Lane change decision method and electronic device

Abstract

This disclosure provides a vehicle lane-changing decision-making method and electronic device, relating to the field of autonomous driving technology. The specific implementation scheme is as follows: based on the navigation path of the target vehicle, multiple drivable paths related to the navigation path are determined; the remaining distance of the current drivable path where the target vehicle is located is determined; if the remaining distance meets specified conditions, another drivable path with a larger remaining distance is determined; and the target vehicle is controlled to change lanes to the other drivable path with the larger remaining distance. According to the technical solution of this disclosure, multiple lane-level drivable paths can be quickly determined based on the vehicle's navigation path, and lane-changing needs can be detected in real time based on the remaining distance of the drivable path where the vehicle is located, enabling rapid lane-changing decisions and changing the vehicle to the most suitable drivable path, providing smoother lane-level lane-changing support for intelligent driving vehicles.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more particularly to a lane-changing decision-making method and electronic device. Background Technology

[0002] Most existing vehicle navigation systems are road-level navigation systems. Road-level navigation provides route planning based on roads, such as turning left from road A onto road B, driving straight for 1 kilometer on road B, and then turning right onto road C.

[0003] However, with the rapid development of autonomous driving technology, autonomous vehicles have placed higher demands on lane changing. Road-level navigation cannot meet the requirements of autonomous vehicles for planned routes, and existing lane-level navigation often does not provide smooth and comfortable lane changes. Summary of the Invention

[0004] This disclosure provides a lane-changing decision-making method and an electronic device.

[0005] According to one aspect of this disclosure, a lane-changing decision-making method is provided, comprising:

[0006] Based on the target vehicle's navigation path, identify multiple drivable routes related to the navigation path;

[0007] Determine the remaining distance on the currently drivable path where the target vehicle is located;

[0008] If the remaining distance meets the specified conditions, determine another drivable path with a greater remaining distance;

[0009] Control the target vehicle to change lanes to another drivable path with a greater remaining distance.

[0010] According to another aspect of this disclosure, an electronic device for lane-changing decision-making is provided, comprising:

[0011] At least one processor; and

[0012] The memory is communicatively connected to the at least one processor; wherein,

[0013] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods in any embodiment of this disclosure.

[0014] According to the technology disclosed herein, multiple drivable lanes at the lane level can be quickly determined based on the vehicle's navigation path, and lane-changing needs can be detected in real time based on the remaining distance of the drivable lane in which the vehicle is located. Lane-changing decisions can be made quickly to change the vehicle to the most suitable drivable lane, providing smoother lane-level lane-changing support for intelligent driving vehicles.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0016] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0017] Figure 1 This is a schematic flowchart of a vehicle lane-changing decision method according to an embodiment of the present disclosure;

[0018] Figure 2 This is a schematic diagram of high-precision map information corresponding to a navigation path obtained according to an embodiment of the present disclosure;

[0019] Figure 3 according to Figure 2 A schematic diagram of the topology map constructed from medium- and high-precision map information;

[0020] Figure 4 It is based on Figure 3 A schematic diagram of the drivable paths generated by traversing the topology graph;

[0021] Figure 5 This is a block diagram of an electronic device used to implement the vehicle lane-changing decision method of the embodiments of this disclosure. Detailed Implementation

[0022] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] Figure 1 This is a flowchart illustrating a vehicle lane-changing decision-making method according to an embodiment of the present disclosure, which may include:

[0024] S110, based on the navigation path of the target vehicle, determine multiple drivable routes related to the navigation path;

[0025] S120, determine the remaining distance of the currently drivable path where the target vehicle is located;

[0026] S130, if the remaining distance meets the specified conditions, determine another drivable path with a larger remaining distance;

[0027] S140, control the target vehicle to change lanes to another drivable path with a greater remaining distance.

