Intelligent vehicle trajectory planning method based on space-time risk map and related device

Abstract

The invention discloses an intelligent vehicle trajectory planning method based on a space-time risk map and a related device, and relates to the technical field of intelligent traffic, and the method comprises the steps: generating a space-time risk sub-map of a certain road region according to obstacle vehicle information and a movement trajectory of an obstacle vehicle in the certain road region, generating a first risk sub-map and a second risk sub-map of the certain road area according to the road boundary line distribution information and the traversal lane line distribution information, and further determining a space-time risk map of the certain road area; and then, according to the reference trajectory and the space-time risk map, generating a dynamic safety corridor, and based on the dynamic safety corridor, solving the updated optimal control model to obtain an optimal planning trajectory of the target intelligent vehicle. According to the method, unified description of different heterogeneous traffic elements from the risk perspective is realized, the complexity of trajectory planning is effectively reduced, the efficiency of trajectory planning is improved, and the consumption of computing resources is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to an intelligent vehicle trajectory planning method and related devices based on a spatiotemporal risk map. Background Art

[0002] Autonomous driving is considered a major innovative technology, promising to play a positive role in reducing traffic accidents, alleviating traffic congestion, and reducing energy consumption. In autonomous driving systems, the planning layer, as a crucial component connecting the perception and control layers, is considered a direct reflection of the intelligence of connected vehicles. Its goal is to find collision-free, comfortable, and smooth trajectories.

[0003] Among the various approaches to trajectory planning for intelligent connected vehicles (ICVs), optimization-based methods typically formulate the trajectory planning problem as an optimal control problem (OCP) in the most accurate, complete, and unified manner, using constraints and objective functions. These methods are highly adaptable and flexible, and are widely used in the field of spatiotemporal trajectory planning. However, in complex urban environments with dense obstacles, this process consumes significant computational resources. This is because complex urban environments contain many heterogeneous traffic elements, such as dynamic obstacles and static obstacles (such as lane boundaries). Different elements often correspond to different mathematical descriptions, such as constraints and costs. This complexity makes OCP a computationally difficult non-convex optimization problem. Furthermore, high-precision maps and prediction modules provide rich traffic scenario information, including reference lanes, occupancy maps, and probabilistic multimodal future trajectories. This information can assist ICVs in planning driving trajectories, but it also increases the complexity of the planning process, further increasing the consumption of computational resources. Consequently, current autonomous driving systems struggle to directly understand and efficiently utilize this information. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent vehicle trajectory planning method and related devices based on a spatiotemporal risk map, which can achieve a unified description of different heterogeneous traffic elements, effectively reduce the complexity of trajectory planning, improve the efficiency of trajectory planning, and reduce the consumption of computing resources.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides an intelligent vehicle trajectory planning method based on a spatiotemporal risk map, comprising:

[0007] Obtain road boundary line distribution information, traversable lane line distribution information, and obstacle vehicle information in a certain road area around the target intelligent vehicle, and predict the movement trajectory of the obstacle vehicle in the certain road area based on the obstacle vehicle information.

[0008] A spatiotemporal risk submap of the certain road area is generated according to the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area.

[0009] A first risk submap and a second risk submap of the certain road area are generated according to the road boundary line distribution information and the crossable lane line distribution information respectively.

[0010] A spatiotemporal risk map of the certain road area is determined based on the spatiotemporal risk submap, the first risk submap, and the second risk submap.

[0011] A dynamic programming algorithm is used to obtain a reference trajectory of the target intelligent vehicle in the certain road area, and a dynamic safety corridor is generated based on the reference trajectory and the spatiotemporal risk map.

[0012] According to the dynamic safety corridor, the dynamic safety corridor boundary constraints in the optimal control model are updated, and the updated optimal control model is solved to obtain the optimal planning trajectory of the target intelligent vehicle.

[0013] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent vehicle trajectory planning method based on the spatiotemporal risk map described in the first aspect.

