Vehicle pose acquisition method and device based on vehicle-mounted multi-perception fusion

Abstract

The invention relates to a vehicle pose acquisition method and system based on vehicle-mounted multi-perception fusion, and the method comprises the steps: constructing an electronic map based on the environment feature information of a driving region of a vehicle, obtaining a deviation component of the vehicle in a region driving road section in an open region of a driving target path of the vehicle, and obtaining the position of the vehicle; based on the deviation component of the regional driving road section, obtaining a matched regional driving effective distance, regional driving effective time and regional driving effective speed to construct a component model, obtaining a deviation component curve of the vehicle in the empty region of the driving target path in the component model, and obtaining a deviation component curve of the vehicle in the shielding region of the driving target path of the vehicle; obtaining environment characteristic information of the shielding area of the vehicle driving target path, obtaining the deviation margin of the vehicle in the shielding area based on the driving effective parameters of the environment characteristic information in the shielding area of the vehicle, and correcting the position of the vehicle on the electronic map according to the deviation margin of the vehicle in the shielding area. And the accurate position information of the driving target path of the vehicle is obtained.

Description

Technical Field

[0001] The present invention relates to the field of positioning, and in particular to a method and device for acquiring vehicle posture based on vehicle-mounted multi-sensory fusion. Background Art

[0002] With the continuous development of science and technology, positioning technology has been widely used in various fields, such as unmanned driving, robot navigation, virtual reality, etc. At present, the commonly used positioning methods mainly include GPS-based positioning, computer vision-based positioning, and inertial sensor-based positioning. However, each of these methods has certain limitations.

[0003] Positioning is particularly difficult in complex environments and extreme weather conditions. Complex environments include tunnels, urban canyons, underground garages, multi-level interchanges and other signal-blocked areas. When vehicles travel in the above environments, satellite signals are easily blocked or interfered with, resulting in positioning blind spots. Extreme weather includes rainy and snowy weather and driving at night. Car sensors are affected by light and water vapor, resulting in positioning errors.

[0004] Based on this, the present invention proposes a vehicle posture acquisition method and device based on vehicle-mounted multi-sensory fusion. Summary of the invention

[0005] The present invention aims at the technical problems existing in the prior art. A component model is constructed in a three-dimensional coordinate system for the deviation components of all regional driving sections in an open area and the corresponding regional effective driving time, regional effective driving speed and regional effective driving distance. The deviation components of the obtained several regional driving sections are connected by a smooth curve in the three-dimensional coordinate system to obtain a deviation component curve of a vehicle in an open area of ​​a driving target path. According to the deviation component curve of the vehicle in the open area of ​​the driving target path, the effective driving time, effective driving speed and effective driving distance of the vehicle in a blocked area of ​​the driving target path under a signal blocking condition are obtained. The effective driving time, effective driving speed and effective driving distance under the signal blocking condition are introduced into the component model to obtain a pre-deviation component of a punctuation environment feature position in the blocked area. When the pre-deviation component of the punctuation environment feature position meets the condition, the pre-deviation component and the effective driving distance under the blocking condition are processed to obtain the target positioning of the blocked area of ​​the vehicle driving target path, and the target positioning is marked on an electronic map to complete the reliable positioning of the vehicle on the driving path under the signal blocking condition.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: a vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion, which constructs an electronic map based on the environmental feature information of the vehicle's driving area to obtain the vehicle's driving target path;

[0007] In an open area of ​​the vehicle's target driving path, the vehicle's driving position and driving position information are obtained multiple times to obtain the deviation component of the vehicle in the regional driving section, and the matching regional driving effective distance, regional driving effective time and regional driving effective speed are obtained based on the deviation component of the regional driving section;

[0008] According to the deviation components of multiple regional driving sections, a component model is constructed by matching the effective regional driving distance, the effective regional driving time and the effective regional driving speed, and a deviation component curve of the vehicle in the open area of ​​the driving target path is obtained in the component model;

[0009] In the blocked area of ​​the vehicle's target path, environmental characteristic information of the blocked area of ​​the vehicle's target path is obtained, and effective driving parameters of the vehicle in the blocked area are obtained based on the environmental characteristic information. According to the effective driving parameters of the blocked area, the deviation margin of the vehicle in the blocked area is obtained, and according to the deviation margin of the vehicle in the blocked area, the position of the vehicle on the electronic map is corrected to obtain accurate position information of the vehicle's target path.

[0010] As a further technical solution of the present invention, the driving position of the vehicle and the driving position information are obtained by an on-board environment recognition unit.

