Path planning method, device and electronic equipment for autonomous driving

Abstract

This application provides a path planning method, device, electronic device, computer-readable storage medium, and computer program product for autonomous driving. The method includes: establishing a solution space for obstacle avoidance paths based on obstacle information in the lane where the vehicle is located and adjacent lanes; sampling and processing within the solution space to obtain multiple discrete waypoints, and planning multiple obstacle avoidance paths based on these waypoints; wherein each obstacle avoidance path starts at the vehicle's position and ends at the farthest waypoint, which represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple waypoints; calculating the driving cost corresponding to each of the multiple obstacle avoidance paths; filtering the multiple obstacle avoidance paths based on their respective driving costs to obtain a target obstacle avoidance path; and controlling the vehicle to drive according to the target obstacle avoidance path. This application can improve driving efficiency while ensuring driving safety.

Description

Technical Field

[0001] This application relates to vehicle technology, and more particularly to an autonomous driving path planning method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] Autonomous driving technology, also known as driverless technology, is a technology for intelligent connected vehicles that uses computer systems to enable unmanned driving. Autonomous driving technology relies on the collaborative efforts of various advanced technologies, such as artificial intelligence, computer vision, radar, and global positioning systems, to enable vehicles to drive automatically and safely without human intervention.

[0003] Autonomous obstacle avoidance is a crucial aspect of autonomous driving technology, directly impacting its intelligence and safety. Current solutions typically involve obstacle avoidance within the vehicle's own lane; however, this planned obstacle avoidance path can negatively affect the vehicle's driving efficiency. Summary of the Invention

[0004] This application provides a path planning method, device, electronic device, computer-readable storage medium, and computer program product for autonomous driving, which can improve driving efficiency while ensuring driving safety.

[0005] The technical solution of this application is implemented as follows:

[0006] This application provides a path planning method for autonomous driving, including:

[0007] The solution space for obstacle avoidance paths is established based on the obstacle information in the lane where the vehicle is located and in adjacent lanes;

[0008] Multiple discrete waypoints are obtained by sampling within the solution space, and multiple obstacle avoidance paths are planned based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts from the position of the vehicle and ends at the waypoint furthest from the vehicle, and the waypoint furthest from the vehicle represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints.

[0009] Calculate the driving cost corresponding to each of the multiple obstacle avoidance paths;

[0010] The multiple obstacle avoidance paths are filtered based on their respective travel costs to obtain the target obstacle avoidance path.

[0011] The vehicle is controlled to travel along the target obstacle avoidance path.

[0012] This application provides a path planning device for autonomous driving, comprising:

[0013] A module is established to create a solution space for obstacle avoidance paths based on information about obstacles in the vehicle's lane and adjacent lanes.

[0014] The planning module is used to perform sampling processing in the solution space to obtain multiple discrete waypoints, and to plan multiple obstacle avoidance paths based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts from the position of the vehicle and ends at the farthest waypoint, and the farthest waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints.

[0015] The calculation module is used to calculate the driving cost corresponding to each of the multiple obstacle avoidance paths;

[0016] The filtering module is used to filter the multiple obstacle avoidance paths according to the driving cost corresponding to each of the multiple obstacle avoidance paths, so as to obtain the target obstacle avoidance path;

[0017] The control module is used to control the vehicle to travel according to the target obstacle avoidance path.

[0018] This application provides an electronic device, including:

[0019] Memory, used to store executable instructions;

[0020] The processor is used to implement the autonomous driving path planning method provided in this application when executing executable instructions stored in the memory.

[0021] This application provides a computer-readable storage medium storing executable instructions for inducing a processor to execute and implement the autonomous driving path planning method provided in this application.

[0022] This application provides a computer program product including executable instructions for implementing the autonomous driving path planning method provided in this application when executed by a processor.

[0023] This application has the following beneficial effects:

[0024] This application establishes a solution space for obstacle avoidance paths based on obstacle information in the vehicle's current lane and adjacent lanes. Multiple discrete road points are obtained through sampling within the solution space, and multiple obstacle avoidance paths are planned based on these road points. Each obstacle avoidance path starts at the vehicle's position and ends at the road point furthest from the vehicle, where the road point represents the road point with the largest longitudinal distance from the vehicle. The driving cost corresponding to each of the multiple obstacle avoidance paths is calculated. Based on the driving costs of each path, the multiple obstacle avoidance paths are filtered to obtain the target obstacle avoidance path. The vehicle is then controlled to drive according to the target obstacle avoidance path. This application comprehensively considers multiple lanes rather than being limited to the current lane, facilitating decisions on whether to avoid obstacles in the current lane or change lanes, ultimately obtaining the target obstacle avoidance path with the lowest driving cost, thus maximizing driving efficiency while ensuring driving safety. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the architecture of an autonomous driving path planning system provided in an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of the structure of the vehicle-mounted device provided in an embodiment of this application;

[0028] Figure 3A This is a first flowchart illustrating the path planning method for autonomous driving provided in an embodiment of this application;

[0029] Figure 3B This is a second flowchart illustrating the path planning method for autonomous driving provided in an embodiment of this application;

[0030] Figure 3C This is a schematic diagram of the third process of the autonomous driving path planning method provided in the embodiments of this application. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] In the following description, references to "some embodiments" describe a subset of all possible embodiments; however, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. In the following description, the term "a plurality of" means at least two.

[0033] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0035] This application provides a path planning method, apparatus, electronic device, computer-readable storage medium, and computer program product for autonomous driving, which can improve driving efficiency while ensuring driving safety. The following describes exemplary applications of the electronic device provided in this application. The electronic device provided in this application can be implemented as an in-vehicle device or as a server.

[0036] See Figure 1 , Figure 1 This is a schematic diagram of the architecture of the autonomous driving path planning system 100 provided in the embodiments of this application. The vehicle-mounted device 400 is connected to the server 200 through the network 300, wherein the network 300 can be a wide area network or a local area network, or a combination of the two.

[0037] In some embodiments, taking an in-vehicle device as an example, the autonomous driving path planning method provided in this application can be implemented by an in-vehicle device. For example, the in-vehicle device 400 establishes a solution space for obstacle avoidance paths based on obstacle information in the lane where the vehicle (referring to the vehicle deployed by the in-vehicle device 400) is located and in adjacent lanes; it performs sampling processing within the solution space to obtain multiple discrete waypoints, and plans multiple obstacle avoidance paths based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts at the position of the vehicle and ends at the farthest discrete waypoint, and the farthest discrete waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints; it calculates the driving cost corresponding to each of the multiple obstacle avoidance paths; it filters the multiple obstacle avoidance paths based on the driving cost corresponding to each of the multiple obstacle avoidance paths to obtain a target obstacle avoidance path; and it controls the vehicle to drive according to the target obstacle avoidance path. In the above method, the vehicle-mounted device 400 performs path planning locally without transmitting data to a remote server for processing. This greatly reduces data transmission time and latency, thereby improving the real-time performance of processing and increasing response speed. At the same time, it is not limited by network conditions, which is especially important for scenarios with unstable network environments or no network connection, such as when the vehicle is driving in a remote mountainous area without network access.

