Trajectory optimization methods, apparatus, electronic devices, computer-readable storage media, and computer program products

Abstract

This application provides a method, apparatus, electronic device, computer program product, and computer-readable storage medium. The method includes: detecting the state of a target vehicle to obtain its lateral motion state, and generating a first driving trajectory for the target vehicle based on its lateral motion state; if the first driving trajectory exceeds the driving boundary of the target vehicle, correcting the lateral motion state of the target vehicle based on its lateral motion state, the first driving trajectory, and the driving boundary to obtain a corrected lateral motion state; and generating a second driving trajectory for the target vehicle based on the corrected lateral motion state to control the target vehicle to move based on the second driving trajectory. This application improves the safety and feasibility of driving trajectories.

Description

Technical Field

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

[0002] During the operation of autonomous vehicles, it is necessary to plan the future driving trajectory of the autonomous vehicles in advance. When the autonomous vehicles approach the boundary, the driving trajectory of the autonomous vehicles may exceed the boundary, causing the autonomous vehicles to be unable to move normally. Summary of the Invention

[0003] This application provides a trajectory optimization method, apparatus, computer-readable storage medium, and computer program product, which can improve the safety and feasibility of driving trajectories.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] This application provides a trajectory optimization method, the method comprising:

[0006] The target vehicle is subjected to state detection to obtain its lateral motion state, and a first driving trajectory of the target vehicle is generated based on its lateral motion state.

[0007] If the first driving trajectory exceeds the driving boundary of the target vehicle, the lateral movement state of the target vehicle is corrected based on the lateral movement state of the target vehicle, the first driving trajectory, and the driving boundary to obtain the corrected lateral movement state.

[0008] Based on the corrected lateral motion state, a second driving trajectory of the target vehicle is generated to control the target vehicle to move based on the second driving trajectory.

[0009] This application provides a trajectory optimization device, including:

[0010] The detection module is used to perform state detection on the target vehicle, obtain the lateral motion state of the target vehicle, and generate the first driving trajectory of the target vehicle based on the lateral motion state of the target vehicle.

[0011] The correction module is used to correct the lateral motion state of the target vehicle based on the lateral motion state of the target vehicle, the first driving trajectory, and the driving boundary if the first driving trajectory exceeds the driving boundary of the target vehicle, so as to obtain the corrected lateral motion state.

[0012] The generation module is used to generate a second driving trajectory of the target vehicle based on the corrected lateral motion state, so as to control the target vehicle to move based on the second driving trajectory.

[0013] In some embodiments, the detection module is further configured to acquire the position of the target vehicle and the motion state of the target vehicle; map the position of the target vehicle based on a natural coordinate system to obtain a first lateral position of the target vehicle, and map the motion state of the target vehicle based on the natural coordinate system to obtain a lateral velocity and a lateral acceleration of the target vehicle; and combine the first lateral position, the lateral velocity, and the lateral acceleration of the target vehicle to form the lateral motion state of the target vehicle.

[0014] In some embodiments, the correction module is further configured to: determine a first longitudinal position corresponding to a first lateral position of the target vehicle; determine a second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary, wherein the intersection point is the point where the first driving trajectory intersects the driving boundary; determine a second longitudinal position corresponding to the second lateral position of the driving boundary; and, based on the first longitudinal position, the second longitudinal position, the first lateral position of the target vehicle, and the second lateral position, correct the lateral velocity of the target vehicle to obtain a corrected lateral velocity, and combine the first lateral position of the target vehicle and the corrected lateral velocity to form a corrected lateral motion state.

[0015] In some embodiments, the correction module is further configured to subtract the second lateral position from the first lateral position of the target vehicle to obtain a first difference; subtract the second longitudinal position from the first longitudinal position to obtain a second difference; and determine a corrected lateral velocity based on the first difference and the second difference, wherein the corrected lateral velocity is positively correlated with the first difference and negatively correlated with the second difference.

[0016] In some embodiments, the correction module is further configured to perform boundary correction on the driving boundary based on the boundary safety distance to obtain the corrected driving boundary; and determine the second lateral position corresponding to the intersection point of the first driving trajectory and the corrected driving boundary.

[0017] This application provides an electronic device, the electronic device comprising:

[0018] Memory is used to store executable instructions or computer programs.

[0019] The processor, when executing computer-executable instructions or computer programs stored in the memory, implements the method provided in the embodiments of this application.

[0020] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the trajectory optimization method provided in this application when executed by a processor.

[0021] This application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the trajectory optimization method provided in this application.

