Self-vehicle prediction trajectory prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a self-vehicle prediction trajectory prediction method and device, electronic equipment and a storage medium, and relates to the technical field of automatic driving. The method comprises the following steps: determining a current trajectory point of a vehicle prediction trajectory; calculating a first coefficient, a second coefficient, a third coefficient and a fourth coefficient of the current track point; the third-order Bezier curve initial formula is updated, and a third-order Bezier curve prediction formula of the current track point is obtained; determining the target position of the target track point according to the fourth coefficient; according to a preset time interval and a third-order Bezier curve prediction formula, calculating a target speed and a target acceleration of the target trajectory point; and updating the target trajectory points as the current trajectory points, returning to the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory points until the number of the target trajectory points reaches the preset trajectory point number, and generating a self-vehicle prediction trajectory according to each target trajectory point. According to the technical scheme of the embodiment of the invention, the accuracy of the self-vehicle prediction trajectory can be improved.

Description

Technical Field

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

[0002] Around the world, with the improvement of living standards in various countries, the automobile industry has developed rapidly. In recent years, the number of cars in my country has continued to increase. In daily life, vehicles have become an essential part of people's daily travel. With the development and popularization of ADAS (Advanced Driver Assistance Systems) and AD (Automated Driving), more and more mass-produced models have been equipped with related functions, such as SACC (Smart Adaptive Cruise Control), AEB (Automatic Emergency Braking) and NOP (Navigate on Pilot) and other functions. For vehicles loaded with such functions, it is necessary to use various sensors to calculate the relevant state of the vehicle and the state of the surrounding environment in real time to realize the function. For the vehicle, it is necessary to predict the driving trajectory of the vehicle, so as to judge the association state with the surrounding environment and realize the relevant ADAS and AD functions. The existing technology predicts the predicted trajectory of the vehicle based on the steering wheel angle. This prediction method of the predicted trajectory of the vehicle is relatively simple, and the corresponding prediction accuracy is low. Summary of the invention

[0003] The present invention provides a method, device, electronic device and storage medium for predicting a self-vehicle predicted trajectory, which can improve the accuracy of self-vehicle predicted trajectory prediction.

[0004] According to one aspect of the present invention, a method for predicting a vehicle trajectory is provided, the method comprising:

[0005] Obtain the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determine the current trajectory point of the ego-vehicle predicted trajectory of the current vehicle;

[0006] Calculate a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval, and the initial formula of the third-order Bezier curve;

[0007] According to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, the initial formula of the third-order Bezier curve is updated to obtain a prediction formula of the third-order Bezier curve corresponding to the current trajectory point;

[0008] Determine a target position of a target trajectory point according to the fourth coefficient; wherein the target trajectory point is separated from the current trajectory point by a preset time interval;

[0009] Calculating the target velocity and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula;

[0010] The target trajectory point is updated to the current trajectory point, and the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration is returned until the number of the target trajectory points reaches the preset number of trajectory points, and the predicted self-vehicle trajectory of the current vehicle is generated according to the target position, the target speed and the target acceleration of each of the target trajectory points.

[0011] According to another aspect of the present invention, a vehicle trajectory prediction device is provided, the device comprising:

[0012] A current trajectory point generation module is used to obtain the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determine the current trajectory point of the ego-vehicle predicted trajectory of the current vehicle;

[0013] a current trajectory point coefficient determination module, configured to calculate a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval, and the initial formula of the third-order Bezier curve;

[0014] A third-order Bezier curve prediction formula determination module, used to update the third-order Bezier curve initial formula according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, to obtain the third-order Bezier curve prediction formula corresponding to the current trajectory point;

[0015] A target position determination module, configured to determine a target position of a target trajectory point according to the fourth coefficient; wherein the target trajectory point is separated from the current trajectory point by a preset time interval;

[0016] A target speed determination module, used to calculate the target speed and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula;

[0017] The self-vehicle predicted trajectory generation module is used to update the target trajectory point to the current trajectory point, return to execute the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of the target trajectory points reaches the preset number of trajectory points, and generate the self-vehicle predicted trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the self-vehicle prediction trajectory prediction method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the self-vehicle prediction trajectory prediction method described in any embodiment of the present invention when executed.

[0023] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program, and the computer program, when executed by a processor, implements the method for predicting a trajectory of a self-vehicle according to any embodiment of the present invention.

[0024] The technical solution of the embodiment of the present invention obtains the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determines the current trajectory point of the self-vehicle predicted trajectory of the current vehicle, calculates the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve, updates the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, obtains the prediction formula of the third-order Bezier curve corresponding to the current trajectory point, determines the target position of the target trajectory point according to the fourth coefficient, and calculates the target trajectory point according to the preset time interval and the third-order Bezier curve. The target trajectory point is updated to the current trajectory point by using a prediction formula, calculating the target speed and target acceleration of the target trajectory point, and returning to the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and the self-vehicle prediction trajectory of the current vehicle is generated according to the target position, the target speed and the target acceleration of each target trajectory point, and the third-order Bezier curve prediction formula of each trajectory point is determined in time periods, taking into account the driving characteristics of the self-vehicle, and improving the accuracy of determining the target trajectory point based on the current trajectory point, thereby improving the accuracy of the self-vehicle prediction trajectory determined based on each target trajectory point, and in summary, the driving efficiency and driving safety of the vehicle can be improved.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a method for predicting a trajectory of a self-driving vehicle provided according to the first embodiment of the present invention;