[0028] For example, the navigation path can be a planned path for conventional road-level navigation, and the drivable path can be a lane-level path determined based on the navigation path. The remaining distance of the current drivable path can represent the distance between the current position of the target vehicle and the end of the current drivable path where the target vehicle is located. Meeting specified conditions reflects the lane-changing needs of the target vehicle determined based on the remaining distance of the current drivable path. Specified conditions can be that the remaining distance of the current drivable path is less than a preset distance, or that the remaining travel time corresponding to the remaining distance of the current drivable path is less than a preset time based on the target vehicle's current speed, etc. These conditions can be set according to specific circumstances and needs, and are not limited here.

[0029] Understandably, the target vehicle can determine its current lane and the corresponding currently drivable path based on its location information. During operation, it continuously monitors the remaining distance of its current drivable path. Based on this remaining distance, it detects lane-changing needs in real time and, if a lane-changing need is detected, pre-determines another drivable path to meet the requirement, thereby controlling the target vehicle to change lanes. This process enables smoother lane changes for the target vehicle, improving passenger comfort.

[0030] In one embodiment, step S110 may further include:

[0031] Obtain high-precision map information corresponding to the navigation path of the target vehicle;

[0032] Construct a topology map based on high-precision map information;

[0033] Based on the topology map, multiple drivable routes for the target vehicle are determined.

[0034] Figure 2 The high-precision map information corresponding to the navigation route is displayed. Each lane in the high-precision map information has its own lane ID, numbered from smallest to largest along the vertical dimension from the origin to the destination. Figure 2 Taking the innermost lanes as an example, they are numbered sequentially as 6, 11, 15, ..., 39, 44, indicating that lane number 6 is closer to the starting point, while lane number 44 is closer to the destination. Lateral dimensions are numbered from the outermost lane to the innermost lanes in ascending order. Figure 2Taking lanes numbered 1, 2, ..., 5, 6 as an example, lane number 1 corresponds to the outermost lane, while lane number 6 corresponds to the innermost lane.

[0035] like Figure 2 As shown, the target vehicle needs to enter the main road from the lanes represented by lane IDs 1, 2, and 7, and then exit the main road from the lanes represented by lane IDs 35, 40, and 45. This navigation path determines that... Figure 2 The road segment information corresponding to 3, 4, 5, 6, and 41, 42, 43, 44 is not included in the road segment information covered by the navigation path. Therefore, in the process of obtaining high-precision map information, it is only necessary to obtain high-precision map information for road segments other than those corresponding to 3, 4, 5, 6, and 41, 42, 43, 44, which reduces the amount of information that needs to be processed to construct the topology map and improves the efficiency of determining drivable routes.

[0036] Furthermore, the topology graph is constructed as follows:

[0037] The lanes in the high-precision map information are used as nodes, and the traffic relationships between lanes are used as edges;

[0038] Construct a topology graph based on nodes and edges.

[0039] For example, the traffic relationship between lanes can represent the feasibility of lane changing between lanes. That is, each node in the constructed topology graph can represent each lane in the road corresponding to the navigation path, and each edge in the topology graph can represent the traffic relationship between the two lane nodes connected to it.

[0040] Figure 3 It shows that according to Figure 2 A schematic diagram of the topology map constructed from medium- and high-precision map information.

[0041] like Figure 3 As shown, the lane node numbers in the topology graph can be taken from the lane IDs in the high-precision map information corresponding to the previously obtained navigation path. Based on this, the constructed topology graph does not include lane nodes corresponding to lane IDs 3, 4, 5, 6 and 41, 42, 43, 44. The bidirectional arrows between nodes represent the edges of the topology graph, indicating the traffic relationship between two lanes. For example, the two lanes corresponding to lane node 2 and lane node 7 have the following traffic relationship: Figure 3 The longitudinal traffic flow is shown. The two lanes corresponding to lane nodes 7 and 8 have the following traffic flow: Figure 3 The lateral driving communication relationship shown means that the traffic relationship can be to merge from the lane corresponding to lane node 7 to the lane corresponding to lane node 8.

