Positioning method and device for memory parking function

Abstract

The invention belongs to the technical field of automobile positioning, and particularly relates to a positioning method and device for a memory parking function, and the method comprises the steps: storing power-off positioning information before a vehicle is powered off; acquiring a relative pose of the vehicle relative to the power-off positioning information when the vehicle is in cold start; correcting the power-off positioning information based on the relative pose to obtain self-vehicle coarse positioning information; acquiring local map semantic feature information based on the vehicle coarse positioning information; and acquiring environment perception information and matching the environment perception information with the local map semantic feature information to obtain self-vehicle fine positioning information at the current moment. The problem that the memory parking function cannot be normally operated after the vehicle is moved in the cold start process is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automobile positioning, and particularly relates to a positioning method and device for a memory parking function. BACKGROUND

[0002] The realization of the memory parking function depends on the matching of perception information and a memory map stored at the vehicle end to obtain the accurate position of the vehicle on the memory map, which can solve the problem of the user parking into a parking space, powering off the vehicle, and then powering on the vehicle the next day.

[0003] When the vehicle is powered off and then powered on, the cold start process takes a long time, and during this period, the perception and positioning algorithms cannot run, and the intelligent driving function cannot be used. Therefore, after the cold start is completed, the positioning module loads the memory information stored before the vehicle is powered off (which generally includes environmental perception, vehicle position, and function state information before the vehicle is powered off), and then combines the perception output information to complete the matching positioning.

[0004] The main problem of the prior art is that once the vehicle is moved during the cold start process, the information stored before the vehicle is powered off is loaded again after the cold start is completed. At this time, the environment and position before the vehicle is powered off are inconsistent, and although the module algorithm has run, it cannot output the correct positioning result, which will cause the memory parking function to fail to operate normally. SUMMARY

[0005] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a positioning method and device for a memory parking function, which solves the problem that the memory parking function cannot operate normally after the vehicle is moved during the cold start process.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions.

[0007] The present application provides a positioning method for a memory parking function, which comprises the following steps: storing power-off positioning information before the ego vehicle is powered off; acquiring the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started; correcting the power-off positioning information based on the relative pose to obtain coarse positioning information of the ego vehicle; acquiring local map semantic feature information based on the coarse positioning information of the ego vehicle; acquiring environmental perception information and matching the environmental perception information with the local map semantic feature information to obtain precise positioning information of the ego vehicle at the current time.

[0008] As an embodiment of the present application, the step of acquiring the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started comprises the following steps: When the ego vehicle is cold started, the relative pose of the ego vehicle relative to the power-off positioning information is estimated based on the chassis wheel speed, wheel rotation angle and IMU sensor information.

[0009] As an embodiment of the present application, the relative pose of the ego vehicle relative to the power-off positioning information is estimated based on the chassis wheel speed, wheel rotation angle and IMU sensor information when the ego vehicle is cold started, comprising: The ego vehicle safety control unit deploys a pose estimation algorithm; When the ego vehicle is cold started, the safety control unit communicates with the chassis steering system and the brake system; The chassis wheel speed, wheel rotation angle and IMU sensor information are obtained; The relative pose of the ego vehicle relative to the power-off positioning information is estimated based on the chassis wheel speed, wheel rotation angle and IMU sensor information through the pose estimation algorithm, and the relative pose includes the direction of the vehicle head, the left side direction, the direction of the roof and the included angle relative to the three directions.

[0010] As an embodiment of the present application, the power-off positioning information is corrected based on the relative pose to obtain the coarse positioning information of the ego vehicle, comprising: The ego vehicle system end deploys a position correction algorithm; The relative pose is sent to the ego vehicle system end; The ego vehicle system end corrects the power-off positioning information based on the relative pose through the position correction algorithm to obtain the coarse positioning information of the ego vehicle.

[0011] As an embodiment of the present application, the environment perception information is obtained and matched with the local map semantic feature information to obtain the fine positioning information of the ego vehicle at the current time, comprising: The ego vehicle system end deploys a repositioning algorithm; The ego vehicle system end obtains the environment perception information, and matches the perception environment information with the local map semantic feature information based on the coarse positioning information of the ego vehicle to obtain the fine positioning information of the ego vehicle on the memory map at the current time.

[0012] As an embodiment of the present application, after obtaining the environment perception information and matching it with the local map semantic feature information to obtain the fine positioning information of the ego vehicle at the current time, it further comprises: The ego vehicle system end updates the fine positioning information of the ego vehicle at the next time based on the fine positioning information of the ego vehicle at the current time.

