WO2021184320A1

WO2021184320A1 - Vehicle positioning method and device

Info

Publication number: WO2021184320A1
Application number: PCT/CN2020/080282
Authority: WO
Inventors: 刘建琴; 王兴冰; 陈军
Original assignee: 华为技术有限公司
Priority date: 2020-03-19
Filing date: 2020-03-19
Publication date: 2021-09-23
Also published as: CN112771352A; CN112771352B

Abstract

A vehicle positioning method and device. The method comprises: determining a first location of a vehicle at a first time (201); determining a first operational design domain (ODD) for the vehicle at a second time (202); performing, according to the first ODD, sampling around the first location to obtain multiple particles for particle filtering, the number or distribution of the multiple particles corresponding to the first ODD (203); and determining a second location of the vehicle at the second time according to the multiple particles (204). In the invention, appropriate classification of ODDs and adaptive configuration of the number or distribution of sampled particles for positioning computation can enhance the positioning efficiency of particle filtering while saving computing resources, thereby performing quick positioning of an automatic driving vehicle.

Description

Vehicle positioning method and device

Technical field

This application relates to the technical field of Internet of Vehicles, and in particular to a vehicle positioning method and device.

Background technique

In an autonomous driving system, the vehicle's own positioning is a very important link. Current positioning methods usually use feature matching methods, particle filter algorithms, etc. to complete vehicle positioning based on observation data collected by different sensors on the vehicle. The sensors on the vehicle may include, for example, a global navigation satellite system (GNSS), an inertial measurement unit (IMU), a laser detection and measurement (light detection and ranging, LiDAR), or a camera.

At present, the particle filter algorithm is a process of approximating the probability density function by looking for a set of random samples propagating in the state space, replacing the integral operation with the sample mean, and then obtaining the minimum variance estimation process of the system state. There are multiple design application domains (operational design domains, ODD) for autonomous driving scenarios. In the prior art, when particle filtering is applied for vehicle positioning, it does not consider different ODDs. Different vehicle sensors have different observation noises and state transition process noises. The situation not only wastes calculation space, but also leads to the problem that the positioning performance of the vehicle cannot be guaranteed and the positioning results vary greatly.

Summary of the invention

The present application provides a vehicle positioning method and device to solve the problem that the positioning performance of the vehicle cannot be guaranteed in the prior art.

In the first aspect, an embodiment of the present application provides a vehicle positioning method, which may be executed by the positioning module of the vehicle itself, or may also be executed by the positioning server on the network side of the automatic driving system. Alternatively, the method can also be executed by other devices with positioning functions. In this method, the first position of the vehicle at the first time can be determined first, where the first position can be obtained by receiving a message, or obtained by observation, for example, the positioning module in the vehicle, such as GPS module, The approximate location of the vehicle, or the approximate location of the vehicle obtained by the positioning server based on the cell positioning method; and then determine the first design applicable domain ODD of the vehicle at the second time, and the first ODD may be determined according to multiple methods For example, it may be determined according to collected observation data, user input, the first position, or received indication information of other devices. Wherein, the first ODD is used to indicate the operating conditions or environmental conditions of the vehicle. Furthermore, a plurality of particles used for particle filtering are sampled around the first position according to the first ODD. Wherein, the number and/or distribution of the plurality of particles corresponds to the first ODD; finally, the second position of the vehicle at the second time is determined according to the plurality of particles obtained by sampling. It should be understood that the second time is after the first time. The embodiment of the application adaptively sets the number or distribution of sampled particles for positioning calculation according to the ODD, so that the collected particles can be more densely distributed near the real position of the vehicle, especially in the iterative process of particle filtering. More accurately complete the positioning of the vehicle itself, and effectively improve the accuracy and efficiency of the positioning of autonomous vehicles.

Based on this solution, when a particle filter algorithm is used to locate a vehicle, the first ODD of the vehicle can be determined, and multiple particles used for particle filtering can be sampled around the first position according to the first ODD. The number and/or distribution of the particles can correspond to the first ODD, so that the multiple particles sampled can meet the operating conditions of the vehicle, so that when the vehicle is positioned based on the multiple particles obtained by the sampling, the positioning performance of the vehicle can be better improved .

In a possible implementation manner, after determining the first ODD of the vehicle at the second time, the automatic driving system may also determine the target level of the first ODD. The automatic driving system may collect a plurality of particles for particle filtering around the first position according to the target level. Specifically, the number and/or distribution of the plurality of particles corresponds to the target level. In an example, the number of the plurality of particles may be positively correlated with the target level, and the higher the level of the first ODD, the greater the number of particles. The positive correlation can be realized by an exponential function, a proportional function or a look-up table mapping with respect to the target level.

Based on this solution, the number and/or distribution of the plurality of particles sampled can correspond to the target level of the first ODD, and a plurality of particles that are more in line with the operating conditions of the vehicle can be determined according to the target level of the first ODD, or the distribution density or The distribution area is more in line with the multiple particles of the operating conditions of the vehicle, so as to improve the positioning performance of the vehicle and make the positioning result more accurate.