[0014] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent vehicle trajectory planning method based on the spatiotemporal risk map described in the first aspect.

[0015] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the intelligent vehicle trajectory planning method based on the spatiotemporal risk map described in the first aspect.

[0016] According to the specific embodiments provided in this application, this application has the following technical effects:

[0017] The present application provides a method and related device for intelligent vehicle trajectory planning based on a spatiotemporal risk map. According to the information of the obstacle vehicle and the movement trajectory of the obstacle vehicle in the certain road area, a spatiotemporal risk submap of the certain road area is generated, and according to the road boundary line distribution information and the traversable lane line distribution information, a first risk submap and a second risk submap of the certain road area are generated respectively. Then, according to the spatiotemporal risk submap, the first risk submap and the second risk submap, the spatiotemporal risk map of the certain road area is determined; then, according to the reference trajectory and the spatiotemporal risk map, a dynamic safety corridor is generated, and based on the dynamic safety corridor, the updated optimal control model is solved to obtain the optimal planned trajectory of the target intelligent vehicle. Through the above scheme, the present application uniformly converts dynamic and static heterogeneous traffic elements such as obstacle vehicles, road boundary lines and traversable lane lines into risks of the road area, and finally generates a spatiotemporal risk map corresponding to the road area, realizing a unified description of different heterogeneous traffic elements, effectively reducing the complexity of trajectory planning, improving the efficiency of trajectory planning, reducing the consumption of computing resources, and effectively ensuring the real-time requirements of trajectory planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a flow chart of an intelligent vehicle trajectory planning method based on a spatiotemporal risk map in one embodiment of the present application;

[0020] Figure 2 This is a flow chart of another intelligent vehicle trajectory planning method based on a spatiotemporal risk map in one embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0023] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] In an exemplary embodiment, Figure 1 As shown, a method for intelligent vehicle trajectory planning based on a spatiotemporal risk map is provided, comprising the following steps 101 to 106. In which:

[0025] Step 101: Obtain road boundary line distribution information, traversable lane line distribution information, and obstacle vehicle information in a certain road area around a target intelligent vehicle, and predict the movement trajectory of the obstacle vehicle in the certain road area based on the obstacle vehicle information.

[0026] Step 102: Generate a spatiotemporal risk submap of the certain road area based on the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area.

[0027] Step 103 : generating a first risk submap and a second risk submap of the certain road area according to the road boundary line distribution information and the crossable lane line distribution information respectively.

[0028] Step 104 : Determine a spatiotemporal risk map for the certain road area based on the spatiotemporal risk submap, the first risk submap, and the second risk submap.

[0029] Step 105 , using a dynamic programming algorithm, obtains a reference trajectory of the target intelligent vehicle in the certain road area, and generates a dynamic safety corridor based on the reference trajectory and the spatiotemporal risk map.

[0030] Step 106 : updating the dynamic safety corridor boundary constraints in the optimal control model according to the dynamic safety corridor, and solving the updated optimal control model to obtain the optimal planned trajectory of the target intelligent vehicle.

[0031] As an optional implementation, in step 105, generating a dynamic safety corridor based on the reference trajectory and the spatiotemporal risk map specifically includes:

[0032] Step 105.11: Determine a preset number of initial rectangular areas based on all adjacent discrete trajectory points on the reference trajectory; the preset number is equal to the number of pairs of all adjacent discrete trajectory points; each pair of adjacent discrete trajectory points is a diagonal point of a corresponding initial rectangular area.

[0033] Step 105.12: Perform several rounds of expansion on each initial rectangular area to obtain an expanded rectangular area corresponding to each initial rectangular area.

[0034] Step 105.13: Determine a dynamic safety corridor based on a preset number of the expanded rectangular areas; the dynamic safety corridor is composed of the preset number of the expanded rectangular areas.

