Dynamic mapping method and system for unmanned vehicle

Abstract

The invention relates to a dynamic mapping method and system for an unmanned vehicle, and relates to the technical field of unmanned vehicles. The method is applied to an environment detection and recording device, and comprises the following steps: when detecting that an environment deviation exists in a map area, determining the map area as a candidate problem area; when the number of environmental deviation times of the candidate problem region is greater than or equal to a deviation number threshold, determining the candidate problem region as a target problem region; when it is detected that the vehicle enters the target problem area, a dynamic mapping instruction and an environment data packet are sent to a mapping device; and receiving an updated map sent by the mapping device, placing the updated map in the target problem area, and updating the mapping time. The method is applied to a mapping device, and comprises the following steps: obtaining a dynamic mapping instruction sent by an environment detection and recording device and an environment data packet of a target problem area; and analyzing the environment data packet and starting dynamic mapping. According to the invention, the opportunity and environment of mapping can be automatically identified, and the labor cost is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned vehicles, and in particular to a dynamic mapping method and system for unmanned vehicles. Background Art

[0002] At present, dynamic mapping of unmanned vehicles is one of the important research directions in the field of unmanned vehicles, aiming to build and update the map of the vehicle's surrounding environment in real time to support the positioning, navigation and decision-making of unmanned vehicles. Existing dynamic mapping methods usually obtain environmental data based on sensors such as lidar, cameras and inertial measurement units, and use algorithms and technologies to convert these data into accurate map representations, so that unmanned vehicles can achieve more reliable positioning and navigation in different environments.

[0003] However, traditional dynamic mapping methods can only be actively recorded by humans or triggered by remote commands, lacking intelligence, real-time performance, and active detection of the external environment. Summary of the invention

[0004] Based on this, it is necessary to provide a dynamic mapping method and system for unmanned vehicles to address the above technical problems.

[0005] In a first aspect, a dynamic mapping method for an unmanned vehicle is provided, the method being applied to an environment detection and recording device, the method comprising:

[0006] For each map area in the vehicle map, when it is detected that the map area has an environmental deviation, the map area is determined as a candidate problem area;

[0007] For each of the candidate problem areas, when the number of times the environmental deviation is detected in the candidate problem area is greater than or equal to a preset deviation number threshold, the candidate problem area is determined as a target problem area;

[0008] For each of the target problem areas, when a vehicle is detected to enter the target problem area, a dynamic mapping instruction and a real-time recorded environmental data packet of the target problem area are sent to a mapping device;

[0009] An updated map sent by the mapping device is received, the updated map is placed in the target problem area, and a mapping time of the target problem area is updated.

[0010] As an optional implementation manner, the method for determining the environmental deviation includes:

[0011] Acquire environmental point cloud data of the vehicle's environment in real time;

[0012] Calculating a registration score between the environmental point cloud data and the map point cloud data of the map area where the vehicle is located;

[0013] If the registration score is less than or equal to a preset registration score threshold, it is determined that the environmental deviation exists in the map area where the vehicle is located.

[0014] As an optional implementation manner, the method for determining environmental deviation further includes:

[0015] Extracting environmental point cloud feature points of the vehicle's environment and map point cloud feature points of the vehicle's map area;

[0016] Based on a preset point cloud feature matching algorithm, determining the map adaptability of the environment point cloud feature points and the map point cloud feature points;

[0017] If the map fitness is less than or equal to a preset fitness threshold, it is determined that the environmental deviation exists in the map area where the vehicle is located.

[0018] As an optional implementation, the method further includes:

[0019] If the current position of the vehicle acquired in real time successfully matches the position information corresponding to the target problem area, it is determined that the vehicle enters the target problem area.

[0020] As an optional implementation, before sending the dynamic mapping instruction and the real-time recorded environment data packet of the target problem area to the mapping device, the method further includes:

[0021] Get the latest map creation time of the target problem area;

[0022] If the time interval from the mapping time is greater than or equal to the preset mapping interval time threshold, the step of sending the dynamic mapping instruction and the real-time recorded environment data packet of the target problem area to the mapping device is performed.