In a possible implementation manner, the number or distribution of the plurality of particles may also correspond to the sensor type of the vehicle.

Based on this solution, the number or distribution of the multiple particles sampled can also correspond to the target level of the first ODD and the sensor type of the vehicle. In this way, the multiple particles sampled can be more in line with the operating conditions of the vehicle, and the positioning results can be improved. precise.

In a possible implementation manner, after the second position of the vehicle at the second time is obtained, the second position may also be determined as the new first position, and the vehicle may be iteratively determined according to the above method in the embodiment of the present application. Positioning. When positioning the vehicle iteratively, if it is determined that the vehicle is switched from the first ODD to the second ODD, a plurality of particles for particle filtering can be sampled around the new first position according to the second ODD . Wherein, the number and/or distribution of the plurality of particles collected again corresponds to the second ODD; finally, the number and/or distribution of the plurality of particles collected again corresponds to the second ODD; and finally, the vehicle is re-determined at the third time after the first time according to the plurality of particles obtained by sampling again. The second position.

Based on this solution, when the ODD of the vehicle changes, the multiple particles used for particle filtering can be resampled around the first position of the vehicle according to the transformed ODD, and the particles used for particle filtering can be reset according to changes in the operating conditions of the vehicle. The number or distribution of multiple particles in the particle filter can make the positioning result more accurate following changes in the environment and operating conditions of the vehicle.

In a possible implementation manner, after the second position of the vehicle at the second time is obtained, the second position may also be determined as the new first position, and the vehicle may be continuously inspected according to the above method in the embodiment of the present application. Positioning. When continuing to locate the vehicle, if the number of effective particles in the collected particles is less than the threshold and the first ODD does not switch, the operation of deleting some invalid particles and copying some effective particles may be performed first, After the particle deletion and copy operations are performed, the third position of the vehicle at a third time after the first time is determined based on the plurality of particles obtained after the operation. In terms of how to determine whether a particle is a valid particle, for example, among the collected particles, each particle is configured with a corresponding weight value. The weight value of different particles can be the same or different. The weight value can be greater than a certain value. Particles with a threshold value are regarded as effective particles, or particles with a weight value less than a certain threshold are regarded as invalid particles.

Based on this solution, when the ODD of the vehicle has not changed and the number of effective particles is less than the threshold, some or all of the effective particles can be used to replicate the particles, so that the number of replicated particles meets the requirements of the vehicle’s ODD, so that the vehicle The positioning is more accurate.

In the second aspect, an embodiment of the present application also provides a vehicle positioning device, which can be used to perform the operations in the foregoing first aspect and any possible implementation manner of the first aspect. For example, the positioning device may include a module or unit for performing each operation in the above-mentioned first aspect or any possible implementation of the first aspect. For example, including processing unit and acquisition unit.

In a third aspect, an embodiment of the present application provides a vehicle positioning device, including a processor, and optionally a memory; wherein the memory stores a computer program, and the processor is used to call and run the computer program from the memory, so that the vehicle The positioning device executes the foregoing first aspect or any method in any possible implementation manner of the first aspect.

In a fourth aspect, the embodiments of the present application provide a computer program product. The computer program product includes: computer program code. When the computer program code is executed by the communication unit, processing unit or transceiver, or processor of the vehicle positioning device, the vehicle The positioning device executes the foregoing first aspect or any method in any possible implementation manner of the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, and the computer-readable storage medium stores a program, and the program causes the vehicle positioning device to execute any of the foregoing first aspect or any of the possible implementation manners of the first aspect. One method.

Among them, the technical effects that can be achieved by any one of the above-mentioned second to fifth aspects or any one of the designs can be referred to the technical effects that can be achieved by any one of the above-mentioned designs for the first aspect or the first aspect, here Do not repeat it again.

Description of the drawings

Figure 1 is a schematic diagram of a typical application scenario of an embodiment of the application;

Fig. 2 is an exemplary flowchart of a vehicle positioning method provided by an embodiment of the application;

FIG. 3 is a schematic diagram of particle distribution under different ODDs in an embodiment of the application;

FIG. 4 is a schematic diagram of particle sampling under different ODDs in an embodiment of the application;

Fig. 5 is a schematic diagram of effective particle distribution in an embodiment of the application;

FIG. 6 is a schematic diagram of the effective particle replication operation in an embodiment of the application;

FIG. 7 is a structural block diagram of a vehicle positioning device provided by an embodiment of the application;

FIG. 8 is a structural block diagram of another vehicle positioning device provided by an embodiment of the application.

Detailed ways

In order to understand the technical solutions provided by the embodiments of the present application, firstly, the relevant terms in the embodiments of the present application are explained:

1) Operational design domain (ODD) refers to the conditions or scope of application for which the autonomous driving system is designed to function, including but not limited to vehicle speed, geographic location, traffic conditions, road type, weather, time, environment, and country Or local traffic laws, etc. It is also commonly referred to as operational design domain, design operational domain, and so on.