[0035] In step 105.12, the several rounds of expansion process for each initial rectangular area are as follows:

[0036] According to the preset translation distance increment, the four sides of the initial rectangular area are sequentially translated outward to obtain the rectangular area after the first round of expansion. Then, according to the preset translation distance increment, the four sides of the rectangular area after the first round of expansion are sequentially translated outward to obtain the rectangular area after the second round of expansion. The expansion operation is repeated until all sides of the expanded rectangular area are marked as expanded; wherein the translation direction of each side is perpendicular to each side.

[0037] The process of performing an outward translation operation on each edge is:

[0038] 1) Determine whether each edge is an edge that has been extended, and obtain a first determination result.

[0039] 2) When the first judgment result is yes, abandoning the outward translation operation on each edge.

[0040] 3) When the first judgment result is no, performing an outward translation operation on each of the edges according to the preset translation distance increment to obtain a corresponding rectangular area.

[0041] 4) Determine whether the corresponding rectangular area contains a location point whose risk value is higher than a preset risk threshold, and obtain a second determination result.

[0042] 5) When the second judgment result is yes, abandon the translation operation performed on each edge, and mark each edge as an edge whose extension is completed.

[0043] 6) When the second judgment result is no, retaining the one translation operation performed on each edge.

[0044] As an optional implementation, step 102 specifically includes:

[0045] Based on the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area, a spatiotemporal risk submap of the certain road area is generated using the obstacle vehicle potential field model. The mathematical expression of the obstacle vehicle potential field model (the potential field model of obstacle vehicle i) is as follows:

[0046]

[0047] Among them, the vector EV represents the risk that the obstacle vehicle generates to the surrounding environment; δ is any point j(x j ,y j ) is the clockwise angle formed by the direction of motion of the obstacle vehicle; a is the current acceleration of the obstacle vehicle; c v is a constant that limits the maximum risk of the vehicle, M i is the virtual mass of the target intelligent vehicle (affected by vehicle type and actual mass), is the ellipse distance.

[0048] The ellipse distance The mathematical expression is as follows:

[0049]

[0050] Among them, τ x and τ y are ellipse parameters, representing the safety margin of the obstacle vehicle in the traveling direction and the vertical direction (perpendicular to the traveling direction), respectively. They are related to the size and speed of the obstacle vehicle. The specific calculation formula is as follows:

[0051]

[0052] Among them, L and L b Respectively represent the length and width of the obstacle vehicle; x and ζ y is the adjustment parameter of the safety margin, which is determined by the safety requirements in different directions; λ is the weight coefficient related to speed, which can adjust the impact range of the risk generated by the (obstacle) vehicle in the driving direction; v i The speed of the obstructing vehicle; is the center of mass coordinate of the obstacle vehicle.

[0053] Because obstacle vehicles have different safety requirements in the direction of travel and perpendicular to the vehicle's travel, for example, it is generally more acceptable to approach an obstacle vehicle perpendicular to the vehicle's travel than to approach it in the direction of travel. Therefore, this embodiment introduces an elliptical distance instead of actual distance to model field strength.

[0054] As an optional implementation, in step 103, generating a first risk submap of the certain road area according to the road boundary line distribution information specifically includes:

[0055] According to the road boundary line distribution information, a first risk submap of the certain road area is generated using a road boundary line potential field model; the mathematical expression of the road boundary line potential field model (the potential field model of road boundary line i) is as follows:

[0056]

[0057] Among them, the vector E B Indicates the risk generated by the road boundary line; represents the distance from the i-th road boundary line to any point j(x j ,y j ) distance vector; c b A is a constant that limits the maximum risk of the road boundary; B is the field intensity control parameter, i.e. the parameter that controls the magnitude of the field intensity; D max is the affected distance threshold, that is, the affected distance threshold of the road boundary line.

