Trajectory prediction method and device, electronic equipment and vehicle

Abstract

The application provides a trajectory prediction method and device, electronic equipment and vehicle. The trajectory prediction method is applied to a trailer with a towing vehicle, and includes: equivalent single shaft of multiple shafts of the trailer; the multiple shafts of the trailer are used for rotation and cannot swing; additional torque generated by the equivalent single shaft is obtained, and a dynamic attribute of a rotational motion of the trailer is obtained; a current state of the towing vehicle and the trailer at a current time is determined based on the additional torque, the dynamic attribute of the rotational motion and a kinematic attribute of the equivalent single shaft of the towing vehicle; and a predicted trajectory of the towing vehicle and the trailer at a next time is obtained by using the current state of the towing vehicle and the trailer at the current time based on a correlation between the current state and a state at the next time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of trajectory prediction, in particular to a trajectory prediction method and device, electronic equipment and vehicle. BACKGROUND

[0002] When driving a trailer, accurately predicting the trajectory of a double-axle trailer is a challenging task. Traditional prediction methods rely on the experience and judgment of the driver, and are prone to human error in prediction. SUMMARY

[0003] The present application provides an improved trajectory prediction method, device, electronic equipment and vehicle.

[0004] The present application provides a trajectory prediction method applied to a trailer with a towing vehicle, comprising:

[0005] equivalent single axle of the multi-axle of the trailer; the multi-axle of the trailer is used for rotation and cannot swing;

[0006] obtaining additional torque generated by the equivalent single axle, and the dynamic properties of the rotational motion of the trailer;

[0007] determining the state of the towing vehicle and the trailer at the current time based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axle of the towing vehicle;

[0008] obtaining the predicted trajectory of the towing vehicle and the trailer at the next time based on the relationship between the current state and the next state, and using the current state of the towing vehicle and the trailer.

[0009] Further, the equivalent single axle of the multi-axle of the trailer comprises:

[0010] equivalent single axle of any axle of the multi-axle of the trailer.

[0011] Further, the equivalent single axle of the multi-axle of the trailer comprises:

[0012] equivalent single axle of the middle of the multi-axle of the trailer.

[0013] Further, the multi-axle comprises the front axle of the trailer and the rear axle of the trailer;

[0014] The additional torque generated by the equivalent single axle comprises:

[0015] obtaining the force in the center transverse direction of the equivalent axle based on the sum of the force in the center longitudinal direction of the front axle and the force in the center transverse direction of the rear axle;

[0016] The additional torque generated by the equivalent single axle is obtained based on a dynamic formula of the additional torque and dynamic attributes of the trailer, wherein the dynamic attributes of the trailer include a cornering stiffness of a wheel of the trailer, a yaw rate of the trailer, a speed of a front wheel of the trailer in a longitudinal direction of the trailer, a distance from an equivalent axle of the trailer to a front axle of the trailer, a distance between the front axle of the trailer and a center of mass of the trailer, and a distance between a rear axle of the trailer and the center of mass of the trailer.

[0017] Further, the current state of the towing vehicle and the trailer is determined based on the additional torque, the dynamic attributes of the rotational motion, and the kinematic attributes of the equivalent single axle of the towing vehicle, including:

[0018] The yaw rate of the equivalent single axle of the towing vehicle is obtained based on a kinematic formula of the equivalent single axle of the towing vehicle according to the kinematic attributes of the equivalent single axle of the towing vehicle, wherein the kinematic attributes of the equivalent single axle include a speed of the towing vehicle in the longitudinal direction, a front wheel turning angle of the towing vehicle, an angle between the towing vehicle and the trailer, a distance between the front axle of the towing vehicle and the center of mass of the towing vehicle, and a distance between the center of mass of the towing vehicle and the rear axle of the towing vehicle.

[0019] Further, the dynamic attributes of the rotational motion include a speed of the front wheel of the trailer in the longitudinal direction of the trailer, the cornering stiffness of the wheel of the trailer, and a moment of inertia of the trailer around the Z axis;

[0020] The current state of the towing vehicle and the trailer is determined based on the additional torque, the dynamic attributes of the rotational motion, and the kinematic attributes of the equivalent single axle of the towing vehicle, including:

[0021] The current state of the towing vehicle and the trailer is determined based on the additional torque and the dynamic attributes of the rotational motion according to a dynamic formula of the rotational motion of the trailer.

[0022] Further, after the predicted trajectory of the towing vehicle and the trailer at the next moment is obtained using the current state of the towing vehicle and the trailer at the current moment based on the correlation between the current state and the state at the next moment, the trajectory prediction method further includes:

[0023] When the trailer is reversing, the predicted trajectory of the motion of the trailer is displayed on the vehicle machine.

