Car following track generation method and device

Abstract

The invention discloses a car following track generation method and device, and the method comprises the steps: obtaining a first predicted driving track of a current car and a second predicted driving track of a target front car in an automatic driving mode; performing near-end point taking processing on the first predicted driving track to obtain position information of a plurality of near-end control points; performing far-end point taking processing on the second predicted driving track to obtain position information of a plurality of far-end control points; and according to the position information of each near-end control point and the position information of each far-end control point, determining a Bezier curve equation for predicting the following track of the vehicle in the future target duration. Therefore, the high-order Bezier curve is combined with a control point dynamic adjustment mechanism, and the vehicle following robustness can be improved. Meanwhile, part of control points are generated through the high-order Bezier curve and the predicted driving track of the vehicle, the smoothness of the vehicle following track under the complex road condition is improved, and the carsickness of passengers is reduced.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and device for generating a vehicle-following trajectory. Background Art

[0002] When following a leading vehicle in autonomous driving mode, the vehicle's response to dynamic situations, such as sudden lane changes or emergency braking, can be delayed. Furthermore, maintaining a smooth and continuous following trajectory can be difficult in complex road conditions, such as when the leading vehicle has just cut in or out of a lane. Furthermore, because the following trajectory requires backtracking to the position of the leading vehicle before it cuts in, the vehicle's following trajectory may experience unnecessary lateral deviation.

[0003] Therefore, how to improve the vehicle's adaptability in dynamic driving scenarios and the smoothness of its trajectory under complex road conditions is a technical problem that we need to solve. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method and device for generating a vehicle-following trajectory to solve the problem that the vehicle-following trajectory is not sufficiently adaptable in dynamic driving scenarios.

[0005] According to a first aspect of the present invention, a method for generating a vehicle-following trajectory is provided, comprising:

[0006] In the automatic driving mode, obtaining a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle;

[0007] Performing proximal point processing on the first predicted driving trajectory to obtain position information of multiple proximal control points;

[0008] Performing remote point processing on the second predicted driving trajectory to obtain position information of multiple remote control points;

[0009] Based on the position information of each proximal control point and the position information of each distal control point, a Bezier curve equation is determined to predict the following trajectory of the vehicle within a future target duration.

[0010] Optionally, before obtaining the first predicted driving trajectory of the host vehicle and the second predicted driving trajectory of the target preceding vehicle, the method further includes:

[0011] Obtaining the steering wheel angle, vehicle speed, and yaw rate of the vehicle, as well as the lateral displacement distance, longitudinal displacement distance, and heading angle of the target preceding vehicle;

[0012] Predicting a first predicted driving trajectory of the vehicle within the target time period in the future based on the steering wheel angle, vehicle speed, and yaw angular velocity of the vehicle;

[0013] A second predicted driving trajectory of the target preceding vehicle within the target time period in the future is predicted based on the lateral displacement distance, the longitudinal displacement distance, and the heading angle of the target preceding vehicle.

[0014] Optionally, predicting a first predicted driving trajectory of the vehicle within the target time period in the future based on the steering wheel angle, vehicle speed, and yaw angular velocity of the vehicle includes:

[0015] Under low-speed conditions, calculating the curvature of the vehicle under the current driving state based on the steering gear ratio, the vehicle wheelbase, and the steering wheel angle of the vehicle, so as to determine a first predicted driving trajectory of the vehicle within the target time period in the future;

[0016] Under high-speed conditions, the curvature of the vehicle in the current driving state is calculated based on the vehicle speed and the yaw angular velocity to determine a first predicted driving trajectory of the vehicle within the target time period in the future.

[0017] Optionally, before calculating the curvature of the vehicle in the current driving state according to the steering gear ratio, the vehicle wheelbase, and the steering wheel angle of the vehicle under the low-speed condition, the method further includes:

[0018] comparing the vehicle speed with a preset speed threshold;

[0019] If the vehicle speed is less than the speed threshold, the vehicle is in a low-speed operating condition;

[0020] If the vehicle speed is greater than or equal to the speed threshold, the vehicle is in a high-speed operating condition.

[0021] Optionally, performing proximal point processing on the first predicted driving trajectory to obtain position information of multiple proximal control points includes:

[0022] using the projection of the first predicted driving trajectory on the first coordinate axis as a first longitudinal displacement segment;

[0023] uniformly inserting all proximal control points in the first longitudinal displacement segment to obtain a first coordinate of each proximal control point on the first coordinate axis;

[0024] For each proximal control point, determine the second coordinate of the proximal control point on the second coordinate axis based on the first predicted driving trajectory and the first coordinate of the proximal control point; wherein the first coordinate and the second coordinate of the proximal control point constitute the position information of the proximal control point.

