Automatic driving method of automatic driving vehicle, electronic device, and storage medium

Abstract

The application discloses an automatic driving method of an automatic driving vehicle, an electronic device and a storage medium. The automatic driving method of the automatic driving vehicle comprises the following steps: acquiring an original map and a current lane where the automatic driving vehicle is located, and the current lane is located within a region range described by the original map; in response to the original map not including lane information of the current lane, acquiring at least one road element around the automatic driving vehicle, wherein the original map does not contain at least one of the at least one road element; fusing the original map and at least one of the at least one road element based on the current lane to obtain a target map; and performing an automatic driving process based on the target map. According to the scheme, at least one road element around the automatic driving vehicle is acquired to supplement the content of the original map, so that the target map capable of being used for automatic driving is obtained, different-precision original maps are adapted, the dependence on the original map is reduced, and the use is more convenient.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to an autonomous driving method, electronic device and storage medium for an autonomous vehicle. Background Technology

[0002] In the field of autonomous driving, current mass-producible autonomous driving solutions (L2+ / L3 / L4) are basically based on high-definition maps (HD-Map). However, the mass production and use of HD-Map still has many limitations and drawbacks. For example, HD-Map needs to be approved before it can be used, and some road HD-Maps are not subject to approval. Therefore, there is an urgent need for a solution that can adapt to maps of different resolutions for autonomous driving. Summary of the Invention

[0003] This application provides at least one autonomous driving method, electronic device, and storage medium for an autonomous vehicle.

[0004] The first aspect of this application provides an autonomous driving method for an autonomous vehicle, comprising: acquiring an original map and the current lane where the autonomous vehicle is located, wherein the current lane is located within the area described by the original map;

[0005] In response to the fact that the original map does not include lane information of the current lane, at least one road element around the autonomous vehicle is obtained, wherein the original map does not include at least one of the at least one road element;

[0006] Based on the current lane, the original map and at least one of the at least one road element are fused to obtain the target map;

[0007] Based on the target map, the autonomous driving process is carried out.

[0008] The lane information includes at least one of road surface information, road signage information, and road marking information;

[0009] The original map does not include lane information for the current lane, including at least one of the following: the content precision of the original map is less than a preset value, so the original map does not include at least one of the lane information; the content precision of the original map is greater than or equal to the preset value, but the original map does not include at least one of the lane information.

[0010] The preset value represents the accuracy of the map content at the lane level.

[0011] The original map may include a navigation map, the accuracy of which is less than the preset value, and the navigation map is used to describe road-level content; or, the original map may include an autonomous driving map, the accuracy of which is greater than or equal to the preset value, and the autonomous driving map is used to describe lane-level content.

[0012] The process of obtaining the current lane where the autonomous vehicle is located includes: obtaining sensor information on the autonomous vehicle, state estimation information of the autonomous vehicle, and at least one road element around the autonomous vehicle.

[0013] The current lane is located in the original map based on at least one of the at least one road element, the sensor information, and the state estimation information, thereby obtaining the current lane.

[0014] The autonomous driving method for autonomous vehicles further includes: in response to the original map being empty, acquiring at least one road element around the autonomous vehicle, state estimation information of the autonomous vehicle, and obstacle information around the autonomous vehicle.

[0015] Based on at least one of at least one road element surrounding the autonomous vehicle, the state estimation information of the autonomous vehicle, and the obstacle information, path planning is performed to execute assisted driving functions.

[0016] The autonomous driving process based on the target map includes: planning the target lane for the autonomous vehicle to travel to the destination based on the target map and the current lane.

[0017] The autonomous driving process based on the target map further includes: obtaining first state estimation information of the autonomous vehicle;

[0018] Based on the target map, the target lane, the first state estimation information, and the obstacle information on the target lane, path planning is performed to obtain a planned trajectory, thereby achieving autonomous driving according to the planned trajectory.

