Travel path planning method, device, and vehicle

Abstract

The present application relates to the technical field of intelligent driving, and provides a travel path planning method, a device, and a vehicle. The present application can improve the accuracy of travel path planning by means of identification of traffic flows. The method comprises: acquiring traffic flow information; determining a first traffic flow and a second traffic flow on the basis of the traffic flow information, wherein the first traffic flow has a lateral distance smaller than a first threshold from a vehicle and travels in a direction same as or similar to that of the vehicle, the second traffic flow has a lateral distance greater than a second threshold from the vehicle, and the second threshold is greater than the first threshold; and planning a target travel path of the vehicle on the basis of the first traffic flow and the second traffic flow, wherein the target travel path follows the first traffic flow and avoids the second traffic flow.

Description

Driving route planning methods, devices and vehicles

[0001] This application claims priority to Chinese Patent Application No. 202410509433.3, filed on April 25, 2024, entitled “Driving Path Planning Method, Apparatus and Vehicle”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving technology, and in particular to a driving path planning method, device and vehicle. Background Technology

[0003] With the development of science and technology and the application of artificial intelligence, intelligent driving systems have experienced rapid development and widespread application, enabling vehicles based on these systems to achieve autonomous driving. To ensure the safe operation of autonomous vehicles in complex traffic environments, it is crucial to acquire accurate, real-time, and comprehensive information about the vehicle's surroundings during operation. Only with a better understanding of the surrounding environment, such as road signs, road obstacles (e.g., flower beds, fences), and lane markings, can the vehicle better plan its driving path, thereby effectively improving the safety of autonomous driving.

[0004] Vehicles use sensing hardware such as lidar, millimeter-wave radar, and onboard cameras to detect information about their surroundings. However, due to the limitations of this sensing hardware, the environmental information detected is insufficient to meet the vehicle's needs for accurate route planning in complex traffic environments such as road obstacles and extreme weather.

[0005] To address this, vehicles can be equipped with high-precision maps containing rich traffic environment information, including road geometry, traffic lights, and buildings, to improve the accuracy of their route planning. However, creating high-precision maps requires collecting and processing large amounts of data, leading to high upfront costs, difficulties in data updates, and high hardware requirements for vehicles. Therefore, improving the accuracy of route planning in vehicles without high-precision maps remains a pressing issue. Summary of the Invention

[0006] To address the aforementioned technical problems, this application provides a driving route planning method, apparatus, and vehicle. The technical solution provided by this application improves the accuracy of driving route planning through traffic flow identification.

[0007] To achieve the above-mentioned technical objectives, this application provides the following technical solution:

[0008] Firstly, a driving path planning method is provided for vehicles. This method includes: acquiring traffic flow information; determining a first traffic flow and a second traffic flow based on the traffic flow information, wherein the first traffic flow has a lateral distance to the vehicle less than a first threshold and travels in the same or similar direction as the vehicle, and the second traffic flow has a lateral distance to the vehicle greater than a second threshold, which is greater than the first threshold; and planning a target driving path for the vehicle based on the first and second traffic flows, wherein the target driving path follows the first traffic flow and avoids the second traffic flow.

[0009] In this way, by leveraging existing traffic flow to plan the current vehicle's route, the efficiency, stability, and robustness of route planning can be improved, achieving human-like autonomous driving effects.

[0010] According to the first aspect, the first traffic flow is the forward traffic flow corresponding to the vehicle, and the second traffic flow is the lateral traffic flow corresponding to the vehicle, which includes the left-side traffic flow and / or the right-side traffic flow.

[0011] In this way, based on the historical driving trajectories of other vehicles in front, the vehicle can determine the established first flow of traffic. Following this first flow can prevent unexpected steering problems caused by perceived lane instability.

[0012] Furthermore, when dealing with obstacles around intersections (such as flower beds at intersections or roadblocks marked by fences in the middle of the road), other vehicles traveling in the forward direction can create an obstacle avoidance path that conforms to semantic rules. Therefore, following the traction of the forward traffic flow, even if the vehicle is limited by the detection range of its own perception hardware, it can plan a reasonable obstacle avoidance path when no obstacle is detected, and this obstacle avoidance path also has the correct obstacle avoidance direction.

[0013] Furthermore, in complex intersection scenarios such as double left turns and multi-lane intersections, the vehicle's planned target driving path can avoid second-flow traffic traveling laterally, thus avoiding interference with other vehicles' driving. In this way, while achieving its own driving goal, the vehicle avoids interfering with other vehicles in the process, enabling it to drive a reasonable, human-like, and efficient driving trajectory.

[0014] According to the first aspect, or any implementation of the first aspect above, determining the first traffic flow and the second traffic flow based on traffic flow information includes: when the distance between a vehicle's driving position and the upcoming exit is greater than a third threshold, determining the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose driving direction is similar to the vehicle's, based on traffic flow information, as the first traffic flow. Similar driving direction includes the first traffic flow being similar to the vehicle's exit position. Alternatively, when the distance between a vehicle's driving position and the upcoming exit is less than or equal to the third threshold, determining the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose driving direction is the same, based on traffic flow information, as the first traffic flow. Same driving direction includes the first traffic flow being in the same lane as the vehicle's current lane.

[0015] Thus, when a vehicle is far from the intersection ahead, it can ensure the correctness of its driving path by simply following other vehicles traveling roughly ahead. However, when a vehicle is close to the intersection ahead, it needs to follow other vehicles traveling in the same lane ahead to ensure driving safety. Based on the distance to the intersection ahead, the vehicle flexibly determines the first flow of traffic, improving the flexibility of the target driving path planning.

[0016] According to the first aspect, or any implementation of the first aspect above, traffic flow information is obtained, including: obtaining the driving information of multiple other vehicles around the vehicle within a preset time period, the driving information including at least one of position, driving direction, and speed; obtaining multiple vehicle trajectories corresponding to the multiple other vehicles based on the driving information; matching multiple vehicle trajectories pairwise, clustering the two successfully matched vehicle trajectories into one traffic flow to obtain multiple traffic flows, the traffic flow information including information about multiple traffic flows.

[0017] In some embodiments, the vehicle is equipped with sensing hardware, such as cameras, radar (e.g., lidar, millimeter-wave radar, etc.), and the vehicle can obtain driving information of other vehicles in the surrounding area based on these sensing hardware, and then generate traffic flow information based on the driving information.

[0018] In this way, vehicles detect the driving trajectories of other vehicles in the vicinity and aggregate these trajectories into a reference traffic flow (such as including a first traffic flow and a second traffic flow), so that subsequent vehicles can plan their routes based on this reference traffic flow. Furthermore, these reference traffic flows already exist within a preset time period, and route planning based on these existing traffic flows can achieve better route planning results.

[0019] According to the first aspect, or any of the above implementations of the first aspect, a successful match includes two vehicle trajectories having a lateral distance less than the fourth threshold and the same driving direction.

[0020] In this way, by matching vehicle trajectories, the number of reference traffic flows can be reduced, thus lowering the difficulty of subsequent driving route planning.

[0021] According to the first aspect, or any implementation of the first aspect above, after clustering the two successfully matched vehicle trajectories into one traffic flow, the method further includes: sorting and smoothing the trajectory points included in all vehicle trajectories within the clustered traffic flow to obtain the processed traffic flow, where multiple traffic flows include multiple processed traffic flows.

[0022] Each trajectory point corresponds to the time information of its generation. Sorting the trajectory points within a class can prevent backflow issues in the generated traffic flow. Each trajectory point also corresponds to the location information of its generation. Smoothing the trajectory points within a class (such as weighted averaging of trajectory points within a preset range) can prevent bends in the generated traffic flow.

[0023] Based on the first aspect, or any of the above implementations of the first aspect, the first traffic flow and the second traffic flow are determined based on traffic flow information, including: filtering out the first traffic flow and the second traffic flow from multiple traffic flows.

[0024] In this way, after obtaining traffic flow information, vehicles can select suitable first and second traffic flows from the multiple traffic flows indicated by the traffic flow information as reference traffic flows, ensuring the correctness of subsequent route planning.

[0025] According to the first aspect, or any implementation of the first aspect above, the target driving path also avoids the boundaries formed by road boundaries and / or obstacles.

