Driving planning method and apparatus, terminal device, and storage medium

Abstract

A driving planning method and apparatus, a terminal device, and a storage medium. The driving planning method comprises: in response to identifying that an ego vehicle has entered an intersection, acquiring intersection layout information corresponding to the intersection (S10); generating a vehicle guidance line on the basis of the intersection layout information, and acquiring static obstacle information and / or dynamic obstacle information corresponding to the current time node (S20); and generating a target planned path on the basis of the static obstacle information and / or the dynamic obstacle information combined with the vehicle guidance line (S30). The traffic efficiency of vehicles at intersections is improved, and the flexibility and safety of vehicle movement are ensured.

Description

Driving planning method, device, terminal equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on February 2, 2024, with application number 2024101581585 and application name “Driving Planning Method, Device, Terminal Equipment and Storage Medium”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving technology, and in particular to a driving planning method, apparatus, terminal device, and storage medium. Background Art

[0003] Intersections usually have various shapes and no clear lane lines. Compared with conventional roads with clear lane lines, the passage of vehicles at intersections is more random and free, which poses a great challenge to the motion planning of autonomous vehicles.

[0004] Related technical solutions typically construct intersection paths based on static geometric information, and then vehicles follow this fixed path. This can lead to problems such as low efficiency and poor trajectory flexibility. Furthermore, for real-time map construction systems based on perception information, vehicle paths can fluctuate due to perception uncertainties, making it difficult to ensure safe movement.

[0005] Summary of the Invention

[0006] In order to solve or partially solve the problems existing in the related art, the present application provides a driving planning method, apparatus, terminal device and storage medium, which can improve the flexibility and / or safety of vehicles when passing through intersections.

[0007] To achieve the above objectives, the present application provides a driving planning method, which includes:

[0008] In response to recognizing that the vehicle enters an intersection, obtaining intersection distribution information corresponding to the intersection;

[0009] generating a vehicle guide line based on the intersection distribution information, and obtaining static obstacle information and / or dynamic obstacle information corresponding to a current time node;

[0010] A target planning path is generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0011] In one embodiment, the step of obtaining intersection distribution information corresponding to the intersection includes:

[0012] determining intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information;

[0013] The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

[0014] In one embodiment, the vehicle guide line includes a static guide line and a candidate guide line, and the step of generating the vehicle guide line based on the intersection distribution information includes:

[0015] Performing a topological analysis on the intersection distribution information to determine a pre-selected exit lane;

[0016] calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes;

[0017] The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

[0018] In one embodiment, the step of generating a target planning path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line includes:

[0019] generating a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determining whether to perform a global path adjustment and / or a local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path;

[0020] The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

[0021] In one embodiment, the step of determining whether to perform global path adjustment and / or local path adjustment and determining a dynamic obstacle avoidance path based on the dynamic obstacle information includes at least one of the following:

[0022] If a global path adjustment is determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is used as the dynamic obstacle avoidance path;

[0023] If global path adjustment and local path adjustment are determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path;

[0024] If it is determined to perform a local path adjustment based on the dynamic obstacle information, the static obstacle avoidance path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path.

[0025] In one embodiment, the step of determining whether to perform global path adjustment based on the dynamic obstacle information includes:

[0026] Calculating the safety risk and / or traffic efficiency corresponding to the target exit lane based on the dynamic obstacle information, and calculating the safety risk and / or traffic efficiency corresponding to the candidate exit lane based on the dynamic obstacle information;

[0027] calculating an evaluation function corresponding to the target exit lane based on the safety risk and / or traffic efficiency corresponding to the target exit lane, and calculating an evaluation function corresponding to the candidate exit lane based on the safety risk and / or traffic efficiency corresponding to the candidate exit lane;

[0028] Determining whether the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane;

[0029] If the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane, it is determined to perform a global path adjustment.

