Driving track adjusting method and device, computer equipment and readable storage medium

Abstract

The invention discloses a driving track adjustment method and device, computer equipment and a readable storage medium, and relates to the technical field of driving track adjustment. The method comprises the steps of obtaining an original trajectory, and predicting a new trajectory according to the original trajectory; obtaining new trajectory points in the new trajectory, and respectively obtaining original trajectory minimum distance points and original trajectory discrete points corresponding to the new trajectory points on the original trajectory; calculating a distance evaluation value corresponding to each new track point according to each new track point, the corresponding original track minimum distance point and the corresponding original track discrete point; calculating the transverse deviation degree, the longitudinal deviation degree and the transverse and longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; performing weighted summation on the transverse deviation degree, the longitudinal deviation degree and the transverse and longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory; and adjusting the current driving track according to the comprehensive deviation degree. In this way, the deviation degree of the new trajectory and the original trajectory is quantified from multiple dimensions, the accuracy of deviation analysis is improved, and therefore the driving precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of driving trajectory adjustment, and particularly to a driving trajectory adjustment method, device, computer device, and readable storage medium. Background Art

[0002] In autonomous driving technology, a trajectory control module receives a trajectory issued by a trajectory planning module and controls a chassis to execute to accurately track the issued trajectory. In related technologies, characteristics such as curvature, speed, and acceleration of the trajectory planned by autonomous driving exceed the physical limits executable by the chassis, or do not conform to the chassis kinematic state equation, resulting in deviations and inaccurate autonomous driving trajectories. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and provide a driving trajectory adjustment method, device, computer device, and readable storage medium that can improve the accuracy of autonomous driving.

[0004] The present invention provides the following technical solutions:

[0005] In a first aspect, the present invention proposes a driving trajectory adjustment method, including:

[0006] Obtain an original trajectory and predict a new trajectory according to the original trajectory;

[0007] Obtain new trajectory points in the new trajectory, and respectively obtain the corresponding original trajectory minimum distance points and original trajectory discrete points on the original trajectory for each of the new trajectory points; the original trajectory minimum distance point is the point on the original trajectory with the minimum distance from the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point;

[0008] Calculate the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point;

[0009] Calculate the lateral deviation degree, longitudinal deviation degree, and transverse and longitudinal fusion deviation degree of the new trajectory according to each of the distance evaluation values;

[0010] Perform weighted summation on the lateral deviation degree, the longitudinal deviation degree, and the transverse and longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory;

[0011] Adjust the current driving trajectory according to the comprehensive deviation degree.

[0012] In an embodiment, the distance evaluation value includes a first straight-line distance value. According to each new trajectory point and its corresponding original trajectory minimum distance point, the distance evaluation value corresponding to each new trajectory point includes:

[0013] For each of the new trajectory points, calculate the straight-line distance between the new trajectory point and the minimum distance point of the original trajectory to obtain the first straight-line distance value corresponding to the new trajectory point.

[0014] In one embodiment, calculating the lateral deviation degree of the new trajectory according to each of the distance evaluation values includes:

[0015] Take the absolute value of the first straight-line distance value corresponding to each of the new trajectory points to obtain a plurality of first absolute values;

[0016] Accumulate each of the first absolute values to obtain a first accumulated value;

[0017] Divide the first accumulated value by the total length of the original trajectory to obtain the lateral deviation degree.

[0018] In one embodiment, the distance evaluation value includes a second straight-line distance value. Calculating the distance evaluation value corresponding to each of the new trajectory points according to each of the new trajectory points, their corresponding minimum distance points of the original trajectory, and the discrete points of the original trajectory includes:

[0019] For each of the new trajectory points, calculate the straight-line distance between the new trajectory point and the discrete points of the original trajectory to obtain the second straight-line distance value corresponding to the new trajectory point.