[0026] In some embodiments, the constraints corresponding to the first traffic flow and the second traffic flow are soft constraints for the target driving path planning generated by the vehicle, while the constraints referenced in the process of planning the driving path may also include hard constraints such as road boundaries and obstacle boundaries.

[0027] Thus, by combining soft and hard constraints in target driving path planning, the vehicle can obtain a more reasonable target driving path.

[0028] Furthermore, even if there are anomalies in the first or second traffic flow, vehicles can still obtain the target driving path that ensures safe driving based on hard constraints.

[0029] According to the first aspect, or any implementation of the first aspect above, before obtaining traffic flow information, the method further includes: determining, based on the collected environmental information, that an intersection appears ahead of the vehicle, and determining the location of the intersection.

[0030] In this way, when a vehicle determines that it needs to pass through a certain area, it plans its own driving path based on other traffic flows, thereby achieving a more human-like autonomous driving effect.

[0031] Secondly, embodiments of this application provide a driving route planning device. The device includes a processor and a memory, the memory being coupled to the processor. The memory stores computer-readable instructions. When the processor reads the computer-readable instructions from the memory, the driving route planning device performs the following: acquiring traffic flow information; determining a first traffic flow and a second traffic flow based on the traffic flow information, wherein the lateral distance between the first traffic flow and the vehicles is less than a first threshold and the traffic flow is in the same or similar direction to the vehicles, and the lateral distance between the second traffic flow and the vehicles is greater than a second threshold, the second threshold being greater than the first threshold; and planning a target driving route for the vehicles based on the first and second traffic flows, the target driving route following the first traffic flow and avoiding the second traffic flow.

[0032] According to the second aspect, the first traffic flow is the forward traffic flow corresponding to the vehicle, and the second traffic flow is the lateral traffic flow corresponding to the vehicle, which includes left-side traffic flow and / or right-side traffic flow.

[0033] According to the second aspect, or any implementation of the second aspect above, determining the first traffic flow and the second traffic flow based on traffic flow information includes: when the distance between a vehicle's driving position and the upcoming exit is greater than a third threshold, determining the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose driving direction is similar to the vehicle's, based on traffic flow information, as the first traffic flow. Similar driving direction includes the first traffic flow being similar to the vehicle's exit position. Alternatively, when the distance between a vehicle's driving position and the upcoming exit is less than or equal to the third threshold, determining the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose driving direction is the same, based on traffic flow information, as the first traffic flow. Same driving direction includes the first traffic flow being in the same lane as the vehicle's current lane.

[0034] According to the second aspect, or any implementation of the second aspect above, traffic flow information is obtained, including: obtaining the driving information of multiple other vehicles around the vehicle within a preset time period, the driving information including at least one of position, driving direction, and speed; obtaining multiple vehicle trajectories corresponding to the multiple other vehicles based on the driving information; matching multiple vehicle trajectories pairwise, clustering the two successfully matched vehicle trajectories into one traffic flow to obtain multiple traffic flows, the traffic flow information including information about multiple traffic flows.

[0035] According to the second aspect, or any of the implementations of the second aspect above, a successful match includes two vehicle trajectories having a lateral distance less than the fourth threshold and the same driving direction.

[0036] According to the second aspect, or any implementation of the second aspect above, when the processor reads computer-readable instructions from memory, it also causes the driving route planning device to perform: sorting and smoothing the trajectory points included in all vehicle trajectories clustered into a traffic flow, and obtaining the processed traffic flow, wherein multiple traffic flows include multiple processed traffic flows.

[0037] According to the second aspect, or any implementation of the second aspect above, the first traffic flow and the second traffic flow are determined based on traffic flow information, including: filtering out the first traffic flow and the second traffic flow from multiple traffic flows.

[0038] According to the second aspect, or any implementation of the second aspect above, the target driving path also avoids the boundaries formed by road boundaries and / or obstacles.

[0039] According to the second aspect, or any implementation of the second aspect above, when the processor reads computer-readable instructions from memory, it also causes the driving route planning device to perform: determining, based on the collected environmental information, that an intersection appears ahead of the vehicle, and determining the location of the intersection.

[0040] Thirdly, this application provides an intelligent device including one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program code, which includes computer instructions. When the one or more processors execute the computer instructions, the intelligent device performs the driving path planning method in any possible implementation of the first aspect described above. Optionally, the intelligent device is, for example, a driving path planning apparatus.

[0041] Fourthly, embodiments of this application provide a means of transportation, which includes a route planning device as described in the second aspect.

[0042] Optionally, the means of transportation includes vehicles. For example, electric cars, sedans, trucks, motorcycles, buses, lawnmowers, recreational vehicles, amusement park vehicles, construction equipment, trams, golf carts, etc., are not specifically limited in the embodiments of this application.

[0043] Fifthly, embodiments of this application provide a chip system including at least one processor and at least one interface circuit. The at least one interface circuit is used to perform transceiver functions and send instructions to the at least one processor. The at least one processor executes the instructions and performs the method of the first aspect and any one of the embodiments of the first aspect.

[0044] Sixthly, embodiments of this application provide a computer-readable storage medium. The computer-readable storage medium includes a computer program (also referred to as instructions or code) that, when executed on a computer, causes the computer to perform the method of the first aspect and any embodiment thereof.

[0045] In a seventh aspect, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to perform the method of the first aspect and any one of the embodiments of the first aspect.

[0046] The technical effects corresponding to any implementation method of aspects two through seven, and all other aspects, can be found in the first aspect and the technical effects corresponding to any implementation method of the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0047] Figure 1 is a schematic diagram of the driving route planning system provided in an embodiment of this application;

[0048] Figure 2 is a schematic diagram of the hardware structure of the vehicle provided in the embodiment of this application;

[0049] Figure 3 is a schematic diagram of the operating environment provided in the embodiments of this application;

[0050] Figure 4 is a schematic flowchart of the driving path planning method provided in an embodiment of this application;

[0051] Figure 5 is a schematic diagram of the traffic flow information generation process provided in an embodiment of this application;

[0052] Figure 6 is a schematic diagram of the real-time traffic flow generation process provided in an embodiment of this application;

[0053] Figure 7 is a schematic diagram of the driving path planning method provided in an embodiment of this application (II).

[0054] Figure 8 is a schematic diagram of the target driving path planning scenario provided in an embodiment of this application;

[0055] Figure 9 is a schematic flowchart of the driving path planning method provided in the embodiment of this application;

[0056] Figure 10 is a schematic diagram of the target driving path planning effect provided in the embodiment of this application;

[0057] Figure 11 is a schematic diagram of the driving path planning device provided in an embodiment of this application;

[0058] Figure 12 is a schematic diagram of the chip system provided in an embodiment of this application. Detailed Implementation

[0059] The technical solutions of the embodiments of this application are described below with reference to the accompanying drawings. In the description of the embodiments of this application, the terminology used in the following embodiments is for the purpose of describing specific embodiments only and is not intended to be a limitation of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one or more (including two).

[0060] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. The term "connection" includes direct connections and indirect connections, unless otherwise stated. "First" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated.

[0061] In the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0062] In some embodiments, due to the high upfront costs, difficulties in data updates, and high hardware requirements of high-precision maps, they cannot currently be widely used in autonomous vehicles. Therefore, vehicles must rely on perception hardware such as LiDAR, millimeter-wave radar, and onboard cameras to detect environmental information around the vehicle and plan driving paths based on this detected information. However, environmental information detection based on perception hardware presents at least the following problems.

[0063] First, the limited sensing range of the sensing hardware can lead to issues with the planned driving path crossing obstacles. For example, due to obstruction by other vehicles, the sensing hardware may fail to detect a roadside flower bed at the intersection ahead, causing the planned driving path to cross the flower bed and creating a safety hazard when the vehicle autonomously drives through the intersection along the planned path.

[0064] Secondly, the perception hardware lacks semantic understanding of obstacle avoidance, which may lead to incorrect left or right avoidance directions in the planned driving path. For example, if there is roadwork ahead and a fence is set up in the middle of the road to protect the work site, and there are intersections on both sides of the work site, but the actual drivable intersection is on the right side of the fence, the vehicle's planned driving path may lead it to the intersection on the left side of the fence due to the perception hardware's lack of semantic understanding of obstacle avoidance. This incorrect avoidance direction creates a safety hazard.