[0011] As a further technical solution of the present invention, the process of obtaining the deviation component of the regional driving section includes:

[0012] Get the starting position of the regional driving section and record it as the regional starting position;

[0013] The real-time environmental feature information of the regional driving section is collected by the vehicle-mounted environmental recognition unit, the collected real-time environmental feature information is matched with the driving area environmental feature information used to construct the electronic map, and the real-time environmental feature information that matches consistently is recorded as the punctuation environmental feature information;

[0014] Mark each punctuation point environmental feature information in the regional driving section at a fixed point to obtain the punctuation point environmental feature position;

[0015] Taking the starting position of the area as the starting point and following the direction of the driving trajectory, several punctuation environment segments are obtained;

[0016] and obtaining the actual punctuation position of the punctuation environment feature position in each punctuation environment segment on the electronic map;

[0017] And according to the vehicle driving speed and vehicle driving time in the punctuation environment section, the evaluation punctuation point position of the punctuation point environment characteristic position on the electronic map is obtained;

[0018] Obtaining a deviation value between an actual punctuation point position of a punctuation point environment characteristic position on an electronic map within a punctuation point environment segment and an estimated punctuation point position of the punctuation point environment characteristic position on the electronic map;

[0019] The deviation values ​​of all punctuation environment segments are processed to obtain the deviation components of the regional driving segments.

[0020] As a further technical solution of the present invention, the deviation values ​​of all punctuation environment segments are processed in the following process:

[0021] Integrate the deviation values ​​of all punctuation environment segments to obtain a deviation value group S1, S2, S3, ..., Sn of the punctuation environment feature positions of the regional driving section on the electronic map;

[0022] According to the formula The standard deviation value Sa of the deviation amount group of the regional driving section is calculated, wherein Sp is the average value of the deviation amount groups S1, S2, S3, ..., Sn;

[0023] If the standard deviation value Sa of the regional driving section deviation group is greater than or equal to the preset standard deviation value Sy, delete the maximum value and / or minimum value in the regional driving section deviation group data, and calculate the standard deviation value Sa of the regional driving section deviation group data again until Sa is less than the preset standard deviation value Sy, then sum and average the remaining data in the regional driving section deviation group to obtain the deviation component of the regional driving section.

[0024] As a further technical solution of the present invention, in the process of obtaining the deviation component of the regional driving section, the punctuation environment section corresponding to the maximum value and / or minimum value in the deleted regional driving section deviation amount group data is recorded as an abnormal environment section;

[0025] The abnormal environment segments in the regional driving section are removed, and the remaining punctuation environment segments are reorganized to obtain the effective regional driving distance;

[0026] And obtain the effective time of regional travel and effective speed of regional travel for effective regional travel distance;

[0027] Obtaining deviation components of a plurality of regional driving sections and regional driving effective distances, regional driving effective times and regional driving effective speeds corresponding to the deviation components of the plurality of regional driving sections;

[0028] A three-dimensional coordinate system is established, and a component model is constructed with the effective time of regional travel as the X-axis, the effective speed of regional travel as the Y-axis, and the effective distance of regional travel as the Z-axis, and the deviation component of the regional travel section obtained by constructing the effective time of regional travel, the effective speed of regional travel, and the effective distance of regional travel in the three-dimensional coordinate system is marked;

[0029] The deviation components of several driving sections are connected with smooth curves in three-dimensional coordinates to obtain the deviation component curve of the vehicle in the open area of ​​the driving target path.

[0030] As a further technical solution of the present invention, the starting position of the vehicle traveling in the shielded area is obtained, and recorded as the shielded starting position;

[0031] The real-time environment feature information in the blocked area is collected by the vehicle environment recognition unit, the collected real-time environment feature information is matched with the environment feature information of the driving area used to construct the electronic map, and the real-time environment feature information that matches consistently is recorded as the punctuation environment feature information;

[0032] Mark the punctuation environment feature information in the occluded area at a fixed point to obtain the punctuation environment feature position in the occluded area;

[0033] When the vehicle reaches each occlusion area mark environmental feature position, the effective driving parameters from the occlusion starting position to the occlusion area mark environmental feature position are obtained, and the effective driving parameters include the effective tunnel driving time, the effective tunnel driving speed and the effective tunnel driving distance;

[0034] The effective tunnel driving time, effective tunnel driving speed and effective tunnel driving distance of the tunnel punctuation environmental characteristic position are placed into the component model to obtain the pre-deviation point of the tunnel punctuation environmental characteristic position in the component model.

