A lane-level path planning method, device, equipment and readable storage medium

Abstract

The application relates to a lane-level path planning method and device, equipment and a readable storage medium, and relates to the technical field of automatic driving. The application comprises the following steps: obtaining a target planning path generated by a navigation map, road shape point information corresponding to the target planning path and a road LINK table; performing segmentation processing on the target planning path to obtain a plurality of segmented paths; performing shape point matching on each segmented path and a high-precision map based on the road shape point information and the road LINK table; for each segmented path, if the matching fails, determining a missing path segment according to the segmented path that fails to match, and determining target shape points corresponding to the starting point and the ending point of the missing path segment in the high-precision map; and generating a lane-level planning path corresponding to the missing path segment based on the road shape point information corresponding to the target shape points, the road LINK table and road attribute information. The application supplements the precision of the navigation map and a visual sensor through the high-precision map, thereby effectively improving the precision of path planning.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a lane-level path planning method, apparatus, device, and readable storage medium. Background Technology

[0002] In autonomous driving, map accuracy directly impacts the decision-making capabilities of the autonomous driving system, which in turn affects the control of the intelligent vehicle, thus influencing the safety and comfort of autonomous driving. Therefore, clear map data is crucial for autonomous driving systems, enabling precise location of the vehicle and better planning of a smooth and reasonable driving trajectory. This plays a key role in the safe and stable control of the intelligent vehicle. Thus, providing high-precision map data is critical for autonomous driving systems, effectively improving driving safety and enhancing the overall perception and decision-making capabilities of the autonomous driving system.

[0003] In related technologies, the combination of navigation maps and visual sensors is used to realize the path planning of autonomous vehicles. However, due to the insufficient accuracy of navigation maps, the autonomous driving system's monitoring and fine control of the vehicle is severely hindered. Furthermore, the limited detection range of visual sensors and external influences on visual sensors make it impossible to generate local high-precision maps, resulting in insufficient precision in trajectory planning and a sharp decrease in the safety of autonomous driving. Summary of the Invention

[0004] This application provides a lane-level path planning method, apparatus, device, and readable storage medium to solve the problem of low accuracy caused by the combination of navigation maps and visual sensors in related technologies.

[0005] Firstly, a lane-level path planning method is provided, including the following steps:

[0006] Obtain the target planning path generated by the navigation map, along with its corresponding road shape point information and road LINK table;

[0007] The target planned path is segmented to obtain multiple segmented paths;

[0008] Based on the road shape point information and the road LINK table, each segmented path is matched with the high-precision map using shape point matching.

[0009] For each segmented path, if a match fails, the missing road segment is determined based on the failed matching segmented path, and the target points corresponding to the start and end points of the missing road segment are determined in the high-precision map.

[0010] Based on the road shape point information corresponding to the target shape point, the road LINK table, and the road attribute information, a lane-level planning path corresponding to the missing road segment is generated.

[0011] In some embodiments, after the step of generating a lane-level planning path corresponding to the missing road segment based on the road shape point information corresponding to the target shape point and the road LINK table, the method further includes:

[0012] Control the intelligent driving system to perform function degradation;

[0013] After the control is downgraded, the intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

[0014] In some embodiments, after the step of determining the missing road segment based on the segmented path that failed to match, the method further includes:

[0015] Determine whether the starting point of the missing road segment is the starting point of the target planned path;

[0016] If so, then control the system to not activate the intelligent driving mode;

[0017] If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0018] In some embodiments, after the step of matching each segmented path with a high-precision map based on the road shape point information and the road LINK table, the method further includes:

[0019] For each segmented path, if a match is successful, the target road shape point information, target road LINK table, and target road attribute information of the high-precision map corresponding to the segmented path are generated.

[0020] A lane-level planning path is generated based on the target road shape point information, the target road LINK table, and the target road attribute information.

[0021] Secondly, a lane-level path planning device is provided, comprising:

[0022] The acquisition unit is used to acquire the target planning path generated by the navigation map and its corresponding road shape point information and road LINK table;

[0023] The segmentation unit is used to segment the target planned path to obtain multiple segmented paths.

