A method and apparatus for unstructured pre-planned road vehicle localization

Abstract

The present disclosure relates to a non-structured pre-determined road vehicle positioning method, device, electronic equipment and storage medium. The method comprises: generating a vehicle driving path based on the vehicle position; establishing a KD tree based on the path point set of the vehicle driving path, and traversing and searching in the KD tree according to the position information of the vehicle, matching the path point on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest area of the vehicle; and filtering the obstacle targets detected by the sensor of the vehicle. The present disclosure generates a drivable connected road of grid driving by topological and gridding processing of the continuous road vehicle driving path, and adopts gradient descent method and energy function based method to smooth the path, so as to ensure that the maximum curvature meets the minimum turning radius of the vehicle, and improve the operation efficiency and use experience of the vehicle unmanned driving system.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of unmanned driving, in particular, to a vehicle positioning method and device on an unstructured predetermined road, an electronic device and a computer readable storage medium. BACKGROUND

[0002] An unmanned mine truck is an important development direction of an intelligent mine area. An unmanned driving system sensing module of a mine area wide-body mine truck needs to sense and warn obstacles on a working path to provide reliable information for behaviors such as stopping when encountering obstacles and detouring obstacles. Compared with urban road conditions with high-precision maps, the working path of an unmanned mine truck in a mine area is relatively single and fixed, so the unmanned mine truck uses a recorded path to cooperate with a local obstacle detouring algorithm to realize cargo carrying.

[0003] Due to the lack of a high-precision map and insufficient GPS accuracy, the mine area scene changes significantly over time, and effective SLAM mapping cannot be performed, so the mine truck lacks necessary road information during unmanned driving. A complete unmanned driving sensing system needs to filter obstacles generated by the sensing system to prevent obstacles on non-driving paths from causing false alarms to the decision system, resulting in unnecessary braking, stopping or detouring, which affects the operation efficiency and use experience of the unmanned driving system.

[0004] Therefore, one or more methods are needed to solve the above problems.

[0005] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present disclosure is to provide a vehicle positioning method and device on an unstructured predetermined road, an electronic device and a computer readable storage medium, thereby at least partially overcoming one or more problems caused by the limitations and defects of the related art.

[0007] According to one aspect of the present disclosure, a vehicle positioning method on an unstructured predetermined road is provided, comprising:

[0008] The vehicle positioning device of the vehicle periodically acquires and stores vehicle path point coordinates, generates a path point coordinate set, and generates a vehicle driving path according to the path point coordinate set;

[0009] The vehicle driving path is classified and processed to generate a path point set of a straight path and a path point set of a curved path;

[0010] KD tree is established based on the path point set of the vehicle driving path, and the path point on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest region of the vehicle are matched through searching in the KD tree according to the position information of the vehicle.

[0011] According to the path point on the vehicle driving path and the path point set of the driving interest region of the vehicle, the obstacle target detected by the sensor of the vehicle is filtered based on the path point set of the straight path and the path point set of the curved path respectively.

[0012] In an exemplary embodiment of the present disclosure, the method further comprises:

[0013] The vehicle path point coordinates are periodically acquired and stored by the vehicle positioning device, the path point coordinate set is generated, and the vehicle driving path and the driving direction of the vehicle on the vehicle driving path are generated according to the path point coordinate set.

[0014] In an exemplary embodiment of the present disclosure, the method further comprises:

[0015] The vehicle driving path is classified based on the average north deviation angle change amount of the vehicle, and the path point set of the straight path and the path point set of the curved path are generated.

[0016] In an exemplary embodiment of the present disclosure, the method further comprises:

[0017] The vehicle driving path is classified based on the average north deviation angle change amount of the vehicle, and the path point set of the straight path and the path point set of the curved path are generated.

[0018]

[0019] The vehicle driving path is classified, and the path point set of the straight path and the path point set of the curved path are generated.