[0020] In one embodiment, calculating the lateral and longitudinal fusion deviation degree of the new trajectory according to each of the distance evaluation values includes:

[0021] Take the absolute value of the second straight-line distance value corresponding to each of the new trajectory points to obtain a plurality of second absolute values;

[0022] Accumulate each of the second absolute values to obtain a second accumulated value;

[0023] Divide the second accumulated value by the total time of the original trajectory to obtain the lateral and longitudinal fusion deviation degree.

[0024] In one embodiment, the distance evaluation value includes a curve distance value. Calculating the distance evaluation value corresponding to each of the new trajectory points according to each of the new trajectory points and their corresponding minimum distance points of the original trajectory includes:

[0025] For each of the new trajectory points, calculate the curve distance between the minimum distance point of the original trajectory and the discrete points of the original trajectory to obtain the curve distance value corresponding to the new trajectory point.

[0026] In one embodiment, calculating the longitudinal deviation degree of the new trajectory according to the distance evaluation value includes:

[0027] Take the absolute value of the curve distance value corresponding to each of the new trajectory points to obtain a plurality of third absolute values;

[0028] Accumulate each of the third absolute values to obtain a third accumulated value;

[0029] Divide the third accumulated value by the total time of the original trajectory to obtain the longitudinal deviation degree.

[0030] In a second aspect, the present invention provides a driving trajectory adjustment device, comprising:

[0031] A prediction module, configured to obtain an original trajectory and predict a new trajectory according to the original trajectory;

[0032] An acquisition module, configured to obtain new trajectory points in the new trajectory, and respectively obtain corresponding original trajectory minimum distance points and original trajectory discrete points on the original trajectory for each of the new trajectory points; the original trajectory minimum distance point is the point on the original trajectory that is closest to the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point; a first calculation module, configured to calculate a distance evaluation value corresponding to each of the new trajectory points according to each of the new trajectory points and their corresponding original trajectory minimum distance points and original trajectory discrete points;

[0033] A second calculation module, configured to calculate a lateral deviation degree, a longitudinal deviation degree, and a lateral-longitudinal fusion deviation degree of the new trajectory according to each of the distance evaluation values;

[0034] An analysis module, configured to perform weighted summation on the lateral deviation degree, the longitudinal deviation degree, and the lateral-longitudinal fusion deviation degree to obtain a comprehensive deviation degree of the new trajectory;

[0035] An adjustment module, configured to adjust the current driving trajectory according to the comprehensive deviation degree.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the driving trajectory adjustment method described in the first aspect is implemented.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the driving trajectory adjustment method described in the first aspect is implemented.

[0038] The driving trajectory adjustment method, device, computer device and readable storage medium disclosed by the present invention obtain an original trajectory and predict a new trajectory according to the original trajectory; obtain new trajectory points in the new trajectory, and respectively obtain the corresponding original trajectory minimum distance points and original trajectory discrete points of each new trajectory point on the original trajectory; calculate the distance evaluation values corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point; calculate the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; perform weighted summation on the lateral deviation degree, the longitudinal deviation degree and the transverse-longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory; and adjust the current driving trajectory according to the comprehensive deviation degree. In this way, the deviation degree between the new trajectory and the original trajectory is quantified from multiple dimensions through the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree, breaking through the limitation of single-dimensional evaluation and improving the accuracy of deviation analysis; and further performing weighted summation by adjusting the weights of the lateral, longitudinal and transverse-longitudinal fusion deviation degrees to obtain a comprehensive deviation degree that can flexibly adapt to different scenario requirements, and adjusting the current driving trajectory according to the comprehensive deviation degree, so as to effectively adjust the driving trajectory and further improve the driving accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the present invention, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the protection scope of the present invention. In each drawing, similar components are numbered similarly.

[0040] Figure 1 FIG. shows a flowchart of the driving trajectory adjustment method proposed in this embodiment;

[0041] Figure 2 FIG. shows another flowchart of the driving trajectory adjustment method proposed in this embodiment;

[0042] Figure 3 FIG. shows still another flowchart of the driving trajectory adjustment method proposed in this embodiment;

[0043] Figure 4 FIG. shows yet another flowchart of the driving trajectory adjustment method proposed in this embodiment;

[0044] Figure 5 FIG. shows a structural diagram of the driving trajectory adjustment device proposed in this embodiment.