[0013] The second aspect of the present application provides a positioning device for a memory parking function, comprising a system end and a control end; wherein: The power-off positioning information is stored by the system end before the ego vehicle is powered off; The relative pose of the ego vehicle relative to the power-off positioning information is obtained by the control end when the ego vehicle is cold started; The system end corrects the power-off positioning information based on the relative pose to obtain coarse positioning information of the ego vehicle; The system end obtains local map semantic feature information based on the coarse positioning information of the ego vehicle; The system end obtains environment perception information and matches the local map semantic feature information to obtain fine positioning information of the ego vehicle at the current time.

[0014] As an embodiment of the present application, the positioning device for the memory parking function further comprises a sensor end, and when the ego vehicle is cold started, the control end estimates the relative pose of the ego vehicle relative to the power-off positioning information based on the sensing information provided by the sensor end.

[0015] The third unit of the present application provides a positioning device for a memory parking function, comprising: A storage unit at least for storing power-off positioning information before the ego vehicle is powered off; A pose acquisition unit at least for acquiring the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started; A coarse positioning unit of the ego vehicle at least for correcting the power-off positioning information based on the relative pose to obtain coarse positioning information of the ego vehicle; A local map acquisition unit at least for obtaining local map semantic feature information based on the coarse positioning information of the ego vehicle; A fine positioning unit of the ego vehicle at least for obtaining environment perception information and matching the local map semantic feature information to obtain fine positioning information of the ego vehicle at the current time.

[0016] The fourth aspect of the present application provides an electronic device, comprising: At least one processor; and at least one memory connected in communication with the processor, wherein: the memory stores program instructions executable by the processor, and the processor invoking the program instructions can execute the steps of the method according to the first aspect of the present application.

[0017] The fifth aspect of the present application provides a readable storage medium storing a computer program, which is executed by a processor to execute the steps of the method according to the first aspect of the present application.

[0018] In summary, compared with the prior art, the present application has at least one of the following beneficial technical effects: 1. The present application can correct the power-off positioning information of the ego vehicle by acquiring the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started, which can avoid the problem that the vehicle positioning algorithm cannot run during the intelligent driving SOC starting process after the vehicle is powered off, and the present application has low requirements for the computing power of the ego vehicle and does not need to perform point cloud matching, so that the position correction can be realized in a relatively simple way. 2.The application can complete the matching process of the sensing element and the map element through the revised initial position, output the accurate map position of the vehicle, support the normal operation of the function, and improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 It is a schematic diagram of route position change before and after cold start of the ego vehicle.

[0021] Figure 2 It is a flowchart of a positioning method for memory parking function in an embodiment of the present application.

[0022] Figure 3 It is a flowchart of another positioning method for memory parking function in an embodiment of the present application.

[0023] Figure 4 It is a flowchart of another positioning method for memory parking function in an embodiment of the present application.

[0024] Figure 5 It is a principle diagram of relative pose of the ego vehicle in an embodiment of the present application.

[0025] Figure 6 It is a display diagram of relative pose of the ego vehicle in an embodiment of the present application.

[0026] Figure 7 It is a block diagram of a positioning device for memory parking function in an embodiment of the present application.

[0027] Figure 8 It is a structural schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application. In addition, it should be understood that the specific embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0029] It should be noted that the sequence of the following embodiments is not as a limitation on the preferred sequence of the embodiments of the present application. And in the following embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0030] On-chip systems, microcontrollers and inertial measurement units are used in autonomous vehicles.

[0031] System on Chip (SOC) refers to integrating multiple functional modules on a single chip to form a complete system, i.e. system-level chip, which is widely used in many fields such as the intelligent driving domain controller SOC in the present application, providing core operation and control capabilities for the device with high computing power. The time required for the SOC chip running the intelligent driving system to start up is called cold start.

[0032] Microcontroller Unit (MCU) has relatively low computing power and is widely used in many fields such as the intelligent driving domain controller MCU or safety control unit MCU in the present application.

[0033] Inertial Measurement Unit (IMU) is a sensor device that can measure the acceleration and angular velocity of an object, mainly composed of an accelerometer, a gyroscope and sometimes a magnetometer. The accelerometer is used to measure the acceleration of the object in three axial directions (usually x, y, z axes), the gyroscope is used to measure the angular velocity of the object around the three axes, and the magnetometer (if any) is used to measure the magnetic field strength and direction to assist in determining the attitude of the object.