[0020] Wherein, Δtheta i is the average north deviation angle change amount, i is the vehicle position, and j is the road in front of the vehicle position i.

[0021] In an exemplary embodiment of the present disclosure, the method further comprises:

[0022] When the KD tree is established based on the path point set of the vehicle driving path, the world coordinates of the path point and the index number of the path point in the vehicle driving path are recorded in the created leaf node.

[0023] In an exemplary embodiment of the present disclosure, the method further comprises:

[0024] According to the position information of the vehicle, a path point on a vehicle travel path corresponding to the position information of the vehicle and a path point set of a travel interest region of the vehicle are searched in the KD tree, the path point set of the travel interest region of the vehicle is filtered according to an index number of the path point corresponding to the path point on the vehicle travel path in the vehicle travel path corresponding to the position information of the vehicle, and the path point of the travel interest region of the vehicle that has been traveled by the vehicle is removed from the path point set of the travel interest region of the vehicle.

[0025] In an example embodiment of the present disclosure, the method further comprises:

[0026] If the path point on the vehicle travel path belongs to the path point set of the straight path, according to the mountain data principle, a path point in the path point set of the travel interest region of the vehicle is searched based on a binary search algorithm, a path point coordinate with the smallest distance from the obstacle in the path point set of the travel interest region of the vehicle is obtained, and a straight path obstacle target filtering process is completed.

[0027] In an example embodiment of the present disclosure, the method further comprises:

[0028] If the path point on the vehicle travel path belongs to the path point set of the curved path, a path point in the path point set of the travel interest region of the vehicle is searched based on a complexity traversal algorithm, a path point coordinate with the smallest distance from the obstacle in the path point set of the travel interest region of the vehicle is obtained, and a curved path obstacle target filtering process is completed.

[0029] In an example embodiment of the present disclosure, the method further comprises:

[0030] If a distance between the path point coordinate with the smallest distance from the obstacle and the obstacle is less than a lateral safety distance of the vehicle, the position information of the obstacle is reported to an unmanned decision module of the vehicle.

[0031] In an aspect of the present disclosure, a vehicle positioning device on an unstructured predetermined road is provided, comprising:

[0032] A vehicle travel path generation module is configured to periodically acquire and store a path point coordinate of a vehicle based on a vehicle positioning device of the vehicle, generate a path point coordinate set, and generate a vehicle travel path based on the path point coordinate set.

[0033] A vehicle travel path classification module is configured to classify the vehicle travel path to generate a path point set of a straight path and a path point set of a curved path.

[0034] The optimal path matching module is configured to establish a KD tree based on the path point set of the vehicle driving path, and perform a search in the KD tree according to the position information of the vehicle to match the path point on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest region of the vehicle.

[0035] The obstacle target filtering module is configured to filter the obstacle targets detected by the sensors of the vehicle based on the path point set of the straight path and the path point set of the curved path, respectively, according to the path point on the vehicle driving path and the path point set of the driving interest region of the vehicle.

[0036] In one aspect of the present disclosure, an electronic device is provided, comprising:

[0037] a processor; and

[0038] a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the method according to any one of the above.

[0039] In one aspect of the present disclosure, a computer readable storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implements the method according to any one of the above.

[0040] In one of the exemplary embodiments of the present disclosure, a vehicle positioning method on an unstructured predetermined road is provided, wherein the method comprises: generating a vehicle driving path based on a vehicle position; establishing a KD tree based on a path point set of the vehicle driving path, and performing a search in the KD tree according to position information of the vehicle to match the path point on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest region of the vehicle; and filtering the obstacle targets detected by the sensors of the vehicle. The present disclosure generates drivable connected roads for grid driving by topological and gridding processing of continuous road vehicle driving paths, and uses gradient descent method and energy function based method to smooth the path to ensure that the maximum curvature meets the minimum turning radius of the vehicle, thereby improving the operation efficiency and use experience of the vehicle autonomous driving system.