[0045] DESCRIPTION OF THE REFERENCE NUMERALS

[0046] 500 - Driving trajectory adjustment device; 501 - Prediction module; 502 - Acquisition module; 503 - First calculation module; 504 - Second calculation module; 505 - Analysis module; 506 - Adjustment module. Detailed implementation manner

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0048] Generally, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations. 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 claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0049] In the following text, the terms "include", "have" and their cognates that can be used in various embodiments of the present invention are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0050] In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0051] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in various embodiments of the present invention.

[0052] Embodiment 1

[0053] The embodiments of the present disclosure provide a driving trajectory adjustment method for quantifying the deviation between the original trajectory and the new trajectory from multiple dimensions, thereby improving the accuracy of deviation analysis of the driving trajectory, effectively adjusting the driving trajectory, and further improving the driving accuracy.

[0054] Please refer to Figure 1, the driving trajectory adjustment method includes steps S101 to S106, and the following is a detailed description of each step.

[0055] Step S101, obtain the original trajectory and predict a new trajectory according to the original trajectory.

[0056] In this embodiment, after obtaining the original trajectory, under the conditions of meeting the chassis performance limit, kinematic constraints, etc., according to the received original trajectory, a new trajectory is predicted through a trajectory derivation algorithm. The original trajectory is a trajectory composed of a set of discrete trajectory points arranged in chronological order issued by the trajectory planning module. Each discrete trajectory point in the original trajectory includes at least, but is not limited to, the trajectory point timestamp, relative time or absolute time, vehicle body position coordinates, horizontal axis component, vehicle body position coordinates, vertical axis component, vehicle body direction angle, steering wheel rudder angle, and vehicle body speed.

[0057] Among them, the trajectory derivation algorithm includes open-loop derivation, closed-loop control derivation, and optimization derivation. All three types of algorithms use integrators, and commonly used ones include forward Euler, fourth-order Runge-Kutta method (RK4), CVODES, etc.

[0058] For the open-loop derivation algorithm, first, the new trajectory is initialized as an empty queue, and the starting point X0_original of the original trajectory is inserted into the end of the new trajectory queue, denoted as the starting point X0_new; take the trajectory point at the end of the new trajectory queue, denoted as Xk_new; take the rudder angle and linear velocity Uk_original of the corresponding trajectory point Xk_original of the original trajectory, and obtain the control command Uk_new after constraint processing (such as limiting the maximum rudder angle, maximum speed, maximum acceleration, etc.). Take Xk_new and Uk_new as the inputs of the vehicle kinematic equation, and use the integrator to obtain the next trajectory point Xk+1_new, which is inserted into the end of the new trajectory queue; until all points of the original trajectory are traversed, a new trajectory composed of a series of new trajectory points X0_new,..., Xn_new can be obtained. The open-loop derivation algorithm only performs initialization once, and subsequent points are iterated in sequence, and there will be cumulative errors; to eliminate the cumulative errors, after a certain number of iterations are completed, re-initialization can be performed and the trajectory points can be continued to be iterated. This algorithm is simple to implement and has less solving time consumption.

[0059] For the closed-loop control derivation algorithm, the overall algorithm process is similar to the open-loop derivation, but the control command Uk_new is obtained through a certain trajectory control algorithm (such as PID\Pure_pursuit\Stanley, etc.). The calculation method ensures convergence and there is no problem of cumulative errors.

[0060] For the optimization derivation algorithm, the original trajectory is used as the reference trajectory, and the vehicle performance parameter limits are used as hard constraints. Optimization algorithms such as Model Predictive Control (MPC) and Iterative Linear Quadratic Regulator (CiLQR) are used to solve for the new trajectory. This algorithm can calculate the optimal solution that satisfies various condition constraints and has a more accurate evaluation.