[0030] In one embodiment, after the step of generating a target planned path based on the static obstacle information and / or dynamic obstacle information corresponding to the current time node in combination with the vehicle guide line, the step further includes:

[0031] Controlling the vehicle to travel along the target planned path and obtaining static obstacle information and / or dynamic obstacle information corresponding to the next time node;

[0032] The target planned path is adjusted according to the static obstacle information and / or dynamic obstacle information corresponding to the next time node until the vehicle exits the intersection.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a driving planning device, which includes:

[0034] A response module, configured to obtain intersection distribution information corresponding to the intersection in response to recognizing that the vehicle enters the intersection;

[0035] A generation module, configured to generate a vehicle guide line based on the intersection distribution information, and obtain static obstacle information and / or dynamic obstacle information corresponding to a current time node;

[0036] A planning module is used to generate a target planning path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0037] In one embodiment, the response module determines intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information;

[0038] The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

[0039] In one embodiment, the vehicle guide line includes a static guide line and a candidate guide line, and the generation module performs a topological analysis on the intersection distribution information to determine a preselected exit lane;

[0040] calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes;

[0041] The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

[0042] In one embodiment, the vehicle guide line includes a static guide line and a candidate guide line, and the planning module generates a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determines whether to perform a global path adjustment and / or a local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path;

[0043] The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a terminal device, which includes a memory, a processor, and a driving planning program stored on the memory and runnable on the processor. When the driving planning program is executed by the processor, the steps of the driving planning method described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which a driving planning program is stored. When the driving planning program is executed by a processor, the steps of the driving planning method described above are implemented.

[0046] The embodiments of the present application propose a driving planning method, apparatus, terminal device, and storage medium. In response to identifying a vehicle entering an intersection, the method obtains intersection distribution information corresponding to the intersection; generates a vehicle guide line based on the intersection distribution information, and obtains static obstacle information and / or dynamic obstacle information corresponding to the current time node; generates a target planning path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line. By comprehensively considering the intersection distribution information, static obstacle information, and dynamic obstacle information, a complete driving planning system is constructed, which helps to improve the vehicle's traffic efficiency at intersections and / or ensure the flexibility and safety of vehicle movement.

[0047] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0049] FIG1 is a schematic diagram of the functional modules of the terminal device to which the driving planning device of the present application belongs;

[0050] FIG2 is a flow chart of an exemplary embodiment of a driving planning method of the present application;

[0051] FIG3 is a schematic diagram of a specific process of generating a vehicle guide line based on the intersection distribution information in the embodiment of FIG2 ;

[0052] FIG4 is a schematic diagram of the road structure of an intersection in an embodiment of the present application;

[0053] FIG5 is a schematic diagram of a left-turn intersection scene in an embodiment of the present application;

[0054] FIG6 is a schematic diagram of a right-turn intersection scene in an embodiment of the present application;

[0055] FIG7 is a schematic diagram of the vehicle guide line generation principle in an embodiment of the present application;

[0056] FIG8 is a schematic diagram of a specific process of generating a target planning path according to the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line in the embodiment of FIG2 ;

[0057] FIG9 is a schematic diagram of the overall process in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although the accompanying drawings illustrate embodiments of the present application, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0059] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0060] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0061] The technical solution provided by the embodiments of this application includes: obtaining intersection distribution information corresponding to the intersection in response to identifying the vehicle entering the intersection; generating a vehicle guide line based on the intersection distribution information, and obtaining static obstacle information and / or dynamic obstacle information corresponding to the current time node; and generating a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line. By comprehensively considering intersection distribution information, static obstacle information, and dynamic obstacle information, this application constructs a comprehensive driving planning system, which helps improve vehicle traffic efficiency at intersections and / or ensures the flexibility and safety of vehicle movement.

[0062] In one embodiment, referring to FIG1 , FIG1 is a schematic diagram of the functional modules of a terminal device to which the driving planning device of the present application belongs. The driving planning device can be a device independent of the terminal device that is capable of driving planning and can be hosted on the terminal device in the form of hardware or software. The terminal device can be a smart mobile terminal with data processing capabilities, such as a mobile phone or tablet computer, or a fixed terminal device or server with data processing capabilities.

[0063] In this embodiment, the terminal device to which the driving planning apparatus belongs includes at least an output module 110 , a processor 120 , a memory 130 and a communication module 140 .

[0064] The memory 130 stores an operating system and a driving planning program. The driving planning device can store information such as the acquired intersection distribution information corresponding to the intersection, the vehicle guide lines generated based on the acquired intersection distribution information, the acquired static obstacle information and / or dynamic obstacle information corresponding to the current time node, and the target planned path generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide lines. The output module 110 can be a display screen, etc. The communication module 140 can include a Wi-Fi module, a mobile communication module, and a Bluetooth module, etc., and communicates with external devices or servers through the communication module 140.

