Autonomous driving method and apparatus, and intelligent driving device

Abstract

An autonomous driving method and apparatus, and an intelligent driving device. The method comprises: acquiring SD map navigation information, wherein the SD map navigation information indicates a first road navigation path from a first location to a second location, and the first road navigation path passes through at least two intersections; on the basis of traffic flow information corresponding to the first road navigation path, determining a first lane navigation path from the first location to the second location, the traffic flow information comprising at least one traffic flow, and the first lane navigation path indicating one or more lanes required to be traveled from the first location to the second location; and controlling a vehicle to travel from the first location to the second location along the first lane navigation path. The technical solution of the present application can be applied to the field of intelligent vehicles such as electric vehicles and new energy vehicles, and can improve, without relying on a high-definition map, the human-like driving and traffic efficiency of vehicles when traveling on previously untraveled roads.

Description

Autonomous driving methods, devices and intelligent driving equipment

[0001] This application claims priority to Chinese Patent Application No. 202410878708.0, filed on June 29, 2024, entitled "Autonomous Driving Method, Apparatus and Intelligent Driving Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to an autonomous driving method, apparatus, and intelligent driving device. Background Technology

[0003] With the rapid development of the automotive industry, many driver assistance and autonomous driving technologies have emerged, which can reduce driving stress and improve safety and traffic efficiency. Currently, most autonomous driving technologies rely on high-precision maps for navigation. However, high-precision maps have drawbacks such as high collection and production costs, long processing times, insufficient coverage, and difficulty in ensuring data freshness, making it difficult to promote autonomous driving technologies relying on high-precision maps nationwide or globally. If navigation relies solely on environmental information perceived by vehicle sensors without high-precision maps, the limited perception range of these sensors prevents the acquisition of information beyond their range, thus restricting the vehicle's autonomous driving capabilities and resulting in less human-like behavior in autonomous vehicles.

[0004] Therefore, an autonomous driving solution that is independent of high-precision maps and has a high degree of human-likeness urgently needs to be developed. Summary of the Invention

[0005] This application provides an autonomous driving method, apparatus, and intelligent driving device that can improve the human-likeness and traffic efficiency of vehicles when driving on roads they have never driven before, without relying on high-precision maps.

[0006] In a first aspect, an autonomous driving method is provided, which can be executed by an intelligent driving device, for example, by a computing platform of the intelligent driving device, or by a chip or circuit for the intelligent driving device; or, the method can also be executed by a cloud server associated with the intelligent driving device.

[0007] The method includes: acquiring standard definition (SD) map navigation information, the SD map navigation information indicating a first road navigation path from a first location to a second location, the first road navigation path passing through at least one intersection; determining a first lane navigation path from the first location to the second location based on traffic flow information corresponding to the first road navigation path, the traffic flow information including at least one traffic flow, the first lane navigation path indicating one or more lanes required to travel from the first location to the second location; and controlling the vehicle to travel from the first location to the second location along the first lane navigation path.

[0008] In some implementations, the first road navigation path can be the path before segmentation (i.e., the SD map navigation path), or it can be the navigation path after segmentation (i.e., the path obtained by dividing the SD map navigation path), or it can be other paths with the same starting and ending points as the SD map navigation path, but with different intermediate locations than the SD map navigation path.

[0009] It should be noted that the intersections involved in this application can be n-way intersections (such as ramp intersections, three-way intersections, crossroads, etc.), where n is an integer greater than or equal to 2. That is, each intersection includes at least two boundaries, and each of the at least two boundaries is connected to a road.

[0010] In the above technical solution, when the vehicle needs to travel from the target starting position to the target ending position, it does not rely on high-precision maps and does not require the vehicle to have historical driving records for the relevant road segments. The vehicle can be controlled to travel from the target starting position along the lane determined by the SD map navigation information and traffic flow information to the target ending position. In other words, the vehicle can gain familiarity with a road segment upon its first use (e.g., it can pass quickly and quickly determine its driving lane), which helps improve the human-likeness of the vehicle in autonomous driving scenarios, thereby enhancing the vehicle's intelligence level. In practical implementation, at least one traffic flow can be generated by small cars or private cars. Therefore, when planning lane-level navigation paths based on traffic flow information, lane selection and avoidance of special lanes (such as bus lanes) can be achieved. This eliminates the need to enumerate the design logic for planning paths in unknown driving scenarios, helping to reduce development costs. In practical implementation, at least one traffic flow included in the traffic flow information is a crowdsourced traffic flow. Determining lane-level navigation paths based on crowdsourced traffic flow has better robustness and foresight, helping to improve the human-likeness of autonomous driving functions.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the first road navigation path passes through at least two intersections.

[0012] In the above technical solution, when the first road navigation path passes through at least two intersections, it is easier to determine the road direction when the first road navigation path approaches the second location, which helps to reduce the computational complexity when determining the lane-level navigation path.

[0013] In conjunction with the first aspect, in certain implementations of the first aspect, the first road navigation path indicates that the journey from the first location to the second location passes through at least the first road, and the traffic flow information includes at least one traffic flow in the first road, the first road including multiple sub-road segments; determining the first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path includes: determining the target lane in each sub-road segment based on at least one traffic flow corresponding to each sub-road segment, the target lane being the lane in which the vehicle is traveling in each sub-road segment; determining the second lane navigation path in the first road based on the target lane in each sub-road segment, the second lane navigation path indicating one or more lanes required for travel in the first road, the first lane navigation path including the second lane navigation path.

[0014] In the aforementioned technical solution, matching the target lane for the first road segment helps improve the smoothness of the planned lane navigation path, thereby enhancing the vehicle's intelligence and the driving experience for passengers. Furthermore, for roads without clear lane markings, determining the vehicle's specific position on the road based on traffic flow information, and then controlling the vehicle's movement according to that position, helps improve traffic efficiency and safety on roads without clear lane markings.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, determining the target lane in each segment of road based on at least one traffic flow corresponding to each segment of road includes: determining at least two drivable lanes in each segment of road based on at least one traffic flow corresponding to each segment of road; determining the target lane from the at least two drivable lanes based on at least one of the following: the number of traffic flows in each of the at least two drivable lanes, or the direction of travel at the first intersection, wherein the first intersection is connected to the first road and the first intersection is adjacent to the second location.

[0016] In some implementations, there may be no lane markings in the first road. In this case, the number of lanes and the location of the lanes in the first road can be determined based on traffic flow information. This allows for control of the specific location of vehicles in the first road (or in the lanes determined based on traffic flow information).

[0017] In the aforementioned technical solution, when multiple drivable lanes exist on a road, the target lane can be determined based on the traffic volume in each drivable lane and / or the direction of travel at the first intersection. This reduces the frequency of lane changes for vehicles traveling on the road, improving driving safety. Furthermore, it avoids invalid lane changes (e.g., if a right turn is needed ahead, and the vehicle is already in the rightmost lane with no obstacles, there is no need to control the vehicle to change lanes; if the vehicle changes lanes, it is considered an invalid lane change), thus improving traffic efficiency and the driving experience for drivers.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the first road navigation path passes through the second intersection, and the traffic flow information includes at least one traffic flow in the second intersection; based on the traffic flow information corresponding to the first road navigation path, determining the first lane navigation path from the first location to the second location includes: determining the target location in the second intersection based on at least one traffic flow in the second intersection; determining the third lane navigation path based on the target location, the third lane navigation path being the path taken by the vehicle when passing through the second intersection, and the first lane navigation path including the third lane navigation path.

[0019] In the above technical solution, when the vehicle is in autonomous driving mode and the vehicle is too far from the intersection to obtain relevant perception information (such as road boundaries or lane lines for autonomous driving navigation) through the perception device, or the accuracy of the obtained perception information is insufficient, the driving path of the vehicle when passing through the intersection can be determined based on traffic flow information, thereby controlling the heading adjustment of the vehicle body, avoiding the vehicle from getting stuck near the intersection, and controlling the vehicle to avoid obstacles in the intersection. This can improve the pass rate and success rate of intelligent driving equipment at intersections in the absence of high-precision maps.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a first group of traffic flows and a second group of traffic flows based on a first starting point and a first ending point of a first road navigation path; wherein the first group of traffic flows includes at least one traffic flow in the first path, the second group of traffic flows includes at least one traffic flow in the second path, the starting points of both the first path and the second path are matched with the first starting point, and the ending points of both the first path and the second path are matched with the first ending point; determining a group of traffic flows as traffic flow information from the first group of traffic flows and the second group of traffic flows based on at least one of the following: the average speed of the first group of traffic flows and the average speed of the second group of traffic flows; or the time information of the vehicles departing from the first location.