[0022] The embodiments of this application have the following beneficial effects:

[0023] The system performs state detection on the target vehicle to obtain its lateral movement state. Based on this lateral movement state, a first driving trajectory is generated. Generating the first driving trajectory using the real-time state of the target vehicle improves its accuracy and timeliness. If the first driving trajectory exceeds the target vehicle's driving boundary, the lateral movement state is corrected based on the target vehicle's lateral movement state, the first driving trajectory, and the driving boundary, resulting in a corrected lateral movement state. Based on the corrected lateral movement state, a second driving trajectory is generated to control the target vehicle's movement along this second trajectory. The corrected lateral movement state allows for the generation of a second driving trajectory that conforms to the current road conditions, enabling the target vehicle to move along this second driving trajectory. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the architecture of the trajectory optimization system 100 provided in an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of the structure of the electronic device 500 provided in the embodiments of this application;

[0026] Figure 3A This is a first flowchart illustrating the trajectory optimization method provided in this application embodiment;

[0027] Figure 3B This is a schematic diagram of the second process of the trajectory optimization method provided in the embodiments of this application;

[0028] Figure 4 This is a schematic diagram of the first driving trajectory provided in an embodiment of this application;

[0029] Figure 5 This is a schematic diagram of the second driving trajectory provided in the embodiments of this application.

[0030] It should be noted that the terms "first" and "second" mentioned above are only used to distinguish between different options and do not represent the degree of superiority or inferiority of the options or their priority in the implementation process. Detailed Implementation

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

[0032] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

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

[0034] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0035] Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit this application.

[0036] In the implementation of this application, the collection and processing of relevant data should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0037] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0038] 1) Target Vehicle: The target vehicle can be an autonomous vehicle, an intelligent transportation tool that can autonomously perceive its environment, plan its route, and drive safely without human driver intervention by incorporating advanced sensors, controllers, actuators, and artificial intelligence algorithms. An autonomous vehicle consists of an environmental perception system, a decision-making and planning system, and a control and execution system. The environmental perception system is responsible for collecting information about the surrounding environment, including cameras (identifying traffic lights, lane lines, and pedestrians), LiDAR (which constructs a 3D environmental model using laser point clouds), millimeter-wave radar (unaffected by rain or fog, detecting vehicle speed and distance), and ultrasonic radar (for short-range detection). The system includes obstacle detection (e.g., when parking) and positioning devices; the decision-making and planning system can make driving decisions and plan routes based on perceived information and targets (e.g., destination). Specifically, it can determine whether to accelerate, decelerate, change lanes, overtake, or avoid pedestrians (e.g., decide to stop when encountering a red light), and plan the optimal trajectory from the current location to the destination, considering safety (avoiding obstacles), legality (not violating traffic rules), and efficiency (shortest time or distance); the control execution system can translate decision commands into actual vehicle actions, specifically by adjusting the throttle, brakes, steering wheel, and gear shifting through the electronic control unit (ECU).

[0039] 2) Lateral Motion State: This refers to the lateral motion state and related characteristics of the target vehicle during its movement, perpendicular to the direction of travel (i.e., laterally or sideways). It primarily reflects the vehicle's position, attitude, and movement trend in the left-right direction, including lateral position, lateral velocity, lateral acceleration, yaw angle, and yaw rate. Lateral position is the lateral distance between the vehicle's center of gravity (or reference point, such as the front wheel axle) and the target path (such as the lane centerline), used to measure whether the vehicle is traveling along the desired path. For example, if the distance deviating from the lane line exceeds a threshold, it may trigger a lane departure warning or automatic correction. Lateral velocity is the speed of the target vehicle's lateral movement, used to reflect the speed of the vehicle's lateral motion. Excessive lateral velocity may lead to… Sideslip (especially on wet surfaces) is a key indicator for judging vehicle stability; lateral acceleration is the acceleration generated by the target vehicle along the direction perpendicular to the forward direction (lateral or sideways) during driving, and is a key indicator for measuring the safety, stability, and comfort of autonomous vehicles; yaw angle is the angle between the vehicle's longitudinal axis (forward and backward) and the tangent direction of the target path, mainly reflecting the vehicle's heading deviation. For example, if the yaw angle is too large when turning, it may cause the vehicle to "cut corners" or deviate from the lane; yaw rate is the angular velocity of the vehicle rotating around an axis perpendicular to the ground (vertical axis), reflecting the speed of the vehicle's turn. Excessive yaw rate may cause the vehicle to lose control (such as fishtailing), and is a core monitoring parameter of the vehicle stability control system.

[0040] 3) Driving Boundaries: These refer to the set of spatial ranges and movement limits that a target vehicle can reach under specific scenarios, based on its own physical performance, road environment constraints, traffic rules, and safety requirements. They mainly refer to the range that the target vehicle can occupy in physical space, and can include road geometric boundaries, obstacle boundaries, and traffic rule boundaries. Road geometric boundaries can include lane lines (left and right boundaries), shoulders, medians, guardrails, etc., defining the lateral range within which a vehicle can legally drive (e.g., a typical lane is about 3.5 meters wide, and vehicles must remain within the lane lines or within the allowed offset range). Obstacle boundaries can include the spatial occupancy of static obstacles (such as streetlights, walls, and construction areas) and dynamic obstacles (such as other vehicles, pedestrians, and cyclists), requiring vehicles to maintain a safe distance (e.g., minimum lateral safety distance, longitudinal following distance). Traffic rule boundaries can include prohibited areas (such as oncoming lanes and pedestrian crossings), intersection stop lines, no-stopping areas, etc., further restricting the spatial distribution of vehicles through traffic rules.