[0065] When the driving planning program in the memory 130 is executed by the processor, the following steps are implemented:

[0066] In response to recognizing that the vehicle enters an intersection, obtaining intersection distribution information corresponding to the intersection;

[0067] generating a vehicle guide line based on the intersection distribution information, and obtaining static obstacle information and / or dynamic obstacle information corresponding to a current time node;

[0068] A target planning path is generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0069] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0070] determining intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information;

[0071] The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

[0072] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0073] Performing a topological analysis on the intersection distribution information to determine a pre-selected exit lane;

[0074] calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes;

[0075] The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

[0076] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0077] generating a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determining whether to perform a global path adjustment and / or a local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path;

[0078] The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

[0079] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0080] If a global path adjustment is determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is used as the dynamic obstacle avoidance path;

[0081] If global path adjustment and local path adjustment are determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path;

[0082] If it is determined to perform a local path adjustment based on the dynamic obstacle information, the static obstacle avoidance path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path.

[0083] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0084] Calculating the safety risk and / or traffic efficiency corresponding to the target exit lane based on the dynamic obstacle information, and calculating the safety risk and / or traffic efficiency corresponding to the candidate exit lane based on the dynamic obstacle information;

[0085] calculating an evaluation function corresponding to the target exit lane based on the safety risk and / or traffic efficiency corresponding to the target exit lane, and calculating an evaluation function corresponding to the candidate exit lane based on the safety risk and / or traffic efficiency corresponding to the candidate exit lane;

[0086] Determining whether the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane;

[0087] If the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane, it is determined to perform a global path adjustment.

[0088] Furthermore, when the driving planning program in the memory 130 is executed by the processor, the following steps are also implemented:

[0089] Controlling the vehicle to travel along the target planned path and obtaining static obstacle information and / or dynamic obstacle information corresponding to the next time node;

[0090] The target planned path is adjusted according to the static obstacle information and / or dynamic obstacle information corresponding to the next time node until the vehicle exits the intersection.

[0091] This embodiment, through the above-mentioned scheme, includes obtaining intersection distribution information corresponding to the intersection in response to recognizing the vehicle entering the intersection; generating a vehicle guide line based on the intersection distribution information; and obtaining static obstacle information and / or dynamic obstacle information corresponding to the current time node; and generating a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line. By comprehensively considering intersection distribution information, static obstacle information, and dynamic obstacle information, this application constructs a comprehensive driving planning system, which helps improve vehicle traffic efficiency at intersections and / or ensures the flexibility and safety of vehicle movement.

[0092] Based on the above terminal device architecture but not limited to the above architecture, an embodiment of the method of the present application is proposed.

[0093] The execution subject of the method of this embodiment may be a driving planning device or a terminal device, etc. This embodiment takes a driving planning device as an example.

[0094] Referring to FIG2 , FIG2 is a flow chart of an exemplary embodiment of a driving planning method of the present application. The driving planning method includes:

[0095] Step S10 , in response to recognizing that the vehicle enters an intersection, obtaining intersection distribution information corresponding to the intersection.

[0096] Because intersections often have diverse shapes and lack clear lane markings, vehicle movement within intersections is more random and free-flowing than on conventional roads with well-defined lanes, posing significant challenges to autonomous vehicle motion planning. Related technical solutions typically construct intersection paths based on static geometric information and then follow this fixed path. This can lead to low traffic efficiency and poor trajectory flexibility. Furthermore, for real-time map-building systems based on perception information, vehicle paths can fluctuate due to perception uncertainty, making it difficult to ensure safe movement.

[0097] The embodiments of the present application provide a solution for high-level assisted and / or autonomous driving vehicles, constructing a complete motion planning system, comprehensively considering the static geometry and topological information of free spaces such as intersections, as well as the dynamic information of surrounding objects, to design an effective, highly applicable and safe autonomous driving planning method.

[0098] In one embodiment, the driving planning method in the embodiment of the present application is applied to the vehicle's assisted driving system and / or automatic driving system. When the system recognizes that the vehicle has arrived at an intersection, it can recognize the road structure by obtaining relevant intersection distribution information.

[0099] In one embodiment, the step of obtaining intersection distribution information corresponding to the intersection includes:

[0100] Determine intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information.

[0101] In one embodiment, the intersection distribution information includes at least one of the intersection shape, entry road, entry lane information, exit road and exit lane information, and may also include static road elements such as lane lines, stop lines, zebra crossings, etc.

[0102] In one embodiment, the map information in the embodiment of the present application can come from a high-precision map or a real-time perception map. Sensor information can be obtained through on-board cameras, lidars and other sensors. The shape of the intersection, incoming roads and outgoing roads, incoming lane information and outgoing lane information, etc. can be determined based on navigation information, map information and sensor information.