[0038] In some embodiments, the autonomous driving path planning method provided in this application can be implemented collaboratively by an in-vehicle device and a server. For example, the in-vehicle device 400 sends obstacle information in the lane where the vehicle is located and in adjacent lanes to the server 200; the server 200 establishes a solution space for obstacle avoidance paths based on the obstacle information in the lane where the vehicle is located and in adjacent lanes; the server 200 performs sampling processing in the solution space to obtain multiple discrete waypoints, and plans multiple obstacle avoidance paths based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts from the vehicle's position and ends at the farthest discrete waypoint, and the farthest discrete waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints; the server 200 calculates the driving cost corresponding to each of the multiple obstacle avoidance paths; the server 200 filters the multiple obstacle avoidance paths based on the driving cost corresponding to each of the multiple obstacle avoidance paths to obtain a target obstacle avoidance path; the server 200 sends the target obstacle avoidance path to the in-vehicle device 400 so that the in-vehicle device 400 controls the vehicle to drive according to the target obstacle avoidance path. In the above approach, server 200 typically possesses powerful computing capabilities and storage resources, enabling efficient path planning; vehicle-mounted equipment 400 is primarily responsible for data acquisition, data transmission, and control, without needing to undertake complex computing tasks, thus reducing the local pressure on vehicle-mounted equipment 400.

[0039] The following description uses an example of an in-vehicle device provided in an embodiment of this application. See also... Figure 2 , Figure 2This is a structural schematic diagram of the vehicle-mounted device 400 provided in an embodiment of this application. Figure 2 The illustrated vehicle-mounted device 400 includes at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in the vehicle-mounted device 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to implement communication between these components. In addition to a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 2 The general labeled all buses as Bus System 440.

[0040] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0041] User interface 430 includes one or more output devices 431 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a microphone, touch screen display, camera, other input buttons and controls.

[0042] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices physically located away from the processor 410.

[0043] The memory 450 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 450 described in this application embodiment is intended to include any suitable type of memory.

[0044] In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0045] Operating system 451 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks;

[0046] The network communication module 452 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0047] Presentation module 453 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 (e.g., a display screen, a speaker, etc.) associated with user interface 430;

[0048] The input processing module 454 is used to detect and translate one or more user inputs or interactions from one or more input devices 432.

[0049] In some embodiments, the autonomous driving path planning device provided in this application can be implemented in software. Figure 2 An autonomous driving path planning device 455 stored in memory 450 is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a creation module 4551, a planning module 4552, a calculation module 4553, a filtering module 4554, and a control module 4555. These modules are logically connected and can therefore be arbitrarily combined or further separated according to the functions they implement. The functions of each module will be described below.

[0050] The path planning method for autonomous driving provided in this application will be described by referring to exemplary applications and implementations of the electronic devices provided in the embodiments of this application.

[0051] See Figure 3A , Figure 3A This is a flowchart illustrating an autonomous driving path planning method provided in an embodiment of this application, which will be combined with... Figure 3A The steps shown are explained.

[0052] In step 101, the solution space for the obstacle avoidance path is established based on the obstacle information in the lane where the vehicle is located and the adjacent lanes.

[0053] Here, information on obstacles in the lane where the vehicle is located and in adjacent lanes is obtained, and a solution space for obstacle avoidance paths is established based on this information. The solution space can be understood as the space in the lane where the vehicle is located and in adjacent lanes where there are no obstacles.

[0054] It is worth noting that the embodiments of this application do not limit the method of obtaining obstacle information. It can be obtained through the vehicle's onboard sensors, which include at least one of onboard cameras and onboard radar. For example, data can be collected separately by onboard cameras and onboard radar, and then the collected data can be fused to obtain obstacle information in the vehicle's lane and adjacent lanes. This improves the accuracy of the obtained obstacle information through sensor fusion.

[0055] It is worth noting that the embodiments of this application do not limit the number of adjacent lanes. For example, adjacent lanes may include at least one of the i lanes to the left and j lanes to the right of the lane where the vehicle is located, where i and j are both integers greater than 0. For example, if the lanes in a road are lane 1, lane 2, ... lane 5 from left to right, and the lane where the vehicle is located is lane 3, then adjacent lanes may include lane 2 and lane 4, or lane 1, lane 2, lane 4 and lane 5.

[0056] It is worth noting that obstacle information includes at least the obstacle's position and speed, and may also include the obstacle's length and width.

[0057] In some embodiments, before establishing the solution space for the obstacle avoidance path based on obstacle information in the lane where the vehicle is located and in adjacent lanes, the path planning method for autonomous driving further includes: determining a first longitudinal distance based on the speed of the vehicle and a first preset time; and obtaining obstacle information of obstacles in the lane where the vehicle is located and in adjacent lanes that have a longitudinal distance from the vehicle that is less than the first longitudinal distance.

[0058] For example, the vehicle's speed can be multiplied by a first preset time interval to obtain a first longitudinal distance. Obstacle information can then be obtained for obstacles in the vehicle's lane and adjacent lanes that are within the first longitudinal distance of the vehicle. This information is used to establish a solution space for an obstacle avoidance path. This solution space can be understood as the space within the vehicle's lane and adjacent lanes that is within the first longitudinal distance (starting from the vehicle's position) and free of obstacles. The first preset time interval can be set according to the actual application scenario, such as 6-8 seconds.

[0059] The above method only acquires obstacle information for obstacles whose longitudinal distance from the vehicle is less than a first longitudinal distance. This ensures the necessity and accuracy of the acquired obstacle information, helps reduce subsequent computational costs, and improves path planning efficiency. Furthermore, by establishing a solution space within the first longitudinal distance from the vehicle's position, it avoids increasing the complexity and uncertainty of path planning due to an excessively large solution space, thus contributing to improved path planning stability.

[0060] It is worth noting that, in the embodiments of this application, "longitudinal" refers to the direction along the lane, and "lateral" refers to the direction perpendicular to the lane.

[0061] In step 102, sampling is performed in the solution space to obtain multiple discrete waypoints, and multiple obstacle avoidance paths are planned based on the multiple discrete waypoints. Each obstacle avoidance path starts from the position of the vehicle and ends at the farthest waypoint. The farthest waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints.