[0041] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0042] The above and other features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0043] Figure 1 A flowchart of a vehicle positioning method on an unstructured predetermined road according to an exemplary embodiment of the present disclosure is shown.

[0044] Figure 2 A path point north angle average variation distribution histogram of a vehicle positioning method on an unstructured predetermined road is shown according to an example embodiment of the present disclosure;

[0045] Figures 3A-3B An obstacle shortest distance calculation schematic diagram of a vehicle positioning method on an unstructured predetermined road is shown according to an example embodiment of the present disclosure;

[0046] Figure 4 A schematic block diagram of a vehicle positioning device on an unstructured predetermined road is shown according to an example embodiment of the present disclosure;

[0047] Figure 5 A block diagram of an electronic device is schematically shown according to an example embodiment of the present disclosure; and

[0048] Figure 6 A schematic diagram of a computer readable storage medium is schematically shown according to an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the several views.

[0050] Moreover, described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the techniques described herein can be practiced without one or more of the specific details, or with other methods, components, materials, apparatus, steps, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail in order to avoid obscuring aspects of the disclosure.

[0051] The block diagrams in the drawings show functions and functionality as they can be implemented in software / firmware. In other words, the block diagrams depict the functional blocks of the apparatus and not the electronic or physical structure. When implemented in software / firmware, the functions and means disclosed by the various blocks in the flowcharts and block diagrams herein can be implemented by computer program instructions contained in or running on the electronic processor(s) of the electronic device, whether the processor is implemented as hardware, software, firmware, or any combination thereof.

[0052] In the present example embodiment, a vehicle positioning method on an unstructured predetermined road is first provided; reference is made toFigure 1 The vehicle positioning method on an unstructured predetermined road can include the following steps:

[0053] In step S110, the vehicle positioning device of the vehicle periodically acquires and stores vehicle path point coordinates, generates a path point coordinate set, and generates a vehicle travel path according to the path point coordinate set.

[0054] In step S120, the vehicle travel path is classified to generate a path point set of a straight path and a path point set of a curved path.

[0055] In step S130, a KD tree is established based on the path point set of the vehicle travel path, and a path point on the vehicle travel path corresponding to the position information of the vehicle and a path point set of a travel interest area of the vehicle are matched by traversing the KD tree according to the position information of the vehicle.

[0056] In step S140, the obstacle targets detected by the sensors of the vehicle are filtered based on the path point set of the straight path and the path point set of the curved path according to the path point on the vehicle travel path and the path point set of the travel interest area of the vehicle.

[0057] The vehicle positioning method on an unstructured predetermined road in an example embodiment of the present disclosure includes: generating a vehicle travel path based on the position of the vehicle; establishing a KD tree based on a path point set of the vehicle travel path, and matching a path point on the vehicle travel path corresponding to the position information of the vehicle and a path point set of a travel interest area of the vehicle by traversing the KD tree according to the position information of the vehicle; and filtering obstacle targets detected by sensors of the vehicle. The present disclosure generates drivable connected roads for grid travel by topological and gridding processing of continuous road vehicle travel paths, and uses gradient descent and energy function-based methods to smooth the paths to ensure that the maximum curvature meets the minimum turning radius of the vehicle, thereby improving the operation efficiency and user experience of the vehicle autonomous driving system.

[0058] The vehicle positioning method on an unstructured predetermined road in an example embodiment of the present disclosure includes: generating a vehicle travel path based on the position of the vehicle; establishing a KD tree based on a path point set of the vehicle travel path, and matching a path point on the vehicle travel path corresponding to the position information of the vehicle and a path point set of a travel interest area of the vehicle by traversing the KD tree according to the position information of the vehicle; and filtering obstacle targets detected by sensors of the vehicle. The present disclosure generates drivable connected roads for grid travel by topological and gridding processing of continuous road vehicle travel paths, and uses gradient descent and energy function-based methods to smooth the paths to ensure that the maximum curvature meets the minimum turning radius of the vehicle, thereby improving the operation efficiency and user experience of the vehicle autonomous driving system.