[0025] Optionally, performing remote point acquisition processing on the second predicted driving trajectory to obtain position information of multiple remote control points includes:

[0026] using the projection of the second predicted driving trajectory on the first coordinate axis as a second longitudinal displacement segment;

[0027] uniformly inserting all distal control points in the second longitudinal displacement segment to obtain a first coordinate of each distal control point on the first coordinate axis;

[0028] For each remote control point, the second coordinate of the remote control point on the second coordinate axis is determined based on the second predicted driving trajectory and the second coordinate of the remote control point; wherein the first coordinate and the second coordinate of the remote control point constitute the position information of the remote control point.

[0029] Optionally, determining the Bezier curve equation according to the position information of each proximal control point and the position information of each distal control point includes:

[0030] According to the position information of each proximal control point and the position information of each distal control point, the Bezier curve equation is determined by the following formula:

[0031]

[0032] The number of proximal control points is 3. When Pi is used as the proximal control point, the value of i ranges from 0 to 2. The number of distal control points is 4. When Pi is used as the distal control point, the value of i ranges from 3 to 6. t is the normalized time parameter.

[0033] According to a second aspect of the present invention, there is provided a vehicle following trajectory generating device, comprising:

[0034] a trajectory prediction module, configured to obtain, in the autonomous driving mode, a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle;

[0035] A first point-taking module is configured to perform proximal point-taking processing on the first predicted driving trajectory to obtain position information of a plurality of proximal control points;

[0036] A second point-taking module is configured to perform remote point-taking processing on the second predicted driving trajectory to obtain position information of a plurality of remote control points;

[0037] The vehicle following trajectory module is used to determine the Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, so as to predict the vehicle following trajectory within the future target time.

[0038] According to a third aspect of the present invention, a controller is provided. The controller includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the aforementioned vehicle-following trajectory generation method.

[0039] According to a fourth aspect of the present invention, a vehicle is provided, comprising a vehicle body and a controller installed in the vehicle body, wherein the controller executes the aforementioned vehicle-following trajectory generation method.

[0040] The above one or more technical solutions in the embodiments of this specification have at least the following technical effects:

[0041] The embodiments of this specification provide a method and device for generating a vehicle-following trajectory. In the automatic driving mode, a first predicted driving trajectory of the vehicle and a second predicted driving trajectory of the target preceding vehicle are obtained, wherein the target preceding vehicle refers to the vehicle in front of the vehicle that the vehicle is following; proximal point processing is performed on the first predicted driving trajectory to obtain the position information of multiple proximal control points; distal point processing is performed on the second predicted driving trajectory to obtain the position information of multiple distal control points; based on the position information of each proximal control point and the position information of each distal control point, a Bezier curve equation is determined to predict the following trajectory of the vehicle within the future target duration. In this way, the high-order Bezier curve combined with the dynamic adjustment mechanism of the control points can improve the robustness of the following vehicle. At the same time, by generating some control points through the high-order Bezier curve and the predicted driving trajectory of the vehicle, the smoothness of the following trajectory under complex road conditions is increased, and the passengers' motion sickness is reduced.

[0042] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. Throughout the drawings, the same reference figures denote the same components. In the drawings:

[0044] Figure 1 A flow chart of a method for generating a vehicle-following trajectory in an embodiment of the present invention is shown.

[0045] Figure 2 A block diagram of a vehicle following trajectory generating device in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0049] In the description of the present invention, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0050] When following a leading vehicle in autonomous driving mode, the vehicle's response to dynamic situations, such as sudden lane changes or emergency braking, can be delayed. Furthermore, maintaining a smooth and continuous following trajectory can be difficult in complex road conditions, such as when the leading vehicle has just cut in or out of a lane. Furthermore, because the following trajectory requires backtracking to the position of the leading vehicle before it cuts in, the vehicle's following trajectory may experience unnecessary lateral deviation.

[0051] Based on the above situation, an embodiment of the present invention provides a method for generating a following vehicle trajectory. It does not rely on the historical trajectory of the target preceding vehicle, but directly constructs control points through the predicted driving trajectory of the target preceding vehicle and the predicted driving trajectory of the own vehicle, thereby avoiding the problem of jitter of the own vehicle's following trajectory caused by the influence of historical trajectory in traditional methods.

