CN114353781A - Map update method, map update device, electronic device and storage medium - Google Patents

Abstract

Embodiments of the present invention provide a map update method and device, electronic equipment, and storage medium; the map update method includes: receiving vector data and original perception data sent by a vehicle-mounted terminal; determining the map error map according to the vector data The target area in the layer; according to the vector data and the original perception data, the target area is updated to obtain an updated layer containing the updated target area. The embodiment of the present invention can quickly generate an updated map, increase the update frequency of the map, so that the data in the map is closer to the actual road conditions, the vehicle can avoid the occurrence of dangerous situations and automatic driving degradation when the vehicle uses the map for automatic driving, and improve the user experience. sense of experience.

Description

Map update method, map update device, electronic device and storage medium

technical field

The present invention relates to the technical field of high precision, in particular to a map updating method, a map updating device, an electronic device and a storage medium.

Background technique

The existing high-precision map update scheme still relies on map manufacturers to use traditional high-precision acquisition vehicles to collect data and then update it by manual editing. The acquisition cost is high, and the production cycle is long. It can only be released quarterly, and the latest version is often Because the production cycle is too long, the data has expired when it is released. The current intelligent assisted driving solutions relying on high-precision maps have high requirements on the accuracy and timeliness of the map. The map does not match the actual road, which greatly affects the user experience of intelligent assisted driving and even causes safety problems. It is necessary to speed up the map update frequency and check for temporary road maintenance failures.

SUMMARY OF THE INVENTION

In view of the above problems, embodiments of the present invention provide a map updating method, a map updating apparatus, an electronic device, and a storage medium that overcome the above problems or at least partially solve the above problems.

An embodiment of the present invention provides a map update method, which is applied to a server, where a map error layer is cached on the server, and the server is connected to a plurality of vehicle-mounted terminals, and the map update method includes:

Receive the vector data and the original perception data sent by the vehicle terminal;

Determine the target area in the map error layer according to the vector data;

According to the vector data and the original perception data, the target area is updated to obtain an updated layer including the updated target area.

Optionally, after the step of receiving the vector data and original sensing data sent by the vehicle-mounted terminal, the method further includes:

Data cleaning is performed on the vector data and the original perception data by means of cross-voting confirmation.

Optionally, the update layer includes road features, and the method further includes:

When the road feature satisfies a preset delivery condition, the update layer is delivered to the vehicle terminal, and the vehicle terminal is configured to update the map according to the update layer.

Optionally, the vector data includes semantic information, and the step of determining the target area in the map error layer according to the vector data includes:

determining data matching the semantic information in the map error layer, and generating local matching information, where the local matching information includes at least one matching position;

Find the remaining position corresponding to the matching position by sliding the closest point method;

The matching positions and the remaining positions are combined to generate a target area.

Optionally, the step of updating the target area according to the vector data and the original perception data to obtain an updated layer containing the updated target area includes:

Integrate the vector data and the original perception data by means of nonlinear optimization to generate a road model for the target area;

A logical connection relationship of the road model is established, and an update layer is generated.

Optionally, the vehicle-mounted terminal is connected to a sensor; the original perception data is generated by the sensor, and the vector data is generated by performing three-dimensional reconstruction on the original perception data.

Optionally, the method further includes:

generating driving behavior data according to the vector data and the original perception data;

On the updated map, a driving route is determined according to the driving behavior data.

An embodiment of the present invention also provides a map update device, which is applied to a server, where a map error layer is cached on the server, and the server is connected to a plurality of vehicle-mounted terminals, and the map update device includes:

a receiving module, configured to receive the vector data and the original perception data sent by the vehicle terminal;

a determination module, configured to determine the target area in the map error layer according to the vector data;

An update module, configured to update the target area according to the vector data and the original perception data to obtain an update layer including the updated target area.

An embodiment of the present invention also provides an electronic device, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to achieve the above The steps of the map update method.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned map updating method are implemented.

