Track planning method, electronic equipment, storage medium and program product

Abstract

The invention provides a trajectory planning method, electronic equipment, a storage medium and a program product, which can be used in the technical field of intelligent driving. The method comprises the following steps: when an emergency lane keeping function of a target vehicle is activated, obtaining vehicle information of the target vehicle; based on a pre-constructed vehicle dynamics model and the vehicle information, obtaining a relative transverse acceleration of the target vehicle and the lane edge; inputting the relative transverse acceleration into a Bezier curve formula for trajectory planning, and generating a target planning trajectory; wherein the target planning track is used for guiding the target vehicle to run. According to the method, the vehicle dynamics model and the Bezier curve are combined, so that the smooth and natural deviation correction track closer to the actual driving condition of the vehicle is generated when the emergency lane keeping function of the vehicle is activated, the stability and safety of track planning are effectively improved, and the collision risk of the vehicle is reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a trajectory planning method, electronic device, storage medium and program product. Background Technology

[0002] Emergency Lane Keeping (ELK) is an important active safety assistance technology for vehicles. When the system detects that the vehicle is deviating from its current lane and the turn signal is not activated, if the driver does not take corrective measures in time, it will assist the vehicle in returning to its original lane, effectively avoiding the risk of collision caused by lane departure.

[0003] Among them, the trajectory planning of emergency lane keeping refers to predicting the trend of vehicle deviation and generating a safe and smooth return path. Its function is to guide the vehicle back to the center of the lane, thereby maximizing driving stability and safety in emergency situations.

[0004] Although emergency lane keeping assist can intervene promptly when a vehicle unintentionally deviates from its lane, using intelligent trajectory planning to help the vehicle return to its original lane and effectively reduce the risk of collision, the trajectory planning results of current emergency lane keeping assist systems are relatively unstable, resulting in a less smooth and natural vehicle trajectory. Summary of the Invention

[0005] This application provides a trajectory planning method, electronic device, storage medium, and program product to solve the technical problem that existing trajectory planning technologies for emergency lane keeping have low stability in trajectory planning results, resulting in an unsmooth and unnatural vehicle driving trajectory.

[0006] According to the first aspect disclosed in this application, this application provides a trajectory planning method, including:

[0007] When the emergency lane keeping function of the target vehicle is activated, the vehicle information of the target vehicle is obtained;

[0008] Based on the pre-built vehicle dynamics model and the vehicle information, the relative lateral acceleration between the target vehicle and the lane edge is obtained;

[0009] The relative lateral acceleration is input into the Bézier curve formula for trajectory planning to generate a target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle.

[0010] In one feasible implementation, based on a pre-built vehicle dynamics model and the vehicle information, the relative lateral acceleration between the target vehicle and the lane edge is obtained, including:

[0011] Based on the pre-built vehicle dynamics model and the vehicle information, the lateral acceleration of the target vehicle after side slip compensation is calculated.

[0012] Based on the lateral acceleration and the lateral acceleration of the lane edge, the relative lateral acceleration between the target vehicle and the lane edge is obtained.

[0013] In one feasible implementation, the lateral acceleration along the edge is obtained based on the following method:

[0014] Based on the edge coefficient of the lane edge, the edge curvature of the lane edge is obtained;

[0015] The lateral acceleration of the edge is obtained based on the edge curvature and the longitudinal velocity of the target vehicle.

[0016] In one feasible implementation, the relative lateral acceleration is input into a Bézier curve formula for trajectory planning to generate a target planned trajectory, including:

[0017] The relative lateral acceleration is input into the Bézier curve formula to obtain a first Bézier curve that characterizes the lateral acceleration of the target vehicle.

[0018] The target trajectory is obtained by performing a second integral on the first Bézier curve.

[0019] In one feasible implementation, the target planning trajectory is obtained by performing a second integral on the first Bézier curve, including:

[0020] Integrating the first Bézier curve yields a second Bézier curve characterizing the lateral velocity of the target vehicle.

[0021] Integrating the second Bézier curve yields the target planned trajectory, which characterizes the lateral displacement of the target vehicle.

[0022] In one feasible implementation, the method further includes:

[0023] Obtain the first maximum rate of change of acceleration of the first Bézier curve;

[0024] If the first maximum rate of change of acceleration is not greater than the rate of change of acceleration threshold, then the target trajectory planning is confirmed to be successful.

[0025] In one feasible implementation, the first Bézier curve includes multiple lateral acceleration curves, and obtaining the first maximum rate of change of acceleration of the first Bézier curve includes:

[0026] Obtain the second maximum rate of change of acceleration for each segment of the transverse acceleration curve in the first Bézier curve;

[0027] The maximum value of the second maximum rate of change of acceleration in each segment of the transverse acceleration curve is obtained as the first maximum rate of change of acceleration.

[0028] In one feasible implementation, the method further includes:

[0029] If the first maximum rate of change of acceleration is greater than the rate of change of acceleration threshold, the target trajectory planning is confirmed to have failed, and the process jumps to the step of obtaining the vehicle information of the target vehicle.