[0035] As a further technical solution of the present invention, the pre-deviation point of the tunnel driving section is obtained and connected with the deviation component curve in the component model to obtain the shortest displacement distance between the pre-deviation point of the tunnel driving section and the deviation component curve in the component model;

[0036] The intersection point of the pre-deviation point of the tunnel driving section and the deviation component curve in the component model is recorded as the pre-deviation component of the tunnel mark environmental feature position;

[0037] The shortest displacement distance is recorded as and recorded as the validation deviation length;

[0038] If the verification deviation length is within the preset verification deviation length interval, a verification consistency signal is obtained;

[0039] Based on the verification consistent signal, the pre-deviation component is recorded as the deviation margin of the characteristic position of the tunnel punctuation environment;

[0040] The effective distance traveled in the tunnel is summed with the deviation margin of the characteristic position of the tunnel punctuation environment to obtain the target positioning of the occluded area of ​​the vehicle's driving target path.

[0041] A vehicle posture acquisition system based on vehicle-mounted multi-sensor fusion, comprising:

[0042] A map construction module, wherein the map construction module constructs an electronic map based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path;

[0043] An open area analysis module, in an open area of ​​the vehicle's target driving path, is used to obtain the vehicle's driving position and driving position information multiple times to obtain the vehicle's deviation component in the regional driving section, and obtain the matching regional driving effective distance, regional driving effective time and regional driving effective speed based on the deviation component of the regional driving section;

[0044] A model building module, wherein the model building module obtains a component model based on deviation components of multiple regional driving sections to match the effective distance of regional driving, the effective time of regional driving, and the effective speed of regional driving, and obtains a deviation component curve of the vehicle in an open area of ​​the driving target path in the component model;

[0045] The occlusion area positioning module obtains environmental characteristic information of the occlusion area of ​​the vehicle's target path in the occlusion area, and obtains the deviation margin of the vehicle in the occlusion area based on the effective driving parameters of the vehicle in the occlusion area based on the environmental characteristic information, and corrects the position of the vehicle on the electronic map according to the deviation margin of the vehicle in the occlusion area to obtain the precise position information of the vehicle's target path.

[0046] The beneficial effects of the present invention are:

[0047] (1) The present invention uses the target driving path of the vehicle in the open area as a reference, divides the target driving path open area into several regional driving sections, performs fixed-point marking on the punctuation environment feature information in each regional driving section, obtains the punctuation environment feature position, and obtains the corresponding punctuation environment section based on the punctuation environment feature position, processes the actual punctuation position and the evaluated punctuation position of the punctuation environment feature position corresponding to each punctuation environment section on the electronic map, obtains the deviation of the punctuation environment feature position on the electronic map, integrates the deviation of all punctuation environment feature positions in the regional driving section, thereby obtaining the deviation component of the regional driving section, and completes the deviation of the travel distance obtained by the time and speed of the vehicle during the driving process on the electronic map and the satellite positioning, and the deviation is screened and processed multiple times, so that the deviation component of the regional driving section is highly accurate;

[0048] (2) The present invention constructs a component model in a three-dimensional coordinate system for the deviation components of all regional driving sections in an open area and the corresponding regional effective driving time, regional effective driving speed and regional effective driving distance, that is, the deviation components of several regional driving sections are connected by a smooth curve in the three-dimensional coordinate system to obtain a deviation component curve of the vehicle in the open area of ​​the driving target path. According to the deviation component curve of the vehicle in the open area of ​​the driving target path, the effective driving time, effective driving speed and effective driving distance of the vehicle in the blocked area of ​​the driving target path under the signal blocking condition are obtained, and the effective driving time, effective driving speed and effective driving distance under the signal blocking condition are introduced into the component model to obtain a pre-deviation component of the punctuation environment feature position in the blocked area. When the pre-deviation component of the punctuation environment feature position meets the conditions, the pre-deviation component and the effective driving distance under the blocking condition are processed to obtain the target positioning of the blocked area of ​​the vehicle's driving target path, and the target positioning is marked on the electronic map to complete the reliable positioning of the vehicle on the driving path under the signal blocking condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The present invention is a flowchart of a method for acquiring vehicle posture based on vehicle-mounted multi-sensor fusion according to an embodiment of the present invention;

[0050] Figure 2 The embodiment of the present invention is a flowchart of a vehicle posture acquisition system based on vehicle-mounted multi-sensor fusion;

[0051] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 those skilled in the art without creative work are within the scope of protection of this application.