[0061] Step S102: Obtain the new trajectory points in the new trajectory, and respectively obtain the corresponding original trajectory minimum distance points and original trajectory discrete points of each of the new trajectory points on the original trajectory.

[0062] In this embodiment, the new trajectory points in the new trajectory are obtained, and each new trajectory point is matched with the original trajectory by the nearest neighbor method to obtain the corresponding original trajectory minimum distance points and original trajectory discrete points of each new trajectory point on the original trajectory. Among them, the original trajectory minimum distance point is used to directly reflect the true nearest relationship between the new trajectory point and the continuous curve of the original trajectory, and the original trajectory discrete point can be used to quickly evaluate the deviation between the new trajectory and the original trajectory discrete point.

[0063] Among them, the original trajectory minimum distance point is the point on the original trajectory with the minimum distance from the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point.

[0064] Exemplarily, for the i-th new trajectory point Xk_new, find the point Xk_original_c_min on the original trajectory that is closest to Xi_new, and take Xk_original_c_min as the original trajectory minimum distance point Xk_original_c_min corresponding to the new trajectory point Xk_new; correspondingly, for the i-th new trajectory point Xk_new, the original trajectory discrete point Xk_original corresponding to Xk_new can be found on the original trajectory according to the timestamp.

[0065] Step S103: Calculate the distance evaluation values corresponding to each of the new trajectory points according to each of the new trajectory points and their corresponding original trajectory minimum distance points and original trajectory discrete points.

[0066] In this embodiment, according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point, calculate the distance evaluation value of each new trajectory point. The distance evaluation value is a quantitative index that comprehensively reflects the deviation between the new trajectory point and the original trajectory.

[0067] Step S104: Calculate the lateral deviation degree, longitudinal deviation degree, and transverse and longitudinal fusion deviation degree of the new trajectory according to each of the distance evaluation values.

[0068] In this embodiment, the lateral deviation degree, the longitudinal deviation degree, and the lateral-longitudinal fusion deviation degree of the new trajectory are calculated according to each distance evaluation value. Among them, the lateral deviation degree measures the rationality of the new trajectory in the direction perpendicular to the reference trajectory, and reflects whether the trajectory deviates from the safe area; the longitudinal deviation degree measures the rationality of the new trajectory in the direction along the reference trajectory, and reflects whether the trajectory meets the speed, acceleration, and time constraints; the lateral-longitudinal fusion deviation degree combines the lateral and longitudinal constraints, reflects the overall rationality of the trajectory in the spatial and temporal dimensions, and avoids conflicts caused by single-dimensional optimization.

[0069] Step S105: Perform weighted summation on the lateral deviation degree, the longitudinal deviation degree, and the lateral-longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory.

[0070] In this embodiment, the lateral deviation degree, the longitudinal deviation degree, and the lateral-longitudinal fusion deviation degree are weighted and summed to obtain the comprehensive deviation degree of the new trajectory, which is used for the pre-check of the trajectory control module, realizes the multi-dimensional quantification of the deviation degree between the new trajectory and the original trajectory, and improves the accuracy of driving trajectory analysis; at the same time, the weights during weighted summation can be adaptively adjusted according to different scenario requirements.

[0071] When the comprehensive deviation degree is closer to 1, it indicates that the new trajectory has a serious deviation (such as frequent lane changes and sudden braking), and the feasibility is lower; when the comprehensive deviation degree is closer to 0, it indicates that the new trajectory is highly consistent with the original trajectory both laterally and longitudinally, and the feasibility is higher. When the feasibility is poor, a warning message can be issued or even the execution of autonomous driving can be stopped, thereby realizing the auxiliary judgment of the factors affecting the trajectory tracking effect, and it can also be used to laterally evaluate and compare the advantages and disadvantages of different planning algorithms of the trajectory planning module.