[0030] In one feasible implementation, the vehicle dynamics model is a bicycle model, a monorail model, or a dual-rail model.

[0031] In one feasible implementation, the Bézier curve is a third-order Bézier curve, a fourth-order Bézier curve, or a fifth-order Bézier curve.

[0032] According to a second aspect disclosed in this application, this application provides a trajectory planning device, comprising:

[0033] The information acquisition module is used to acquire vehicle information of the target vehicle when the emergency lane keeping function of the target vehicle is activated.

[0034] An acceleration acquisition module is used to acquire the relative lateral acceleration between the target vehicle and the lane edge based on a pre-built vehicle dynamics model and the vehicle information.

[0035] The trajectory planning module is used to input the relative lateral acceleration into the Bézier curve formula for trajectory planning and generate a target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle to drive.

[0036] According to a third aspect disclosed in this application, this application provides an electronic device, including a processor and a memory communicatively connected to the processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory to implement the method described in any one of the first aspects.

[0039] According to the fourth aspect disclosed in this application, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the method described in any one of the first aspects.

[0040] According to the fifth aspect disclosed in this application, this application provides a computer program product, including a computer program, which, when executed, is used to implement the method described in any one of the first aspects.

[0041] According to the sixth aspect disclosed in this application, this application provides a vehicle that includes electronic equipment as described in the third aspect.

[0042] Compared with the prior art, this application has the following advantages:

[0043] This application provides a trajectory planning method, electronic device, storage medium, and program product. By combining a vehicle dynamics model and Bézier curves, the method utilizes the vehicle dynamics model to obtain a more accurate relative lateral acceleration between the target vehicle and the lane edge. This relative lateral acceleration is then input into a Bézier curve formula to generate a smoother and more natural vehicle correction trajectory that more closely resembles the actual driving conditions when the vehicle's emergency lane keeping function is activated. This effectively improves the stability and safety of trajectory planning and reduces the risk of vehicle collisions. Furthermore, the method considers the impact of the rate of change of acceleration on the stability of the planned trajectory. The maximum rate of change of acceleration is calculated, and a certain threshold for the rate of change of acceleration is set to determine the success of trajectory planning for the emergency lane keeping function. This further enhances the safety of the planned trajectory along the road edge, thereby significantly reducing the risk of vehicle-road edge collisions. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] Figure 1 A flowchart illustrating a trajectory planning method provided in an embodiment of this application;

[0046] Figure 2 A flowchart illustrating another trajectory planning method provided in an embodiment of this application;

[0047] Figure 3 This application provides a schematic diagram of trajectory planning for emergency lane keeping in a lane edge scenario, as an embodiment of the present application.

[0048] Figure 4 This is a schematic diagram of the structure of a trajectory planning device provided in an embodiment of this application;

[0049] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0050] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0051] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0052] Emergency Lane Keeping (ELK) is an important active safety assistance technology for vehicles. It uses high-precision cameras and sensors to monitor the vehicle's trajectory and lane markings in real time. When the system detects that the vehicle has unintentionally deviated from its current lane due to driver distraction, fatigue, or operational error, and the turn signal has not been activated, it will immediately alert the driver through slight steering wheel vibration or visual / auditory warnings. If the driver does not take corrective action in time, the system will automatically apply gentle steering intervention to assist the vehicle in returning to its original lane, effectively avoiding the risk of collision caused by lane departure, and significantly improving driving safety, especially at high speeds or in complex road conditions.

[0053] Among them, the trajectory planning of emergency lane keeping refers to the use of intelligent algorithms to predict the vehicle's deviation trend and quickly generate a safe and smooth return path. Its role is to ensure that when the system intervenes, it avoids the risk of loss of control caused by sharp steering wheel turns, accurately guides the vehicle back to the center of the lane, minimizes interference with the driver's operation, and makes the correction process natural and smooth, thereby maximizing driving stability and safety in emergency situations.

[0054] While emergency lane keeping assist has demonstrated significant advantages in improving driving safety by intervening promptly when a vehicle unintentionally deviates from its lane and intelligently planning a correction trajectory to help the vehicle return to its original lane, effectively reducing the risk of collision, the stability of current emergency lane keeping trajectory planning results is relatively low. Specifically, in complex road conditions (such as curves, blurred lane lines, or uneven road surfaces) or at high speeds, the correction trajectory generated by the system may fluctuate or overcorrect, resulting in an unsmooth and unnatural vehicle trajectory. This instability not only weakens the reliability of the function but may also reduce user trust in the system. Therefore, improving the stability of emergency lane keeping trajectory planning results, ensuring that it generates accurate, reliable, and human-friendly correction paths under various conditions, remains a critical issue that urgently needs to be addressed.

