CN110967023B - Automobile positioning method and automobile positioning device - Google Patents

Abstract

The present application provides a car positioning method and a car positioning device. The car positioning method includes: obtaining the running status information of the car. The running status information is used to represent the status information of the car during operation; according to the car's running status information; The operating status information determines the surface features of the road on which the car has been driven. The surface features of the road on which the car has been driven are used to represent one or more of the surface relief and surface roughness of the road on which the car has been driven; according to the The surface features of the road the car has traveled on and the preset surface features determine the current location of the car. Correspondingly, a corresponding device is also provided. Using this application, the accuracy of car positioning can be effectively improved.

Description

Car positioning method and car positioning device

Technical field

The present application relates to the field of automatic driving technology, and in particular to a car positioning method and a car positioning device.

Background technique

Advanced driving assistance systems and autonomous driving systems have developed rapidly in recent years and have become the mainstream trend in future transportation. Environmental perception, map positioning, planning decision-making and execution control are indispensable core key technologies for autonomous driving systems. Among them, map positioning provides the premise for the autonomous driving system to realize autonomous driving from point A to point B. That is, map positioning solves the problem of "where am I" for autonomous driving. Only based on the car's current location information can the autonomous driving system plan the correct route to the destination. Therefore, without a map positioning module, autonomous vehicles cannot achieve autonomous driving. For the positioning problem of autonomous driving, the following solutions can generally be adopted, namely: positioning based on global positioning system (GPS), positioning based on GPS and inertial measurement unit (IMU), and synchronization based on vision or laser. Positioning and mapping (simultaneous localization and mapping, SLAM) positioning.

However, the above positioning methods are greatly affected by the external environment. For example, for GPS positioning, it is difficult to use GPS to position vehicles in environments with weak GPS signals such as residential areas or underground garages. Another example is SLAM positioning. For example, if a map is constructed on a sunny day, features will change after rain, causing the positioning to fail.

Therefore, how to improve the accuracy of positioning needs to be solved urgently.

Contents of the invention

This application provides a car positioning method and a car positioning device, which can effectively improve the accuracy of positioning.

In the first aspect, embodiments of the present application provide a car positioning method, including:

Obtain the running status information of the car, which is used to represent the status information of the car during operation; determine the surface characteristics of the road on which the car has traveled based on the running status information of the car, and determine the surface characteristics of the road where the car has traveled. The surface features of the road on which the car has been driven are used to represent one or more of the surface relief and surface roughness of the road on which the car has been driven; the surface features of the road on which the car has been driven are determined based on the preset surface features. The current location of the car is described, and the preset surface features include the mapping relationship between the road and the surface features.

Implementing the embodiments of this application, in environments such as parking lots or residential areas blocked by obstacles, cars can also be effectively positioned based on the surface characteristics of the road, avoiding low positioning accuracy due to environmental effects. This effectively improves positioning accuracy.

In a possible implementation, determining the surface characteristics of the road on which the car has traveled based on the running status information of the car includes: inputting the running status information into a vibration model of the car, and outputting The road surface height of the road on which the car has traveled; the change of the road surface height of the road on which the car has traveled with the distance is determined based on the road surface height of the road on which the car has traveled and the operating status information; according to the road surface height of the road on which the car has traveled; The road surface height of the road changes with the distance, and the road surface characteristics of the road where the car has traveled are matched to obtain the surface characteristics of the road where the car has traveled.

Implementing the embodiments of this application, by modeling the vibration of the car, the surface characteristics of the road on which the car has been driven can be estimated based on the operating status information. On the one hand, the operating status information such as vehicle speed and acceleration can be obtained based on the vehicle-mounted sensors, which reduces the car positioning process. On the other hand, the road surface characteristics are relatively stable and not affected by obstacles, etc., which can effectively improve the accuracy of positioning.

In a possible implementation, the road surface features of the road where the car has been driven are matched based on the change of the road surface height with the distance of the road where the car has been driven, and the surface features of the road where the car has been driven are obtained, The method includes: performing top-level feature matching on the road on which the car has traveled based on changes in road surface height with distance, and obtaining top-level road surface features of the road on which the car has traveled; The top-level pavement feature of the road performs sub-feature matching on the road on which the car has traveled to obtain the sub-pavement features of the road on which the car has traveled.

In a possible implementation, the top-level pavement features include one or more of the number of sub-features, top-level feature frequency distribution, top-level feature maximum amplitude, top-level feature average amplitude, and top-level feature variance; the sub-pavement features Including one or more of sub-feature separation distance, sub-feature persistence distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude and sub-feature variance.

In a possible implementation, inputting the operating status information into the vibration model of the car and outputting the road surface height of the road on which the car has traveled includes: converting the operating status information a(t ) is input into the vibration model of the car, and the road surface height h(t) of the road on which the car has been driven is output, where the vibration model is: h(t)=f ^-1 (a(t)).

In a possible implementation, the running status information includes one or more of acceleration information and speed information.

In a possible implementation, the current location of the car includes one or more of an undulating location and a location with a roughness greater than a roughness threshold.

In a second aspect, embodiments of the present application provide a car positioning device, including:

An acquisition unit is used to obtain the running status information of the car, and the running status information is used to represent the status information of the car during operation; a first determining unit is used to determine the car based on the running status information of the car. The surface characteristics of the road that has been traveled, the surface characteristics of the road that has been traveled are used to represent one or more of the surface relief and surface roughness of the road that the car has traveled; a second determination unit, used to The current location of the car is determined based on the surface features of the road on which the car has traveled and preset surface features, which include the mapping relationship between the road and the surface features.