[0062] Here, multiple discrete waypoints are obtained through sampling within the solution space. This sampling can be random or based on a specific pattern; the latter improves the orderliness of path planning and reduces computational cost. Then, multiple obstacle avoidance paths are planned based on these discrete waypoints. Each path starts at the vehicle's position and ends at the farthest waypoint. The farthest waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle; there may be one or more farthest waypoints.

[0063] In some embodiments, multiple obstacle avoidance paths can be planned exhaustively to avoid missing any possible obstacle avoidance paths.

[0064] In some embodiments, the above-mentioned sampling process in the solution space to obtain multiple discrete waypoints can be achieved in the following manner: sampling is performed in the longitudinal direction of the solution space according to the longitudinal sampling distance, and in the transverse direction of the solution space according to the transverse sampling distance, to obtain multiple discrete waypoints.

[0065] Here, regular sampling can be performed within the solution space to obtain multiple discrete waypoints. For example, sampling can be performed along the longitudinal direction and along the lateral direction of the solution space according to the sampling longitudinal distance, resulting in multiple discrete waypoints. Both the sampling longitudinal and lateral distances can be preset, for example, the sampling longitudinal distance can be set to 5 meters and the sampling lateral distance to 0.2 meters. This method, through regular sampling, can improve the orderliness of path planning.

[0066] For example, multiple discrete waypoints obtained through sampling are arranged in an M-row, N-column configuration, where rows refer to the horizontal direction and columns refer to the vertical direction, and M and N are both integers greater than 1. During the planning process, starting from the vehicle's position, a discrete waypoint is selected in each of the M rows and connected sequentially to obtain the planned obstacle avoidance path. This ensures the effectiveness of the planned obstacle avoidance path, i.e., it conforms to actual driving conditions.

[0067] In some embodiments, before sampling processing is performed in the longitudinal direction of the solution space according to the sampling longitudinal distance and in the lateral direction of the solution space according to the sampling lateral distance, the autonomous driving path planning method further includes: determining a second longitudinal distance based on the speed of the vehicle and a second preset time; and determining the maximum value of the second longitudinal distance and the preset longitudinal distance as the sampling longitudinal distance used for sampling processing in the longitudinal direction.

[0068] Here, the second longitudinal distance is determined based on the vehicle's speed and a second preset duration. The second preset duration can be set according to the actual application scenario, such as 0.5 seconds. Then, the maximum value between the second longitudinal distance and the preset longitudinal distance (e.g., 5 meters) is determined as the sampling longitudinal distance used for sampling processing in the longitudinal direction. This method improves the rationality of the sampling longitudinal distance, avoiding an excessive number of discrete waypoints due to an excessively small sampling longitudinal distance, while ensuring that the vehicle's speed supports travel along the planned obstacle avoidance path.

[0069] In step 103, the driving cost corresponding to each of the multiple obstacle avoidance paths is calculated.

[0070] Here, for each planned obstacle avoidance path, the corresponding driving cost is calculated. The driving cost directly reflects the effectiveness of the obstacle avoidance path. This application embodiment does not limit the calculation method of the driving cost, and factors such as safety and riding experience can be considered. For example, the driving cost corresponding to each obstacle avoidance path can be obstacle cost, smoothness cost, or lane cost.

[0071] In step 104, the multiple obstacle avoidance paths are filtered according to the driving costs corresponding to each path to obtain the target obstacle avoidance path.

[0072] The lower the travel cost, the better the obstacle avoidance path. Therefore, the obstacle avoidance path with the lowest travel cost among multiple obstacle avoidance paths can be identified as the target obstacle avoidance path, thus achieving the selection of multiple obstacle avoidance paths.

[0073] In some embodiments, after calculating the driving costs corresponding to the multiple obstacle avoidance paths, the autonomous driving path planning method further includes: when a target obstacle avoidance path cannot be selected based on the driving costs corresponding to the multiple obstacle avoidance paths, discarding the furthest discrete waypoint and returning to the step of planning multiple obstacle avoidance paths based on the multiple discrete waypoints.

[0074] Here, a situation may arise where the target obstacle avoidance path cannot be selected based on the travel costs corresponding to multiple obstacle avoidance paths. For example, the travel costs of multiple obstacle avoidance paths may all be the same, or the travel costs of multiple obstacle avoidance paths may all be infinite. In this case, all currently furthest waypoints are discarded, and the process returns to the step of planning multiple obstacle avoidance paths based on multiple discrete waypoints. For example, if the multiple discrete waypoints obtained through sampling are arranged in an M-row N-column format, the discrete waypoint in the M-th row (the furthest waypoint) is discarded, and multiple obstacle avoidance paths are re-planned based on the remaining M-1-row N-column discrete waypoints. In this way, the discrete waypoint in the M-1-row is used as the new furthest waypoint, ensuring that the target obstacle avoidance path can ultimately be selected, greatly enhancing the robustness of path planning.

[0075] In step 105, the vehicle is controlled to travel along the target obstacle avoidance path.

[0076] Since the target obstacle avoidance path is the most effective among multiple obstacle avoidance paths, the vehicle is controlled to drive according to the target obstacle avoidance path.

[0077] In some embodiments, steps 101 to 105 can be performed periodically, that is, path planning is continuously performed during the vehicle's driving process to ensure that the latest target obstacle avoidance path can meet the latest situation and fully adapt to the ever-changing external environment.

[0078] like Figure 3A As shown, this embodiment establishes a solution space for obstacle avoidance paths based on obstacle information in the vehicle's lane and adjacent lanes. Multiple discrete road points are obtained through sampling within the solution space, and multiple obstacle avoidance paths are planned based on these road points. Each obstacle avoidance path starts at the vehicle's position and ends at the road point furthest from the vehicle, where the road point has the largest longitudinal distance from the vehicle. The driving cost corresponding to each of the multiple obstacle avoidance paths is calculated. The multiple obstacle avoidance paths are then filtered based on their respective driving costs to obtain a target obstacle avoidance path. The vehicle is then controlled to drive according to the target obstacle avoidance path. This embodiment comprehensively considers multiple lanes rather than being limited to the current lane, facilitating decisions on whether to avoid obstacles in the current lane or change lanes, ultimately obtaining the target obstacle avoidance path with the lowest driving cost, thus maximizing driving efficiency while ensuring driving safety.

[0079] In some embodiments, see Figure 3B , Figure 3B This is a flowchart illustrating an autonomous driving path planning method provided in an embodiment of this application. Figure 3A Step 103 shown can be implemented through steps 201 to 204, which will be explained in conjunction with each step.

[0080] In step 201, the obstacle cost of any obstacle avoidance path is calculated based on the lateral distance between multiple discrete waypoints and obstacles in any obstacle avoidance path.

[0081] For ease of explanation, we will take any one of the obstacle avoidance paths, pathA, as an example to illustrate the process of calculating the travel cost.