[0055] To address the aforementioned technical problems, this application proposes a trajectory planning method, electronic device, storage medium, and program product. By using a vehicle dynamics model to calculate the initial value of the lateral acceleration after lateral compensation, and then using a Bezier curve to calculate the vehicle's correction trajectory, the maximum rate of change of acceleration of the planned trajectory is calculated to determine whether the trajectory planning is successful. This significantly reduces the risk of vehicle collisions with road edges while further improving the stability and safety of the planned trajectory.

[0056] The technical solutions of the trajectory planning method, electronic device, storage medium, and program product provided in this application will be described in detail below through specific embodiments. It should be noted that the following embodiments may exist independently or in combination with each other, and the same or similar content may not be described again in different embodiments.

[0057] Figure 1 A flowchart illustrating a trajectory planning method provided in this application is shown below. Figure 1 In some embodiments, the trajectory planning method includes the following steps:

[0058] S101: When the emergency lane keeping function of the target vehicle is activated, obtain the vehicle information of the target vehicle.

[0059] When the emergency lane keeping function of the target vehicle is activated, it indicates that the target vehicle has deviated from the current lane. At this time, the vehicle information of the target vehicle is obtained to provide data support for subsequent trajectory planning.

[0060] Specifically, vehicle information includes vehicle parameters and driving data. Vehicle parameters include vehicle weight, distance from the front axle to the center of gravity, distance from the rear axle to the center of gravity, etc. Driving data includes vehicle longitudinal speed, front tire force, rear tire force, etc.

[0061] Specifically, the vehicle comprehensively determines whether to activate the emergency lane keeping function based on multiple factors, including vehicle speed, lane line clarity, vehicle system status, driver operation, and environmental condition compatibility. Specifically, vehicle speed must not exceed a preset speed range; at too low a speed, the risk of lane departure is low, and the system does not need to intervene; at too high a speed, the system may limit its function due to insufficient reaction time. Lane line clarity requires that the lane lines be clearly visible and the camera's field of view be unobstructed. Vehicle system status requires that components such as the camera, millimeter-wave radar, and steering wheel torque sensor be functioning normally and without malfunction. Driver operation requires that the vehicle not unintentionally deviate from the lane (without using turn signals) and that the driver's hands not be on the steering wheel for an extended period. Environmental condition compatibility requires that the radius of road curves meet the required radius. Therefore, when the vehicle determines to activate the emergency lane keeping function based on the current information, it obtains the vehicle's current information.

[0062] S102, based on a pre-built vehicle dynamics model and vehicle information, obtains the relative lateral acceleration between the target vehicle and the lane edge.

[0063] In particular, by combining vehicle dynamics models and vehicle information, various physical characteristics of the target vehicle during driving are accurately modeled and analyzed, thereby enabling precise acquisition of the relative lateral acceleration between the target vehicle and the lane edge, thus improving the accuracy and reliability of the relative lateral acceleration data.

[0064] Specifically, lane edges include lane line edges and road edges.

[0065] S103, input the relative lateral acceleration into the Bézier curve formula for trajectory planning, and generate the target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle to drive.

[0066] Because Bézier curves define their shape through control points, their curvature and direction can be precisely controlled simply by adjusting the positions of these control points, meeting the dynamic requirements of vehicle steering and lane changes. Furthermore, Bézier curves possess geometric invariance and convex hull properties, ensuring that the generated trajectory always lies within the convex hull formed by the control points, effectively constraining the vehicle's range of motion and conforming to dynamic and positional constraints. Moreover, Bézier curves can generate high-order, continuous, and smooth trajectories, allowing the vehicle to maintain curvature continuity during steering and lane changes, avoiding bumps or sideslips caused by abrupt trajectory changes, and significantly improving ride comfort, safety, and stability.

[0067] After generating the target planning trajectory, the target vehicle is guided back to the correct lane through the target planning trajectory to correct the target vehicle's deviation and avoid the risk of collision.

[0068] In this embodiment, by combining vehicle dynamics model and Bézier curve, the vehicle dynamics model is used to obtain a more accurate relative lateral acceleration between the target vehicle and the lane edge. This relative lateral acceleration is then input into the Bézier curve formula to generate a smoother and more natural vehicle correction trajectory that is closer to the actual driving conditions of the vehicle when the vehicle's emergency lane keeping function is activated. This effectively improves the stability and safety of trajectory planning and reduces the risk of vehicle collision.

[0069] exist Figure 1 Based on the embodiments shown, the following is combined with Figure 2 The technical solution of the above trajectory planning method will be further introduced.

[0070] Figure 2 A flowchart illustrating another trajectory planning method provided in this application embodiment is shown below. Figure 2 In some embodiments, the trajectory planning method includes the following steps:

[0071] S201: When the emergency lane keeping function of the target vehicle is activated, obtain the vehicle information of the target vehicle.

[0072] S202 calculates the lateral acceleration of the target vehicle after side slip compensation, based on a pre-built vehicle dynamics model and vehicle information.

[0073] Optionally, the vehicle dynamics model can be a bicycle model, a monorail model, or a dual-rail model.