[0042] For all high-precision map information, road segment information is updated very frequently. If all high-precision map information is constructed into a topology map and extracted according to navigation road segments, frequent checks and updates are required to modify the topology map. In contrast, the topology map construction and acquisition method in this embodiment only obtains the high-precision map information corresponding to the navigation path, which is more targeted and can reduce the computational load.

[0043] Optionally, the methods for determining a drivable path include:

[0044] Based on the opposite direction to the navigation path, traverse the corresponding nodes and edges in the connection topology graph to determine multiple drivable paths for the target vehicle.

[0045] Understandably, traversing the navigation path in the opposite direction—that is, from the destination back to the starting point—involves checking the lanes and the traffic relationships between them. This determines at least one drivable path in each segment of the navigation path, and then summarizes these paths to obtain multiple drivable paths for the target vehicle. For example, if the navigation path direction corresponds to lane nodes 1, 2, 7, 8, 12, ..., 31, 35, 40, 45, then traversing in reverse order in the direction of 45, 40, 35, 31, ..., 12, 8, 7, 2, 1, checking the traffic relationships between each lane, the lane corresponding to lane nodes 1, 2, 7, 8, 12, ..., 31, 35, 40, 45 is identified as a drivable path.

[0046] Compared to regular traversal, reverse traversal is result-driven, with fewer combinations of lanes, which can save time in determining drivable paths and improve computational efficiency.

[0047] It is understood that the above-described numbering methods for lane IDs in high-precision map information and the corresponding node numbering methods in the topology map are merely for better explanation of the embodiments of this application and are not intended to limit this application. In actual implementation, the numbering rules can be adaptively adjusted according to different scenarios and objectives, and these adjustments should also fall within the protection scope of the lane-changing decision method of this application.

[0048] In one implementation, the method for determining the drivable path further includes:

[0049] For any node in the topology graph, if the lane corresponding to any node is a ramp, determine the node corresponding to the outermost lane of the road connected to the ramp.

[0050] Connect the node corresponding to the ramp to the node corresponding to the outermost lane to determine a drivable path.

[0051] It is understandable that when a target vehicle is driving, it often needs to enter or exit ramps when changing lanes. Connecting the ramp to the node corresponding to the outermost lane of the road it connects to, and defining it as a drivable path, can allow vehicles to enter the ramp more smoothly.

[0052] Figure 4 According to Figure 3 The diagram shows the drivable routes generated by traversing the topological graph. In drivable routes 1, 2, and 3, all lane nodes are on a straight line and belong to the same road segment. Drivable route 5 is another road segment connected to routes 1, 2, and 3. Lane nodes 8, 12, 17, 22, 27, and 31 in drivable route 4 belong to the same road segment as drivable routes 1, 2, and 3. Lane nodes 35, 40, and 45 are ramps. Since lane nodes 8, 12, 17, 22, 27, and 31 are the outermost lanes connecting their respective road segments to the ramps, lane nodes 35, 40, and 45 are classified as part of the same drivable route as lane nodes 8, 12, 17, 22, 27, and 31.

[0053] In one embodiment, step S130 specifically includes:

[0054] For at least one drivable route that the target vehicle can change lanes, calculate the remaining distance of at least one drivable route;

[0055] At least one drivable path with a remaining distance greater than the remaining distance of the current drivable path is identified as another drivable path with a larger remaining distance.

[0056] For example, when it is detected that the remaining distance of the current drivable path meets the specified conditions, that is, when the lane-changing requirement of the target vehicle is known, it is necessary to determine the target of the lane-changing decision, that is, another drivable path with a larger remaining distance, among the drivable paths where the target vehicle can change lanes.

[0057] Understandably, the scenario where a target vehicle needs to change lanes, determined by the remaining distance of its current drivable path, indicates that, based on the navigation route, the target vehicle needs to move from its current drivable path into another road segment. In this case, only the drivable path connecting to the other road segment within the current road segment has a greater remaining distance than the other drivable paths. Based on the aforementioned method of determining the other drivable path with a greater remaining distance, the target vehicle can change lanes in advance to the drivable path connecting to the other road segment when it needs to enter another road segment, making the lane-changing process smoother.