[0058] As an optional implementation, step 103 generates a second risk submap for the certain road area based on the distribution information of the traversable lane lines, specifically including:

[0059] Based on the traversable lane marking distribution information, a second risk submap for the certain road area is generated using a traversable lane marking potential field model. The actual impact of traversable lane markings is defined according to traffic regulations. The mathematical expression of the traversable lane marking potential field model (the potential field model of traversable lane marking i) is as follows:

[0060]

[0061] Among them, the vector E L Indicates the risk of crossing the lane line; A L is a parameter for adjusting the peak value of the field intensity; σ is a constant that determines the growth rate of the field intensity when approaching the lane line; represents the distance from the i-th crossable lane line to any point j(x j ,y j ) is the distance vector of .

[0062] As an optional implementation, the updated optimal control model includes an objective function, an updated dynamic safety corridor boundary constraint, a vehicle system dynamics constraint, and a vehicle dynamics boundary constraint; and solving the updated optimal control model to obtain the optimal planned trajectory of the target intelligent vehicle specifically includes:

[0063] Based on the reference trajectory, the updated optimal control model is solved with the goal of minimizing the objective function to obtain the optimal planned trajectory of the target intelligent vehicle.

[0064] As an optional implementation, the mathematical expression of the objective function is as follows:

[0065]

[0066] in, represents the objective function; φ i (t) is the front wheel turning angle of the target intelligent vehicle at time t, β i (t) is the front wheel angular velocity of the target intelligent vehicle at time t, jerk i (t) is the rate of change of the acceleration of the target intelligent vehicle at time t, L W is the wheelbase of the target intelligent vehicle, is the weight coefficient of each sub-index; Smoothness expression: is the trajectory smoothing term; Comfort expression: is the passenger comfort term; t0 is the initial moment of the reference trajectory, t T is the end time of the reference trajectory.

[0067] To facilitate understanding of the above-mentioned solution of the present application, the technical solution of the present application is further explained below from the perspective of solution design.

[0068] This application addresses the shortcomings of existing technologies by proposing a method for intelligent vehicle trajectory planning based on spatiotemporal risk maps. This method uses potential field theory to model the risks of traffic elements of different states or types, and then establishes a spatiotemporal risk map based on the risk mapping. This method, combined with dynamic safety corridors, solves an optimal control problem. This method supports real-time trajectory planning for intelligent connected vehicles in highly dynamic and high-risk scenarios.

[0069] like Figure 2 As shown, the design ideas of the intelligent vehicle trajectory planning method based on the spatiotemporal risk map of this application are specifically as follows:

[0070] Step 1: Conduct risk modeling for traffic elements in different states and establish a spatiotemporal risk map based on risk mapping.

[0071] (1.1) A potential field model is constructed for the road boundary line. This potential field is defined as being generated by the road boundary line and is time-invariant. The constructed road boundary line potential field model is described above.

[0072] (1.2) A potential field model is constructed for traversable lane markings. These lane markings guide connected vehicles (e.g., the target vehicle) along the lane centerline and provide minor obstacles during lane changes. The actual impact of traversable lane markings is defined by traffic regulations. The potential field model for traversable lane markings is described previously.

[0073] (1.3) Because the safety requirements of an obstacle vehicle differ when traveling in the direction of the vehicle and when traveling perpendicularly, for example, it is generally more acceptable to approach the obstacle vehicle perpendicularly than when traveling in the direction of the vehicle. Therefore, an elliptical distance is introduced to model the field strength instead of the actual distance. The specific calculation formula for the elliptical distance is described above.

[0074] (1.4) A potential field model is established for the obstacle vehicle, taking into account its motion state and spatial position. For the specific potential field model of the obstacle vehicle, please refer to the previous article.

[0075] (1.5) Based on the road boundary (line), traversable lane line, and obstacle vehicle potential field established in steps 1.1-1.4, the risk value of each location point in the spatiotemporal risk map is calculated. Considering the independence of each part, each part of the driving environment can be locally normalized. The risk value of each location in the spatiotemporal risk map is recorded as:

[0076]

[0077] Among them, |E T | * is the total field strength at any point in space; |E B_max |Yes|E B The maximum value in |E L_max |Yes|E L The maximum value in |E V_max |Yes|E V The maximum value in |ω b 、ω l 、ω v is the proportional coefficient.