[0074] The bicycle model treats the vehicle as a two-wheeled system (one front wheel and one rear wheel), assuming perfectly symmetrical motion of the left and right wheels and considering only the steering of the front wheel. This model describes the vehicle's lateral motion (lateral displacement) and yaw motion (rotation about the vertical axis) using three state variables: lateral velocity, yaw rate, and longitudinal velocity. It is simple in structure and computationally efficient.

[0075] The monorail model, based on the bicycle model, introduces a nonlinear tire model (such as the magic formula) to more accurately describe the relationship between tire slip angle and lateral force. It still maintains the simplified assumption of two wheels, but by dynamically calculating the slip angles of the front and rear wheels and combining them with the tire's force-angle characteristic curve, it can capture nonlinear behavior (such as tire force saturation) under high-speed or large steering angle conditions.

[0076] The dual-track model is the most realistic complex dynamics model of a vehicle. It considers the independent motion of the left and right wheels and introduces the roll angle (rotation about the vehicle's longitudinal axis) and its dynamic equilibrium equations. By calculating the lateral forces of the four independent wheels (left and right front wheels, left and right rear wheels) and combining the roll stiffness and damping characteristics of the suspension system, this model can analyze the coupling effects of lateral motion, yaw motion, and roll motion.

[0077] See Figure 3 Exemplary Figure 3 The diagram illustrates trajectory planning for emergency lane keeping in a lane-edge scenario, using the activation of the emergency lane keeping function on the right side of the lane as an example. Figure 3 In the diagram, Ego represents the target vehicle, and ①, ②, and ③ represent the first, second, and third Bézier curves, respectively.

[0078] Specifically, taking the two-degree-of-freedom bicycle model as an example, the established dynamic equations for the lateral motion and yaw motion of the bicycle model satisfy the following formula (1):

[0079]

[0080]

[0081] Where m represents the total vehicle mass. Indicates the centroid sideslip angle. Indicates yaw rate. Indicates the tire force of the front wheels. Indicates the tire force of the rear wheels. This represents the moment of inertia in the yaw direction of the vehicle about the z-axis. Indicates the distance from the front axle to the center of gravity. This indicates the distance from the rear axle to the center of mass.

[0082] in, and They respectively satisfy the following formula (2):

[0083]

[0084] in, This indicates the lateral stiffness of the front tires. This indicates the tire lateral stiffness of the rear wheels. Indicates the front wheel slip angle. This indicates the rear wheel slip angle.

[0085] in, and They respectively satisfy the following formula (3):

[0086]

[0087]

[0088] in, Indicates the steering angle of the vehicle's front wheels. This indicates the vehicle's longitudinal speed.

[0089] Considering the steady-state steering characteristics of a car, we can assume:

[0090]

[0091] Therefore, by substituting formulas (2) and (3) into formula (1), the lateral acceleration of the target vehicle after lateral offset compensation can be obtained:

[0092]

[0093] S203, based on lateral acceleration and the lateral acceleration of the lane edge, obtains the relative lateral acceleration between the target vehicle and the lane edge.

[0094] Among them, the initial lateral acceleration after lateral compensation is calculated using the vehicle dynamics model, and the initial lateral acceleration for the Bezier curve trajectory planning is further calculated, which helps to improve the stability of the planned trajectory.

[0095] Specifically, the relative lateral acceleration, i.e. the initial acceleration of the Bezier curve, satisfies the following formula (4):

[0096]

[0097] in, Indicates relative lateral acceleration. Indicates lateral acceleration. This indicates the lateral acceleration at the edge.

[0098] Optionally, the lateral acceleration at the edge is obtained based on the following method:

[0099] Step 1: Obtain the edge curvature of the lane edge based on the edge coefficient of the lane edge.

[0100] The edge curvature satisfies the following formula:

[0101]

[0102] in, This indicates the coefficient of the right-hand road edge.

[0103] Step 2: Based on the edge curvature and the longitudinal velocity of the target vehicle, obtain the edge lateral acceleration.

[0104] The lateral acceleration along the edge satisfies the following formula:

[0105]

[0106] S204. Input the relative lateral acceleration into the Bézier curve formula to obtain the first Bézier curve used to characterize the lateral acceleration of the target vehicle.

[0107] The relative lateral acceleration is input into the Bézier curve formula. Based on the linear relationship between lateral acceleration and trajectory curvature in vehicle dynamics, and combined with the curvature continuity characteristics of the Bézier curve, the first Bézier curve is generated by controlling the acceleration control points in stages.

[0108] Optionally, the Bézier curve can be a third-order, fourth-order, or fifth-order Bézier curve.