[0028] Figure 2 is a flow chart of a method for predicting a trajectory of a self-driving vehicle provided according to a second embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of the structure of a self-vehicle trajectory prediction device provided according to Embodiment 3 of the present invention;

[0030] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the self-vehicle trajectory prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1 A flowchart of a self-vehicle prediction trajectory prediction method provided in Embodiment 1 of the present invention. The embodiment of the present invention can be applied to the case where the vehicle trajectory is predicted using the Bezier prediction formula. The method can be executed by a self-vehicle prediction trajectory prediction device. The self-vehicle prediction trajectory prediction device can be implemented in the form of hardware and / or software. The self-vehicle prediction trajectory prediction device can be configured in an electronic device that carries the self-vehicle prediction trajectory prediction function, such as a vehicle-mounted terminal or a server.

[0035] See also Figure 1 The self-vehicle prediction trajectory prediction method shown includes:

[0036] S110, obtaining the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determining the current trajectory point of the self-vehicle predicted trajectory of the current vehicle.

[0037] The current position may be the position of the current vehicle at the current moment. The current speed may be the speed of the current vehicle at the current moment. The current acceleration may be the acceleration of the current vehicle at the current moment. The preset time interval may be the preset time interval between the current trajectory point and the target trajectory point. The preset number of trajectory points may be used to characterize the number of target trajectory points in the preset self-vehicle predicted trajectory. The preset number of trajectory points and the preset time interval may jointly determine the preset duration of the self-vehicle predicted trajectory. Exemplarily, the preset time interval may be 1s; the preset number of trajectory points may be 4; thus, based on the preset time interval and the preset number of trajectory points, the preset duration of the self-vehicle predicted trajectory may be determined to be 4s, that is, the self-vehicle driving trajectory of the current vehicle in the next 4s may be predicted. The initial formula of the third-order Bezier curve may be a third-order Bezier curve formula with undetermined coefficients. The Bezier curve may have different orders, such as first order, third order, fifth order, sixth order, and seventh order. In order to take into account both the amount of calculation and the prediction effect of the trajectory points, the third-order Bezier curve is selected. It can be understood that in order to ensure driving safety, it is necessary to predict the state of the vehicle in the next 4 seconds. The first-order Bezier curve cannot meet the current needs, and the fifth-order, sixth-order and seventh-order Bezier curves are too computationally intensive and too inefficient. Therefore, the third-order Bezier curve can be used to predict the trajectory of the vehicle in the next 4 seconds. The controller needs to estimate the position, speed and acceleration of the vehicle in the next 4 seconds.

[0038] Exemplarily, the following formula may be used to represent the initial formula of the third-order Bezier curve:

[0039] x=P0(1-t 3 )+3P1(1-t 2 )t+3P2(1-t)t 2 +P3t 3 ;

[0040] Wherein, x is the output result of the initial formula of the third-order Bezier curve; P0 is the first coefficient; P1 is the second coefficient; P2 is the third coefficient; P3 is the fourth coefficient; and t is time.

[0041] The current trajectory point may be a trajectory point corresponding to the current position, current speed, and current acceleration. The current trajectory point may be used as an estimate of a target trajectory point in the predicted trajectory of the ego vehicle.

[0042] Specifically, the current position, current speed and current acceleration detected by the current vehicle sensor can be obtained. The preset time interval, the preset number of trajectory points and the initial formula of the third-order Bezier curve preset by the technician can be obtained.

[0043] S120, calculating a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval, and the initial formula of the third-order Bezier curve.

[0044] The first coefficient, the second coefficient, the third coefficient and the fourth coefficient are all the coefficients corresponding to the initial formula of the third-order Bezier curve at the current trajectory point. In order to ensure the accuracy of the predicted trajectory of the self-vehicle, the corresponding first coefficient, second coefficient, third coefficient and fourth coefficient are calculated for each current trajectory point.

[0045] Specifically, the first coefficient corresponding to the current trajectory point can be calculated with the current position as the starting point and the current time as the starting time. Based on the current position, current speed, current acceleration and preset time interval, a linear estimate can be made for the target position of the current vehicle after the preset time interval to determine the fourth coefficient corresponding to the current trajectory point. The initial formula of the third-order Bezier curve can be derived to determine the second coefficient corresponding to the current trajectory point. The initial formula of the third-order Bezier curve can be derived twice to determine the third coefficient corresponding to the current trajectory point.

[0046] S130. Update the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient to obtain a prediction formula of the third-order Bezier curve corresponding to the current trajectory point.

[0047] The third-order Bezier curve prediction formula may be an actual prediction formula for predicting a target trajectory point based on a current trajectory point.

[0048] Specifically, the first coefficient, the second coefficient, the third coefficient, and the fourth coefficient may be used to update the initial formula of the third-order Bezier curve to obtain the prediction formula of the third-order Bezier curve corresponding to the current trajectory point.

[0049] S140. Determine a target position of the target trajectory point according to the fourth coefficient.

[0050] The target trajectory point may be the next trajectory point adjacent to the current trajectory point in the predicted trajectory of the vehicle. The target trajectory point is separated from the current trajectory point by a preset time interval. The target position may be the position of the target trajectory point. Optionally, the target position may include the actual position of the target trajectory point in the earth coordinate system or the position of the vehicle trajectory point relative to the current trajectory point.