[0054] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0055] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0056] Example 1

[0057] A vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion includes the following steps:

[0058] An electronic map is constructed based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path;

[0059] The driving area environmental characteristic information includes road condition information and building information of the driving area;

[0060] In an open area of ​​the vehicle's target driving path, the vehicle's driving position and driving position information are obtained multiple times to obtain the deviation component of the vehicle in the regional driving section, and the matching regional driving effective distance, regional driving effective time and regional driving effective speed are obtained based on the deviation component of the regional driving section;

[0061] According to the deviation components of multiple regional driving sections, a component model is constructed by matching the effective regional driving distance, the effective regional driving time and the effective regional driving speed, and a deviation component curve of the vehicle in the open area of ​​the driving target path is obtained in the component model;

[0062] Among them, an empty area on the driving target path indicates that the signal is not blocked;

[0063] In the blocked area of ​​the vehicle's target path, environmental feature information of the blocked area of ​​the vehicle's target path is obtained, and based on the effective parameters of the vehicle's driving in the blocked area, the deviation margin of the vehicle in the blocked area is obtained according to the effective parameters of the driving in the blocked area, and the position of the vehicle on the electronic map is corrected according to the deviation margin of the vehicle in the blocked area to obtain accurate position information of the vehicle's target path;

[0064] Among them, the occlusion area of ​​the driving target path shows that the signal is blocked.

[0065] Select m regional driving sections on the open area of ​​the driving target path, obtain the deviation component of each regional driving section, and construct the deviation component curve of the vehicle in the open area of ​​the driving target path in three-dimensional coordinates by using the deviation component of each regional driving section, that is, obtain the deviation margin of the vehicle in the open area of ​​the driving target path;

[0066] Specifically, the process of obtaining the deviation component of the regional driving section is as follows:

[0067] Get the starting position of the regional driving section and record it as the regional starting position;

[0068] The real-time environmental feature information of the regional driving section is collected by the vehicle-mounted environmental recognition unit, the collected real-time environmental feature information is matched with the driving area environmental feature information used to construct the electronic map, and the real-time environmental feature information that matches consistently is recorded as the punctuation environmental feature information;

[0069] Wherein, the vehicle-mounted environment recognition unit includes but is not limited to a camera device;

[0070] Mark the environmental characteristic information of the punctuation points in the regional driving section at fixed points to obtain the environmental characteristic positions of the punctuation points;

[0071] Taking the starting position of the area as the starting point, according to the driving trajectory direction, the interval between the starting position of the area and the first punctuation environmental feature position within the driving section of the area is recorded as the first punctuation environmental segment;

[0072] Record the interval between the second punctuation environment feature position and the second punctuation environment feature position as the second punctuation environment segment;

[0073] The interval between the second punctuation environment characteristic position and the third punctuation environment characteristic position is recorded as the third punctuation environment segment;

[0074] By analogy, the interval between the n-1th punctuation environment feature position and the nth punctuation environment feature position is recorded as the nth punctuation environment segment.

[0075] Obtaining the actual punctuation position of the first punctuation environment feature position in the first punctuation environment segment on the electronic map;

[0076] Among them, the actual punctuation position is obtained by satellite positioning;

[0077] Establish a plane coordinate system, with the horizontal axis being time and the vertical axis being speed;

[0078] The vehicle driving speed in the first punctuation point environment section is plotted in the plane coordinate system to obtain the vehicle driving curve in the first punctuation point environment section;

[0079] Obtaining the area formed by the vehicle driving curve and the plane coordinate system in the first punctuation environmental segment, and obtaining the driving distance value of the first punctuation environmental segment;

[0080] Mark the driving distance value of the first punctuation point environment section on the electronic map according to the driving length, and obtain the evaluation punctuation point position of the first punctuation point environment feature position on the electronic map;

[0081] Calculate the actual punctuation point position of the first punctuation point environment characteristic position on the electronic map and the estimated punctuation point position of the first punctuation point environment characteristic position on the electronic map to obtain the deviation of the first punctuation point environment characteristic position on the electronic map, and record it as S1;

[0082] Obtain the deviation between the first punctuation environmental feature position on the electronic map and the second punctuation environmental feature position on the electronic map, and record it as S2;

[0083] By analogy, the deviation of the nth punctuation environmental feature position on the electronic map is obtained, which is recorded as Sn;

[0084] Thus, a deviation group S1, S2, S3, ..., Sn of the punctuation environmental feature positions of the regional driving section on the electronic map is obtained;

[0085] According to the formula The standard deviation value Sa of the deviation amount group of the regional driving section is calculated, wherein Sp is the average value of the deviation amount groups S1, S2, S3, ..., Sn;

[0086] If the standard deviation value Sa of the regional driving section deviation group is greater than or equal to the preset standard deviation value Sy, delete the maximum value and / or minimum value in the regional driving section deviation group data, and calculate the standard deviation value Sa of the regional driving section deviation group data again until Sa is less than the preset standard deviation value Sy, then sum and average the remaining data in the regional driving section deviation group to obtain the deviation component of the regional driving section.