[0034] The high-level intelligent driving function of autonomous vehicles includes the memory parking function (or valet parking function), which aims to help users automatically drive from the entrance of the parking lot to the parking space and automatically drive from the parking space to the exit of the parking lot.

[0035] In the memory parking or valet parking function, the user needs to manually drive to scan and map the parking lot. The system records the features of the parking lot such as walls, columns, parking spaces and road signs, and generates a parking lot map in combination with the driving trajectory of the vehicle. When the user enters the mapped parking lot for the second time, the system determines that the user enters the parking lot and determines the initial position of the vehicle in the parking lot. The local parking lot map features are loaded at this position, matched with the real-time perceived environmental features, and the accurate map coordinates of the vehicle are obtained. The coordinates are used as the initial position at the next time, and the perceived environmental features at the next time are used to iteratively update the position of the vehicle in the current parking lot map. Thus, the system knows the accurate position of the vehicle in the parking lot map, controls the vehicle to drive according to the remembered route, reaches the target parking position, and automatically parks in the parking space. Conversely, the vehicle automatically parks out of the parking space and drives to the end of the remembered route, such as the parking lot exit. The core key technology is to obtain the accurate position of the vehicle in the parking lot.

[0036] The scenario of driving out of the parking space to the parking lot exit often occurs the next day after the user turns off the power and locks the vehicle. During this process, the vehicle is powered off, and the intelligent driving system generally needs to store the positioning information when powered off and load the stored information when powered on to support the normal operation of the function.

[0037] However, in real life, the SOC chip of the intelligent driving system needs time (referred to as cold start) to start up, and the time is about 0.5-1 min. During this period, the driver can move the vehicle, but the intelligent driving algorithm still loads the stored information before the power is turned off after the SOC cold start is completed, which causes the actual position of the vehicle to be inconsistent with the stored information loaded by the intelligent driving system at the initial operation, resulting in that the subsequent function cannot be normally used.

[0038] As shown in Figure 1 , the vehicle stores the P position information of the vehicle in the map (i.e., the power-off positioning information stored before the vehicle is powered off as described below) before the vehicle is powered off. After the vehicle is powered on, the vehicle moves during the cold start process of the intelligent driving system. When the system cold start is completed, the actual position of the vehicle is at the P'0 position in the map, but the positioning algorithm mistakenly believes that the vehicle is still at the P position. The map feature elements are loaded according to the P position and matched with the perceived information, and the correct positioning result of the vehicle in the map cannot be output.

[0039] The common solution to the above problems is to keep the power supply of the intelligent driving sensors and domain controllers after the vehicle is turned off, so that the positioning algorithm continuously runs and outputs the position of the vehicle in the map. The user feels that the vehicle can immediately operate the function after the vehicle is powered on. The biggest disadvantage of this method is the increase of the energy consumption of the whole vehicle, especially in the case of long parking time, which has a negative impact on the cruising of new energy vehicles. Or after the vehicle is powered on, the driver is prompted to wait during the system cold start, and the function can be used. This method will reduce the user experience.

[0040] In view of this, as shown in Figures 2-4 The first aspect of the present application provides a positioning method for a memory parking function, comprising the following steps.

[0041] Step S100: store the power-off positioning information before the ego vehicle is powered off, wherein the power-off positioning information comprises the position of the ego vehicle in the map Figure 1

[0042] The memory parking function is a function provided by high-level autonomous vehicles, and its function implementation depends on the matching of perception information and the memory map stored by the vehicle to obtain the accurate position of the vehicle in the memory map, which is the basis for the function to run. The implementation of the above basis requires the operation of the intelligent driving perception module and the positioning module of the high-level autonomous vehicle. Generally, the intelligent driving domain controller mainly includes a system-on-chip (SOC) and a micro control unit (MCU), and the perception and positioning algorithms run in the system-on-chip (SOC).

[0043] Step S200: obtain the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started.

[0044] Specifically, the representation of the relative pose is represented by , wherein the front direction is x, the left direction is y, the top direction is z, and the included angles of the three directions are roll, pitch, and yaw.

[0045] For example, the present application relies on the safety control unit to deploy a simple pose estimation algorithm to obtain the relative pose of the ego vehicle relative to the power-off positioning information. Compared with the SOC, the pose estimation algorithm deployed in the safety control unit has relatively low requirements for position accuracy / heading accuracy.