[0024] A matching unit is used to perform shape point matching between each segmented path and a high-precision map based on the road shape point information and the road LINK table;

[0025] The processing unit is used to determine the missing road segment based on the failed matching for each segmented path, and to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0026] The planning unit is used to generate lane-level planning paths corresponding to the missing road segments based on the road shape point information, road LINK table, and road attribute information corresponding to the target shape point.

[0027] In some embodiments, the processing unit is further configured to:

[0028] The intelligent driving system is controlled to perform a function degradation process, so that the degraded intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

[0029] In some embodiments, the processing unit is further configured to:

[0030] Determine whether the starting point of the missing road segment is the starting point of the target planned path;

[0031] If so, then control the system to not activate the intelligent driving mode;

[0032] If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0033] In some embodiments, the processing unit is further configured to generate, for each segmented path, target road shape point information, target road LINK table and target road attribute information of a high-precision map corresponding to the segmented path if a match is successful;

[0034] The planning unit is also used to generate lane-level planning paths based on the target road shape point information, the target road LINK table, and the target road attribute information.

[0035] Thirdly, a lane-level path planning device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned lane-level path planning method.

[0036] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned lane-level path planning method.

[0037] This application provides a lane-level path planning method, apparatus, device, and readable storage medium, including acquiring a target planned path generated from a navigation map and its corresponding road shape point information and road LINK table; segmenting the target planned path to obtain multiple segmented paths; matching each segmented path with a high-precision map based on the road shape point information and the road LINK table; for each segmented path, if the matching fails, determining the missing road segment based on the failed matching segmented path, and determining the target shape points corresponding to the start and end points of the missing road segment in the high-precision map; generating a lane-level planned path corresponding to the missing road segment based on the road shape point information, road LINK table, and road attribute information corresponding to the target shape points. This application supplements the missing road segments caused by insufficient accuracy of the navigation map, limitations of the visual sensor's detection range, and susceptibility to external influences through a high-precision map, thereby generating lane-level planned paths for the missing road segments. In other words, it supplements the accuracy of the navigation map and visual sensor through a high-precision map, thus effectively improving the accuracy of path planning. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A flowchart illustrating a lane-level path planning method provided in an embodiment of this application;

[0040] Figure 2 This is a schematic diagram of data interaction in segmented path matching provided in an embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the target navigation trajectory provided in the embodiments of this application;

[0042] Figure 4 This is a schematic diagram of the segmented path provided in the embodiments of this application;

[0043] Figure 5 This is a schematic diagram illustrating the relationship between the planning paths at each layer, provided in an embodiment of this application.

[0044] Figure 6 This is a schematic diagram of the structure of a lane-level path planning device provided in an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] This application provides a lane-level path planning method, apparatus, device, and readable storage medium, which can solve the problem of low accuracy caused by combining navigation maps and visual sensors to achieve path planning in related technologies.

[0047] Figure 1 This application provides a lane-level path planning method, which includes the following steps:

[0048] Step S10: Obtain the target planning path generated by the navigation map and its corresponding road shape point information and road LINK table;

[0049] As an example, it is understandable that current levels of autonomous driving include manual driving (L0), driver assistance (L1), semi-autonomous driving (L2), conditional autonomous driving (L3), highly automated driving (L4), and fully automated driving (L5). Among them, under L3 autonomous driving conditions, the autonomous driving system will complete all driving operations and monitor the surrounding environment within the operating scenario, allowing the driver to disengage from the driving task. When external factors have a significant impact on the autonomous driving system, the autonomous driving system needs to make reasonable plans based on map information.

[0050] Currently, path planning for autonomous vehicles can be achieved by combining navigation maps with visual sensors. This involves using navigation maps to plan the driving trajectory while using visual sensors to detect the surrounding environment. The navigation map trajectory and the surrounding environment data are then fused with the visual sensor detection data to form a local high-precision map.