[0082] On the one hand, based on the lateral distances between multiple discrete waypoints in the obstacle avoidance path A and the obstacles, the obstacle cost of the obstacle avoidance path A is calculated. The smaller the lateral distance between multiple discrete waypoints in the obstacle avoidance path A and the obstacles, the greater the probability of colliding with the obstacles, and therefore the greater the obstacle cost of the obstacle avoidance path A.

[0083] It is worth noting that the premise for calculating the lateral distance between discrete waypoints and obstacles is that the obstacle and the discrete waypoint are located in the same cross section (i.e., in the same row).

[0084] In some embodiments, the above-mentioned calculation of the obstacle cost of any obstacle avoidance path based on the lateral distance between multiple discrete waypoints and obstacles in any obstacle avoidance path can be achieved in the following manner: calculate the obstacle cost of any discrete waypoint based on the lateral distance between any discrete waypoint and obstacle in any obstacle avoidance path; perform a second fusion process on the obstacle costs corresponding to the multiple discrete waypoints in any obstacle avoidance path to obtain the obstacle cost of any obstacle avoidance path.

[0085] Here, the obstacle cost of each discrete waypoint in the obstacle avoidance path pathA is calculated based on the lateral distance between that waypoint and the obstacle. Then, a second fusion process is performed on the obstacle costs corresponding to multiple discrete waypoints in pathA to obtain the obstacle cost of pathA. The fusion processes involved in this application embodiment (such as the first fusion process, the second fusion process, and the third fusion process) can employ methods such as summation, weighted summation, taking the maximum value, taking the average value, and integration. In the above methods, each discrete waypoint in the obstacle avoidance path is considered individually first, and then the obstacle cost of the obstacle avoidance path is obtained by combining all discrete waypoints in the obstacle avoidance path, providing a feasible method for calculating the obstacle cost of the obstacle avoidance path.

[0086] In some embodiments, the above-mentioned calculation of the obstacle cost of any discrete waypoint based on the lateral distance between any discrete waypoint and an obstacle in any obstacle avoidance path can be achieved in the following manner: when the lateral distance between any discrete waypoint and an obstacle is less than the minimum safe distance, the obstacle cost of any discrete waypoint is determined to be infinite; when the lateral distance between any discrete waypoint and an obstacle is greater than the maximum safe distance, the obstacle cost of any discrete waypoint is determined to be zero; when the lateral distance between any discrete waypoint and an obstacle is greater than or equal to the minimum safe distance and less than or equal to the maximum safe distance, the difference between the lateral distance between any discrete waypoint and the obstacle and the maximum safe distance is calculated, and the obstacle cost of any discrete waypoint is calculated based on the difference.

[0087] For ease of explanation, let's take any discrete waypoint point A in the obstacle avoidance path A as an example to illustrate the process of calculating obstacle cost:

[0088] 1) When the lateral distance between a discrete waypoint A and an obstacle is less than the minimum safe distance, a collision risk is considered to exist. Therefore, the obstacle cost for determining discrete waypoint A is infinite. This can be described by the following formula:

[0089] d_obs–vehicle_width / 2 <d_safe

[0090] Where d_obs represents the lateral distance between the center point of the vehicle and the obstacle when the vehicle is at the discrete waypoint pointA; vehicle_width represents the width of the vehicle; d_obs–vehicle_width / 2 represents the lateral distance between the discrete waypoint pointA and the obstacle, that is, the redundant vehicle_width / 2 is removed from d_obs; d_safe represents the minimum safe distance, which can be preset.

[0091] 2) When the lateral distance between discrete waypoint A and an obstacle is greater than the maximum safe distance, there is no risk of collision, and therefore the obstacle cost for discrete waypoint A is determined to be zero. This can be described by the following formula:

[0092] d_obs–vehicle_width / 2>d_free

[0093] Here, d_free represents the maximum safe distance, which can be preset.

[0094] It is worth noting that the maximum safe distance is greater than the minimum safe distance.

[0095] 3) When the lateral distance between discrete waypoint A and an obstacle is greater than or equal to the minimum safe distance and less than or equal to the maximum safe distance, calculate the difference between the lateral distance between discrete waypoint A and the obstacle and the maximum safe distance, and calculate the obstacle cost of discrete waypoint A based on this difference. The obstacle cost of discrete waypoint A is positively correlated with the aforementioned difference. For example, this can be described by the following formula:

[0096] cost_obs=w_obs(d_free–d_obs)^2

[0097] Where cost_obs represents the obstacle cost of discrete waypoint pointA; w_obs represents the preset weights.

[0098] In some embodiments, the path planning method for autonomous driving further includes: determining a minimum safe distance range based on the obstacle type of the obstacle corresponding to any discrete waypoint; wherein the minimum value in the minimum safe distance range corresponds to the minimum obstacle avoidance speed of the vehicle, and the maximum value in the minimum safe distance range corresponds to the maximum obstacle avoidance speed of the vehicle; and performing interpolation processing based on the vehicle's speed, the vehicle's minimum obstacle avoidance speed, the vehicle's maximum obstacle avoidance speed, and the minimum safe distance range to obtain the minimum safe distance.

[0099] The minimum safe distance can be preset or calculated in other ways. Here, we will give an example of the latter method.

[0100] First, the minimum safe distance range is determined based on the obstacle type corresponding to the discrete waypoint pointA. The obstacle corresponding to pointA refers to an obstacle located on the same cross-section as pointA. For different obstacle types, the minimum safe distance range dist_min to dist_max can be pre-calibrated based on the vehicle's maximum obstacle avoidance speed v_max and minimum obstacle avoidance speed v_min. The maximum obstacle avoidance speed refers to the maximum speed during obstacle avoidance function activation, and the minimum obstacle avoidance speed refers to the minimum speed during obstacle avoidance function activation. Both the maximum and minimum obstacle avoidance speeds can be pre-set. The minimum value dist_min in the minimum safe distance range corresponds to v_min, and the maximum value dist_max in the minimum safe distance range corresponds to v_max. For example, obstacle types include static obstacles (such as water-filled barriers, cones, and cylinders) and dynamic obstacles (such as vehicles, two-wheeled vehicles, and people). The minimum safe distance range for static obstacles is defined as static_dist_min to static_dist_max, and the minimum safe distance range for dynamic obstacles is defined as dynamic_dist_min to dynamic_dist_max.