[0058] Still with Figure 4For example, the preset distance can be set to 500m. Assuming that the condition specified in step S130 is that the remaining distance of the currently drivable route is less than the preset distance, if the target vehicle is traveling on route 2, and the target vehicle is currently in lane node 24, the end of route 2 is the termination position of lane node 38. That is, the remaining distance of route 2 is the sum of the lengths corresponding to lane nodes 29, 33, and 38. In this case, the sum of their lengths is less than 500m, so the remaining distances of routes 1, 3, and 4, which the target vehicle can switch to, are calculated. Since the remaining distances of routes 1 and 3 are the same as those of route 2, and route 4 has an additional length corresponding to a ramp node compared to routes 1, 2, and 3, its remaining distance is greater than that of routes 1, 2, and 3. Therefore, a decision can be made to switch to route 4, and the target vehicle can be controlled to switch to route 4, so that the target vehicle can enter the ramp more smoothly.

[0059] The method described in the above embodiments can detect lane-changing needs in real time based on the remaining distance of the current drivable path during vehicle operation, and quickly determine the corresponding drivable path when a lane-changing need is detected, making the lane-changing process more natural and smooth.

[0060] The specific settings and implementation methods of the embodiments of this application have been described above from different perspectives. Using the method provided in the above embodiments, a topology map can be quickly constructed based on the navigation path, multiple drivable paths at the lane level corresponding to the navigation path in the high-precision map information can be determined, and lane-changing needs can be detected in real time based on the remaining distance of the drivable path where the vehicle is located. Lane-changing decisions can be made quickly, and the vehicle can be changed to the most suitable drivable path, providing smoother lane-level lane-changing support for intelligent driving vehicles.

[0061] As an implementation of the above methods, this disclosure also provides a vehicle lane-changing decision-making device, which can be applied to a vehicle or the cloud, and the device may include:

[0062] The first determining module is used to determine multiple drivable paths related to the navigation path based on the navigation path of the target vehicle;

[0063] The distance determination module is used to determine the remaining distance of the target vehicle on the current drivable path.

[0064] The second determining module is used to determine another drivable path with a larger remaining distance if the remaining distance meets the specified conditions.

[0065] The lane-changing module is used to control the target vehicle to change lanes to another drivable path with a greater remaining distance.

[0066] For example, the first determining module mentioned above includes:

[0067] The acquisition unit is used to acquire high-precision map information corresponding to the navigation path of the target vehicle;

[0068] Topology graph construction unit, used to construct a topology graph based on high-precision map information;

[0069] The first determining unit is used to determine multiple drivable paths for the target vehicle based on the topology map.

[0070] Specifically, the topology graph building unit is used for:

[0071] The lanes in the high-precision map information are used as nodes, and the traffic relationships between lanes are used as edges;

[0072] Construct a topology graph based on nodes and edges.

[0073] For example, the first determining unit is specifically used for:

[0074] Based on the opposite direction to the navigation path, traverse the corresponding nodes and edges in the connection topology graph to determine multiple drivable paths for the target vehicle.

[0075] In one implementation, the first determining unit is further configured to:

[0076] For any node in the topology graph, if the lane corresponding to any node is a ramp, determine the node corresponding to the outermost lane of the road connected to the ramp.

[0077] Connect the node corresponding to the ramp to the node corresponding to the outermost lane to determine a drivable path.

[0078] For example, the second determining module described above includes:

[0079] The calculation unit is used to calculate the remaining distance of at least one drivable path for the target vehicle to switch lanes.

[0080] The second determining unit is used to determine at least one drivable path whose remaining distance is greater than the remaining distance of the current drivable path as another drivable path with a larger remaining distance.