[0023] As an optional implementation, the environmental data includes point cloud data, vehicle status data, inertial navigation data and real-time motion positioning data.

[0024] As an optional implementation, the method for acquiring the environment data packet includes:

[0025] Read multi-source sensor data from a shared memory, wherein the buffer of the shared memory is a ring buffer;

[0026] The multi-source sensor data is encapsulated into the environmental data packet.

[0027] In a second aspect, a dynamic mapping method for an unmanned vehicle is provided, the method being applied to a mapping device, the method comprising:

[0028] Obtain dynamic mapping instructions and environmental data packets of target problem areas sent by environmental detection and recording devices;

[0029] Parse the environment data packet and start dynamic mapping.

[0030] As an optional implementation, the method further includes:

[0031] When dynamic mapping fails, a mapping failure message is sent to the environment detection and recording device, and the mapping status is cleared;

[0032] When dynamic mapping is successful, the updated map of the target problem area is packaged and sent to the environment detection and recording device.

[0033] In a third aspect, a dynamic mapping system for an unmanned vehicle is provided, the system comprising an environment detection and recording device as described in any one of the first aspect and a mapping device as described in any one of the second aspect.

[0034] The present application provides a method and system for dynamic mapping of an unmanned vehicle. The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the method is applied to an environmental detection and recording device, and the method includes: for each map area in a vehicle map, when it is detected that the map area has an environmental deviation, the map area is determined as a candidate problem area; for each candidate problem area, when the number of times the candidate problem area is detected to have the environmental deviation is greater than or equal to a preset deviation number threshold, the candidate problem area is determined as a target problem area; for each target problem area, when it is detected that a vehicle enters the target problem area, a dynamic mapping instruction and a real-time recorded environmental data packet of the target problem area are sent to a mapping device; an updated map sent by the mapping device is received, the updated map is placed in the target problem area and the mapping time of the target problem area is updated. The method is applied to a mapping device, and the method includes: obtaining a dynamic mapping instruction and an environmental data packet of a target problem area sent by an environmental detection and recording device; parsing the environmental data packet and starting dynamic mapping. This application can automatically identify the time and environment when automatic mapping is required, which can greatly reduce the required manpower costs and operating costs caused by system instability, improve the robustness of the system, and parallel computing can be used in detection and construction. Figure 1 Integration greatly improves the efficiency of use.

[0035] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of a dynamic mapping system for an unmanned vehicle provided in an embodiment of the present application;

[0038] Figure 2 A flowchart of a dynamic mapping method for an unmanned vehicle provided in an embodiment of the present application;

[0039] Figure 3 A flow chart of a method for determining an environmental deviation provided in an embodiment of the present application;

[0040] Figure 4 A flowchart of another method for determining environmental deviation provided in an embodiment of the present application;

[0041] Figure 5 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application;

[0042] Figure 6 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application;

[0043] Figure 7 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The unmanned vehicle dynamic mapping method provided in the embodiment of the present application can be applied to the unmanned vehicle dynamic mapping system. Figure 1As shown, the dynamic mapping system of the unmanned vehicle includes an environment detection and recording device 110 and a mapping device 120. The environment detection and recording device 110 and the mapping device 120 can realize data transmission and functional collaboration through a network communication interface or a shared memory mechanism, forming a complete closed loop of the dynamic mapping process. The environment detection and recording device 110 is responsible for real-time detection of dynamic changes in the environment in which the vehicle is located, generating an environmental data packet, and sending the data to the mapping device 120 through shared memory or network transmission. The mapping device 120 parses the received environmental data packet, and after the dynamic mapping is completed, transmits the updated map information back to the environment detection and recording device 110 through the same connection mechanism. The dynamic optimization of the environmental adaptability of the unmanned vehicle and the real-time update of the map are realized, providing reliable support for the autonomous navigation of the unmanned vehicle in complex environments.

[0046] The following will describe in detail a method for building a dynamic map of an unmanned vehicle provided by an embodiment of the present application in combination with a specific implementation method. Figure 2 A flowchart of a dynamic mapping method for an unmanned vehicle provided in an embodiment of the present application, such as Figure 2 As shown, the method is applied to the environment detection and recording device, and the specific steps are as follows:

[0047] Step 201 : for each map area in the vehicle map, when it is detected that the map area has an environmental deviation, the map area is determined as a candidate problem area.