In a possible implementation, the first determination unit includes: an input and output subunit, configured to input the operating status information into the vibration model of the car and output the road surface of the road on which the car has traveled. height; a determination subunit, used to determine the change of the road surface height of the road the car has traveled with the distance according to the road surface height of the road the car has traveled and the operating status information; a feature matching subunit, used to determine the change of the road surface height of the road the car has traveled based on the distance; The road surface height of the road on which the car has been driven changes with the distance, and the road surface characteristics of the road on which the car has been driven are matched to obtain the surface features of the road on which the car has been driven.

In a possible implementation, the feature matching subunit is specifically configured to perform top-level feature matching on the road on which the car has traveled based on the change in road surface height of the road on which the car has traveled with the distance, to obtain the The top-level road surface characteristics of the road on which the car has traveled; and performing sub-feature matching on the road on which the car has traveled based on the top-level road surface characteristics of the road on which the car has traveled to obtain the sub-road surface characteristics of the road on which the car has traveled.

In a possible implementation, the top-level pavement features include one or more of the number of sub-features, top-level feature frequency distribution, top-level feature maximum amplitude, top-level feature average amplitude, and top-level feature variance; the sub-pavement features Including one or more of sub-feature separation distance, sub-feature persistence distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude and sub-feature variance.

In a possible implementation, the input and output subunit is used to input the operating status information into the vibration model of the car and output the road surface height of the road on which the car has traveled, specifically:

The operating status information a(t) is input into the vibration model of the car, and the road surface height h(t) of the road on which the car has traveled is output, where the vibration model is: h(t)=f ^-1 (a(t)).

In a possible implementation, the running status information includes one or more of acceleration information and speed information.

In a possible implementation, the current location of the car includes one or more of an undulating location and a location with a roughness greater than a roughness threshold.

In a third aspect, embodiments of the present application also provide a car positioning device, which can implement the car positioning method described in any one of the above first aspects; the car positioning device may be a chip, a device, etc.; The car positioning device can implement the above method through software, hardware, or through hardware executing corresponding software.

When part or all of the above car positioning method is implemented by software, the car positioning device includes: a memory and a processor; the memory is used to store program instructions; the processor is used to execute the memory. The stored program instructions, when executed, enable the car positioning device to implement the method provided by at least one of the above first aspects.

In a possible implementation, the memory may be a physically independent unit or may be integrated with the processor.

In the fourth aspect, embodiments of the present application provide a car positioning system, which includes a car positioning device and a vehicle-mounted sensor. The vehicle-mounted sensor is used to measure the operating status information of the car; the car positioning device is used to obtain the vehicle-mounted sensor. The measured operating status information, and the surface characteristics of the road on which the car has been driven are determined based on the operating status information, and the current location of the car is determined based on the surface features of the road on which the car has been driven.

In a possible implementation manner, the car positioning device may be a chip or a separate device, which is not limited by the embodiments of this application.

In a fifth aspect, embodiments of the present application provide a computer-readable storage medium. Program instructions are stored in the computer-readable storage medium. When the program instructions are executed on a computer or processor, the computer or processor causes the computer or processor to The device performs the method described in at least one of the first aspects.

In a sixth aspect, embodiments of the present application provide a computer program product including program instructions. When the program instructions are executed on a computer or processor, the computer or processor causes the computer or processor to execute at least one of the first aspects. method described.

Description of the drawings

In order to more clearly explain the technical solutions in the embodiments of the present application or the background technology, the drawings required to be used in the embodiments or the background technology of the present application will be described below.

Figure 1 is a schematic architectural diagram of an autonomous driving system provided by an embodiment of the present application;

Figure 2 is a schematic structural diagram of a car positioning device provided by an embodiment of the present application;

Figure 3 is a schematic structural diagram of a car positioning system provided by an embodiment of the present application;

Figure 4 is a schematic flowchart of a car positioning method provided by an embodiment of the present application;

Figure 5 is a schematic diagram of a vehicle vibration model provided by an embodiment of the present application;

Figure 6 is a schematic diagram of a process for determining road surface characteristics provided by an embodiment of the present application;

Figure 7 is a schematic diagram of a hierarchical feature modeling scenario provided by an embodiment of the present application;

Figure 8 is a schematic scene diagram of a car positioning method provided by an embodiment of the present application;

Figure 9 is a schematic scene diagram of a road feature matching method provided by an embodiment of the present application;

Figure 10 is a schematic diagram of a car positioning scene provided by an embodiment of the present application;

Figure 11 is a schematic diagram of a scene of autonomous driving of a car in an underground parking garage provided by an embodiment of the present application;

Figure 12 is a schematic structural diagram of another car positioning device provided by an embodiment of the present application;

Figure 13 is a schematic structural diagram of a first determination unit provided by an embodiment of the present application.

Detailed ways

The embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

The terms "first" and "second" in the description, claims and drawings of this application are used to distinguish different objects, rather than describing a specific sequence. Furthermore, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes Other steps or units inherent to such processes, methods, products or devices.

It should be understood that in this application, "at least one (item)" refers to one or more, "plurality" refers to two or more, and "at least two (items)" refers to two or three and three or more, "and/or" is used to describe the relationship between associated objects, indicating that there can be three relationships. For example, "A and/or B" can mean: only A exists, only B exists, and A exists at the same time. and B, where A and B can be singular or plural. The character "/" generally indicates that the related objects are in an "or" relationship. “At least one of the following” or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items). For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c" ”, where a, b, c can be single or multiple.