Embodiments of the present invention can achieve at least one of the following advantages:

The present invention receives the vector data and the original perception data sent by the vehicle terminal; the server directly obtains the original information and vector data, and can use sufficient computing power to perform various complex optimization algorithms to obtain better maps than the vehicle terminal. As a result, it is avoided that the required accuracy cannot be achieved after accumulating multiple errors, and the transmission pressure can also be reduced;

Determine the target area in the map error layer according to the vector data; refine the map update method based on the error layer guide, determine the target area that needs to be updated, and update the map according to the vector data and the original perception data Described target area, obtain the update layer that contains the target area that has been updated;

Realize the rapid generation and update of the map, increase the update frequency of the map, and make the data in the map closer to the actual road conditions. When the vehicle uses the map for automatic driving, it can avoid the occurrence of dangerous situations and automatic driving degradation, and improve the user experience.

Description of drawings

Fig. 1 is a flow chart of steps of a method for updating a map according to an embodiment of the present invention;

2 is a flow chart of steps of another map updating method according to an embodiment of the present invention;

FIG. 3 is a structural block diagram of a map updating apparatus according to an embodiment of the present invention.

Detailed ways

In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

In the current autonomous driving technology, high-precision maps are used to provide lane information for path planning. The high-precision maps are generated by map manufacturers based on the data collected by the dedicated high-precision vehicles on the actual road, and then drawn. Therefore, the production cycle of maps is long, so that map manufacturers mostly release maps on a quarterly basis to update the maps. However, road changes such as temporary lane maintenance occur daily. When vehicles pass through these road sections, when the data collected by the sensor is inconsistent with the data in the high-precision map, it may lead to errors in the automatic driving control and cause accidents. The occurrence of these areas threatens the safety of human life, or degrades or interrupts automatic driving, relying on manual driving to pass through these areas, making the driver's experience poor.

Referring to FIG. 1 , a flow chart of steps of a method for updating a map according to an embodiment of the present invention is shown. The method is applied to a server, a map error layer is cached on the server, and the server is connected to a plurality of vehicle-mounted terminals; Wherein, the server and multiple vehicle terminals may be wirelessly connected, and the wirelessly connected networks include but are not limited to mobile communication networks, NB-IoT (Narrow Band Internet of Things, Narrow Band Internet of Things) networks, LoRa (Long Range Radio, remote range radio) networks, digital radio stations, etc. The in-vehicle terminal is a data processing unit on a mass-produced vehicle, and the mass-produced vehicle is a vehicle that is routinely used and is not dedicated to road data collection. The server is connected to multiple vehicle-mounted terminals, and can receive data sent by multiple vehicle-mounted terminals at the same time. As for the number of connected vehicle-mounted terminals, an appropriate number of connections may be set under the regulation of the maximum number of connections of the server; the embodiment of the present invention does not specifically limit the data connected to the vehicle-mounted terminals.

The map error layer records the scope of the area that needs to be repaired, and the problem classification description provides strategic guidance for repair. The range of the repaired area can be marked and determined by the on-board terminal that detects inconsistencies with the map during vehicle driving, or it can be manually added by relevant personnel. This embodiment of the present invention does not specifically limit this.

The method may specifically include the following steps:

Step 101, receiving vector data and original sensing data sent by the vehicle-mounted terminal;

During the actual driving of the vehicle, the vehicle-mounted terminal takes the data collected by the components on the vehicle for road perception as the original perception data, and performs down-sampling processing on the original perception data to generate vector data and store it in the designated storage address. The original perception data may be data collected by all components on the vehicle for road perception, or may be data collected by some components for road perception, which is not limited in this embodiment of the present invention.

When the vehicle is parked and the in-vehicle terminal remains connected to the service, the in-vehicle terminal can send the vector data and the original perception data to the server; the server receives the vector data and the original perception data sent by the in-vehicle terminal.

It should be noted that the vector data and the original sensing data sent by the vehicle terminal are sent after the consent of the user, so as to ensure the legality of the data. Wherein, the way of consent may be determined based on the authority of one consent, such as asking whether to agree to send the subsequent collected data of the vehicle before the first sending, and after the user agrees, the data collected each time will be automatically sent. The way of consent may also be successive inquiries, and the current data is sent during the current inquiry.

Step 102, determining the target area in the map error layer according to the vector data;

After receiving the vector data and the original perception data, the server can start the map update process. First, it can determine the actual location of the road collected in the vehicle terminal according to the vector data, read the cached map error layer, and display the map error layer in the map error layer. Identify target areas where updates can be made.

Step 103: Update the target area according to the vector data and the original perception data to obtain an updated layer including the updated target area.