[0072] Step S106: Adjust the current driving trajectory according to the comprehensive deviation degree.

[0073] In this embodiment, the current driving trajectory is adjusted according to the comprehensive deviation degree, so as to effectively adjust the driving trajectory and further improve the driving accuracy.

[0074] In a specific embodiment, the distance evaluation value includes a first straight-line distance value, and step S103 includes: for each of the new trajectory points, calculate the straight-line distance between the new trajectory point and the minimum distance point of the original trajectory to obtain the first straight-line distance value corresponding to the new trajectory point.

[0075] In this embodiment, for each new trajectory point, calculate the straight-line distance between the new trajectory point and its corresponding minimum distance point of the original trajectory to obtain the first straight-line distance value corresponding to each new trajectory point. The first straight-line distance value can be the Euclidean distance between the new trajectory point Xk_new and the minimum distance point Xk_original_c_min of the original trajectory.

[0076] Please refer toFigure 2 , in a specific embodiment, step S104 includes steps S201 to S203, and the following is a detailed description of each step.

[0077] Step S201: Take the absolute value of the first linear distance value corresponding to each of the new trajectory points to obtain a plurality of first absolute values.

[0078] In this embodiment, take the absolute value of the first linear distance value corresponding to each new trajectory point to obtain a plurality of first absolute values, thereby eliminating the positive and negative nature of the distance (such as the sign difference of the left and right deviation of the trajectory), and only retaining the geometric magnitude of the deviation, which is convenient for subsequent accumulation and normalization.

[0079] Step S202: Accumulate each of the first absolute values to obtain a first accumulated value.

[0080] In this embodiment, accumulate each of the first absolute values to obtain a first accumulated value, thereby quantifying the total geometric error of the new trajectory points deviating from the original trajectory and reflecting the overall lateral deviation degree of the trajectory.

[0081] Step S203: Divide the first accumulated value by the total length of the original trajectory to obtain the lateral deviation degree.

[0082] In this embodiment, divide the first accumulated value by the total length of the original trajectory to obtain the lateral deviation degree, thereby normalizing the total error to the scale of the original trajectory length and obtaining a dimensionless lateral deviation degree score, which is convenient for comparing the lateral rationality between different trajectories.

[0083] In a specific embodiment, the distance evaluation value includes a second linear distance value, and step S103 includes: for each of the new trajectory points, calculate the linear distance between the new trajectory point and the discrete point of the original trajectory to obtain the second linear distance value corresponding to the new trajectory point.

[0084] In this embodiment, for each new trajectory point, calculate the linear distance between each new trajectory point and its corresponding discrete point of the original trajectory to obtain the second linear distance value corresponding to the new trajectory point. The second linear distance value reflects the degree of geometric deviation of the new trajectory point from the original trajectory.

[0085] Please refer to Figure 3 , in a specific embodiment, step S104 includes steps S301 to S303, and the following is a detailed description of each step.

[0086] Step S301: Take the absolute value of the second linear distance value corresponding to each of the new trajectory points to obtain a plurality of second absolute values.

[0087] In this embodiment, the absolute values of the second straight-line distance values corresponding to each new trajectory point are taken to obtain a plurality of second absolute values, which are used to eliminate the positive and negative signs of the distances, only focus on the geometric amplitude of the deviation, and avoid the cancellation of positive and negative distances with each other.

[0088] Step S302: Accumulate each of the second absolute values to obtain a second accumulated value.

[0089] In this embodiment, each of the second absolute values is accumulated to obtain a second accumulated value, so as to quantify the total geometric deviation amount between the new trajectory point set and the original trajectory and reflect the overall deviation degree.

[0090] Step S303: Divide the second accumulated value by the total time of the original trajectory to obtain the horizontal and vertical fusion deviation degree.

[0091] In this embodiment, the second accumulated value is divided by the total time of the original trajectory to obtain the horizontal and vertical fusion deviation degree. Normalize the total geometric deviation amount to the time dimension to reflect the average deviation degree per unit time and facilitate the horizontal comparison between different trajectories.