2) Particles refer to random samples propagating in the state space, which can be used as reference points for determining the position of the vehicle in the automatic driving system. A large number of particles can simulate the motion state and trajectory of the vehicle for particle filtering.

The technical solution of the present application will be described below in conjunction with the drawings.

The technical solutions provided in the embodiments of the present application can be applied to various automatic driving systems, such as automatic driving (AD) systems, highly automated driving (HAD) systems, and advanced driver assistance systems, ADAS), and future autonomous driving systems.

This application will present various aspects, embodiments, or features around a system that may include multiple devices, components, modules, and the like. It should be understood and understood that each system may include additional devices, components, modules, etc., and/or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. In addition, a combination of these schemes can also be used.

In addition, in the embodiments of the present application, the word "exemplary" is used to mean serving as an example, illustration, or illustration. Any embodiment or design solution described as an "example" in this application should not be construed as being more preferable or advantageous than other embodiments or design solutions. Rather, the term example is used to present the concept in a concrete way.

The network architecture and business scenarios described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. Those of ordinary skill in the art will know that with the network With the evolution of architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems.

In the embodiments of the present application, information, signal, message, and channel can sometimes be used together. It should be noted that the meanings to be expressed are the same when the differences are not emphasized. "的 (of)", "corresponding (relevant)" and "corresponding (corresponding)" can sometimes be used together. It should be pointed out that the meanings to be expressed are the same when the difference is not emphasized.

To facilitate the understanding of the embodiments of the present application, first, the communication system shown in FIG. 1 is taken as an example to describe the communication system of the embodiments of the present application in detail. Fig. 1 shows a schematic diagram of a communication system suitable for a vehicle positioning method according to an embodiment of the present application. As shown in FIG. 1, the communication system 100 includes a network device 101, a positioning server 103 on the network side, a vehicle 102 and a control management device 104 on the vehicle 102. The network device 101 may be configured with multiple antennas, and the vehicle 102 may also be configured with multiple antennas. Optionally, the communication system may further include a network device 105, and the network device 105 may also be configured with multiple antennas.

It should be understood that the network device 101 or the network device 105 may also include multiple components related to signal transmission and reception (for example, a processor, a modulator, a multiplexer, a demodulator, or a demultiplexer, etc.).

The technical solutions provided by the embodiments of the present application may be executed by a positioning module with a positioning function in the control management device 104 or may also be executed by the positioning server 103 on the network side in FIG. 1.

Among them, the network device may be a device with a wireless transceiver function or a chip that can be installed in the device. The device includes but is not limited to: evolved Node B (eNB), radio network controller (RNC) ), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (for example, home evolved NodeB, or home Node B, HNB), Baseband unit (BBU), access point (AP), wireless relay node, wireless backhaul node, and transmission point (transmission and reception point, TRP) in wireless fidelity (WIFI) systems Or transmission point, TP), etc., and can also be 5G, such as NR, gNB in the system, or transmission point (TRP or TP), one or a group (including multiple antenna panels) antennas of the base station in the 5G system The panel, or, may also be a network node constituting a gNB or transmission point, such as a baseband unit (BBU), or a distributed unit (DU, distributed unit), etc.

If the network device is a base station, the different base stations in the embodiments of the present application may be base stations with different identities, or base stations with the same identity and deployed in different geographic locations. Before the base station is deployed, the base station does not know whether it will involve the scenario applied in the embodiment of the present application. Therefore, the base station or the baseband chip should support the method provided in the embodiment of the present application before deployment. It is understandable that the aforementioned base stations with different identities may be base station identities, cell identities or other identities.

In some deployments, the gNB may include a centralized unit (CU) and a DU. The gNB may also include a radio unit (RU). CU implements some functions of gNB, DU implements some functions of gNB, for example, CU implements radio resource control (radio resource control, RRC), packet data convergence protocol (packet data convergence protocol, PDCP) layer functions, DU implements wireless link Channel control (radio link control, RLC), media access control (media access control, MAC) and physical (physical, PHY) layer functions. Since the information of the RRC layer will eventually be transformed into the information of the PHY layer, or transformed from the information of the PHY layer, under this architecture, high-level signaling, such as RRC layer signaling or PDCP layer signaling, can also be It is considered to be sent by DU, or sent by DU+CU. It can be understood that the network device may be a CU node, or a DU node, or a device including a CU node and a DU node. In addition, the CU can be divided into network equipment in the access network RAN, and the CU can also be divided into network equipment in the core network CN, which is not limited here.

In the communication system 100, both the network device 101 and the network device 105 can communicate with multiple vehicles (for example, the vehicle 102 shown in the figure). It should be understood that both the network device 101 and the network device 105 can communicate with one or more vehicles similar to the vehicle 102, and the vehicle 102 can communicate with different network devices to realize the function of automatic driving (also called unmanned driving). However, it should be understood that the vehicle communicating with the network device 101 and the vehicle communicating with the network device 105 may be the same or different. The vehicle 102 shown in FIG. 1 can communicate with the network device 101 and the network device 105 at the same time, but this only shows one possible scenario. In some scenarios, the vehicle 102 may only communicate with the network device 101 or the network device 105. Communication, this application does not limit this.