The server fuses the vector data and the original perception data, determines the geometric model of the road that needs to be replaced in the target area, updates the target area, and obtains an updated layer containing the updated target area, so as to realize the rapid generation of the map update part, which is convenient for The map is updated in time.

The present invention receives the vector data and the original perception data sent by the vehicle terminal; the server directly obtains the original information and vector data, and can use sufficient computing power to perform various complex optimization algorithms to obtain better maps than the vehicle terminal. As a result, it is avoided that the required accuracy cannot be achieved after accumulating errors for many times, and the transmission pressure can also be reduced; the target area in the map error layer is determined according to the vector data; based on the guidance of the error layer, the map update method is refined to determine Obtain the target area that needs to be updated, update the target area according to the vector data and the original perception data, and obtain an updated layer containing the updated target area; realize the rapid generation of the updated map, and improve the update frequency of the map, so that The data in the map is closer to the actual road conditions. When the vehicle uses the map to drive automatically, it can avoid the occurrence of dangerous situations and the degradation of automatic driving, and improve the user's experience.

Referring to FIG. 2 , there is shown a flow chart of the steps of another map update method according to an embodiment of the present invention, which is applied to a server, where a map error layer is cached, and the server is connected to a plurality of vehicle-mounted terminals.

In practical applications, the server may be a cloud server connected to a vehicle-mounted terminal. The vehicle-mounted terminal is a vehicle-mounted terminal on a mass-produced vehicle, and the mass-produced vehicle is equipped with road recognition sensors such as vision sensors, lidars It is also equipped with a locator that detects the position of mass-produced vehicles. The cloud server can receive crowdsourced data sent by multiple in-vehicle terminals.

A map error layer is cached on the cloud server, and the map error layer will provide the area range that needs to be repaired and the problem classification description to provide policy guidance for repairing, and the update process will perform different processing methods according to the problem classification.

The method specifically includes the following steps:

Step 201, receiving vector data and original sensing data sent by the vehicle-mounted terminal;

During the driving process of the vehicle, the vehicle-mounted terminal will perform vectorization processing according to the road data sensed by the sensors on the vehicle in real time, generate various vector data, and save the original perception data sensed by the sensor in the local memory of the vehicle-mounted terminal; When the terminal confirms that the vehicle is in the state of parking and charging, it sends the vector data in the local memory and the original perception data to the cloud server through the data transmission link established with the cloud server. After the transmission is completed, the vector data and the original sensing data in the local memory can be deleted in the local memory to reduce the storage pressure of the local memory; they can also be continuously stored in the local memory, which is not further limited in this embodiment of the present invention.

Furthermore, since there are many sensors on the vehicle, and the information of some sensors is redundant data for the map update process, the on-board terminal can only send part of the original sensing data to reduce the transmission pressure with the cloud server.

Specifically, the in-vehicle terminal is connected to a sensor on the vehicle; the sensor is a sensor that can detect the road environment around the vehicle; in an example of the present invention, the sensor includes a camera and a locator; the raw The sensory data generates data by detecting the road environment around the vehicle by the sensor. For example, when the sensor is a camera, the data generated by collecting lane lines and various road surface elements around the vehicle is the original perception data; when the sensor is a locator, the positioning information of the vehicle on the road is the original perception data. The vector data is generated by performing 3D reconstruction (3D Reconstruction) on the original perception data. For example, various vector data are generated after 3D reconstruction based on the lane lines and various road elements perceived by the camera in real time.

The cloud server always receives the vector data and the original perception data sent by each vehicle terminal for subsequent map update processing.

Step 202, performing data cleaning on the vector data and the original perception data by means of cross-voting confirmation;

After the cloud server receives the vector data and the original perception data, the error of the original perception data may be distorted due to differences in hardware capabilities of each vehicle terminal or differences in the actual operating environment, and the vector data may be distorted due to differences in the vehicle terminal's hardware capabilities or actual operating environment. There is an error in the limitation of computing resources, resulting in a conflict or a large deviation between the vector data received by the cloud server and the original sensory data. Cloud services can perform data cleaning through cross-voting confirmation based on big data to obtain correct data before entering the subsequent map update process. The cross-voting method is to compare the data of a plurality of vehicle-mounted terminals, and use the one with a larger number as the correct data.