[0021] In the above technical solution, the traffic flow used to determine the lane-level navigation path is determined based on the average speed of the traffic flow and the start time of the target journey (i.e., the time information of the vehicle departing from the first position), so that when planning the route, congested roads or impassable roads can be avoided, thereby improving the user's driving experience.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the SD map navigation information indicates multiple road navigation paths from a first location to a second location, each of the multiple road navigation paths passes through at least two intersections, and the multiple road navigation paths include a first road navigation path and a second road navigation path, and there is a first overlapping area between the first road navigation path and the second road navigation path, the length of the first overlapping area being greater than or equal to a length threshold.

[0023] In some implementations, the length of the first overlapping region refers to the length of the overlapping region parallel to the direction of the road navigation path.

[0024] In the above technical solution, setting an overlap area of ​​appropriate length between any two adjacent road navigation paths helps to improve the smoothness of the connection between the two adjacent road navigation paths and reduces the probability of vehicles driving slowly or getting stuck between the two adjacent road navigation paths.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the second road navigation path and the fourth lane navigation path correspond to each other, the target lane of the fourth lane navigation path in the first overlapping area is the first lane, the target lane of the first lane navigation path in the first overlapping area is the second lane, and the vehicle travels to the second position sequentially via the fourth lane navigation path and the first lane navigation path. The method further includes: determining a fifth lane navigation path in the first overlapping area based on the first lane and the second lane, the fifth lane navigation path including a path for changing from the first lane to the second lane; and controlling the vehicle to pass through the first overlapping area along the fifth lane navigation path.

[0026] In the above technical solution, when the lane-level navigation paths corresponding to two adjacent road navigation paths are not the same lane in the first overlapping area, the vehicle can be controlled to change lanes in the first overlapping area according to the position of the lane, which helps to improve traffic efficiency.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the traffic flow information also includes the average speed of the traffic flow, and the method further includes: determining a target speed based on the average speed of the traffic flow; controlling the vehicle to travel from a first position to a second position along a navigation path in the first lane, including: controlling the vehicle to travel from the first position to the second position along the navigation path in the first lane at the target speed.

[0028] In the above technical solution, vehicle speed can be planned based on traffic flow information to avoid vehicles exceeding road speed limits, which helps improve driving safety.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when controlling the vehicle to travel from the first position to the second position, obtaining environmental information of the current driving road, the environmental information including at least one of road boundaries, lane line positions, and obstacle positions; controlling the vehicle to travel from the first position to the second position along a first lane navigation path, including: controlling the vehicle to travel from the first position to the second position based on the environmental information and the first lane navigation path.

[0030] For example, environmental information can be acquired by the vehicle's perception system.

[0031] In the above technical solutions, for road sections with no traffic flow information or with little traffic flow information, the vehicle's movement can be controlled by combining the environmental information perceived by the vehicle. This can reduce the probability of vehicles getting stuck, improve the smoothness of vehicle traffic, and thus improve traffic efficiency and driving safety.

[0032] In a second aspect, an autonomous driving device is provided, comprising an acquisition unit and a processing unit, wherein the acquisition unit is configured to: acquire SD map navigation information, the SD map navigation information indicating a first road navigation path from a first location to a second location, the first road navigation path passing through at least one intersection; the processing unit is configured to: determine a first lane navigation path from the first location to the second location based on traffic flow information corresponding to the first road navigation path, the traffic flow information including at least one traffic flow, the first lane navigation path indicating one or more lanes required to travel from the first location to the second location; the processing unit is further configured to: control the vehicle to travel along the first lane navigation path from the first location to the second location.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the first road navigation path passes through at least two intersections.

[0034] In conjunction with the second aspect, in some implementations of the second aspect, the first road navigation path indicates that the journey from the first location to the second location passes through at least the first road, and the traffic flow information includes at least one traffic flow in the first road, the first road including multiple sub-road segments; the processing unit is configured to: determine the target lane in each sub-road segment based on at least one traffic flow corresponding to each sub-road segment, the target lane being the lane in which the vehicle is traveling in each sub-road segment; and determine the second lane navigation path in the first road based on the target lane in each sub-road segment, the second lane navigation path indicating one or more lanes required for travel in the first road, the first lane navigation path including the second lane navigation path.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: determine at least two drivable lanes in each segment of road based on at least one traffic flow corresponding to each segment of road; and determine a target lane from the at least two drivable lanes based on at least one of the following: the number of traffic flows in each of the at least two drivable lanes, or the direction of travel at the first intersection, wherein the first intersection is connected to the first road and is adjacent to the second location.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the first road navigation path passes through the second intersection, and the traffic flow information includes at least one traffic flow in the second intersection; the processing unit is used to: determine the target location in the second intersection based on at least one traffic flow in the second intersection; determine the third lane navigation path based on the target location, the third lane navigation path being the path taken by the vehicle when passing through the second intersection, and the first lane navigation path including the third lane navigation path.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: determine a first group of traffic flows and a second group of traffic flows based on a first starting point and a first ending point of the first road navigation path; wherein the first group of traffic flows includes at least one traffic flow in the first path, the second group of traffic flows includes at least one traffic flow in the second path, the starting points of both the first path and the second path are matched with the first starting point, and the ending points of both the first path and the second path are matched with the first ending point; and determine a group of traffic flows as traffic flow information from the first group of traffic flows and the second group of traffic flows based on at least one of the following: the average speed of the first group of traffic flows and the average speed of the second group of traffic flows; or the time information of the vehicle's departure from the first location.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the SD map navigation information indicates multiple road navigation paths from the first location to the second location, each of the multiple road navigation paths passes through at least two intersections, and the multiple road navigation paths include a first road navigation path and a second road navigation path, and there is a first overlapping area between the first road navigation path and the second road navigation path, the length of the first overlapping area being greater than or equal to a length threshold.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the second road navigation path and the fourth lane navigation path correspond to each other. The target lane of the fourth lane navigation path in the first overlapping area is the first lane, and the target lane of the first lane navigation path in the first overlapping area is the second lane. The vehicle travels to the second position sequentially via the fourth lane navigation path and the first lane navigation path. The processing unit is further configured to: determine the fifth lane navigation path in the first overlapping area based on the first lane and the second lane, the fifth lane navigation path including the path from the first lane to the second lane; and control the vehicle to pass through the first overlapping area along the fifth lane navigation path.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the traffic flow information also includes the average speed of the traffic flow, and the processing unit is further configured to: determine a target speed based on the average speed of the traffic flow; control the vehicle to travel from the first position to the second position along the navigation path of the first lane, including: controlling the vehicle to travel from the first position to the second position along the navigation path of the first lane at the target speed.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is further configured to: acquire environmental information of the current driving road when controlling the vehicle to travel from the first position to the second position, the environmental information including at least one of road boundary, lane line position, and obstacle position; the processing unit is further configured to: control the vehicle to travel from the first position to the second position based on the environmental information and the first lane navigation path.

[0042] Thirdly, an autonomous driving device is provided, the device comprising: a processor for executing a computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0043] In conjunction with the third aspect, in some implementations of the third aspect, the autonomous driving device also includes a memory.

[0044] Fourthly, an intelligent driving device is provided, which includes means as described in any of the possible implementations of the second to third aspects.

[0045] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the intelligent driving device is a vehicle.

[0046] Fifthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0047] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0048] In a sixth aspect, a computer-readable medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0049] In a seventh aspect, a chip is provided, the chip including circuitry for performing the method in any of the possible implementations of the first aspect described above. Attached Figure Description

[0050] Figure 1 is a functional schematic block diagram of the intelligent driving device provided in an embodiment of this application;

[0051] Figure 2 is a schematic diagram of the autonomous driving system architecture provided in an embodiment of this application;

[0052] Figure 3 is a schematic flowchart of a path planning method for autonomous driving provided in an embodiment of this application;

[0053] Figure 4 is a schematic diagram of an application scenario of the autonomous driving method provided in an embodiment of this application;

[0054] Figure 5 is a schematic diagram of the SD map navigation path segmentation results involved in the embodiments of this application;

[0055] Figure 6 is a schematic diagram showing the correspondence between traffic flow lines and lane-level navigation paths for a certain road segment provided in an embodiment of this application.

[0056] Figure 7 is a schematic diagram of the relationship between two adjacent segments of the lane-level navigation path in the SD map navigation path provided in the embodiment of this application;

[0057] Figure 8 is a schematic diagram of the lane-level navigation path at the intersection provided in an embodiment of this application;

[0058] Figure 9 is a schematic diagram of the lane-level navigation path from the starting position to the target position determined by the autonomous driving method provided in the embodiments of this application;

[0059] Figure 10 is a schematic diagram of an application scenario of the autonomous driving method provided in an embodiment of this application;

[0060] Figure 11 is a schematic flowchart of the autonomous driving method provided in an embodiment of this application;

[0061] Figure 12 is a schematic block diagram of the device provided in an embodiment of this application;

[0062] Figure 13 is another schematic block diagram of the device provided in the embodiments of this application. Detailed Implementation

[0063] Before introducing the solution of this application, let's first introduce the relevant concepts involved in this application:

[0064] 1. SD Map: The accuracy is generally at the meter level, and the richness is relatively low. It mainly includes road information and point of interest (POI) information. Among them, POI is point data in electronic map, which includes at least four attributes: name, address, coordinates, and category.