[0101] After determining the minimum safe distance range from dist_min to dist_max (e.g., static_dist_min to static_dist_max or dynamic_dist_min to dynamic_dist_max, depending on the obstacle type), interpolation is performed based on the vehicle's speed, minimum obstacle avoidance speed, maximum obstacle avoidance speed, and the minimum safe distance range. This interpolation determines the value corresponding to the vehicle's speed within the minimum safe distance range, which is then used as the minimum safe distance. For example, this can be described by the following formula:

[0102] d_safe=(v–v_min)*(dist_max–dist_min) / (v_max–v_min)+dist_min

[0103] Where v represents the vehicle's speed (current speed).

[0104] In the above method, determining the appropriate minimum safe distance based on the type of obstacle not only ensures driving safety and enhances the sense of security for drivers and passengers, but also ensures that reasonable obstacle avoidance paths are not missed.

[0105] In step 202, the smoothness cost of any obstacle avoidance path is calculated based on the lateral distance between multiple discrete waypoints in any obstacle avoidance path.

[0106] On the other hand, the smoothness cost of obstacle avoidance path A is calculated based on the lateral distance between multiple discrete waypoints in the obstacle avoidance path A. If the lateral distance between multiple discrete waypoints in the obstacle avoidance path A is smaller, it proves that the obstacle avoidance path A is smoother and the driving experience is more comfortable. Therefore, the smoothness cost of obstacle avoidance path A is smaller.

[0107] In some embodiments, the above-mentioned calculation of the smoothness cost of any obstacle avoidance path based on the lateral distance between multiple discrete waypoints in any obstacle avoidance path can be achieved in the following manner: Any obstacle avoidance path is divided into multiple sub-paths; each sub-path consists of two adjacent discrete waypoints in any obstacle avoidance path; the smoothness cost of each sub-path is calculated based on the lateral distance between the two discrete waypoints in each sub-path; when the smoothness cost of any sub-path is greater than a smoothness cost threshold, the smoothness cost of any obstacle avoidance path is determined to be infinite; when the smoothness costs corresponding to each of the multiple sub-paths are all less than or equal to the smoothness cost threshold, a third fusion process is performed on the smoothness costs corresponding to each of the multiple sub-paths to obtain the smoothness cost of any obstacle avoidance path.

[0108] Here, the obstacle avoidance path A is first divided into multiple sub-paths, where each sub-path consists of two adjacent discrete waypoints in the obstacle avoidance path A. For example, if the discrete waypoints in the obstacle avoidance path A are point A, point B, point C, and point D, then the obstacle avoidance path A can be divided into three sub-paths: sub-path A1 includes point A and point B, sub-path A2 includes point B and point C, and sub-path A3 includes point C and point D.

[0109] Then, the smoothness cost of each sub-path is calculated based on the lateral distance between two discrete waypoints in that sub-path. The smoothness cost of a sub-path is positively correlated with the lateral distance between the two discrete waypoints in that sub-path. For example, the smoothness cost of a sub-path can be obtained by dividing the lateral distance between the two discrete waypoints by the longitudinal distance between them.

[0110] When the smoothness cost of any sub-path is greater than the smoothness cost threshold, it proves that the obstacle avoidance path pathA as a whole is not smooth, and therefore the smoothness cost of the obstacle avoidance path pathA is determined to be infinite; when the smoothness costs corresponding to multiple sub-paths are all less than or equal to the smoothness cost threshold, the smoothness costs corresponding to multiple sub-paths are subjected to a third fusion process to obtain the smoothness cost of the obstacle avoidance path pathA.

[0111] For example, it can be described using a formula:

[0112] cost_smooth A1=(pointB_x–pointA_x) / delta_s

[0113] cost_smooth A2=(pointC_x–pointB_x) / delta_s

[0114] cost_smooth A3=(pointD_x–pointC_x) / delta_s

[0115] Where cost_smooth A1 represents the smoothness cost of sub-path pathA1, pointA_x represents the lateral position of pointA, and so on; delta_s represents the longitudinal distance between two adjacent discrete waypoints in the obstacle avoidance path pathA (here it is assumed that the longitudinal distance between two discrete waypoints in each sub-path is the same), which corresponds to the sampling longitudinal distance mentioned above.

[0116] When any one of cost_smooth A1, cost_smooth A2, and cost_smooth A3 is greater than the smoothness cost threshold, the smoothness cost of obstacle avoidance path pathA is determined to be infinite. When cost_smooth A1, cost_smooth A2, and cost_smooth A3 are all less than or equal to the smoothness cost threshold, a third fusion process is performed on cost_smooth A1, cost_smooth A2, and cost_smooth A3 to obtain the smoothness cost of obstacle avoidance path pathA, i.e., cost_smooth = w1*cost_smooth A1^2 + w2*cost_smooth A2^2 + w3*cost_smooth A3^2, where cost_smooth represents the smoothness cost of obstacle avoidance path pathA, and w1, w2, and w3 all represent pre-set weights.

[0117] In step 203, the lane cost of any obstacle avoidance path is calculated based on the lateral distances between the furthest point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lanes.

[0118] On the other hand, the lane cost of obstacle avoidance path A is calculated based on the lateral distances between the farthest point in obstacle avoidance path A and the lane where the vehicle is located and the adjacent lane. The greater the lateral distance between the farthest point in obstacle avoidance path A and the lane where the vehicle is located and the adjacent lane, the more difficult it is for the vehicle to return to the lane, and therefore the greater the lane cost of obstacle avoidance path A.

[0119] In some embodiments, the lateral distance between the furthest exit point and the lane can refer to the lateral distance between the furthest exit point and the centerline (longitudinal centerline) of the lane. Based on this, the lane cost refers to the cost incurred by a vehicle to return to the centerline of the lane.

[0120] In some embodiments, the above-mentioned calculation of lane cost for any obstacle avoidance path based on the lateral distances between the farthest point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lane can be achieved in the following manner: based on the lateral distances between the farthest point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lane, the nearest lane is selected from the lane where the vehicle is located and the adjacent lane; based on the lateral distance between the farthest point in any obstacle avoidance path and the nearest lane, the lane cost for any obstacle avoidance path is calculated.

[0121] For example, after determining the lateral distances between the farthest point in the obstacle avoidance path A and the vehicle's lane and adjacent lanes, the lane with the smallest lateral distance is identified as the nearest lane. Then, based on the lateral distances between the farthest point in the obstacle avoidance path A and the nearest lane, the lane cost of the obstacle avoidance path A is calculated, for example:

[0122] cost_ref=w_ref*(l_cur-l_ref)^2

[0123] Where cost_ref represents the lane cost of obstacle avoidance path A; w_ref represents the pre-set weight; l_cur represents the lateral position of the furthest point in obstacle avoidance path A; and l_ref represents the lateral position of the centerline of the nearest lane.

[0124] The above method, when multiple lanes exist, selects the nearest lane to calculate the lane cost of the obstacle avoidance path. This conforms to the actual vehicle driving pattern, that is, vehicles usually return to the center line of the nearest lane to continue driving, thus ensuring the accuracy of the obtained lane cost.