[0041] 4) Jeep acceleration: Maximum jeep acceleration refers to the maximum rate of change of acceleration with respect to time during an object's motion. It is a key indicator for measuring the impact of motion, and its unit is meters per second squared. Jeep acceleration directly affects the human body's perception of motion. Excessive jeep acceleration can cause violent shaking of the vehicle body (such as the "jerkiness" when suddenly accelerating / braking, or the "swaying" when suddenly turning the steering wheel), causing discomfort or even motion sickness among passengers. Maximum jeep acceleration is limited (e.g., passenger cars are typically set at ±5 to ±10 m / s²). 3 Acceleration can significantly improve ride comfort; however, drastic acceleration changes can impact the vehicle's transmission system, suspension, brakes, and other components, increasing wear and the risk of failure. Controlling maximum acceleration can extend vehicle lifespan; in autonomous driving trajectory planning, maximum acceleration is an important constraint. For example, the generated trajectory must ensure that the acceleration does not exceed a threshold to guarantee that the vehicle can be smoothly tracked by actuators (such as accelerator, brake, and steering motors).

[0042] This application provides a trajectory optimization method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the safety and feasibility of driving trajectories. The following describes exemplary applications of the electronic devices provided in this application. The devices provided in this application can be implemented as various types of terminals such as laptops, tablets, desktop computers, set-top boxes, smartphones, smart speakers, smartwatches, smart TVs, and vehicle terminals, or as servers. Exemplary applications when the device is implemented as a terminal will be described below.

[0043] See Figure 1 , Figure 1This is a schematic diagram of the architecture of the trajectory optimization system 100 provided in the embodiment of this application. In order to support a trajectory optimization application, the sensor 400 is connected to the terminal 200 through the internal circuit 300.

[0044] Sensor 400 is used to collect data on the target vehicle, including its position, speed, and distance from the boundary. The collected data is then transmitted to terminal 200. Terminal 200 uses sensor 400 to perform state detection on the target vehicle, obtaining its lateral motion state. Based on this lateral motion state, it generates a first driving trajectory for the target vehicle. If the first driving trajectory exceeds the driving boundary, the lateral motion state is corrected based on the target vehicle's lateral motion state, the first driving trajectory, and the driving boundary, resulting in a corrected lateral motion state. Based on the corrected lateral motion state, a second driving trajectory is generated to control the target vehicle's movement along the second driving trajectory.

[0045] See Figure 2 , Figure 2 This is a schematic diagram of the structure of the electronic device 500 provided in the embodiments of this application, with the electronic device 500 as an example. Figure 1 Taking terminal 200 as an example, Figure 2 The illustrated electronic device 500 includes at least one processor 510, a memory 550, at least one network interface 520, and a user interface 530. The various components in the electronic device 500 are coupled together via a bus system 540. It is understood that the bus system 540 is used to implement communication between these components. In addition to a data bus, the bus system 540 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 2 The general labeled all buses as Bus System 540.

[0046] The processor 510 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0047] User interface 530 includes one or more output devices 531 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 530 also includes one or more input devices 532, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0048] The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 550 may optionally include one or more storage devices physically located away from the processor 510.

[0049] The memory 550 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 550 described in this application embodiment is intended to include any suitable type of memory.

[0050] In some embodiments, memory 550 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0051] Operating system 551 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks;

[0052] The network communication module 552 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 520, exemplary network interfaces 520 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0053] Presentation module 553 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 531 (e.g., a display screen, a speaker, etc.) associated with user interface 530;

[0054] The input processing module 554 is used to detect and translate one or more user inputs or interactions from one or more input devices 532.

[0055] In some embodiments, the apparatus provided in this application can be implemented in software. Figure 2 A trajectory optimization device 555 stored in memory 550 is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a detection module 5551, a correction module 5552, and a generation module 5553. These modules are logically linked and can therefore be arbitrarily combined or further separated according to their implemented functions. The functions of each module will be described below.

[0056] In other embodiments, the apparatus provided in this application can be implemented in hardware. As an example, the apparatus provided in this application can be a processor in the form of a hardware decoding processor, which is programmed to execute the trajectory optimization method provided in this application. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0057] The trajectory optimization method provided in the embodiments of this application will be described below. As mentioned above, the electronic device implementing the trajectory optimization method in the embodiments of this application can be a terminal deployed in an unmanned vehicle. Therefore, the executing entity of each step will not be described again below.

[0058] See Figure 3A , Figure 3A This is a first flowchart illustrating the trajectory optimization method provided in this application embodiment, which will be combined with... Figure 3A The steps shown are explained.

[0059] In step 101, the target vehicle is subjected to state detection to obtain the lateral motion state of the target vehicle, and the first driving trajectory of the target vehicle is generated based on the lateral motion state of the target vehicle.