[0065] Furthermore, sensing hardware typically detects individual vehicles around the vehicle and considers avoiding those vehicles during the route planning process. However, insufficient consideration of traffic flow avoidance can lead to the planned route potentially interfering with other vehicles' traffic flow.

[0066] Based on this, embodiments of this application provide a driving path planning method that can acquire traffic flow information and generate a first traffic flow and a second traffic flow based on the traffic flow information. Specifically, the first traffic flow has a lateral distance of less than a first threshold and travels in the same or similar direction as the vehicles; the second traffic flow has a lateral distance of greater than a second threshold, which in turn is greater than the first threshold. Then, based on the first and second traffic flows, a target driving path for the vehicle can be planned. The target driving path follows the first traffic flow and avoids the second traffic flow. In this way, by utilizing existing traffic flows to plan the current vehicle's driving path, the efficiency, stability, and robustness of driving path planning are improved, achieving a human-like autonomous driving effect at intersections.

[0067] The solutions in this application embodiment can be applied to a driving path planning device. The driving path planning device can be an intelligent device, such as an autonomous vehicle, a robot, or other electronic device with autonomous driving capabilities; this application embodiment does not limit this. In some embodiments, the solutions in this application embodiment can also be applied to other devices (such as cloud servers, mobile terminals, etc.) that have the function of controlling the aforementioned driving path planning device. The driving path planning device or other devices can implement the driving path planning method provided in this application embodiment through their included components (including hardware and software).

[0068] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0069] In this embodiment of the application, for ease of distinction, the vehicle to which the driving path planning method is applied can be referred to as the "self vehicle," and other vehicles in the surrounding environment of the self vehicle can be referred to as "other vehicles."

[0070] Referring to Figure 1, Figure 1 illustrates a driving route planning system 10 provided in an embodiment of this application. As shown in Figure 1, the driving route planning system 10 includes a detection module 11 and a driving route planning device 12. The detection module 11 and the driving route planning device 12 are connected and communicate with each other. The driving route planning device 12 includes a judgment module 121, a traffic flow processing module 122, and a route generation module 123.

[0071] In some embodiments, the detection module 11 is used to acquire detection data, which is used to indicate the vehicle's driving information and the environmental information surrounding the vehicle. Optionally, the detection data may include, for example, the vehicle's driving position, driving direction, and driving speed; the detection data may also include, for example, the position, driving direction, driving speed, distance from other vehicles, and information about surrounding obstacles. Optionally, obstacle information may include, for example, appearance information such as position, outline (or boundary shape), and size, as well as the distance between the obstacle and the vehicle, wherein the obstacle can be a dynamic obstacle or a static obstacle. In some embodiments, other vehicles can also be understood as dynamic obstacles.

[0072] The detection module 11 may include one or more of the following sensing hardware: LiDAR, millimeter-wave radar, vehicle camera, etc.

[0073] It should be understood that the above description of the detection module 11 is merely illustrative.

[0074] Referring to Figure 1, the driving path planning device 12 shown in Figure 1 can be used to plan a driving path based on the detection data received from the detection module 11, and output the driving path to instruct the vehicle to trigger autonomous driving according to the driving path.

[0075] In some embodiments, the driving route planning device 12 includes a judgment module 121, a traffic flow processing module 122, and a route generation module 123.

[0076] The judgment module 121 is used to determine whether the path planning conditions are met. Optionally, the driving path planning device 12 determines that the path planning conditions are met through the judgment module 121 before performing path planning. Optionally, the path planning conditions include, for example, the appearance of an intersection ahead of the vehicle and the determination of the intersection's location. Optionally, the path planning conditions may also include that the vehicle has no intention to change lanes.

[0077] The traffic flow processing module 122 is used to acquire real-time traffic flow based on detection data and filter the first traffic flow and the second traffic flow from the real-time traffic flow. The first traffic flow is the forward traffic flow corresponding to the vehicle, and the second traffic flow is the lateral traffic flow corresponding to the vehicle, which includes left-side traffic flow and / or right-side traffic flow.

[0078] The path generation module 123 is used to plan the target driving path of the vehicle based on the first traffic flow and the second traffic flow. The target traffic flow follows the first traffic flow and avoids other vehicles. By following the normally moving forward traffic flow for path planning, a reasonable path around obstacles can be planned. Furthermore, by planning the path based on the lateral traffic flow, interference with other vehicles can be avoided. Thus, an efficient path can be planned that reaches the target while avoiding interference with other vehicles, producing a human-like effect.

[0079] The following will use an autonomous vehicle (hereinafter referred to as a vehicle) as an example to illustrate the solution provided in the embodiments of this application.

[0080] Please refer to Figure 2, which shows a functional block diagram of a vehicle 100 provided in an embodiment of this application. The vehicle 100 may include various devices and components disposed in and / or on the vehicle body. In one embodiment, the devices and components disposed in the vehicle 100 may include, but are not limited to, an autonomous driving system and autonomous driving function applications. It is understood that vehicles with a certain degree of autonomous driving capability are typically equipped with an autonomous driving system.

[0081] Vehicle 100 may include various subsystems, such as a mobility system 102, a sensor system 104, a control system 106, one or more peripheral devices 108, a power supply 110, a computer system 112, and a user interface 116. Optionally, vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of vehicle 100 may be interconnected via wired or wireless means.

[0082] Sensor system 104 (also referred to as "acquisition device") may include several sensors for sensing information about the surrounding environment of vehicle 100. For example, sensor system 104 may include a positioning system (which may be a Global Positioning System (GPS), BeiDou Navigation Satellite System, or other positioning systems), an inertial measurement unit (IMU), radar, and cameras. Sensor system 104 may also include sensors from the internal systems of the monitored vehicle 100 (such as an in-vehicle air quality detector, fuel gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (such as position, shape, orientation, speed, etc.). This detection and identification is a key function for the safe operation of autonomous driving of vehicle 100.

[0083] The positioning system can be used to estimate the geographical location of vehicle 100. An inertial measurement unit (IMU) can be used to sense changes in the position and orientation of vehicle 100 based on inertial acceleration. In one embodiment, the IMU can be a combination of an accelerometer and a gyroscope.

[0084] Radar can use radio signals to sense objects in the surrounding environment of vehicle 100, such as dynamic obstacles of various types, including pedestrians, cyclists, motorcycles, and other vehicles, as well as static obstacles such as curbs, fences, and flower beds. In some embodiments, in addition to sensing objects, radar can also be used to sense one or more of the following states of an object: speed, position, and direction of travel.

[0085] The camera can be used to capture multiple images of the vehicle 100's surrounding environment. The camera can be a still camera or a video camera.

[0086] The control system 106 controls the operation of the vehicle 100 and its components. The control system 106 may include various components such as a steering system, throttle, braking unit, computer vision system, and path planning system. The steering system is operable to adjust the forward direction of the vehicle 100. Optionally, the steering system may be a steering wheel system. The throttle can be used to control the operating speed of the engine and thus the speed of the vehicle 100. The braking unit can be used to control the deceleration of the vehicle 100.

[0087] Computer vision systems can process and analyze images captured by cameras to identify various types of objects and / or features in the environment surrounding vehicle 100. Computer vision systems can use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision systems can be used to map the environment, track objects, estimate object velocities, etc.

[0088] The path control system is used to determine the driving path of vehicle 100. In some embodiments, the path control system may combine detection data from the output of sensing hardware to identify, assess and avoid or otherwise cross a second flow of traffic in the environment of vehicle 100, as well as follow a first flow of traffic, to determine the driving path for vehicle 100.

[0089] Of course, in one instance, the control system 106 may include components other than those described above, either by addition or substitution. Alternatively, some of the aforementioned components may be omitted.

[0090] Vehicle 100 interacts with external sensors, other vehicles, other computer systems, or users via peripheral devices 108. Peripheral devices 108 may include wireless communication systems, on-board computers, microphones, and / or speakers.

[0091] Some or all of the functions of vehicle 100 are controlled by computer system 112. Computer system 112 may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as data memory. Computer system 112 may also be multiple computing devices that control individual components or subsystems of vehicle 100 in a distributed manner.