Referring to Figure 1, Figure 1 is a schematic architectural diagram of an automatic driving system provided by an embodiment of the present application. As shown in Figure 1, the automatic driving system includes: a map positioning module 101, an environment sensing module 2, a planning and decision-making module 3, an execution Control module 104; among them, the map positioning module, the environment perception module, the planning and decision-making module and the execution control module can exist independently, or they can be integrated together, etc. The embodiment of the present application is for these four modules. The specific form is not limited. The map positioning module, environment sensing module, planning and decision-making module and execution control module can be connected to each other through connectors, or can also be connected through wireless communication, etc. The embodiment of the present application does not limit how these four modules are connected. .

Among them, the map positioning module can estimate the position and attitude of the car based on prior map information, vehicle-mounted sensors, GPS, IMU and other information, and obtain the positioning information of the car.

The environment sensing module can collect driving environment information around the car through multiple sensors. Among them, the sensors may include various visual sensors and radar sensors. The visual sensors may include monocular sensors, binocular sensors, multi-ocular sensors, etc.; the radar sensors may include ultrasonic radar sensors, millimeter wave radar sensors, lidar sensors, etc.

The planning and decision-making module can plan and make decisions on the movement trajectory of the car based on the driving environment information around the car collected by the environment sensing module and the positioning information of the map positioning module.

The execution control module can realize the automatic driving control function of the car based on the steering instructions, acceleration instructions and braking instructions output by the planning and decision-making module.

It can be seen from the above that the map positioning module provides an implementation basis for unmanned driving systems or automatic driving systems. At the same time, in general car navigation systems, the map positioning module also provides an implementation basis for car navigation. However, in obstructed environments, such as residential areas, underground libraries and other environments with weak GPS signals, it is difficult to use GPS to achieve car positioning. Another example is that when using the SLAM method to achieve positioning, SLAM is greatly affected by the external environment. For example, if a map is constructed on a sunny day, rain will cause feature changes and cause positioning failure; another example is that large changes in light will also cause positioning difficulties; and If the background features change greatly, it will also cause positioning difficulties. For example, SLAM is used to build a map when the parking lot is full of cars, and then positioned when the parking lot is empty. The inability to match the features will lead to positioning failure. At the same time, SLAM is a feature-based map, so the storage capacity of SLAM maps is large.

Therefore, the embodiments of the present application provide a low-cost method that can stabilize positioning even when the external environment changes. Specifically, the car positioning method provided by the embodiment of the present application can also be applied to road sections that cars frequently pass through, such as commuting routes or community garages, etc. The methods provided by the embodiments of this application will be introduced in detail below.

It can be understood that before introducing the method provided by the embodiment of the present application, please refer to Figure 2. Figure 2 is a schematic structural diagram of a car positioning device provided by the embodiment of the present application. The car positioning device can be used to perform the car positioning provided by the embodiment of the present application. Positioning method.

As shown in Figure 2, the car positioning device may include a processor 201 and a vehicle-mounted sensor 202. The processor and the vehicle-mounted sensor may be coupled through a connector. The connector may include various interfaces, transmission lines, buses, etc. This application The examples are not limiting.

Among them, the vehicle-mounted sensor can be used to read the running status information of the car. For example, the vehicle-mounted sensor can be used to read the acceleration information and speed information of the car, etc., which are not limited in the embodiments of this application. Optionally, the vehicle-mounted sensor may also include other names, etc., and the embodiment of the present application does not limit the name of the vehicle-mounted sensor.

The processor may be one or more central processing units (CPUs). When the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU. Optionally, the processor may be a processor group composed of multiple processors, and the multiple processors are coupled to each other through one or more buses. Optionally, the processor may also include other types of processors, etc., which are not limited by the embodiments of this application.

It can be understood that in a possible implementation, the car positioning device may also include a memory (not shown in the figure), which may be used to store computer program instructions, including an operating system (OS), and for Various types of computer program codes that execute the program codes of the embodiments of the present application. Optionally, the memory includes but is not limited to non-power-off volatile memory, such as embedded multi media card (EMMC), general-purpose Universal flash storage (UFS) or read-only memory (ROM), or other types of static storage devices that can store static information and instructions, or volatile memory (volatile memory) ), such as random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or electrically erasable programmable read-only memory (EEPROM), Compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, Or any other computer-readable storage medium that can be used to carry or store program codes in the form of instructions or data structures and can be accessed by a computer. The memory is used to store related instructions and data. In this embodiment of the present application, the memory can be used to store preset surface features and the like.

Specifically, the processor can be used to determine the surface features of the car's current road based on the car's operating status information, determine its current location, and so on.

It can be understood that in specific implementation, the car positioning device may be in the form of a chip, or in the form of an independent device, etc., which are not limited by the embodiments of this application.

It can be understood that the above is only a schematic structural diagram of a car positioning device provided by the embodiment of the present application. In a specific implementation, the car positioning device may have more or less components than those shown, and two or more may be combined. More components, or different configuration implementations with different components, etc.

It can be understood that what is shown in Figure 2 is an example of a car positioning device. In specific implementation, the system used to implement the method provided by the embodiment of the present application can also be shown in Figure 3. Figure 3 is an example of a car positioning device provided by the embodiment of the present application. is a schematic structural diagram of a car positioning system. The car positioning system includes: a car positioning device 301 and a vehicle-mounted sensor 302. The car positioning device can be connected to the vehicle-mounted sensor through a connector, or the car positioning device can also be connected to the vehicle-mounted sensor in a wireless manner, etc., which are not limited by the embodiments of this application.