It should be understood that FIG. 1 is only a simplified schematic diagram of an example for ease of understanding, and the communication system may also include other network devices or other vehicles, which are not shown in FIG. 1.

In the system architecture shown in FIG. 1, when the vehicle 102 is traveling, it needs to collect detailed information such as road information, obstacle information, and the position of the vehicle 102 on the lane in which the vehicle 102 is located, so as to be based on the collected information. To control the traveling direction and speed of the vehicle 102. Compared with ordinary vehicles, the accuracy required for recognition in the field of autonomous driving is not only "what road the vehicle 102 is driving on", but "in which lane the vehicle 102 is driving". Usually the width of a lane is only 2.7m-4.6m, and the allowable error is extremely small. Therefore, the realization of automatic driving is inseparable from the demand for high-precision positioning of the vehicle.

Based on FIG. 1 or other system architectures similar to the system architecture shown in FIG. 1, FIG. 2 is an exemplary flowchart of a vehicle positioning method provided by an embodiment of the application, which may include the following processes:

Step 201: Determine the first position of the vehicle at the first time.

In a possible implementation manner, the first position of the vehicle can be determined by the control and management equipment installed in the vehicle; for example, the control and management equipment of the vehicle can control the global installed in the communication equipment installed in the vehicle itself or in the communication equipment carried in the vehicle. Positioning system (global positioning system, GPS), Beidou satellite navigation system (beidou navigation satellite system, BDS) and other components with positioning function, perform positioning operations on the vehicle's position at the first time, and obtain the vehicle's first position at the first time. Location. Alternatively, the first position may also be an approximate position obtained by the control and management device of the vehicle by controlling a sensor installed in the vehicle itself, and the sensor may be, for example, a camera, a global navigation satellite system (GNSS) or other sensors. During implementation, the control management device can calculate the first position through the data obtained by the vehicle's sensor observations. For example, the GNSS obtains the distance information between the vehicle and the satellite at the first time, reports the distance information to the control and management device, and the control and management device calculates the first position of the vehicle at the first time based on the distance information.

In another possible implementation manner, the positioning server on the network side of the automatic driving system may also determine the first position of the vehicle. The positioning server may confirm the first position of the vehicle at the first time based on the information of the cell where the vehicle is located at the first time.

It should be noted that the first position here may be the positioning result obtained from the previous calculation based on the iterative calculation of this solution. Based on iterative calculations, the positioning results can be continuously updated according to changes in the environment and status. The first position here may also be the approximate initial position of the vehicle. For example, it may be an approximate fuzzy position of the vehicle. For example, the first position can indicate which area or road the vehicle is in at the first time, but cannot give specific information about the vehicle. Information such as latitude and longitude, that is to say, the first position is position information with relatively low accuracy, which does not meet the requirements for vehicle positioning in the current automatic driving system. Therefore, in order to require the high-precision positioning of the vehicle by the automatic driving system, it is necessary to continue to determine the high-precision position of the vehicle based on the first position. In this application, the position of the vehicle with higher accuracy than the first position is referred to as the second position.

In the following description of this application, based on the preliminary rough determination of the vehicle’s first position at the first time, combined with the vehicle’s current ODD information, multiple reference particles for determining the second position information are determined around the first position. The first position and the determined multiple reference particles are used to determine the second position with higher accuracy through a particle filter algorithm. Since more information is collected and used when the second position is calculated, the particle filter algorithm is used to iterate, and the accuracy of the positioning result is also higher.

Step 202: Determine the first design applicable domain ODD of the vehicle at the second time.

The first ODD of the vehicle can be determined based on the observation data of the sensors of the vehicle. The operating conditions of the vehicle may include road type, weather, time, traffic characteristics, vehicle speed, local traffic laws, etc. The traffic characteristics here can be traffic participants, such as pedestrians, bicycles, traffic lights, etc.

In the embodiment of the present application, the correspondence relationship between different ODDs and different observation data may be stored in advance. In this way, after the observation data of the vehicle at the second time point is collected through the vehicle's sensors, etc., the first ODD corresponding to the vehicle at the second time can be determined according to the corresponding relationship.

Step 203: According to the first ODD, sample a plurality of particles used for particle filtering around the first position, and the number or distribution of the plurality of particles corresponds to the first ODD.

In an embodiment, the number of multiple particles may be determined according to the first ODD, and sampling is performed around the first location according to a predetermined distribution of multiple particles. Alternatively, the distribution of multiple particles may be determined according to the first ODD, and sampling is performed around the first position according to a predetermined number of multiple particles. Alternatively, the number and distribution of multiple particles may be determined according to the first ODD, and sampling may be performed around the first position, which is not specifically limited in the embodiment of the present application.

The following respectively introduces the implementation manners for determining the number or distribution of multiple particles according to the first ODD.