[0092] In a specific embodiment, the distance evaluation value includes a curve distance value, and step S103 includes: for each of the new trajectory points, calculate the curve distance between the minimum distance point of the original trajectory and the discrete points of the original trajectory to obtain the curve distance value corresponding to the new trajectory point.

[0093] In this embodiment, for each new trajectory point, based on the original trajectory curve, calculate the curve distance between the minimum distance point of the original trajectory corresponding to the new trajectory point and the discrete points of the original trajectory corresponding to the new trajectory point to obtain the curve distance value corresponding to the new trajectory point.

[0094] Please refer to Figure 4 , in a specific embodiment, step S104 includes steps S401 to S403, and the following will explain each step in detail.

[0095] Step S401: Take the absolute values of the curve distance values corresponding to each of the new trajectory points to obtain a plurality of third absolute values.

[0096] In this embodiment, the absolute values of the curve distance values corresponding to each new trajectory point are taken to obtain a plurality of third absolute values, so as to convert the deviation direction (positive / negative) of the curve distance into a scalar value and only focus on the deviation degree.

[0097] Step S402: Accumulate each of the third absolute values to obtain a third accumulated value.

[0098] In this embodiment, each of the third absolute values is accumulated to obtain a third accumulated value to quantify the total deviation amount between the new trajectory point set and the original trajectory.

[0099] Step S403: Divide the third accumulated value by the total time of the original trajectory to obtain the longitudinal deviation degree.

[0100] In this embodiment, dividing the third accumulated value by the total time of the original trajectory to obtain the longitudinal deviation degree, so as to obtain the average trajectory deviation intensity per unit time, making the result independent of the trajectory duration.

[0101] The driving trajectory adjustment method proposed in this embodiment obtains the original trajectory and predicts a new trajectory according to the original trajectory; obtains the new trajectory points in the new trajectory, and respectively obtains the corresponding original trajectory minimum distance points and original trajectory discrete points of each new trajectory point on the original trajectory; calculates the distance evaluation values corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point; calculates the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; performs weighted summation on the lateral deviation degree, the longitudinal deviation degree and the transverse-longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory; adjusts the current driving trajectory according to the comprehensive deviation degree. In this way, the deviation degree between the new trajectory and the original trajectory is quantified from multiple dimensions through the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree, breaking through the limitations of single-dimensional evaluation and improving the accuracy of deviation analysis; and further performing weighted summation by adjusting the weights of the lateral, longitudinal and transverse-longitudinal fusion deviation degrees to obtain a comprehensive deviation degree that can flexibly adapt to different scenario requirements, so as to realize the feasibility evaluation of the driving trajectory, and then effectively adjust the driving trajectory and improve the driving accuracy.

[0102] Embodiment 2

[0103] In addition, an embodiment of the present disclosure provides a driving trajectory adjustment device 500. Please refer to Figure 5 , including:

[0104] A prediction module 501, configured to obtain an original trajectory and predict a new trajectory according to the original trajectory;

[0105] An acquisition module 502, configured to obtain the new trajectory points in the new trajectory, and respectively obtain the corresponding original trajectory minimum distance points and original trajectory discrete points of each new trajectory point on the original trajectory; the original trajectory minimum distance point is the point on the original trajectory with the smallest distance from the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point;

[0106] A first calculation module 503, configured to calculate the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point;

[0107] The second calculation module 504 is configured to calculate the lateral deviation, the longitudinal deviation, and the lateral-longitudinal fusion deviation of the new trajectory according to each of the distance evaluation values;

[0108] The analysis module 505 is configured to perform a weighted sum of the lateral deviation, the longitudinal deviation, and the lateral-longitudinal fusion deviation to obtain the comprehensive deviation of the new trajectory.

[0109] The adjustment module 506 is configured to adjust the current driving trajectory according to the comprehensive deviation.