Among them, the car positioning device 301 may include: a processor 3011 and a memory 3012. The processor and the memory may be coupled through a connector, which may include various interfaces, transmission lines, buses, etc., which are not limited in the embodiments of the present application. It should be understood that in various embodiments of the present application, coupling refers to interconnection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

The memory can be used to store computer program instructions, including various types of computer program codes including operating system (OS) and program codes for executing embodiments of the present application. Optionally, the memory includes but is not limited to right and wrong. Electrically volatile memory, such as embedded multi media card (EMMC), universal flash storage (UFS) or read-only memory (ROM), or can store static information and other types of static storage devices for instructions, which can also be power-off volatile memory (volatile memory), such as random access memory (RAM) or other types of dynamic storage devices that can store information and instructions. It can also be electrically erasable programmable read-only memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs). Optical disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or any other computer-readable device capable of carrying or storing program code in the form of instructions or data structures that can be accessed by a computer Storage media, etc., this memory is used to store relevant instructions and data. In this embodiment of the present application, the memory can be used to store preset surface features.

The processor may be one or more central processing units (CPUs). When the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU. Optionally, the processor may be a processor group composed of multiple processors, and the multiple processors are coupled to each other through one or more buses. Optionally, the processor may also include other types of processors, etc., which are not limited by the embodiments of this application. Specifically, the processor can be used to determine the surface features of the car's current road based on the car's operating status information, determine its current location, and so on.

Wherein, when the car positioning device is in the form of an independent device, the car positioning device may also include a transceiver (not shown in the figure) that can be used to receive and send data. For example, the transceiver can be used to receive data from a vehicle-mounted sensor. The running status information of the car, etc. are not limited in the embodiments of this application.

The vehicle-mounted sensor can be used to read the running status information of the car. For example, the vehicle-mounted sensor can be used to read the acceleration data and speed data of the car, etc., which are not limited by the embodiments of this application. Optionally, the vehicle-mounted sensor may also include other names, etc., and the embodiment of the present application does not limit the name of the vehicle-mounted sensor.

It can be understood that FIG. 3 and FIG. 2 respectively show different structures for executing the methods provided by the embodiments of the present application. In specific implementations, the embodiments of the present application do not uniquely limit the above structures.

Referring to Figure 4, Figure 4 is a schematic flow chart of a car positioning method provided by an embodiment of the present application. The car positioning method can be applied to the car positioning device shown in Figure 2 and the car positioning system shown in Figure 3. As shown in Figure 4, the car positioning method includes:

401. The car positioning device obtains the running status information of the car. The running status information is used to represent the status information of the car during operation.

In the embodiment of the present application, the running status information of the car can be obtained by the vehicle-mounted sensor in the car positioning device; or it can also be obtained by the vehicle-mounted sensor connected to the car positioning device, and then the car positioning device can obtain it from the vehicle-mounted sensor. The running status information, etc., the embodiments of this application do not limit the above two implementation methods.

Specifically, the running status information of the car may include the acceleration data (that is, acceleration information) and speed data (that is, speed information) of the car. The acceleration data may include the vehicle's vertical acceleration data, or may include the vehicle's horizontal acceleration data, etc. This is not limited in the embodiments of the present application.

402. The car positioning device determines the surface features of the road on which the car has been driven based on the operating status information of the car. The surface features of the road on which the car has been driven are used to represent the surface undulations and surface roughness of the road on which the car has been driven. one or more items.

In the embodiments of the present application, the surface characteristics of the road on which the car has been driven can be used to represent one or more of the surface relief and surface roughness of the road on which the car has been driven. Specifically, the surface features of the road on which the car has been driven can be used to represent the surface roughness of the road on which the car has been driven; or, the surface features of the road on which the car has been driven can be used to represent the surface roughness of the road on which the car has been driven. ; Alternatively, the surface features of the road on which the car has been driven can be used to represent the surface relief state and surface roughness of the road on which the car has been driven. Among them, surface undulations can be used to represent potholes, bumps, speed bumps, etc. on the road that will cause bumps in the car; surface roughness can represent microscopic undulations of the road surface and pavements of different materials (such as asphalt pavement, concrete pavement, gravel road surface, etc.) can cause high vibrations in the car.

Specifically, the above-mentioned determination of the surface characteristics of the road on which the above-mentioned car has been driven based on the above-mentioned car's operating status information includes:

41) Input the above-mentioned operating status information into the vibration model of the above-mentioned car, and output the road surface height of the road on which the above-mentioned car has traveled;

42) Determine the change of the road surface height of the road where the above-mentioned car has traveled based on the distance traveled based on the road surface height of the road where the above-mentioned car has traveled and the above-mentioned operating status information;

43) Perform road surface feature matching on the road where the above-mentioned car has traveled based on the change of the road surface height with the distance, and obtain the surface characteristics of the road where the above-mentioned car has traveled.

Wherein, the vibration model of the above-mentioned automobile may include a low-pass filter model of the above-mentioned automobile.

In order to more vividly understand the surface characteristics of the road on which the car has been driven, provided by the embodiment of the present application, see Figure 5 , which is a schematic diagram of a vehicle vibration model provided by the embodiment of the present application. Among them, the main function of automobile tires and suspension is to alleviate the vibration of the road surface, so the vibration model of the automobile can be simplified as a low-pass filter.