[0052] Specifically, the embodiment of the present invention provides a method for generating a vehicle following trajectory, combining Figure 1 As shown in the flowchart, the vehicle following trajectory generation method includes steps 101 to 104:

[0053] Step 101: In the automatic driving mode, obtaining a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle;

[0054] Step 102: performing proximal point processing on the first predicted driving trajectory to obtain position information of multiple proximal control points;

[0055] Step 103: performing remote point acquisition processing on the second predicted driving trajectory to obtain position information of multiple remote control points;

[0056] Step 104: Determine a Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, and use it to predict the following trajectory of the vehicle within the future target duration.

[0057] In this embodiment, the vehicle may be a new energy vehicle. The target preceding vehicle refers to the vehicle located in front of the vehicle and being followed by the vehicle. In the autonomous driving mode, the vehicle's onboard sensors (such as lidar, camera, millimeter-wave radar, etc.) will perceive the surrounding environment in real time. Combined with the high-precision map and positioning system, it can obtain driving information related to the vehicle (for example, steering wheel angle, vehicle speed, yaw angular velocity, etc.) in order to predict the first predicted driving trajectory of the vehicle within the future target duration (for example, the target duration is in the range of 3-5 seconds).

[0058] It should be noted that the first predicted driving trajectory is not the path the vehicle will travel within the target duration. It is primarily a predicted trajectory based on the vehicle's current driving state and is used to select Bezier curve control points. The coupling design of the first predicted driving trajectory based on the steering wheel angle and the control points of the Bezier curve equation directly maps the steering dynamics of the vehicle to the constraints of the Bezier curve's proximal control points. This avoids the discontinuity in following the vehicle caused by mechanically spliced ​​trajectories, thereby improving driving comfort.

[0059] Furthermore, this embodiment uses a target detection and tracking algorithm to identify the preceding vehicle, i.e., the target preceding vehicle. Based on the target preceding vehicle's current driving information (e.g., lateral displacement distance, longitudinal displacement distance, heading angle, etc.), a second predicted driving trajectory of the target preceding vehicle is generated. Both the first and second predicted driving trajectories are represented as a sequence of discrete points, including the position information of each point.

[0060] The control points selected based on the second predicted driving trajectory dynamically adjust their positions by taking into account the lateral and longitudinal states and heading angle of the target preceding vehicle, making the following trajectory of the vehicle more flexible while balancing smoothness and fast response.

[0061] It should be noted that Bezier curves are parametric curves commonly used in computer graphics, with their shape defined by control points. In autonomous driving, Bezier curves can be used to describe a vehicle's following trajectory. The shape of the following trajectory can be flexibly adjusted using control points to adapt to different scenarios (such as curves and lane changes). The following trajectory maintains a smooth and continuous curve, satisfying the vehicle's kinematic constraints.

[0062] Therefore, it is not difficult to find that when using the Bezier curve equation to determine the vehicle's following trajectory, the selection of control points is particularly important.

[0063] In this embodiment, to ensure smoothness and stability of the vehicle's following trajectory, control points are selected based on the first predicted trajectory of the vehicle and the second predicted trajectory of the target vehicle ahead. Specifically, in this embodiment, there are multiple control points, some of which are selected as proximal control points in the first predicted trajectory, and others as distal control points in the second predicted trajectory.

[0064] Regarding performing near-end point selection processing on the first predicted driving trajectory, specific steps may include:

[0065] using the projection of the first predicted driving trajectory on the first coordinate axis as a first longitudinal displacement segment;

[0066] uniformly inserting all proximal control points in the first longitudinal displacement segment to obtain a first coordinate of each proximal control point on the first coordinate axis;

[0067] For each proximal control point, determine the second coordinate of the proximal control point on the second coordinate axis based on the first predicted driving trajectory and the first coordinate of the proximal control point; wherein the first coordinate and the second coordinate of the proximal control point constitute the position information of the proximal control point.

[0068] In this embodiment, there are multiple proximal control points. The following content of this embodiment is described by taking the example that the number of proximal control points is 3.

[0069] In this embodiment, the vehicle coordinate system is established with the center of the rear axle of the vehicle as the origin, the first coordinate axis (also called the X axis) is the longitudinal direction (i.e. the forward direction of the vehicle), and the second coordinate axis (also called the Y axis) is the transverse direction.

[0070] Project all points in the first predicted driving trajectory onto the X-axis. The X-axis coordinate range covered by these projected points constitutes the first longitudinal displacement segment. For example, if the minimum first coordinate covered by the X-axis projections of all points in the first predicted driving trajectory is 5 and the maximum first coordinate is 25, then the first longitudinal displacement segment is [5, 25].