[0051] Specifically, the fourth coefficient may be directly determined as the target position of the target trajectory point.

[0052] S150, calculating a target velocity and a target acceleration of a target trajectory point according to a preset time interval and a third-order Bezier curve prediction formula.

[0053] The target speed may be the speed of the target trajectory point. The target acceleration may be the acceleration of the target trajectory point. Optionally, the target speed may be the combined speed; the target acceleration may be the combined acceleration.

[0054] Specifically, the target velocity and target acceleration of the target trajectory point may be calculated according to a preset time interval and a third-order Bezier curve prediction formula.

[0055] In an optional embodiment of the present invention, the target speed and target acceleration of the target trajectory point are calculated according to a preset time interval and a third-order Bezier curve prediction formula, including: deriving the third-order Bezier curve prediction formula, and calculating the derived third-order Bezier curve prediction formula according to the preset time interval to calculate the target speed of the target trajectory point; and performing a second derivative of the third-order Bezier curve prediction formula, and calculating the second derivative of the third-order Bezier curve prediction formula according to the preset time interval to calculate the target acceleration of the target trajectory point.

[0056] Specifically, the third-order Bezier curve prediction formula can be derived, and the preset time interval can be brought into the derived third-order Bezier curve prediction formula to calculate the target speed of the target trajectory point. The third-order Bezier curve prediction formula can be derived twice, and the preset time interval can be brought into the derived third-order Bezier curve prediction formula to calculate the target acceleration of the target trajectory point.

[0057] Exemplarily, the preset time interval may be 1 second; the target speed of the target trajectory point may be expressed by the following formula:

[0058]

[0059] In the formula, x ′ is the derivation result of the prediction formula of the third-order Bezier curve; is the target speed of the target trajectory point; P0 is the first coefficient; P1 is the second coefficient; P3 is the third coefficient; P4 is the fourth coefficient.

[0060] The target acceleration of the target trajectory point can be expressed by the following formula:

[0061] x ′′ =A=6P1-12P2+6P3;

[0062] In the formula, x ′′ is the result of the second derivative of the third-order Bezier curve prediction formula; A is the target acceleration of the target trajectory point; P1 is the second coefficient; P3 is the third coefficient; P4 is the fourth coefficient.

[0063] This solution calculates the target speed of the target trajectory point by deriving the third-order Bezier curve prediction formula, and calculating the derived third-order Bezier curve prediction formula according to a preset time interval, and calculates the target acceleration of the target trajectory point. The target speed and target acceleration of the target trajectory point can be quickly determined, thereby improving the prediction efficiency of the self-vehicle prediction trajectory.

[0064] S160, updating the target trajectory point to the current trajectory point, returning to execute the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and generating the predicted self-vehicle trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point.

[0065] The number of target trajectory points reaches the preset number of trajectory points, which can be understood as the duration of the self-vehicle predicted trajectory reaches the preset duration to be predicted. For example, 4s or 10s, etc. The self-vehicle predicted trajectory can be the predicted trajectory of the current vehicle after the predicted duration from the current moment. Optionally, the self-vehicle predicted trajectory can be relative to the self-vehicle coordinate system or the earth coordinate system. Optionally, the self-vehicle predicted trajectory can be in the form of discrete trajectory points or continuous trajectory lines.

[0066] When the third-order Bezier curve is used to predict the trajectory of the self-driving vehicle of a preset duration (for example, 4s), only the first segment needs to set the initial value, that is, the current position, current speed and current acceleration need to be obtained. The subsequent segments (for example, 4 segments) will be recursively calculated based on the first segment to obtain new calculation state information, that is, the new current position, current speed and current acceleration; when the several segments are finished, the first segment is processed with the initial value, so the initial value is updated every preset duration (for example, 4s), and finally the target trajectory point of each segment is obtained, and the self-driving vehicle predicted trajectory of each preset time interval in the future is output, such as the self-driving vehicle predicted trajectory composed of 1s, 2s, 3s and 4s in the future.

[0067] Specifically, the target trajectory point can be updated to the current trajectory point, and the step of calculating the first coefficient, the second coefficient, the third coefficient, and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, and the current acceleration is returned until the number of target trajectory points reaches the preset number of trajectory points, and the position of each target trajectory point in the earth coordinate system can be determined according to the target position of each target trajectory point. The target speed and the target acceleration can be added to each target trajectory point to obtain each discrete target trajectory point with the target speed and the target acceleration, and the self-vehicle predicted trajectory of the current vehicle is generated.

[0068] The technical solution of the embodiment of the present invention obtains the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determines the current trajectory point of the self-vehicle predicted trajectory of the current vehicle, calculates the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve, updates the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, obtains the prediction formula of the third-order Bezier curve corresponding to the current trajectory point, determines the target position of the target trajectory point according to the fourth coefficient, and calculates the target trajectory point according to the preset time interval and the third-order Bezier curve. The target trajectory point is updated to the current trajectory point by using a prediction formula, calculating the target speed and target acceleration of the target trajectory point, and returning to the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and the self-vehicle prediction trajectory of the current vehicle is generated according to the target position, the target speed and the target acceleration of each target trajectory point, and the third-order Bezier curve prediction formula of each trajectory point is determined in time periods, taking into account the driving characteristics of the self-vehicle, and improving the accuracy of determining the target trajectory point based on the current trajectory point, thereby improving the accuracy of the self-vehicle prediction trajectory determined based on each target trajectory point, and in summary, the driving efficiency and driving safety of the vehicle can be improved.