1. Determine the number of multiple particles according to the first ODD.

In the embodiment of the present application, the number of multiple particles may be related to the characteristics of the first ODD. Below, without loss of generality, a simple description will be given by taking the type of road where the vehicle is located as an example.

When a vehicle is traveling on a highway, the first ODD is used to characterize the highway. At this time, the characteristics of the first ODD may include fast speed, sparse obstacles, simple traffic characteristics, and so on. Therefore, the noise covariance and the observation noise covariance of the positioning process are small, and then according to the first ODD, a smaller number of particles can be collected around the first position.

When a vehicle is driving on a road in a city block, the first ODD is used to characterize a road in a city block. At this time, the characteristics of the first ODD include low vehicle speed, dense obstacles, and complex traffic characteristics. Therefore, the noise covariance and the observation noise covariance of the positioning process are relatively large, and at this time, according to the first ODD, a larger number of particles can be collected around the first position.

In a possible implementation, the corresponding relationship between different ODDs and the number of particles to be collected can be established in advance, so that when the current ODD of the vehicle is determined, the corresponding relationship can be used to determine the need to collect around the first position of the vehicle. How many particles.

In another possible implementation manner, it is also possible to determine how many particles need to be collected around the first position of the vehicle according to the ODD where the vehicle is currently located according to the functional relationship between the ODD and the number of particles to be collected.

In an example, each ODD can be divided into multiple levels, that is, one ODD contains multiple levels. The multiple levels contained in an ODD correspond to the number of multiple particles that need to be collected. For example, the number of multiple particles that need to be collected may be positively correlated with a level under the corresponding ODD, that is, the higher a level under the ODD, the greater the number of multiple particles that need to be collected. For example, the positive correlation can be embodied in an exponential way or a positive proportional way.

Specifically, a level under the ODD and the corresponding number of particles to be collected may conform to the following formula (1) or formula (2).

N=f*a^i Formula (1)

Among them, N is the number of multiple particles to be collected, a is a preset integer greater than 1, f is a preset positive integer, and i is a level under ODD.

N=f*i Formula (2)

Alternatively, the number of multiple particles that need to be collected may also be negatively correlated with a level under the corresponding ODD, that is, the higher a level under the ODD, the smaller the number of multiple particles that need to be collected. It should be understood that when the number of multiple particles that need to be collected is positively correlated with the next level of ODD, the division of multiple levels of ODD is negatively related to the number of multiple particles that need to be collected and the next level of OD. The division of each level can be different.

Based on this solution, it can be determined that the vehicle belongs to the specific target level under the first ODD according to the current environment and other information of the vehicle, and then according to the specific target level under the first ODD and the above method, it is determined that the vehicle needs to be in the first ODD. The number of multiple particles collected around a location can make the number of sampled particles more in line with the operating conditions of the vehicle, and can also improve the positioning performance of the vehicle.

In yet another possible implementation manner, the number of multiple particles that need to be collected may also correspond to the sensor type of the vehicle and the specific target level under which the vehicle belongs to the first ODD. In the embodiment of the present application, multiple candidate ranges of the number of particles may be configured for the sensor type of the vehicle and the multiple levels included in the first ODD to which the vehicle belongs. When sampling, you can randomly select a number in the candidate range. Hereinafter, taking the first ODD as an expressway and the first ODD as an example of an urban block road respectively, the above method of determining the number of multiple particles will be described.

Combining the determination method of the above formula (1) and formula (2), and the determination method of the candidate range, the relationship table shown in Table 1 can be given. For example, when the first ODD is used to characterize the expressway, the first ODD It can include levels 1-3, and the number of multiple particles as shown in Table 1 can be determined by the above-mentioned multiple methods for each level.

Combining the determination methods of the above formula (1) and formula (2), as well as the determination of the candidate range, the relationship table shown in Table 2 can be given. For example, when the first ODD is used to characterize roads in urban blocks, the first The ODD can include levels 1-3, and the number of multiple particles as shown in Table 2 can be determined by the above-mentioned multiple methods for each level.

Based on the above method, the number of particles used for particle filtering can be determined according to the first ODD, so that when the first position is iterated through the particle filter algorithm, the information used is closer to the operating conditions of the vehicle, which can improve the positioning of the vehicle. The performance can make the positioning result of the vehicle (the second position in the embodiment of the present application) more accurate.

2. Determine the distribution of multiple particles according to the first ODD.

In the embodiment of the present application, the distribution of the plurality of particles may be related to the characteristics of the first ODD. Below, without loss of generality, a simple description will be given by taking the type of road where the vehicle is located as an example.

When a vehicle is traveling on a highway, the first ODD is used to characterize the highway. At this time, the characteristics of the first ODD may include fast speed, sparse obstacles, simple traffic characteristics, and so on. Therefore, the noise covariance and the observation noise covariance of the positioning process are small, and at this time, the multiple particles collected around the first position may present an aggregated distribution mode.