For example, when the cloud server receives the vector data and the original perception data detected for the same road environment sent by the three vehicle-mounted terminals, and performs cross-voting, when the vector data of the first vehicle-mounted terminal and the second vehicle-mounted terminal are within a predetermined deviation When it is within the range, it can be determined that the vector data of the first terminal and the second vehicle-mounted terminal are correct data. When the vector data of the first vehicle-mounted terminal and the second vehicle-mounted terminal exceed the predetermined deviation range, that is, one of the vector data in the first vehicle-mounted terminal and the second vehicle-mounted terminal is noise data, the vector data of the third vehicle-mounted terminal is introduced, respectively. Determine the deviation range from the vector data of the first vehicle-mounted terminal and the second vehicle-mounted terminal. When the vector data of the first vehicle-mounted terminal and the third vehicle-mounted terminal are within the deviation range, determine the vector data of the first vehicle-mounted terminal and the third vehicle-mounted terminal. The data is correct data, and the vector data of the second vehicle-mounted terminal is filtered out.

Step 203, determining the target area in the map error layer according to the vector data;

When the cloud server enters the map update process, it can first use the vector data sent by the vehicle terminal to match the map error layer to determine the target area for update.

In an optional embodiment of the present invention, the vector data includes semantic information, and the step of determining the target area in the map error layer according to the vector data includes:

Sub-step S2031, determine the data in the map error layer that matches the semantic information, and generate local matching information, where the local matching information includes at least one matching position;

The vector data includes semantic information, and the actual road markers corresponding to the data are identified by the semantic information, such as lane lines, speed limit signs, and the like.

Completely credible local matching information is determined by comparing the semantic information with the data in the map error layer, wherein the local matching information must include at least one matching position.

For example, if the semantic information is the left lane line of the second lane on the left, it is compared with the data in the map error layer one by one to determine the left lane line of the second left lane in the map error layer.

Sub-step S2032, find the remaining position corresponding to the matching position by sliding iterative closest point method;

Then, based on the matching position, the corresponding remaining position is found by sliding iteratively closest point (ICP, IterativeClosest Point) in a forward or reverse direction. Further, the matching relationship between the remaining positions and the lane lines in the map error layer can also be performed.

Sub-step S2033, combine the matching position and the remaining position to generate a target area.

Combining the matching location and the area where the remaining locations are located determines the target area that can be updated.

Step 204, according to the vector data and the original perception data, update the target area to obtain an updated layer containing the updated target area;

After determining the target area that can be updated, the vector data and the original perception data can be used for fusion to generate the corresponding road model to update the target area, and obtain an update layer containing the updated target area.

In an optional embodiment of the present invention, the step of updating the target area according to the vector data and the original sensory data to obtain an updated layer including the updated target area includes:

Sub-step S2041, using nonlinear optimization to fuse the vector data and the original perception data to generate a road model for the target area;

In practical applications, the vector data and the original perception data are fused by nonlinear optimization to generate a road model of the road geometry part to be replaced in the target area, and the road model includes at least one lane geometry data. A person skilled in the art may select a specific processing algorithm for nonlinear optimization according to actual requirements, which is not specifically limited in this embodiment of the present invention.

In sub-step S2042, the logical connection relationship of the road model is established, and an update layer is generated.

The road model is established, which is just an island-like geometric model. Therefore, it is necessary to establish a logical connection relationship with the road model of the unnecessary replacement part, so that the road model generated this time can be correctly spliced with other road models, and an update layer is generated. , wherein the update layer includes road features.

Step 205: When the road feature meets a preset delivery condition, deliver the update layer to the vehicle-mounted terminal, and the vehicle-mounted terminal is configured to update the map according to the update layer.

After obtaining the updated layer, the cloud server may further judge the updated layer to determine whether the road feature satisfies the preset delivery conditions. When the road features meet the preset delivery conditions, the updated layer will be delivered to the vehicle terminal, and the vehicle terminal will then update the updated layer and the relevant part of the unupdated high-precision map to generate an updated high-precision map.

When the road features do not meet the preset delivery conditions, the updated layer may only have temporary road changes such as temporary maintenance status switching of some roads. Therefore, the updated layer may not be delivered to the vehicle terminal to reduce the map Update frequency to reduce verification cost.