[0069] In an optional embodiment of the present invention, the method also includes: obtaining the current vehicle curvature and curvature change rate of the current trajectory point, and calculating the target vehicle curvature of the target trajectory point; generating the self-vehicle predicted trajectory of the current vehicle according to the target position, target speed and target acceleration of each target trajectory point, including: generating the self-vehicle predicted trajectory line of the current vehicle according to the target position, target speed, target acceleration and target vehicle curvature of each target trajectory point.

[0070] The curvature of the current vehicle can be used to characterize the curvature of the current trajectory point. The curvature change rate can be used to characterize the curvature change from the current trajectory point to the target trajectory point. The target vehicle curvature can be used to characterize the curvature of the target trajectory point. The predicted trajectory line of the ego vehicle can be the predicted trajectory line of the current vehicle after the predicted time from the current moment.

[0071] Specifically, the sensor of the current vehicle can be used to obtain the curvature and curvature change rate of the current trajectory point. The target vehicle curvature calculation formula can be used to calculate the target vehicle curvature of the target trajectory point. The position of each target trajectory point in the earth coordinate system can be determined according to the target position of each target trajectory point. The target speed and target acceleration can be added to each target trajectory point to obtain each discrete target trajectory point with the target speed and target acceleration. The target vehicle curvature can be used to connect each discrete target trajectory point to obtain the self-vehicle predicted trajectory line of the current vehicle.

[0072] This scheme introduces the process of obtaining the current vehicle curvature and curvature change rate of the current trajectory point, as well as the process of calculating the target vehicle curvature of the target trajectory point. Based on the target curvature of each target trajectory point, a continuous self-vehicle predicted trajectory line of the current vehicle is generated, further improving the comprehensiveness of the self-vehicle predicted trajectory.

[0073] In an optional embodiment of the present invention, after calculating the target speed and target acceleration of the target trajectory point according to a preset time interval and a third-order Bezier curve prediction formula, it also includes: decomposing the target speed to obtain a target lateral speed and a target longitudinal speed; calculating the vehicle head heading angle corresponding to the target trajectory point according to the target lateral speed and the target longitudinal speed; generating a self-vehicle predicted trajectory of the current vehicle according to the target position, target speed and target acceleration of each target trajectory point, including: splitting the target speed according to the vehicle head heading angle to obtain a first target speed in the same direction as the vehicle head heading angle and a second target speed perpendicular to the vehicle head heading angle; splitting the target acceleration according to the vehicle head heading angle to obtain a first target acceleration in the same direction as the vehicle head heading angle and a second target acceleration perpendicular to the vehicle head heading angle; generating the self-vehicle predicted trajectory of the current vehicle according to the target position, first target speed, second target speed, first target acceleration and second target acceleration of each target trajectory point.

[0074] The target lateral speed may be the decomposition result of decomposing the target speed in the lateral direction of the earth coordinate system. The target longitudinal speed may be the decomposition result of decomposing the target speed in the longitudinal direction of the earth coordinate system. The vehicle head heading angle corresponding to the target trajectory point may be used to characterize the vehicle head posture state corresponding to the target trajectory point. The first target speed may be the result of splitting the target speed in the same direction as the vehicle head heading angle. The second target speed may be the result of splitting the target speed in the vertical direction to the vehicle head heading angle. The first target acceleration may be the result of splitting the target acceleration in the same direction as the vehicle head heading angle. The second target acceleration may be the result of splitting the target acceleration in the vertical direction to the vehicle head heading angle. Exemplarily, the target speed and target acceleration solved above are based on the Bezier curve coordinate system, and the initial position P0 at time T0 may be set to 0, so the target speed and target acceleration solved are also relative to time T0. In order to calculate the target speed and target acceleration of the actual vehicle coordinate system, it is necessary to calculate according to the current acceleration and current speed at the current time T0. The target speed and target acceleration at the target time T1 require the heading angle of the vehicle at the time T1. T1 This ensures the comprehensiveness and continuity of the vehicle's predicted trajectory.

[0075] Specifically, the target speed can be decomposed using the horizontal and vertical directions of the earth coordinate system to obtain the target horizontal speed and the target longitudinal speed. The head heading angle calculation formula can be used to calculate the head heading angle corresponding to the target trajectory point according to the target horizontal speed and the target longitudinal speed. The target speed can be split according to the head heading angle to obtain a first target speed in the same direction as the head heading angle and a second target speed perpendicular to the head heading angle. The target acceleration can be split according to the head heading angle to obtain a first target acceleration in the same direction as the head heading angle and a second target acceleration perpendicular to the head heading angle. The position of each target trajectory point in the earth coordinate system can be determined according to the target position of each target trajectory point. The first target speed, the second target speed, the first target acceleration and the second target acceleration can be added to each target trajectory point to generate the self-vehicle predicted trajectory of the current vehicle.

