exclude such interference and effectively constrain the vehicle pose.

[0075] It can be understood that the above examples of correcting the IMU data are only for the purpose of illustration and do not constitute a limitation on the application range of the technical solutions of the present application. In actual applications, there can be other examples. For example, the angular velocity information of the vehicle can also be corrected based on the road attribute information (such as road curvature) of the location of the vehicle.

[0076] In one or more embodiments, the vehicle speed information collected by the vehicle speed detection device can be corrected before data fusion positioning.

[0077] Specifically, first, the speed information of the target vehicle collected by a speed sensor can be acquired; and the road attribute information corresponding to the estimated position of the target vehicle in a high-precision map can be acquired, the road attribute information including at least one of road speed limit information, road curvature information, and road slope information; then, based on the road attribute information, the theoretical speed range of the target vehicle can be determined; and according to the theoretical speed range, the speed information of the target vehicle is corrected to obtain corrected speed information, or the precision factor of the speed information of the target vehicle is determined.

[0078] For example, in an automatic driving environment, when the vehicle speed obtained by a speed sensor is 125 km / h, and the speed limit information of the road where the vehicle is currently located obtained from a high-precision map is 60-120 km / h, then the speed of 125 km / h can be corrected according to the limit of 60-120 km / h (for example, adjusted to 120 km / h and marked), or the precision factor of the vehicle speed can be determined to be 5 km / h or more.

[0079] In actual application, the speed signal can only provide the speed value, and cannot provide the precision related information of the value. In the case of high-precision map, the speed precision can be reasonably inferred and constrained according to the speed limit information, road curvature, slope and other information, so as to achieve better positioning effect.

[0080] In one or more embodiments, before data fusion positioning is performed on the simultaneous localization and mapping information collected by the odometer sensor, the simultaneous localization and mapping information can be corrected.

[0081] At present, the solutions for vehicle positioning based on visual SLAM and laser SLAM (Simultaneous Localization and Mapping) are not closely related to high-precision maps, and the advantages of high-precision maps are not fully utilized.

[0082] In the embodiments of the present specification, specifically, first, the synchronous positioning and mapping information collected by a mileage sensor, which includes at least one of a visual odometer or a radar odometer, can be acquired, and the synchronous positioning and mapping information includes relative position information of surrounding objects of the target vehicle relative to the target vehicle; then, the alternative object information within a preset distance range around the estimated position of the target vehicle in the high-precision map can be acquired, and the estimated position is determined based on satellite positioning information of the target vehicle; and the actual object information contained in the sensing information collected by the mileage sensor is determined by referring to the alternative object information; then, the target object corresponding to the actual object is determined from the alternative objects; and then, the vehicle pose information of the target vehicle can be corrected based on the absolute coordinate information of the target object and the relative coordinate information of the target object relative to the target vehicle, and the vehicle pose information is determined based on the synchronous positioning and mapping information collected by the mileage sensor.

[0083] In actual application, radar or visual sensing information can be used to perform semantic segmentation and target extraction with the aid of a high-precision map, and the perceived vector results (such as signs, lane lines, etc.) are extracted, and the perceived vector results are matched with the vector information stored in the high-precision map; after successful matching, the pose deviation between the stored pose of the quantity information in the high-precision map and the perceived pose of the quantity data is used to constrain the pose of the SLAM scheme, so as to maintain the high-precision positioning state of the vehicle.

[0084] In one or more embodiments, before data fusion positioning is performed on the data collected by any sensor, the data collected by the sensor can be corrected based on high-precision map data. In this way, the accuracy of the fusion positioning result and the robustness of the vehicle navigation positioning can be improved.

[0085] In the embodiments of the present specification, high-precision pose information is provided for automatic driving and intelligent cockpit, and the information of the high-precision map is dynamically fused in real time in combination with the input of various sensors. In the case where a positioning scheme relying only on sensors cannot achieve high-precision positioning, high-precision positioning is still maintained by relying on the data information of the high-precision map; when the confidence of the sensor data is unreliable, the high-precision map is used to correct the confidence of the sensor.

[0086] The high-precision positioning of the present scheme can expand the usable range of the automatic driving function, and at the same time, the pose information highly consistent with the high-precision map is more easily used by automatic driving and intelligent cockpit, so as to achieve better vehicle control effect and cockpit display effect.