[0051] However, the use of traditional map data has the following pain points and difficulties: (1) Visual sensor scenarios are limited. For example, in many scenarios such as snowy days, worn lane lines, obstructions, or smog, both traditional visual and lidar sensors will fail to some extent. For example, in the complex road environment of the city, there are many traffic lights. Relying on a simple visual system, it is difficult to distinguish which lane the traffic light controls. (2) Traditional satellite positioning scenarios are limited. That is, when traditional satellites perform positioning, they usually use RTK (Real-Time Kinematic) plus an automotive-grade IMU (Inertial Measurement Unit). However, in complex scenarios such as overpasses and tunnels, GPS / RTK is very easy to be interfered with. In addition, in urban environments, tall buildings, mirror reflections, and even large bodies of water will also be affected by signal interference, making it impossible to accurately locate which level of overpass or which lane the vehicle is currently on. (3) The positioning accuracy in the navigation map is insufficient. Since the navigation map uses GPS positioning, the accuracy of simple satellite positioning in civilian use is generally around 10 meters, and the better performance can reach 5 meters. However, for autonomous driving, high-precision location information is required, and the support of the navigation map is inevitably inadequate. For example, during lane changing, it is necessary to locate which lane the vehicle is in, and there is also a lack of corresponding high-precision map data to effectively support and respond to it, which will seriously hinder the autonomous driving system's monitoring and refined control of the vehicle.

[0052] Therefore, while using navigation maps is relatively inexpensive, their insufficient accuracy severely hinders the autonomous driving system's monitoring and refined control of the vehicle. Furthermore, when external factors significantly impact the visual sensors, it becomes impossible to generate localized high-precision maps, leading to a sharp decline in autonomous driving safety. To address these issues, this embodiment fully utilizes the navigation map data from the in-vehicle navigation system and performs shape-point matching between the high-precision map and the navigation map to output a vehicle-grade planned trajectory. In other words, the high-precision map supplements the accuracy of the navigation map and the visual sensors, effectively improving the accuracy of path planning.

[0053] Specifically, after the vehicle is started, the driver sets the starting point and destination of the navigation on the in-vehicle navigation system according to the actual situation. After the navigation map completes the route planning, the driver selects and confirms one of the planned routes (i.e., the target planned route). Then, through the IVI (In-Vehicle Infotainment) and based on Ethernet, the road name, road type, and other road point information (i.e., the latitude and longitude information of each point) and the corresponding road LINK table of the target planned route are sent to the MPU (Map Positioning Control Unit).

[0054] It's important to note that the IVI (In-Vehicle Detection System) must send the entire route to the MPU (Multi-Purpose Unit) once the navigation map has been planned. Furthermore, regardless of whether the autonomous driving system is activated, the IVI must send the corresponding road shape point information and its associated road link table to the MPU every time the navigation route is updated. For example, if a driver takes over after the autonomous vehicle has traveled along the planned route and then drives outside the planned route, the IVI must send the re-planned route to the MPU once the autonomous driving system is activated again. Similarly, each time the autonomous driving system is activated, the planned route from the current location to the previously entered destination must be sent to the MPU. However, if the navigation map is re-planned while the autonomous driving system is deactivated, the re-planned route does not need to be sent to the MPU.

[0055] It should be understood that the road LINK table contains navigation trajectory information output by the navigation map based on the user's input of the starting point and destination, as shown in Tables 1 to 6.

[0056] Table 1 is the summary table corresponding to the Road LINK table.

[0057] Structure / Class Name Path Member Name describe Pathid Unique ID of the line Length Total length of the line Destpt:vector <lonlat> < / lonlat> Destination / Transit Point Links:vector <link> This path contains a collection of all link information. Function Description Third-party route information, including itinerary lists and route details.

[0058] Table 2 Links Table

[0059]

[0060]

[0061] Table 3 Linkpt Table

[0062] Structure / Class Name Link Member Name describe lon Longitude, the original longitude value is retained to 5 decimal places, and then multiplied by 10 to the power of 5. lat Dimensions, format same as longitude Function Description Latitude and longitude coordinates are encrypted using the coordinates of the State Bureau of Surveying and Mapping.