[0076] For example, the following formula may be used to represent the calculation formula of the vehicle head heading angle corresponding to the target trajectory point:

[0077]

[0078] In the formula, is the vehicle heading angle corresponding to the target trajectory point; T1 is the target time; a is the vehicle heading angle calculation coefficient; V long is the target lateral velocity; V lat is the target longitudinal velocity.

[0079] This scheme introduces the vehicle head heading angle corresponding to the target trajectory point, realizes the vector decomposition of the target velocity and target acceleration, and further improves the comprehensiveness of the information contained in the predicted trajectory of the ego vehicle.

[0080] Embodiment 2

[0081] Figure 2 A flowchart of a method for predicting the trajectory of a self-driving vehicle provided in the second embodiment of the present invention. Based on the above embodiments, the embodiment of the present invention specifies "calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve" as "determining the first coefficient corresponding to the current trajectory point according to the current position; calculating the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration and the preset time interval; taking the derivative of the initial formula of the third-order Bezier curve, and calculating the second coefficient corresponding to the current trajectory point according to the first coefficient and the current speed; taking the second derivative of the initial formula of the third-order Bezier curve, and calculating the third coefficient corresponding to the current trajectory point according to the first coefficient, the second coefficient and the current acceleration", thereby realizing the rapid calculation of the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point, which can improve the determination efficiency of the third-order Bezier curve prediction formula corresponding to the current trajectory point, and thus improve the prediction efficiency of the self-driving vehicle prediction trajectory. It should be noted that for the parts not described in detail in the embodiment of the present invention, please refer to the description of other embodiments.

[0082] See also Figure 2 The self-vehicle prediction trajectory prediction method shown includes:

[0083] S210, obtaining the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determining the current trajectory point of the predicted trajectory of the current vehicle.

[0084] S220. Determine a first coefficient corresponding to the current trajectory point according to the current position.

[0085] When calculating the first coefficient corresponding to the current trajectory point, the current time can be used to determine the starting time, that is, t=0 can be substituted into the initial formula of the third-order Bezier curve. It can be seen that the current position is equal to the first coefficient of the current trajectory point.

[0086] Specifically, the current position may be directly determined as the first coefficient of the current trajectory point.

[0087] Exemplarily, the following formula may be used to represent the first coefficient corresponding to the current trajectory point:

[0088]

[0089] In the formula, is the output result of the initial formula of the third-order Bezier curve at time T0, that is, the current position; P0 is the first coefficient corresponding to the current trajectory point. Optionally, the current position can be used as the starting position, that is, P0 = 0.

[0090] S230. Calculate a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration and the preset time interval.

[0091] Specifically, the reference position of the current vehicle after a preset time interval from the current position according to the current speed and the current acceleration can be calculated, and the reference position can be directly determined as the fourth coefficient corresponding to the current trajectory point.

[0092] Exemplarily, the preset time interval may be 1 second; the following formula may be used to represent the fourth coefficient corresponding to the current trajectory point:

[0093]

[0094] In the formula, It is the output result of the initial formula of the third-order Bezier curve at time T1, that is, the reference position; P3 is the fourth coefficient corresponding to the current trajectory point.

[0095] In an optional embodiment of the present invention, the fourth coefficient corresponding to the current trajectory point is calculated according to the current position, the current speed, the current acceleration and the preset time interval, including: calculating the reference position of the current vehicle after the preset time interval starting from the current position according to the current speed and the current acceleration; obtaining a first weight of the current position and a second weight of the reference position; using the first weight and the second weight, weighted summing the first coefficient, the current position and the reference position to obtain the fourth coefficient corresponding to the current trajectory point.

[0096] The reference position can be the position to which the current vehicle moves at a uniform acceleration after a preset time interval. Optionally, the reference position can be a relative position to the current position. It can be understood that when the vehicle moves in an arc, the position cannot be simply solved by a linear motion equation, because it is a curved motion. In the preset time interval, the vehicle can be regarded as a circular motion, and a circle is made with the radius of curvature of the vehicle, and the vehicle is a point on the circle. In this way, the vehicle motion is converted into a reference position of a certain point on the circumference at a preset time interval in the future. The coordinates of the reference position solved are relative to the center of the circle, not the vehicle, so the reference position after the solution is obtained by geometrically solving with the vehicle as the reference system. The first weight can be the weight of the current position. The second weight can be the weight of the reference position. The first weight and the second weight can be determined and adjusted based on the experience of the technician.

[0097] Specifically, the reference position of the current vehicle after a preset time interval from the current position according to the current speed and the current acceleration can be calculated. The first weight and the second weight predetermined by the technician based on the empirical formula can be obtained. The first weight and the second weight can be used to perform a weighted summation on the first coefficient, the current position, and the reference position to obtain the fourth coefficient of the current trajectory point.

[0098] Exemplarily, the following formula may be used to represent the calculation process of the fourth coefficient corresponding to the current trajectory point:

[0099]

[0100] Wherein, P3 is the fourth coefficient corresponding to the current trajectory point; P0 is the first coefficient corresponding to the current trajectory point; is the output result of the initial formula of the third-order Bezier curve at time T0, that is, the current position; where T0 is the current time; It is the output result of the initial formula of the third-order Bezier curve at time T1, that is, the reference position; where T1 is the target time; 0.7 is the first weight; and 0.3 is the second weight.