[0087] Based on the same idea, the present specification also provides a device corresponding to the above method. Figure 3 The present specification provides a device corresponding to the above method.Figure 2 A schematic diagram of the structure of a fusion positioning module. (See diagram below.) Figure 3 As shown, this module may include:

[0088] The sensor information acquisition unit 302 is used to acquire sensor information collected by multiple different types of sensors mounted on the target vehicle.

[0089] The high-precision map information acquisition unit 304 is used to acquire, from high-precision map data, first map information corresponding to the estimated position of the target vehicle and second map information within a preset distance range around the estimated position; the first map information includes at least one of lane attribute information and road attribute information; the second map information includes ground feature attribute information.

[0090] The correction unit 306 is used to correct the sensor information collected by the different types of sensors based on at least one of the first map information and the second map information, so as to obtain the corrected sensor information.

[0091] The data fusion unit 308 is used to fuse the corrected sensor information corresponding to the multiple different types of sensors with the high-precision map data to obtain the fused high-precision positioning information of the target vehicle.

[0092] It is understood that the modules mentioned above refer to computer programs or program segments used to perform one or more specific functions. Furthermore, the distinction between these modules does not imply that the actual program code must also be separate.

[0093] Based on the same idea, the embodiments of this specification also provide high-precision map engines corresponding to the above methods and modules.

[0094] Figure 4 This is a schematic diagram of the structure of a high-precision map engine provided in the embodiments of this specification.

[0095] like Figure 4 As shown, the high-precision map engine 400 may include:

[0096] Includes such as Figure 3 The fusion positioning module 401 shown is shown.

[0097] The electronic horizon module 402 is used to receive external high-precision vehicle location information and match it to a map, providing a functional interface for autonomous driving applications to make control and judgments.

[0098] In addition, at least one of the following: autonomous driving design and operation domain judgment module 403, map update module 404, crowdsourcing preprocessing and feedback module 405, path intersection association module 406, and lane-level path planning module 407.

[0099] The automatic driving design operation domain judgment module 403 is configured to configure an automatic driving area and judge requirements.

[0100] The map update module 404 is configured to obtain map data update information of a high-precision map based on a vehicle position and a planned path.

[0101] The crowdsourcing preprocessing and return module 405 is configured to perform preprocessing such as screening and fusion on UGC visual vector data, return to the cloud, and update a map data center.

[0102] The path intersection correlation module 406 is configured to synchronize a global path planning result initiated by a user to an automatic driving system, perform cross correlation with a high-precision map, and obtain a matching path of a navigation path on the high-precision map.

[0103] The lane-level path planning module 407 is configured to output a lane level and a local path planning within a certain length range in front of a vehicle according to a result of navigation path matching and route correction.

[0104] The above describes specific embodiments of the present specification, and in some cases, the actions or steps recorded in the claims can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0105] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other.

[0106] The device, equipment and method provided by the embodiments of the present specification are corresponding, therefore, the device and equipment also have similar beneficial technical effects as the corresponding method, since the beneficial technical effects of the method have been described in detail above, therefore, the beneficial technical effects of the corresponding device and equipment will not be described here.

[0107] In the 1990s, it was possible to distinguish whether an improvement in a technology was a hardware improvement (e.g., an improvement in the circuit structure of a diode, transistor, switch, etc.) or a software improvement (an improvement in a method flow). However, as technology has advanced, many improvements in method flows today can be considered as direct improvements in hardware circuit structures. Designers almost always obtain a corresponding hardware circuit structure by programming the improved method flow into a hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A designer programs a digital system "integrated" on a PLD by himself / herself, without having to ask a chip manufacturer to design and manufacture a special integrated circuit chip. Moreover, instead of manually manufacturing an integrated circuit chip, this programming is now mostly implemented using "logic compiler" software, which is similar to a software compiler used when developing a program, and the original code before compilation is also written in a specific programming language, which is called a hardware description language (HDL), and there are many types of HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should be aware that, as long as a method flow is logically programmed in one of the above-mentioned hardware description languages and programmed into an integrated circuit, a hardware circuit implementing the logical method flow can be easily obtained.