[0110] Optionally, the distance evaluation value includes a first straight-line distance value. The first calculation module 503 is further configured to calculate, for each of the new trajectory points, the straight-line distance between the new trajectory point and the minimum distance point of the original trajectory, to obtain the first straight-line distance value corresponding to the new trajectory point.

[0111] Optionally, the second calculation module 504 is further configured to take the absolute value of each of the first straight-line distance values corresponding to the new trajectory points to obtain a plurality of first absolute values; accumulate each of the first absolute values to obtain a first accumulated value; divide the first accumulated value by the total length of the original trajectory to obtain the lateral deviation.

[0112] Optionally, the distance evaluation value includes a second straight-line distance value. The first calculation module 503 is further configured to calculate, for each of the new trajectory points, the straight-line distance between the new trajectory point and the discrete point of the original trajectory, to obtain the second straight-line distance value corresponding to the new trajectory point.

[0113] Optionally, the second calculation module 504 is further configured to take the absolute value of each of the second straight-line distance values corresponding to the new trajectory points to obtain a plurality of second absolute values; accumulate each of the second absolute values to obtain a second accumulated value; divide the second accumulated value by the total time of the original trajectory to obtain the lateral-longitudinal fusion deviation.

[0114] Optionally, the distance evaluation value includes a curve distance value. The first calculation module 503 is further configured to calculate, for each of the new trajectory points, the curve distance between the minimum distance point of the original trajectory and the discrete point of the original trajectory, to obtain the curve distance value corresponding to the new trajectory point.

[0115] Optionally, the second calculation module 504 is further configured to take the absolute value of each of the curve distance values corresponding to the new trajectory points to obtain a plurality of third absolute values; accumulate each of the third absolute values to obtain a third accumulated value; divide the third accumulated value by the total time of the original trajectory to obtain the longitudinal deviation.

[0116] The device provided by the embodiments of the present disclosure can execute the steps of the driving trajectory adjustment method provided in Embodiment 1. To avoid repetition, details are not described herein again.

[0117] The driving trajectory adjustment device proposed in this embodiment acquires the original trajectory and predicts a new trajectory based on the original trajectory; acquires new trajectory points in the new trajectory, and respectively acquires the corresponding original trajectory minimum distance points and original trajectory discrete points of each new trajectory point on the original trajectory; calculates the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point; calculates the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; performs weighted summation on the lateral deviation degree, the longitudinal deviation degree and the transverse-longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory. In this way, the deviation degree between the new trajectory and the original trajectory is quantified from multiple dimensions through the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree, breaking through the limitation of single-dimensional evaluation and improving the accuracy of deviation analysis; and further performing weighted summation by adjusting the weights of the lateral, longitudinal and transverse-longitudinal fusion deviation degrees to obtain a comprehensive deviation degree that can flexibly adapt to different scenario requirements, and adjusting the current driving trajectory according to the comprehensive deviation degree, so as to realize the feasibility evaluation of the driving trajectory, and then effectively adjust the driving trajectory and improve the driving accuracy.

[0118] Embodiment 3

[0119] In addition, an embodiment of the present disclosure provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the driving trajectory adjustment method described in Embodiment 1 is implemented.

[0120] The device provided by the embodiment of the present disclosure can execute the steps of the driving trajectory adjustment method provided in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0121] Embodiment 4

[0122] An embodiment of the present disclosure proposes a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the driving trajectory adjustment method described in Embodiment 1 of this embodiment is implemented.

[0123] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk or an optical disc, etc.

[0124] The computer-readable storage medium provided by this embodiment can implement the driving trajectory adjustment method provided in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0125] In all examples shown and described herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0126] It should be noted that like reference numerals and letters refer to like items in the following figures. Thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

[0127] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention.