[0087] In the process of obtaining the deviation component of the regional driving section, the punctuation environment section corresponding to the maximum value and / or the minimum value in the deleted regional driving section deviation amount group data is recorded as the abnormal environment section;

[0088] The abnormal environment segments in the regional driving section are removed, and the remaining punctuation environment segments are reorganized to obtain the effective regional driving distance;

[0089] And obtain the effective time of regional travel and effective speed of regional travel for effective regional travel distance;

[0090] Among them, the effective time of regional travel is the time to complete the effective distance of regional travel;

[0091] Among them, the effective speed of regional driving is the average speed of completing the effective distance of regional driving;

[0092] Thus, the deviation component of the regional driving section and the regional driving effective distance, regional driving effective time and regional driving effective speed corresponding to the deviation component of the regional driving section are obtained.

[0093] Obtaining deviation components of m regional driving sections and regional driving effective distances, regional driving effective times and regional driving effective speeds corresponding to the deviation components of the multiple regional driving sections;

[0094] A three-dimensional coordinate system is established, and a component model is constructed with the effective time of regional travel as the X-axis, the effective speed of regional travel as the Y-axis, and the effective distance of regional travel as the Z-axis, and the deviation component of the obtained regional travel section is constructed in the three-dimensional coordinate system with the effective time of regional travel, the effective speed of regional travel, and the effective distance of regional travel obtained by the regional travel section;

[0095] The deviation components of the m regional driving sections are connected by smooth curves in the three-dimensional coordinates to obtain the deviation component curve of the vehicle in the open area of ​​the driving target path.

[0096] In the vehicle's target path obstruction area, this embodiment takes a tunnel as an example;

[0097] Get the starting position of the tunnel, and record it as the starting position of the tunnel;

[0098] The real-time environment feature information in the tunnel is collected by the vehicle-mounted environment recognition unit, the collected real-time environment feature information is matched with the environment feature information of the driving area used to construct the electronic map, and the real-time environment feature information that matches consistently is recorded as the punctuation environment feature information;

[0099] Mark the environmental characteristic information of the punctuation points in the tunnel at fixed points to obtain the environmental characteristic positions of the punctuation points in the tunnel;

[0100] When the vehicle arrives at each tunnel punctuation environmental characteristic position, the effective driving parameters from the tunnel starting position to the tunnel punctuation environmental characteristic position are obtained, and the effective driving parameters include the effective tunnel driving time, the effective tunnel driving speed and the effective tunnel driving distance;

[0101] The effective time of tunnel driving is the time taken by the vehicle to reach the characteristic position of the tunnel punctuation environment from the starting position of the tunnel. The effective time of tunnel driving is detected by the time sensor built into the vehicle.

[0102] The effective speed of tunnel driving is the average speed of the vehicle from the starting position of the tunnel to the characteristic position of the tunnel punctuation environment. The effective speed of tunnel driving is detected by the vehicle's built-in speed sensor.

[0103] The effective distance of tunnel driving is the distance from the starting position of the tunnel to the characteristic position of the tunnel punctuation environment;

[0104] The effective tunnel driving time, effective tunnel driving speed and effective tunnel driving distance of the tunnel punctuation environmental characteristic position are placed into the component model to obtain the pre-deviation point of the tunnel punctuation environmental characteristic position in the component model;

[0105] The pre-deviation point of the tunnel driving section is obtained and connected with the deviation component curve in the component model to obtain the shortest displacement distance between the pre-deviation point of the tunnel driving section and the deviation component curve in the component model;

[0106] The intersection point of the pre-deviation point of the tunnel driving section and the deviation component curve in the component model is recorded as the pre-deviation component of the tunnel mark environmental feature position;

[0107] The shortest displacement distance is recorded as and recorded as the validation deviation length;

[0108] If the verification deviation length is within the preset verification deviation length interval, a verification consistency signal is obtained;

[0109] Based on the verification consistent signal, the pre-deviation component is recorded as the deviation margin of the characteristic position of the tunnel punctuation environment;

[0110] If the verification deviation length is not within the preset verification deviation length interval, a divergence and agreement signal is obtained;

[0111] Based on the divergent and consistent signals, the vehicle-mounted environment recognition unit pre-processes the real-time environment feature information in the tunnel;

[0112] Preprocessing includes but is not limited to methods such as smoothing filtering, denoising, and removing artifacts of real-time environmental feature information.