[0108] The controller can be implemented in any suitable way, e.g. the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, e.g. software or firmware, executable by the (micro)processor, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers, examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91 SAM, Microchip PIC 18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to being implemented in pure computer readable program code form, the controller can perfectly well be implemented by means of logic programmed into logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers, etc. to perform the same functions. The controller can thus be considered as a hardware component, and the means comprised therein for performing various functions can be considered as structures within the hardware component. Alternatively, or even additionally, the means for performing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0109] The systems, apparatuses, modules or units illustrated by the above embodiments can be implemented by computer chips or entities, or products with certain functions. A typical implementation device is a computer. Specifically, the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0110] For the sake of description, the above apparatuses are described in various units by functions respectively. Of course, the functions of the units can be implemented in one or more software and / or hardware in the implementation of the present application.

[0111] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk memory, CD-ROM, optical memory, etc.) containing computer usable program code.

[0112] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks

[0113] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks

[0114] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks

[0115] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0116] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, for storing

[0117] Computer-readable media includes permanent and non-permanent, movable and non-movable 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0118] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus that includes a list of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0119] The present application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

[0120] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for determining high-precision positioning information, characterized in that, The method includes: The sensor information collected by multiple different types of sensors mounted on the target vehicle is acquired respectively; From high-precision map data, obtain first map information corresponding to the estimated location of the target vehicle and second map information within a preset distance range around the estimated location; the first map information includes at least one of lane attribute information and road attribute information; the second map information includes ground feature attribute information. Based on at least one of the first map information and the second map information, the sensor information collected by the different types of sensors is corrected to obtain the corrected sensor information. The calibrated sensor information corresponding to the multiple different types of sensors is fused with the high-precision map data to obtain the fused high-precision positioning information of the target vehicle.

2. The method as described in claim 1, characterized in that, The step of correcting the sensor information collected by the different types of sensors based on at least one of the first map information and the second map information specifically includes: The sensor information includes sensing data; The sensor data in the sensor information is corrected based on at least one of the first map information and the second map information.

3. The method as described in claim 2, characterized in that, The sensing data specifically includes at least one of the following: satellite positioning data, inertial measurement data, radar mileage data, visual mileage data, or vehicle speed data.

4. The method as described in claim 1, characterized in that, The step of correcting the sensor information collected by the different types of sensors based on at least one of the first map information and the second map information specifically includes: The sensor information includes an accuracy factor; Based on the first map information, the accuracy factor in the sensor information is corrected.

5. The method according to claim 2, characterized in that, The sensing data includes satellite positioning information of the target vehicle collected by the satellite positioning device; The step of correcting the sensor data in the sensor information based on at least one of the first map information and the second map information specifically includes: From the candidate ground features within a preset distance range around the estimated location of the target vehicle in the high-precision map, a target ground feature that matches the surrounding ground features captured by the vector camera is determined; the estimated location is determined based on the satellite positioning information of the target vehicle. The satellite positioning information of the target vehicle is corrected based on the absolute coordinate information of the target feature and the relative coordinate information of the target feature with respect to the target vehicle.

6. The method as described in claim 4, characterized in that, The lane attribute information includes at least one of lane width information and lane position information; The step of correcting the accuracy factor in the sensor information based on the first map information specifically includes: Based on the lane attribute information, determine whether the preset positioning accuracy adjustment conditions are met, and obtain the first judgment result; If the first judgment result indicates that the preset positioning accuracy adjustment conditions are met, then the accuracy factor of the satellite positioning information of the target vehicle is adjusted according to the positioning accuracy adjustment strategy corresponding to the preset positioning accuracy adjustment conditions.

7. The method as described in claim 6, characterized in that, The step of determining whether the preset positioning accuracy adjustment conditions are met based on the lane attribute information specifically includes: Determine whether the lane width of the lane where the target vehicle is located is less than a first preset threshold, and whether the accuracy factor of the satellite positioning information of the target vehicle is greater than a second preset threshold; If the first determination result indicates that a preset positioning accuracy adjustment condition is met, then the accuracy factor of the satellite positioning information of the target vehicle is adjusted according to the positioning accuracy adjustment strategy corresponding to the preset positioning accuracy adjustment condition, specifically including: If the lane width of the lane where the target vehicle is located is less than a first preset threshold, and the accuracy factor of the satellite positioning information of the target vehicle is greater than a second preset threshold, then the accuracy factor of the satellite positioning information of the target vehicle is reduced according to a preset accuracy factor reduction scheme.