[0065] 2. High-definition (HD) maps: HD maps offer higher accuracy and richness than SD maps, with both absolute and relative accuracy at the centimeter level. In terms of richness, HD maps provide an environmental model of the autonomous vehicle's environment, including static high-definition maps and other dynamic information. The static high-definition map includes lane models, road components, and road attributes. Lane models include road details such as lane lines, lane center lines, and lane attribute changes. Other dynamic information includes all dynamic information within the intelligent network system, such as map dynamics, sensor information, driving behavior, and traffic dynamic information management.

[0066] 3. Traffic flow information: The traffic flow information corresponding to a road can include one or more traffic flows. Each traffic flow is the trajectory formed by one or more vehicles traveling on the road. Each traffic flow can include multiple coordinate points, the orientation and pose of each coordinate point, the speed of the traffic flow, the road information associated with the traffic flow, and the time (such as the time period in which the traffic flow was formed).

[0067] As mentioned above, current autonomous driving technologies largely rely on high-precision maps for navigation. However, high-precision maps have drawbacks such as high acquisition and production costs, long processing times, insufficient coverage, and difficulty in ensuring data freshness, making it difficult to promote autonomous driving technologies that rely on high-precision maps nationwide or globally. If navigation relies solely on environmental information perceived by vehicle sensors without high-precision maps, the limited perception range of these sensors prevents the acquisition of information beyond their range, thus restricting the vehicle's autonomous driving capabilities. For example, when a vehicle needs to pass through large or irregular intersections, or make left or right turns at intersections, it may be unable to obtain information such as lane position and road boundaries at the exit point, affecting its autonomous driving planning capabilities. For instance, the vehicle may be unable to determine the direction of deviation and travel, resulting in poor human-like behavior and low traffic efficiency.

[0068] In view of this, embodiments of this application provide an autonomous driving method, apparatus, and intelligent driving device that can determine a lane-level navigation path based on SD map navigation information and traffic flow information along the roads traversed from the starting position to the ending position, which helps to improve the human-likeness of the vehicle's autonomous driving function and the vehicle's traffic efficiency.

[0069] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0070] Figure 1 is a functional block diagram of an intelligent driving device provided in an embodiment of this application. As shown in Figure 1, the intelligent driving device 100 may include a perception system 120 and a computing platform 150. The perception system 120 may include several sensors for sensing information about the environment surrounding the intelligent driving device 100. For example, the perception system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or other positioning systems. As another example, the perception system 120 may also include one or more of the following: an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0071] Some or all of the functions of the intelligent driving device 100 can be controlled by the computing platform 150. The computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory to implement the corresponding functions.

[0072] The intelligent driving device 100 may include an intelligent driving system, which may include an advanced driving assistance system (ADAS) and an autonomous driving system (ADS). The intelligent driving system utilizes various sensors on the intelligent driving device (including but not limited to: lidar, millimeter-wave radar, camera devices, ultrasonic sensors, global positioning system, inertial measurement unit) to acquire information from the surroundings of the intelligent driving device, and analyzes and processes the acquired information to achieve functions such as obstacle perception, target recognition, intelligent driving device localization, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving the intelligent driving device.

[0073] Logically, intelligent driving systems generally include three main functional modules: a perception module, a decision-making module, and an execution module. The perception module senses the environment around the vehicle through sensors and inputs corresponding real-time data to the decision-making processing center. The perception module mainly includes onboard cameras, ultrasonic radar, millimeter-wave radar, and lidar. The decision-making module makes corresponding decisions based on the information obtained by the perception module using computing devices and algorithms. After receiving the decision signal from the decision-making module, the execution module takes corresponding actions, such as driving, changing lanes, steering, braking, and issuing warnings.

[0074] At different levels of autonomous driving (L0-L5), ADAS can achieve different levels of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. The aforementioned autonomous driving levels (L0-L5) are based on the classification standards of the Society of Automotive Engineers (SAE). L0 is no automation; L1 is driver assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly completed by the driver and the system, requiring the driver to take over dynamic driving tasks. At levels L4 and L5, the driver can completely transform into a passenger. Currently, the functions that ADAS can achieve mainly include, but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, forward cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keeping assist, rear collision warning, traffic sign recognition, traffic jam assist, and highway assist. It should be understood that the above-mentioned functions can have specific modes at different levels of autonomous driving (L0-L5). The higher the level of autonomous driving, the more intelligent the corresponding mode.

[0075] In this embodiment of the application, the computing platform 150 can determine the lane-level navigation path from the target start position to the target end position of the intelligent driving device based on the navigation path based on the SD map and the traffic flow information corresponding to the navigation path.

[0076] Figure 2 shows a schematic diagram of the autonomous driving system architecture provided in an embodiment of this application. As shown in Figure 2, the system includes a map information acquisition module 210, a navigation information generation module 220, and a planning and control module 240. The map information acquisition module 210, the navigation information generation module 220, and the planning and control module 240 may each include one or more processors from the computing platform 150 shown in Figure 1. Optionally, the navigation information generation module 220 may also include one or more processors located in a cloud server communicating with the intelligent driving device 100. Furthermore, the system shown in Figure 2 may also include a perception module 230, which may include one or more camera devices from the perception system 120 shown in Figure 1, or may also include one or more radars from the perception system 120. The functions of each module in the system shown in Figure 2 are described below.

[0077] (i) The map information acquisition module 220 is used to determine the SD navigation path between the target start and target end positions of the intelligent driving device based on the SD map, and then send the navigation path to the navigation information determination module 220. The navigation path is a road-level navigation path, and the navigation path may pass through multiple intersections.

[0078] (II) The navigation information determination module 220 is used to determine the lane-level navigation path between the target start position and the target end position of the intelligent driving device based on the SD navigation path between the target start position and the target end position of the intelligent driving device. More specifically, the navigation information determination module 220 includes an SD map navigation path segmentation module 221, a traffic flow trajectory matching module 222, and a target navigation path stitching module 223. The SD map navigation path segmentation module 221 is used to divide the SD navigation path into multiple road-level paths, each of which passes through at least two intersections. The traffic flow trajectory matching module 222 is used to determine the traffic flow information corresponding to each road-level path, and then cluster the multiple traffic flows included in the traffic flow information to determine the lane-level navigation path corresponding to that road segment. The target navigation path stitching module 223 is used to determine the target lane-level path from the target start position to the target end position of the intelligent driving device based on the lane-level navigation path corresponding to each road-level path.

[0079] In some implementations, when determining traffic flow information, the traffic flow trajectory matching module 222 can filter traffic flow information based on the start and end points of each road-level path. The filtered traffic flow can match the road-level path (i.e., the traffic flow direction follows the road-level path), or the filtered traffic flow may not match the road-level path (i.e., the traffic flow direction does not follow the road-level path). In some implementations, the traffic flow trajectory matching module 222 can determine traffic flow information based on information such as time period and speed. For example, it can filter traffic flow that coincides with the current travel time of the intelligent driving device, and / or filter traffic flow with an average speed greater than or equal to a speed threshold.

[0080] (III) The perception module 230 is used to acquire environmental information around the intelligent driving device and send it to the navigation information determination module 220. This environmental information includes road information, such as the road boundaries and lane lines of the road currently being driven by the intelligent driving device. For example, the perception module 210 may also include one or more processors to process the acquired perception information to obtain environmental information. For example, taking the perception information as an image, one or more processors in the perception module 210 can extract environmental information such as road boundaries, intersection boundaries, and lane lines from the acquired image.

[0081] (iv) The planning and control module 240 is used to calculate the control quantity for controlling the intelligent driving device to travel along the target lane-level path based on the target lane-level path, and output the control quantity to the actuator. When the actuator executes the control quantity, it controls the intelligent driving device to travel along the planned lane-level path. In some possible implementations, the actuator may include the steering and braking control system in the intelligent driving device 100.

[0082] It should be understood that the above modules are only an example, and in actual applications, these modules may be added or removed as needed. For example, in the system architecture shown in Figure 2, the SD map navigation path segmentation module 221 and the traffic flow trajectory matching module 222 can be merged into one module.

[0083] The above describes the autonomous driving system architecture provided in the embodiments of this application. The following details the process of implementing the path planning method and autonomous driving method for autonomous driving provided in the embodiments of this application based on the autonomous driving system shown in Figure 2.

[0084] The intelligent driving devices involved in the embodiments of this application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving device can be a vehicle, which is a vehicle in a broad sense, and can be a means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle. For ease of understanding, the following description uses a vehicle as an example of an intelligent driving device.