When a vehicle is driving on a road in a city block, the first ODD is used to characterize a road in a city block. At this time, the characteristics of the first ODD include low vehicle speed, dense obstacles, and complex traffic characteristics. Therefore, the noise covariance and the observation noise covariance of the positioning process are relatively large, and the multiple particles collected around the first position may present a discrete distribution.

As shown in Figure 3, (1) is a schematic diagram of the distribution of multiple particles collected around the first position of the vehicle when the first ODD is used to characterize expressways, and (2) is when the first ODD is used to characterize roads in urban blocks A schematic diagram of the distribution of multiple particles collected around a location of the vehicle.

Hereinafter, the method for determining the distribution of multiple particles in the embodiment of the present application will be specifically introduced. Wherein, the distribution of the plurality of particles may be determined according to the distribution variance of the plurality of particles or the particle interval of the plurality of particles.

In an example, in the embodiment of the present application, each ODD can be divided into multiple levels, that is, one ODD includes multiple levels. The multiple levels contained in an ODD correspond to the distribution variance of the particles to be collected. For example, the distribution variance of the particles to be collected may be positively correlated with a level under the corresponding ODD, that is to say, the higher the level under the ODD, the larger the distribution variance of the particles that need to be collected. Specifically, the distribution variance can conform to the following formula (3):

in,

Is the variance of the distribution of multiple particles.

In another example, the multiple levels contained in one ODD correspond to the particle interval of the particles to be collected. In the embodiment of the present application, the corresponding particle interval can be determined according to the current target level of the first ODD of the vehicle.

In the embodiment of the present application, after the number and particle interval of the plurality of particles are determined, uniform sampling is performed around the first position of the vehicle according to the number and the particle interval. Alternatively, centralized sampling may be performed at the first position of the vehicle according to the number and the particle interval. In centralized sampling, sampling may be performed in a specific area of the first position. The centralized sampling can be uniform sampling, for example, the interval between particles is the same.

As shown in FIG. 4, (1) and (2) are schematic diagrams of uniform sampling around the first position of the vehicle, and (3) are schematic diagrams of centralized sampling at the first position of the vehicle.

Based on this solution, the distribution of multiple particles can be determined according to the target level of the first ODD, so that the distribution of the multiple particles sampled can meet the operating conditions of the vehicle, and the positioning performance of the vehicle can also be improved.

Step 204: Determine the second position of the vehicle at the second time according to the plurality of particles.

The second time here is after the aforementioned first time. In the embodiment of the present application, after determining the number and distribution of multiple particles used for particle filtering, the second position of the vehicle at the second time may be determined according to the particle filtering algorithm. Based on this solution, multiple particles can be sampled around the first position according to the first ODD, so that the number or distribution of the multiple particles can correspond to the first ODD, and the positioning performance of the vehicle can be improved.

After the second position is obtained, the second position can be determined as the new first position in the embodiment of the present application, and the positioning method provided in the embodiment of the present application is used to continue positioning the vehicle. For example, if the second position a of the vehicle is obtained according to the aforementioned steps 201-204, it can be determined that point a is the new first position, and the vehicle can be positioned continuously according to steps 201-204 to obtain the new The second position.

It should be noted that after the second position is determined as the new first position, if the aforementioned first ODD is switched to the second ODD, the new first position can be reset according to the technical solution provided in the embodiments of the present application. The specific implementation method for determining the number or distribution of multiple particles used for particle filtering is the same as the above method, and will not be repeated here.

If the ODD of the vehicle is still the aforementioned first ODD, the effective particles among the plurality of particles obtained by sampling can be determined. Among them, the weight value of each particle in a plurality of particles can be determined, and the effective particle can be determined according to the weight value. Hereinafter, the method of determining effective particles will be described in conjunction with FIG. 5.

As shown in FIG. 5, there are multiple traffic participants on the road on which the vehicle is traveling, such as the signal light 501, the road sign 502, and the building 503 in FIG. 5. The landmark 501 can be selected in the first position according to a preset rule. The control and management equipment of the vehicle can calculate the first distance from the multiple particles to the road sign 501 and the second distance from the vehicle to the road sign 501 based on the data observed by the sensors installed in the vehicle itself. Wherein, the higher the similarity between the first distance and the second distance, the greater the weight value of the particle corresponding to the first distance. When the weight value is less than or equal to the first threshold, it can be determined that the particle corresponding to the first distance is an invalid particle. In Figure 5, black particles are effective particles, and white particles are ineffective particles.

Alternatively, when the difference between the first distance and the second distance is greater than the second threshold, it may be determined that the particle corresponding to the first distance is an ineffective particle. The first threshold and the second threshold here may be preset based on empirical values, which are not specifically limited in this application.

When the number of effective particles is less than the threshold, the second position at the second time can be determined as the new first position according to the technical solution provided in the embodiments of the present application, and sampling around the new first position is used for particle filtering The specific implementation method of the number and/or distribution of the multiple particles is the same as the above method, and will not be repeated here. When the number of effective particles is greater than or equal to the threshold, the second position can be determined as the new first position, some ineffective particles can be deleted around the new first position, and some effective particles can be copied, and this part of effective particles can be adopted. The filtering algorithm continues to locate the vehicle.