[0078] (1.6) The position (x, y), time t and risk |E T | * Match and correspond to form a spatiotemporal risk map, which is defined as:

[0079]

[0080] Spatiotemporal risk maps can quantify the risk level at each location at each moment.

[0081] Step 2: Based on the spatiotemporal risk map generated in step 1, a dynamic safety corridor is constructed according to the preset risk threshold.

[0082] (2.1) First, use dynamic programming to determine the reference trajectory (traj ref x(t), traj ref y(t),traj ref θ(t)), t∈[t0, t T]. x, y, θ are the horizontal coordinates, vertical coordinates and heading angles of the reference trajectory in the Cartesian coordinate system. t0 is the initial time of the trajectory to be planned, which is also the initial time of the reference trajectory; t T is the end time of the trajectory to be planned, which is also the end time of the reference trajectory. ref Discretized into N ref trajectory points (also called path points), N ref The set of trajectory points is represented as Track point time interval [t i , t i+1 ],

[0083] (2.2) Two consecutive path points q i With q i+1 Considered as the two diagonal points of the initial rectangle (i.e. the initial rectangular area), a rectangular initial channel is generated The initial rectangle cannot be created successfully in some cases, for example, i With q i+1 The line connecting the two is parallel to the X axis (i.e. the horizontal coordinate in the Cartesian coordinate system). i With q i+1 The initial rectangle can only be successfully created if the line connecting the two adjacent path points is not parallel to the X-axis. In addition, in order to ensure the success of the final dynamic safety corridor construction process, the risk value within the initial rectangle constructed by continuous trajectory points is required to be lower than the preset risk threshold. If either of these two conditions is not met, additional steps are required to find the initial rectangle. For example, in the case where the line connecting two adjacent path points is parallel to the X-axis, any path point can be moved a certain distance along the Y-axis (i.e., the vertical coordinate in the Cartesian coordinate system) so that the line connecting the two is no longer parallel to the X-axis. The same method can also be used to handle another situation.

[0084] (2.3) Gradually expand the initial rectangle In the Cartesian coordinate system, based on the initial rectangle, the rectangle is expanded step by step in the order of +y, +x, -y, -x with a step distance Δd (i.e., the preset translation distance increment). Using the preset risk threshold R thr As a condition for the completion of the expansion. Specifically, if the risk in a certain direction is higher than R in the Kth step thr , then expansion in this direction is prohibited, and from step K+1 onwards, only expansion in the remaining directions will be performed in the specified order. When all directions are prohibited, expansion stops.

[0085] (2.4) Extensions that are not disabled are merged into the local security corridor (i.e. the expanded rectangular area i), is a rectangle, The upper and lower boundaries in the x-axis and y-axis directions respectively.

[0086] (2.5) All local safety corridors Along the reference trajectory traj ref Combined to form a dynamic safety corridor.

[0087] Step 3: Consider trajectory smoothness and passenger comfort to construct an optimal control problem and solve it to generate a trajectory within the corridor that meets the requirements.

[0088] (3.1) The objective function considers two aspects: trajectory smoothness and passenger comfort. Trajectory smoothness refers to the smoothness of trajectory changes during motion and is described as curvature-dependent. Passenger comfort is set in relation to the control variable, encouraging the control variable to approach zero, which means reducing drastic changes or vibrations. The definition of the objective function is described above.