[0019] The step of achieving autonomous driving according to the planned trajectory includes: obtaining second state estimation information of the autonomous vehicle, wherein the second state estimation information is different from the first state estimation information;

[0020] Based on the second state estimation information, the autonomous vehicle is controlled to drive along the planned trajectory to achieve autonomous driving.

[0021] A second aspect of this application provides an electronic device including a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the autonomous driving method for an autonomous vehicle described in the first aspect above.

[0022] A third aspect of this application provides a non-volatile computer-readable storage medium for storing a computer program, which, when executed by a processor, is used to implement the autonomous driving method for an autonomous vehicle described in the first aspect above.

[0023] The aforementioned solution obtains the original map and the current lane of the autonomous vehicle. Responding to the original map's omission of lane information (which is not present in the current lane), it acquires at least one road element surrounding the autonomous vehicle. Based on the current lane, it fuses the original map and at least one of the road elements to obtain a target map. This process supplements the original map with road elements, resulting in a supplemented target map, which is then used for the autonomous driving process. The solution in this application, by acquiring at least one road element surrounding the autonomous vehicle and supplementing the original map, obtains a target map suitable for autonomous driving. It adapts to original maps of varying precision, reduces dependence on the original map, and is more convenient to use.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0026] Figure 1 This is a flowchart illustrating the autonomous driving method for an autonomous vehicle in an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a scenario in an embodiment of this application;

[0028] Figure 3 This is a schematic diagram of another scenario in an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of the structure of the electronic device in the embodiments of this application;

[0030] Figure 5 This is a schematic diagram of the structure of a non-volatile computer-readable storage medium in an embodiment of this application. Detailed Implementation

[0031] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the application. Similarly, the following embodiments are only some, not all, embodiments of the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0032] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, "many" in this document means two or more. Additionally, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. Furthermore, the terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features.

[0034] As mentioned above, the mass production and use of high-precision maps still has many limitations and drawbacks. For example, high-precision maps need to be approved before they can be used, and some high-precision maps for certain roads are not subject to approval. Therefore, there is an urgent need for a solution that can adapt to maps of different precision for autonomous driving.

[0035] Therefore, this application provides an autonomous driving method, electronic device, and storage medium for an autonomous vehicle.

[0036] Please see Figure 1 , Figure 1 This is a flowchart illustrating the autonomous driving method for an autonomous vehicle in an embodiment of this application. It should be noted that if substantially the same result is achieved, the method of this application is not necessarily identical. Figure 1The illustrated process sequence is limited. This method can be applied to electronic devices with computing and other functions. These devices can execute this method by receiving information collected by sensor devices, such as millimeter-wave radar, lidar, or cameras equipped in autonomous vehicles. The sensor devices perceive the dynamic real-world scene surrounding the vehicle during its operation. Figure 1 As shown, the autonomous driving method for autonomous vehicles includes the following steps:

[0037] S1. Obtain the original map and the current lane where the autonomous vehicle is located, where the current lane is within the area described by the original map.

[0038] In one application scenario, an autonomous vehicle is driving on a road. During this process, the system acquires the original map and the vehicle's current lane, which is located within the area described by the original map. Understandably, the original map is known, and the vehicle's current lane falls within the area described by the original map. However, the original map may or may not include lane information for the current lane, meaning the current lane may or may not be displayed on the original map.

[0039] S2. In response to the original map not including lane information of the current lane, obtain at least one road element around the autonomous vehicle, wherein the original map does not include at least one of the at least one road element.

[0040] The original map does not include lane information for the current lane. Understandably, lane information includes specific details about the road surface and lanes, such as lane lines. The original map does not include lane information for the current lane, meaning that while the original map can describe the corresponding road information, it does not include lane information, which is more detailed than road information. This results in the current lane not being displayed in the original map.