[0063] Table 4 Usage Table

[0064]

[0065]

[0066] Table 5 Type Table

[0067]

[0068] Table 6 Level Table

[0069]

[0070]

[0071] Step S20: Segment the target planned path to obtain multiple segmented paths;

[0072] As an example, in this embodiment, see Figure 2 As shown, when the IVI sends the target planned path (i.e., Path-Planning) after the navigation map is planned to the MPU, the MPU will perform data verification, that is, verify the data packet to determine the integrity of the data packet, and reply to the IVI with the received frame status, that is, feedback confirmation signal: ACK Path-Planning.

[0073] Once the MPU receives the complete target planning path (i.e., the complete navigation trajectory), it will segment the target planning path to obtain multiple segmented paths. For example, by segmenting it into small segments of 5km / 10km, the complete navigation map will be split into several smaller map segments.

[0074] Step S30: Based on the road shape point information and the road LINK table, perform shape point matching between each segmented path and the high-precision map;

[0075] As an example, in this embodiment, the MPU performs shape point matching on the segmented path and sends the feedback results to the ADCU (Automated Driving Control Unit). Specifically, for each segmented path, shape point matching is performed based on the road shape point information and road LINK table generated by the navigation map and the corresponding road LINK table in the high-precision map. That is, the latitude and longitude of the road shape points in the navigation map are matched with those in the high-precision map. If the latitude and longitude are the same or the difference between the two is within a preset range, the match is considered successful, meaning the path is continuous. If the latitude and longitude are different or the difference between the two exceeds the preset range, the match is considered unsuccessful, meaning the path is discontinuous.

[0076] It should be noted that shape and point matching between navigation maps and high-precision maps can be achieved through map matching algorithms based on Hidden Markov Models, map matching localization technology (which refers to the process of matching the latitude and longitude sampling sequence of the autonomous vehicle's driving trajectory with the road network of a high-precision map), or other algorithms capable of shape and point matching. Therefore, the specific method used can be determined according to actual needs and is not limited here.

[0077] Step S40: For each segmented path, if the matching fails, the missing road segment is determined based on the segmented path that failed to match, and the target points corresponding to the start and end points of the missing road segment are determined in the high-precision map respectively.

[0078] As an example, in this embodiment, when performing shape point matching on the trajectory generated by the navigation map in the MPU, if a disconnection occurs, shape point supplementation and reverse matching need to be performed according to the trajectory situation, and a matching failure signal (e.g., IVIMatchingResults = 0) is fed back to the ADCU. It should be noted that this embodiment will determine whether the planned path is continuous based on whether the shape point matching is successful; specifically: if the starting point of the currently participating segment path and the ending point of the previous segment path are not at the same latitude and longitude, it is determined to be discontinuous; if there is a road jump or a road shape point jump in the matching result of the currently participating segment path, it will also be determined to be discontinuous.

[0079] Specifically, the missing road segments are first identified by identifying the failed matching segments. Then, target shape points corresponding to the start and end points of the missing road segments are determined in the high-precision map. These target shape points are used to supplement the target planned path, thus completing the reverse matching. For example, if the end point of segment path A->C is C, and the start point of segment path C->D is C, if the connection point C of the two trajectories is not the same, or if a shape point in C->D fails to match, the trajectory is considered discontinuous. For instance, if the start point of segment path C->D is point C′ in the high-precision map, then the corresponding missing road segment is C->C′. In this case, the MPU will use the start point (C) and end point (C′) of the failed matching in the high-precision map to supplement the target planned path with point C′ as a target shape point, connecting the interrupted shape points, completing the result continuation, and thus obtaining a complete and more accurate planned path. It should be noted that if reverse matching fails, i.e., shape point supplementation cannot be performed, the result is segmented, i.e., the road shape point information and road LINK table of the segmented path A->C in the high-precision map are directly output.