[0103] In one embodiment, the shape of the intersection may include a crossroads, a T-shaped intersection, a Y-shaped intersection, a roundabout, and a polygonal intersection, etc. The same intersection may include multiple modes of passage, such as straight-ahead passage, left-turn passage, right-turn passage, and U-shaped passage, etc. The embodiment of the present application mainly uses straight-ahead passage as an example for explanation.

[0104] In one embodiment, different entry roads and exit roads may include different numbers of lanes. The entry lane information may include the lane position of the vehicle entering the intersection, and the exit lane information may include the distribution order of lanes in the exit road, the number of lanes that can be used as exit lanes, etc.

[0105] In one embodiment, the intersection distribution information may also include information about obstacles in the intersection area that may affect the movement of vehicles, such as fences, cones, water barriers, and walls.

[0106] Step S20: generating a vehicle guide line based on the intersection distribution information, and obtaining static obstacle information and / or dynamic obstacle information corresponding to the current time node.

[0107] Furthermore, after the intersection distribution information is obtained, a vehicle guide line may be generated based on the intersection distribution information, and static obstacle information and / or dynamic obstacle information corresponding to the current time node may be obtained.

[0108] In one embodiment, by performing a topological analysis on intersection distribution information, the effective range of the exit lane, i.e., the pre-selected exit lane, can be determined. Furthermore, geometric information such as the distance and angle between each candidate exit lane and the entry lane can be comprehensively considered, and the optimal exit lane, i.e., the target exit lane, can be determined from among the pre-selected exit lanes using quantitative indicators. Lanes in the pre-selected exit lanes other than the target exit lane can be used as candidate exit lanes.

[0109] In one embodiment, a static guide line may be generated based on target exit lane and entry lane information; and a candidate guide line may be generated based on candidate exit lane and entry lane information.

[0110] In one embodiment, static obstacle information and / or dynamic obstacle information around the vehicle can be obtained through visual sensors installed on the vehicle body. The visual sensors used may include various sensors such as cameras, lidars, infrared sensors, ultrasonic sensors, and radars, which are used to capture and process environmental information around the vehicle.

[0111] Step S30: generating a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0112] Furthermore, after generating a vehicle guide line based on the intersection distribution information and obtaining the static obstacle information and / or dynamic obstacle information corresponding to the current time node, the target planning path can be generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0113] In one embodiment, based on the acquired static obstacle information, curve translation, hybrid A* or potential field methods can be used on the generated static guide line to generate a navigable path that can bypass the static obstacles in the environment, that is, a static obstacle avoidance path.

[0114] In one embodiment, after acquiring dynamic obstacle information, dynamic obstacles with potential collision risks near the vehicle may be selected, thereby determining whether to perform global path adjustment and / or local path adjustment to determine a dynamic obstacle avoidance path.

[0115] In one embodiment, when there are no dynamic obstacles with potential collision risks near the static obstacle avoidance path, that is, no path adjustment is required, and the static obstacle avoidance path can be directly used as the target planning path; when there are dynamic obstacles with potential collision risks near the static obstacle avoidance path, the dynamic obstacle avoidance path is determined through global path adjustment and / or local path adjustment, and the dynamic obstacle avoidance path is used as the target planning path.

[0116] In one embodiment, after the step of generating a target planned path based on the static obstacle information and / or dynamic obstacle information corresponding to the current time node in combination with the vehicle guide line, the step further includes:

[0117] Controlling the vehicle to travel along the target planned path and obtaining static obstacle information and / or dynamic obstacle information corresponding to the next time node;

[0118] The target planned path is adjusted according to the static obstacle information and / or dynamic obstacle information corresponding to the next time node until the vehicle exits the intersection.

[0119] In one embodiment, after the vehicle's target planned path at the intersection is determined, the vehicle further considers the motion information of surrounding vehicles and assigns time information to the path. This is known as trajectory planning. This typically involves using optimization methods or using A* to search for a speed profile for the set path based on the ST graph. Once the trajectory is generated, it is sent to the control module to drive the vehicle.

[0120] In one embodiment, since static obstacles and dynamic obstacles may change during the movement of the vehicle, the target planned path can be adjusted according to the static obstacle information and / or dynamic obstacle information obtained in real time while the vehicle is moving in the intersection area, and a new target planned path can also be regenerated according to the static obstacle information and / or dynamic obstacle information obtained in real time.