[0048] In implementation, if it is detected that the current environment of the vehicle is inconsistent with the map, there is an environmental deviation in the map area, such as dynamic changes (increase in obstacles or changes in road morphology), and the area needs to be further marked as a candidate problem area.

[0049] Step 202 : for each candidate problem area, when the number of times that the candidate problem area is detected to have environmental deviation is greater than or equal to a preset deviation number threshold, the candidate problem area is determined as a target problem area.

[0050] In practice, environmental changes may be short-term (such as temporary obstacles) or long-term (such as construction diversion). In order to avoid misjudgment, the environmental deviation of the candidate problem area needs to be confirmed multiple times. When the cumulative number of deviations reaches the preset number threshold, it can be marked as a target problem area. For example, the number of environmental deviations of the candidate problem area can be accumulated. When the cumulative number of deviations reaches 3 times, the area is marked as a target problem area, and the location information is written into the "target problem area file".

[0051] Step 203 : for each target problem area, when a vehicle is detected to enter the target problem area, a dynamic mapping instruction and a real-time recorded environment data packet of the target problem area are sent to a mapping device.

[0052] In practice, the triggering of dynamic mapping is conditional on the vehicle entering the target problem area. If it is detected that the current position of the vehicle falls within the target problem area, multi-source sensor data recording can be started and encapsulated into an environmental data packet. The environmental data packet and dynamic mapping instructions are transmitted to the mapping device through the network. For example, when a vehicle enters the tunnel entrance marked as the target problem area, environmental data such as point cloud and vehicle status data can be recorded in real time and packaged into an environmental data packet, and dynamic mapping instructions can be sent to the mapping device.

[0053] Step 204: receiving the updated map sent by the mapping device, placing the updated map in the target problem area and updating the mapping time of the target problem area.

[0054] In implementation, after the mapping device completes the dynamic mapping of the target problem area, it returns the updated map to the environmental detection and recording device, which replaces the map of the target problem area and records the updated mapping time to ensure that the future mapping process refers to the latest timestamp. For example: After the mapping device completes the mapping, it returns the updated map file to the environmental detection and recording device. The environmental detection and recording device decompresses the received map file and replaces the old map file corresponding to the target problem area. At the same time, the current timestamp is recorded to the target problem area file, marked as the latest mapping time of the area.

[0055] As an optional implementation, Figure 3 A flow chart of a method for determining an environmental deviation provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the specific steps of determining the environmental deviation in step 201 are as follows:

[0056] Step 301, obtaining environmental point cloud data of the vehicle's environment in real time.

[0057] In practice, environmental point cloud data is three-dimensional point cloud information of the space around the vehicle collected in real time by the LiDAR sensor, which represents the structure and characteristics of the vehicle's current environment. Real-time acquisition of point cloud data is the basis for dynamic mapping, ensuring that the latest environmental changes can be reflected. The LiDAR sensor can scan the surrounding environment at a fixed frequency (such as 10 times per second) to generate point cloud data. The environmental detection and recording device can obtain the latest point cloud data from the shared memory or real-time transmission channel through the sensor interface. For example: When a vehicle is driving on a city road, the LiDAR collects three-dimensional point cloud information of surrounding buildings, pedestrians, vehicles, etc., with a coverage range of 30 meters in front and a horizontal angle of 120°.

[0058] Step 302 , calculating a registration score between the environment point cloud data and the map point cloud data of the map area where the vehicle is located.

[0059] In implementation, the registration score can be calculated by a point cloud registration algorithm (such as the ICP algorithm), which indicates the similarity between the current environment point cloud and the map point cloud. A higher registration score indicates a better match between the two, while a low score indicates a deviation. The registration score usually ranges from 0 to 1, with 1 indicating a perfect match and 0 indicating a complete mismatch. For example, an environmental detection and recording device can obtain the current environment point cloud data and the map point cloud data. The ICP algorithm is used to iteratively match the two sets of point clouds, and the registration score is calculated to be 0.68.