[0041] At least one road element surrounding the autonomous vehicle is acquired, wherein the original map does not include at least one of the at least one road element. It is understood that at least one road element surrounding the autonomous vehicle can be obtained through perception, and the specific perception method can be selected according to actual usage requirements without specific limitations. The road element may include specific information about the roads surrounding the autonomous vehicle, such as the number of lanes, and the original map does not include at least one of the at least one road element; that is, the original map does not include a portion of the at least one road element. Additionally, at least one road element may include lane information for the current lane.

[0042] S3. Based on the current lane, merge the original map and at least one of at least one road element to obtain the target map.

[0043] Based on the current lane, the original map is fused with at least one of at least one road element to obtain the target map. It is understood that the original map does not include lane information for the current lane. The fusion of the original map with at least one of at least one road element, specifically those road elements missing from the original map, supplements the content of the original map by using road elements to display the current lane, thus obtaining the target map, which displays the current lane. For example, the target map may include lane information, lane shapes, and the number of lanes surrounding the autonomous vehicle. The specific fusion method can be chosen according to actual usage requirements and is not specifically limited.

[0044] Taking the example of at least one road element obtained by perception including element a, element b and element c, if the original map does not include element a, element b and element c, then based on the current lane, the original map is fused with element a, element b and element c to obtain the target map displaying the current lane; if the original map does not include element a and element c, then based on the current lane, the original map is fused with element a and element c to obtain the target map displaying the current lane.

[0045] S4. Based on the target map, proceed with the autonomous driving process.

[0046] Based on the target map, an autonomous driving process is carried out, thereby enabling autonomous driving based on original maps of varying precision.

[0047] The aforementioned solution acquires the original map and the current lane of the autonomous vehicle. Responding to the original map's omission of lane information (which is not present in the current lane), it acquires at least one road element surrounding the autonomous vehicle. Based on the current lane, it fuses the original map and at least one of the road elements to obtain a target map. This process supplements the original map with road elements, resulting in a supplemented target map, which is then used for the autonomous driving process. The solution in this application, by acquiring at least one road element surrounding the autonomous vehicle and supplementing the original map, obtains a target map suitable for autonomous driving. It adapts to original maps of varying precision, reduces dependence on the original map, and is more convenient to use.

[0048] As described above, the original map and the current lane of the autonomous vehicle are obtained. In response to the original map not including lane information for the current lane, at least one road element surrounding the autonomous vehicle is obtained. In one embodiment of this application, lane information includes at least one of road surface information, road signage information, and road surface marking information; the original map not including lane information for the current lane includes at least one of the following: the content precision of the original map is less than a preset value, thus the original map does not include at least one of the lane information; the content precision of the original map is greater than or equal to the preset value, but the original map does not include at least one of the lane information; wherein, the preset value represents the map content precision at the lane level.

[0049] Lane information includes at least one of road surface information, road directional information, and road marking information. It is understood that road surface information may include lane lines on the road surface; road directional information may include road signs, light poles, and traffic lights; and road marking information may include text and arrows on the road surface.

[0050] The original map does not include lane information for the current lane, which includes at least one of the following: the content accuracy of the original map is less than a preset value, so the original map does not include at least one of the lane information; the content accuracy of the original map is greater than or equal to the preset value, but the original map does not include at least one of the lane information.

[0051] Understandably, the preset value represents the map's content precision at the lane level. Lane level indicates that the minimum level of displayed content is the lane, such as lane lines. If the original map's content precision is less than the preset value, it means the original map does not include content at the lane level. In other words, the original map does not include lane information at the lane level, while the current lane's lane information belongs to the lane level. Therefore, the original map does not include at least one of the following: road surface information, road signs, and road markings, causing the current lane not to be displayed. For example, if the original map includes a navigation map (SD-Map), and the navigation map's content precision is less than the preset value, then the navigation map will not include at least one of the following: road surface information, road signs, and road markings for the current lane, and thus the current lane will not be displayed in the navigation map.