[0121] In one embodiment, in order to save the system's computing power, the target planned path is adjusted or updated at intervals of a preset time (for example, 0.1 seconds) in the embodiment of the present application, that is, the current time node and the next time node are separated by 0.1 seconds, and the target planned path is adjusted or updated at the next time node based on the re-acquired static obstacle information and / or dynamic obstacle information until the vehicle exits the intersection, and the driving planning of the intersection is considered to be completed.

[0122] In this embodiment, in response to recognizing a vehicle entering an intersection, intersection distribution information corresponding to the intersection is obtained; a vehicle guide line is generated based on the intersection distribution information; and static obstacle information and / or dynamic obstacle information corresponding to the current time node is obtained; and a target planned path is generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line. By comprehensively considering intersection distribution information, static obstacle information, and dynamic obstacle information, this application constructs a comprehensive driving planning system, which helps improve vehicle traffic efficiency at intersections and / or ensures the flexibility and safety of vehicle movement.

[0123] Referring to FIG3 , FIG3 is a schematic diagram of a specific process of generating a vehicle guide line based on the intersection distribution information in the embodiment of FIG2 . This embodiment is based on the embodiment shown in FIG2 , and in this embodiment, the steps of generating a vehicle guide line based on the intersection distribution information include:

[0124] Step S201: Perform a topological analysis on the intersection distribution information to determine a pre-selected exit lane.

[0125] In one embodiment, based on the order of the entry lanes in the intersection distribution information, the effective range of the exit lanes, that is, the pre-selected exit lanes, can be determined through topological analysis.

[0126] Refer to Figure 4, which is a schematic diagram of the intersection road structure in the embodiment of the present application. As shown in Figure 4, the incoming road contains 5 lanes, and the order of the vehicle entering the lane is 3 (the lane order defaults to starting from 1 from left to right), using N 1S Indicates the number of lanes entering the road N 2S Indicates the number of lanes exiting the road. If N 1S ≥N 2S , then the valid range of lane exit sequence N2 can be determined as:

[0127] where N diff N 1S With N 2S The absolute value of the difference.

[0128] Wherein, N1 is the lane entry sequence. As shown in FIG4 , the lane entry sequence is N1=3.

[0129] If N 1S <N 2S , then the valid range of lane exit sequence N2 is:

[0130] Step S202 : Calculate a geometric quantization index based on the intersection distribution information, select or determine a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and use lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes.

[0131] In one embodiment, geometric information such as the distance and angle between each candidate exit lane and the entry lane is comprehensively considered, and the optimal lane is preliminarily selected from the valid range of the exit lane sequence N2 using quantitative indicators. This lane is the target exit lane, and lanes other than the target exit lane among the pre-selected exit lanes can be used as candidate exit lanes.

[0132] In one embodiment, as shown in FIG4 , P1 is the intersection of the entry lane and the entry end face, P2 is the intersection of the exit lane and the exit end face, V1 and V2 are the normal vectors of the entry end face and the exit end face, respectively, and α and β are vectors respectively. The angle between V1 and V2 (α and β are taken as absolute values ​​by default), the angle quantitative index of exit lane selection can be defined as: f i =α i +β i , the distance quantization index is marked as d i , represents the Euclidean distance between P1 and P2, and i represents the order of exiting the lane. Generally, the optimal lane is the exit lane with the smallest F(i) value:

[0133] F(i)=min(w1*f i +w2*d i )

[0134] Among them, w1 and w2 are empirical parameters.

[0135] Step S203 : generating the static guide line according to the target exit lane and entrance lane information, and generating the candidate guide line according to the candidate exit lane and entrance lane information.

[0136] Referring to Figures 5 and 6, Figure 5 is a schematic diagram of a left-turn intersection scenario in accordance with an embodiment of the present application, and Figure 6 is a schematic diagram of a right-turn intersection scenario in accordance with an embodiment of the present application. As shown in Figures 5 and 6, static guide lines can be generated based on target exit and entry lane information. Furthermore, candidate guide lines can be generated based on candidate exit and entry lane information.