The vibration model of the car is abstracted as a low-pass filter f(x), the road height h(t) is used as the input signal, and the acceleration data a(t) of the car is used as the output of the filter, that is:

a(t)=f(h(t)) (1)

According to the inverse function of formula (1), we can get:

h(t)＝f ^-1 (a(t)) (2)

For example, the specific form of the above filter(x) can be as follows: h(s) is assumed to be the Laplace transform of h(t), that is, h(s)=L(h(t)); a( s) is assumed to be the Laplace transform of a(t), that is, a(s)=L(a(t)).

Then the formula f(x) can be written as a transfer function as follows:

The inverse function can look like this:

According to formula (2) and the acceleration data of the car, the road surface height can be calculated. Then through the car's speed data v, the change of the road surface height with the distance h (s) can be obtained, as shown below:

h(s)＝h(t*v) (3)

Referring to Figure 6, Figure 6 is a schematic diagram of a process for determining road surface characteristics provided by an embodiment of the present application. As shown in Figure 6, through acceleration data (also called acceleration signal), and the above formula (2) and formula (3) ) can obtain the surface characteristics of the road the car has traveled on. It can be understood that the above formula (1), formula (2) and formula (3) are a method provided by the embodiment of this application. In specific implementation, h(s) may also be determined based on other operating status information. This application The examples are not limiting.

More specifically, there is a wealth of information on road surface features. Therefore, hierarchical feature modeling can be further performed on road surface features. Therefore, embodiments of the present application also provide a method of hierarchical feature modeling, as shown below. :

The above-mentioned method performs road surface feature matching on the road on which the above-mentioned car has traveled based on the change of the road surface height with the distance, and obtains the surface features of the above-mentioned road on which the above-mentioned car has traveled, including:

431) Perform top-level feature matching on the road where the above-mentioned car has traveled based on the change in road surface height with distance, and obtain the top-level road surface characteristics of the road where the above-mentioned car has traveled;

432) Perform sub-feature matching on the road where the above-mentioned car has traveled based on the top-level road surface features of the road where the above-mentioned car has traveled, and obtain the sub-surface characteristics of the road where the above-mentioned car has traveled.

To clearly understand the hierarchical feature modeling method provided above, please refer to Figure 7 . Figure 7 is a schematic diagram of a hierarchical feature modeling scenario provided by an embodiment of the present application. As shown in Figure 7, the top-level road surface features may include feature 1 (i.e. S1), feature 2 (S2) and feature 3 (S3) shown in Figure 7; the sub-pavement features may include sub-surface features under the top-level features shown in Figure 7. Features, such as sub-feature 1.1, sub-feature 1.2,..., sub-feature 1.n under feature 1, and sub-feature 3.1,..., sub-feature 3.n under feature 3, etc. It can be understood that the number of top-level road surface features and the number of sub-features of each top-level road surface feature shown above are only an example.

Among them, in order to more vividly distinguish the above-mentioned top-level pavement features and sub-pavement features, the embodiment of the present application also provides a method of how to quantitatively distinguish the top-level pavement features and sub-pavement features, as shown below:

The above-mentioned top-level pavement features include one or more of the number of sub-features, top-level feature frequency distribution, top-level feature maximum amplitude, top-level feature average amplitude, and top-level feature variance;

The above-mentioned sub-pavement features include one or more of sub-feature spacing distance, sub-feature duration distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude and sub-feature variance.

Among them, the number of sub-features refers to the number of sub-features corresponding to the top-level road surface features. As shown in Figure 7, the number of sub-features of feature 1 is 4 (the number shown in the figure), and the number of sub-features of feature 2 is 4. The number is 3, and the number of sub-features of feature 3 is 3. The top-level feature frequency distribution refers to the distribution of distance intervals between each sub-feature. Specifically, it can refer to the distribution characteristics of the amplitude with frequency after the top-level feature time history curve undergoes Fourier transformation. As shown in Figure 7, the distance interval between each sub-feature in feature 1 is greater than the distance interval between each sub-feature in feature 2, but smaller than the distance between each sub-feature in feature 3. The maximum amplitude of the top-level feature refers to the top-level pavement feature corresponding to the maximum road height that the car passes when driving on each top-level pavement feature, as shown in Figure 7. It can be seen from the figure that the maximum amplitude of the top-level pavement can be a feature 3 amplitude. The average amplitude of the top-level features refers to the average amplitude of the sub-features corresponding to each top-level pavement feature. As shown in Figure 7, the average amplitude of feature 1 can be the average of the amplitudes of the four sub-features in the figure, and the average amplitude of feature 2 can be The average of the amplitudes of the three sub-features in the figure. The top-level feature variance refers to the amplitude variance between each top-level road surface feature. As shown in Figure 7, the variance between the amplitude of feature 1, the amplitude of feature 2, and the amplitude of feature 3.

The sub-feature spacing distance may refer to the distance between each sub-feature. Sub-feature duration refers to the distance the car travels on the sub-feature. The sub-feature frequency distribution can refer to the distribution characteristics of the amplitude with frequency after the sub-feature time history curve has been Fourier transformed. The maximum amplitude of a sub-feature refers to the sub-feature corresponding to the maximum road height that the car passes when driving on each sub-feature. The average amplitude of sub-features refers to the average amplitude of each sub-feature. Specifically, it can refer to the average amplitude between sub-features of sub-features. As shown in Figure 7, for sub-feature 1.1, the car in this sub-feature When running up, vibration will also be generated. Therefore, the average amplitude of the sub-feature can refer to the average amplitude of each small amplitude in the sub-feature 1.1. Sub-feature variance refers to the amplitude variance between sub-features.