[0059] In step S110, the vehicle positioning device of the vehicle periodically acquires and stores vehicle path point coordinates, generates a path point coordinate set, and generates a vehicle travel path according to the path point coordinate set.

[0060] In the example embodiment, the method further includes:

[0061] The vehicle-based on-board positioning device periodically acquires and stores vehicle path point coordinates, generates a path point coordinate set, and generates a vehicle travel path and a travel direction of the vehicle on the vehicle travel path based on the path point coordinate set.

[0062] In the embodiment of the present example, the acquisition of predetermined fixed travel trajectory path points is implemented, and the unmanned mine vehicle periodically acquires the current position of the unmanned mine vehicle using the combined navigation module during travel along the path trajectory.

[0063] Each row of the acquired path point represents a path sampling point, and the three columns of floating-point numbers represent the coordinates x, y and the travel direction north angle theta of the current position of the unmanned mine vehicle in the world coordinate system.

[0064] In step S120, the vehicle travel path can be classified to generate a path point set of a straight path and a path point set of a curved path.

[0065] In the embodiment of the present example, the method further comprises:

[0066] Based on the average north angle change amount of the vehicle, the vehicle travel path is classified to generate a path point set of a straight path and a path point set of a curved path.

[0067] In the embodiment of the present example, the method further comprises:

[0068] Based on the average north angle change amount of the vehicle, the vehicle travel path is classified to generate a path point set of a straight path and a path point set of a curved path.

[0069]

[0070] The vehicle travel path is classified to generate a path point set of a straight path and a path point set of a curved path.

[0071] Wherein, Δtheta i is the average north angle change amount, i is the vehicle position, and j is the road in front of the vehicle position i.

[0072] In the embodiment of the present example, the path is preprocessed offline, and first, the type of the road in front is judged to divide the road into two types of straight road and curved road. The road in front is defined as a distance of 70 m in front of the predetermined trajectory of the unmanned mine truck. This distance is also called a safety distance, and is also the longitudinal distance of the region of interest.

[0073] The average north angle change amount of the road in front of the vehicle position i is calculated by formula (1) using the acquired original data to judge the curved region. Figure 2 The occurrence frequency of the average north angle change amount of the path point is counted.

[0074] From Figure 2It can be found that the frequency of occurrence of the average northward angle in the range of 5-10 has a significant decrease. For the purpose of conservative strategy, 5 is taken as the threshold to distinguish the path points, and the path points are divided into two categories, one of which is that the road ahead is a straight road, and the other of which is that the road ahead is a curved road.

[0075] In step S130, a KD tree can be established based on the path point set of the vehicle driving path, and path points on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest region of the vehicle are found by traversing the KD tree according to the position information of the vehicle.

[0076] In the embodiment of the present example, the method further comprises:

[0077] When the KD tree is established based on the path point set of the vehicle driving path, the world coordinates of the path point and the index number of the path point in the vehicle driving path are recorded in the created leaf node.

[0078] In the embodiment of the present example, the method further comprises:

[0079] According to the position information of the vehicle, the path points on the vehicle driving path corresponding to the position information of the vehicle and the path point set of the driving interest region of the vehicle are found by traversing the KD tree, and the path point set of the driving interest region of the vehicle is filtered by the index number of the path point in the vehicle driving path corresponding to the path point on the vehicle driving path corresponding to the position information of the vehicle, and the path points of the vehicle driving path in the path point set of the driving interest region of the vehicle are removed.