8. The method as described in claim 6, characterized in that, The lane location information is specifically a first information or a second information, wherein the first information is used to indicate that the target lane is adjacent to the road boundary, and the second information is used to indicate that the target lane is not adjacent to the road boundary. The step of determining whether the preset positioning accuracy adjustment conditions are met based on the lane attribute information specifically includes: Determine whether the lane where the target vehicle is located is near the road boundary, and whether the accuracy factor of the satellite positioning information of the target vehicle is less than a third preset threshold; If the lane where the target vehicle is located is close to the road boundary, and the accuracy factor of the target vehicle's satellite positioning information is less than a third preset threshold, then the accuracy factor of the target vehicle's satellite positioning information is amplified according to a preset accuracy factor amplification scheme.

9. The method as described in claim 2, characterized in that, The sensing data includes inertial measurement information of the target vehicle collected by the inertial measurement unit; the inertial measurement information includes acceleration and angular velocity. Based on the road attribute information, determine the range of inertial measurement information for the target vehicle; Based on the range of inertial measurement information, the inertial measurement information collected by the inertial measurement unit is corrected to obtain corrected inertial measurement information.

10. The method as described in claim 9, characterized in that, The road attribute information specifically includes road slope information; Based on the road slope information, the theoretical acceleration range of the target vehicle is determined; The acceleration collected by the inertial measurement unit is corrected according to the theoretical acceleration range.

11. The method as described in claim 2, characterized in that, The sensing data includes the vehicle speed information of the target vehicle collected by the vehicle speed sensor; the road attribute information includes at least one of road speed limit information, road curvature information, and road slope information. Based on the road attribute information, the theoretical speed range of the target vehicle is determined; Based on the theoretical speed range, the vehicle speed information of the target vehicle is corrected to obtain corrected vehicle speed information, or the accuracy factor of the vehicle speed information of the target vehicle is determined.

12. The method as described in claim 2, characterized in that, The sensing data includes synchronous positioning and mapping information collected by the odometer sensor; the odometer sensor includes at least one of a visual odometer or a radar odometer; the synchronous positioning and mapping information includes the relative position information of the surrounding ground features of the target vehicle relative to the target vehicle. Referring to candidate ground features within a preset distance range around the estimated location of the target vehicle on a high-precision map, the actual ground feature information contained in the sensing information collected by the odometer sensor is determined; the estimated location is determined based on the satellite positioning information of the target vehicle. From the candidate features, determine the target feature that corresponds to the actual feature; Based on the absolute coordinates of the target feature and its relative coordinates with respect to the target vehicle, the vehicle pose information of the target vehicle is corrected; the vehicle pose information is determined based on the synchronous positioning and mapping information collected by the odometer sensor.

13. A fusion positioning module, characterized in that, The module includes: The sensor information acquisition unit is used to acquire sensor information collected by multiple different types of sensors mounted on the target vehicle. A high-precision map information acquisition unit is used to acquire, from high-precision map data, first map information corresponding to the estimated position of the target vehicle and second map information within a preset distance range around the estimated position; the first map information includes at least one of lane attribute information and road attribute information; the second map information includes ground feature attribute information. The calibration unit is used to calibrate the sensor information collected by the different types of sensors based on at least one of the first map information and the second map information, so as to obtain the calibrated sensor information. The data fusion unit is used to fuse the corrected sensor information corresponding to the multiple different types of sensors with the high-precision map data to obtain the fused high-precision positioning information of the target vehicle.

14. A high-precision map engine, characterized in that, include: The fusion positioning module as described in claim 13; The electronic horizon module is used to receive external high-precision vehicle location information and match it to a map, providing a functional interface for autonomous driving applications to make control and judgments. In addition, at least one of the following modules: autonomous driving design and operation domain judgment module, map update module, crowdsourcing preprocessing and feedback module, path intersection association module, and lane-level path planning module; The autonomous driving design operation domain judgment module is used to configure the autonomous driving area and judgment requirements. The map update module is used to obtain map data update information of a high-precision map based on the vehicle's location and the planned route. The crowdsourcing preprocessing and feedback module is used to filter and fuse UGC visual vector data, feed it back to the cloud, and update the map data center. The path cross-association module is used to synchronize the global path planning results initiated by the user to the autonomous driving system, and obtain the matching path of the navigation path on the high-precision map by cross-associating with the high-precision map. The lane-level path planning module is used to output lane-level local path planning within a certain length range in front of the vehicle based on the results of navigation path matching and route correction.

Images