[0125] In step 204, the obstacle cost, smoothness cost, and lane centerline cost of any obstacle avoidance path are subjected to a first fusion process to obtain the driving cost of any obstacle avoidance path.

[0126] Finally, the obstacle cost, smoothness cost, and lane centerline cost of obstacle avoidance path A are fused together to obtain the driving cost of obstacle avoidance path A, for example:

[0127] Cost=cost_obs+cost_smooth+cost_ref

[0128] Where Cost represents the driving cost of obstacle avoidance path A; cost_obs in the formula represents the obstacle cost of obstacle avoidance path A.

[0129] like Figure 3BAs shown, in this embodiment, the obstacle cost of any obstacle avoidance path is calculated based on the lateral distances between multiple discrete waypoints and obstacles in the path; the smoothness cost of any obstacle avoidance path is calculated based on the lateral distances between multiple discrete waypoints in the path; and the lane cost of any obstacle avoidance path is calculated based on the lateral distances between the furthest waypoint in the path and the lane where the vehicle is located and the adjacent lane, respectively. The obstacle cost, smoothness cost, and lane centerline cost of any obstacle avoidance path are then fused to obtain the driving cost of that path. By comprehensively considering these three costs to obtain the final driving cost, the comprehensiveness and accuracy of the driving cost can be improved, facilitating the subsequent selection of the target obstacle avoidance path with the best overall performance based on the driving cost.

[0130] In some embodiments, see Figure 3C , Figure 3C This is a flowchart illustrating an autonomous driving path planning method provided in an embodiment of this application. Figure 3A Step 101 shown can be implemented through steps 301 to 302, which will be explained in conjunction with each step.

[0131] In step 301, the obstacle trajectory is predicted based on the obstacle information in the lane where the vehicle is located and in the adjacent lanes.

[0132] Here, considering that obstacles may be in dynamic motion in traffic scenarios, the obstacle trajectory is predicted based on the obstacle information in the vehicle's lane and adjacent lanes.

[0133] In some embodiments, obstacle information includes obstacle position and obstacle speed. The above-mentioned prediction of obstacle trajectory based on obstacle information in the vehicle's lane and adjacent lanes can be achieved in the following manner: when the obstacle speed of any obstacle in the vehicle's lane and adjacent lanes is less than a preset speed, a uniform deceleration motion model is used to predict the obstacle trajectory of any obstacle based on its position and speed; when the obstacle speed of any obstacle is greater than or equal to the preset speed, a uniform motion model is used to predict the obstacle trajectory of any obstacle based on its position and speed.

[0134] Here, we take any obstacle A in the lane where the vehicle is located and in the adjacent lane as an example. When the speed of obstacle A is less than the preset speed, it indicates that it is likely decelerating. Therefore, a uniform deceleration motion model (i.e., decelerating at a constant speed until the speed is zero) is used to predict the obstacle trajectory based on the obstacle's position and speed. When the speed of obstacle A is greater than or equal to the preset speed, a uniform speed motion model is used to predict the obstacle trajectory based on its position and speed. In the above method, using an appropriate motion model based on the obstacle's speed can improve the accuracy of the predicted obstacle trajectory.

[0135] In some embodiments, the above-mentioned prediction of obstacle trajectories based on obstacle information in the vehicle's lane and adjacent lanes can be achieved by predicting obstacle trajectories within a third preset time period based on obstacle information in the vehicle's lane and adjacent lanes. The third preset time period can be set according to the actual application scenario, such as 6-8 seconds. On the one hand, considering the limited size of the solution space to be established, predicting only obstacle trajectories within the third preset time period can save computational costs; on the other hand, the predicted obstacle trajectories within the third preset time period can guarantee accuracy, while predicting obstacle trajectories from a longer time period is difficult to guarantee accuracy.

[0136] In step 302, the space in the lane where the vehicle is located and in the adjacent lanes that is outside the obstacle trajectory is determined as the solution space for the obstacle avoidance path.

[0137] Here, the space in the lane where the vehicle is located and in the adjacent lanes that is outside the obstacle trajectory (i.e., without obstacle trajectory) is defined as the solution space for the obstacle avoidance path, thereby ensuring that the planned obstacle avoidance path will not collide with the obstacle in the future.

[0138] like Figure 3C As shown, in this embodiment, the obstacle trajectory is predicted based on obstacle information in the vehicle's lane and adjacent lanes; the space in the vehicle's lane and adjacent lanes that is outside the obstacle trajectory is determined as the solution space for the obstacle avoidance path. Thus, considering the dynamic nature of obstacles, the obstacle trajectory is excluded when establishing the solution space, thereby ensuring that the obstacle avoidance path planned based on the solution space will not collide with obstacles in the future.

[0139] The following continues to describe the exemplary structure of the autonomous driving path planning device 455 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2 As shown, the software modules in the autonomous driving path planning device 455 stored in the memory 450 may include: a building module 4551, used to build a solution space for obstacle avoidance paths based on obstacle information in the lane where the vehicle is located and adjacent lanes; a planning module 4552, used to perform sampling processing in the solution space to obtain multiple discrete waypoints, and plan multiple obstacle avoidance paths based on the multiple discrete waypoints; wherein each obstacle avoidance path starts from the position of the vehicle and ends at the farthest discrete waypoint, and the farthest discrete waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints; a calculation module 4553, used to calculate the driving cost corresponding to each of the multiple obstacle avoidance paths; a filtering module 4554, used to filter the multiple obstacle avoidance paths based on the driving cost corresponding to each of the multiple obstacle avoidance paths to obtain the target obstacle avoidance path; and a control module 4555, used to control the vehicle to drive according to the target obstacle avoidance path.

[0140] In some embodiments, the calculation module 4553 is further configured to: for any one of the multiple obstacle avoidance paths, perform the following processing: calculate the obstacle cost of any obstacle avoidance path based on the lateral distance between multiple discrete waypoints in any obstacle avoidance path and the obstacle; calculate the smoothness cost of any obstacle avoidance path based on the lateral distance between multiple discrete waypoints in any obstacle avoidance path; calculate the lane cost of any obstacle avoidance path based on the lateral distance between the furthest discrete waypoint in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lane, respectively; and perform a first fusion processing on the obstacle cost, smoothness cost and lane centerline cost of any obstacle avoidance path to obtain the driving cost of any obstacle avoidance path.

[0141] In some embodiments, the calculation module 4553 is further configured to: calculate the obstacle cost of any discrete waypoint based on the lateral distance between any discrete waypoint and an obstacle in any obstacle avoidance path; and perform a second fusion process on the obstacle costs corresponding to multiple discrete waypoints in any obstacle avoidance path to obtain the obstacle cost of any obstacle avoidance path.