[0085] Figure 3 shows a schematic flowchart of a path planning method for autonomous driving provided in an embodiment of this application. This method 300 can be applied to the intelligent driving device shown in Figure 1, or it can be executed by the system shown in Figure 2. More specifically, this method 300 can be executed by the navigation information determination module 220, and it may include:

[0086] S301, Obtain SD navigation information, which indicates at least a navigation path from the vehicle's target starting position to the target ending position, passing through multiple intersections.

[0087] For example, the navigation path described above is the entire navigation path generated based on the SD map from the vehicle's target starting position to the target ending position. This navigation path consists of multiple shape points, each indicating a geographic location. It should be understood that this navigation path is a road-level navigation path, meaning that it can indicate which intersections the vehicle needs to pass through to reach its target ending position. However, when there are multiple lanes on the road, this navigation path cannot indicate which specific lane the vehicle is traveling in.

[0088] S302 divides the navigation path into multiple road-level paths, and each road-level path passes through at least two intersections.

[0089] In some implementations, the distance between the start and end points of each road-level path and the intersection is greater than or equal to a distance threshold of 1. In the example, the distance threshold of 1 can be 50 meters, 100 meters, or other values.

[0090] In some implementations, there is an overlapping area between two adjacent road-level paths, and the length of the overlapping area is greater than or equal to a distance threshold 2. For example, the distance threshold 2 can be 30 meters, 50 meters, or other values. For instance, the distance threshold 2 can be determined based on intersections traversed by both road-level paths; for example, the distance threshold 2 may be greater than or equal to the length of the intersection, or the overlapping area may cover the intersection. Here, the length of the overlapping area refers to its length parallel to the path direction, and the length of the intersection refers to its length along the path direction.

[0091] S303 determines the lane-level navigation path corresponding to each road-level path based on the traffic flow information corresponding to each road-level path.

[0092] In some implementations, the traffic flow information may include multiple traffic flows, each of which has a length greater than or equal to a length threshold. The starting point and ending point of each of the multiple traffic flows may satisfy at least one of the following: the starting point of each traffic flow coincides with the starting point of the road-level path; the starting point of each traffic flow is located before the starting point of the road-level path; the ending point of each traffic flow coincides with the ending point of the road-level path; the ending point of each traffic flow is located after the ending point of the road-level path; or the starting point of each traffic flow is located after the starting point of the road-level path and the ending point of each traffic flow is located before the ending point of the road-level path. The terms "before" and "after" mentioned above refer to the direction of traffic flow. More specifically, if the starting point of the traffic flow is before the starting point of the road-level path, it can be understood as: compared to the starting point of the road-level path, the starting point of the traffic flow is closer to the target starting position of the vehicles. If the starting point of the traffic flow is after the starting point of the road-level path, it can be understood as: compared to the starting point of the road-level path, the starting point of the traffic flow is closer to the target ending position of the vehicles. In other words, the traffic flow information corresponding to a road-level path can include multiple traffic flows within that road-level path, or it can include multiple traffic flows from other paths with the same starting and ending points as the road-level path. It should be noted that traffic flow within a path can be understood as: the traffic flow formed by vehicles traveling on the road corresponding to that path. For example, traffic flow within a road-level path refers to the traffic flow formed by vehicles traveling on the road corresponding to that road-level path.

[0093] For example, the length threshold can be 200 meters, or 300 meters, or other values. For example, the length threshold can be determined based on the length of the road-level path, such as 60% or 70% of the length of the road-level path.

[0094] In some implementations, before executing S303, the method further includes: determining the traffic flow information corresponding to each road-level path based on each road-level path segment.

[0095] For example, each traffic flow includes multiple coordinate points and the orientation pose of each coordinate point, or each traffic flow may also include one or more of the following: the speed of the traffic flow (such as the average speed of the traffic flow), the road information associated with the traffic flow (such as road signs), and the time associated with the traffic flow (such as the time period in which the traffic flow was formed, the date in which the traffic flow was formed, etc.).

[0096] In one example, multiple traffic flows that match each road-level path can be filtered out, meaning the traffic flow information includes multiple traffic flows within the road-level path. In other words, each traffic flow satisfies at least one of the following: the coordinates of each traffic flow are located on the road corresponding to the road-level path, or the road identifier associated with each traffic flow is consistent with the road identifier corresponding to the road-level path.

[0097] In another example, multiple traffic flows whose starting and ending points coincide with the starting and ending points of each road-level path can be filtered based on the path's starting and ending points. This means the traffic flow information includes multiple traffic flows from another path with the same starting and ending points as the road-level path. Specifically, the starting point of each traffic flow must be before (or coincide with) the starting point of the road-level path, and the ending point of each traffic flow must be after (or coincide with) the ending point of the road-level path. Furthermore, at least one point in the middle of each traffic flow must not be located within the road-level path.

[0098] In some implementations, determining the traffic flow information corresponding to each road-level path can be further refined to: determining the traffic flow information corresponding to each road-level path based on each road-level path and the average speed of the traffic flow.

[0099] For example, consider a road-level path consisting of multiple road segments, including road-level path a. Road-level path a includes a starting point a and an ending point a. Road-level path a begins at starting point a, passes through intersection 1, intersection 2, and intersection 3, and ends at ending point a. In addition to road-level path a, the route from starting point a to ending point a also includes path a', which begins at starting point a, passes through intersection 1, intersection 2', and intersection 3, and ends at ending point a. If, based on the average speed of traffic flow in road-level path a, it is determined that the travel time from starting point a to ending point a via road-level path a is 1; and based on the average speed of traffic flow in path a', it is determined that the travel time from starting point a to ending point a via path a' is 2, and the travel time 1 is greater than the travel time, then multiple traffic flows in path a' are selected as traffic flow information. For instance, if traffic is congested due to road construction or other reasons on the road corresponding to road-level path a, resulting in a slow traffic flow in road-level path a, traveling via road-level path a to the destination would lead to excessively long travel time and a poor driving experience. Therefore, for the above scenario, filtering the traffic flow in path a' from the starting point a to the ending point a as the traffic flow information corresponding to the road-level path a helps to improve the traffic efficiency of vehicles.

[0100] In other implementations, the traffic flow information corresponding to each road-level path is determined. This can be further refined as follows: the traffic flow information corresponding to each road-level path is determined based on each road-level path, the average speed of the traffic flow, and the start time corresponding to the vehicle's target journey. Here, the target journey is the journey from the target starting position to the target ending position, and the start time corresponding to the target journey can be the time of departure from the target starting position.

[0101] For example, taking multiple road-level paths including road-level path a as an example, and from start point a to end point a, in addition to road-level path a, it also includes the aforementioned path a'. If the average speed of traffic flow in road-level path a is greater than the average speed of traffic flow in path a' between 6:30 AM and 9:00 AM, and the average speed of traffic flow in road-level path a is less than the average speed of traffic flow in path a' between 5:00 PM and 7:00 PM, if it is determined that the vehicle arrives at road-level path a between 6:30 AM and 9:00 AM based on the start time corresponding to the target trip, then the traffic flow in road-level path a is selected as the traffic flow information corresponding to road-level path a. If it is determined that the vehicle arrives at road-level path a between 5:00 PM and 7:00 PM based on the start time corresponding to the target trip, then the traffic flow in path a' is selected as the traffic flow information corresponding to road-level path a.

[0102] In some implementations, determining the lane-level navigation path corresponding to each road-level path based on the traffic flow information can be refined as follows: clustering multiple traffic flows included in the traffic flow information to determine the distribution of traffic flow along the width of the road corresponding to the road-level path, and then determining the lane the vehicle travels in that road based on the distribution. For example, the road corresponding to each road-level path can be further divided into multiple sub-roads, and for each sub-road, the distribution of traffic flow along the width of that sub-road is determined. In some implementations, this distribution can be represented by a Gaussian distribution, where the peak of the Gaussian distribution indicates the coordinates in the sub-road, which can indicate a lane within that sub-road; that is, the peak position of the Gaussian distribution represents the vehicle's position within that sub-road segment. Furthermore, for a road-level path, by concatenating the peak value (e.g., the maximum peak value) of the Gaussian distribution corresponding to each sub-road segment, the lane-level navigation path corresponding to that road-level path can be obtained.

[0103] In some implementations, the lane-level navigation path corresponding to each road-level path is determined based on the traffic flow information. This can be further refined as follows: Traffic flow at multiple fixed locations along each road-level path is clustered to obtain the traffic flow distribution at each fixed location (e.g., obtaining a Gaussian distribution curve of the traffic flow at each fixed location, or obtaining the number of traffic flows at different locations parallel to the width of the road-level path at each fixed location). These multiple fixed locations can be evenly distributed along the road-level path, each fixed location can be a line segment parallel to the width of the road-level path, and the distance between any two adjacent fixed locations can be a fixed distance (e.g., 5 meters, 10 meters, or other distances). Then, based on the traffic flow distribution, a target location is determined for each fixed location, which can indicate a lane. For example, the target location can be the location with the largest number of traffic flows parallel to the width of the road-level path at that fixed location. Based on the target location corresponding to each fixed location, a lane-level navigation path is obtained for that road-level path segment. For example, by sequentially connecting the target locations corresponding to each fixed location, a lane-level navigation path is obtained for that road-level path segment. Furthermore, based on the lane-level navigation path, the vehicle can be controlled to sequentially travel along the target locations corresponding to each fixed location.