[0092] A processor may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0093] In some embodiments, the memory may contain instructions (e.g., program logic) that can be executed by a processor to perform various functions of the vehicle 100, including those described above. The memory may also contain additional instructions, including instructions for transmitting data, receiving data from, interacting with, and / or controlling one or more of the following: the driving system 102, the sensor system 104, the control system 106, and the peripheral devices 108. In addition to instructions, the memory may store data such as road maps, route information, vehicle data including position, direction, speed, and traffic flow information, as well as other information such as the position, orientation, and speed of various objects in the vehicle's surrounding environment. This information can be used by the vehicle 100, the computer system 112, and the control system 106 during operation of the vehicle 100 in automatic, semi-automatic, and / or manual modes.

[0094] Computer system 112 can control the functions of vehicle 100 based on inputs received from various subsystems (e.g., driving system 102, sensor system 104, control system 106) and from user interface 116. For example, computer system 112 can utilize inputs from control system 106 to control the steering unit to avoid obstacles such as traffic flow detected by the path planning system. In some embodiments, computer system 112 can provide control over many aspects of vehicle 100 and its subsystems.

[0095] It is understood that the structure shown in Figure 2 is merely illustrative and does not limit the structure of the vehicle in the embodiments of this application. In other embodiments of this application, the vehicle 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements, or have different configurations with the same or more functions as shown in Figure 2. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0096] An autonomous vehicle traveling on a road, such as vehicle 100 above, can determine its speed adjustment command based on objects in its surrounding environment. These objects can be static objects such as traffic control equipment or green belts, or dynamic objects such as pedestrians, cyclists, motorcycles, and other vehicles. In some embodiments, vehicle 100 can detect each object in its surrounding environment using its own configured perception hardware, and based on the object's characteristics, such as its current speed, acceleration, and distance from the vehicle, the processor determines the vehicle 100's speed adjustment command.

[0097] Optionally, the vehicle 100, which is an autonomous vehicle, or its associated computer equipment (such as computer system 112, computer vision system, memory) can plan a driving path based on the identified first and second traffic flows, so that the vehicle 100 can avoid the second traffic flow while following the traffic flow.

[0098] In addition to providing instructions to adjust the speed of the autonomous vehicle, the computer device can also provide instructions to modify the steering angle of the vehicle 100 so that the autonomous vehicle follows a given trajectory and / or maintains a safe lateral and longitudinal distance between the autonomous vehicle and nearby objects (such as cars in adjacent lanes).

[0099] It is understood that the aforementioned vehicle 100 can be a car, truck, motorcycle, bus, boat, lawnmower, recreational vehicle, amusement park vehicle, construction equipment, tram, golf cart, etc., and this application embodiment does not impose any particular limitation. For example, vehicle 100 can also be a smart car or smart robot with autonomous driving capabilities in the field of smart homes.

[0100] In other embodiments of this application, the autonomous vehicle may further include hardware structures and / or software modules to implement the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0101] In one possible implementation, the computer system 112 shown in Figure 2 may include a processor coupled to a system bus. The processor may be one or more processors, each of which may include one or more processor cores. A video adapter drives a display, which is coupled to the system bus. The system bus is coupled to an input / output (I / O) bus via a bus bridge. I / O interfaces are coupled to the I / O bus and communicate with various I / O devices, such as input devices (e.g., keyboard, mouse, touchscreen), media trays (e.g., multimedia interfaces), transceivers (which can send and / or receive radio communication signals), cameras (which can capture still and moving digital video images), and external universal serial bus (USB) ports. Optionally, the interface connected to the I / O interfaces may be a USB interface.

[0102] The processor can be any conventional processor, including reduced instruction set computer (RISC) processors, complex instruction set computer (CISC) processors, or combinations thereof. Optionally, the processor can also be a special-purpose device such as an application-specific integrated circuit (ASIC). Optionally, the processor can also be a neural network processor or a combination of a neural network processor and the aforementioned conventional processors.

[0103] Optionally, in the various embodiments described in this application, the computer system 112 may be located remotely from the autonomous vehicle and wirelessly communicate with the autonomous vehicle. In other aspects, some processes described in this application may be executed on a processor within the autonomous vehicle, while others may be executed by a remote processor, including taking actions necessary to perform a single manipulation.

[0104] Computer system 112 can communicate with a software deployment server via a network interface. Optionally, the network interface can be a hardware network interface, such as a network interface card (NIC). The network can be an external network, such as the Internet, or an internal network, such as Ethernet or a virtual private network (VPN). Optionally, the network can also be a wireless network, such as a wireless fidelity (Wi-Fi) network or a cellular network.

[0105] In other embodiments of this application, computer system 112 may also receive information from or transfer information to other computer systems. Alternatively, sensor data collected from sensor system 104 of vehicle 100 may be transferred to another computer for processing. For example, data from computer system 112 may be transmitted via a network to a cloud-based computer system for further processing. In one example, computer system 112 may include a server with multiple computers, such as a load balancing server cluster.

[0106] Referring to Figure 3, an example of interaction between an autonomous vehicle and a cloud service center (cloud server) is shown. The cloud service center 220 can receive information (such as data collected by vehicle sensors or other information) from a vehicle 212 within its operating environment 200 via a network 211, such as a wireless communication network. The vehicle 212 may be an autonomous vehicle.

[0107] Based on the received data, the cloud service center 220 runs stored programs related to autonomous driving to control the vehicle 212. These programs can be: programs that manage the interaction between the autonomous vehicle and obstacles on the road, programs that control the path or speed of the autonomous vehicle, or programs that control the interaction between the autonomous vehicle and other autonomous vehicles on the road.

[0108] For example, cloud service center 220 can provide portions of a map to vehicle 212 via network 211. In other examples, operations can be divided among different locations. For instance, multiple cloud service centers can receive, verify, combine, and / or send information reports. In some embodiments, information reports and / or sensor data can also be sent between vehicles. Other configurations are also possible.

[0109] In some embodiments, cloud service center 220 sends suggested solutions (e.g., informing the vehicle of obstacles ahead and how to avoid them) to the autonomous vehicle regarding possible driving situations in the environment. For example, cloud service center 220 can assist the vehicle in determining how to proceed when facing specific obstacles in the environment. For instance, when cloud service center 220 determines that there is a turning intersection obstacle ahead of vehicle 212, it can determine a first traffic flow and a second traffic flow based on environmental information surrounding vehicle 212, thereby instructing vehicle 212 to follow the first traffic flow and avoid the second traffic flow.

[0110] The methods described in the following embodiments can all be implemented in a vehicle with the above-described hardware structure or in other devices that have the function of controlling the vehicle. For example, in an autonomous vehicle, it can also be a processor in a vehicle or other device that has the function of controlling the vehicle, such as the processor in the cloud service center 220 mentioned above.

[0111] With the rapid development of intelligent connected vehicle technology, autonomous driving has become an important direction for the automotive industry. According to the classification system of the Society of Automotive Engineers (SAE), autonomous driving can be divided into six levels: Level 0 to Level 5, with higher levels indicating a higher degree of automation. Level 0 is driverless automation, where the vehicle is completely manually driven, and the driver must perform all vehicle control operations. Level 1 is driver assistance, where the vehicle can assist the driver in performing simple and repetitive driving operations. Level 2 is partial driver automation, where the vehicle can simultaneously control speed and direction to complete some basic driving tasks, but the driver still needs to monitor the surrounding environment and take over the vehicle at any time. Level 3 is conditional driver automation, where the vehicle can achieve autonomous driving under specific conditions, such as on highways or dedicated roads. Under these conditions, Level 3 autonomous driving can complete all driving tasks and monitor the surrounding environment, and the driver can temporarily refrain from driving. However, once the automated system issues a takeover request, the driver must immediately take over the vehicle. Level 4 is high driver automation, where the vehicle can achieve fully autonomous driving in a specific area or environment without human intervention. Level 5 is a fully automated driving level, where the entire driving process is completed by the vehicle itself without any human intervention. Currently, no mass-produced vehicles have reached a true Level 3 level.

[0112] The following will use an autonomous vehicle (hereinafter referred to as the vehicle) as an example, specifically a Level 2 to Level 5 vehicle, and will describe a driving path planning method provided in this application with reference to the accompanying drawings. As shown in Figure 4, the driving path planning method may include:

[0113] S401, Vehicles obtain traffic flow information.

[0114] The traffic flow information includes the location, direction, and speed of other vehicles traveling around the vehicle, which is used to plan the vehicle's route.