[0046] Step S300: correct the power-off positioning information based on the relative pose to obtain the coarse positioning information of the ego vehicle, wherein the coarse positioning information of the ego vehicle is also referred to as the initialization position information of the ego vehicle.

[0047] Step S400: obtain the local map semantic feature information based on the coarse positioning information of the ego vehicle.

[0048] Step S500: obtain the environment perception information and match it with the local map semantic feature information to obtain the precise positioning information of the ego vehicle at the current time.

[0049] Here, the present application completes the matching process of perception elements and map elements through the corrected power-off positioning information to output the accurate map position of the vehicle, which can support the normal operation of functions such as memory parking.

[0050] ​In an embodiment of the present application, the relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started is obtained by: when the ego vehicle is cold started, estimating the relative pose of the ego vehicle relative to the power-off positioning information based on chassis wheel speed, wheel rotation angle, and IMU sensor information.

[0051] Specifically, as shown in Figures 5-6 The relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started is estimated based on chassis wheel speed, wheel rotation angle, and IMU sensor information, including: The ego vehicle safety control unit deploys a pose estimation algorithm. When the ego vehicle is cold started, the safety control unit communicates with the chassis steering system and the braking system through CAN, wherein the wheel speed / wheel rotation angle information and the IMU information can be quickly obtained within 1 second after the vehicle is powered on through CAN communication; chassis wheel speed, wheel rotation angle, and IMU sensor information are obtained. The relative pose of the ego vehicle relative to the power-off positioning information is estimated based on chassis wheel speed, wheel rotation angle, and IMU sensor information through a pose estimation algorithm, and the relative pose includes the direction of the vehicle head, the direction of the left side, the direction of the roof, and the included angle of the three directions, with the center of the rear axle of the vehicle as the origin.

[0052] Specifically, after the MCU cold start is completed, the vehicle lateral speed and longitudinal speed can be obtained based on the vehicle wheel speed and wheel rotation angle with the center of the rear axle of the vehicle as the coordinate origin when the vehicle is powered on, and the vehicle's heading angle can be estimated through time integration of the wheel rotation angle and the IMU yaw rate, and the above can obtain the estimated result of the ego vehicle (x, y, yaw).

[0053] Further, the (z, pitch, roll) information of the ego vehicle is obtained by time integration of the vertical acceleration and angular velocity around the x&y axis based on the IMU.

[0054] Here, the relative pose of the ego vehicle relative to the power-off positioning information can be obtained in this way.

[0055] In an embodiment of the present application, the relative pose is used to correct the power-off positioning information to obtain the coarse positioning information of the ego vehicle, including: A position correction algorithm is deployed at the ego vehicle system end. The relative pose is sent to the ego vehicle system end. The ego vehicle system end corrects the power-off positioning information based on the relative pose through the position correction algorithm to obtain the coarse positioning information of the ego vehicle.

[0056] Specifically, the ego vehicle system end is the SOC end, and the relative pose corrects the power-off positioning information to obtain the coarse positioning information of the ego vehicle in a manner

[0057] In an embodiment of the present application, the obtaining of the environment perception information and the matching with the local map semantic feature information to obtain the self-vehicle fine positioning information at the current time comprises: deploying a repositioning algorithm at the self-vehicle system end; the self-vehicle system end obtains the environment perception information, and matches the perception environment information with the local map semantic feature information based on the self-vehicle coarse positioning information to obtain the self-vehicle fine positioning information at the current time on the memory map.

[0058] Further, after the obtaining of the environment perception information and the matching with the local map semantic feature information to obtain the self-vehicle fine positioning information at the current time, further comprising: the self-vehicle system end updates the self-vehicle fine positioning information at the next time based on the self-vehicle fine positioning information at the current time.

[0059] Considering that in the prior art, after the vehicle is powered off and then powered on again, the positioning algorithm cannot run during the cold start process of the intelligent driving SOC, and the storage position of the algorithm loading before the power-off after the cold start is completed is not the actual position of the self-vehicle, the present application utilizes the relatively short cold start time of the MCU chip to deploy a self-vehicle pose estimation module at the MCU end, and when the SOC cold start is completed and the positioning module loads the storage information before the power-off, the pose information output by the MCU is referred to to correct the information stored before the power-off, so that the corrected storage information matches the actual position of the vehicle, and based on this premise, the positioning and perception module algorithms complete the positioning matching to support the normal use of functions.