[0080] Furthermore, after the step of determining the missing road segment based on the segmented path that failed to match, the method further includes:

[0081] Determine whether the starting point of the missing road segment is the starting point of the target planned path;

[0082] If so, then control the system to not activate the intelligent driving mode;

[0083] If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0084] As an example, in this embodiment, upon initial startup, if the matching result of the first segment path is successful, the intelligent driving mode is activated, and the MPU sends map data packets for the segment path. If the matching result of the first segment path fails, the intelligent driving mode is not activated. For example, if the first segment path in the target planning path is A->F with the destination F, and the latitude and longitude of point A in the navigation map are different from those in the high-precision map, it indicates that the matching result of the first segment path has failed, meaning the accuracy of the target planning path planned by the navigation map is very poor, and it is not suitable to activate the intelligent driving mode in this case. If a shape point matching problem occurs in the middle segment path of the target planning path, shape point supplementation and reverse matching will be performed based on the trajectory.

[0085] Step S50: Generate a lane-level planning path corresponding to the missing road segment based on the road shape point information, road LINK table, and road attribute information corresponding to the target shape point.

[0086] As an example, in this embodiment, after the reverse matching is completed, the road shape point information, road LINK table and road attribute information (such as speed limit information, lane width, etc.) corresponding to the target shape point in the high-precision map will be output. Then, based on the above information, the lane-level planning path corresponding to the missing road segment can be generated. That is, through this embodiment, the complete shape point data of the high-precision map and the road attribute information related to the shape point can be output, thereby realizing a complete lane-level planning path to improve the accuracy of path planning.

[0087] Furthermore, after the step of generating a lane-level planning path corresponding to the missing road segment based on the road shape point information corresponding to the target shape point and the road LINK table, the method further includes:

[0088] Control the intelligent driving system to perform function degradation;

[0089] After the control is downgraded, the intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

[0090] As an example, it's understandable that high-precision maps, due to their highly accurate confirmation of surrounding environmental information, enable highly precise trajectory planning, and can even be used independently for path planning in autonomous driving. However, maintaining the "freshness" of high-precision maps requires maintaining the map data through manual collection of road information, resulting in very high costs. These high costs are often unaffordable and unacceptable, leading to a compromise in the freshness of high-precision maps. Without guaranteed freshness, path planning using high-precision maps becomes impossible, rendering autonomous driving functions unusable.

[0091] In this embodiment, route planning is primarily achieved through the navigation map, while the high-precision map is used to supplement accuracy when the route planning accuracy is low. That is, the accuracy advantage of the high-precision map compensates for the accuracy of the navigation map; therefore, the high-precision map in this embodiment does not need to maintain high-precision "freshness." Specifically, if a segment of the path fails to match, a matching failure signal (e.g., IVIMatchingResults = 0) will be fed back to the ADCU. Upon receiving this feedback signal, the ADCU can control the intelligent driving system to downgrade, and the downgraded intelligent driving system will then drive according to the lane-level planned path updated by the reverse matching result. This ensures that the intelligent driving system can continue to drive normally even when the high-precision map cannot guarantee freshness, without directly exiting the intelligent driving mode.

[0092] Understandably, the MPU will distribute lane-level planning paths in segments as the vehicle's position changes, and before distributing the lane-level planning paths for each segment, it will send the matching results of that segment's road to the ADCU, so that the DACU can determine whether it is necessary to control the intelligent driving system to perform function degradation based on the matching results.

[0093] Furthermore, after the step of matching each segmented path with the high-precision map based on the road shape point information and the road LINK table, the method further includes:

[0094] For each segmented path, if a match is successful, the target road shape point information, target road LINK table, and target road attribute information of the high-precision map corresponding to the segmented path are generated.

[0095] A lane-level planning path is generated based on the target road shape point information, the target road LINK table, and the target road attribute information.

[0096] In this exemplary embodiment, after the intelligent system is activated, if the segmented path matching is successful, it indicates that the path is continuous, i.e., the road links are continuous. The MPU will then generate high-precision map shape point data and related road attributes, including the target road shape point information, target road link table, and target road attribute information corresponding to the segmented path. Based on this information, a lane-level planned path is then generated. (See also...) Figure 2 As shown, the MPU then sends the map data package (i.e., lane-level planning path) for that segment path and a matching success signal (e.g., IVIMatchingResults=1) to the ADCU to maintain the intelligent driving state.