[0080] In the embodiment of the present example, before vehicle positioning and obstacle filtering, the path points are built into a KD-tree offline. The KD-tree is a tree data structure for storing instance points in k-dimensional space for fast retrieval. Using the structure of the KD-tree for storage can reduce the time complexity of path point traversal and retrieval from O(N) to O(logN). However, existing open source algorithm libraries (such as opencv, pcl, sklearn, etc.) usually only provide two APIs for nearest point query and neighborhood point query. However, our application scenario requires the determination of the vehicle's position in the path points and the acquisition of the single-side neighboring points (forward direction) in one query. If the open source algorithm library is used, two KD-tree traversals are required. The first KD-tree traversal determines the vehicle's position in the predetermined path trajectory according to the current position coordinates of the vehicle. The second KD-tree traversal finds the neighboring points within the range of the region of interest according to the found position. The present scheme uses the characteristics of the KD-tree data structure to implement a new traversal function, which can determine the vehicle's position in the path points and acquire the neighboring points in the forward direction in one tree traversal.

[0081] The specific implementation idea of the KD-tree traversal function of the present scheme is that, in the KD-tree building process, when creating a leaf node, record the world coordinates x and y of the path point, as well as the index number of the sampling path point in the path trajectory; during the KD-tree traversal process, record the nearest path point best_node and the region of interest path point set neighborhood two variables at the same time, obtain the region of interest path point set while completing the nearest point query, and filter the nodes according to the index number to eliminate the rear path points.

[0082] In step S140, the obstacle targets detected by the sensors of the vehicle can be filtered based on the path points on the vehicle driving path and the path point set of the driving interest region of the vehicle, respectively based on the path point set of the straight path and the path point set of the curved path.

[0083] In the embodiment of the present example, the method further comprises:

[0084] If the path point on the vehicle driving path belongs to the path point set of the straight path, the path point in the path point set of the driving interest region of the vehicle is found based on the bisection search algorithm according to the mountain data principle, to obtain the path point coordinates with the smallest distance from the obstacle in the path point set of the driving interest region of the vehicle, and complete the straight path obstacle target filtering process.

[0085] In the embodiment of the present example, the method further comprises:

[0086] If the path point on the vehicle driving path belongs to the path point set of the curve path, the path point in the path point set of the driving interest area of the vehicle is searched based on a complexity traversal algorithm to obtain path point coordinates with the minimum distance to the obstacle, and the curve path obstacle target filtering processing is completed.

[0087] In an embodiment of the present example, the method further comprises:

[0088] The distance between the path point coordinates with the minimum distance to the obstacle and the obstacle is calculated, and if the distance is less than the lateral safety distance of the vehicle, the obstacle position information is reported to the unmanned driving decision module of the vehicle.

[0089] In an embodiment of the present example, after the nearest path point and the front road path point set are obtained, the obstacle targets generated by the sensor can be filtered. The shortest distance of the obstacle to the front road is an important indicator during the driving of the vehicle. The filtering basis is that the shortest distance is less than the pre-set lateral safety distance, and the obstacle is removed, otherwise, the obstacle is retained and reported to the unmanned driving decision module. The filtering of the obstacle is processed in a corresponding manner according to the different road categories (straight road and curve), and the road categories are obtained by constructing the path in the first part of the present scheme.

[0090] As shown in Figure 3A For the obstacle beside the straight road, the distance of the obstacle to the front road path point satisfies the rule of first decreasing and then increasing, and the array meeting the rule is called a mountain array. According to the segmented and ordered characteristics of the mountain array, the present scheme uses the binary search algorithm to reduce the complexity of traversing the path points in the interest area from O(N) to O(logN), and finds the nearest position and distance to the obstacle.

[0091] As shown in Figure 3B For the obstacle beside the curve, the condition of the mountain array of the straight road is not met. Therefore, the log(N) complexity traversal algorithm is used to traverse the path point set in the interest area, and the nearest position and distance to the obstacle are found.