[0137] Refer to Figure 7, which illustrates the principle behind generating vehicle guide lines in an embodiment of the present application. As shown in Figure 7, based on the positions of the intersection points P1 and P2 between the entry and exit lanes and their corresponding end faces, and vectors V1 and V2, guide lines for vehicles passing through intersections can be generated using methods such as geometric primitive combination curves, RS curves, Dubins curves, Bezier curves, and spirals. As shown in Figure 7, O1 is the intersection point of the extended lines of the entry and exit end faces; O2 is a point on the line segment O1P2, and the following holds:

[0138] And there are:

[0139] And there are:

[0140] In one embodiment, arc ①, arc ③, and line segment ② are fused to construct a guide line from P1 to P2, thereby obtaining a static guide line.

[0141] In one embodiment, the method for generating candidate guide lines is similar to that for generating static guide lines, except that the exit lane is different.

[0142] This embodiment, through the above-mentioned scheme, includes determining a preselected exit lane by performing a topological analysis on the intersection distribution information; calculating a geometric quantitative index based on the intersection distribution information, and selecting or determining a target exit lane from the preselected exit lanes based on the geometric quantitative index, and using lanes other than the target exit lane in the preselected exit lanes as candidate exit lanes; generating the static guide line based on the target exit lane and entry lane information, and generating the candidate guide line based on the candidate exit lane and entry lane information, and then combining the static guide line or the candidate guide line with static obstacle information and / or dynamic obstacle information to generate a target planned path, thereby forming a complete driving planning system, which helps to improve the traffic efficiency of vehicles at intersections and / or ensure the flexibility and safety of vehicle travel.

[0143] Referring to FIG8 , FIG8 is a schematic diagram of a specific process for generating a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line in the embodiment of FIG2 . This embodiment is based on the embodiment shown in FIG2 . In this embodiment, the steps of generating a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line include:

[0144] Step S301: Generate a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determine whether to perform global path adjustment and / or local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path.

[0145] Step S302: Using the static obstacle avoidance path or the dynamic obstacle avoidance path as the target planning path.

[0146] Referring to Figure 9, which is a schematic diagram of the overall process in an embodiment of the present application, as shown in Figure 9, based on the acquired static obstacle information, methods such as curve translation, hybrid A*, or potential field can be used on the generated static guide line to generate a navigable path that can circumvent static obstacles in the environment, namely, a static obstacle avoidance path.

[0147] In one embodiment, while or after generating a static obstacle avoidance path based on the static guide line, a static candidate path can also be generated based on the candidate guide line, or a static candidate path can be generated based on the lanes on both sides (e.g., left and right sides) of the lane where the target exits.

[0148] In one embodiment, after acquiring dynamic obstacle information, dynamic obstacles with potential collision risks near the vehicle may be selected, thereby determining whether to perform global path adjustment and / or local path adjustment to determine a dynamic obstacle avoidance path.

[0149] In one embodiment, when there are no dynamic obstacles with potential collision risks near the static obstacle avoidance path, that is, no path adjustment is required, and the static obstacle avoidance path can be directly used as the target planning path; when there are dynamic obstacles with potential collision risks near the static obstacle avoidance path, the dynamic obstacle avoidance path is determined through global path adjustment and / or local path adjustment, and the dynamic obstacle avoidance path is used as the target planning path.

[0150] In one embodiment, the step of determining whether to perform global path adjustment based on the dynamic obstacle information includes:

[0151] Calculating the safety risk and / or traffic efficiency corresponding to the target exit lane based on the dynamic obstacle information, and calculating the safety risk and / or traffic efficiency corresponding to the candidate exit lane based on the dynamic obstacle information;

[0152] calculating an evaluation function corresponding to the target exit lane based on the safety risk and / or traffic efficiency corresponding to the target exit lane, and calculating an evaluation function corresponding to the candidate exit lane based on the safety risk and / or traffic efficiency corresponding to the candidate exit lane;

[0153] Determining whether the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane;

[0154] If the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane, it is determined to perform a global path adjustment.

[0155] In one embodiment, by integrating information from the surrounding dynamic environment, it is possible to assess whether a global path adjustment is necessary, that is, whether the current static obstacle avoidance path needs to be switched. This assessment is typically based on potential safety risks and the vehicle's traffic efficiency. Assuming i is the order of exiting a lane, its corresponding safety risk assessment function is S(i), and its traffic efficiency assessment function is E(i). The selection criterion for updating the guideline can be defined as the exit lane with the minimum value of the assessment function F2(i). F2(i) is defined as follows:

[0156] Where c1 and c2 are empirical parameters, and k is the optimal lane order determined by the topological analysis process.