[0115] Here, "self-vehicle" refers to the vehicle itself, and "other vehicles" refers to other vehicles around the vehicle. In some embodiments, the vehicle is equipped with sensing hardware, such as cameras, radar (e.g., lidar, millimeter-wave radar, etc.), etc. The vehicle can obtain the driving information of other vehicles around it based on this sensing hardware, and then generate traffic flow information based on this driving information.

[0116] In some embodiments, the vehicle acquires driving information of multiple other vehicles around it within a preset time period (e.g., 30 seconds, 45 seconds, 60 seconds, etc.). This driving information includes at least one of location, direction of travel, and speed. Based on the driving information, the vehicle acquires multiple vehicle trajectories corresponding to the other vehicles. Then, the vehicle matches the multiple vehicle trajectories together to obtain multiple successfully matched traffic flows. This traffic flow information includes information about the multiple traffic flows.

[0117] Optionally, a vehicle can determine the driving information of other vehicles by acquiring video information through cameras, point cloud information through lidar, information through millimeter-wave radar, and so on. That is, a vehicle can determine the driving information of other vehicles by acquiring some or all of the information from multiple sensing hardware.

[0118] For example, a vehicle pairs multiple vehicle trajectories, clusters two successfully matched trajectories into one traffic flow, and obtains the corresponding multiple traffic flows. Then, the vehicle again pairs these multiple traffic flows together, obtaining the corresponding multiple traffic flows, repeating the above steps until the obtained multiple traffic flows can no longer be matched successfully. These traffic flows that cannot be matched again are identified as the final multiple traffic flows obtained by the vehicle. It should be understood that during this process, there may be vehicle trajectories that cannot be matched successfully with other vehicle trajectories or traffic flows temporarily (or permanently). If there is a vehicle trajectory that ultimately cannot be matched successfully with other traffic flows (or vehicle trajectories), the vehicle can identify that vehicle trajectory as a traffic flow containing only that single trajectory, and the traffic flow information obtained by the vehicle also includes the information of that vehicle trajectory.

[0119] A successful match includes two vehicle trajectories (or traffic flows) having a lateral distance less than a fourth threshold and traveling in the same direction. Optionally, the vehicle can determine the lateral distance between different vehicle trajectories (or traffic flows) based on the location of other vehicles indicated by their driving information. Optionally, the fourth threshold may be, for example, 0.5 meters, 1 meter, etc. For example, based on driving information, the vehicle obtains the locations of vehicle 1 and vehicle 3, determines that the lateral distance between driving trajectory 1 corresponding to vehicle 1 and driving trajectory 3 corresponding to vehicle 3 is 0.8 meters, and determines that this lateral distance is less than the fourth threshold of 1 meter. Then, the vehicle can determine that the driving trajectories of vehicle 1 (driving trajectory 1) and vehicle 3 (driving trajectory 3) are successfully matched, that is, vehicle 1 (driving trajectory 1) and vehicle 3 (driving trajectory 3) can be clustered into one traffic flow, such as traffic flow A. Optionally, the vehicle can also obtain the location of vehicle 4 based on driving information, determine that the lateral distance between driving trajectory 4 corresponding to vehicle 4 and traffic flow A is 0.5 meters, and determines that this lateral distance is less than the fourth threshold of 1 meter. If the vehicle can determine that the driving trajectory 4 of vehicle 4 is successfully matched with traffic flow A, then the vehicle can cluster the driving trajectory 4 of vehicle 4 and traffic flow A into a single traffic flow, such as traffic flow B.

[0120] In some embodiments, after obtaining multiple traffic flows, vehicles are clustered into the trajectory points of all vehicle trajectories within a single traffic flow, and then sorted and smoothed to obtain the processed traffic flow. The multiple traffic flows include multiple processed traffic flows.

[0121] For example, as shown in Figure 5, the vehicle is equipped with at least one camera. The vehicle captures images within the field of view of all cameras to obtain the driving information of other vehicles within the field of view. The vehicle refreshes its historical trajectory at preset time intervals (e.g., 30 seconds). That is, the vehicle captures images at preset time intervals and, based on the driving information of other vehicles included in the images, obtains the driving trajectory of other vehicles in the image frame corresponding to a given time interval. For example, as shown in Figure 6(a), the vehicle obtains multiple driving trajectories of other vehicles in the image frame corresponding to a certain time interval. Then, the vehicle performs pairwise matching on all the multiple driving trajectories of other vehicles to obtain matching results, which include successful matches and unsuccessful matches. For example, the vehicle identifies two driving trajectories with a lateral physical distance less than a fourth threshold and the same driving direction (e.g., the same driving trend) as successfully matched driving trajectories, while driving trajectories with a lateral physical distance greater than or equal to the fourth threshold, or with different driving directions, are identified as unsuccessfully matched driving trajectories. Then, the vehicle outputs an adjacency matrix representing the matching result. For example, the vehicle obtains driving trajectory 1, driving trajectory 2, and driving trajectory 3. The vehicle matches the three driving trajectories and determines that driving trajectory 1 and driving trajectory 3 are successfully matched, driving trajectory 1 and driving trajectory 2 are not successfully matched, and driving trajectory 2 and driving trajectory 3 are not successfully matched. Then, the vehicle can output the adjacency matrix shown below (1).

[0122] Then, as shown in Figure 5, the vehicle can cluster the acquired multiple other vehicle trajectories based on the adjacency matrix. The vehicle groups the trajectory points of all other vehicle trajectories together and sorts and smooths these grouped trajectory points according to the driving direction of the other vehicles. Based on this, the vehicle can complete the processing of each class. The trajectory point corresponds to the time information of its generation. Sorting the trajectory points within a class can avoid backflow problems in the generated traffic flow. The trajectory point also corresponds to the location information of its generation. Smoothing the trajectory points within a class (such as weighted averaging of trajectory points within a preset range) can avoid bending problems in the generated traffic flow. Afterwards, the vehicle can acquire all traffic flows within its field of view per unit time. For example, based on the trajectory processing process shown in Figure 5, the vehicle can generate multiple traffic flows as shown in Figure 6(b) based on the multiple other vehicle trajectories shown in Figure 6(a). It should be understood that the road topology structure shown by the dashed lines in Figure 6 includes lane lines, road boundaries, intersection area diagrams, etc.

[0123] In this way, vehicles detect the driving trajectories of other vehicles in the vicinity and aggregate these trajectories into a reference traffic flow, which subsequent vehicles can use for route planning. Furthermore, by using this reference traffic flow, which includes existing traffic within a preset time period, route planning can achieve better results.

[0124] It should be understood that the reference traffic flow is the traffic flow obtained by clustering, sorting, and smoothing the driving trajectories of other vehicles. For example, the reference traffic flow is shown in Figure 6(b).

[0125] Furthermore, the trajectory processing shown in Figure 5 is a cyclical process. Vehicles refresh their historical trajectories according to preset time intervals, and upon acquiring new traffic flow information, they can refresh the historical traffic flow information again. Based on the new traffic flow information, subsequent steps then plan the target driving path. In this way, the target driving path acquired by the vehicle can be updated over time to meet the latest driving requirements.

[0126] In some embodiments, during the trajectory processing described above, the vehicle can also acquire the driving trajectories of other vehicles through other sensing hardware. For example, the vehicle can determine the distance between itself and different other vehicles by using lidar ranging, and then determine the driving trajectories of different other vehicles and the corresponding traffic flow based on the lidar ranging results. Alternatively, the vehicle can combine images captured by a camera with lidar ranging results to determine the trajectories of different other vehicles and the corresponding traffic flow. It should be understood that this application embodiment uses the example of a vehicle acquiring images through a camera to determine traffic flow to describe the vehicle's driving path planning process. The specific implementation methods of the vehicle acquiring traffic flow through other sensing hardware can refer to the implementation of acquiring traffic flow through a camera, and will not be exemplified one by one here.

[0127] In some embodiments, the vehicle may also acquire detection data sent by other roadside devices (such as roadside cameras), other vehicles, servers, etc., such as data including the driving trajectories of vehicles near the vehicle.

[0128] In this way, vehicles can combine the detection data they acquire with the detection data sent by other devices to generate traffic flow information.

[0129] In some embodiments, the vehicle obtains traffic flow information only when it determines that route planning is needed. For example, as shown in FIG7, step S400 is included before step S401.