[0142] In some embodiments, the calculation module 4553 is further configured to: determine that the obstacle cost of any discrete waypoint is infinite when the lateral distance between any discrete waypoint and an obstacle is less than the minimum safe distance; determine that the obstacle cost of any discrete waypoint is zero when the lateral distance between any discrete waypoint and an obstacle is greater than the maximum safe distance; and calculate the difference between the lateral distance between any discrete waypoint and an obstacle and the maximum safe distance when the lateral distance between any discrete waypoint and an obstacle is greater than or equal to the minimum safe distance and less than or equal to the maximum safe distance, and calculate the obstacle cost of any discrete waypoint based on the difference.

[0143] In some embodiments, the calculation module 4553 is further configured to: determine the minimum safe distance range based on the obstacle type of the obstacle corresponding to any discrete waypoint; wherein the minimum value in the minimum safe distance range corresponds to the minimum obstacle avoidance speed of the vehicle, and the maximum value in the minimum safe distance range corresponds to the maximum obstacle avoidance speed of the vehicle; and perform interpolation processing based on the vehicle's speed, the vehicle's minimum obstacle avoidance speed, the vehicle's maximum obstacle avoidance speed, and the minimum safe distance range to obtain the minimum safe distance.

[0144] In some embodiments, the calculation module 4553 is further configured to: divide any obstacle avoidance path into multiple sub-paths; wherein each sub-path consists of two adjacent discrete waypoints in any obstacle avoidance path; calculate the smoothness cost of the sub-path based on the lateral distance between the two discrete waypoints in each sub-path; determine that the smoothness cost of any obstacle avoidance path is infinite when the smoothness cost of any sub-path is greater than the smoothness cost threshold; and perform a third fusion process on the smoothness costs of the multiple sub-paths respectively when the smoothness costs of the multiple sub-paths are all less than or equal to the smoothness cost threshold to obtain the smoothness cost of any obstacle avoidance path.

[0145] In some embodiments, the calculation module 4553 is further configured to: select the nearest lane in the lane where the vehicle is located and the adjacent lane based on the lateral distance between the farthest scatter point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lane, respectively; and calculate the lane cost of any obstacle avoidance path based on the lateral distance between the farthest scatter point in any obstacle avoidance path and the nearest lane.

[0146] In some embodiments, the establishment module 4551 is further configured to: predict the obstacle trajectory based on the obstacle information in the lane where the vehicle is located and the adjacent lanes; and determine the space in the lane where the vehicle is located and the adjacent lanes that is outside the obstacle trajectory as the solution space for the obstacle avoidance path.

[0147] In some embodiments, obstacle information includes obstacle position and obstacle speed; the establishment module 4551 is further configured to: when the obstacle speed of any obstacle in the lane where the vehicle is located and in the adjacent lane is less than a preset speed, use a uniform deceleration motion model to predict the obstacle trajectory of any obstacle based on the obstacle position and obstacle speed of any obstacle; when the obstacle speed of any obstacle is greater than or equal to the preset speed, use a uniform motion model to predict the obstacle trajectory of any obstacle based on the obstacle position and obstacle speed of any obstacle.

[0148] In some embodiments, the autonomous driving path planning device 455 further includes an acquisition module, configured to: determine a first longitudinal distance based on the vehicle's speed and a first preset time; and acquire obstacle information of obstacles in the lane where the vehicle is located and in adjacent lanes that have a longitudinal distance from the vehicle that is less than the first longitudinal distance.

[0149] In some embodiments, the planning module 4552 is further configured to: perform sampling processing in the longitudinal direction of the solution space according to the sampling longitudinal distance and in the transverse direction of the solution space according to the sampling transverse distance to obtain multiple discrete waypoints.

[0150] In some embodiments, the planning module 4552 is further configured to: determine a second longitudinal distance based on the vehicle's speed and a second preset duration; and determine the maximum value of the second longitudinal distance and the preset longitudinal distance as the sampling longitudinal distance for sampling processing in the longitudinal direction.

[0151] In some embodiments, the autonomous driving path planning device 455 further includes a discard module, configured to: discard the furthest discrete waypoint when a target obstacle avoidance path cannot be selected based on the driving costs corresponding to the multiple obstacle avoidance paths, and return to the step of planning multiple obstacle avoidance paths based on the multiple discrete waypoints.

[0152] This application provides a computer program product or computer program, which includes executable instructions stored in a computer-readable storage medium. The processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, causing the electronic device to implement the autonomous driving path planning method described above in this application.

[0153] This application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored and, when executed by a processor, will cause the processor to implement the autonomous driving path planning method provided in this application.

[0154] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0155] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0156] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0157] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A path planning method for autonomous driving, characterized in that, include: The solution space for obstacle avoidance paths is established based on the obstacle information in the lane where the vehicle is located and in adjacent lanes; Multiple discrete waypoints are obtained by sampling within the solution space, and multiple obstacle avoidance paths are planned based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts from the position of the vehicle and ends at the waypoint furthest from the vehicle, and the waypoint furthest from the vehicle represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints. Calculating the driving cost corresponding to each of the multiple obstacle avoidance paths includes: for any one of the multiple obstacle avoidance paths, performing the following processing: calculating the obstacle cost of the obstacle avoidance path based on the lateral distances between multiple discrete waypoints in the obstacle avoidance path and obstacles; calculating the smoothness cost of the obstacle avoidance path based on the lateral distances between multiple discrete waypoints in the obstacle avoidance path; calculating the lane cost of the obstacle avoidance path based on the lateral distances between the furthest discrete waypoint in the obstacle avoidance path and the lane where the vehicle is located and the adjacent lanes; and performing a first fusion processing on the obstacle cost, smoothness cost, and lane centerline cost of the obstacle avoidance path to obtain the driving cost of the obstacle avoidance path, where longitudinal refers to the direction along the lane and lateral refers to the direction perpendicular to the lane. The multiple obstacle avoidance paths are filtered based on their respective travel costs to obtain the target obstacle avoidance path. The vehicle is controlled to travel along the target obstacle avoidance path.

2. The method according to claim 1, characterized in that, The step of calculating the obstacle cost of any obstacle avoidance path based on the lateral distances between multiple discrete waypoints and obstacles in any obstacle avoidance path includes: Calculate the obstacle cost of any discrete waypoint in any obstacle avoidance path based on the lateral distance between the waypoint and the obstacle. A second fusion process is performed on the obstacle costs corresponding to multiple discrete waypoints in any obstacle avoidance path to obtain the obstacle cost of any obstacle avoidance path.