[0060] As an example, the target vehicle could be an autonomous vehicle, an intelligent transportation tool that, by incorporating advanced sensors, controllers, actuators, and artificial intelligence algorithms, can autonomously perceive its environment, plan its route, and drive safely without human driver intervention. An autonomous vehicle consists of an environmental perception system, a decision-making and planning system, and a control and execution system. The environmental perception system is responsible for collecting information about the surrounding environment, including cameras (identifying traffic lights, lane lines, and pedestrians), LiDAR (which constructs a 3D environmental model using laser point clouds), millimeter-wave radar (unaffected by rain or fog, detecting vehicle speed and distance), and ultrasonic radar (for short-range detection). The system includes obstacle detection (e.g., when parking) and positioning devices; the decision-making and planning system can make driving decisions and plan routes based on perceived information and targets (e.g., destination). Specifically, it can determine whether to accelerate, decelerate, change lanes, overtake, or avoid pedestrians (e.g., decide to stop when encountering a red light), and plan the optimal trajectory from the current location to the destination, considering safety (avoiding obstacles), legality (not violating traffic rules), and efficiency (shortest time or distance); the control execution system can translate decision commands into actual vehicle actions, specifically by adjusting the throttle, brakes, steering wheel, and gear shifting through the electronic control unit (ECU).

[0061] As an example, lateral motion status can refer to the motion state and related characteristics of a target vehicle along a direction perpendicular to its forward direction (i.e., lateral or sideways) during its movement. It primarily reflects the vehicle's position, attitude, and motion trend in the left-right direction, including lateral position, lateral velocity, lateral acceleration, yaw angle, and yaw rate. Lateral position is the lateral distance between the vehicle's center of gravity (or reference point, such as the front wheel axle) and the target path (such as the lane centerline), used to measure whether the vehicle is traveling along the desired path. For example, if the distance deviating from the lane line exceeds a threshold, it may trigger a lane departure warning or automatic correction. Lateral velocity is the target vehicle's lateral movement speed, used to reflect the speed of the vehicle's lateral movement. Excessive lateral velocity... Lateral acceleration, which can cause skidding (especially on wet surfaces), is a key indicator for assessing vehicle stability. Lateral acceleration, the acceleration of a vehicle along a direction perpendicular to its forward motion (lateral or sideways), is a crucial indicator for evaluating the safety, stability, and comfort of autonomous vehicles. Yaw angle, the angle between the vehicle's longitudinal axis (forward / backward direction) and the tangent to the target path, primarily reflects the vehicle's heading deviation; for example, excessive yaw angle during a turn can cause the vehicle to "cut corners" or veer off course. Yaw velocity, the angular velocity of a vehicle rotating about an axis perpendicular to the ground (vertical axis), reflects the speed of a turn; excessive yaw velocity can lead to loss of control (such as fishtailing) and is a core monitoring parameter of the vehicle stability control system.

[0062] In some embodiments, the state detection of the target vehicle in step 101 to obtain the lateral motion state of the target vehicle can be implemented by the following technical solution: obtaining the position and motion state of the target vehicle; mapping the position of the target vehicle based on a natural coordinate system to obtain the lateral position of the target vehicle, and mapping the motion state of the target vehicle based on the natural coordinate system to obtain the lateral velocity and lateral acceleration of the target vehicle; combining the lateral position, lateral velocity, and lateral acceleration of the target vehicle to form the lateral motion state of the target vehicle.

[0063] As an example, the position and motion state of the target vehicle can be collected by sensors mounted on the target vehicle. The motion state of the target vehicle can include the target vehicle's speed, acceleration, etc.

[0064] As an example, we first need to define a reference path (such as the center line of a lane) and parameterize its geometric features. For any point of arc length s on the reference path: Cartesian coordinates: P_r(s) = [x_r(s), y_r(s)]; heading angle (angle between the tangent and the x-axis): θ_r(s) = arctan(dy_r / dx_r); curvature (derivative of heading angle with respect to arc length): κ(s) = dθ_r(s) / ds (describes the curvature of the path); rate of change of curvature: dκ / ds (optional, used for higher-order derivative transformation).

[0065] For the coordinates of the target vehicle's position, the longitudinal coordinate s can be the arc length from the starting point to the "projection point of the vehicle position on the reference path" on the reference path; the lateral coordinate d can be the directed distance from the vehicle position to the reference path (along the normal vector direction, positive on the left and negative on the right).

[0066] For the target vehicle's speed, define the tangential unit vector (along the direction of increasing s): t(s) = [cosθ_r(s), sinθ_r(s)]; the normal unit vector (perpendicular to the tangent, pointing in the positive direction of d): n(s) = [-sinθ_r(s), cosθ_r(s)]; determine the projection of speed v in the tangential direction (speed along the reference path) to obtain the longitudinal speed, and determine the projection of speed v in the normal direction (speed perpendicular to the reference path) to obtain the lateral speed;

[0067] For the acceleration of the target vehicle, acceleration is the derivative of velocity with respect to time, therefore the longitudinal acceleration a s =dv s / dt; Lateral acceleration a d =dv d / dt.