[0060] Step 303: If the registration score is less than or equal to a preset registration score threshold, it is determined that there is an environmental deviation in the map area where the vehicle is located.

[0061] In implementation, by comparing the calculated registration score with a preset threshold, the environment detection and recording device can determine whether the current environment deviates from the original map. If the score is lower than the threshold, it means that the map needs to be updated. For example, if the registration score threshold is 0.7, when the registration score is less than or equal to 0.7, the environment detection and recording device can mark the current map area as having an environmental deviation.

[0062] As an optional implementation, Figure 4 A flowchart of another method for determining environmental deviation provided in an embodiment of the present application, such as Figure 4 As shown, the specific steps of determining the environmental deviation in step 201 are as follows:

[0063] Step 401 , extracting environmental point cloud feature points of the vehicle's environment and map point cloud feature points of the map area where the vehicle is located.

[0064] In implementation, feature points are points in the point cloud with significant geometric characteristics, such as corner points, edge points, etc., which can represent the key structures of the environment. Extracting these feature points can reduce the amount of data while retaining enough information for matching and adaptability evaluation. For example: feature extraction algorithms (such as SIFT or ISS algorithms) can be used to extract feature points in the environmental point cloud and map point cloud of the nine-square grid environment where the current vehicle is located. Environmental point cloud feature points can include road boundaries, road signs, building corners, etc., and map point cloud feature points can include recorded static structural features.

[0065] Step 402: Determine the map fit between the environment point cloud feature points and the map point cloud feature points based on a preset point cloud feature matching algorithm.

[0066] In implementation, feature point matching algorithms (such as RANSAC or FLANN) can find the best matching pair between the environment point cloud and the map point cloud based on the geometric relationship and feature descriptors of the feature points of the point cloud. The fitness refers to the proportion of successfully matched feature point pairs to the total feature point pairs, reflecting the similarity between the two. For example, the RANSAC algorithm can be used to eliminate false matches in feature point pairs and calculate the number of feature point pairs that are finally matched.

[0067] Step 403: If the map fitness is less than or equal to a preset fitness threshold, it is determined that an environmental deviation exists in the map area where the vehicle is located.

[0068] In implementation, the degree of similarity between the environment and the map is determined by comparing the degree of fit with a threshold. If the degree of fit is lower than the threshold, it means that the environment has changed significantly or the map has errors and needs to be updated. For example, the degree of fit threshold can be set to 0.85. If the degree of fit is 0.8 (lower than the threshold), the environment detection and recording device can determine that there is an environmental deviation in the current map area.

[0069] As an optional implementation, the specific method for detecting the vehicle entering the target problem area in step 203 is: if the current position of the vehicle acquired in real time successfully matches the position information corresponding to the target problem area, it is determined that the vehicle enters the target problem area.

[0070] As an optional implementation, Figure 5 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application, such as Figure 5 As shown, before sending the dynamic mapping instruction and the real-time recorded environment data packet of the target problem area to the mapping device in step 203, the following steps are also included:

[0071] Step 501, obtaining the latest map creation time of the target problem area.

[0072] In practice, the latest mapping time of the target problem area is obtained to determine whether the map of the area needs to be updated. If the time interval from the last mapping is long, there may be environmental changes or the map is outdated, and dynamic mapping is required. This time information can be extracted from the database or status record in the mapping system. For example: the environmental detection and recording device can retrieve the timestamp of the last mapping of the target problem area by querying the database of the mapping device.

[0073] Step 502, if the time interval from the mapping time is greater than or equal to the preset mapping interval time threshold, the step of sending the dynamic mapping instruction and the real-time recorded environment data packet of the target problem area to the mapping device is executed.

[0074] In practice, when determining whether dynamic mapping is needed, the environment detection and recording device can compare the current time with the last mapping time of the target problem area. If the time interval is greater than or equal to the preset mapping interval threshold, it means that the map of the area is outdated or the environment has changed. The environment detection and recording device can trigger a dynamic mapping instruction and send the relevant environment data packet to the mapping device for map update, avoiding unnecessary frequent updates and ensuring the timeliness and accuracy of map updates.

[0075] As an optional implementation, the environmental data includes point cloud data, vehicle status data, inertial navigation data and real-time motion positioning data.