In one embodiment, when the effective particle copy operation is performed, particles with the same position as the effective particle may be sampled at the new first position. The same position can mean that the distance between the particles and the vehicle is the same, or the distribution of the particles around the vehicle is the same. As shown in Figure 5, the black particles are effective particles, and point b is the second position of the vehicle at the second time, that is, the new first position. According to the technical solutions in the embodiments of the present application, all effective particles can be copied for particle filtering. After the particle copy operation is performed, the number and distribution of the particles are shown in FIG. 6, and the particle filter algorithm can be used according to the particles in FIG. 6 to determine the position of the vehicle at the third time.

In the embodiment of the present application, a strategy for resetting the number or distribution of multiple particles may be stored in advance, as shown in Table 3:

The vehicle positioning method according to the embodiment of the present application has been described in detail above with reference to FIGS. 1 to 6. The vehicle positioning device according to the embodiment of the present application will be described in detail below with reference to FIGS. 7 to 8.

The vehicle positioning device 700 includes one or more processors 701, and the one or more processors 701 can implement the method in the embodiment shown in FIG. 2.

In a possible design, the vehicle positioning device 700 includes means for sampling a plurality of particles around the first position for particle filtering according to the first ODD. For the number or distribution of the plurality of particles, refer to the relevant description in the above method embodiment. For example, the first ODD may be determined by one or more processors. Optionally, the processor 701 may implement other functions in addition to the method of the embodiment shown in FIG. 2.

Optionally, in a design, the processor 701 may execute instructions to make the vehicle positioning device 700 execute the method described in the foregoing method embodiment. The instructions may be stored in the processor in whole or in part, and may also be stored in the memory 702 coupled to the processor in whole or in part.

In another possible design, the vehicle positioning device 700 may also include a circuit, and the circuit may implement the functions in the foregoing method embodiments.

In another possible design, the vehicle positioning device 700 may include one or more memories 702, on which instructions 704 are stored, and the instructions may be executed on the processor, so that the vehicle positioning device 700 executes the method described in the above method embodiment. Optionally, data may also be stored in the memory. The optional processor may also store instructions and/or data. For example, the one or more memories 702 may store the first ODD described in the foregoing embodiment, or the number or distribution of multiple particles involved in the foregoing embodiment. The processor and the memory can be provided separately or integrated together.

In another possible design, the communication device 700 may further include a transceiver unit 705 and an antenna 706. The processor 701 may be referred to as a processing unit, which controls the vehicle positioning device. The transceiver unit 705 may be called a transceiver, a transceiver circuit, or a transceiver, etc., and is used to implement the transceiver function of the vehicle positioning device through the antenna 706.

In a possible implementation, the vehicle positioning device 800 shown in FIG. 8 can be used as the positioning server on the management side or the control and management equipment of the vehicle itself involved in the above method embodiment, and executes the positioning server in the above method embodiment. The server or the management control device of the vehicle executes the steps. As shown in FIG. 8, the vehicle positioning device 800 may include a processing unit 801 and an acquisition unit 802, and the processing unit 801 and the acquisition unit 802 are coupled with each other. The processing unit 801 may be used to support the vehicle positioning device 800 to execute the processing actions in the foregoing method embodiments.

When performing the actions performed by the vehicle positioning device in the above method embodiments, the processing unit 801 can be used to determine the first position of the vehicle at the first time; or, it can also be used to determine that the first design of the vehicle at the second time is applicable. Domain ODD.

The collection unit 802 samples a plurality of particles used for particle filtering around the first position according to the first ODD. For the number or distribution of the multiple particles, refer to the relevant description in the foregoing method embodiment.

In one design, the processing unit 801 may also be used to determine the second position of the vehicle at the second time according to the plurality of particles.

In one design, the processing unit 801 may also be used to determine the target level of the first ODD after determining the first ODD of the vehicle at the second time, where the target level of the first ODD and how to determine the first ODD For the target level of ODD, refer to the relevant description in the above method embodiment.

In one design, the processing unit 801 may also be used to determine that the first ODD is switched to the second ODD. The collection unit 802 may also be used to reset the number or distribution of the plurality of particles according to the second ODD. Wherein, how to reset the number or distribution of the multiple particles according to the second ODD can refer to the relevant description in the above method embodiment.

Alternatively, the processing unit 801 may also be used to determine that the number of effective particles in the plurality of particles is less than a threshold and the first ODD has not been switched; delete some ineffective particles and copy some effective particles. Among them, how to determine the number of effective particles and how to copy some effective particles can refer to the relevant description in the above method embodiment. For how to perform heartbeat detection on the server to be upgraded, reference may be made to the related description in the foregoing method embodiment.