[0092] In an embodiment of the present example, a fitting method is used to process the broken path to obtain a continuous discretized path, and the driving path during the recording of the wide-body truck can be completely obtained. A topological and gridding method is used to process the continuous path to obtain a drivable connected road for grid driving. A gradient descent method and an energy function based method are used to smooth the path, so as to ensure that the maximum curvature meets the minimum turning radius of the vehicle and the change of the curvature value between points is smooth.

[0093] It is noted that although the various steps of the methods of the present disclosure are described in a particular order in the accompanying drawings, this is not required or implied that the steps must be performed in that particular order, or that all of the steps shown must be performed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into a single step, a single step can be broken into multiple steps, etc.

[0094] In addition, in the present example embodiment, a non-structured pre-planned road vehicle positioning device is also provided. Referring to Figure 4 As shown in the figure, the non-structured pre-planned road vehicle positioning device 400 can include a vehicle travel path generation module 410, a vehicle travel path classification module 420, an optimal path matching module 430, and an obstacle target filtering module 440. Among them:

[0095] The vehicle travel path generation module 410 is configured to periodically acquire and store vehicle path point coordinates based on the vehicle's on-board positioning device, generate a path point coordinate set, and generate a vehicle travel path based on the path point coordinate set;

[0096] The vehicle travel path classification module 420 is configured to classify the vehicle travel path to generate a path point set of a straight path and a path point set of a curved path;

[0097] The optimal path matching module 430 is configured to establish a KD tree based on the path point set of the vehicle travel path, and to traverse and search in the KD tree based on the vehicle's location information to match the path point on the vehicle travel path corresponding to the vehicle's location information and the path point set of the vehicle's travel interest area;

[0098] The obstacle target filtering module 440 is configured to filter the obstacle targets detected by the vehicle's sensors based on the path point on the vehicle travel path and the path point set of the vehicle's travel interest area, respectively based on the path point set of the straight path and the path point set of the curved path.

[0099] The specific details of each of the non-structured pre-planned road vehicle positioning device modules described above have been described in detail in the corresponding non-structured pre-planned road vehicle positioning method, and therefore will not be described here.

[0100] It should be noted that although several modules or units of the unstructured pre-defined road off-vehicle positioning device 400 are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into embodied by multiple modules or units.

[0101] Furthermore, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0102] Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method or a program product. Therefore, various aspects of the present disclosure can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" here.

[0103] The electronic device 500 according to this embodiment of the present disclosure will be described below with reference to Figure 5 Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0104] As shown in Figure 5 , the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 can include, but are not limited to, the at least one processing unit 510 described above, the at least one storage unit 520 described above, a bus 530 connecting different system components including the storage unit 520 and the processing unit 510, and a display unit 540.

[0105] The storage unit stores program code that can be executed by the processing unit 510, so that the processing unit 510 performs the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Method" section of the present specification. For example, the processing unit 510 can perform steps S110 to S140 as shown in Figure 1

[0106] The storage unit 520 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 5201 and / or a cache memory unit 5202, and can further include a read-only memory (ROM) 5203.

[0107] ​​The storage unit 520 can also include a number of program modules 5203 that are stored in the memory 5204, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or a combination of which can include implementation of a network environment.

[0108] The bus 550 can represent one or more of several types of bus structures, including a storage unit bus or bus controller, a peripheral bus, a graphics acceleration port, a processing unit bus, or a local bus using any of a variety of bus architectures.

[0109] The electronic device 500 can also communicate with one or more external devices 570 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with the electronic device 500; and / or one or more devices that enable the electronic device 500 to communicate with one or more other computing devices. Such communication can be facilitated by an Input / Output (I / O) interface 550. Still yet, the electronic device 500 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 560. As depicted, the network adapter 560 can communicate with the other components of the electronic device 500 through the bus 550. It should be appreciated that although the network adapter 560 is depicted as a single component, the network adapter 560 can comprise two or more components that operate together to facilitate communications with one or more networks. It should be appreciated that the electronic device 500 might communicate with an ad hoc network, a personal area network (PAN), a local area network (LAN), a metropolitan area network (MAN), and / or a wide area network (WAN) such as the Internet. As the herein described subject matter is implemented in software, the operations of the electronic device 500 might be spread across one or more software modules and can be distributed across one or more computing devices and memory and / or storage devices. As one example, the electronic device 500 can include a plurality of different processing units 510 and these processing units 510 can be physically located within the same device, or the different processing units 510 can be physically located within different devices and can be communicatively coupled via a network-based communication mechanism, such as the Internet. It will be appreciated that the herein described subject matter can be implemented on processors of both a single location and a distributed location.