By further distinguishing top-level pavement features and sub-pavement features, hierarchical modeling of the road on which the car travels can be performed, thereby improving the accuracy and accuracy of determining the pavement features, thereby improving the accuracy of the positioning of the car positioning device.

403. The car positioning device determines the current location of the car based on the surface features of the road on which the car has traveled and the preset surface features. The preset surface features include the mapping relationship between the road and the surface features.

In the embodiment of the present application, the preset surface features include the mapping relationship between the road and the surface features, that is, by storing the preset surface features, the car positioning device can be based on the surface features of the road that has been traveled and the preset surface features. to get the current location.

It can be understood that the current location of the car may include undulating locations on the road and locations where the surface roughness of the road is greater than the roughness threshold. Therefore, the vehicle positioning device can accurately locate the current location based on surface features. The roughness threshold is used to measure the surface roughness of the road. Therefore, the embodiment of the present application does not limit the roughness threshold.

It can be understood that the method provided by the embodiment of the present application can also be used to calibrate the navigation system of the car. For example, after the car positioning device determines the current position of the car, the car positioning device can compare whether the current position of the car is consistent with the current position of the car. Check whether the position in the installed navigation system is consistent. If not, you can modify the position displayed in the navigation system.

Implementing the embodiments of this application, in environments such as parking lots or residential areas blocked by obstacles, cars can also be effectively positioned based on the surface characteristics of the road, avoiding low positioning accuracy due to environmental effects. This effectively improves positioning accuracy.

In order to clearly understand the method shown in Figure 4, specific examples will be described below.

First, refer to Figure 8. Figure 8 is a schematic scene diagram of a car positioning method provided by an embodiment of the present application. This method can be applied to the car positioning device shown in Figure 2, or to the car positioning system shown in Figure 3. . As shown in Figure 8, the car positioning method includes:

801. Acquire the acceleration data and speed data of the car when driving on the preset road through the vehicle-mounted sensor, perform feature modeling of the preset road based on the acceleration data and speed data, and after obtaining the road features, store the road features of the preset road .

In the embodiment of this application, the preset road may be a road that the user frequently passes, or it may be a road in the city where the user is located, etc. The embodiment of this application does not limit the specific setting of the preset road.

It can be understood that for the specific implementation of step 801, reference can also be made to the method shown in Figure 4, which will not be described in detail here.

802. Acquire the acceleration data and speed data when the car is driving, and perform feature matching on the road the car is currently driving based on the acceleration data and speed data.

Specifically, see Figure 9, which is a schematic diagram of a road feature matching method provided by an embodiment of the present application. As shown in Figure 9, the road feature matching method includes:

91) Based on the automobile vibration model, extract the pavement features of the current road and obtain the change h(s) of the road height with the distance;

92) Perform top-level feature matching; if it can be matched with each stored top-level feature in turn, for example, perform Nth top-level feature matching, where N is an integer greater than or equal to 1, and N is used to distinguish different objects, and Doesn't mean sorting.

93) Determine whether the top-level pavement feature of the current road matches the N-th top-level feature. If it matches, perform sub-feature matching; if not, perform N+1-th top-level feature matching;

94) When performing sub-feature matching, it can be matched with the sub-features of the Nth top-level feature in sequence. For example, the m-th sub-feature is matched, and m is an integer greater than or equal to 1;

95) Determine whether the sub-feature of the current road matches the m-th sub-feature of the N-th top-level feature. If it matches, determine that the top-level pavement feature and sub-pavement feature of the current road are the m-th sub-feature of the N-th layer in sequence; if they do not match , then the m+1th sub-feature matching is performed.

803. Predict the position of the car.

Among them, after obtaining the surface characteristics of the road the car is currently traveling on, the current road can be determined based on the road characteristics of the preset road, that is, the location prediction of the car is achieved.

It can be understood that the embodiment of the present application can also realize the correction of the position of the car. Specifically, for a specific example of the correction method, see Figure 10. Figure 10 is a schematic diagram of a car positioning scene provided by the embodiment of the present application. As shown in Figure 10, when the car is driving, it will pass through position 1 (1#), position 2 (2#) and position 3 (3#) shown in Figure 10. Specifically, position 1 is the well cover. , position 2 is the speed bump. First it hits the manhole cover, the vehicle's speed is 27.2, and then it hits the speed bump, the vehicle's speed is 19.1. Among them, the first waveform change point 1# is at 15m from the initial position, the second waveform change point 2# is at 80m from the initial position, and the third waveform change point 3# is at 200m from the initial position. In the feature matching stage, the matched waveform is 2#, and the position can be determined to be 80m, while the predicted position of the car is 70m. For this purpose, the corrected position can be 80m based on the road feature matching results.

In the embodiment of this application, the positioning method depends on road surface characteristics, so this application is not affected by the strength of the GPS signal. Therefore, in environments with weak GPS signals such as residential areas and underground garages, vehicle positioning is achieved through road surface characteristics. Positioning is achieved based on road surface features, such as speed bumps, uphill and downhill slopes, potholes and other features that will not change or change slightly over a long period of time, and are not easily affected by external light and weather. At the same time, pavement features have sparse characteristics, that is, the distribution of pavement features in space is relatively scattered, so the amount of data stored in pavement features is relatively small. The extraction of road surface features relies on vehicle-mounted acceleration sensors. Most vehicles currently have acceleration sensors installed, so there is no need to add sensors. Even if they need to be added, the cost of acceleration sensors is low.