[0097] The following combination Figure 3 and Figure 4 Illustrate the process and principle of shape point matching in MPU with an example.

[0098] Users set their destination on the navigation map and generate... Figure 3 The target navigation trajectory shown is from A to B, where A is the starting point (current location) and B is the destination; the IVI sends the target navigation trajectory generated by the navigation map to the MPU.

[0099] After receiving the complete target navigation trajectory sent by the IVI, the MPU will split the target navigation trajectory into, according to the rules, such as... Figure 4 The system displays several segmented paths. Internally, the MPU matches the map of each segmented path with a high-precision map, that is, it matches the latitude and longitude of the points of the segmented path in the navigation map with the latitude and longitude of the points of the high-precision map. If a segmented path is successfully matched, the system outputs the points of the high-precision map corresponding to that segmented path, as well as the road attributes, thus generating a lane-level planned path.

[0100] If a path segment fails to match, a reverse matching is required. For example, if the endpoint of A->C is C, and the starting point of C->D is C, and the connection point C of the two trajectories is not at the same point, or if the matching of a physical point in the C->D path fails, the trajectory is considered discontinuous. In this case, the MPU will use the starting point of the current path segment and the endpoint of the previous path segment in the high-precision map where the matching failed to occur to supplement the missing physical points according to the road conditions, thus completing the reverse matching. Simultaneously, the intelligent driving system will degrade and then proceed based on the reverse matching result. Therefore, see [link to relevant documentation]. Figure 5 As shown, in this embodiment, the target planning path of the IVI road layer is first generated through the navigation map, and then the shape point is matched with the navigation map through the high-precision map. When the matching result fails, that is, the target planning path is not continuous, the missing shape points in the target planning path will be supplemented through the high-precision map layer to complete the reverse matching, and then the lane-level planning path of the lane-level road layer will be generated.

[0101] In summary, compared to using navigation maps alone, this embodiment can generate high-precision maps covering a wider area as needed, with an accuracy range of 2km, 3km, 5km, or even 10km. Furthermore, compared to using high-precision maps alone, if an autonomous vehicle is driving on a newly constructed road, the lack of up-to-date high-precision maps results in a lack of relevant map data, making route planning impossible. This embodiment, however, can provide high-precision local map data by combining navigation maps with visual sensors, thereby effectively reducing costs.

[0102] It should be noted that the step numbers in the embodiments of this application do not limit the order of operations in the technical solution of this application.

[0103] This application also provides a lane-level path planning device, including:

[0104] The acquisition unit is used to acquire the target planning path generated by the navigation map and its corresponding road shape point information and road LINK table;

[0105] The segmentation unit is used to segment the target planned path to obtain multiple segmented paths.

[0106] A matching unit is used to perform shape point matching between each segmented path and a high-precision map based on the road shape point information and the road LINK table;

[0107] The processing unit is used to determine the missing road segment based on the failed matching for each segmented path, and to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0108] The planning unit is used to generate lane-level planning paths corresponding to the missing road segments based on the road shape point information, road LINK table, and road attribute information corresponding to the target shape point.

[0109] Furthermore, the processing unit is also used to: control the intelligent driving system to perform function degradation processing, so that the degraded intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

[0110] Furthermore, the processing unit is also used for:

[0111] Determine whether the starting point of the missing road segment is the starting point of the target planned path;

[0112] If so, then exit the intelligent driving mode.

[0113] If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

[0114] Furthermore, the processing unit is also used to generate target road shape point information, target road LINK table and target road attribute information of a high-precision map corresponding to each segmented path if a match is successful; the planning unit is also used to generate lane-level planning paths based on the target road shape point information, the target road LINK table and the target road attribute information.

[0115] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the device and each unit described above can be referred to the corresponding processes in the aforementioned lane-level path planning method embodiments, and will not be repeated here.

[0116] The lane-level path planning device provided in the above embodiments can be implemented as a computer program, which can, for example, Figure 6 It runs on the lane-level path planning device shown.