[0071] After determining the first longitudinal displacement segment, three proximal control points are evenly inserted into the first longitudinal displacement segment and the corresponding first coordinates are calculated. This can be understood as the three proximal control points evenly dividing the first longitudinal displacement segment into two segments, with one proximal control point serving as the starting point, one proximal control point as the midpoint, and one proximal control point as the end point.

[0072] Then, the first coordinate of each proximal control point is substituted into the first predicted driving trajectory to obtain the corresponding second coordinate. The position information of the proximal control point is composed of the first coordinate and the second coordinate of the proximal control point.

[0073] Performing proximal point processing on the first predicted driving trajectory can ensure that the proximal following trajectory matches the steering wheel direction.

[0074] Regarding performing remote point acquisition processing on the second predicted driving trajectory to obtain position information of multiple remote control points, specific steps may include:

[0075] using the projection of the second predicted driving trajectory on the first coordinate axis as a second longitudinal displacement segment;

[0076] uniformly inserting all distal control points in the second longitudinal displacement segment to obtain a first coordinate of each distal control point on the first coordinate axis;

[0077] For each remote control point, the second coordinate of the remote control point on the second coordinate axis is determined based on the second predicted driving trajectory and the second coordinate of the remote control point; wherein the first coordinate and the second coordinate of the remote control point constitute the position information of the remote control point.

[0078] In this embodiment, the method for selecting the distal control point is similar to that for the proximal control point. The vehicle coordinate system is also established with the center of the vehicle's rear axle as the origin. The first coordinate axis (also called the X-axis) is the longitudinal direction (the vehicle's forward direction), and the second coordinate axis (also called the Y-axis) is the transverse direction.

[0079] It should be noted that the number of proximal control points and the number of distal control points are related to the order of the Bezier curve equation. If, in this embodiment, the order of the Bezier curve equation is 6 and the number of proximal control points is 3, then the number of distal control points is 4. The following description of this embodiment uses the example of 4 distal control points.

[0080] Project all points in the second predicted driving trajectory onto the X-axis. The X-axis coordinate range covered by these projected points constitutes the second longitudinal displacement segment. For example, if the minimum first coordinate covered by the X-axis projections of all points in the second predicted driving trajectory is 30 and the maximum first coordinate is 42, then the second longitudinal displacement segment is [30, 42].

[0081] After determining the second longitudinal displacement segment, four distal control points are evenly inserted into the second longitudinal displacement segment and the corresponding first coordinates are calculated. It can be understood that the four distal control points evenly divide the first longitudinal displacement segment into three segments.

[0082] Then, the first coordinate of each remote control point is substituted into the second predicted driving trajectory to obtain the corresponding second coordinate. The position information of the remote control point is composed of the first coordinate and the second coordinate of the remote control point.

[0083] Performing a remote point processing operation on the second predicted driving trajectory can ensure that the remote following vehicle trajectory matches the heading of the target preceding vehicle.

[0084] After determining the position information of each proximal control point and distal control point, the Bezier curve equation can be determined by the following formula:

[0085]

[0086] Among them, the number of proximal control points is 3, when Pi is used as the proximal control point, the value range of i is 0-2; the number of distal control points is 4, when Pi is used as the distal control point, the value range of i is 3-6; t is the normalized time parameter.

[0087] In this embodiment, the parameter t may be associated with a target duration t′ (for example, the target duration is 3.6 seconds), for example: t=t′ / 3.6.

[0088] In an optional embodiment, before obtaining the first predicted driving trajectory of the host vehicle and the second predicted driving trajectory of the target preceding vehicle, the method further includes the step of generating the first predicted driving trajectory:

[0089] Obtaining the steering wheel angle, vehicle speed, and yaw rate of the vehicle, as well as the lateral displacement distance, longitudinal displacement distance, and heading angle of the target preceding vehicle;

[0090] Predicting a first predicted driving trajectory of the vehicle within the target time period in the future based on the steering wheel angle, vehicle speed, and yaw angular velocity of the vehicle;

[0091] A second predicted driving trajectory of the target preceding vehicle within the target time period in the future is predicted based on the lateral displacement distance, the longitudinal displacement distance, and the heading angle of the target preceding vehicle.

[0092] Specifically, the vehicle's internal sensors can acquire relevant driving information in real time. For example, the steering wheel angle is collected by a steering wheel angle sensor, which converts the steering wheel angle into an electrical signal based on a potentiometer or magnetoresistive effect. Vehicle speed can be measured by wheel speed sensors, which typically use Hall effect or electromagnetic induction technology to calculate wheel speed and convert it into vehicle speed. Yaw angular velocity is acquired by the gyroscope in the inertial measurement unit (IMU), which simultaneously monitors the vehicle's angular velocity and acceleration in three-dimensional space. This collected information is filtered to remove noise and ensure accuracy and stability, providing a reliable basis for subsequent trajectory prediction.