The preset delivery condition may be a judgment condition about timeliness. For example, the data of the updated layer needs to be the latest information of the current road section, for example, there is a large delay between the generated vector data of the updated layer and the original perception data. After the cloud server receives the update layer and generates the corresponding update layer, if there is an update layer updated in the same target area, the update layer generated this time will not be delivered. The preset delivery condition can also be a judgment condition related to whether the road feature has a temporary state of the road. For example, a road in the updated layer is temporarily closed, and this closure will be canceled in a short period of time; therefore, the following The delivery condition is set to whether there is no temporary road state. When there is no temporary road status, the update layer is determined to be delivered; when there is a temporary road status, the update layer is not delivered, so as to avoid the need to repeatedly deliver the updated layer when the temporary road status is cancelled. Update layers.

In an optional embodiment of the present invention, the method further includes:

Step S1, generating driving behavior data according to the vector data and the original perception data;

In practical applications, the cloud server can determine the lane and road where the vehicle travels during the driving process according to the vector data and the original perception data, and generate driving behavior data.

Step S2, on the updated map, determine a driving route according to the driving behavior data.

According to the user's driving behavior data, the user's driving preference is determined to learn the user's common driving mode; on the updated map, when performing automatic driving, the driving path of the automatic driving can be determined according to the driving behavior data, so that the automatic driving is more in line with the User driving habits.

In the embodiment of the present invention, by receiving the vector data and the original perception data sent by the vehicle terminal; the server directly obtains the original information and vector data, and sufficient computing power can be used to perform various complex optimization algorithms to obtain more efficient maps than the vehicle terminal fusion map. A good result can avoid the inability to achieve the required accuracy after accumulating multiple errors, and can also reduce the transmission pressure. Data cleaning is performed on the vector data and the original perception data by means of cross-voting confirmation, noise data is filtered out, and the accuracy of map update is improved. Determine the target area in the map error layer according to the vector data; refine the map update method based on the error layer guide, determine the target area that needs to be updated, and update the map according to the vector data and the original perception data In the target area, an update layer containing the updated target area is obtained; the rapid generation of the updated map is realized, and the update frequency of the map is increased, so that the data in the map is closer to the actual road situation, and the vehicle uses the map for automatic driving. It can avoid the occurrence of dangerous situations and the degradation of automatic driving, and improve the user's experience. And when the road features meet the preset delivery conditions, the updated layer is delivered to the vehicle terminal, thereby reducing the cost of map verification.

It should be noted that, for the sake of simple description, the method embodiments are described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequences, because According to embodiments of the present invention, certain steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

Referring to FIG. 3 , a block diagram of a map update device according to an embodiment of the present invention is shown, the device is applied to a server, a map error layer is cached on the server, and the server is connected to a plurality of vehicle-mounted terminals;

The device may specifically include the following modules:

a receiving module 301, configured to receive the vector data and the original perception data sent by the vehicle terminal;

A determination module 302, configured to determine the target area in the map error layer according to the vector data;

An update module 303, configured to update the target area according to the vector data and the original perception data, to obtain an update layer including the updated target area.

In an optional embodiment of the present invention, the apparatus further includes:

A data cleaning module, configured to perform data cleaning on the vector data and the original perception data by means of cross-voting confirmation.

In an optional embodiment of the present invention, the update layer includes road features, and the apparatus further includes:

A delivery module, configured to deliver the update layer to the vehicle terminal when the road feature meets a preset delivery condition, and the vehicle terminal is configured to update the map according to the update layer.

In an optional embodiment of the present invention, the vector data includes semantic information, and the determining module 302 includes:

a first matching submodule, configured to determine data matching the semantic information in the map error layer, and generate local matching information, where the local matching information includes at least one matching position;

The second matching submodule is used to find the remaining position corresponding to the matching position by sliding iterative closest point mode;

A combining module, configured to combine the matching positions and the remaining positions to generate a target area.

In an optional embodiment of the present invention, the update module 303 includes:

a fusion sub-module, configured to fuse the vector data and the original perception data by means of nonlinear optimization to generate a road model for the target area;

A generating sub-module is used to establish the logical connection relationship of the road model and generate an update layer.

In an optional embodiment of the present invention, the in-vehicle terminal is connected to a sensor; the original perception data is generated by the sensor, and the vector data is generated by performing three-dimensional reconstruction on the original perception data.