Only one or more of the units in FIG. 8 can be implemented by software, hardware, firmware, or a combination thereof. The software or firmware includes but is not limited to computer program instructions or codes, and can be executed by a hardware processor. The hardware includes, but is not limited to, various integrated circuits, such as a central processing unit (CPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

It should be noted that the processor in the embodiment of the present application may be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the foregoing method embodiments can be completed by hardware integrated logic circuits in the processor or instructions in the form of software. The above-mentioned processor may be a general-purpose processor, a digital signal processor (digital signal processor, DSP), an application specific integrated circuit (ASIC), a ready-made programmable gate array (field programmable gate array, FPGA) or other Programming logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

It can be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of exemplary but not restrictive description, many forms of RAM are available, such as static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), and synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (synchlinkDRAM, SLDRAM) And direct memory bus random access memory (direct rambusRAM, DR RAM). It should be noted that the memories of the systems and methods described herein are intended to include, but are not limited to, these and any other suitable types of memories.

The embodiment of the present application also provides a computer-readable medium on which a computer program is stored, and when the computer program is executed by a computer, the vehicle positioning method described in any of the foregoing method embodiments is implemented.

The embodiment of the present application also provides a computer program product, which, when executed by a computer, implements the vehicle positioning method described in any of the foregoing method embodiments.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center. Transmission to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media. The usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (for example, a solid state disk, SSD)) etc.

An embodiment of the present application also provides a vehicle positioning device, including a processor and an interface; the processor is configured to execute the vehicle positioning method described in any of the foregoing method embodiments.

It should be understood that the aforementioned vehicle positioning device may be a chip, and the processor may be implemented by hardware or software. When implemented by hardware, the processor may be a logic circuit, an integrated circuit, etc.; when implemented by software, When implemented, the processor may be a general-purpose processor, which is implemented by reading the software code stored in the memory, and the memory may be integrated in the processor, may be located outside the processor, and exist independently.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application. Should be covered within the scope of protection of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A vehicle positioning method, characterized in that it comprises:

Determine the first position of the vehicle at the first time;

Determine the first design applicable domain ODD of the vehicle at the second time;

Sampling a plurality of particles used for particle filtering around the first position according to the first ODD, where the number or distribution of the plurality of particles corresponds to the first ODD;

The second position of the vehicle at a second time is determined according to the plurality of particles, and the second time is after the first time.
The method according to claim 1, wherein after the determining that the vehicle is at the first ODD at the second time, the method further comprises:

Determining the target level of the first ODD;

The sampling of a plurality of particles used for particle filtering around the first position according to the first ODD, and the number or distribution of the plurality of particles corresponding to the first ODD includes:

A plurality of particles for particle filtering are sampled around the first position according to the target level, and the number or distribution of the plurality of particles corresponds to the target level.
The method according to claim 2, wherein the number or distribution of the plurality of particles further corresponds to the sensor type of the vehicle.
The method according to any one of claims 1-3, wherein the method further comprises:

Determining that the first ODD is switched to the second ODD;

The number or distribution of the plurality of particles is reset according to the second ODD.
The method according to any one of claims 4, wherein the method further comprises:

Determining that the number of effective particles in the plurality of particles is less than a threshold value and that the first ODD does not switch;

Delete some invalid particles and copy some valid particles.
A vehicle positioning device, characterized in that it comprises:

A processing unit for determining the first position of the vehicle at the first time, and the first design application domain ODD of the vehicle at the second time;

A collecting unit, configured to sample a plurality of particles used for particle filtering around the first position according to the first ODD, and the number or distribution of the plurality of particles corresponds to the first ODD;

The processing unit is further configured to determine a second position of the vehicle at a second time according to the plurality of particles, the second time being after the first time.
7. The device according to claim 6, wherein the processing unit is further configured to determine the target level of the first ODD after determining the first ODD of the vehicle at the second time;

The collecting unit samples a plurality of particles used for particle filtering around the first position according to the first ODD, and the number or distribution of the plurality of particles corresponding to the first ODD includes: the collecting The unit samples a plurality of particles for particle filtering around the first position according to the target level, and the number or distribution of the plurality of particles corresponds to the target level.
The device according to claim 7, wherein the number or distribution of the plurality of particles further corresponds to the sensor type of the vehicle.
The device according to any one of claims 6-8, characterized in that:

The processing unit is further configured to determine that the first ODD is switched to the second ODD;

The collection unit is further configured to reset the number or distribution of the plurality of particles according to the second ODD.
The device according to claim 9, wherein the processing unit is further configured to:

Determining that the number of effective particles in the plurality of particles is less than a threshold value and that the first ODD does not switch;

Delete some invalid particles and copy some valid particles.
A vehicle positioning device, characterized in that it comprises:

Memory for storing computer programs; and

The processor is configured to execute the calculation program stored in the memory, so that the vehicle positioning device executes the method according to any one of claims 1-5.
A computer-readable storage medium, characterized in that it stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the vehicle positioning device executes the vehicle positioning device as described in any one of claims 1-5. The method described.
A computer program product, characterized in that, when the computer program product runs on a processor, the vehicle positioning device is caused to execute the method according to any one of claims 1-5.