3. The method according to claim 2, characterized in that, The step of calculating the obstacle cost of any discrete waypoint based on the lateral distance between any discrete waypoint in any obstacle avoidance path and the obstacle includes: When the lateral distance between any discrete waypoint and an obstacle is less than the minimum safe distance, the cost of determining the obstacle at any discrete waypoint is infinite. When the lateral distance between any discrete waypoint and an obstacle is greater than the maximum safe distance, the obstacle cost of any discrete waypoint is determined to be zero. When the lateral distance between any discrete waypoint and an obstacle is greater than or equal to the minimum safe distance and less than or equal to the maximum safe distance, the difference between the lateral distance between any discrete waypoint and the obstacle and the maximum safe distance is calculated, and the obstacle cost of any discrete waypoint is calculated based on the difference.

4. The method according to claim 3, characterized in that, The method further includes: The minimum safe distance range is determined based on the obstacle type of the obstacle corresponding to any discrete waypoint; wherein, the minimum value in the minimum safe distance range corresponds to the minimum obstacle avoidance speed of the vehicle, and the maximum value in the minimum safe distance range corresponds to the maximum obstacle avoidance speed of the vehicle. The minimum safe distance is obtained by interpolating the vehicle's speed, minimum obstacle avoidance speed, maximum obstacle avoidance speed, and minimum safe distance range.

5. The method according to claim 1, characterized in that, The step of calculating the smoothness cost of any obstacle avoidance path based on the lateral distance between multiple discrete waypoints in any obstacle avoidance path includes: Each obstacle avoidance path is divided into multiple sub-paths; each sub-path is composed of two adjacent discrete waypoints in the obstacle avoidance path. Calculate the smoothness cost of each sub-path based on the lateral distance between two discrete waypoints in each sub-path; When the smoothness cost of any sub-path is greater than the smoothness cost threshold, the smoothness cost of any obstacle avoidance path is determined to be infinite. When the smoothness cost corresponding to each of the multiple sub-paths is less than or equal to the smoothness cost threshold, a third fusion process is performed on the smoothness costs corresponding to each of the multiple sub-paths to obtain the smoothness cost of any obstacle avoidance path.

6. The method according to claim 1, characterized in that, The calculation of the lane cost of any obstacle avoidance path based on the lateral distances between the furthest exit point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lanes includes: Based on the lateral distances between the farthest point in any obstacle avoidance path and the lane where the vehicle is located and the adjacent lanes, the nearest lane is selected from the lane where the vehicle is located and the adjacent lanes. The lane cost of any obstacle avoidance path is calculated based on the lateral distance between the furthest scatter point and the nearest lane in any obstacle avoidance path.

7. The method according to claim 1, characterized in that, The solution space for establishing an obstacle avoidance path based on obstacle information in the vehicle's lane and adjacent lanes includes: The obstacle trajectory is predicted based on the obstacle information in the lane where the vehicle is located and in adjacent lanes; The space in the lane where the vehicle is located and in adjacent lanes that is outside the trajectory of the obstacle is defined as the solution space for the obstacle avoidance path.

8. The method according to claim 7, characterized in that, Obstacle information includes obstacle location and obstacle speed; the step of predicting the obstacle trajectory based on obstacle information in the vehicle's lane and adjacent lanes includes: When the speed of any obstacle in the lane where the vehicle is located or in an adjacent lane is less than a preset speed, a uniform deceleration motion model is used to predict the obstacle trajectory of any obstacle based on its position and speed. When the speed of any obstacle is greater than or equal to the preset speed, a uniform motion model is used to predict the obstacle trajectory of any obstacle based on its position and speed.

9. The method according to claim 1, characterized in that, Before establishing the solution space for the obstacle avoidance path based on the obstacle information in the vehicle's lane and adjacent lanes, the method further includes: The first longitudinal distance is determined based on the speed of the vehicle and the first preset time. Obstacle information is obtained for obstacles in the lane where the vehicle is located and in adjacent lanes, where the longitudinal distance between the vehicle and the obstacle is less than the first longitudinal distance.

10. The method according to claim 1, characterized in that, The sampling process within the solution space yields multiple discrete waypoints, including: Multiple discrete waypoints are obtained by sampling in the longitudinal direction of the solution space according to the sampling longitudinal distance and in the transverse direction of the solution space according to the sampling transverse distance.

11. The method according to claim 10, characterized in that, Before performing sampling processing in the longitudinal direction of the solution space according to the sampling longitudinal distance and in the transverse direction of the solution space according to the sampling transverse distance, the method further includes: The second longitudinal distance is determined based on the speed of the vehicle and the second preset duration. The maximum value of the second longitudinal distance and the preset longitudinal distance is determined as the sampling longitudinal distance used for sampling processing in the longitudinal direction.

12. The method according to claim 1, characterized in that, The method further includes: If a target obstacle avoidance path cannot be selected based on the driving costs corresponding to the multiple obstacle avoidance paths, discard the furthest discrete waypoint and return to the step of planning multiple obstacle avoidance paths based on the multiple discrete waypoints.

13. A path planning device for autonomous driving, characterized in that, include: A module is established to create a solution space for obstacle avoidance paths based on information about obstacles in the vehicle's lane and adjacent lanes. The planning module is used to perform sampling processing in the solution space to obtain multiple discrete waypoints, and to plan multiple obstacle avoidance paths based on the multiple discrete waypoints; wherein, each obstacle avoidance path starts from the position of the vehicle and ends at the farthest waypoint, and the farthest waypoint represents the discrete waypoint with the largest longitudinal distance from the vehicle among the multiple discrete waypoints. The calculation module is used to calculate the driving cost corresponding to each of the multiple obstacle avoidance paths. For any one of the multiple obstacle avoidance paths, the calculation of the driving cost corresponding to each of the multiple obstacle avoidance paths includes: for any one of the multiple obstacle avoidance paths, performing the following processing: calculating the obstacle cost of any one obstacle avoidance path based on the lateral distance between multiple discrete waypoints in the obstacle avoidance path and the obstacle; calculating the smoothness cost of any one obstacle avoidance path based on the lateral distance between the furthest discrete waypoint in the obstacle avoidance path and the lane where the vehicle is located and the adjacent lane, respectively; and performing a first fusion processing on the obstacle cost, smoothness cost, and lane centerline cost of any one obstacle avoidance path to obtain the driving cost of any one obstacle avoidance path, where longitudinal refers to the direction along the lane and lateral refers to the direction perpendicular to the lane. The filtering module is used to filter the multiple obstacle avoidance paths according to the driving cost corresponding to each of the multiple obstacle avoidance paths, so as to obtain the target obstacle avoidance path; The control module is used to control the vehicle to travel according to the target obstacle avoidance path.

14. An electronic device, characterized in that, include: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, It stores executable instructions for implementing the method of any one of claims 1 to 12 when executed by a processor.

Images