[0104] In some implementations, the lane-level navigation path corresponding to each road-level path is determined based on the traffic flow information. This can be further refined as follows: multiple traffic flows included in the traffic flow information are clustered using a clustering algorithm to obtain at least one traffic flow cluster; then, each traffic flow within the at least one cluster is clustered using a clustering algorithm to obtain the lane-level driving path of each traffic flow on the road. In other words, the lane-level navigation path corresponding to each road-level path can include at least one lane-level navigation path, and vehicles can control lane changes on the road based on at least one lane-level navigation path.

[0105] In some implementations, the lane-level navigation path corresponding to a road-level path may include pose information of one or more points, which indicates the coordinates and pose angle of that point.

[0106] S304, based on the lane-level navigation path corresponding to each road-level path, determine the target lane-level path from the vehicle's target start position to the target end position.

[0107] In some implementations, the lane-level navigation path corresponding to each road-level path is sequentially spliced ​​together to obtain the target lane-level path.

[0108] It should be noted that after determining the target lane-level path, the vehicle can achieve autonomous driving based on the target lane-level path. Specifically, the vehicle can control itself to travel from the target starting position to the target ending position according to the target lane-level path.

[0109] In some implementations, the target speed of the vehicle on the road corresponding to the road-level path can be determined based on the traffic flow information. This allows the vehicle to be controlled to achieve autonomous driving along the target lane-level path at the target speed. For example, if the speed limit of the lane-level navigation path corresponding to the road-level path varies at different times, the target speed can be determined based on the start time of the target journey.

[0110] In practical implementation, each segment of a multi-segment road-level path may have corresponding traffic flow information; alternatively, a segment of a multi-segment road-level path may lack traffic flow information. For a road-level path b with corresponding traffic flow information, a lane-level navigation path can be determined, and the vehicle can be controlled to travel along this path from its starting point to its ending point. For a road-level path c without traffic flow information, the vehicle can combine the road-level path with road information identified by its perception system (such as lane lines, road boundaries, and obstacle locations) to control its travel along road-level path c from its starting point to its ending point.

[0111] The path planning method for autonomous driving provided in this application embodiment can plan a lane-level navigation path for the vehicle from the target starting position to the target ending position without relying on high-precision maps or requiring the vehicle to have historical driving records of relevant road segments. This helps improve the human-likeness of the vehicle in autonomous driving scenarios and even allows the vehicle to gain a familiar road experience when driving on a certain road segment for the first time (e.g., it can pass quickly and quickly determine the driving lane), thereby improving the intelligence level of the vehicle.

[0112] To facilitate understanding of the technical methods of this application, the path planning method and autonomous driving method provided by the embodiments of this application are described in detail below with reference to Figures 4 to 10.

[0113] Figure 4 illustrates an application scenario of the path planning method and autonomous driving method provided in this application embodiment. As shown in Figure 4, the starting point can be considered as an example of the target starting position in method 300, and the ending point can be considered as an example of the target ending position in method 300. The gray guiding route shown in Figure 4 is the navigation path indicated by the SD navigation information in method 300. As can be seen from Figure 4, the navigation path indicated by the SD navigation information needs to pass through intersection a to intersection e sequentially from the starting point to the ending point.

[0114] Furthermore, the navigation path indicated by the SD navigation information is divided into multiple road-level paths. In one example, as shown in Figure 5(a), the multiple road-level paths include road-level paths AB1, A1B2, and A2B. Road-level path AB1 passes through intersections a and b, road-level path A1B2 passes through intersections b, c, and d, and road-level path A2B passes through intersections d and e. The overlapping area between road-level paths AB1 and A1B2 covers intersection b (i.e., the length of the overlapping area is greater than the length of intersection b). In another example, as shown in Figure 5(b), the multiple road-level paths include road-level paths AB1', A1'B2', and A2B. Road-level path AB1' passes through intersections a, b, and c, road-level path A1'B2' passes through intersections c and d, and road-level path A2B passes through intersections d and e. It should be understood that the road-level path division method shown in Figure 5 is only an example. In actual implementation, for the navigation path shown in Figure 4, more or fewer road-level paths can be divided. For example, two road-level paths can be divided, each passing through three intersections; or four road-level paths can be divided, each passing through two intersections.

[0115] Multiple traffic flows determined from a single road-level path within a multi-segment road-level path can be illustrated as shown in Figure 6(a), where each traffic flow line represents a single traffic flow. For example, the road corresponding to this road-level path (hereinafter referred to as road-level path d) includes three lanes (i.e., lane 1, lane 2, and lane 3). Alternatively, the three lanes shown in Figure 6(a) can also be those corresponding to a path with the same start and end points as road-level path d. The determined multiple traffic flows corresponding to road-level path d include multiple traffic flows located in lane 2, multiple traffic flows changing from lane 3 to lane 2, and multiple traffic flows changing from lane 3 to lane 2 and then back to lane 1. Further, the road is divided into multiple segments (e.g., segment 1, segment 2, segment 3, and segment 4, a total of four segments), and the traffic flows in each segment are clustered to obtain a traffic flow distribution representation for each segment. For example, the traffic flow distribution representation can be a Gaussian distribution curve, where the peak value of the Gaussian distribution curve represents the location with more traffic. The Gaussian distribution of each segment may include a single peak or multiple peaks. When multiple peaks are included, it indicates that there are many vehicles traveling at the locations corresponding to multiple peaks in that road segment. It should be noted that if segment 4 is adjacent to intersection ①, and the road-level path d indicates a left turn at intersection ①, then the peak of the Gaussian distribution curve corresponding to segment 4 represents that both lane 1 and lane 2 support left turns at intersection ①; if segment 4 is adjacent to intersection ①, and the road-level path d indicates going straight at intersection ①, then the peak of the Gaussian distribution curve corresponding to segment 4 represents that both lane 1 and lane 2 support going straight at the intersection adjacent to segment 4.

[0116] By sequentially concatenating the peak values ​​of the Gaussian distribution curves of each segment, the lane-level navigation path corresponding to the road-level path d can be obtained, specifically as shown in Figure 6(b). In some implementations, when one or more segments include multiple peak values, the lane-level navigation path can be determined based on the lane the vehicle is in when entering the segment and the number of lane changes. For example, if segment 1 and intersection ② are adjacent, and road-level path d only passes through intersections ② and ①, and there is a neighboring road-level path e before road-level path d (i.e., closer to the target starting position), and the lane-level navigation path corresponding to road-level path e instructs the vehicle to travel through intersection ② to lane 3, then for segment 1 of road-level path d, the lane-level navigation path can pass through the peak value of lane 3 instead of the peak value of lane 2, to enhance the connection between road-level path e and road-level path d. Furthermore, for segments 2, 3, and 4, the lane-level navigation path can sequentially pass through the peak value of lane 2 to reduce the number of lane changes. For example, intersection ② and intersection ① can be intersection a and intersection b as shown in Figure 4, or intersection ② and intersection ① can be intersection d and intersection e as shown in Figure 4.

[0117] In some implementations, when a segmented Gaussian distribution curve includes multiple peaks, each peak has a different height. The height of a peak can be interpreted as representing the amount of traffic; the higher the peak, the more traffic there is at that location. Therefore, when a segmented Gaussian distribution curve includes multiple peaks, the determined lane-level navigation path can be found through the peak with the highest peak.

[0118] It should be noted that the number of segments shown in Figure 6 is only an illustrative example. In actual implementation, a road corresponding to a road-level path can also be divided into more or fewer segments. For example, the length of each segment along the path direction can be a fixed length (such as 5 meters, 10 meters, or other values), or any two segments in a road corresponding to a road-level path can have different lengths along the path direction.

[0119] In some implementations, road-level path f and road-level path g are two adjacent road-level paths, and as mentioned above, there is an overlapping area between them. If, as shown in Figure 7, the lane-level navigation path corresponding to road-level path f is driving path 1, and the lane-level navigation path corresponding to road-level path g is driving path 2, then in the overlapping area of ​​road-level paths f and g, driving path 1 is located in lane a, and driving path 2 is located in lane c. Therefore, when splicing driving paths 1 and 2, the path in the overlapping area can be a path changing from lane a to lane c, as shown in the transition path in Figure 7. For example, road-level path f and road-level path g can be road-level path AB1 and road-level path A1B2 as shown in Figure 5(a), or road-level path f and road-level path g can be road-level path A1B2 and road-level path A2B as shown in Figure 5(a), or road-level path f and road-level path g can be road-level path AB1' and road-level path A1'B2' as shown in Figure 5(b), or road-level path f and road-level path g can be road-level path A1'B2' and road-level path A2B as shown in Figure 5(b).