[0052] The original map's content precision is greater than or equal to a preset value, but it does not include at least one of the following lane information: lane-level content. This means the original map includes lane information with lane-level precision, and the current lane's information is lane-level content. However, the original map does not include at least one of the following: road surface information, road signage, or road markings. Therefore, the original map does not display the current lane. For example, if the original map includes a high-definition map (HD-Map), although the HD-Map includes lane-level content, if it does not include at least one of the following, the current lane will also not be displayed in the HD-Map.

[0053] As mentioned above, the original map does not include lane information for the current lane. In one embodiment of this application, the original map includes a navigation map, the navigation map having a content precision lower than a preset value, and the navigation map is used to describe road-level content.

[0054] Figure 2 This is a schematic diagram of a scenario in an embodiment of this application, such as... Figure 2 As shown, the original map includes a navigation map (SD-Map). The navigation map has lower resolution, and its content accuracy is less than the preset value. Understandably, the navigation map describes road-level content, where the minimum level of displayed content is the road itself, such as its shape. Navigation maps typically require a resolution of 5m-10m. Their content includes road topology, shape, and road classification, but cannot describe lane-level content. Since the current lane's lane information belongs to the lane-level, the navigation map does not include it, thus preventing the current lane from being displayed. Please refer to [link / reference needed]. Figure 2 Taking the original map as the navigation map as an example, since the navigation map does not include lane information of the current lane, the navigation map is fused with at least one of at least one road element based on the current lane to obtain a target map that displays the current lane, and then the autonomous driving process is carried out based on the target map.

[0055] As mentioned above, the original map does not include lane information for the current lane. In one embodiment of this application, the original map includes an autonomous driving map, the content accuracy of which is greater than or equal to a preset value, and the autonomous driving map is used to describe lane-level content.

[0056] Figure 3 This is another scenario illustration in the embodiments of this application, such as... Figure 3As shown, the original map includes an autonomous driving map, also known as a high-definition map (HD-Map). Autonomous driving maps have high precision, with content accuracy greater than or equal to preset values, enabling them to describe lane-level content. Therefore, autonomous driving maps can be directly used for route planning during autonomous vehicle operation. Understandably, the main content stored in autonomous driving maps is lane-level information, typically with centimeter-level precision. Autonomous driving maps also store richer content, such as lane line geometry, lane-specific facilities, and whether construction is underway. Although autonomous driving maps can describe lane-level content, and the current lane's information belongs to lane-level content, if the autonomous driving map does not include the current lane's lane information, the current lane will not be displayed on the autonomous driving map.

[0057] Please refer to it again. Figure 3 Taking the original map as an example of an autonomous driving map, if the autonomous driving map does not include lane information of the current lane, the current lane will not be displayed in the autonomous driving map. Therefore, based on the current lane, the autonomous driving map is fused with at least one of at least one road element to obtain a target map that displays the current lane, and then the autonomous driving process is carried out based on the target map.

[0058] The production of autonomous driving maps can be divided into centralized mapping and crowdsourced data collection. Centralized mapping uses dedicated data collection vehicles, which are typically equipped with LiDAR, cameras, GNSS, and IMU. LiDAR-collected point clouds usually provide accurate geometric information, cameras provide rich pixel information, GNSS provides relatively accurate positional information, and IMUs offer the advantage of accurate positional estimation through integration, resulting in highly accurate autonomous driving maps. Crowdsourced data collection requires data collection and alignment, and outputs the geometric and logical information of the map through modeling, resulting in faster production speeds and shorter cycles. Furthermore, the production process of autonomous driving maps includes vision-based SLAM, LiDAR-based SLAM, and information fusion technologies. LiDAR-based SLAM, specifically single-LiDAR solutions, includes LOAM and solutions incorporating sensors such as IMUs and cameras. The method described above for generating autonomous driving maps using radar point clouds is a standard industry practice. In other embodiments, other feasible methods can also be used to generate autonomous driving maps, selected according to actual usage requirements, without specific limitations.