[0081] The functions of each unit, module, or sub-module in the various devices of this disclosure embodiment can be found in the corresponding descriptions in the above method embodiments, and they have corresponding beneficial effects, which will not be repeated here.

[0082] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0083] Figure 5 A structural block diagram of an electronic device according to an embodiment of this application is shown. Figure 5 As shown, the electronic device includes a memory 510 and a processor 520, wherein the memory 510 stores instructions executable on the processor 520. When the processor 520 executes these instructions, it implements the method for identifying lane edges as described in the above embodiments. The number of memories 510 and processors 520 can be one or more. This electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0084] The electronic device may also include a communication interface 530 for communicating with external devices and exchanging data. The devices are interconnected using different buses and can be mounted on a common motherboard or otherwise as needed. The processor 520 can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). The bus can be divided into address buses, data buses, control buses, etc. For ease of illustration, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0085] Optionally, in a specific implementation, if the memory 510, processor 520, and communication interface 530 are integrated on a single chip, then the memory 510, processor 520, and communication interface 530 can communicate with each other through an internal interface.

[0086] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0087] This application provides a computer-readable storage medium (such as the memory 510 described above) that stores computer instructions, which, when executed by a processor, implement the method provided in this application.

[0088] Optionally, memory 510 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device for recognizing lane edges, etc. Furthermore, memory 510 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 510 may optionally include memory remotely generated relative to processor 520, which can be connected to the electronic device for recognizing lane edges via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0089] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other physical classes of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage media, or any other non-transferable media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0090] For example, the processor in the controller or electronic device includes an Automated-driving Domain Control Module (ADCM).

[0091] For example, the vehicle in this embodiment can be any power-driven vehicle such as a gasoline-powered vehicle, an electric vehicle, or a solar-powered vehicle. For example, the vehicle in this embodiment can be an autonomous vehicle.

[0092] Other components of the vehicle in this embodiment, such as the specific structure of the frame and wheels, as well as the connecting and fastening components, can adopt various technical solutions that are now and will be known in the future to those skilled in the art, and will not be described in detail here.

[0093] In the description of this specification, the terms "first" and "second" 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0094] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A lane-changing decision-making method, characterized in that, include: Based on the target vehicle's navigation path, identify multiple drivable routes related to the navigation path; Determine the remaining distance of the currently drivable path where the target vehicle is located; If the remaining distance meets specified conditions, determine another drivable route with a greater remaining distance, including: For at least one drivable route that the target vehicle can change lanes, calculate the remaining distance of the at least one drivable route; The drivable path with a remaining distance greater than the remaining distance of the current drivable path is identified as another drivable path with a larger remaining distance. Control the target vehicle to change lanes to another drivable path with a greater remaining distance.

2. The method according to claim 1, characterized in that, The navigation path based on the target vehicle determines multiple drivable routes related to the navigation path, including: Obtain high-precision map information corresponding to the navigation path of the target vehicle; Based on the high-precision map information, a topology map is constructed; Based on the topology map, the multiple drivable paths are determined.

3. The method according to claim 2, characterized in that, The construction of the topology map based on the high-precision map information includes: The lanes in the high-precision map information are used as nodes, and the traffic relationships between the lanes are used as edges; Construct a topology graph based on the nodes and edges.

4. The method according to claim 3, characterized in that, The determination of the multiple drivable paths based on the topology map includes: Based on the opposite direction to the navigation path, traverse and connect the corresponding nodes and edges in the topology graph to determine multiple drivable paths for the target vehicle.

5. The method according to claim 4, characterized in that, The step of determining the multiple drivable paths based on the topology map further includes: For any node in the topology graph, if the lane corresponding to any node is a ramp, determine the node corresponding to the outermost lane of the road connected to the ramp; Connect the node corresponding to the ramp to the node corresponding to the outermost lane to determine a drivable path.

6. An electronic device for lane-changing decision-making, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

7. The electronic device according to claim 6, characterized in that, The processor includes an autonomous driving domain control module.

Images