Referring to Figure 11, Figure 11 is a schematic diagram of a scene of autonomous driving of a car in an underground parking garage according to an embodiment of the present application. As shown in Figure 11,

This application is mainly used in road sections that vehicles frequently pass through (commuting routes, community garages, etc.). For example, in a typical scenario, when a self-driving car drives into a community and needs to park the vehicle in an underground garage, the vehicle will face the problem of weak GPS signal and difficult positioning after entering the underground garage.

The car needs to go from point A outside the underground garage to point B in the underground garage. In this process, this application can be used to position the car based on the slope and speed bumps on the underground garage road surface, thereby realizing automatic driving from point A to point B outside the garage.

The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

Referring to Figure 12, Figure 12 is a schematic structural diagram of a car positioning device provided by an embodiment of the present application. The car positioning device can be used to perform the methods described in Figures 4 to 11. As shown in Figure 12, the car positioning device includes :

The acquisition unit 1210 is used to acquire the running status information of the car, and the above running status information is used to represent the status information of the above-mentioned car during operation;

The first determination unit 1220 is configured to determine the surface characteristics of the road on which the above-mentioned car has traveled based on the operating status information of the above-mentioned automobile. The surface characteristics of the above-mentioned road on which the above-mentioned automobile has traveled are used to represent the surface undulations and surface roughness of the road on which the above-mentioned automobile has traveled. one or more of the degrees;

The second determination unit 1230 is configured to determine the current location of the car based on the surface features of the road on which the car has traveled and preset surface features. The preset surface features include the mapping relationship between the road and the surface features.

Implementing the embodiments of this application, in environments such as parking lots or residential areas blocked by obstacles, cars can also be effectively positioned based on the surface characteristics of the road, avoiding low positioning accuracy due to environmental effects. This effectively improves positioning accuracy.

Specifically, as shown in Figure 13, the first determining unit 1220 includes:

The input and output subunit 1221 is used to input the above-mentioned operating status information into the vibration model of the above-mentioned car, and output the road surface height of the road on which the above-mentioned car has traveled;

The determination subunit 1222 is used to determine the change of the road surface height of the road on which the above-mentioned car has traveled based on the road surface height on which the above-mentioned car has traveled and the above-mentioned operating status information;

The feature matching subunit 1223 is used to perform road surface feature matching on the road on which the car has traveled based on changes in road surface height with distance, and obtain surface features of the road on which the car has traveled.

Specifically, the above-mentioned feature matching subunit 1223 is specifically used to perform top-level feature matching on the road on which the above-mentioned car has traveled based on the change of the road surface height of the above-mentioned car on the road with the distance, and obtain the top-level road surface characteristics of the road on which the above-mentioned car has traveled. ; and performing sub-feature matching on the road where the above-mentioned car has traveled based on the top-level road surface features of the road where the above-mentioned car has traveled, to obtain the sub-surface characteristics of the road where the above-mentioned car has traveled.

Specifically, the above-mentioned top-level pavement features include one or more of the number of sub-features, top-level feature frequency distribution, top-level feature maximum amplitude, top-level feature average amplitude, and top-level feature variance;

The above-mentioned sub-pavement features include one or more of sub-feature spacing distance, sub-feature duration distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude and sub-feature variance.

Specifically, the vibration model of the above-mentioned car includes the low-pass filter model of the above-mentioned car.

Specifically, the above running status information includes one or more of acceleration information and speed information.

Specifically, the current location of the car includes one or more of an undulating location and a location where the roughness is greater than the roughness threshold.

It can be understood that for the specific implementation of the car positioning device of Figure 12, reference can be made to the methods shown in Figures 4 to 11, which will not be described in detail here.

It can be understood that the processor shown in Figure 2 can be used to perform the implementation shown in steps 401 to 403 shown in Figure 4, and can also be used to perform the obtaining unit 1210, the first determining unit 1220 and the second determining unit 1230. The implementation methods will not be described in detail here. Alternatively, in a possible implementation, the method shown in step 401 can also be performed by the transceiver (not shown in the figure) in the car positioning device shown in Figure 2, or the method shown in the acquisition unit can also be performed by the transceiver in the car positioning device shown in Figure 2 The transceiver in the car positioning device shown is used to perform the execution, etc., and the embodiments of this application are not limited to uniqueness.

It can be understood that the processor shown in FIG. 3 can also be used to execute the implementation shown in steps 401 to 403 shown in FIG. The implementation methods shown will not be described in detail here. Alternatively, in a possible implementation, the method shown in step 401 can also be performed by the transceiver (not shown in the figure) in the car positioning device shown in Figure 3, or the method shown in the acquisition unit can also be performed by the transceiver in the car positioning device shown in Figure 3 The transceiver in the car positioning device shown is used to perform the execution, etc., and the embodiments of this application are not limited to uniqueness.

Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores instructions. When it is run on a car positioning device, the method flow shown in Figure 4, Figure 8 and Figure 9 can be achieved. accomplish.

Embodiments of the present application also provide a computer program product. When the computer program product is run on a car positioning device, the method flows shown in Figures 4, 8, 9, etc. are implemented.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments are implemented. This process can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, , may include the processes of the above method embodiments. The aforementioned storage media include: ROM, random access memory (RAM), magnetic disks, optical disks and other media that can store program codes.

Claims (17)

1. A method of locating an automobile, comprising:

acquiring running state information of an automobile, wherein the running state information is used for representing the state information of the automobile in the running process;

determining a surface feature of a road on which the automobile has traveled according to the running state information of the automobile, the surface feature of the road on which the automobile has traveled being used to represent one or more of a surface relief condition and a surface roughness of the road on which the automobile has traveled;

and determining the current position of the automobile according to the surface characteristics of the road on which the automobile is driven and preset surface characteristics, wherein the preset surface characteristics comprise the mapping relation between the road and the surface characteristics.