[0059] As described above, the original map and the current lane of the autonomous vehicle are obtained, with the current lane located within the description area of ​​the original map. In one embodiment of this application, obtaining the current lane of the autonomous vehicle includes: obtaining sensor information on the autonomous vehicle, state estimation information of the autonomous vehicle, and at least one road element surrounding the autonomous vehicle; locating the current lane in the original map based on at least one of the at least one road element, the sensor information, and the state estimation information, thereby obtaining the current lane.

[0060] The process involves acquiring sensor information from the autonomous vehicle, state estimation information of the autonomous vehicle, and at least one road element surrounding the autonomous vehicle. Understandably, image sensors can be used to collect image data of the scene surrounding the autonomous vehicle, and radar sensors can be used to collect point cloud data of the scene surrounding the autonomous vehicle to obtain the sensor information. The state estimation information of the autonomous vehicle can be obtained through estimation; the specific estimation method can be selected according to actual usage requirements and is not specifically limited. For example, the state estimation information may include turning and lane-changing information of the autonomous vehicle. At least one road element surrounding the autonomous vehicle can be obtained through perception; the specific perception method can be selected according to actual usage requirements and is not specifically limited. The road element may include specific information about the roads surrounding the autonomous vehicle. For example, image sensors and radar sensors can be mounted on a mobile device. This mobile device can be an automated mobile device, such as a robot or an autonomous vehicle.

[0061] In some embodiments, the image sensor may be a camera, and the radar sensor may be a lidar sensor, such as a mechanical lidar, semi-solid-state lidar, or solid-state lidar. In one embodiment, the radar sensor may be any radar device that provides point cloud data and is used in autonomous driving to meet perception accuracy requirements.

[0062] In one scenario, autonomous vehicles drive on the road, and sensor devices installed on the autonomous vehicles acquire sensor information, state estimation information of the autonomous vehicles, and road elements around the autonomous vehicles.

[0063] Based on at least one road element, sensor information, and state estimation information, the current lane is located in the original map, thereby obtaining the current lane. It is understood that the current lane is located within the area described by the original map. Therefore, based on at least one road element surrounding the autonomous vehicle, sensor information, and the state estimation information of the autonomous vehicle, the current lane can be located in the original map, thus obtaining the current lane.

[0064] As described above, in one embodiment of this application, the autonomous driving method for an autonomous vehicle further includes: in response to an empty original map, obtaining at least one road element surrounding the autonomous vehicle, state estimation information of the autonomous vehicle, and obstacle information surrounding the autonomous vehicle; and performing path planning based on at least one of the at least one road element surrounding the autonomous vehicle, the state estimation information of the autonomous vehicle, and the obstacle information to perform assisted driving functions.

[0065] In response to an empty original map (i.e., no original map exists), the system acquires at least one road element surrounding the autonomous vehicle, the vehicle's state estimation information, and obstacle information surrounding the vehicle. Understandably, at least one road element surrounding the autonomous vehicle can be obtained through perception, where the specific perception method can be selected based on actual usage requirements and is not specifically limited; for example, the road element may include specific information about the roads surrounding the autonomous vehicle. The autonomous vehicle's state estimation information can be obtained through estimation, where the specific estimation method can be selected based on actual usage requirements and is not specifically limited; for example, the state estimation information may include the autonomous vehicle's turning and lane-changing information. The obstacle information surrounding the autonomous vehicle can be obtained through perception, where the specific perception method can be selected based on actual usage requirements and is not specifically limited; for example, obstacle information may include road bollards and stone pillars.

[0066] Based on at least one of the road elements surrounding the autonomous vehicle, the state estimation information of the autonomous vehicle, and obstacle information, path planning is performed to execute assisted driving functions. It is understandable that autonomous driving is impossible without an original map; however, by planning the autonomous vehicle's driving path based on at least one of the road elements surrounding the autonomous vehicle, the state estimation information of the autonomous vehicle, and obstacle information, assisted driving functions can be achieved.