[0130] S400, The vehicle is determined to meet the route planning conditions. If so, proceed to step S401.

[0131] The path planning conditions include the appearance of an intersection ahead of the vehicle and the determination of the intersection's location. Optionally, the intersection generally encompasses a large area, including an entrance and an exit. For example, as shown in Figure 8, the vehicle determines that an intersection appears ahead, within the area indicated by the rectangular dashed box. Furthermore, the vehicle can determine the intersection's location, such as determining that it is approaching an entrance within the area indicated by the elliptical dashed line 81 and an exit within the area indicated by the elliptical dashed line 82. In this case, the vehicle can determine that the path planning conditions are met, triggering step S401 to begin acquiring traffic flow for path planning.

[0132] Optionally, if the distance between the vehicle and the intersection is less than or equal to a fifth threshold, it can be determined that the vehicle is approaching the intersection. Optionally, the vehicle can determine the fifth threshold based on its current speed. For example, the vehicle can multiply its current speed by a preset time (e.g., 2 seconds) as the fifth threshold, thus determining whether the vehicle is about to enter the intersection while traveling at its current speed.

[0133] Optionally, the vehicle is generally equipped with a standard map that indicates basic road conditions, based on which the vehicle can determine whether an exit is ahead. For example, the vehicle can also determine whether an exit is ahead in the real environment through sensing devices. In some embodiments, if the position difference between the exit location determined by the vehicle based on the standard map and the exit location determined by the sensing devices does not exceed a sixth threshold (e.g., 5 meters), the vehicle can determine that the current navigation information is valid and the exit location is clear.

[0134] In some embodiments, the vehicle determines an intersection ahead and its location based on the acquired environmental information. The vehicle then acquires traffic flow information. Optionally, the vehicle may determine the environmental information by capturing images of its surroundings using a camera. Alternatively, the vehicle may determine the environmental information using laser point cloud information acquired by LiDAR.

[0135] Optionally, vehicles can identify intersections by recognizing intersection signs, lane lines, and the appearance of static obstacles (such as fence appearance).

[0136] In some embodiments, vehicles identify entrances and exits to facilitate more accurate subsequent path planning. For example, in step S402 below, the vehicle needs to determine the traffic flow it needs to follow and the traffic flow it needs to avoid. The traffic flow the vehicle needs to follow must enter and exit the same intersection as the vehicle. For example, as shown in Figure 8, the traffic flow formed by the trajectory of another vehicle 83 enters the same intersection as the vehicle, and the vehicle may need to follow the traffic flow corresponding to that vehicle 83. However, since the exit of that vehicle 83 is not the vehicle's exit, the vehicle cannot follow the traffic flow corresponding to that vehicle 83. Therefore, after determining the entrance and exit locations, the vehicle triggers path planning to facilitate subsequent traffic flow filtering. The specific traffic flow filtering process is described in detail below.

[0137] In this way, when a vehicle determines that it needs to pass through an intersection, it plans its own driving path based on other traffic flow, so as to achieve a more human-like autonomous driving effect.

[0138] S402. Based on traffic flow information, the vehicle determines the first traffic flow and the second traffic flow. The first traffic flow has a lateral distance of less than a first threshold and travels in the same or similar direction as the vehicle. The second traffic flow has a lateral distance of greater than a second threshold, and the second threshold is greater than the first threshold.

[0139] The first traffic flow is the forward traffic flow corresponding to the vehicle, and the second traffic flow is the lateral traffic flow corresponding to the vehicle. The lateral traffic flow includes the left-side traffic flow and / or the right-side traffic flow.

[0140] In some embodiments, during the vehicle's operation, at least one other vehicle is present near the first traffic flow. Through the steps described above, the vehicle can obtain traffic flow information of the other vehicle based on its trajectory, such as multiple traffic flows near the first traffic flow. Then, the vehicle can determine the first traffic flow and the second traffic flow based on this information. For example, the vehicle can filter out the first and second traffic flows from among the multiple traffic flows.

[0141] In some embodiments, after acquiring multiple traffic flows, the vehicle can obtain the lateral distance between the vehicle and each of the multiple traffic flows. The vehicle can then filter between a first traffic flow and a second traffic flow based on this lateral distance. Optionally, the vehicle can determine the lateral distance between itself and the multiple traffic flows based on its own position and the positions of other vehicles indicated by their driving information.

[0142] Optionally, the vehicle itself has a certain width, and the traffic flow it is targeting also has a certain width. Therefore, in determining the lateral distance between the vehicle and the traffic flow, the vehicle can determine the distance between the left or right edge of the vehicle and the left or right edge of the traffic flow based on the relative position of the vehicle and the traffic flow, and use this distance as the lateral distance. For example, if the vehicle determines that the traffic flow is to its right, the lateral distance can be determined as the distance between the right edge of the vehicle and the left edge of the traffic flow.

[0143] For example, traffic flows that are close to a vehicle laterally and travel in the same or similar direction can guide the vehicle's movement. The vehicle can then consider this traffic flow as the first traffic flow. The number of first traffic flows is one. The vehicle can determine the first traffic flow that is close to it laterally using a small first threshold, such as 0.5 meters or 1 meter. For example, among multiple traffic flows, the vehicle selects the traffic flow that is less than 1 meter laterally and travels in the same or similar direction as its first traffic flow. Optionally, similar travel direction includes situations where other traffic flows and the vehicle's exit point are similar, such as both heading towards the same exit. Optionally, the exit may include multiple lanes, and same travel direction includes situations where the lane of other traffic flows is the same lane as the vehicle's current lane. The specific process for determining the first traffic flow is detailed in the following description.

[0144] For example, traffic flows that are laterally distant from a vehicle or traveling in the opposite direction cannot be used as guiding traffic flows, but these flows may affect driving safety, so vehicles need to avoid them. In this case, the vehicle can use these flows as secondary traffic flows, where there must be at least one secondary traffic flow, such as at least one left-hand flow or at least one right-hand flow. The vehicle can determine secondary traffic flows that are laterally distant from it using a large second threshold, such as 3.5 meters or 4 meters. For example, from multiple traffic flows acquired, the vehicle selects those laterally distant from it by more than 4 meters or traveling in the opposite direction as secondary traffic flows.

[0145] Optionally, the vehicle acquires the traffic flow within its field of vision through sensing devices, assuming that this traffic flow will affect the vehicle's driving. Therefore, the vehicle filters out a first traffic flow and a second traffic flow from this traffic flow. Alternatively, traffic flows with a lateral distance exceeding a preset threshold from the vehicle will not guide the vehicle's driving and will not affect the vehicle's driving safety. Then, based on the traffic flow information, the vehicle can first filter out traffic flows with a distance less than the preset threshold from the acquired traffic flows. Then, the first traffic flow is further filtered out from these traffic flows with distances less than the preset threshold, resulting in a first traffic flow and a second traffic flow. Optionally, the sensing devices may include, for example, sensing hardware and a processor within the vehicle. The processor processes the data collected by the sensing hardware through a pre-configured program to obtain the traffic flow information.

[0146] It should be understood that the preset threshold is greater than the second threshold. For example, the preset threshold is 8 meters, 10 meters, etc.

[0147] For example, as shown in Figure 8, after detecting an intersection ahead, the vehicle obtains nearby traffic flow information. The vehicle can then filter the traffic flow generated by other vehicles traveling in front of it (first traffic flow) and by other vehicles traveling to its left or right (second traffic flow).

[0148] In some scenarios, the driving environment may change as a vehicle approaches an intersection. For example, as a vehicle approaches an exit, it may need to change lanes, and the first traffic flow it chooses to follow may also change. Therefore, as the distance between the vehicle and the exit changes, the vehicle can adaptively select the first traffic flow to follow. Optionally, when the vehicle does not need to change lanes, it plans its route based on the determined first and second traffic flows. When the vehicle intends to change lanes, it triggers the determination of the first and second traffic flows again. In this way, the vehicle can adaptively trigger the refresh of the first and second traffic flows according to changes in the driving environment.

[0149] For example, as shown in Figure 9, step S402 may include steps S4021a and S4021b-S4023b.

[0150] S4021a, Select vehicles whose lateral distance from each other is greater than a second threshold as the second traffic flow.

[0151] In some embodiments, after obtaining traffic flow information, the vehicle selects from the multiple traffic flows indicated by the traffic flow information the traffic flow flow with a lateral distance greater than a second threshold as the second traffic flow.