In an optional embodiment of the present invention, the device further includes:

a driving behavior determination module, configured to generate driving behavior data according to the vector data and the original perception data;

A driving path determination module, configured to determine a driving path according to the driving behavior data on the updated map.

As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for related parts.

The embodiment of the present invention also provides an electronic device, including:

A processor and a storage medium, where the storage medium stores a computer program executable by the processor, when the electronic device runs, the processor executes the computer program to execute any one of the embodiments of the present invention Methods. The specific implementation manner and technical effects are similar to those of the method embodiments, and are not repeated here.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the storage medium, and the computer program is executed by a processor to execute the method according to any one of the embodiments of the present invention. The specific implementation manner and technical effects are similar to those of the method embodiments, and are not repeated here.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments may be referred to each other.

It should be understood by those skilled in the art that the embodiments of the embodiments of the present invention may be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.

Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in a flow or flows of the flowcharts and/or a block or blocks of the block diagrams.

These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flows of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing terminal equipment, so that a series of operational steps are performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby executing on the computer or other programmable terminal equipment The instructions executed on the above provide steps for implementing the functions specified in the flowchart or blocks and/or the block or blocks of the block diagrams.

Although preferred embodiments of the embodiments of the present invention have been described, additional changes and modifications to these embodiments may be made by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present invention.

Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or terminal device comprising a list of elements includes not only those elements, but also a non-exclusive list of elements. other elements, or also include elements inherent to such a process, method, article or terminal equipment. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

A map updating method and device, electronic equipment, and storage medium provided by the present invention have been described above in detail. The principles and implementations of the present invention are described with specific examples in this paper. The description of the above embodiments is only for In order to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation and application scope. In summary, this specification The contents should not be construed as limiting the present invention.

Claims (10)

1. a map update method, is characterized in that, is applied to the server, and the map error layer is cached on the server, and the server is connected with a plurality of vehicle-mounted terminals, and the map update method comprises: Receive the vector data and the original perception data sent by the vehicle terminal; Determine the target area in the map error layer according to the vector data; According to the vector data and the original perception data, the target area is updated to obtain an updated layer including the updated target area. 2. The method according to claim 1, characterized in that, after the step of receiving the vector data and original sensing data sent by the vehicle-mounted terminal, the method further comprises: Data cleaning is performed on the vector data and the original perception data by means of cross-voting confirmation. 3. The method of claim 1, wherein the update layer comprises road features, the method further comprising: When the road feature meets a preset delivery condition, the update layer is delivered to the vehicle terminal, and the vehicle terminal is configured to update the map according to the update layer. 4. The method according to any one of claims 1 to 3, wherein the vector data includes semantic information, and the step of determining the target area in the map error layer according to the vector data comprises: : determining data matching the semantic information in the map error layer, and generating local matching information, where the local matching information includes at least one matching position; Find the remaining position corresponding to the matching position by sliding the closest point method; The matching positions and the remaining positions are combined to generate a target area. 5. The method according to any one of claims 1 to 3, wherein the target area is updated according to the vector data and the original sensory data to obtain an update including the updated target area The steps for layering include: Integrate the vector data and the original perception data in a nonlinear optimization manner to generate a road model for the target area; A logical connection relationship of the road model is established, and an update layer is generated. 6. The method according to any one of claims 1 to 3, wherein the vehicle-mounted terminal is connected to a sensor; the raw sensing data is generated by the sensor, and the vector data is generated by the sensor for the raw sensing The data is generated by 3D reconstruction. 7. The method according to claim 3, wherein the method further comprises: generating driving behavior data according to the vector data and the original perception data; On the updated map, a driving route is determined according to the driving behavior data. 8. A map updating device, characterized in that, applied to a server, a map error layer is cached on the server, the server is connected with a plurality of vehicle-mounted terminals, and the map updating device comprises: a receiving module, configured to receive the vector data and the original perception data sent by the vehicle terminal; a determining module, configured to determine the target area in the map error layer according to the vector data; An update module, configured to update the target area according to the vector data and the original perception data to obtain an update layer including the updated target area. 9. An electronic device, characterized in that the electronic device comprises a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor When implementing the steps of the map updating method according to any one of claims 1 to 7. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the map according to any one of claims 1 to 7 is realized Steps to update the method.

Images