[0076] As an optional implementation, Figure 6 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the specific steps of obtaining the environment data packet in step 203 are as follows:

[0077] Step 601, reading multi-source sensor data from a shared memory, where the buffer of the shared memory is a ring buffer.

[0078] In practice, shared memory allows multiple processors or threads to share the same memory area. The embodiment of the present application uses a circular buffer to store sensor data because the circular buffer has a fixed size. Once the buffer is full, the oldest data will be overwritten, ensuring that the latest data is always in the buffer.

[0079] Step 602: Encapsulate the multi-source sensor data into an environmental data packet.

[0080] In practice, the environmental detection and recording device can encapsulate the data of multiple sensors into an environmental data packet, which can facilitate subsequent transmission and processing. The encapsulation process includes integrating and formatting the data of different sensors, and adding timestamps and other necessary metadata to the data packet. The encapsulation of the environmental data packet can be serialized in protobuf or JSON format for easy transmission and parsing.

[0081] In the following, another method for building a dynamic map of an unmanned vehicle provided by an embodiment of the present application will be described in detail in combination with a specific implementation method. Figure 7 A flowchart of another method for dynamic mapping of an unmanned vehicle provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the method is applied to a mapping device, and the specific steps are as follows:

[0082] Step 701, obtaining a dynamic mapping instruction and an environmental data packet of a target problem area sent by an environmental detection and recording device.

[0083] In practice, during the dynamic mapping process, the mapping device can receive dynamic mapping instructions from the environmental detection and recording device and an environmental data packet containing the target problem area. The data packet contains environmental data from different sensors (such as lidar, camera, IMU, etc.) and is used to perform real-time mapping in the target problem area. By receiving this data packet, the mapping device can obtain the necessary real-time environmental information to ensure that subsequent mapping tasks can proceed smoothly.

[0084] Step 702, parse the environment data packet and start dynamic mapping.

[0085] In practice, by parsing environmental data packets, the mapping device can extract information such as lidar point cloud data, images, and IMU data from them, and use them to build a map that is updated in real time. After the analysis is completed, the mapping device can perform dynamic mapping operations based on these data and gradually optimize the map to adapt to environmental changes. For example: the mapping device can use the SLAM algorithm to gradually create a map of the target problem area, and dynamically adjust and optimize it based on the data obtained from the IMU and other sensors to ensure map accuracy and consistency.

[0086] As an optional implementation, when dynamic mapping fails, a mapping failure message is sent to the environment detection and recording device, and the mapping state is cleared. When dynamic mapping succeeds, the updated map of the target problem area is packaged and sent to the environment detection and recording device.

[0087] In implementation, when dynamic mapping fails, the mapping device can send a mapping failure message to the environment detection and recording device, and clear the mapping state to wait for the next recording. When mapping is successful, the mapping device can package the map and send it to the environment detection and recording device via network transmission, and can send a mapping completion message to the environment detection and recording device after the transmission is completed.

[0088] The embodiment of the present application provides a method and system for dynamic mapping of an unmanned vehicle. The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the method is applied to an environmental detection and recording device, and the method includes: for each map area in the vehicle map, when it is detected that the map area has an environmental deviation, the map area is determined as a candidate problem area; for each candidate problem area, when the number of times the candidate problem area is detected to have an environmental deviation is greater than or equal to a preset deviation number threshold, the candidate problem area is determined as a target problem area; for each target problem area, when it is detected that the vehicle enters the target problem area, the dynamic mapping instruction and the real-time recorded environmental data packet of the target problem area are sent to the mapping device; the updated map sent by the mapping device is received, the updated map is placed in the target problem area and the mapping time of the target problem area is updated. The method is applied to a mapping device, and the method includes: obtaining the dynamic mapping instruction and the environmental data packet of the target problem area sent by the environmental detection and recording device; parsing the environmental data packet and starting dynamic mapping. This application can automatically identify the time and environment when automatic mapping is required, which can greatly reduce the required manpower costs and operating costs caused by system instability, improve the robustness of the system, and parallel computing can be used in detection and construction. Figure 1 Integration greatly improves the efficiency of use. Parallel processing and distributed computing capabilities enable map message recording and mapping tasks to be completed with higher efficiency. It can identify changing environments, allowing the system to cope with more usage scenarios, and can maintain the stability of the system in changing scenarios to improve the robustness of the overall autonomous driving system. Through the external message interface and multiple trigger conditions, targeted reconstruction work can be carried out for areas where the environment changes greatly, the map quality is poor, or where specified reconstruction is required, rather than overall reconstruction, which greatly reduces computing events and maintenance costs. In summary, the embodiments of the present application make the map message recording and mapping process more efficient, accurate, and reliable, and provide a better foundation and support for the navigation and decision-making of unmanned vehicles.