[0117] This application also provides a lane-level path planning device, including: a memory, a processor, and a network interface connected via a system bus. The memory stores at least one instruction, which is loaded and executed by the processor to implement all or part of the steps of the aforementioned lane-level path planning method.

[0118] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0119] A processor can be a CPU, or other general-purpose processors, DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), 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. The processor is the control center of a computer device, connecting all parts of the computer device through various interfaces and lines.

[0120] Memory can be used to store computer programs and / or modules. The processor performs various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on system usage, etc. Furthermore, memory may include high-speed random access memory (RAM), and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SMC (Smart Media Card), SD (Secure Digital) cards, flash memory cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0121] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements all or part of the steps of the aforementioned lane-level path planning method.

[0122] The embodiments of this application can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, ROM (Read-Only memory), RAM (Random Access memory), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0123] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, servers, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0124] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0125] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A lane-level path planning method, characterized by, Includes the following steps: Obtain the target planning path generated by the navigation map, along with its corresponding road shape point information and road LINK table; The target planned path is segmented to obtain multiple segmented paths; Based on the road shape point information and the road LINK table, each segmented path is matched with the high-precision map using shape point matching. For each segmented path, if a match fails, the missing road segment is determined based on the failed matching segmented path, and the target points corresponding to the start and end points of the missing road segment are determined in the high-precision map. Based on the road shape point information corresponding to the target shape point, the road LINK table, and the road attribute information, a lane-level planning path corresponding to the missing road segment is generated.

2. The lane-level path planning method of claim 1, wherein, After the step of generating a lane-level planning path corresponding to the missing road segment based on the road shape point information corresponding to the target shape point and the road LINK table, the method further includes: Control the intelligent driving system to perform function degradation; After the control is downgraded, the intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

3. The lane-level path planning method of claim 1, wherein, After the step of determining the missing road segment based on the segmented path that failed to match, the method further includes: Determine whether the starting point of the missing road segment is the starting point of the target planned path; If so, then control the system to not activate the intelligent driving mode; If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

4. The lane-level path planning method of claim 1, wherein, After the step of matching each segmented path with the high-precision map based on the road shape point information and the road LINK table, the method further includes: For each segmented path, if a match is successful, the target road shape point information, target road LINK table, and target road attribute information of the high-precision map corresponding to the segmented path are generated. A lane-level planning path is generated based on the target road shape point information, the target road LINK table, and the target road attribute information.

5. A lane-level path planning device characterized by comprising: include: The acquisition unit is used to acquire the target planning path generated by the navigation map and its corresponding road shape point information and road LINK table; The segmentation unit is used to segment the target planned path to obtain multiple segmented paths. A matching unit is used to perform shape point matching between each segmented path and a high-precision map based on the road shape point information and the road LINK table; The processing unit is used to determine the missing road segment based on the failed matching for each segmented path, and to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map. The planning unit is used to generate lane-level planning paths corresponding to the missing road segments based on the road shape point information, road LINK table, and road attribute information corresponding to the target shape point.

6. The lane-level path planning apparatus according to claim 5, characterized by, The processing unit is also used for: The intelligent driving system is controlled to perform a function degradation process, so that the degraded intelligent driving system drives based on the lane-level planned path corresponding to the missing road segment.

7. The lane-level path planning apparatus according to claim 5, wherein The processing unit is also used for: Determine whether the starting point of the missing road segment is the starting point of the target planned path; If so, then control the system to not activate the intelligent driving mode; If not, then proceed to determine the target points corresponding to the start and end points of the missing road segment in the high-precision map.

8. The lane-level path planning device as described in claim 5, characterized in that: The processing unit is also used to generate, for each segmented path, target road shape point information, target road LINK table and target road attribute information of a high-precision map corresponding to the segmented path if the matching is successful; The planning unit is also used to generate lane-level planning paths based on the target road shape point information, the target road LINK table, and the target road attribute information.

9. A lane-level path planning device characterized by comprising: include: A memory and a processor, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the lane-level path planning method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements the lane-level path planning method according to any one of claims 1 to 4.

Images