[0152] The method for obtaining the second traffic flow is detailed in step S402 above and will not be repeated here.

[0153] S4021b: The vehicle determines that the distance between its driving position and the upcoming exit is greater than a third threshold. If yes, proceed to step S4022b; otherwise, proceed to step S4023b.

[0154] S4022b: Select the first traffic flow as the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose driving direction is similar to that of the vehicle.

[0155] S4023b: Select the traffic flow whose lateral distance to the vehicle is less than the first threshold and whose travel direction is the same as the vehicle as the first traffic flow.

[0156] In some embodiments, when determining whether the current path planning conditions are met, the vehicle has already determined whether an intersection has been detected ahead of the current driving path. If an intersection is detected ahead, the vehicle can then continue to detect the distance between the vehicle and the exit of that intersection, and combine this distance with the selected first traffic flow from among the multiple traffic flows already acquired.

[0157] For example, if the distance between a vehicle's position and the upcoming exit is greater than a third threshold, the vehicle, based on traffic flow information, identifies traffic flows whose lateral distance is less than a first threshold and whose travel direction is similar as the first traffic flow. Similar travel direction includes the first traffic flow having an exit position similar to the vehicle's. Optionally, similar exit position may include, for example, an angular deviation between the travel direction of the first traffic flow and the vehicle's travel direction not exceeding 30 degrees.

[0158] Alternatively, if the distance between the vehicle's driving position and the exit ahead is less than or equal to the third threshold, the vehicle determines the traffic flow that is less than the first threshold in lateral distance and travels in the same direction as the first traffic flow based on the traffic flow information. Traveling in the same direction includes the first traffic flow being in the same lane as the vehicle's current lane.

[0159] Optionally, the vehicle can determine a third threshold based on its current speed. For example, the vehicle can multiply its current speed by a preset time (e.g., 1 second) as the third threshold. In this way, the vehicle can determine whether it is about to reach an exit while traveling at its current speed, and then select the first traffic flow to follow.

[0160] In this way, when a vehicle is far from the exit, it has the opportunity to change lanes and can choose from multiple lanes. Therefore, by simply following another vehicle traveling roughly ahead, the correctness of the driving path can be ensured. However, when a vehicle is close to the exit, it does not have the opportunity to change lanes and must follow another vehicle traveling in the same lane ahead to ensure the correctness of the driving path.

[0161] It should be understood that the embodiments of this application do not limit the selection order between the first traffic flow and the second traffic flow. A vehicle may first select the first traffic flow from among the multiple traffic flows already acquired, and then select the second traffic flow from among the multiple traffic flows already acquired; alternatively, a vehicle may first select the second traffic flow from among the multiple traffic flows already acquired, and then select the first traffic flow from among the multiple traffic flows already acquired. That is, the embodiments of this application do not limit the execution order between steps S4021a and steps S4021b-S4023b.

[0162] S403. The vehicle plans its target driving path based on the first traffic flow and the second traffic flow. The target driving path follows the first traffic flow and avoids the second traffic flow.

[0163] In some embodiments, after determining the first traffic flow and the second traffic flow, the vehicle can plan a target driving path based on the first traffic flow and the second traffic flow. Furthermore, the planned target driving path needs to follow the first traffic flow and avoid the second traffic flow.

[0164] In some embodiments, the target travel path is a predicted safe path that the vehicle can subsequently travel, and this target travel path is a passable area for the vehicle. Driving within this passable area ensures driving safety.

[0165] In some embodiments, the constraints corresponding to the first and second traffic flows are soft constraints for the target driving path planning generated by the vehicles. The constraints referenced during the vehicle's driving path planning process may also include hard constraints such as road boundaries and obstacle boundaries. Therefore, the target driving path also avoids boundaries formed by road boundaries and / or obstacles.

[0166] Optionally, the vehicle can detect hard constraints such as road boundaries and obstacle boundaries through sensing hardware, and the vehicle can determine the hard constraints by determining the detection data output by the sensing device.

[0167] Thus, by combining soft and hard constraints in target driving path planning, the vehicle can obtain a more reasonable target driving path.

[0168] Furthermore, even if there are anomalies in the first or second traffic flow, vehicles can still obtain the target driving path that ensures safe driving based on hard constraints.

[0169] For example, the vehicle takes a first traffic flow and a second traffic flow as input to perform driving path planning, and outputs a target driving path that follows the first traffic flow and avoids the second traffic flow. As shown in Figure 10, the first traffic flow can guide the vehicle's driving path (e.g., the corrected driving path), and the second traffic flow forms the boundary of the vehicle's driving path. The vehicle uses the first and second traffic flows as constraints to perform secondary optimization on the original driving path (e.g., the driving path determined based on hard constraints) to obtain the corrected driving path.

[0170] In some embodiments, during the secondary optimization process, the vehicle uses the trajectory points corresponding to the first traffic flow as the initial conjecture of the target driving path, the trajectory points corresponding to the first traffic flow as the reference points for generating the target driving path, and the trajectory points corresponding to the second traffic flow as the left / right soft boundaries of the target driving path. Furthermore, the boundaries formed by road boundaries, obstacles, etc., can also be used as hard boundaries. The target driving path is generated through the target cost function.

[0171] Optionally, the target cost function may include, for example, a smoothness cost for the target driving path, an overall length cost, and a distance cost from a reference point. The smoothness cost ensures the smoothness of the acquired target driving path, such as improving the smoothness of subsequent vehicle travel and avoiding frequent lane changes. The overall length cost reduces the overall length of the target driving path, thereby reducing the travel distance of subsequent vehicles. The reference point distance cost ensures that the distance between trajectory points in the acquired target driving path and the reference point is small (i.e., the target driving path offset is small), enabling the target driving path to follow the first traffic flow.

[0172] For example, a vehicle can generate a target driving path using the target cost function shown in formula (1) below. Here, w1, w2, and w3 represent the weights of different costs included in the target cost function, which can be determined based on empirical or experimental values. cos1 represents the smoothness cost, which can be determined using formula (2) below. cost2 represents the overall length cost, which can be determined using formula (3) below. cost3 represents the distance cost to the reference point, which can be determined using formula (4) below. Where x i y i The coordinates of the optimization point are represented by: i represents the i-th trajectory point; n represents the total number of trajectory points; x i-ref y i-ref This represents the trajectory points of the reference path. It should be understood that the reference path is the first traffic flow and the second traffic flow, the reference points are the trajectory points in the first and second traffic flows obtained by the vehicle, and the optimization points are the trajectory points in the target driving path planned based on the reference points.

[0173] Thus, compared to driving path planning methods that rely solely on hardware-based obstacle perception, the original planned driving path obtained is different. The driving path planning method provided in this application, based on the corrected planned driving path obtained from existing traffic flow, can achieve safer passage through intersections by using the first traffic flow as a guide and the second traffic flow as the boundary of the passable area.

[0174] In this way, based on the historical driving trajectories of other vehicles in front, a stable first traffic flow can be generated. Following this first traffic flow can prevent unexpected steering problems caused by perceived lane instability.

[0175] Furthermore, when dealing with obstacles around intersections (such as flower beds at intersections or roadblocks marked by fences in the middle of the road), other vehicles traveling in the forward direction can create an obstacle avoidance path that conforms to semantic rules. Therefore, following the traction of the forward traffic flow, even if the vehicle is limited by the detection range of its own perception hardware, it can plan a reasonable obstacle avoidance path when no obstacle is detected, and this obstacle avoidance path also has the correct obstacle avoidance direction.

[0176] Furthermore, in complex intersection scenarios such as double left turns and multi-lane intersections, the vehicle's planned target driving path can avoid second-flow traffic traveling laterally, thus avoiding interference with other vehicles' driving. In this way, while achieving its own driving goal, the vehicle avoids interfering with other vehicles in the process, enabling it to drive a reasonable, human-like, and efficient driving trajectory.

[0177] In some embodiments, after a target driving path is generated, the vehicle can be controlled to drive according to the target path, such as to cross an intersection.

[0178] In some embodiments, after the vehicle generates a target driving path, it can display the target driving path on the in-vehicle display screen, thereby providing users with the experience of viewing the driving path even during autonomous driving.