[0109] Third-order, fourth-order, and fifth-order Bézier curves all define their shape using control points, but they differ in the number of control points, mathematical complexity, and curve characteristics. A third-order Bézier curve consists of four control points (start, end, and two intermediate control points), calculated using cubic polynomial interpolation. This allows for complex shapes with fewer control points and high computational efficiency. A fourth-order Bézier curve is defined by five control points (start, end, and three intermediate control points), calculated using fourth-order polynomial interpolation. The increased number of control points allows for more precise curve shape adjustments, but also increases mathematical complexity (more computation). A fifth-order Bézier curve consists of six control points, calculated using fifth-order polynomial interpolation. This further increases the number of control points, making curve shape adjustments extremely flexible and capable of describing more complex paths. However, the computational cost increases significantly, impacting trajectory planning efficiency.

[0110] Specifically, the selection strategy for Bézier curves is adaptively adjusted based on the complexity of the road edge scene (such as edge type, obstacle distribution, and rate of curvature change). For example, a third-order Bézier curve is used in simple straight road scenes (reducing computational load), while a four-segment Bézier curve is used in complex curved or obstacle-dense scenes (increasing control points to improve trajectory accuracy). Scene classification is achieved through a multi-feature fusion algorithm (such as CNN-based image classification) from the environment perception module, and the segmentation strategy adjustment is dynamically triggered by the rule engine.

[0111] participate Figure 3 For example, to ensure the continuity and smoothness of each segment of the planned trajectory curve, a third-order Bézier curve is selected. Each segment of the third-order Bézier curve requires four acceleration control points.

[0112] Specifically, based on the kinematic relationship of lateral velocity, the following formula (5) can be calculated:

[0113]

[0114]

[0115] in, This represents the lateral velocity difference of the first segment of the Bézier curve. This represents the difference in lateral velocity of the second segment of the Bézier curve; This represents the lateral acceleration at the starting point, i.e., the relative lateral acceleration. The lateral acceleration at the end point of the first Bézier curve is the same as the lateral acceleration at the beginning point of the second Bézier curve. This represents the lateral acceleration at the termination point. In trajectory planning for emergency lane keeping, the lateral acceleration at the termination point is set to 0. It is assumed that the planning time for the two Bézier curves is the same. This represents the planning time for each segment of the Bézier curve.

[0116] Based on the kinematic relationship of lateral displacement, the following formula (6) can be obtained:

[0117]

[0118]

[0119] in, This represents the lateral displacement difference of the first segment of the Bézier curve. This represents the lateral displacement difference of the second segment of the Bézier curve. Indicates the lateral velocity at the starting point; This represents the lateral velocity at the termination point. In the trajectory planning for emergency lane keeping, the lateral velocity at the termination point is set to 0.

[0120] Based on the relationship between the velocity and displacement of the two Bézier curves, the following formula (7) can be derived:

[0121]

[0122] in, This represents the difference in lateral velocity between the starting and ending points of the planned trajectory. This represents the difference in lateral displacement between the end point and the starting point of the planned trajectory.

[0123] Substituting the first formula in formula (5) into the first formula in formula (7), we obtain the following formula (8):

[0124]

[0125] Substituting the second formula in formula (6) into the second formula in formula (7), we obtain the following formula (9):

[0126]

[0127] Then, using formulas (8) and (9), the lateral acceleration at the termination point of the first segment of the Bézier curve can be obtained. Planning time for each segment of the Bézier curve The expression.

[0128] Then refer to Figure 3 The acceleration control point of the first segment of the Bézier curve in trajectory planning is... The planned time is The planning duration is The acceleration control point for the second segment of the Bézier curve in trajectory planning is... The planned time is The planning duration is The acceleration control point of the third segment of the Bézier curve in trajectory planning is... The planned time is The planning duration is ,in, This represents the maximum planning time for maintaining the trajectory in the emergency lane. Therefore, three smooth lateral acceleration curves can be obtained using the third-order Bézier curve formula. Considering the stability and safety issues of the vehicle during the correction process, using three third-order Bézier curves as the correction planning algorithm for road edge scenarios not only helps improve the stability and safety of the planned trajectory but also helps reduce the risk of vehicle collisions with the road edge.

[0129] S205, perform a second integration on the first Bézier curve to obtain the target planned trajectory.

[0130] Based on the fundamental principles of kinematics in physics, the lateral acceleration is integrated once. According to the integral relationship between acceleration and velocity, the lateral velocity curve of the vehicle is obtained. Then, the lateral velocity curve is integrated again. Since there is an integral relationship between velocity and displacement (displacement is the accumulation of velocity over time), this second integration yields the lateral displacement curve of the vehicle. Specifically, this includes:

[0131] Step 1: Integrate the first Bézier curve to obtain the second Bézier curve used to characterize the lateral velocity of the target vehicle.

[0132] In the analysis of vehicle or object motion, lateral acceleration reflects the rate of change of the vehicle's velocity in the lateral direction. According to the fundamental principles of calculus, acceleration is the first derivative of velocity with respect to time; that is, acceleration describes the rate of change of velocity over time. Conversely, velocity is the integral of acceleration with respect to time. When integrating the lateral acceleration curve of the first Bézier curve, we are essentially calculating the cumulative sum of the velocity changes caused by lateral acceleration in each time interval. Through this accumulation, we can gradually deduce the change of lateral velocity over time from the change of lateral acceleration over time. Therefore, by integrating the first Bézier curve, we can obtain the corresponding lateral velocity curves, forming the second Bézier curve.