[0157] In one embodiment, the step of determining whether to perform global path adjustment and / or local path adjustment and determining a dynamic obstacle avoidance path based on the dynamic obstacle information includes at least one of the following:

[0158] If a global path adjustment is determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is used as the dynamic obstacle avoidance path;

[0159] If global path adjustment and local path adjustment are determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path;

[0160] If it is determined to perform a local path adjustment based on the dynamic obstacle information, the static obstacle avoidance path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path.

[0161] In one embodiment, after evaluating whether to perform global path adjustments, a globally optimal path can be determined that effectively avoids static and dynamic obstacles in the entire intersection area. However, this does not necessarily effectively avoid obstacles in the local path near the vehicle. Therefore, in this embodiment, obstacles near the vehicle with potential collision risks are selected and, by adjusting the vehicle's local planned path, avoidance or detour actions are implemented in advance, thereby further ensuring the safety and efficiency of vehicle traffic at the intersection. In one embodiment, the local path planning method can generally utilize a potential field or safety corridor, that is, treating key obstacles and their surrounding areas as inaccessible spaces for path planning, to adjust the static obstacle avoidance path and obtain a dynamic obstacle avoidance path.

[0162] This embodiment, through the above-mentioned scheme, includes generating a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determining whether to perform global and / or local path adjustments based on the dynamic obstacle information to determine a dynamic obstacle avoidance path; and using the static obstacle avoidance path or the dynamic obstacle avoidance path as the target planning path. By comprehensively considering intersection distribution information, static obstacle information, and dynamic obstacle information, this application constructs a comprehensive driving planning system, which helps improve vehicle traffic efficiency at intersections and / or ensures vehicle flexibility and safety.

[0163] In addition, an embodiment of the present application further provides a driving planning device, which includes:

[0164] A response module, configured to obtain intersection distribution information corresponding to the intersection in response to recognizing that the vehicle enters the intersection;

[0165] A generation module, configured to generate a vehicle guide line based on the intersection distribution information, and obtain static obstacle information and / or dynamic obstacle information corresponding to a current time node;

[0166] A planning module is used to generate a target planning path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

[0167] In one embodiment, the response module determines intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information;

[0168] The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

[0169] In one embodiment, the vehicle guide line includes a static guide line and a candidate guide line, and the generation module performs a topological analysis on the intersection distribution information to determine a preselected exit lane;

[0170] calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes;

[0171] The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

[0172] In one embodiment, the vehicle guide line includes a static guide line and a candidate guide line, and the planning module generates a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determines whether to perform a global path adjustment and / or a local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path;

[0173] The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

[0174] For the principle and implementation process of driving planning implemented in this embodiment, please refer to the above embodiments and will not be repeated here.

[0175] In addition, an embodiment of the present application also proposes a terminal device, which includes a memory, a processor, and a driving planning program stored in the memory and runnable on the processor. When the driving planning program is executed by the processor, the steps of the driving planning method described above are implemented.

[0176] Since the driving planning program adopts all the technical solutions of all the aforementioned embodiments when executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0177] In addition, an embodiment of the present application also proposes a computer-readable storage medium, on which a driving planning program is stored. When the driving planning program is executed by a processor, the steps of the driving planning method described above are implemented.

[0178] Since the driving planning program adopts all the technical solutions of all the aforementioned embodiments when executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0179] Compared to related technologies, the driving planning method, apparatus, terminal device, and storage medium proposed in the embodiments of this application obtain intersection distribution information corresponding to the intersection in response to identifying the vehicle entering the intersection; generate a vehicle guide line based on the intersection distribution information, and obtain static obstacle information and / or dynamic obstacle information corresponding to the current time node; and generate a target planned path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line. By comprehensively considering intersection distribution information, static obstacle information, and dynamic obstacle information, this application constructs a comprehensive driving planning system, which helps improve vehicle traffic efficiency at intersections and / or ensures the flexibility and safety of vehicle movement.

[0180] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0181] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0182] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, controlled terminal, or network device, etc.) to execute the method of each embodiment of the present application.