[0089] (3.2) The target intelligent vehicle travels within the dynamic safety corridor, ensuring that it can safely avoid all dynamic and static obstacles. Considering the geometric shape of the target intelligent vehicle, it is necessary to ensure that the entire rectangular body of the target intelligent vehicle is within the boundary of the dynamic safety corridor. A double circle model is used to describe the shape of the target intelligent vehicle, with two circles evenly covering the body. The centers of the two circles are and is the quartile point along the axle. The center of the circle is solved using the following formula:

[0090]

[0091]

[0092] Among them, θ i (t) represents the heading angle of the target intelligent vehicle at time t; α r The coefficients defined for the geometric parameters of the target intelligent vehicle, r is the radius of the circle, which can be obtained by the size parameter L w , L r , L f To calculate. In addition, L w is the wheelbase, L f is the front overhang distance, L r is the rear overhang distance, L b is the vehicle width; x i (t) and y i (t) is the coordinate of the center of mass of the target intelligent vehicle at time t. The center of mass of the target intelligent vehicle is the center position of the line connecting the centers of its two rear wheels.

[0093] (3.3) The dynamic safety corridor boundary constraint is established and used as the collision constraint in the optimal control problem, which is expressed as:

[0094]

[0095] The above collision constraints ensure that the target intelligent vehicle corresponding to time t will not exceed the local safety corridor the border.

[0096] (3.4) During trajectory planning, each variable must follow (not violate) the evolution relationship of the vehicle kinematics law, thus establishing the vehicle system dynamics constraints, which can be expressed as:

[0097]

[0098] Among them, (x i (t), y i (t)) represents the position coordinates of the target intelligent vehicle; v i (t) represents the vehicle speed along the longitudinal axis of the vehicle body; θ i (t),φ i (t) respectively represent the heading angle and front wheel turning angle in the Cartesian coordinate system; a i (t) represents the acceleration along the longitudinal axis of the vehicle; jerk i (t) represents the rate of change of acceleration; β i (t) represents the angular velocity of the front wheel. χ i (t) is the state variable of the target intelligent vehicle at time t; U i (t) is the control variable of the target intelligent vehicle at time t.

[0099] (3.5) The above χ i (t) and U i (t) has upper and lower bounds, reflecting the physical or mechanical limitations related to vehicle kinematics, and thus establishes the vehicle dynamics boundary constraints, expressed as:

[0100]

[0101] Among them, φ i,min 、φ i,max Represents φ i The upper and lower bounds of (t); β i,min , β i,max Represents β i The upper and lower boundaries of (t); v i,min 、v i,max Indicates v i (t) the upper and lower boundaries; a i,min 、a i,max Indicates a i (t) upper and lower boundaries; jerk i,min , jerk i,max Indicates jerki The upper and lower bounds of (t).

[0102] (3.6) Taking into account the objective function, collision constraints, vehicle system dynamics constraints, and vehicle dynamics boundary constraints, an optimal control model is constructed, which is expressed as:

[0103]

[0104]

[0105] The optimal planning trajectory is solved through the above optimal control model.

[0106] (3.7) Taking the reference trajectory as the initial iteration value, the optimal control model is solved to output the optimal planning trajectory.

[0107] The present application also provides an application scenario, which applies the above-mentioned intelligent vehicle trajectory planning method based on the spatiotemporal risk map. Specifically: the intelligent vehicle trajectory planning method based on the spatiotemporal risk map provided in this embodiment can be applied in an autonomous driving scenario. The autonomous driving scenario includes a surrounding road condition information acquisition link, a trajectory planning link, and an autonomous driving link; the road boundary line distribution information, the traversable lane line distribution information, and the obstacle vehicle information enter the trajectory planning link from the surrounding road condition information acquisition link, and the trajectory planning link generates the optimal planning trajectory based on the road boundary line distribution information, the traversable lane line distribution information, and the obstacle vehicle information, and the autonomous driving link drives the target intelligent vehicle based on the optimal planning trajectory. The intelligent vehicle trajectory planning method based on the spatiotemporal risk map provided in this embodiment belongs to the trajectory planning link. Specifically, in the trajectory planning link, trajectory planning for a period of time in the future is performed based on the road boundary line distribution information, the traversable lane line distribution information, and the obstacle vehicle information.