[0113] In a specific embodiment, based on the divergence and consistency signals, correction processing of the effective time and effective speed of tunnel driving is also included.

[0114] Based on the verification consistency signal, the deviation margin of the effective tunnel driving distance and the tunnel punctuation environmental feature position is summed to obtain the target positioning of the vehicle's driving target path obstruction area, and the target positioning is marked on the electronic map to obtain the precise position information of the vehicle's driving target path.

[0115] Based on the above working process, it can be known that, with the target driving path of the vehicle in the open area as a reference, the open area of ​​the target driving path is divided into several regional driving sections, the punctuation environment feature information in each regional driving section is fixed-point marked to obtain the punctuation environment feature position, and the corresponding punctuation environment section is obtained based on the punctuation environment feature position, the actual punctuation position and the evaluated punctuation position of the punctuation environment feature position corresponding to each punctuation environment section on the electronic map are processed to obtain the deviation of the punctuation environment feature position on the electronic map, the deviation of all punctuation environment feature positions in the regional driving section is integrated and processed, so as to obtain the deviation component of the regional driving section, and the travel distance obtained by the time and speed of the vehicle during the driving process on the electronic map and the satellite positioning deviation are completed, and the deviation is screened and processed multiple times, so that the deviation component of the regional driving section is highly accurate;

[0116] Furthermore, a component model is constructed in a three-dimensional coordinate system for the deviation components of all regional driving sections in the open area and the corresponding regional driving effective time, regional driving effective speed and regional driving effective distance, that is, the deviation components of several regional driving sections obtained are connected by a smooth curve in the three-dimensional coordinate system to obtain a deviation component curve of the vehicle in the open area of ​​the driving target path, and based on the deviation component curve of the vehicle in the open area of ​​the driving target path, the effective driving time, effective driving speed and effective driving distance of the vehicle in the blocked area of ​​the driving target path under the signal blocking condition are obtained, and the effective driving time, effective driving speed and effective driving distance under the signal blocking condition are introduced into the component model to obtain a pre-deviation component of the punctuation environment feature position in the blocked area, and when the pre-deviation component of the punctuation environment feature position meets the conditions, the pre-deviation component and the effective driving distance under the blocking condition are processed to obtain the target positioning of the blocked area of ​​the vehicle's driving target path, and the target positioning is marked on the electronic map, thereby obtaining the precise position information of the vehicle's driving target path.

[0117] Example 2

[0118] See also Figure 2 , a vehicle posture acquisition device based on vehicle-mounted multi-sensor fusion, comprising:

[0119] A map construction module, wherein the map construction module constructs an electronic map based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path;

[0120] The driving area environmental characteristic information includes road condition information and building information of the driving area;

[0121] An open area analysis module, in an open area of ​​the vehicle's target driving path, is used to obtain the vehicle's driving position and driving position information multiple times to obtain the vehicle's deviation component in the regional driving section, and obtain the matching regional driving effective distance, regional driving effective time and regional driving effective speed based on the deviation component of the regional driving section;

[0122] A model building module, wherein the model building module obtains a component model based on deviation components of multiple regional driving sections to match the effective distance of regional driving, the effective time of regional driving, and the effective speed of regional driving, and obtains a deviation component curve of the vehicle in an open area of ​​the driving target path in the component model;

[0123] Among them, the empty area of ​​the driving target path indicates that the signal is not blocked;

[0124] The obstruction area positioning module obtains environmental characteristic information of the obstruction area of ​​the vehicle's driving target path in the obstruction area, obtains the deviation margin of the vehicle in the obstruction area based on the effective parameters of the vehicle in the obstruction area based on the environmental characteristic information, and corrects the position of the vehicle on the electronic map according to the deviation margin of the vehicle in the obstruction area to obtain the precise position information of the vehicle's driving target path;

[0125] Among them, the occlusion area of ​​the driving target path shows that the signal is blocked.