[0067] As described above, the autonomous driving process is based on a target map. In one embodiment of this application, the autonomous driving process based on a target map includes: planning the target lane for the autonomous vehicle to travel to its destination based on the target map and the current lane.

[0068] Based on the target map and the current lane, the target lane that the autonomous vehicle will travel to reach its destination can be planned. In other words, based on the fused target map and the current lane, the road and specific lane that the autonomous vehicle needs to travel to reach its destination can be planned, that is, the target lane, thereby achieving autonomous driving.

[0069] As described above, the autonomous driving process is based on a target map. In one embodiment of this application, the autonomous driving process based on a target map further includes: obtaining first state estimation information of the autonomous vehicle; performing path planning based on the target map, the target lane, the first state estimation information, and obstacle information on the target lane to obtain a planned trajectory, thereby achieving autonomous driving according to the planned trajectory.

[0070] The first state estimation information of the autonomous vehicle is obtained. The first state information may include the speed information and attitude information of the autonomous vehicle. The first state estimation information is obtained by global coordinate estimation. The specific estimation method can be selected according to the actual use requirements and is not specifically limited.

[0071] Based on the target map, target lane, first state estimation information, and obstacle information in the target lane, path planning is performed to obtain a planned trajectory, thereby enabling autonomous driving. Understandably, based on the current lane, fusing the original map with at least one of at least one road element yields the target map; and based on the target map and the current lane, the target lane for the autonomous vehicle can be planned; obstacle information in the target lane can be obtained through perception. Then, based on the target map, target lane, first state estimation information, and obstacle information in the target lane, path planning is performed to obtain the planned trajectory of the autonomous vehicle, enabling it to achieve autonomous driving according to the planned trajectory.

[0072] For example, based on the target map, we know that the autonomous vehicle will turn right at the next intersection to reach its destination. The target lane is the right-turn lane. The first state estimation information includes the autonomous vehicle's speed (50 km / h) and its attitude (straight ahead). Obstacle information in the target lane includes a rock in the lane. Path planning is then performed to obtain the planned trajectory. This trajectory, understandably, involves entering the right-turn lane, slowing down, avoiding the rock and pedestrians in the right-turn lane, turning right at the next intersection, and finally reaching the destination, thus achieving autonomous driving.

[0073] As described above, path planning is performed based on the target map, target lane, first state estimation information, and obstacle information on the target lane to obtain a planned trajectory, thereby achieving autonomous driving according to the planned trajectory. In one embodiment of this application, achieving autonomous driving according to the planned trajectory includes: obtaining second state estimation information of the autonomous vehicle, wherein the second state estimation information is different from the first state estimation information; and controlling the autonomous vehicle to drive according to the planned trajectory based on the second state estimation information to achieve autonomous driving.

[0074] The second state estimation information of the autonomous vehicle is obtained, which differs from the first state estimation information. The first state estimation information is obtained using global coordinate estimation, while the second state estimation information is obtained using high-precision, high-frequency state estimation in a globally independent local coordinate system. The specific estimation method can be selected based on actual usage requirements and is not specifically limited, thus ensuring the difference between the second and first state estimation information. The second state estimation information may include the autonomous vehicle's position information, attitude information, and speed information.

[0075] Based on the second state estimation information, the autonomous vehicle is controlled to drive along the planned trajectory to achieve autonomous driving. It is understandable that a planned trajectory can be obtained based on the target map, the target lane, the first state estimation information, and obstacle information on the target lane. Then, based on the second state estimation information, the autonomous vehicle is controlled to drive along the obtained planned trajectory, thereby achieving autonomous driving.

[0076] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0077] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of this application. The electronic device 300 includes a memory 301 and a processor 302 coupled to each other. The processor 302 executes program instructions stored in the memory 301 to implement the steps of the above-described autonomous driving method embodiment for an autonomous vehicle. In a specific implementation scenario, the electronic device 300 may include, but is not limited to, a microcomputer or a server.