[0108] This application provides a new trajectory planning method for intelligent connected vehicles, which can uniformly describe different traffic elements in complex environments, thereby integrating traffic scene information and reducing the impact of heterogeneous element types, combinations, and the motion states of obstacle vehicles on the real-time and quality of planned trajectory generation.

[0109] Specifically, this application has the following advantages:

[0110] (1) The intelligent vehicle trajectory planning method based on the spatiotemporal risk map proposed in this application relies on the risk space during the planning process. By quantifying and integrating the risk factors in the environment, it can more flexibly respond to dynamic changes in complex traffic situations and achieve the transformation from "spatial safety" to "risk safety".

[0111] (2) The potential field-based spatiotemporal risk map generation method proposed in this application can uniformly describe complex traffic environments (heterogeneous traffic elements) and map environmental information to risk space, so that complex environmental information can be uniformly described and evaluated.

[0112] (3) This application proposes a method for constructing a dynamic safety corridor. The dynamic safety corridor is generated based on a spatiotemporal risk map. Unlike corridors that guarantee a free space in the environment, the dynamic safety corridor constructed by the method of this application can ensure that the risk within the corridor is lower than a preset risk threshold over a period of time in the future. Moreover, by adjusting the preset risk threshold, personalized driving needs can also be effectively addressed.

[0113] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store trajectory planning related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a method for intelligent vehicle trajectory planning based on a spatiotemporal risk map.

[0114] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0115] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0116] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0117] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0118] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0119] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0120] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An intelligent vehicle trajectory planning method based on spatiotemporal risk map, characterized in that: The intelligent vehicle trajectory planning method based on the spatiotemporal risk map includes: Obtaining road boundary line distribution information, traversable lane line distribution information, and obstacle vehicle information in a certain road area around the target intelligent vehicle, and predicting the movement trajectory of the obstacle vehicle in the certain road area based on the obstacle vehicle information; generating a spatiotemporal risk submap of the certain road area based on the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area; generating a first risk submap and a second risk submap for the certain road area based on the road boundary line distribution information and the crossable lane line distribution information respectively; determining a spatiotemporal risk map for the certain road area based on the spatiotemporal risk submap, the first risk submap, and the second risk submap; Using a dynamic programming algorithm, a reference trajectory of the target intelligent vehicle in the certain road area is obtained, and a dynamic safety corridor is generated based on the reference trajectory and the spatiotemporal risk map; According to the dynamic safety corridor, the dynamic safety corridor boundary constraints in the optimal control model are updated, and the updated optimal control model is solved to obtain the optimal planning trajectory of the target intelligent vehicle.

2. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 1 is characterized in that: Generating a dynamic safety corridor based on the reference trajectory and the spatiotemporal risk map, specifically comprising: Determine a preset number of initial rectangular areas based on all adjacent discrete trajectory points on the reference trajectory; the preset number is equal to the number of pairs of all adjacent discrete trajectory points; each pair of adjacent discrete trajectory points is a diagonal point of a corresponding initial rectangular area; Perform several rounds of expansion on each initial rectangular area to obtain the expanded rectangular area corresponding to each initial rectangular area; Determining a dynamic safety corridor based on a preset number of the expanded rectangular areas; the dynamic safety corridor is composed of the preset number of the expanded rectangular areas; The process of several rounds of expansion of each initial rectangular area is as follows: According to a preset translation distance increment, the four sides of the initial rectangular area are sequentially translated outward once to obtain a rectangular area after a first round of expansion. Then, according to the preset translation distance increment, the four sides of the rectangular area after the first round of expansion are sequentially translated outward once to obtain a rectangular area after a second round of expansion. The expansion operation is repeated until all sides of the expanded rectangular area are marked as expanded; wherein the translation direction of each side is perpendicular to each side; The process of performing an outward translation operation on each edge is: Determine whether each edge is an edge that has been extended, and obtain a first determination result; When the first judgment result is yes, abandoning the outward translation operation on each edge; When the first judgment result is no, performing an outward translation operation on each of the edges according to the preset translation distance increment to obtain a corresponding rectangular area; Determine whether the corresponding rectangular area contains a location point with a risk value higher than a preset risk threshold, and obtain a second determination result; When the second judgment result is yes, abandoning the translation operation performed on each edge, and marking each edge as an edge whose extension is completed; When the second judgment result is no, the one translation operation performed on each edge is retained.

3. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 1 is characterized in that: Generating a spatiotemporal risk submap of the certain road area according to the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area specifically includes: Based on the obstacle vehicle information and the movement trajectory of the obstacle vehicle in the certain road area, a spatiotemporal risk submap of the certain road area is generated using an obstacle vehicle potential field model; the mathematical expression of the obstacle vehicle potential field model is as follows: Among them, the vector E V represents the risk that the obstacle vehicle generates to the surrounding environment; δ is any point j(x j ,y j ) is the clockwise angle formed by the direction of motion of the obstacle vehicle; a is the current acceleration of the obstacle vehicle; c v is a constant, M i is the virtual mass of the target intelligent vehicle, is the ellipse distance; The ellipse distance The mathematical expression is as follows: Among them, τ x and τ y are ellipse parameters, representing the safety margin of the obstacle vehicle in the driving direction and the vertical direction respectively. The calculation formula is as follows: t y =ζ y L b ; Among them, L and L b Respectively represent the length and width of the obstacle vehicle; x and ζ y is the adjustment parameter; λ is the weight coefficient; v i is the speed of the obstructing vehicle; is the center of mass coordinate of the obstacle vehicle.

4. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 1 is characterized in that: According to the road boundary line distribution information, a first risk sub-map of the certain road area is generated, specifically including: According to the road boundary line distribution information, a first risk submap of the certain road area is generated using a road boundary line potential field model; the mathematical expression of the road boundary line potential field model is as follows: Among them, the vector E B Indicates the risk generated by the road boundary line; represents the distance from the i-th road boundary line to any point j(x j ,y j ) distance vector; c b is a constant; A B is the field intensity control parameter; D max is the distance threshold.

5. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 1 is characterized in that: Generating a second risk submap for the certain road area based on the crossable lane line distribution information specifically includes: Based on the traversable lane line distribution information, a second risk submap of the certain road area is generated using a traversable lane line potential field model. The mathematical expression of the traversable lane line potential field model is as follows: Among them, the vector E L Indicates the risk of crossing the lane line; A L is the parameter for adjusting the peak value of field intensity; σ is a constant; represents the distance from the i-th crossable lane line to any point j(x j ,y j ) is the distance vector of .

6. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 1 is characterized in that: The updated optimal control model includes an objective function, an updated dynamic safety corridor boundary constraint, a vehicle system dynamics constraint, and a vehicle dynamics boundary constraint; and solving the updated optimal control model to obtain the optimal planning trajectory of the target intelligent vehicle specifically includes: Based on the reference trajectory, the updated optimal control model is solved with the goal of minimizing the objective function to obtain the optimal planned trajectory of the target intelligent vehicle.

7. The intelligent vehicle trajectory planning method based on spatiotemporal risk map according to claim 6 is characterized in that: The mathematical expression of the objective function is as follows: in, represents the objective function; φ i (t) is the front wheel turning angle of the target intelligent vehicle at time t, β i (t) is the front wheel angular velocity of the target intelligent vehicle at time t, jerk i (t) is the rate of change of the acceleration of the target intelligent vehicle at time t, L W is the wheelbase of the target intelligent vehicle, is the weight coefficient of each item; Smoothness expression: is the trajectory smoothing term; Comfort expression: is the passenger comfort term; t0 is the initial moment of the reference trajectory, t T is the end time of the reference trajectory.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent vehicle trajectory planning method based on a spatiotemporal risk map according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent vehicle trajectory planning method based on the spatiotemporal risk map according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the intelligent vehicle trajectory planning method based on the spatiotemporal risk map according to any one of claims 1 to 7 is implemented.

Images