[0093] Similarly, information about the target vehicle ahead can be collected using sensors such as the vehicle's onboard radar (such as millimeter-wave radar and lidar) and cameras. For example, radar uses the reflection principle of electromagnetic waves or lasers to accurately measure the lateral and longitudinal displacement distances of the target vehicle ahead. Cameras use image recognition technology combined with computer vision algorithms to identify the outline of the preceding vehicle and calculate its position. Furthermore, multi-sensor data fusion technology integrates radar and camera information to simultaneously obtain the heading angle of the target vehicle ahead, further improving the reliability and comprehensiveness of the information.

[0094] When predicting the vehicle's first predicted driving trajectory within the target timeframe, curvature is calculated to determine the first predicted driving trajectory. It's important to note that the effect of curvature on tire cornering characteristics varies from linear to nonlinear with vehicle speed: at low speeds, curvature changes can be smoothly addressed with a small slip angle, while at high speeds, the coupled effect of curvature and the square of vehicle speed significantly amplifies the risk of cornering.

[0095] Based on this, and considering the tire's cornering characteristics during high-speed driving, this embodiment differentiates operating conditions based on vehicle speed to accurately calculate curvature. The specific steps include:

[0096] comparing the vehicle speed with a preset speed threshold;

[0097] If the vehicle speed is less than the speed threshold, the vehicle is in a low-speed operating condition;

[0098] If the vehicle speed is greater than or equal to the speed threshold, the vehicle is in a high-speed operating condition.

[0099] The speed threshold is within the range of 50-80 km / h. Under low-speed conditions, the curvature of the vehicle under the current driving state is calculated based on the steering gear ratio, vehicle wheelbase, and steering wheel angle of the vehicle to determine a first predicted driving trajectory of the vehicle within the target time period in the future.

[0100] Specifically, if the speed threshold is 50 km / h (the specific threshold can be adjusted according to the vehicle dynamics), when the vehicle speed is less than the speed threshold, the vehicle's steering characteristics are relatively stable, the tire cornering force is small, and trajectory prediction can be performed based on a simplified kinematic model.

[0101] This embodiment calculates the curvature of the vehicle under the current driving state based on the vehicle's steering ratio, vehicle wheelbase, and steering wheel angle. The steering ratio reflects the relationship between the steering wheel angle and the steering wheel angle and is typically determined by vehicle design parameters. The ratio of the steering wheel angle to the steering ratio is the steering wheel angle s; the curvature k = tan(s) / w, where s is the steering wheel angle and w is the vehicle wheelbase. By substituting the real-time steering wheel angle, the known steering ratio, and the vehicle wheelbase into the above formula, the curvature under the current driving state can be calculated.

[0102] For example, a vehicle with a wheelbase of 2.7m and a steering ratio of 15, when the steering wheel angle is 30 degrees, the steering wheel angle is 2 degrees, and the curvature k = 0.0013m -1 .

[0103] After obtaining the current curvature, assuming the vehicle maintains this curvature for the target duration in the future, the algorithm performs an iterative calculation with a time step of Δt, taking into account the vehicle's current speed v and initial heading angle. Within each time step, the vehicle's lateral displacement y = v × Δt × sin(θ) and its longitudinal displacement x = v × Δt × cos(θ), where θ is the vehicle's heading angle (which can be calculated by converting the steering wheel angle), and the change in θ Δθ = k × v × Δt. Through continuous iteration, a series of vehicle position points within the target duration can be obtained, and connecting these points forms the first predicted driving trajectory.

[0104] Under high-speed conditions, this embodiment calculates the curvature of the vehicle under the current driving state based on the vehicle speed and yaw angular velocity to determine the first predicted driving trajectory of the vehicle within the target time period in the future.

[0105] Specifically, if the speed threshold is 50 km / h (the specific threshold can be adjusted according to the vehicle's dynamic characteristics), when the vehicle speed is greater than or equal to the speed threshold, the tire cornering force has a significant impact on the vehicle's motion, and the vehicle's dynamic characteristics become more complex, requiring a dynamics-based method for trajectory prediction.