[0120] Figures 6 and 7 illustrate how to determine lane-level navigation paths based on traffic flow information. In practice, the driving path at the intersection between two road segments can also be determined based on traffic flow information. Specifically, when there are obstacles at the intersection, lane-level navigation paths that bypass the obstacles can be determined based on traffic flow information. Figure 8 shows a schematic diagram of traffic flow distribution at an intersection. As shown in Figure 8(a), the presence of obstacles at the intersection means that when a vehicle travels from the left-turn lane of Road 1 to Road 2, it can only travel to the leftmost or rightmost lane of Road 2. That is, the traffic flow information includes multiple traffic flows traveling from the left lane of Road 1 to the left lane of Road 2, and multiple traffic flows traveling from the left lane of Road 1 to the right lane of Road 2. Based on the traffic flow information, the lane-level navigation path from Road 1 through the intersection to Road 2 can be determined, including driving path a and driving path b, as shown in Figure 8(b). In one example, when multiple paths exist at the intersection, a path can be determined from the multiple paths based on the path distance as the lane-level navigation path for the vehicle passing through the intersection. For example, in Figure 8(b), for driving paths a and b, since driving path b has a shorter distance, it can be determined as the lane-level navigation path when the vehicle passes through the intersection. In another example, if the intersection between road 1 and road 2 is the end intersection of road-level path h (such as intersection b through road-level path AB1), and the intersection between road 1 and road 2 is also the end intersection of road-level path i (such as intersection b through road-level path A1B2), then a path can be determined from multiple paths based on the lane-level navigation path corresponding to road-level path i, as the lane-level navigation path when the vehicle passes through the intersection. For example, if road-level path i indicates that the vehicle should travel from road 2 to road 3 via intersection ③, and the lane-level navigation path corresponding to road-level path i indicates that the vehicle needs to turn right at intersection ③ to travel to road 3, then for driving paths a and b shown in Figure 8(b), driving path a can be determined as the lane-level navigation path when the vehicle passes through the intersection; if the lane-level navigation path corresponding to road-level path i indicates that the vehicle needs to turn left at intersection ③ to travel to road 3, then for driving paths a and b shown in Figure 8(b), driving path b can be determined as the lane-level navigation path when the vehicle passes through the intersection.

[0121] In some implementations, the lane configuration of the road between two adjacent intersections (a to e) is shown in Figure 9. Each lane between any two adjacent intersections can be considered a one-way lane. For example, the three lanes between intersections a and b all have a travel direction from intersection a to intersection b. For instance, the navigation path shown in Figure 4 is divided into multiple road-level paths as shown in Figure 5(a). Traffic flow information is determined based on each road-level path, and then the lane-level navigation path corresponding to each road-level path is determined based on the traffic flow information. For example, the lane-level navigation path corresponding to road-level path AB1 is shown by the gray short dashed line, the lane-level navigation path corresponding to road-level path A1B2 is shown by the black short dashed line, and the lane-level navigation path corresponding to road-level path A2B is shown by the black dotted line. The overlapping area between two adjacent road-level paths is shown in the gray shaded area. The lane-level navigation paths corresponding to each road-level path are then concatenated sequentially to obtain the target lane-level path, as shown in Figure 9. More specifically, when there is an obstacle at intersection d, the target lane-level path at intersection d can be a path that bypasses the obstacle, determined based on traffic flow information.

[0122] In some implementations, the navigation path shown in Figure 4 is divided into multiple road-level paths as shown in Figure 5(b). For road-level path AB1', the path with the same origin and destination also includes the path shown in Figure 10, which sequentially passes through intersections a, b', and c. When determining the traffic flow information corresponding to road-level path AB1', if the average speed of the traffic flow in the path passing through intersections a, b', and c is determined to be faster than the average speed of the traffic flow in road-level path AB1', then the lane-level navigation path corresponding to road-level path AB1' can be determined based on the traffic flow in the path passing through intersections a, b', and c. That is, the lane-level navigation path corresponding to road-level path AB1' is a lane-level path sequentially passing through intersections a, b', and c.

[0123] Figure 11 shows a schematic flowchart of an autonomous driving method 1100 provided in an embodiment of this application. The method 1100 can be executed by the intelligent driving device 100 shown in Figure 1, or it can be executed by the system shown in Figure 2. The method 1100 includes:

[0124] S1110, Obtain SD map navigation information, the SD map navigation information indicates a first road navigation path from the first location to the second location, the first road navigation path passes through at least one intersection.

[0125] In some implementations, the first road navigation path passes through at least two intersections.

[0126] For example, the SD map navigation information may include the SD navigation information in method 300, or the SD map navigation information may also include other information that can indicate a road-level navigation path from the target start position to the target end position.

[0127] When the SD map navigation information is the SD navigation information in method 300, in one example, the first position and the second position can be the target starting position (the starting point in Figure 4) and the target ending position (the ending point in Figure 4), respectively. In this case, the first road navigation path can be the entire path from the first position to the second position, such as the road-level path from the starting point through intersection a to e to the ending point as shown in Figure 4; or, the first road navigation path can also be a segment of the road-level path from the first position to the second position, such as any one of the road-level paths AB1, A1B2, or A2B as shown in Figure 5. In another example, the first position and the second position can also be any two positions between the target starting position and the target ending position, such as the first position being a position between intersection c and intersection d as shown in Figure 4, and the second position being a position between intersection e and the ending point as shown in Figure 4. In this case, the first road navigation path can be the entire path from the first position to the second position, such as the road-level path A2B as shown in Figure 5.

[0128] In other words, the first road navigation path can be the path before segmentation (i.e., the navigation path indicated by SD navigation information), or it can be the navigation path after segmentation (i.e., the path obtained by dividing the navigation path indicated by SD navigation information), or it can be another path whose origin and destination are the same as the navigation path indicated by SD navigation information, but whose intermediate locations are different from the navigation path indicated by SD navigation information.

[0129] S1120, based on the traffic flow information corresponding to the first road navigation path, determine the first lane navigation path from the first location to the second location. The traffic flow information includes at least one traffic flow. The first lane navigation path indicates one or more lanes that need to be taken to travel from the first location to the second location.

[0130] For example, traffic flow information may include the traffic flow information in the foregoing embodiments, and the method for determining traffic flow information can be referred to the description in method 300, which will not be repeated here.

[0131] In some implementations, the first road navigation path indicates that the journey from the first location to the second location passes through at least one first road, and the traffic flow information includes at least one traffic flow in the first road, which comprises multiple sub-road segments. Therefore, the step in S1120 of determining the first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path can be refined as follows: Based on at least one traffic flow corresponding to each sub-road segment, determine the target lane in each sub-road segment, where the target lane is the lane the vehicle is in when traveling in each sub-road segment; based on the target lane in each sub-road segment, determine the second lane navigation path in the first road, where the second lane navigation path indicates one or more lanes required for travel in the first road, and the first lane navigation path includes the second lane navigation path.

[0132] In one example, the first road can be any road between two adjacent intersections along the route from the first position to the second position. Taking the first road as shown in Figure 6(a) as an example, the multiple sub-road segments can include segments 1 to 4 shown in Figure 6(a). Based on at least one traffic flow corresponding to each sub-road segment, the target lane in each sub-road segment is determined. This can be understood as: clustering at least one traffic flow in each sub-road segment to obtain a Gaussian distribution curve of the traffic flow, and then determining the location of the peak of the Gaussian distribution curve as the target lane. In another example, each road segment can be any road between two adjacent fixed positions. More specific implementation methods can be found in the description of S303 and the corresponding part of Figure 6, and will not be repeated here.

[0133] It should be noted that the inclusion of the second lane navigation path in the first lane navigation path can be understood as the second lane navigation path being a part of the first lane navigation path. For example, if the first lane navigation path is the entire gray dashed line shown in Figure 9, then the second lane navigation path can be the gray dashed line portion of the road between intersection a and intersection b.

[0134] In some implementations, the target lane in each segment of a road is determined based on at least one traffic flow corresponding to each segment of the road. This can be further refined as follows: Based on at least one traffic flow corresponding to each segment of the road, at least two drivable lanes in each segment of the road are determined; the target lane is determined from the at least two drivable lanes based on at least one of the following: the number of traffic flows in each of the at least two drivable lanes, or the direction of travel at the first intersection, where the first intersection is connected to the first road and is adjacent to the second location.