[0078] Specifically, processor 302 controls itself and memory 301 to implement the steps of the above-described autonomous driving method embodiment for an autonomous vehicle. Processor 302 can also be called a CPU (Central Processing Unit), and may be an integrated circuit chip with signal processing capabilities. Processor 302 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 302 can be implemented using integrated circuit chips.

[0079] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a non-volatile computer-readable storage medium in an embodiment of this application. The computer-readable storage medium 500 is used to store a computer program 501, which, when executed by the processor 302, is used to implement the steps in the above-described embodiment of the autonomous driving method for an autonomous vehicle.

[0080] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed methods and related devices can be implemented in other ways. For example, the related device implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication disconnection shown or discussed may be indirect coupling or communication disconnection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0082] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0083] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An autonomous driving method for an autonomous vehicle, characterized in that, include: Obtain the original map and the current lane where the autonomous vehicle is located, wherein the current lane is located within the area described by the original map; In response to the original map not including lane information of the current lane, at least one road element around the autonomous vehicle is obtained, wherein the original map does not include at least one of the at least one road element, and the original map not including lane information of the current lane means that the current lane is not displayed in the original map; Based on the current lane, the original map and at least one of the at least one road element are fused to obtain a target map displaying the current lane; Based on the target map, the autonomous driving process is carried out.

2. The method according to claim 1, characterized in that, The lane information includes at least one of road surface information, road signage information, and road marking information; The original map does not include lane information for the current lane, including at least one of the following: the content precision of the original map is less than a preset value, so the original map does not include at least one of the lane information; the content precision of the original map is greater than or equal to the preset value, but the original map does not include at least one of the lane information. The preset value represents the accuracy of the map content at the lane level.

3. The method according to claim 2, characterized in that, The original map includes a navigation map, the navigation map having a lower content precision than the preset value, and the navigation map is used to describe road-level content; or The original map includes an autonomous driving map, the content accuracy of which is greater than or equal to the preset value, and the autonomous driving map is used to describe lane-level content.

4. The method according to claim 1, characterized in that, Obtaining the current lane where the autonomous vehicle is located includes: Acquire sensor information on the autonomous vehicle, state estimation information of the autonomous vehicle, and at least one road element around the autonomous vehicle; The current lane is located in the original map based on at least one of the at least one road element, the sensor information, and the state estimation information, thereby obtaining the current lane.

5. The method according to claim 1, characterized in that, Further includes: In response to the original map being empty, at least one road element around the autonomous vehicle, state estimation information of the autonomous vehicle, and obstacle information around the autonomous vehicle are obtained. Based on at least one of at least one road element surrounding the autonomous vehicle, the state estimation information of the autonomous vehicle, and the obstacle information, path planning is performed to execute assisted driving functions.

6. The method according to claim 1, characterized in that, The autonomous driving process based on the target map includes: Based on the target map and the current lane, the target lane for the autonomous vehicle to travel to its destination is planned.

7. The method according to claim 6, characterized in that, The autonomous driving process based on the target map further includes: Obtain the first state estimation information of the autonomous vehicle; Based on the target map, the target lane, the first state estimation information, and the obstacle information on the target lane, path planning is performed to obtain a planned trajectory, thereby achieving autonomous driving according to the planned trajectory.

8. The method according to claim 7, characterized in that, The process of achieving autonomous driving according to the planned trajectory includes: Obtain second state estimation information of the autonomous vehicle, wherein the second state estimation information is different from the first state estimation information; Based on the second state estimation information, the autonomous vehicle is controlled to drive along the planned trajectory to achieve autonomous driving.

9. An electronic device, characterized in that, It includes a memory and a processor coupled to each other, the processor being used to execute program instructions stored in the memory to implement an autonomous driving method for an autonomous vehicle as described in any one of claims 1-8.

10. A non-volatile computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed by a processor, is used to implement the autonomous driving method of the autonomous vehicle as described in any one of claims 1-8.

Images