[0060] In a second aspect of the present application, a positioning device for a memory parking function comprises a system end and a control end, wherein: the system end stores the power-off positioning information before the self-vehicle is powered off; the control end obtains the relative pose of the self-vehicle relative to the power-off positioning information when the self-vehicle is cold started; the system end corrects the power-off positioning information based on the relative pose to obtain the self-vehicle coarse positioning information; the system end obtains the local map semantic feature information based on the self-vehicle coarse positioning information; the system end obtains the environment perception information and matches the perception environment information with the local map semantic feature information to obtain the self-vehicle fine positioning information at the current time.

[0061] In an embodiment of the present application, the control end estimates the relative pose of the self-vehicle relative to the power-off positioning information based on the sensing information provided by the sensor end when the self-vehicle is cold started. The sensing information includes but is not limited to chassis wheel speed, wheel rotation angle and IMU sensor information.

[0062] Specifically, in the present application, the module for estimating the relative pose of the ego vehicle relative to the power-off positioning information at the control end is specifically a pose estimation module. Exemplarily, the control end is specifically an MCU, and the pose estimation module can output the rough pose of the ego vehicle when the vehicle is powered on, i.e., a pose estimation algorithm.

[0063] Specifically, the rough positioning information and the precise positioning information of the ego vehicle obtained by the system end can assist the positioning algorithm module to obtain. Exemplarily, the system end is specifically an SOC, and the positioning algorithm module is arranged in the SOC and can normally output only after the SOC cold start is completed. The ego vehicle pose output by the positioning algorithm module has higher accuracy. The task of the positioning algorithm module includes two parts: 1. ego vehicle positioning: calculating a relative pose (relative to the position when the cold start is completed) with higher accuracy, i.e., a position correction algorithm; and 2. repositioning: obtaining the accurate pose of the ego vehicle in the map based on the perception input information and the map information, i.e., a repositioning algorithm.

[0064] Here, the system end and the control end are distinguished according to the time when the cold start is completed and the computing power, and the sensor end is combined with the sensing information. The pose is obtained in the control end in which the cold start is completed earlier, and the position correction and the feature information matching are implemented in the control end in which the cold start is completed later, so as to finally obtain the precise positioning information of the ego vehicle at the current time.

[0065] As shown in the first aspect of the present application, Figure 7 As shown in the first aspect of the present application, a storage unit, at least for storing power-off positioning information before the ego vehicle is powered off; a pose acquisition unit, at least for acquiring a relative pose of the ego vehicle relative to the power-off positioning information when the ego vehicle is cold started; an ego vehicle rough positioning unit, at least for correcting the power-off positioning information based on the relative pose to obtain ego vehicle rough positioning information; a local map acquisition unit, at least for acquiring local map semantic feature information based on the ego vehicle rough positioning information; an ego vehicle precise positioning unit, at least for acquiring environment perception information and matching the local map semantic feature information to obtain the precise positioning information of the ego vehicle at the current time.

[0066] Based on the same idea as the method in the above embodiment, the device provided by the present application can implement the method of the above embodiment. For the convenience of description, only the part related to the embodiment of the present application is shown in the structure diagram of the device embodiment, and those skilled in the art can understand that the structure shown in the diagram does not limit the device, and the device can include more or fewer components than those shown in the diagram, or some components can be combined, or different components can be arranged.

[0067] As shown in the first aspect of the present application, Figure 8 As shown in the first aspect of the present application, at least one memory connected with the processor, wherein: the memory stores program instructions executable by the processor, and the processor invoking the program instructions can execute steps of the method according to any one of the above embodiments.

[0068] The fifth aspect of the present application discloses a readable storage medium, which stores a computer program, and the computer program is executed by a processor to execute steps of the method according to any one of the above embodiments.

[0069] The computer readable storage medium can include any entity or device capable of carrying the computer program, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), software distribution medium, etc. The computer program includes computer program code. The computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer readable storage medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), software distribution medium, etc.

[0070] Any process or method descriptions, or steps of the flow diagrams described herein, can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) of the above described embodiments, and that the modules can be implemented by hardware, software, firmware or any combination thereof. The various embodiments and implementations of the present application can be realized in electronic hardware, computer software, or any combination thereof. Any resulting implementation, whether software or hardware, can be realized as a stand-alone or integrated system comprising the described logic, steps, and / or components.