[0135] For example, at least two drivable lanes in each road segment can be understood as follows: the Gaussian distribution curve obtained by clustering the traffic flow in the road segment includes at least two peaks, as shown in the traffic flow distribution representation corresponding to segments 3 and 4 in Figure 6(a). The first intersection connects to the first road and is adjacent to the second location, which can be understood as the first intersection being located near the end of the journey in the first road. For example, if the first road is the road between intersection a and intersection b shown in Figure 4, then the first intersection is intersection b. Determining the target lane from at least two drivable lanes can be understood as: determining a peak from multiple peaks in the Gaussian distribution curve corresponding to the road segment, and using the parking space corresponding to that peak as the target lane. For a more specific implementation, please refer to the description in S303 and the corresponding part of Figure 6, which will not be repeated here.

[0136] In some implementations, the first road navigation path passes through the second intersection, and the traffic flow information includes at least one traffic flow at the second intersection. Therefore, S1120, determining the first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path, can be refined as follows: determining the target location at the second intersection based on at least one traffic flow at the second intersection; determining the third lane navigation path based on the target location, where the third lane navigation path is the path taken by the vehicle when passing through the second intersection, and the first lane navigation path includes the third lane navigation path.

[0137] For example, the second intersection can be any intersection from intersection a to intersection e shown in Figure 4. The target location in the second intersection is determined based on at least one traffic flow in the second intersection. This can be understood as: clustering at least one traffic flow in the second intersection to obtain the Gaussian distribution curve of the traffic flow, and then determining the location of the peak of the Gaussian distribution curve as the target location. For a more specific implementation method, please refer to the description in S303 and the corresponding part of Figure 8, which will not be repeated here.

[0138] For example, the third lane navigation path can be either driving path a or driving path b as shown in Figure 8. The specific implementation of determining the third lane navigation path can be referred to the description of the corresponding part of Figure 8, which will not be repeated here.

[0139] In some implementations, the inclusion of the third lane navigation path in the first lane navigation path can be understood as the third lane navigation path being a part of the first lane navigation path. For example, if the first lane navigation path is all the black dotted lines shown in Figure 9, then the third lane navigation path can be the black dotted line portion at intersection d, or it can also be the black dotted line portion at intersection e.

[0140] In some implementations, before executing S1120, method 1100 further includes: determining a first group of traffic flows and a second group of traffic flows based on a first starting point and a first ending point of a first road navigation path; wherein the first group of traffic flows includes at least one traffic flow in the first path, the second group of traffic flows includes at least one traffic flow in the second path, the starting points of both the first path and the second path are matched with the first starting point, and the ending points of both the first path and the second path are matched with the first ending point; determining a group of traffic flows as traffic flow information from the first group of traffic flows and the second group of traffic flows based on at least one of the following: the average speed of the first group of traffic flows and the average speed of the second group of traffic flows; or the time information of the vehicles departing from the first location.

[0141] For example, the time information of the vehicle's departure from the first location can be the start time of the aforementioned target journey.

[0142] For example, taking the road-level path AB1' shown in Figure 5 as the first road navigation path, the first path can be the path shown in Figure 10 that passes through intersections a, b, and c, and the second path can be the path shown in Figure 10 that passes through intersections a, b', and c. Further, the specific implementation of determining the first group of traffic flows and the second group of traffic flows, and the specific implementation of determining one group of traffic flows from the first group of traffic flows and the second group of traffic flows as traffic flow information, can be referred to the descriptions in S303 and the corresponding parts of Figure 10, and will not be repeated here.

[0143] S1130, control the vehicle to travel from the first position to the second position along the navigation path of the first lane.

[0144] In some implementations, the SD map navigation information indicates multiple road navigation paths from a first location to a second location. Each of the multiple road navigation paths passes through at least two intersections, and the multiple road navigation paths include a first road navigation path and a second road navigation path. There is a first overlapping area between the first road navigation path and the second road navigation path, and the length of the first overlapping area is greater than or equal to a length threshold.

[0145] For example, the multiple road navigation paths may include road-level paths AB1, A1B2, and A2B as shown in Figure 5, or the multiple road navigation paths may also include road-level paths AB1', A1'B2', and A2B as shown in Figure 5. Taking the first road navigation path and the second road navigation path as road-level paths AB1 and A1B2 respectively, the first overlapping area may be the overlapping area crossing intersection b as shown in Figure 9. For example, the length threshold may be 30 meters, 50 meters, or other values. For example, the length threshold may be determined based on the intersections traversed by both road-level paths, such as the length threshold being greater than or equal to the length of the intersection, or the first overlapping area covering the intersection. The length threshold and the distance threshold 2 in method 300 may be the same value.

[0146] In some implementations, the second road navigation path and the fourth lane navigation path correspond, with the target lane of the fourth lane navigation path in the first overlapping area being the first lane, and the target lane of the first lane navigation path in the first overlapping area being the second lane. The vehicle travels sequentially via the fourth lane navigation path and the first lane navigation path to the second position. The method 1100 further includes: determining a fifth lane navigation path in the first overlapping area based on the first lane and the second lane, the fifth lane navigation path including a path for changing from the first lane to the second lane; and controlling the vehicle to pass through the first overlapping area along the fifth lane navigation path.

[0147] For example, the first lane can be lane a as shown in Figure 7, the second lane can be lane c as shown in Figure 7, and the navigation path of the fifth lane can be the transition path shown in Figure 7. The specific implementation of determining the navigation path of the fifth lane can be referred to the description of the corresponding part of Figure 7, which will not be repeated here.

[0148] In some implementations, the traffic flow information also includes the average speed of the traffic flow. Method 1100 further includes: determining a target speed based on the average speed of the traffic flow. S1130 can be refined to: controlling the vehicle to travel from a first position to a second position along a navigation path in the first lane at the target speed.

[0149] For example, the specific implementation of determining the target speed can be referred to in the description in S304, and will not be repeated here.

[0150] In some implementations, the method 1100 further includes: when controlling the vehicle to travel from the first position to the second position, acquiring environmental information of the current driving road, the environmental information including at least one of road boundaries, lane line positions, and obstacle positions. S1130 can be refined to: controlling the vehicle to travel from the first position to the second position based on the environmental information and the first lane navigation path.

[0151] For example, environmental information may include road information in S304. The method for obtaining environmental information can be referred to the description in the foregoing embodiments, and will not be repeated here.

[0152] The autonomous driving method provided in this application embodiment does not rely on high-precision maps when the vehicle needs to travel from the target starting position to the target ending position, and does not require the vehicle to have historical driving records of relevant road sections. It can control the vehicle to travel from the target starting position to the target ending position along a determined lane, which helps to improve the human-likeness of the vehicle in autonomous driving scenarios, thereby improving the intelligence level of the vehicle.

[0153] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0154] The path planning method and autonomous driving method for autonomous driving provided by the embodiments of this application have been described in detail above with reference to Figures 1 to 11. The apparatus provided by the embodiments of this application will be described in detail below with reference to Figures 12 and 13. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments; therefore, any content not described in detail can be referred to the method embodiments above, and for the sake of brevity, will not be repeated here.

[0155] Figure 12 shows a schematic block diagram of an apparatus 2000 provided in an embodiment of this application. The apparatus 2000 may include units for executing method 300, method 300, and method 1100. Furthermore, each unit in the apparatus 2000 implements the corresponding flow of the above-described method embodiments. The apparatus 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transmission / reception functions. The apparatus 2000 also includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0156] Optionally, the device 2000 further includes a storage unit, which can be used to store instructions and / or data. The processing unit 2020 can read the instructions and / or data in the storage unit so that the device can perform the relevant actions in the aforementioned method embodiments.

[0157] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0158] It should also be understood that the device 2000 described herein is embodied in the form of a functional unit. The terms “module” or “unit” may refer to application-specific ASICs, electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0159] The apparatuses described above have the function of implementing the corresponding steps in the methods described above. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0160] Exemplarily, the acquisition unit 2010 and processing unit 2020 can be disposed in the intelligent driving device 100 shown in FIG1, or they can also be disposed in the system shown in FIG2. More specifically, the acquisition unit 2010 and processing unit 2020 can be disposed in the planning and control module 240, or they can also be disposed in the navigation information determination module 220. Exemplarily, the operations performed by the acquisition unit 2010 and processing unit 2020 can be performed by a single processor, or they can be performed by different processors. In specific implementation, the one or more processors can be processors disposed in the intelligent driving device 100 shown in FIG1; or the device 2000 can be a chip disposed in the intelligent driving device 100.

[0161] In the specific implementation process, the units in the above device can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0162] Figure 13 is another schematic block diagram of the apparatus provided in an embodiment of this application. The apparatus 2100 shown in Figure 13 may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0163] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0164] Memory 2130 can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes various forms such as: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0165] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0166] This application also provides an intelligent driving device, which includes the device 2000 or device 2100 in the above embodiments.

[0167] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0168] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0169] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0170] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0171] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes 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, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0172] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple 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 connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0174] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0175] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, 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.