[0179] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information (such as vehicle surrounding images and vehicle driving trajectories) in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals. For example, in the technical solution of this application, the processing of user personal information is carried out with the user's authorization, which is stated uniformly here and will not be repeated below.

[0180] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] This application embodiment can divide the driving route planning system into functional modules based on the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0182] Figure 11 illustrates a possible structural diagram of the driving route planning device involved in the above embodiments. As shown in Figure 11, the driving route planning device 1100 may include an acquisition unit 1101 and a processing unit 1102. The driving route planning device 1100 is used to execute the driving route planning method described above, for example, to execute the driving route planning method shown in Figures 4, 7, or 9. Of course, the driving route planning device may also include other modules, or it may include fewer modules. This application embodiment does not limit this.

[0183] The acquisition unit 1101 is used to acquire detection data.

[0184] Specifically, the acquisition unit 1101 is used to execute step S401 shown in Figure 4. For example, the acquisition unit 1101 is used to acquire detection data for determining traffic flow information, such as the vehicle's driving position, driving direction, driving speed, the position, driving direction, driving speed, distance from other vehicles, information on surrounding obstacles, and the distance between obstacles and the vehicle.

[0185] Processing unit 1102 is used to acquire traffic flow information based on detection data, generate a first traffic flow and a second traffic flow based on the traffic flow information, and plan the target driving path of the vehicles based on the first traffic flow and the second traffic flow. For example, processing unit 1102 is used to execute steps S401, S402, and S403 shown in Figure 4. Alternatively, processing unit 1102 is used to execute step S400 shown in Figure 7. Alternatively, processing unit 1102 is used to execute steps S4021a and S4021b-S4023b shown in Figure 9.

[0186] Optionally, the driving route planning device 1100 shown in FIG11 may further include a storage unit (not shown in FIG11) storing a program or instructions. When the acquisition unit 1101 and the processing unit 1102 execute the program or instructions, the driving route planning device 1100 shown in FIG11 can perform the driving route planning method described in the above method embodiments.

[0187] The operation and / or function of each unit in the driving route planning device 1100 are respectively to implement the corresponding process of the driving route planning method described in the above method embodiments. All relevant contents of each step involved in the above method embodiments can be referred to the functional description of the corresponding functional unit. For the sake of brevity, they will not be repeated here.

[0188] The technical effects of the driving path planning device 1100 shown in Figure 11 can be referred to the technical effects of the driving path planning method described in the above method embodiments, and will not be repeated here.

[0189] This application also provides a chip system, as shown in FIG12. The chip system 1200 includes at least one processor 1201 and at least one interface circuit 1202. As an example, when the chip system 1200 includes one processor and one interface circuit, the processor can be the processor 1201 shown in the solid box in FIG12 (or the processor 1201 shown in the dashed box), and the interface circuit can be the interface circuit 1202 shown in the solid box in FIG12 (or the interface circuit 1202 shown in the dashed box). When the chip system 1200 includes two processors and two interface circuits, the two processors include the processor 1201 shown in the solid box and the processor 1201 shown in the dashed box in FIG12, and the two interface circuits include the interface circuit 1202 shown in the solid box and the interface circuit 1202 shown in the dashed box in FIG12. This is not a limitation.

[0190] The processor 1201 and the interface circuit 1202 can be interconnected via a line. For example, the interface circuit 1202 can be used to receive signals. As another example, the interface circuit 1202 can be used to send signals to other devices (e.g., a processor). Exemplarily, the interface circuit 1202 can read instructions stored in memory and send those instructions to the processor. When the instructions are executed by the processor, the driving path planning device can perform the steps in the above embodiments. Of course, the chip system may also include other discrete components, and this application embodiment does not specifically limit this.

[0191] For example, the chip system may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0192] It should be understood that each step in the above method embodiments can be completed by integrated logic circuits in the processor hardware or by instructions in software form. The method steps disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0193] This application also provides a computer-readable storage medium for storing one or more computer programs, the one or more computer programs including instructions that, when executed by a computer, cause the computer to perform the corresponding process of the driving path planning method described above.

[0194] In some embodiments, the disclosed method may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art.

[0195] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the driving path planning method described above.

[0196] The apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments of this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0197] The steps of the methods or algorithms described in conjunction with the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, compact disc read-only memory (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an application-specific integrated circuit (ASIC).

[0198] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, the division of the above functional modules is only used as an example. In practical applications, the above functions can be assigned to different functional modules as needed; that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0199] In the several embodiments provided in this application, it should be understood that the disclosed methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of modules or units may be electrical, mechanical or other forms.

[0200] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0201] Computer-readable storage media include, but are not limited to, any of the following: USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media capable of storing program code.

[0202] 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. A method for planning a driving route, characterized in that, Applied to vehicles, the method includes: Obtain traffic flow information; Based on the traffic flow information, a first traffic flow and a second traffic flow are determined. The first traffic flow has a lateral distance of less than a first threshold and travels in the same or similar direction as the vehicle. The second traffic flow has a lateral distance of greater than a second threshold and travels in the same or similar direction as the vehicle. Based on the first traffic flow and the second traffic flow, a target driving path for the vehicle is planned, which follows the first traffic flow and avoids the second traffic flow.

2. The method according to claim 1, characterized in that, The first traffic flow is the forward traffic flow corresponding to the vehicle, and the second traffic flow is the lateral traffic flow corresponding to the vehicle, wherein the lateral traffic flow includes left-side traffic flow and / or right-side traffic flow.

3. The method according to claim 1 or 2, characterized in that, The step of determining the first traffic flow and the second traffic flow based on the traffic flow information includes: If the distance between the vehicle's driving position and the exit ahead is greater than a third threshold, based on the traffic flow information, the traffic flow that is less than the first threshold in lateral distance from the vehicle and has a similar driving direction is identified as the first traffic flow. The similar driving direction includes the first traffic flow being similar to the exit position of the vehicle. or, If the distance between the vehicle's driving position and the exit ahead is less than or equal to the third threshold, based on the traffic flow information, the traffic flow that is less than the first threshold in lateral distance from the vehicle and travels in the same direction is identified as the first traffic flow. The same travel direction includes the first traffic flow being in the same lane as the lane where the vehicle is currently located.

4. The method according to any one of claims 1-3, characterized in that, The acquisition of traffic flow information includes: Obtain the driving information of multiple other vehicles around the vehicle within a preset time period, wherein the driving information includes at least one of location, driving direction, and speed; Based on the driving information, obtain multiple vehicle trajectories corresponding to the multiple other vehicles; The multiple vehicle trajectories are matched in pairs, and the two successfully matched vehicle trajectories are clustered into a single traffic flow to obtain multiple traffic flows. The traffic flow information includes information about the multiple traffic flows.

5. The method according to claim 4, characterized in that, A successful match is defined as two vehicle trajectories having a lateral distance less than a fourth threshold and traveling in the same direction.

6. The method according to claim 4 or 5, characterized in that, After clustering the two successfully matched vehicle trajectories into a single traffic flow, the method further includes: The trajectory points of all vehicles clustered into a single traffic flow are sorted and smoothed to obtain the processed traffic flow. The multiple traffic flows include multiple processed traffic flows.

7. The method according to any one of claims 4-6, characterized in that, The step of determining the first traffic flow and the second traffic flow based on the traffic flow information includes: The first traffic flow and the second traffic flow are selected from the multiple traffic flows.

8. The method according to any one of claims 1-7, characterized in that, The target driving path also avoids road boundaries and / or boundaries formed by obstacles.

9. The method according to any one of claims 1-8, characterized in that, Prior to acquiring traffic flow information, the method further includes: Based on the collected environmental information, it is determined that an intersection appears ahead of the vehicle, and the location of the intersection is determined.

10. A driving path planning device, characterized in that, include: A processor and a memory, the memory being coupled to the processor, the memory being used to store computer-readable instructions, which, when read from the memory by the processor, cause the driving path planning device to perform the method as described in any one of claims 1-9.

11. A vehicle, characterized in that, The vehicle includes the vehicle itself and the driving path planning device as described in claim 10.

12. A chip system, characterized in that, It includes at least one processor and at least one interface circuit, the at least one interface circuit being used to perform transceiver functions and send instructions to the at least one processor, the at least one processor executing the instructions, the at least one processor performing the method as described in any one of claims 1-9.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1-9.

14. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method as described in any one of claims 1-9.

Images