[0110] Those skilled in the art will readily understand that the example embodiments described herein can be implemented by software and / or by hardware coupled with software, as described above. Thus, the techniques that are embodied in accordance with the embodiments of the present disclosure can be embodied in a software product that can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0111] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section above.

[0112] refer to Figure 6 As shown, a program product 600 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0113] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0114] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0115] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0116] The program code may be implemented in any of various ways, including procedure-based, narrative-based, object-based, and / or architectural-based versions. In procedure-based implementations, the program code is implemented in a series of isolated procedures, which rely primarily on extrinsic (or global) variables to communicate with one another. In narrative-based implementations, the program code is implemented at various levels by an interpreter or virtual machine. In object-based versions, the program code is implemented as a series of objects, which interact to perform the functionality of the present application. In architectural-based versions, the program code is implemented based on a component model, which organizes functionality into components that are interconnected to achieve the functionality of the present application.

[0117] Furthermore, the above-described diagrams are only schematic and are non-limiting. As such, the processes described above, and shown in the diagrams, are not intended to be limiting. For example, it will be readily apparent to those skilled in the art that the orders of the processes described above can be modified in various ways. Furthermore, the processes can be implemented by hardware that is functionally coupled to the modules in the illustrated software, including the modules that are not explicitly shown or discussed. Additionally, it will be readily apparent that the processes can be performed in parallel, or in an order different than that described above.

[0118] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features of the disclosure disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0119] It is to be understood that the disclosure is not limited to the precise construction described and shown in the drawings and that various modifications and changes can be made by those skilled in the art without departing from the scope of the disclosure. The scope of the disclosure is limited only by the claims appended hereto.

Claims

1. A method for vehicle positioning under unstructured predetermined roads, characterized in that, The method includes: The vehicle-mounted positioning device periodically acquires and stores the coordinates of vehicle path points, generates a set of path point coordinates, and generates the vehicle driving path based on the set of path point coordinates. The vehicle's driving path is classified to generate a set of path points for straight paths and a set of path points for curved paths. A KD tree is built based on the set of path points of the vehicle's driving path. The vehicle's location information is then traversed in the KD tree to search and match the path points on the vehicle's driving path corresponding to the vehicle's location information and the set of path points in the vehicle's driving interest region. Based on the path points along the vehicle's driving path and the set of path points in the vehicle's region of interest, the obstacle targets detected by the vehicle's sensors are filtered based on the set of path points for straight paths and the set of path points for curved paths, respectively. The method further includes: Based on the average change in northward angle of the vehicle, the vehicle's driving path is classified to generate a set of path points for straight paths and a set of path points for curved paths. Based on the average northward angle change of the vehicle, according to Δtheta i =∑J=[the road ahead of i}|theta i -theta j | / ∑ j＝{i前方的道路} 1 The vehicle's driving path is classified to generate a set of path points for straight paths and a set of path points for curved paths. Wherein, Δtheta i Let i be the average change in northward angle, i be the vehicle position, and j be the road ahead of vehicle position i. If the path points on the vehicle's driving path belong to the path point set of the straight path, then based on the mountain data principle and the binary search algorithm, the path points in the path point set of the vehicle's driving interest region are searched to obtain the coordinates of the path point with the smallest lateral distance to the obstacle in the path point set of the vehicle's driving interest region, thus completing the straight path obstacle target filtering process. If the path points on the vehicle's driving path belong to the path point set of the curved path, then based on the complexity traversal algorithm, the path points in the path point set of the vehicle's driving interest region are searched to obtain the coordinates of the path point with the smallest lateral distance from the obstacle in the path point set of the vehicle's driving interest region, thus completing the obstacle target filtering process for the curved path.