[0177] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should 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. An autonomous driving method, characterized in that, include: Obtain standard SD map navigation information, wherein the SD map navigation information indicates a first road navigation path from a first location to a second location, and the first road navigation path passes through at least one intersection; Based on the traffic flow information corresponding to the first road navigation path, a first lane navigation path is determined from the first location to the second location. The traffic flow information includes at least one traffic flow. The first lane navigation path indicates one or more lanes that need to be taken to travel from the first location to the second location. Control the vehicle to travel from the first position to the second position along the navigation path of the first lane.

2. The method according to claim 1, characterized in that, The first road navigation route passes through at least two intersections.

3. The method according to claim 1 or 2, characterized in that, The first road navigation path indicates that the route from the first location to the second location passes through at least a first road, and the traffic flow information includes at least one traffic flow on the first road, which includes multiple road segments; Determining the first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path includes: Based on at least one traffic flow corresponding to each of the multiple road segments, a target lane is determined in each road segment, wherein the target lane is the lane in which the vehicle is traveling in each road segment; Based on the target lane in each sub-road segment, a second lane navigation path is determined in the first road. The second lane navigation path indicates one or more lanes required for travel in the first road, and the first lane navigation path includes the second lane navigation path.

4. The method according to claim 3, characterized in that, The step of determining the target lane in each of the multiple road segments based on at least one traffic flow corresponding to each road segment includes: Based on at least one traffic flow corresponding to each road segment, determine at least two drivable lanes in each road segment; The target lane is determined from the at least two drivable lanes based on at least one of the following: The number of vehicles in each of the at least two drivable lanes, or The direction of travel at the first intersection, the first intersection is connected to the first road and the first intersection is adjacent to the second location.

5. The method according to any one of claims 1 to 4, characterized in that, The first road navigation route passes through a second intersection, and the traffic flow information includes at least one traffic flow at the second intersection; Determining the first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path includes: Determine the target location in the second intersection based on at least one traffic flow in the second intersection; The third lane navigation path is determined based on the target location. The third lane navigation path is the path taken by the vehicle when passing through the second intersection. The first lane navigation path includes the third lane navigation path.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Based on the first starting point and the first ending point of the first road navigation path, determine the first group of traffic flow and the second group of traffic flow; Wherein, the first group of traffic flows includes at least one traffic flow in the first path, the second group of traffic flows includes at least one traffic flow in the second path, the starting points of the first path and the second path are both matched with the first starting point, and the ending points of the first path and the second path are both matched with the first ending point; Traffic flow information is determined from the first group of traffic flows and the second group of traffic flows based on at least one of the following: The average speed of the first group of traffic flows and the average speed of the second group of traffic flows; or The time information of when the vehicle departed from the first location.

7. The method according to any one of claims 1 to 6, characterized in that, The SD map navigation information indicates multiple road navigation paths from the first location to the second location. Each of the multiple road navigation paths passes through at least two intersections, and the multiple road navigation paths include the first road navigation path and the second road navigation path. There is a first overlapping area between the first road navigation path and the second road navigation path, and the length of the first overlapping area is greater than or equal to a length threshold.

8. The method according to claim 7, characterized in that, The second road navigation path and the fourth lane navigation path correspond to each other. The target lane of the fourth lane navigation path in the first overlapping area is the first lane, and the target lane of the first lane navigation path in the first overlapping area is the second lane. The vehicle travels to the second position sequentially via the fourth lane navigation path and the first lane navigation path. The method further includes: Based on the first lane and the second lane, a navigation path for the fifth lane in the first overlapping area is determined, the fifth lane navigation path including a path from the first lane to the second lane; Control the vehicle to navigate along the fifth lane through the first overlapping area.

9. The method according to any one of claims 1 to 8, characterized in that, The traffic flow information also includes the average speed of the traffic flow, and the method further includes: The target speed is determined based on the average speed of the traffic flow; The control of the vehicle to travel from the first position to the second position along the navigation path of the first lane includes: Control the vehicle to travel from the first position to the second position along the navigation path of the first lane at the target speed.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: When controlling the vehicle to travel from the first position to the second position, environmental information of the current driving road is obtained, and the environmental information includes at least one of the road boundary, lane line position, and obstacle position. The control of the vehicle to travel from the first position to the second position along the navigation path of the first lane includes: Based on the environmental information and the first lane navigation path, the vehicle is controlled to travel from the first position to the second position.

11. An automatic driving device, characterized in that, include: The acquisition unit is used to acquire standard SD map navigation information, wherein the SD map navigation information indicates a first road navigation path from a first location to a second location, and the first road navigation path passes through at least one intersection. The processing unit is configured to determine a first lane navigation path from the first location to the second location based on the traffic flow information corresponding to the first road navigation path, wherein the traffic flow information includes at least one traffic flow, and the first lane navigation path indicates one or more lanes required to travel from the first location to the second location. The processing unit is further configured to: control the vehicle to travel from the first position to the second position along the navigation path of the first lane.

12. The apparatus according to claim 11, characterized in that, The first road navigation route passes through at least two intersections.

13. The apparatus according to claim 11 or 12, characterized in that, The first road navigation path indicates that the route from the first location to the second location passes through at least a first road, and the traffic flow information includes at least one traffic flow on the first road, which includes multiple road segments; The processing unit is used for: Based on at least one traffic flow corresponding to each of the multiple road segments, a target lane is determined in each road segment, wherein the target lane is the lane in which the vehicle is traveling in each road segment; Based on the target lane in each sub-road segment, a second lane navigation path is determined in the first road. The second lane navigation path indicates one or more lanes required for travel in the first road, and the first lane navigation path includes the second lane navigation path.

14. The apparatus according to claim 13, characterized in that, The processing unit is used for: Based on at least one traffic flow corresponding to each road segment, determine at least two drivable lanes in each road segment; The target lane is determined from the at least two drivable lanes based on at least one of the following: The number of vehicles in each of the at least two drivable lanes, or The direction of travel at the first intersection, the first intersection is connected to the first road and the first intersection is adjacent to the second location.

15. The apparatus according to any one of claims 11 to 14, characterized in that, The first road navigation route passes through a second intersection, and the traffic flow information includes at least one traffic flow at the second intersection; The processing unit is used for: Determine the target location in the second intersection based on at least one traffic flow in the second intersection; The third lane navigation path is determined based on the target location. The third lane navigation path is the path taken by the vehicle when passing through the second intersection. The first lane navigation path includes the third lane navigation path.

16. The apparatus according to any one of claims 11 to 15, characterized in that, The processing unit is also used for: Based on the first starting point and the first ending point of the first road navigation path, determine the first group of traffic flow and the second group of traffic flow; Wherein, the first group of traffic flows includes at least one traffic flow in the first path, the second group of traffic flows includes at least one traffic flow in the second path, the starting points of the first path and the second path are both matched with the first starting point, and the ending points of the first path and the second path are both matched with the first ending point; Traffic flow information is determined from the first group of traffic flows and the second group of traffic flows based on at least one of the following: The average speed of the first group of traffic flows and the average speed of the second group of traffic flows; or The time information of when the vehicle departed from the first location.

17. The apparatus according to any one of claims 11 to 16, characterized in that, The SD map navigation information indicates multiple road navigation paths from the first location to the second location. Each of the multiple road navigation paths passes through at least two intersections, and the multiple road navigation paths include the first road navigation path and the second road navigation path. There is a first overlapping area between the first road navigation path and the second road navigation path, and the length of the first overlapping area is greater than or equal to a length threshold.

18. The apparatus according to claim 17, characterized in that, The second road navigation path and the fourth lane navigation path correspond to each other. The target lane of the fourth lane navigation path in the first overlapping area is the first lane, and the target lane of the first lane navigation path in the first overlapping area is the second lane. The vehicle travels to the second position sequentially via the fourth lane navigation path and the first lane navigation path. The processing unit is further configured to: Based on the first lane and the second lane, a navigation path for the fifth lane in the first overlapping area is determined, the fifth lane navigation path including a path from the first lane to the second lane; Control the vehicle to navigate along the fifth lane through the first overlapping area.

19. The apparatus according to any one of claims 11 to 18, characterized in that, The traffic flow information also includes the average speed of the traffic flow, and the processing unit is further configured to: The target speed is determined based on the average speed of the traffic flow; The control of the vehicle to travel from the first position to the second position along the navigation path of the first lane includes: Control the vehicle to travel from the first position to the second position along the navigation path of the first lane at the target speed.

20. The apparatus according to any one of claims 11 to 19, characterized in that, The acquisition unit is also used for: When controlling the vehicle to travel from the first position to the second position, environmental information of the current driving road is obtained, and the environmental information includes at least one of the road boundary, lane line position, and obstacle position. The processing unit is also used for: Based on the environmental information and the first lane navigation path, the vehicle is controlled to travel from the first position to the second position.

21. An automatic driving device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 10.

22. The apparatus according to claim 21, characterized in that, The device also includes the memory.

23. An intelligent driving device, characterized in that, Includes the apparatus as described in any one of claims 11 to 22.

24. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 10.

25. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 10.

26. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 10.

Images