[0068] The above method can map the position, velocity, and acceleration of the target vehicle into the natural coordinate system, thereby accurately obtaining the lateral motion state of the target vehicle in the natural coordinate system.

[0069] As an example, the first driving trajectory can be a trajectory generated with maximum jerk as a constraint. Maximum jerk refers to the maximum rate of change of acceleration with respect to time during the motion of an object. It is a key indicator for measuring the impact of motion, and its unit is meters per second squared. Jerk directly affects the human body's perception of motion. Excessive jerk can cause violent shaking of the vehicle body (such as the "jerkiness" when suddenly stepping on the accelerator / brake, or the "swaying" when suddenly turning the steering wheel), causing discomfort or even motion sickness among passengers. By limiting the maximum jerk (such as the setting of ±5 to ±10 m / s² for passenger cars), 3 Acceleration can significantly improve ride comfort; however, drastic acceleration changes can impact the vehicle's transmission system, suspension, brakes, and other components, increasing wear and the risk of failure. Controlling maximum acceleration can extend vehicle lifespan; in autonomous driving trajectory planning, maximum acceleration is an important constraint. For example, the generated trajectory must ensure that the acceleration does not exceed a threshold to guarantee that the vehicle can be smoothly tracked by actuators (such as accelerator, brake, and steering motors).

[0070] As an example, the lateral position, lateral velocity, and lateral acceleration of the target vehicle can be input into the optimizer. Using the maximum jerk as a constraint, the optimizer generates leftward and rightward movement trajectories for the target vehicle. Finally, the leftward and rightward movement trajectories are combined into a first movement trajectory. The optimizer generates the first movement trajectory as follows: the movement trajectory must simultaneously describe the geometric path (the spatial path of the vehicle) and the time allocation (velocity / time at each point on the path). Common representation methods include: parametric curves, such as polynomials (quintic polynomials, cubic polynomials), spline curves (B-splines, Bézier curves), etc., defining the trajectory shape through coefficient parameters; and discrete point sequences, splitting the trajectory into multiple discrete waypoints (e.g., (x0, y0, t0), (x1, y1, t1), ..., (x...). n ,yn,t n The coordinates and time of the waypoints are the optimization variables; combined with vehicle dynamics, the trajectory is represented by the time series of state variables such as the lateral position, lateral velocity and lateral acceleration of the target vehicle.

[0071] The optimizer must ensure that the generated trajectory satisfies both hard constraints (which cannot be violated, such as safety and physical limitations) and soft constraints (which should be satisfied as much as possible, such as comfort preferences). Hard constraints can include vehicle dynamics constraints, environmental and safety constraints, and boundary condition constraints. Vehicle dynamics constraints are determined by the physical performance of the target vehicle and must avoid exceeding the actuator's capabilities. These constraints include speed constraints (e.g., ≤50km / h in urban areas, ≤120km / h on highways) and acceleration constraints (e.g., longitudinal acceleration ≤±3m / s²). 2 Lateral acceleration ≤ ±2m / s 2 To prevent rollover, jerk constraints (e.g., j≤±10m / s²) are applied. 3 To reduce impact and improve comfort, soft constraints can include trajectory smoothness, path efficiency, and reference path fit. Trajectory smoothness can include minimizing Jerk integral to reduce vehicle sway; path efficiency can include minimizing total trajectory length or travel time; and reference path fit can include minimizing deviation from the lane centerline to reduce unnecessary lane changes.

[0072] The objective function is the "evaluation metric" of the optimizer. By weighted combination of multiple optimization objectives, a multi-objective problem is transformed into a single-objective optimization. If the objective function is a convex function and the constraints are a convex set (such as linear constraints + quadratic objective function), it can be solved efficiently by interior point method or gradient descent method (good real-time performance). If the problem is non-convex due to obstacle constraints, nonlinear dynamics, etc. (such as nonlinear distance constraints during obstacle avoidance), numerical methods are required to approximate the solution and obtain the first driving trajectory.

[0073] In step 102, if the first driving trajectory exceeds the driving boundary of the target vehicle, the lateral movement state of the target vehicle is corrected based on the lateral movement state of the target vehicle, the first driving trajectory, and the driving boundary to obtain the corrected lateral movement state.

[0074] As an example, driving boundaries can refer to the set of spatial ranges and movement limits that a target vehicle can reach under specific scenarios, based on its own physical performance, road environment constraints, traffic rules, and safety requirements. It mainly refers to the range that the target vehicle can occupy in physical space, which can include road geometric boundaries, obstacle boundaries, and traffic rule boundaries. Road geometric boundaries can include lane lines (left and right boundaries), shoulders, medians, guardrails, etc., defining the lateral range within which vehicles can legally drive (e.g., a typical lane is about 3.5 meters wide, and vehicles must remain within the lane lines or within the allowed offset range). Obstacle boundaries can include the spatial occupancy of static obstacles (such as streetlights, walls, and construction areas) and dynamic obstacles (such as other vehicles, pedestrians, and cyclists), with vehicles needing to maintain a safe distance (such as minimum lateral safety distance and longitudinal following distance). Traffic rule boundaries can include prohibited areas (such as oncoming lanes and pedestrian crossings), intersection stop lines, no-stopping areas, etc., further restricting the spatial distribution of vehicles through traffic rules.