[0106] The curvature of the vehicle in its current driving state is calculated based on the vehicle speed and yaw rate. The yaw rate ω reflects the speed of the vehicle's rotation around the vertical axis. The ratio of the vehicle speed v to the yaw rate ω can be used to approximate the vehicle's turning radius R, that is, R = v / ω, from which the curvature k = ω / v can be obtained. For example, when the vehicle speed v = 80 km / h ≈ 22.2 m / s and the yaw rate ω = 0.1 rad / s, the curvature k ≈ 0.0045 m-1 .

[0107] After determining the current curvature, the vehicle is assumed to maintain this curvature for the target duration. The algorithm then iterates the calculations with a time step of Δt, taking into account the vehicle's current speed v and initial heading angle. Within each time step, the vehicle's lateral displacement y = v × Δt × sin(θ) and longitudinal displacement x = v × Δt × cos(θ), where θ is the vehicle's heading angle and the change in θ is Δθ = k × v × Δt. Through continuous iteration, a series of vehicle positions within the target duration are obtained. Connecting these points forms the first predicted trajectory.

[0108] When predicting the second predicted trajectory of the target preceding vehicle, this embodiment determines the trajectory based on the lateral displacement distance, longitudinal displacement distance, and heading angle of the target preceding vehicle. Specifically, the lateral and longitudinal displacement distances measured by the sensors are first converted to the vehicle coordinate system. Then, based on the motion characteristics of the target preceding vehicle, an appropriate prediction model (e.g., a constant velocity model, a constant acceleration model, or a nonlinear model) is selected to obtain the second predicted trajectory of the target preceding vehicle.

[0109] In summary, the embodiment of this specification provides a method for generating a vehicle-following trajectory, which obtains a first predicted driving trajectory of the vehicle and a second predicted driving trajectory of the target preceding vehicle in the automatic driving mode, wherein the target preceding vehicle refers to the vehicle in front of the vehicle following the vehicle; performs proximal point processing on the first predicted driving trajectory to obtain the position information of multiple proximal control points; performs distal point processing on the second predicted driving trajectory to obtain the position information of multiple distal control points; and determines the Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, which is used to predict the following trajectory of the vehicle within the future target duration. In this way, the robustness of the following vehicle is improved by combining the high-order Bezier curve with the dynamic adjustment mechanism of the control points. At the same time, by generating some control points through the high-order Bezier curve and the predicted driving trajectory of the vehicle, the smoothness of the following trajectory under complex road conditions is increased, and the passengers' motion sickness is reduced.

[0110] Based on the same inventive concept, combined Figure 2 As shown, an embodiment of the present invention further provides a vehicle following trajectory generating device, comprising:

[0111] a trajectory prediction module, configured to obtain, in the autonomous driving mode, a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle;

[0112] A first point-taking module is configured to perform proximal point-taking processing on the first predicted driving trajectory to obtain position information of a plurality of proximal control points;

[0113] A second point-taking module is configured to perform remote point-taking processing on the second predicted driving trajectory to obtain position information of a plurality of remote control points;

[0114] The vehicle following trajectory module is used to determine the Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, so as to predict the vehicle following trajectory within the future target time.

[0115] Optionally, the trajectory prediction module is also used to:

[0116] Obtaining the steering wheel angle, vehicle speed, and yaw rate of the vehicle, as well as the lateral displacement distance, longitudinal displacement distance, and heading angle of the target preceding vehicle;

[0117] Predicting a first predicted driving trajectory of the vehicle within the target time period in the future based on the steering wheel angle, vehicle speed, and yaw angular velocity of the vehicle;

[0118] A second predicted driving trajectory of the target preceding vehicle within the target time period in the future is predicted based on the lateral displacement distance, the longitudinal displacement distance, and the heading angle of the target preceding vehicle.

[0119] Optionally, the trajectory prediction module is also used to:

[0120] Under low-speed conditions, calculating the curvature of the vehicle under the current driving state based on the steering gear ratio, the vehicle wheelbase, and the steering wheel angle of the vehicle, so as to determine a first predicted driving trajectory of the vehicle within the target time period in the future;

[0121] Under high-speed conditions, the curvature of the vehicle in the current driving state is calculated based on the vehicle speed and the yaw angular velocity to determine a first predicted driving trajectory of the vehicle within the target time period in the future.

[0122] Optionally, the trajectory prediction module is also used to:

[0123] comparing the vehicle speed with a preset speed threshold;

[0124] If the vehicle speed is less than the speed threshold, the vehicle is in a low-speed operating condition;

[0125] If the vehicle speed is greater than or equal to the speed threshold, the vehicle is in a high-speed operating condition.