[0101] This scheme introduces a reference position, a first weight of the current position and a second weight of the reference position. By taking a weighted sum of the first coefficient, the current position and the reference position, the curvature change rate of the current vehicle during movement is taken into account, thereby improving the accuracy of the calculation of the fourth coefficient corresponding to the current trajectory point.

[0102] S240, deriving the initial formula of the third-order Bezier curve, and calculating the second coefficient corresponding to the current trajectory point according to the first coefficient and the current speed.

[0103] Specifically, the initial formula of the third-order Bezier curve may be derived, and the second coefficient corresponding to the current trajectory point may be calculated according to the first coefficient and the current speed.

[0104] Exemplarily, the following formula may be used to represent the process of deriving the initial formula of the third-order Bezier curve:

[0105] x ′ =V=3P1-3P0+(6P0-12P1+6P2)t+(9P1-3P0-9P2+9P3)t 2 ;

[0106] In the formula, x ′ is the derivative result of the initial formula of the third-order Bezier curve; V is the velocity of the trajectory point; P0 is the first coefficient; P1 is the second coefficient; P3 is the third coefficient; P4 is the fourth coefficient.

[0107] You can set t=0 and use the following formula to express the second coefficient corresponding to the current trajectory point:

[0108]

[0109] Where, P1 is the second coefficient; P0 is the first coefficient; is the current speed.

[0110] S250, performing a second derivative on the initial formula of the third-order Bezier curve, and calculating a third coefficient corresponding to the current trajectory point according to the first coefficient, the second coefficient and the current acceleration.

[0111] Specifically, the initial formula of the third-order Bezier curve may be secondarily derived, and the third coefficient corresponding to the current trajectory point may be calculated according to the first coefficient, the second coefficient and the current acceleration.

[0112] Exemplarily, the following formula may be used to represent the process of taking a second derivative of the initial formula of the third-order Bezier curve:

[0113] a ′′ =A=6P1-12P2+6P3;

[0114] In the formula, a ′′ is the result of the second derivative of the initial formula of the third-order Bezier curve; A is the acceleration of the trajectory point; P1 is the second coefficient; P3 is the third coefficient; P4 is the fourth coefficient.

[0115] You can set t=0 and use the following formula to express the third coefficient corresponding to the current trajectory point:

[0116]

[0117] Wherein, P2 is the third coefficient; P1 is the second coefficient; P0 is the first coefficient; is the current acceleration.

[0118] S260: Update the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient to obtain a prediction formula of the third-order Bezier curve corresponding to the current trajectory point.

[0119] S270. Determine the target position of the target trajectory point according to the fourth coefficient.

[0120] The target track point is separated from the current track point by a preset time interval.

[0121] S280, calculating the target velocity and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula.

[0122] S290, update the target trajectory point to the current trajectory point, return to execute the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and generate the predicted self-vehicle trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point.

[0123] The technical solution of the embodiment of the present invention determines the first coefficient corresponding to the current trajectory point according to the current position, calculates the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration and the preset time interval, derives the initial formula of the third-order Bezier curve, and calculates the second coefficient corresponding to the current trajectory point according to the first coefficient and the current speed, performs a second derivative of the initial formula of the third-order Bezier curve, and calculates the third coefficient corresponding to the current trajectory point according to the first coefficient, the second coefficient and the current acceleration, thereby realizing the rapid calculation of the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point, which can improve the determination efficiency of the third-order Bezier curve prediction formula corresponding to the current trajectory point, thereby improving the prediction efficiency of the predicted trajectory of the vehicle.

[0124] Embodiment 3

[0125] Figure 3 A schematic diagram of the structure of a self-vehicle prediction trajectory prediction device provided in Embodiment 3 of the present invention. The embodiment of the present invention can be applied to the case where the self-vehicle trajectory is predicted by using the Bezier prediction formula, the device can execute the self-vehicle prediction trajectory prediction method, the device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device carrying the self-vehicle prediction trajectory prediction function, such as a vehicle-mounted terminal or a server.

[0126] See also Figure 3 The self-vehicle prediction trajectory prediction device shown includes: a current trajectory point generation module 310, a current trajectory point coefficient determination module 320, a third-order curve prediction formula determination module 330, a target position determination module 340, a target speed determination module 350 and a self-vehicle prediction trajectory generation module 360. Among them, the current trajectory point generation module 310 is used to obtain the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determine the current trajectory point of the self-vehicle prediction trajectory of the current vehicle; the current trajectory point coefficient determination module 320 is used to calculate the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve; the third-order Bezier curve prediction formula determination module 330 is used to update the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, and obtain the third-order Bezier curve corresponding to the current trajectory point. line prediction formula; a target position determination module 340, used to determine the target position of the target trajectory point according to the fourth coefficient; wherein the target trajectory point is separated from the current trajectory point by a preset time interval; a target speed determination module 350, used to calculate the target speed and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula; a self-vehicle predicted trajectory generation module 360, used to update the target trajectory point to the current trajectory point, return to execute the steps of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and generate the self-vehicle predicted trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point.