[0075] As an example, a way to determine whether the first driving trajectory exceeds the driving boundary of the target vehicle is to determine that the driving trajectory exceeds the driving boundary if the maximum lateral distance of the left-turning driving trajectory in the first driving trajectory is less than the right boundary of the driving boundary, or the right-turning driving trajectory is less than the left boundary of the driving boundary.

[0076] In some embodiments, the lateral motion state of the target vehicle includes the first lateral position and the lateral velocity of the target vehicle. Step 102 corrects the lateral motion state of the target vehicle based on its lateral motion state, the first driving trajectory, and the driving boundary. The corrected lateral motion state can be obtained through methods such as... Figure 3B Steps 1021 to 1024 shown are implemented as follows:

[0077] In step 1021, the first longitudinal position corresponding to the first lateral position of the target vehicle is determined.

[0078] As an example, the first lateral position of the target vehicle can be the first lateral position corresponding to the centroid of the target vehicle. The position of the target vehicle is composed of the first lateral position and the first longitudinal position. The first longitudinal position corresponding to the first lateral position is the position of the target vehicle in the longitudinal coordinate axis.

[0079] In step 1022, a second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary is determined, wherein the intersection point is the point where the first driving trajectory intersects the driving boundary.

[0080] In some embodiments, determining the second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary in step 1022 can be achieved by the following technical solution: based on the boundary safety distance, the driving boundary is corrected to obtain the corrected driving boundary; the second lateral position corresponding to the intersection point of the first driving trajectory and the corrected driving boundary is determined.

[0081] As an example, the greater the distance between the autonomous vehicle and the driving boundary during the autonomous vehicle's operation, the safer the autonomous vehicle is. Therefore, when correcting the first driving trajectory, the distance between the autonomous vehicle's driving trajectory and the driving boundary can be increased. Specifically, when determining the intersection point of the driving trajectory and the driving boundary, the driving boundary can be corrected first, so that the driving boundary moves a safe distance into the road, thereby obtaining the boundary safety distance. Then, the second lateral position corresponding to the intersection point of the driving trajectory and the corrected driving boundary can be determined.

[0082] In step 1023, the second longitudinal position corresponding to the second lateral position is determined.

[0083] As an example, the second longitudinal position corresponding to the second lateral position of the driving boundary is the longitudinal position corresponding to the intersection point of the driving trajectory and the driving boundary.

[0084] In step 1024, the lateral velocity of the target vehicle is corrected based on the first longitudinal position, the second longitudinal position, the first lateral position and the second lateral position of the target vehicle to obtain the corrected lateral velocity, and the first lateral position of the target vehicle and the corrected lateral velocity are combined to form the corrected lateral motion state.

[0085] In some embodiments, the step 1024, which corrects the lateral velocity of the target vehicle based on the first longitudinal position, the second longitudinal position, the first lateral position, and the second lateral position, to obtain the corrected lateral velocity, can be achieved through the following technical solution: subtracting the second lateral position from the first lateral position of the target vehicle to obtain a first difference; subtracting the second longitudinal position from the first longitudinal position to obtain a second difference; and determining the corrected lateral velocity based on the first difference and the second difference, wherein the corrected lateral velocity is positively correlated with the first difference and negatively correlated with the second difference.

[0086] As an example, the corrected lateral velocity can be determined by referring to the following formula (1):

[0087]

[0088] In formula (1), d′ is the corrected lateral velocity, d2 is the second lateral position, d1 is the first lateral position, d2-d1 is the first difference, and ΔS is the second difference, where ΔS=S2-S1, S2 is the second longitudinal position, and S1 is the first longitudinal position.

[0089] By using the above method, the corrected lateral speed of the target vehicle can be accurately obtained, thereby improving the accuracy of the subsequent second driving trajectory.

[0090] In step 103, based on the corrected lateral motion state, a second driving trajectory of the target vehicle is generated to control the target vehicle to move based on the second driving trajectory.

[0091] As an example, the corrected lateral motion state can be input into the optimizer, which will then generate the second driving trajectory of the target vehicle.

[0092] The following will describe an exemplary application of the embodiments of this application in a real-world application scenario.

[0093] To address the issue of autonomous vehicles tending towards the boundary due to errors during operation, making it impossible to plan a trajectory that satisfies the vehicle's kinematic constraints, the maximum lateral third derivative (jerk) method is used to correct the optimization boundary. The correction process is implemented through the following steps:

[0094] First, based on the vehicle's current lateral motion state (in the Frenet coordinate system, the lateral motion state is defined by d, d', and d”, where d is the lateral position based on the reference line, d' is the first derivative of d with respect to s, and d” is the second derivative of d with respect to s) and the vehicle's maximum lateral third derivative (jerk, which is a specified maximum value or the vehicle's limit motion value), the trajectory of the maximum jerk (i.e., the first driving trajectory mentioned above) is generated.