[0126] Optionally, the first point-taking module is further configured to:

[0127] using the projection of the first predicted driving trajectory on the first coordinate axis as a first longitudinal displacement segment;

[0128] uniformly inserting all proximal control points in the first longitudinal displacement segment to obtain a first coordinate of each proximal control point on the first coordinate axis;

[0129] For each proximal control point, determine the second coordinate of the proximal control point on the second coordinate axis based on the first predicted driving trajectory and the first coordinate of the proximal control point; wherein the first coordinate and the second coordinate of the proximal control point constitute the position information of the proximal control point.

[0130] Optionally, the second point module is further used to:

[0131] using the projection of the second predicted driving trajectory on the first coordinate axis as a second longitudinal displacement segment;

[0132] uniformly inserting all distal control points in the second longitudinal displacement segment to obtain a first coordinate of each distal control point on the first coordinate axis;

[0133] For each remote control point, the second coordinate of the remote control point on the second coordinate axis is determined based on the second predicted driving trajectory and the second coordinate of the remote control point; wherein the first coordinate and the second coordinate of the remote control point constitute the position information of the remote control point.

[0134] Optionally, the vehicle tracking module is also used to:

[0135] According to the position information of each proximal control point and the position information of each distal control point, the Bezier curve equation is determined by the following formula:

[0136]

[0137] Among them, the number of proximal control points is 3, when Pi is used as the proximal control point, the value range of i is 0-2; the number of distal control points is 4, when Pi is used as the distal control point, the value range of i is 3-6; t is the normalized time parameter.

[0138] In summary, the embodiment of this specification provides a vehicle following trajectory generation device, which obtains a first predicted driving trajectory of the vehicle and a second predicted driving trajectory of the target preceding vehicle in the automatic driving mode, wherein the target preceding vehicle refers to the vehicle in front of the vehicle following the vehicle; performs proximal point processing on the first predicted driving trajectory to obtain the position information of multiple proximal control points; performs distal point processing on the second predicted driving trajectory to obtain the position information of multiple distal control points; determines the Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, and is used to predict the following trajectory of the vehicle within the future target time period. In this way, the robustness of the vehicle following is improved by combining the high-order Bezier curve with the dynamic adjustment mechanism of the control points. At the same time, by generating some control points through the high-order Bezier curve and the predicted driving trajectory of the vehicle, the smoothness of the following trajectory under complex road conditions is increased, and the passengers' motion sickness is reduced.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the vehicle following trajectory generating device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0140] Based on the same inventive concept, an embodiment of the present invention also provides a controller, which includes a vehicle following trajectory generation device, a memory, a processor and a communication unit. The memory stores machine-readable instructions executable by the processor. When the controller is running, the processor and the memory communicate through a bus, the processor executes the machine-readable instructions, and executes the vehicle following trajectory generation method.

[0141] The memory, processor, and communication unit components are electrically connected to each other, directly or indirectly, to enable signal transmission or interaction. For example, these components may be electrically connected to each other via one or more communication buses or signal lines. The vehicle-following trajectory generation device includes at least one software function module that can be stored in the memory in the form of software or firmware. The processor is configured to execute the executable module stored in the memory (e.g., the software function module or computer program included in the vehicle-following trajectory generation device).

[0142] Among them, the memory can be, but is 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.

[0143] In some embodiments, the processor is used to perform one or more functions described in this embodiment. In some embodiments, the processor may include one or more processing cores (eg, a single-core processor (S) or a multi-core processor (S)).

[0144] In this embodiment, the memory is used to store the program, and the processor is used to execute the program after receiving the execution instruction. The process definition method disclosed in any implementation of this embodiment can be applied to the processor or implemented by the processor.

[0145] The communication unit is used to establish a communication connection between the controller and other devices through the network, and to send and receive data through the network.

[0146] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the controller described above can refer to the corresponding process in the aforementioned method, and will not be elaborated here.

[0147] Based on the same inventive concept, an embodiment of the present invention further provides a vehicle, comprising a vehicle body and a controller installed in the vehicle body, wherein the controller is used to implement the aforementioned vehicle-following trajectory generation method.

[0148] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the vehicle controller described above can refer to the corresponding process in the aforementioned method and will not be elaborated here.

[0149] The above are merely various embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for generating a vehicle-following trajectory, characterized in that: include: In the automatic driving mode, obtaining a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle; Performing proximal point processing on the first predicted driving trajectory to obtain position information of multiple proximal control points; Performing remote point processing on the second predicted driving trajectory to obtain position information of multiple remote control points; Based on the position information of each proximal control point and the position information of each distal control point, a Bezier curve equation is determined to predict the following trajectory of the vehicle within a future target duration.