[0133] Step 2: Integrate the second Bézier curve to obtain the target planning trajectory used to characterize the lateral displacement of the target vehicle.

[0134] In kinematics, lateral velocity represents the rate of change of an object's position in the lateral direction, while lateral displacement is the amount of change in position in the lateral direction. According to the principles of calculus, velocity is the first derivative of displacement with respect to time (i.e., the rate of change of displacement). Therefore, integrating the lateral velocity curve of the second Bézier curve essentially accumulates the change in lateral velocity over time. Thus, by calculating the sum of the areas enclosed by the second Bézier curve and the time axis, the total lateral displacement change of the vehicle can be obtained, leading to the target trajectory composed of the corresponding lateral displacement curves.

[0135] S206, obtain the first maximum rate of change of acceleration of the first Bézier curve.

[0136] Optionally, since the first Bézier curve includes multiple lateral acceleration curves, obtaining the first maximum rate of change of acceleration of the first Bézier curve includes:

[0137] Step 1: Obtain the second maximum rate of change of acceleration for each segment of the transverse acceleration curve in the first Bézier curve.

[0138] Specifically, based on the principle of the Bézier curve algorithm, the rate of change of lateral acceleration of the planned trajectory can be calculated through lateral acceleration. The rate of change of lateral acceleration satisfies the following formula (10):

[0139]

[0140] in, This represents the planning time for each segment of the Bézier curve. These represent the four acceleration control points for each segment of the Bézier curve.

[0141] From formula (4), we can see that when s = 0.5, If an extremum exists, then the extreme value of the lateral acceleration of the first segment of the Bézier curve is... Satisfy the following formula (11):

[0142]

[0143] Similarly, the extreme value of the lateral acceleration of the second segment of the Bezier curve satisfies the following formula (12):

[0144]

[0145] Step 2: Obtain the maximum value of the second maximum rate of change of acceleration in each segment of the transverse acceleration curve, and use it as the first maximum rate of change of acceleration.

[0146] Specifically, the maximum rate of change of acceleration for the entire Bessel trajectory planning satisfies the following formula (13):

[0147]

[0148] S207, if the first maximum rate of change of acceleration is not greater than the rate of change of acceleration threshold, then the target trajectory planning is confirmed to be successful.

[0149] Where the first maximum rate of change of acceleration is not greater than the rate of change of acceleration threshold If so, the Bézier curve trajectory planning is successful.

[0150] Specifically, the initial threshold for the rate of change of acceleration can be set to... Alternatively, an adaptive threshold adjustment algorithm can be designed to dynamically adjust the threshold range based on the vehicle's real-time status (such as vehicle speed, tire grip, and road friction coefficient). For example, when the vehicle is traveling at high speed, the upper limit of the threshold automatically decreases to limit sudden acceleration changes; when a decrease in the road friction coefficient is detected, the threshold range narrows to ensure a smoother trajectory. This adjustment is implemented through a fuzzy logic controller, with vehicle state parameters as input and dynamic thresholds as output.

[0151] S208, if the first maximum rate of change of acceleration is greater than the rate of change of acceleration threshold, then the target trajectory planning is confirmed to have failed, and the process jumps to the step of obtaining the vehicle information of the target vehicle.

[0152] Correspondingly, when the first maximum rate of change of acceleration is greater than the rate of change of acceleration threshold... If the Bézier curve trajectory planning fails, the process will jump to the step of obtaining the vehicle information of the target vehicle and re-plan the trajectory.

[0153] The rate of change of acceleration is the rate at which acceleration changes over time, and its physical meaning lies in reflecting how quickly acceleration changes. In trajectory planning, if the rate of change of acceleration exceeds a threshold, it indicates an abrupt change in the acceleration curve (such as rapid acceleration, rapid deceleration, or sharp turning), causing the vehicle to experience instantaneous impact forces. For example, during rapid acceleration, passengers may lose balance due to a "push-back feeling," and during sharp turning, lateral centrifugal force will be generated. These abrupt changes will affect the stability of the planned trajectory, reduce ride comfort, and increase mechanical load.

[0154] Therefore, by setting a threshold for the rate of change of acceleration, the smoothness of the trajectory can be quantitatively evaluated. If the first maximum rate of change of acceleration is within the threshold, it indicates that the acceleration change is gradual and the trajectory is reasonable; if the first maximum rate of change of acceleration exceeds the threshold, the trajectory is unreasonable due to abrupt changes. Determining the success of the planned trajectory by using the logical judgment condition of the maximum rate of change of acceleration for the entire planned trajectory can further improve the safety of planned trajectories in roadside scenarios and has high practical value.