[0127] The technical solution of the embodiment of the present invention obtains the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determines the current trajectory point of the self-vehicle predicted trajectory of the current vehicle, calculates the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve, updates the initial formula of the third-order Bezier curve according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, obtains the prediction formula of the third-order Bezier curve corresponding to the current trajectory point, determines the target position of the target trajectory point according to the fourth coefficient, and calculates the target trajectory point according to the preset time interval and the third-order Bezier curve. The target trajectory point is updated to the current trajectory point by using a prediction formula, calculating the target speed and target acceleration of the target trajectory point, and returning to the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of target trajectory points reaches the preset number of trajectory points, and the self-vehicle prediction trajectory of the current vehicle is generated according to the target position, the target speed and the target acceleration of each target trajectory point, and the third-order Bezier curve prediction formula of each trajectory point is determined in time periods, taking into account the driving characteristics of the self-vehicle, and improving the accuracy of determining the target trajectory point based on the current trajectory point, thereby improving the accuracy of the self-vehicle prediction trajectory determined based on each target trajectory point, and in summary, the driving efficiency and driving safety of the vehicle can be improved.

[0128] In an optional embodiment of the present invention, the current trajectory point coefficient determination module 320 includes: a first coefficient determination unit, which is used to determine the first coefficient corresponding to the current trajectory point according to the current position; a fourth coefficient determination unit, which is used to calculate the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration and the preset time interval; a second coefficient determination unit, which is used to derive the initial formula of the third-order Bezier curve, and calculate the second coefficient corresponding to the current trajectory point according to the first coefficient and the current speed; a third coefficient determination unit, which is used to perform a second derivative of the initial formula of the third-order Bezier curve, and calculate the third coefficient corresponding to the current trajectory point according to the first coefficient, the second coefficient and the current acceleration.

[0129] In an optional embodiment of the present invention, the fourth coefficient determination unit includes: a reference position calculation subunit, which is used to calculate the reference position of the current vehicle after the current position has traveled for a preset time interval according to the current speed and the current acceleration; a position weight acquisition subunit, which is used to obtain a first weight of the current position and a second weight of the reference position; and a fourth coefficient determination subunit, which is used to use the first weight and the second weight to perform a weighted summation of the first coefficient, the current position and the reference position to obtain a fourth coefficient corresponding to the current trajectory point.

[0130] In an optional embodiment of the present invention, the target speed determination module 350 includes: a target speed calculation subunit, which is used to derive the third-order Bezier curve prediction formula, and calculate the derived third-order Bezier curve prediction formula according to a preset time interval to calculate the target speed of the target trajectory point; a target acceleration calculation subunit, which is used to perform a second derivative of the third-order Bezier curve prediction formula, and calculate the second derivative of the third-order Bezier curve prediction formula according to a preset time interval to calculate the target acceleration of the target trajectory point.

[0131] In an optional embodiment of the present invention, the device also includes: a target vehicle curvature calculation module, which is used to obtain the current vehicle curvature and curvature change rate of the current trajectory point, and calculate the target vehicle curvature of the target trajectory point; an ego vehicle predicted trajectory generation module 360, including: an ego vehicle predicted trajectory line generation unit, which is used to generate the ego vehicle predicted trajectory line of the current vehicle according to the target position, target speed, target acceleration and target vehicle curvature of each target trajectory point.

[0132] In an optional embodiment of the present invention, the device further includes: a first target speed decomposition module, which is used to decompose the target speed to obtain a target lateral speed and a target longitudinal speed after calculating the target speed and the target acceleration of the target trajectory point according to a preset time interval and a third-order Bezier curve prediction formula; a vehicle head heading angle calculation module, which is used to calculate the vehicle head heading angle corresponding to the target trajectory point according to the target lateral speed and the target longitudinal speed; a self-vehicle predicted trajectory generation module 360, including: a first target speed splitting unit, which is used to split the target speed according to the vehicle head heading angle to obtain a first target speed in the same direction as the vehicle head heading angle and a second target speed perpendicular to the vehicle head heading angle; a first target acceleration splitting unit, which is used to split the target acceleration according to the vehicle head heading angle to obtain a first target acceleration in the same direction as the vehicle head heading angle and a second target acceleration perpendicular to the vehicle head heading angle; and a self-vehicle predicted trajectory generation unit, which is used to generate the self-vehicle predicted trajectory of the current vehicle according to the target position, the first target speed, the second target speed, the first target acceleration and the second target acceleration of each target trajectory point.

[0133] The self-vehicle predicted trajectory prediction device provided in the embodiment of the present invention can execute the self-vehicle predicted trajectory prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0134] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of the current position, current speed, current acceleration, preset time interval, preset number of trajectory points, initial formula of the third-order Bezier curve, first weight of the current position, second weight of the reference position, current vehicle curvature and curvature change rate of the current trajectory point, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0135] Embodiment 4

[0136] Figure 4 A schematic diagram of the structure of an electronic device 400 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0137] like Figure 4 As shown, the electronic device 400 includes at least one processor 401, and a memory connected to the at least one processor 401 in communication, such as a read-only memory (ROM) 402, a random access memory (RAM) 403, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 401 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 402 or the computer program loaded from the storage unit 408 to the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The processor 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0138] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0139] The processor 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 401 performs the various methods and processes described above, such as the self-vehicle prediction trajectory prediction method.

[0140] In some embodiments, the self-vehicle prediction trajectory prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the processor 401, one or more steps of the self-vehicle prediction trajectory prediction method described above may be performed. Alternatively, in other embodiments, the processor 401 may be configured to perform the self-vehicle prediction trajectory prediction method in any other suitable manner (e.g., by means of firmware).