Claims

1. A driving trajectory adjustment method, characterized in that Including: Obtain an original trajectory and predict a new trajectory based on the original trajectory; Obtain new trajectory points in the new trajectory, and respectively obtain the corresponding original trajectory minimum distance points and original trajectory discrete points on the original trajectory for each of the new trajectory points; the original trajectory minimum distance point is the point on the original trajectory with the minimum distance from the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point; Calculate the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point; Calculate the lateral deviation degree, longitudinal deviation degree and transverse-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; Perform a weighted sum on the lateral deviation degree, the longitudinal deviation degree and the transverse-longitudinal fusion deviation degree to obtain the comprehensive deviation degree of the new trajectory; Adjust the current driving trajectory according to the comprehensive deviation degree.

2. The driving trajectory adjustment method according to claim 1, characterized in that The distance evaluation value includes a first straight-line distance value. Calculating the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point includes: For each new trajectory point, calculate the straight-line distance between the new trajectory point and the original trajectory minimum distance point to obtain the first straight-line distance value corresponding to the new trajectory point.

3. The driving trajectory adjustment method according to claim 2, characterized in that, The calculating the lateral deviation degree of the new trajectory according to each distance evaluation value includes: Take the absolute value of the first straight-line distance value corresponding to each new trajectory point to obtain a plurality of first absolute values; Accumulate each of the first absolute values to obtain a first accumulated value; Divide the first accumulated value by the total length of the original trajectory to obtain the lateral deviation degree.

4. The driving trajectory adjustment method according to claim 2, wherein The distance evaluation value includes a second straight-line distance value. Calculating the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point includes: For each new trajectory point, calculate the straight-line distance between the new trajectory point and the original trajectory discrete point to obtain the second straight-line distance value corresponding to the new trajectory point.

5. The driving trajectory adjustment method according to claim 4, wherein Calculating the transverse-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value includes: Take the absolute value of the second straight-line distance value corresponding to each new trajectory point to obtain a plurality of second absolute values; Accumulate each of the second absolute values to obtain a second accumulated value; Divide the second accumulated value by the total time of the original trajectory to obtain the transverse-longitudinal fusion deviation degree.

6. The driving trajectory adjustment method according to claim 4, wherein The distance evaluation value includes a curve distance value. Calculating the distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point includes: For each new trajectory point, calculate the curve distance between the original trajectory minimum distance point and the original trajectory discrete point to obtain the curve distance value corresponding to the new trajectory point.

7. The driving trajectory adjustment method according to claim 6, wherein Calculating the longitudinal deviation degree of the new trajectory according to the distance evaluation value includes: Take the absolute value of the curve distance value corresponding to each new trajectory point to obtain a plurality of third absolute values; Accumulate each of the third absolute values to obtain a third accumulated value; Divide the third accumulated value by the total time of the original trajectory to obtain the longitudinal deviation degree.

8. A driving trajectory adjustment device, characterized in that, Including: A prediction module, configured to obtain an original trajectory and predict a new trajectory according to the original trajectory; An acquisition module, configured to obtain new trajectory points in the new trajectory, and respectively obtain corresponding original trajectory minimum distance points and original trajectory discrete points on the original trajectory for each of the new trajectory points; the original trajectory minimum distance point is the point on the original trajectory that is closest to the new trajectory point, and the original trajectory discrete point is the point on the original trajectory corresponding to the timestamp of the new trajectory point; A first calculation module, configured to calculate a distance evaluation value corresponding to each new trajectory point according to each new trajectory point and its corresponding original trajectory minimum distance point and original trajectory discrete point; A second calculation module, configured to calculate a lateral deviation degree, a longitudinal deviation degree, and a lateral-longitudinal fusion deviation degree of the new trajectory according to each distance evaluation value; An analysis module, configured to perform weighted summation on the lateral deviation degree, the longitudinal deviation degree, and the lateral-longitudinal fusion deviation degree to obtain a comprehensive deviation degree of the new trajectory; An adjustment module, configured to adjust the current driving trajectory according to the comprehensive deviation degree.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the driving trajectory adjustment method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the driving trajectory adjustment method according to any one of claims 1 to 7 is implemented.

Images