[0155] In this embodiment, the stability and safety of the planned trajectory are fully considered during vehicle operation. Under different roadside scenario conditions, this solution uses a two-degree-of-freedom bicycle model to calculate the lateral acceleration after lateral compensation, and uses three third-order Bézier curves as the correction trajectory for emergency lane keeping function. At the same time, the maximum rate of change of acceleration of the planned trajectory is obtained and the success of the planned trajectory is determined. Under the premise of further improving the stability and safety of the planned trajectory, the risk of collision between the vehicle and the roadside can be greatly reduced.

[0156] Figure 4 This is a schematic diagram of the structure of a trajectory planning device provided in an embodiment of this application. (See attached diagram.) Figure 4 The trajectory planning device includes various functional modules for implementing the aforementioned trajectory planning method, and any functional module can be implemented by software and / or hardware.

[0157] In some embodiments, the trajectory planning device 400 includes an information acquisition module 401, an acceleration acquisition module 402, and a trajectory planning module 403. Wherein:

[0158] The information acquisition module 401 is used to acquire vehicle information of the target vehicle when the emergency lane keeping function of the target vehicle is activated.

[0159] The acceleration acquisition module 402 is used to acquire the relative lateral acceleration between the target vehicle and the lane edge based on a pre-built vehicle dynamics model and vehicle information.

[0160] The trajectory planning module 403 is used to input the relative lateral acceleration into the Bézier curve formula for trajectory planning and generate the target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle to drive.

[0161] In some embodiments, the acceleration acquisition module 402 is specifically used for:

[0162] Based on a pre-built vehicle dynamics model and vehicle information, the lateral acceleration of the target vehicle after side slip compensation is calculated.

[0163] The relative lateral acceleration between the target vehicle and the lane edge is obtained based on lateral acceleration and the lateral acceleration along the lane edge.

[0164] In some embodiments, the acceleration acquisition module 402 is further configured to:

[0165] The edge curvature of the lane edge is obtained based on the edge coefficient of the lane edge.

[0166] The lateral acceleration of the edge is obtained based on the edge curvature and the longitudinal velocity of the target vehicle.

[0167] In some embodiments, the trajectory planning module 403 is specifically used for:

[0168] By inputting the relative lateral acceleration into the Bézier curve formula, the first Bézier curve used to characterize the lateral acceleration of the target vehicle is obtained.

[0169] The target trajectory is obtained by performing a second integral on the first Bézier curve.

[0170] In some embodiments, the trajectory planning module 403 is further configured to:

[0171] Integrating the first Bézier curve yields a second Bézier curve used to characterize the lateral velocity of the target vehicle.

[0172] Integrating the second Bezier curve yields the target planned trajectory used to characterize the lateral displacement of the target vehicle.

[0173] In some embodiments, the device 400 further includes a trajectory determination module 404, which is specifically used for:

[0174] Obtain the first maximum rate of change of acceleration for the first Bézier curve;

[0175] If the first maximum rate of change of acceleration is not greater than the acceleration rate of change threshold, then the target trajectory planning is confirmed to be successful.

[0176] In some embodiments, the first Bézier curve includes multiple lateral acceleration curves, and the trajectory determination module 404 is further configured to:

[0177] Obtain the second maximum rate of change of acceleration for each segment of the transverse acceleration curve in the first Bézier curve;

[0178] The maximum value of the second maximum rate of change of acceleration in each segment of the transverse acceleration curve is taken as the first maximum rate of change of acceleration.

[0179] In some embodiments, the trajectory determination module 404 is further configured to:

[0180] If the first maximum rate of change of acceleration is greater than the rate of change of acceleration threshold, the target trajectory planning is confirmed to have failed, and the process jumps to the step of obtaining vehicle information of the target vehicle.

[0181] In some embodiments, the vehicle dynamics model is a bicycle model, a monorail model, or a dual-rail model.

[0182] In some embodiments, the Bézier curve is a third-order Bézier curve, a fourth-order Bézier curve, or a fifth-order Bézier curve.

[0183] The trajectory planning device 400 provided in this application embodiment is used to execute the technical solution provided in the aforementioned trajectory planning method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0184] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing elements, entirely in hardware, or partially in software via processing elements and partially in hardware. For example, the information acquisition module 401 can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0185] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. (See attached diagram.) Figure 5 The electronic device 500 includes a processor 501 and a memory 502 communicatively connected to the processor 501;

[0186] Memory 502 stores instructions executed by the computer;

[0187] The processor 501 executes the computer execution instructions stored in the memory 502 to implement the aforementioned trajectory planning method.

[0188] In the aforementioned electronic device 500, the memory 502 and the processor 501 are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines, such as bus connections. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be classified as address buses, data buses, control buses, etc., but this does not mean that there is only one bus or one type of bus. The memory 502 stores computer execution instructions that implement the aforementioned trajectory planning method, including at least one software functional module that can be stored in the memory 502 in the form of software or firmware. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502.