[0071] The logic and / or steps represented in the flow diagrams described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination thereof.

[0072] The above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A positioning method for a parking memory function, characterized in that, include: Store power-off location information before the vehicle is powered off; During a cold start, the relative pose of the vehicle with respect to the power-off positioning information is obtained. Based on the relative pose correction power-down positioning information, the vehicle coarse positioning information is obtained; Local map semantic feature information is obtained based on the vehicle coarse positioning information; By acquiring environmental perception information and matching it with local map semantic feature information, the vehicle's precise positioning information at the current moment can be obtained.

2. The positioning method for memory parking function according to claim 1, characterized in that, The process of acquiring the relative pose of the vehicle with respect to the power-off positioning information during a cold start includes: During a cold start, the relative pose of the vehicle with respect to the power-off positioning information is estimated based on chassis wheel speed, wheel rotation angle, and IMU sensor information.

3. The positioning method for memory parking function according to claim 2, characterized in that, The method of estimating the relative pose of the vehicle with respect to the power-off positioning information based on chassis wheel speed, wheel rotation angle, and IMU sensor information during a cold start includes: Deploy pose estimation algorithms in the vehicle's safety control unit; During a cold start of the vehicle, the safety control unit communicates with the chassis steering system and braking system; Acquire chassis wheel speed, wheel rotation angle, and IMU sensor information; The relative pose of the vehicle relative to the power-off positioning information is estimated by a pose estimation algorithm based on chassis wheel speed, wheel rotation angle and IMU sensor information. With the rear axle center of the vehicle as the origin, the relative pose includes the front direction, the left direction, the roof direction and the included angle between the three directions.

4. The positioning method for memory parking function according to claim 1, characterized in that, The process of obtaining coarse vehicle positioning information based on relative pose correction of the power-on positioning information includes: Deploy a position correction algorithm on the vehicle system side; Send the relative pose to the vehicle system. The vehicle system uses a position correction algorithm based on relative pose to correct the power-off positioning information and obtain coarse positioning information for the vehicle.

5. The positioning method for memory parking function according to claim 1, characterized in that, The process of acquiring environmental perception information and matching it with local map semantic feature information to obtain the vehicle's precise positioning information at the current moment includes: Deploy relocation algorithms on the vehicle system side; The vehicle system acquires environmental perception information and matches the perceived environmental information with the semantic feature information of the local map based on the vehicle's coarse localization information to obtain the vehicle's fine localization information on the memory map at the current moment.

6. The positioning method for memory parking function according to claim 5, characterized in that, After acquiring environmental perception information and matching it with local map semantic feature information to obtain the vehicle's precise localization information at the current moment, the process also includes: The vehicle system updates its precise positioning information for the next moment based on the current precise positioning information.

7. A positioning device for a parking memory function, characterized in that, include: System end and control end; where: The system stores the power-off location information before the vehicle is powered off. During a cold start of the vehicle, the control terminal obtains the relative pose of the vehicle relative to the power-off positioning information. The system corrects the power-down positioning information based on the relative pose to obtain the vehicle's coarse positioning information; The system obtains local map semantic feature information based on the vehicle coarse positioning information; The system acquires environmental perception information and matches it with local map semantic feature information to obtain the vehicle's precise positioning information at the current moment.

8. The positioning device for memory parking function according to claim 7, characterized in that, It also includes the sensor side. When the vehicle is cold-started, the control side estimates the relative pose of the vehicle with respect to the power-off positioning information based on the sensing information provided by the sensor side.

9. A positioning device for a memory parking function, characterized in that, include: The storage unit is used at least to store power-off location information before the vehicle is powered off; The pose acquisition unit is used at least to acquire the relative pose of the vehicle relative to the power-off positioning information during a cold start of the vehicle. The vehicle coarse positioning unit is used at least to correct the power-down positioning information based on the relative pose to obtain the vehicle coarse positioning information. The local map acquisition unit is at least used to acquire local map semantic feature information based on the vehicle coarse positioning information; The vehicle localization unit is used at least to acquire environmental perception information and match it with local map semantic feature information to obtain the vehicle localization information at the current moment.

10. An electronic device, characterized in that, include: At least one processor; And at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the steps of the positioning method for memory parking function as described in any one of claims 1-7.

11. A readable storage medium storing a computer program, characterized in that, The computer program is executed by a processor using the steps of the positioning method for memory parking function as described in any one of claims 1-7.

Images