[0095] Secondly, iterate through the boundary results of the input optimizer and calculate the left and right trajectories corresponding to the maximum jerk trajectory for each boundary. If the maximum lateral distance of the left-turning trajectory in the first driving trajectory is less than the right boundary of the driving boundary, or the right-turning trajectory is less than the left boundary of the driving boundary, then it is determined that the driving trajectory exceeds the driving boundary and boundary correction judgment is required.

[0096] Then, after entering the boundary correction judgment, the kinematic relationship is used. The initial lateral motion state d' is corrected, where d2 is the second lateral position, d1 is the first lateral position, d2-d1 is the first difference, ΔS is the second difference, where ΔS=S2-S1, S2 is the second longitudinal position, S1 is the first longitudinal position, and d′ is the corrected lateral velocity. In physical terms, this means virtually correcting the vehicle's heading so that a trajectory within the boundary can be planned.

[0097] like Figure 4 As shown, Figure 4 This is a schematic diagram of the first driving trajectory provided in the embodiment of this application. The trajectory generated under the maximum jerk will still go out of bounds. Therefore, the initial state d' is corrected at this point to generate the corrected trajectory. For application conditions, it should be ensured that the boundary is a lane boundary with a certain degree of redundancy, and should not be an obstacle boundary. Correction is performed under a certain threshold condition.

[0098] Finally, based on the correction result d', it is assigned to the lateral motion state of the target vehicle. The corrected lateral motion state of the target vehicle is then input into the optimizer, which outputs the optimized second driving trajectory, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of the second driving trajectory provided in the embodiments of this application. Figure 5 In the process, the corrected second driving trajectory is located within the driving boundary. In addition, for safety measures, the target speed of the target vehicle is reduced to a certain threshold.

[0099] It is understood that in the embodiments of this application, data such as user information are involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0100] The following description continues to illustrate the exemplary structure of the trajectory optimization device 555 provided in the embodiments of this application as a software module. In some embodiments, such as... Figure 2 As shown, the software modules stored in the trajectory optimization device 555 in the memory 550 may include:

[0101] The detection module 5551 is used to perform state detection on the target vehicle, obtain the lateral motion state of the target vehicle, and generate the first driving trajectory of the target vehicle based on the lateral motion state of the target vehicle.

[0102] The correction module 5552 is used to correct the lateral motion state of the target vehicle based on the lateral motion state of the target vehicle, the first driving trajectory and the driving boundary if the first driving trajectory exceeds the driving boundary of the target vehicle, so as to obtain the corrected lateral motion state.

[0103] The generation module 5553 is used to generate a second driving trajectory of the target vehicle based on the corrected lateral motion state, so as to control the target vehicle to move based on the second driving trajectory.

[0104] In some embodiments, the detection module 5551 is further configured to acquire the position of the target vehicle and the motion state of the target vehicle; map the position of the target vehicle based on a natural coordinate system to obtain a first lateral position of the target vehicle, and map the motion state of the target vehicle based on the natural coordinate system to obtain a lateral velocity and a lateral acceleration of the target vehicle; and combine the first lateral position, the lateral velocity, and the lateral acceleration of the target vehicle to form the lateral motion state of the target vehicle.

[0105] In some embodiments, the correction module 5552 is further configured to: determine a first longitudinal position corresponding to a first lateral position of the target vehicle; determine a second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary, wherein the intersection point is the point where the first driving trajectory intersects the driving boundary; determine a second longitudinal position corresponding to the second lateral position of the driving boundary; and, based on the first longitudinal position, the second longitudinal position, the first lateral position of the target vehicle, and the second lateral position, correct the lateral velocity of the target vehicle to obtain a corrected lateral velocity, and combine the first lateral position of the target vehicle and the corrected lateral velocity to form a corrected lateral motion state.

[0106] In some embodiments, the correction module 5552 is further configured to subtract the second lateral position from the first lateral position of the target vehicle to obtain a first difference; subtract the second longitudinal position from the first longitudinal position to obtain a second difference; and determine a corrected lateral velocity based on the first difference and the second difference, wherein the corrected lateral velocity is positively correlated with the first difference and negatively correlated with the second difference.

[0107] In some embodiments, the correction module 5552 is further configured to perform boundary correction on the driving boundary based on the boundary safety distance to obtain the corrected driving boundary; and determine the second lateral position corresponding to the intersection point of the first driving trajectory and the corrected driving boundary.

[0108] This application provides a computer program product comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the trajectory optimization method described above in this application.

[0109] This application provides a computer-readable storage medium storing computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the processor will execute the trajectory optimization method provided in this application. For example, ... Figure 3A The trajectory optimization method is shown.