2. The method according to claim 1, characterized in that Before obtaining the first predicted driving trajectory of the host vehicle and the second predicted driving trajectory of the target preceding vehicle, the method further includes: Obtaining the steering wheel angle, vehicle speed, and yaw rate of the vehicle, as well as the lateral displacement distance, longitudinal displacement distance, and heading angle of the target preceding vehicle; Predicting a first predicted driving trajectory of the vehicle within the target time period in the future based on the steering wheel angle, the vehicle speed, and the yaw rate of the vehicle; A second predicted driving trajectory of the target preceding vehicle within the target time period in the future is predicted based on the lateral displacement distance, the longitudinal displacement distance, and the heading angle of the target preceding vehicle.

3. The method according to claim 2, characterized in that The predicting, based on the steering wheel angle, the vehicle speed, and the yaw rate of the vehicle, a first predicted driving trajectory of the vehicle within the target time period in the future includes: Under low-speed conditions, calculating the curvature of the vehicle under the current driving state based on the steering gear ratio, the vehicle wheelbase, and the steering wheel angle of the vehicle, so as to determine a first predicted driving trajectory of the vehicle within the target time period in the future; Under high-speed conditions, the curvature of the vehicle in the current driving state is calculated based on the vehicle speed and the yaw angular velocity to determine a first predicted driving trajectory of the vehicle within the target time period in the future.

4. The method according to claim 3, characterized in that Before calculating the curvature of the vehicle in the current driving state according to the steering gear ratio, the vehicle wheelbase, and the steering wheel angle of the vehicle under the low-speed condition, the method further includes: comparing the vehicle speed with a preset speed threshold; If the vehicle speed is less than the speed threshold, the vehicle is in a low-speed operating condition; If the vehicle speed is greater than or equal to the speed threshold, the vehicle is in a high-speed operating condition.

5. The method according to claim 1, wherein The performing of proximal point acquisition processing on the first predicted driving trajectory to obtain position information of a plurality of proximal control points includes: using the projection of the first predicted driving trajectory on the first coordinate axis as a first longitudinal displacement segment; uniformly inserting all proximal control points in the first longitudinal displacement segment to obtain a first coordinate of each proximal control point on the first coordinate axis; For each proximal control point, determine the second coordinate of the proximal control point on the second coordinate axis based on the first predicted driving trajectory and the first coordinate of the proximal control point; wherein the first coordinate and the second coordinate of the proximal control point constitute the position information of the proximal control point.

6. The method according to claim 1, characterized in that The performing remote point acquisition processing on the second predicted driving trajectory to obtain position information of multiple remote control points includes: using the projection of the second predicted driving trajectory on the first coordinate axis as a second longitudinal displacement segment; uniformly inserting all distal control points in the second longitudinal displacement segment to obtain a first coordinate of each distal control point on the first coordinate axis; For each remote control point, the second coordinate of the remote control point on the second coordinate axis is determined based on the second predicted driving trajectory and the second coordinate of the remote control point; wherein the first coordinate and the second coordinate of the remote control point constitute the position information of the remote control point.

7. The method according to claim 1, characterized in that Determining the Bezier curve equation according to the position information of each proximal control point and the position information of each distal control point includes: According to the position information of each proximal control point and the position information of each distal control point, the Bezier curve equation is determined by the following formula: Among them, the number of proximal control points is 3, when Pi is used as the proximal control point, the value range of i is 0-2; the number of distal control points is 4, when Pi is used as the distal control point, the value range of i is 3-6; t is the normalized time parameter.

8. A vehicle following trajectory generating device, characterized in that: include: a trajectory prediction module, configured to obtain, in the autonomous driving mode, a first predicted driving trajectory of the host vehicle and a second predicted driving trajectory of a target preceding vehicle, wherein the target preceding vehicle is a vehicle in front of the host vehicle; A first point-taking module is configured to perform proximal point-taking processing on the first predicted driving trajectory to obtain position information of a plurality of proximal control points; A second point-taking module is configured to perform remote point-taking processing on the second predicted driving trajectory to obtain position information of a plurality of remote control points; The vehicle following trajectory module is used to determine the Bezier curve equation based on the position information of each proximal control point and the position information of each distal control point, so as to predict the vehicle following trajectory within the future target time.

9. A controller, characterized in that: The controller includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for generating a vehicle-following trajectory according to any one of claims 1 to 7 is implemented.

10. A vehicle, characterized in that: The vehicle includes a vehicle body and a controller installed in the vehicle body, wherein the controller executes the vehicle following trajectory generation method described in any one of claims 1-7.

Images