[0189] The memory 502 includes at least one type of readable storage medium, not limited to Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 502 stores programs, and the processor 501 executes the programs after receiving execution instructions. Furthermore, the software programs and modules within the memory 502 may also include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components.

[0190] Processor 501 can be an integrated circuit chip with signal processing capabilities. The aforementioned processor 501 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or processor 501 can be any conventional processor.

[0191] The electronic device 500 is used to execute the technical solution provided in the aforementioned trajectory planning method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0192] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the technical solution of the trajectory planning method described above.

[0193] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0194] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. Both the processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components within the control unit of the trajectory planning device.

[0195] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the technical solution of the trajectory planning method described above.

[0196] In the above embodiments, those skilled in the art will understand that the above method embodiments can be implemented entirely or partially by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless network, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0197] This application also provides a vehicle that includes the aforementioned electronic equipment.

[0198] In this embodiment, a vehicle equipped with the aforementioned electronic device can calculate the initial value of the lateral acceleration after lateral offset compensation using a vehicle dynamics model, and then calculate the vehicle's correction trajectory using a Bezier curve. At the same time, the maximum rate of change of acceleration of the planned trajectory is calculated to determine whether the trajectory planning is successful. This significantly reduces the risk of collision between the vehicle and the road edge while further improving the stability and safety of the planned trajectory.

[0199] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0200] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

[0201] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A trajectory planning method, characterized in that, include: When the emergency lane keeping function of the target vehicle is activated, the vehicle information of the target vehicle is obtained; Based on the pre-built vehicle dynamics model and the vehicle information, the relative lateral acceleration between the target vehicle and the lane edge is obtained; The relative lateral acceleration is input into the Bézier curve formula for trajectory planning to generate a target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle.

2. The method according to claim 1, characterized in that, Based on a pre-built vehicle dynamics model and the vehicle information, the relative lateral acceleration between the target vehicle and the lane edge is obtained, including: Based on the pre-built vehicle dynamics model and the vehicle information, the lateral acceleration of the target vehicle after side slip compensation is calculated. Based on the lateral acceleration and the lateral acceleration of the lane edge, the relative lateral acceleration between the target vehicle and the lane edge is obtained.

3. The method according to claim 2, characterized in that, The lateral acceleration along the edge is obtained based on the following method: Based on the edge coefficient of the lane edge, the edge curvature of the lane edge is obtained; The lateral acceleration of the edge is obtained based on the edge curvature and the longitudinal velocity of the target vehicle.

4. The method according to claim 1, characterized in that, The relative lateral acceleration is input into the Bézier curve formula for trajectory planning to generate the target planned trajectory, including: The relative lateral acceleration is input into the Bézier curve formula to obtain a first Bézier curve that characterizes the lateral acceleration of the target vehicle. The target trajectory is obtained by performing a second integral on the first Bézier curve.

5. The method according to claim 4, characterized in that, The target trajectory is obtained by performing a quadratic integration on the first Bézier curve, including: Integrating the first Bézier curve yields a second Bézier curve characterizing the lateral velocity of the target vehicle. Integrating the second Bézier curve yields the target planned trajectory, which characterizes the lateral displacement of the target vehicle.

6. The method according to claim 4, characterized in that, The method further includes: Obtain the first maximum rate of change of acceleration of the first Bézier curve; If the first maximum rate of change of acceleration is not greater than the rate of change of acceleration threshold, then the target trajectory planning is confirmed to be successful.

7. The method according to claim 6, characterized in that, The first Bézier curve includes multiple lateral acceleration curves. Obtaining the first maximum rate of change of acceleration of the first Bézier curve includes: Obtain the second maximum rate of change of acceleration for each segment of the transverse acceleration curve in the first Bézier curve; The maximum value of the second maximum rate of change of acceleration in each segment of the transverse acceleration curve is obtained as the first maximum rate of change of acceleration.

8. The method according to claim 7, characterized in that, The method further includes: If the first maximum rate of change of acceleration is greater than the rate of change of acceleration threshold, the target trajectory planning is confirmed to have failed, and the process jumps to the step of obtaining the vehicle information of the target vehicle.

9. The method according to any one of claims 1-8, characterized in that, The vehicle dynamics model is a bicycle model, a single-track model, or a double-track model.

10. The method according to any one of claims 1-8, characterized in that, The Bézier curve is a third-order, fourth-order, or fifth-order Bézier curve.

11. A trajectory planning device, characterized in that, include: The information acquisition module is used to acquire vehicle information of the target vehicle when the emergency lane keeping function of the target vehicle is activated. An acceleration acquisition module is used to acquire the relative lateral acceleration between the target vehicle and the lane edge based on a pre-built vehicle dynamics model and the vehicle information. The trajectory planning module is used to input the relative lateral acceleration into the Bézier curve formula for trajectory planning and generate a target planned trajectory; wherein, the target planned trajectory is used to guide the target vehicle to drive.

12. An electronic device, characterized in that, Includes a processor and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as claimed in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-10.

15. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 12.

Images