2. The method of claim 1, wherein the determining the surface characteristics of the road on which the vehicle has traveled based on the operating state information of the vehicle comprises:

inputting the running state information into a vibration model of the automobile, and outputting the road surface height of a road on which the automobile runs;

determining the change of the road surface height of the road on which the automobile runs along with the distance according to the road surface height of the road on which the automobile runs and the running state information;

And carrying out pavement characteristic matching on the road on which the automobile runs according to the change of the pavement height of the road on which the automobile runs along with the change of the distance, so as to obtain the surface characteristics of the road on which the automobile runs.

3. The method according to claim 2, wherein the step of performing the road surface feature matching on the road on which the automobile has traveled according to the change of the road surface height of the road on which the automobile has traveled along with the change of the distance, to obtain the surface feature of the road on which the automobile has traveled, comprises:

carrying out top-layer feature matching on the road on which the automobile runs according to the change of the road surface height of the road on which the automobile runs along with the change of the distance, so as to obtain the top-layer road surface feature of the road on which the automobile runs;

and performing sub-feature matching on the road on which the automobile runs according to the top road surface feature of the road on which the automobile runs, so as to obtain the sub-road surface feature of the road on which the automobile runs.

4. The method of claim 3, wherein the top level pavement features include one or more of a number of sub-features, a top level feature frequency distribution, a top level feature maximum amplitude, a top level feature average amplitude, and a top level feature variance;

The sub-road surface features include one or more of sub-feature separation distance, sub-feature duration distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude, and sub-feature variance.

5. The method according to any one of claims 2 to 4, wherein the inputting the operation state information into the vibration model of the automobile, outputting the road surface height of the road on which the automobile has traveled, comprises:

inputting the operation state information a (t) to the deviceIn a vibration model of an automobile, outputting a road surface height h (t) of a road on which the automobile has traveled, wherein the vibration model is: h (t) =f ^-1 (a(t))。

6. The method according to any one of claims 1 to 5, wherein the operation state information includes one or more of acceleration information and speed information.

7. The method of any one of claims 1 to 6, wherein the current location of the car comprises one or more of a heave location and a location with a roughness greater than a roughness threshold.

8. An automobile positioning device, comprising:

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring running state information of an automobile, and the running state information is used for representing the state information of the automobile in the running process;

A first determining unit configured to determine a surface feature of a road on which the automobile has traveled, based on running state information of the automobile, the surface feature of the road on which the automobile has traveled being used to represent one or more of a surface relief condition and a surface roughness of the road on which the automobile has traveled;

and the second determining unit is used for determining the current position of the automobile according to the surface characteristics of the road on which the automobile is driven and preset surface characteristics, wherein the preset surface characteristics comprise the mapping relation between the road and the surface characteristics.

9. The apparatus of claim 8, wherein the first determining unit comprises:

the input/output subunit is used for inputting the running state information into the vibration model of the automobile and outputting the road surface height of the road on which the automobile runs;

a determining subunit, configured to determine a change of a road surface height of a road on which the automobile has traveled along with a distance according to the road surface height of the road on which the automobile has traveled and the running state information;

and the characteristic matching subunit is used for matching the road surface characteristics of the road on which the automobile runs according to the change of the road surface height of the road on which the automobile runs along with the change of the distance, so as to obtain the surface characteristics of the road on which the automobile runs.

10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,

the characteristic matching sub-unit is specifically configured to perform top-layer characteristic matching on the road on which the automobile has traveled according to the change of the road surface height of the road on which the automobile has traveled along with the change of the distance, so as to obtain the top-layer road surface characteristic of the road on which the automobile has traveled; and performing sub-feature matching on the road on which the automobile runs according to the top road surface feature of the road on which the automobile runs, so as to obtain the sub-road surface feature of the road on which the automobile runs.

11. The apparatus of claim 10, wherein the top level road surface features include one or more of a number of sub-features, a top level feature frequency distribution, a top level feature maximum amplitude, a top level feature average amplitude, and a top level feature variance;

the sub-road surface features include one or more of sub-feature separation distance, sub-feature duration distance, sub-feature frequency distribution, sub-feature maximum amplitude, sub-feature average amplitude, and sub-feature variance.

12. The device according to any one of claims 9-11, characterized by an input output subunit for inputting the running state information into a vibration model of the car, outputting the road surface height of the road on which the car has run, in particular:

Inputting the running state information a (t) into a vibration model of the automobile, and outputting the road surface height h (t) of a road on which the automobile has run, wherein the vibration model is as follows: h (t) =f ^-1 (a(t))。

13. The apparatus according to any one of claims 8 to 12, wherein the operation state information includes one or more of acceleration information and velocity information.

14. The apparatus of any one of claims 8 to 13, wherein the current location of the vehicle comprises one or more of a heave location and a location with a roughness greater than a roughness threshold.

15. An automobile positioning device, comprising: a processor; the processor being operative to invoke program instructions in the memory to perform corresponding functions in the method as claimed in any of claims 1 to 7.

16. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein program instructions, which when run on a computer or a processor, cause the computer or the memory to perform the method of any of claims 1 to 7.

17. A computer program product comprising instructions which, when run on a computer or processor, cause the computer or processor to perform the method of any of claims 1 to 7.