2. The method as described in claim 1, characterized in that, The method further includes: The vehicle-mounted positioning device periodically acquires and stores the coordinates of vehicle path points, generates a set of path point coordinates, and generates the vehicle driving path and the driving direction of the vehicle on the driving path based on the set of path point coordinates.

3. The method as described in claim 1, characterized in that, The method further includes: When constructing a KD tree based on the set of path points of a vehicle's travel path, the world coordinates of the path points and the index number of the path points in the vehicle's travel path are recorded in the created leaf nodes.

4. The method as described in claim 1, characterized in that, The method further includes: Based on the vehicle's location information, the KD tree is traversed to find the path points on the vehicle's driving path corresponding to the vehicle's location information and the set of path points in the vehicle's region of interest. By using the index number of the path point on the vehicle's driving path corresponding to the vehicle's location information in the vehicle's driving path, the set of path points in the vehicle's region of interest is filtered to remove the path points in the set of path points in the vehicle's region of interest that are on the path the vehicle has already traveled.

5. The method as described in claim 1, characterized in that, The method further includes: Calculate the distance between the path point coordinates that has the smallest lateral distance to the obstacle and the obstacle. If the distance is less than the vehicle's lateral safety distance, then report the obstacle's location information to the vehicle's autonomous driving decision module.

6. A vehicle positioning device under unstructured predetermined roads, characterized in that, The device includes: The vehicle driving path generation module is used to periodically acquire and store the coordinates of vehicle path points based on the vehicle's on-board positioning device, generate a set of path point coordinates, and generate the vehicle driving path based on the set of path point coordinates. The vehicle driving path classification module is used to classify the vehicle driving path and generate a set of path points for straight paths and a set of path points for curved paths. The optimal path matching module is used to build a KD tree based on the set of path points of the vehicle's driving path, and to traverse and search in the KD tree according to the vehicle's location information to match the path points on the vehicle's driving path corresponding to the vehicle's location information and the set of path points of the vehicle's driving interest region. The obstacle target filtering module is used to filter obstacle targets detected by the vehicle's sensors based on the path points on the vehicle's driving path and the path point set of the vehicle's driving interest region, respectively based on the path point set of the straight path and the path point set of the curved path; and to classify the vehicle's driving path based on the vehicle's average north angle change, generating the path point set of the straight path and the path point set of the curved path. Based on the average northward angle change of the vehicle, according to Δtheta i =∑ j＝{i前方的道路} |theta i -theta j | / ∑ j-{i前方的道路} 1 The vehicle's driving path is classified to generate a set of path points for straight paths and a set of path points for curved paths. Wherein, Δtheta i Let i be the average change in northward angle, i be the vehicle position, and j be the road ahead of vehicle position i. If the path points on the vehicle's driving path belong to the path point set of the straight path, then based on the mountain data principle and the binary search algorithm, the path points in the path point set of the vehicle's driving interest region are searched to obtain the coordinates of the path point with the smallest lateral distance to the obstacle in the path point set of the vehicle's driving interest region, thus completing the straight path obstacle target filtering process. If the path points on the vehicle's driving path belong to the path point set of the curved path, then based on the complexity traversal algorithm, the path points in the path point set of the vehicle's driving interest region are searched to obtain the coordinates of the path point with the smallest lateral distance from the obstacle in the path point set of the vehicle's driving interest region, thus completing the obstacle target filtering process for the curved path.

7. An electronic device, characterized in that, include Processor; and A memory storing computer-readable instructions that, when executed by the processor, implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images