[0183] The embodiments of the present application have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

1. A driving planning method, characterized in that: The driving planning method comprises: In response to recognizing that the vehicle enters an intersection, obtaining intersection distribution information corresponding to the intersection; generating a vehicle guide line based on the intersection distribution information, and obtaining static obstacle information and / or dynamic obstacle information corresponding to a current time node; A target planning path is generated based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

2. The driving planning method according to claim 1, wherein: The obtaining of intersection distribution information corresponding to the intersection includes: Determining intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information; The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

3. The driving planning method according to claim 2, wherein: The vehicle guide line includes a static guide line and a candidate guide line, and the generating of the vehicle guide line based on the intersection distribution information includes: Performing a topological analysis on the intersection distribution information to determine a pre-selected exit lane; calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes; The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

4. The driving planning method according to claim 1, wherein: The vehicle guide line includes a static guide line and a candidate guide line, and generating a target planning path based on the static obstacle information and / or the dynamic obstacle information in combination with the vehicle guide line includes: generating a static obstacle avoidance path based on the static obstacle information and the static guide line, and / or determining whether to perform a global path adjustment and / or a local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path; The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

5. The driving planning method according to claim 4, characterized in that: The determining whether to perform global path adjustment and / or local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path includes at least one of the following: If global path adjustment is determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is as the dynamic obstacle avoidance path; or, If global path adjustment and local path adjustment are determined based on the dynamic obstacle information, a static candidate path is generated based on the static obstacle information and the candidate guide line, and the static candidate path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path; or, If it is determined to perform a local path adjustment based on the dynamic obstacle information, the static obstacle avoidance path is adjusted based on the dynamic obstacle information to obtain the dynamic obstacle avoidance path.

6. The driving planning method according to claim 4, characterized in that: The determining whether to perform global path adjustment according to the dynamic obstacle information includes: Calculating the safety risk and / or traffic efficiency corresponding to the target exit lane based on the dynamic obstacle information, and calculating the safety risk and / or traffic efficiency corresponding to the candidate exit lane based on the dynamic obstacle information; calculating an evaluation function corresponding to the target exit lane based on the safety risk and / or traffic efficiency corresponding to the target exit lane, and calculating an evaluation function corresponding to the candidate exit lane based on the safety risk and / or traffic efficiency corresponding to the candidate exit lane; Determining whether the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane; If the evaluation function corresponding to the target exit lane is greater than the evaluation function corresponding to the candidate exit lane, it is determined to perform a global path adjustment.

7. The driving planning method according to claim 1, wherein: After generating the target planned path based on the static obstacle information and / or dynamic obstacle information corresponding to the current time node in combination with the vehicle guide line, the method further includes: Controlling the vehicle to travel along the target planned path and obtaining static obstacle information and / or dynamic obstacle information corresponding to the next time node; The target planned path is adjusted according to the static obstacle information and / or dynamic obstacle information corresponding to the next time node until the vehicle exits the intersection.

8. A driving planning device, characterized in that: The driving planning device comprises: A response module, configured to obtain intersection distribution information corresponding to the intersection in response to recognizing that the vehicle enters the intersection; A generation module, configured to generate a vehicle guide line based on the intersection distribution information, and obtain static obstacle information and / or dynamic obstacle information corresponding to a current time node; A planning module is used to generate a target planning path based on the static obstacle information and / or dynamic obstacle information in combination with the vehicle guide line.

9. The driving planning device according to claim 8, wherein: The response module determines intersection distribution information corresponding to the intersection based on at least one of navigation information, map information, and sensor information; The intersection distribution information includes at least one of the intersection shape, incoming road, incoming lane information, outgoing road and outgoing lane information.

10. The driving planning device according to claim 9, wherein: The vehicle guide lines include static guide lines and candidate guide lines, and the generation module performs a topological analysis on the intersection distribution information to determine a preselected exit lane; calculating a geometric quantization index based on the intersection distribution information, and selecting or determining a target exit lane from the pre-selected exit lanes based on the geometric quantization index, and using lanes in the pre-selected exit lanes other than the target exit lane as candidate exit lanes; The static guide line is generated according to the target exit lane and entrance lane information, and the candidate guide line is generated according to the candidate exit lane and entrance lane information.

11. The driving planning device according to claim 8, wherein: The vehicle guide lines include static guide lines and candidate guide lines. The planning module generates a static obstacle avoidance path based on the static obstacle information and the static guide lines, and / or determines whether to perform global path adjustment and / or local path adjustment based on the dynamic obstacle information to determine a dynamic obstacle avoidance path. The static obstacle avoidance path or the dynamic obstacle avoidance path is used as the target planning path.

12. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a driving planning program stored in the memory and executable on the processor. When the driving planning program is executed by the processor, the driving planning method according to any one of claims 1 to 7 is implemented.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a driving planning program, which, when executed by a processor, implements the driving planning method according to any one of claims 1 to 7.

Images