[0126] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0127] An electronic map is constructed based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path;

[0128] The driving area environmental characteristic information includes road condition information and building information of the driving area;

[0129] In an open area of ​​the vehicle's target driving path, the vehicle's driving position and driving position information are obtained multiple times to obtain the deviation component of the vehicle in the regional driving section, and the matching regional driving effective distance, regional driving effective time and regional driving effective speed are obtained based on the deviation component of the regional driving section;

[0130] According to the deviation components of multiple regional driving sections, a component model is constructed by matching the effective regional driving distance, the effective regional driving time and the effective regional driving speed, and a deviation component curve of the vehicle in the open area of ​​the driving target path is obtained in the component model;

[0131] Among them, an empty area on the driving target path indicates that the signal is not blocked;

[0132] In the blocked area of ​​the vehicle's target path, environmental feature information of the blocked area of ​​the vehicle's target path is obtained, and based on the effective parameters of the vehicle's driving in the blocked area, the deviation margin of the vehicle in the blocked area is obtained according to the effective parameters of the driving in the blocked area, and the position of the vehicle on the electronic map is corrected according to the deviation margin of the vehicle in the blocked area to obtain accurate position information of the vehicle's target path;

[0133] Among them, the occlusion area of ​​the driving target path shows that the signal is blocked.

[0134] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the steps of any of the above-mentioned vehicle posture acquisition methods based on vehicle-mounted multi-sensor fusion are implemented.

[0135] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] 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.

[0137] 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 computer, or other programmable data processing device to generate 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.

[0138] 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.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0140] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion, characterized in that: An electronic map is constructed based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path; In an open area of ​​the vehicle's target driving path, the vehicle's driving position and driving position information are obtained multiple times to obtain the deviation component of the vehicle in the regional driving section, and the matching regional driving effective distance, regional driving effective time and regional driving effective speed are obtained based on the deviation component of the regional driving section; According to the deviation components of multiple regional driving sections, a component model is constructed by matching the effective regional driving distance, the effective regional driving time and the effective regional driving speed, and a deviation component curve of the vehicle in the open area of ​​the driving target path is obtained in the component model; In the blocked area of ​​the vehicle's target path, environmental characteristic information of the blocked area of ​​the vehicle's target path is obtained, and effective driving parameters of the vehicle in the blocked area are obtained based on the environmental characteristic information. According to the effective driving parameters of the blocked area, the deviation margin of the vehicle in the blocked area is obtained, and according to the deviation margin of the vehicle in the blocked area, the position of the vehicle on the electronic map is corrected to obtain accurate position information of the vehicle's target path.

2. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 1 is characterized in that: The vehicle's driving position and driving position information are obtained through the vehicle-mounted environment recognition unit.

3. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 2 is characterized in that: The process of obtaining the deviation component of the regional driving section includes: Get the starting position of the regional driving section and record it as the regional starting position; The real-time environmental feature information of the regional driving section is collected by the vehicle-mounted environmental recognition unit, the collected real-time environmental feature information is matched with the driving area environmental feature information used to construct the electronic map, and the real-time environmental feature information that matches consistently is recorded as the punctuation environmental feature information; Mark each punctuation point environmental feature information in the regional driving section at a fixed point to obtain the punctuation point environmental feature position; Taking the starting position of the area as the starting point and following the direction of the driving trajectory, several punctuation environment segments are obtained; and obtaining the actual punctuation position of the punctuation environment feature position in each punctuation environment segment on the electronic map; and obtaining the evaluation punctuation point position of the punctuation point environment characteristic position on the electronic map according to the vehicle travel speed and vehicle travel time in the punctuation point environment segment; Obtaining a deviation value between an actual punctuation point position of a punctuation point environment characteristic position on an electronic map within a punctuation point environment segment and an estimated punctuation point position of the punctuation point environment characteristic position on the electronic map; The deviation values ​​of all punctuation environment segments are processed to obtain the deviation components of the regional driving segments.

4. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 3 is characterized in that: The deviation value processing process of all punctuation environment segments includes: Integrate the deviation values ​​of all punctuation environment segments to obtain a deviation value group S1, S2, S3, ..., Sn of the punctuation environment feature positions of the regional driving section on the electronic map; According to the formula The standard deviation value Sa of the deviation amount group of the regional driving section is calculated, wherein Sp is the average value of the deviation amount groups S1, S2, S3, ..., Sn; If the standard deviation value Sa of the regional driving section deviation group is greater than or equal to the preset standard deviation value Sy, delete the maximum value and / or minimum value in the regional driving section deviation group data, and calculate the standard deviation value Sa of the regional driving section deviation group data again until Sa is less than the preset standard deviation value Sy, then sum and average the remaining data in the regional driving section deviation group to obtain the deviation component of the regional driving section.

5. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 4 is characterized in that: In the process of obtaining the deviation component of the regional driving section, the punctuation environment section corresponding to the maximum value and / or the minimum value in the deleted regional driving section deviation amount group data is recorded as the abnormal environment section; The abnormal environment segments in the regional driving section are removed, and the remaining punctuation environment segments are reorganized to obtain the effective regional driving distance; And obtain the effective time of regional travel and effective speed of regional travel for effective regional travel distance; Obtaining deviation components of a plurality of regional driving sections and regional driving effective distances, regional driving effective times and regional driving effective speeds corresponding to the deviation components of the plurality of regional driving sections; A three-dimensional coordinate system is established, and a component model is constructed with the effective time of regional travel as the X-axis, the effective speed of regional travel as the Y-axis, and the effective distance of regional travel as the Z-axis, and the deviation component of the regional travel section obtained by constructing the effective time of regional travel, the effective speed of regional travel, and the effective distance of regional travel in the three-dimensional coordinate system is marked; The deviation components of several regional driving sections are connected by smooth curves in three-dimensional coordinates to obtain the deviation component curve of the vehicle in the open area of ​​the driving target path.

6. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 5 is characterized in that: Obtain the starting position of the vehicle in the occlusion area, recorded as the occlusion starting position; The real-time environment feature information in the blocked area is collected by the vehicle environment recognition unit, the collected real-time environment feature information is matched with the environment feature information of the driving area used to construct the electronic map, and the real-time environment feature information that matches consistently is recorded as the punctuation environment feature information; Mark the punctuation environment feature information in the occluded area at a fixed point to obtain the punctuation environment feature position in the occluded area; When the vehicle reaches each occlusion area mark environmental feature position, the effective driving parameters from the occlusion starting position to the occlusion area mark environmental feature position are obtained, and the effective driving parameters include the effective tunnel driving time, the effective tunnel driving speed and the effective tunnel driving distance; The effective tunnel driving time, effective tunnel driving speed and effective tunnel driving distance of the tunnel punctuation environmental characteristic position are placed into the component model to obtain the pre-deviation point of the tunnel punctuation environmental characteristic position in the component model.

7. The vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion according to claim 6 is characterized in that: The pre-deviation point of the tunnel driving section is obtained and connected with the deviation component curve in the component model to obtain the shortest displacement distance between the pre-deviation point of the tunnel driving section and the deviation component curve in the component model; The intersection point of the pre-deviation point of the tunnel driving section and the deviation component curve in the component model is recorded as the pre-deviation component of the tunnel mark environmental feature position; The shortest displacement distance is recorded as and recorded as the validation deviation length; If the verification deviation length is within the preset verification deviation length interval, a verification consistency signal is obtained; Based on the verification consistent signal, the pre-deviation component is recorded as the deviation margin of the characteristic position of the tunnel punctuation environment; The effective distance traveled in the tunnel is summed with the deviation margin of the characteristic position of the tunnel punctuation environment to obtain the target positioning of the occluded area of ​​the vehicle's driving target path.

8. A vehicle posture acquisition system based on vehicle-mounted multi-sensor fusion, characterized in that: include: A map construction module, wherein the map construction module constructs an electronic map based on the environmental characteristic information of the vehicle's driving area to obtain the vehicle's driving target path; An open area analysis module, in an open area of ​​the vehicle's target driving path, is used to obtain the vehicle's driving position and driving position information multiple times to obtain the vehicle's deviation component in the regional driving section, and obtain the matching regional driving effective distance, regional driving effective time and regional driving effective speed based on the deviation component of the regional driving section; A model building module, wherein the model building module obtains a component model based on deviation components of multiple regional driving sections to match the effective distance of regional driving, the effective time of regional driving, and the effective speed of regional driving, and obtains a deviation component curve of the vehicle in an open area of ​​the driving target path in the component model; The occlusion area positioning module obtains environmental characteristic information of the occlusion area of ​​the vehicle's target path in the occlusion area, and obtains the deviation margin of the vehicle in the occlusion area based on the effective driving parameters of the vehicle in the occlusion area based on the environmental characteristic information, and corrects the position of the vehicle on the electronic map according to the deviation margin of the vehicle in the occlusion area to obtain the precise position information of the vehicle's target path.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the vehicle posture acquisition method based on vehicle-mounted multi-sensor fusion as described in any one of claims 1 to 7 is implemented.

Images