[0110] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0111] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0112] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0113] As an example, computer-executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0114] In summary, the embodiments of this application can achieve the following beneficial effects:

[0115] The system performs state detection on the target vehicle to obtain its lateral movement state. Based on this lateral movement state, a first driving trajectory is generated. Generating the first driving trajectory using the real-time state of the target vehicle improves its accuracy and timeliness. If the first driving trajectory exceeds the target vehicle's driving boundary, the lateral movement state is corrected based on the target vehicle's lateral movement state, the first driving trajectory, and the driving boundary, resulting in a corrected lateral movement state. Based on the corrected lateral movement state, a second driving trajectory is generated to control the target vehicle's movement along this second trajectory. The corrected lateral movement state allows for the generation of a second driving trajectory that conforms to the current road conditions, enabling the target vehicle to move along this second driving trajectory.

[0116] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A trajectory optimization method, characterized in that, The method includes: The target vehicle is subjected to state detection to obtain the lateral motion state of the target vehicle, which includes a first lateral position, lateral velocity and lateral acceleration; Based on the first lateral position, the lateral velocity, and the lateral acceleration, and with the maximum jerk as a constraint, the leftward and rightward driving trajectories of the target vehicle are generated, and the leftward and rightward driving trajectories are combined to form the first driving trajectory of the target vehicle. If the first driving trajectory exceeds the driving boundary of the target vehicle, the lateral movement state of the target vehicle is corrected based on the lateral movement state of the target vehicle, the first driving trajectory, and the driving boundary to obtain the corrected lateral movement state. Based on the corrected lateral motion state, a second driving trajectory of the target vehicle is generated to control the target vehicle to move based on the second driving trajectory.

2. The method according to claim 1, characterized in that, The step of performing state detection on the target vehicle to obtain the lateral motion state of the target vehicle includes: Obtain the position and motion state of the target vehicle; The position of the target vehicle is mapped based on the natural coordinate system to obtain the first lateral position of the target vehicle, and the motion state of the target vehicle is mapped based on the natural coordinate system to obtain the lateral velocity and lateral acceleration of the target vehicle. The first lateral position of the target vehicle, the lateral velocity of the target vehicle, and the lateral acceleration of the target vehicle constitute the lateral motion state of the target vehicle.

3. The method according to claim 1, characterized in that, The step of correcting the lateral motion state of the target vehicle based on its lateral motion state, the first driving trajectory, and the driving boundary to obtain a corrected lateral motion state includes: Determine the first longitudinal position corresponding to the first lateral position of the target vehicle; Determine the second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary, wherein the intersection point is the point where the first driving trajectory intersects the driving boundary; Determine the second longitudinal position corresponding to the second lateral position of the driving boundary; Based on the first longitudinal position, the second longitudinal position, the first lateral position and the second lateral position of the target vehicle, the lateral velocity of the target vehicle is corrected to obtain the corrected lateral velocity, and the first lateral position of the target vehicle and the corrected lateral velocity are combined to form the corrected lateral motion state.

4. The method according to claim 3, characterized in that, The step of correcting the lateral velocity of the target vehicle based on the first longitudinal position, the second longitudinal position, the first lateral position, and the second lateral position to obtain the corrected lateral velocity includes: The first difference is obtained by subtracting the second lateral position from the first lateral position of the target vehicle; The difference between the second longitudinal position and the first longitudinal position is obtained to obtain the second difference; Based on the first difference and the second difference, a corrected lateral velocity is determined, wherein the corrected lateral velocity is positively correlated with the first difference and negatively correlated with the second difference.

5. The method according to claim 3, characterized in that, Determining the second lateral position corresponding to the intersection point of the first driving trajectory and the driving boundary includes: Based on the boundary safety distance, the driving boundary is corrected to obtain the corrected driving boundary; Determine the second lateral position corresponding to the intersection point of the first driving trajectory and the corrected driving boundary.

6. A trajectory optimization device, characterized in that, The device includes: The detection module is used to perform state detection on the target vehicle to obtain the lateral motion state of the target vehicle, which includes a first lateral position, lateral velocity, and lateral acceleration. Based on the first lateral position, the lateral velocity, and the lateral acceleration, and with the maximum jerk as a constraint, the module generates a leftward movement trajectory and a rightward movement trajectory of the target vehicle, and combines the leftward movement trajectory and the rightward movement trajectory into a first movement trajectory of the target vehicle. The correction module is used to correct the lateral motion state of the target vehicle based on the lateral motion state of the target vehicle, the first driving trajectory, and the driving boundary if the first driving trajectory exceeds the driving boundary of the target vehicle, so as to obtain the corrected lateral motion state. The generation module is used to generate a second driving trajectory of the target vehicle based on the corrected lateral motion state, so as to control the target vehicle to move based on the second driving trajectory.

7. An electronic device, characterized in that, The electronic device includes: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements the trajectory optimization method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, the trajectory optimization method according to any one of claims 1 to 5 is implemented.

9. A computer program product comprising computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, the trajectory optimization method according to any one of claims 1 to 5 is implemented.

Images