[0141] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0143] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0146] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0147] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting a trajectory of a self-driving vehicle, characterized in that: The method comprises: Obtain the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determine the current trajectory point of the ego-vehicle predicted trajectory of the current vehicle; Calculate a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval, and the initial formula of the third-order Bezier curve; According to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, the initial formula of the third-order Bezier curve is updated to obtain a prediction formula of the third-order Bezier curve corresponding to the current trajectory point; Determine a target position of a target trajectory point according to the fourth coefficient; wherein the target trajectory point is separated from the current trajectory point by a preset time interval; Calculating the target velocity and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula; The target trajectory point is updated to the current trajectory point, and the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration is returned until the number of the target trajectory points reaches the preset number of trajectory points, and the predicted self-vehicle trajectory of the current vehicle is generated according to the target position, the target speed and the target acceleration of each of the target trajectory points.

2. The method according to claim 1, characterized in that The calculating, according to the current position, the current speed, the current acceleration, the preset time interval and the initial formula of the third-order Bezier curve, the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point comprises: Determine a first coefficient corresponding to the current trajectory point according to the current position; Calculating a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration and the preset time interval; Derivative the initial formula of the third-order Bezier curve, and calculate the second coefficient corresponding to the current trajectory point according to the first coefficient and the current speed; The initial formula of the third-order Bezier curve is secondarily differentiated, and a third coefficient corresponding to the current trajectory point is calculated according to the first coefficient, the second coefficient and the current acceleration.

3. The method according to claim 2, characterized in that The calculating, according to the current position, the current speed, the current acceleration and the preset time interval, a fourth coefficient corresponding to the current trajectory point includes: Calculating a reference position of the current vehicle after the preset time interval has elapsed since the current position according to the current speed and the current acceleration; Acquire a first weight of the current position and a second weight of the reference position; The first weight and the second weight are used to perform weighted summation on the first coefficient, the current position, and the reference position to obtain a fourth coefficient corresponding to the current trajectory point.

4. The method according to claim 1, characterized in that: The calculating the target speed and the target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula includes: Derivative the third-order Bezier curve prediction formula, and calculate the derived third-order Bezier curve prediction formula according to the preset time interval to calculate the target speed of the target trajectory point; The third-order Bezier curve prediction formula is secondarily derived, and the third-order Bezier curve prediction formula after the second derivative is calculated according to the preset time interval to calculate the target acceleration of the target trajectory point.

5. The method according to claim 1, characterized in that Also includes: Acquire the current vehicle curvature and curvature change rate of the current trajectory point, and calculate the target vehicle curvature of the target trajectory point; The generating the predicted self-vehicle trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point includes: The predicted self-vehicle trajectory line of the current vehicle is generated according to the target position, the target speed, the target acceleration and the target vehicle curvature of each target trajectory point.

6. The method according to claim 1, characterized in that After calculating the target speed and the target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula, the method further includes: Decomposing the target speed to obtain a target lateral speed and a target longitudinal speed; Calculating the vehicle head heading angle corresponding to the target trajectory point according to the target lateral speed and the target longitudinal speed; The generating the predicted self-vehicle trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point includes: The target speed is split according to the vehicle head heading angle to obtain a first target speed in the same direction as the vehicle head heading angle and a second target speed perpendicular to the vehicle head heading angle; The target acceleration is split according to the vehicle head heading angle to obtain a first target acceleration in the same direction as the vehicle head heading angle and a second target acceleration perpendicular to the vehicle head heading angle; A predicted self-vehicle trajectory of the current vehicle is generated according to the target position, the first target speed, the second target speed, the first target acceleration, and the second target acceleration of each target trajectory point.

7. A vehicle trajectory prediction device, characterized in that: The device comprises: A current trajectory point generation module is used to obtain the current position, current speed, current acceleration, preset time interval, preset number of trajectory points and the initial formula of the third-order Bezier curve of the current vehicle, and determine the current trajectory point of the ego-vehicle predicted trajectory of the current vehicle; a current trajectory point coefficient determination module, configured to calculate a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient corresponding to the current trajectory point according to the current position, the current speed, the current acceleration, the preset time interval, and the initial formula of the third-order Bezier curve; A third-order Bezier curve prediction formula determination module, used to update the third-order Bezier curve initial formula according to the first coefficient, the second coefficient, the third coefficient and the fourth coefficient, to obtain the third-order Bezier curve prediction formula corresponding to the current trajectory point; A target position determination module, configured to determine a target position of a target trajectory point according to the fourth coefficient; wherein the target trajectory point is separated from the current trajectory point by a preset time interval; A target speed determination module, used to calculate the target speed and target acceleration of the target trajectory point according to the preset time interval and the third-order Bezier curve prediction formula; The self-vehicle predicted trajectory generation module is used to update the target trajectory point to the current trajectory point, return to execute the step of calculating the first coefficient, the second coefficient, the third coefficient and the fourth coefficient corresponding to the current trajectory point according to the current position, the current speed and the current acceleration, until the number of the target trajectory points reaches the preset number of trajectory points, and generate the self-vehicle predicted trajectory of the current vehicle according to the target position, the target speed and the target acceleration of each target trajectory point.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the self-vehicle trajectory prediction method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the self-vehicle trajectory prediction method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the self-vehicle trajectory prediction method according to any one of claims 1 to 6.

Images