[0089] It should be understood that although Figures 2 to 7 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figures 2 to 7 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0090] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can refer to each other, and each embodiment focuses on the differences from other embodiments. For related points, please refer to the description of other method embodiments.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0093] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0094] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0095] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0096] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A dynamic mapping method for an unmanned vehicle, characterized in that: The method is applied to an environment detection and recording device, and the method comprises: For each map area in the vehicle map, when it is detected that the map area has an environmental deviation, the map area is determined as a candidate problem area; For each of the candidate problem areas, when the number of times the environmental deviation is detected in the candidate problem area is greater than or equal to a preset deviation number threshold, the candidate problem area is determined as a target problem area; For each of the target problem areas, when a vehicle is detected to enter the target problem area, a dynamic mapping instruction and a real-time recorded environmental data packet of the target problem area are sent to a mapping device; An updated map sent by the mapping device is received, the updated map is placed in the target problem area, and a mapping time of the target problem area is updated.

2. The method according to claim 1, characterized in that The method for determining the environmental deviation comprises: Acquire environmental point cloud data of the vehicle's environment in real time; Calculating a registration score between the environmental point cloud data and the map point cloud data of the map area where the vehicle is located; If the registration score is less than or equal to a preset registration score threshold, it is determined that the environmental deviation exists in the map area where the vehicle is located.

3. The method according to claim 1, characterized in that The method for determining the environmental deviation further includes: Extracting environmental point cloud feature points of the vehicle's environment and map point cloud feature points of the vehicle's map area; Based on a preset point cloud feature matching algorithm, determining the map adaptability of the environment point cloud feature points and the map point cloud feature points; If the map fitness is less than or equal to a preset fitness threshold, it is determined that the environmental deviation exists in the map area where the vehicle is located.

4. The method according to claim 1, characterized in that: The method further comprises: If the current position of the vehicle acquired in real time successfully matches the position information corresponding to the target problem area, it is determined that the vehicle enters the target problem area.

5. The method according to claim 1, characterized in that Before sending the dynamic mapping instruction and the real-time recorded environmental data packet of the target problem area to the mapping device, the method further includes: Get the latest map creation time of the target problem area; If the time interval from the mapping time is greater than or equal to the preset mapping interval time threshold, the step of sending the dynamic mapping instruction and the real-time recorded environment data packet of the target problem area to the mapping device is performed.

6. The method according to claim 1, characterized in that The environmental data includes point cloud data, vehicle status data, inertial navigation data and real-time motion positioning data.

7. The method according to claim 1, characterized in that The method for obtaining the environmental data packet comprises: Read multi-source sensor data from a shared memory, wherein the buffer of the shared memory is a ring buffer; The multi-source sensor data is encapsulated into the environmental data packet.

8. A dynamic mapping method for an unmanned vehicle, characterized in that: The method is applied to a mapping device, and the method comprises: Obtain dynamic mapping instructions and environmental data packets of target problem areas sent by environmental detection and recording devices; Parse the environment data packet and start dynamic mapping.

9. The method according to claim 8, characterized in that The method further comprises: When dynamic mapping fails, a mapping failure message is sent to the environment detection and recording device, and the mapping status is cleared; When dynamic mapping is successful, the updated map of the target problem area is packaged and sent to the environment detection and recording device.

10. A dynamic mapping system for an unmanned vehicle, characterized in that: The system comprises the environment detection and recording device as described in any one of claims 1-7 and the mapping device as described in any one of claims 8-9.

Images