[0024] Further, the dynamic attributes of the rotational motion of the trailer are obtained by the following steps:

[0025] In a case where a prompt information is displayed on the vehicle machine, vehicle information input for the prompt information is received; the vehicle information includes size information and mass information of the vehicle and the trailer;

[0026] For the vehicle information, a candidate multi-axle trailer type is displayed;

[0027] A multi-axle trailer type is selected from the candidate multi-axle trailer types as a target trailer type;

[0028] From the pre-set moment of inertia and side stiffness corresponding to the multi-axle trailer type, the moment of inertia and side stiffness corresponding to the target trailer type are obtained.

[0029] The application provides a trajectory prediction device applied to a trailer with a towing vehicle, and the trajectory prediction device comprises:

[0030] An equivalent module is configured to equivalently convert a multi-axle of the trailer into an equivalent single axle; the multi-axle of the trailer is used for rotation and cannot swing;

[0031] An acquisition module is configured to acquire an additional torque generated by the equivalent single axle and a dynamic attribute of a rotational motion of the trailer;

[0032] A state determination module of a current time point is configured to determine a current time point state of the towing vehicle and the trailer based on the additional torque, the dynamic attribute of the rotational motion and a kinematic attribute of the equivalent single axle of the towing vehicle;

[0033] A state determination module of a next time point is configured to obtain a predicted trajectory of the towing vehicle and the trailer in the next time point motion based on an association relationship between the current time point state and the next time point state and using the current time point state of the towing vehicle and the trailer.

[0034] The application provides an electronic device comprising one or more processors configured to implement the trajectory prediction method.

[0035] The application provides a vehicle comprising one or more processors configured to implement the trajectory prediction method.

[0036] The application provides a computer readable storage medium having a program stored thereon, and the program is executed by a processor to implement the method according to any one of the above.

[0037] The application provides a computer program product comprising a computer program / instruction, and the computer program / instruction is executed by a processor to implement the method according to any one of the above.

[0038] In some embodiments, the trajectory prediction method of the present application considers the additional torque generated by the equivalent single axle, and the dynamic properties of the rotational motion of the trailer. In this way, not only the kinematic properties of the trailer are considered, but also the dynamic properties of the trailer. In this way, the current state of the tractor and trailer is used to more comprehensively consider the properties of the trailer, without relying on manual intervention, so that the accuracy of the predicted trajectory of the trailer motion at the next time is relatively high. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 A schematic diagram of the trajectory prediction method of the present application is shown.

[0040] Figure 2 A schematic diagram of the trajectory prediction method of the present application is shown.

[0041] Figure 3 For Figure 2 A schematic diagram of the shape parameters of the dual-axle trailer model in the trajectory prediction method is shown.

[0042] Figure 4 For Figure 3 A schematic diagram of the equivalent single-axle trailer of the dual-axle trailer model is shown.

[0043] Figure 5 For Figure 2 A schematic diagram of the single-axle trailer motion in the trajectory prediction method is shown.

[0044] Figure 6 For Figure 2 A schematic diagram of the rotational motion of the trailer of the dual-axle trailer model in the trajectory prediction method is shown.

[0045] Figure 7 A schematic diagram of the trajectory prediction device of the present application is shown.

[0046] Figure 8 A schematic diagram of the trajectory prediction system provided by the present application is shown. DETAILED DESCRIPTION

[0047] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is intended to apply to all alternative modifications and embodiments as would be apparent to those skilled in the art. It is to be understood that the following description is exemplary only and intended to provide a generic description of the use of the application as embodied in exemplary embodiments in accordance with the disclosure. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein.

[0048] It should be noted that the steps of the corresponding method are not necessarily performed in the order shown and described in the specification in other embodiments. In some other embodiments, the steps included in the method thereof can be more or less than described in the specification. In addition, a single step described in the specification can be divided into multiple steps for description in other embodiments, and multiple steps described in the specification can be combined into a single step for description in other embodiments.

[0049] To solve the technical problem of easy to occur predicted human error, the embodiment of the application provides a trajectory prediction method, which simplifies the multi-axle of the trailer into an equivalent single axle, and determines the state of the trailer at the current time based on the additional torque and the dynamic properties of the rotational motion generated by the equivalent single axle, to obtain the predicted trajectory of the trailer motion at the next time. In this way, without relying on the experience and judgment of the driver, by combining the actual dynamic characteristics of the multi-axle trailer, the predicted trajectory of the trailer motion at the next time can be automatically predicted based on the data of the multi-axle trailer itself and the state of the trailer at the current time. In this way, without relying on artificial, the accuracy of predicting the predicted trajectory of the trailer motion at the next time is relatively high.

[0050] In related technologies, based on the network of deep learning, based on the data-driven technology, relying on neural network models such as convolutional neural network CNN (Convolutional Neural Network) or CNN (Recurrent Neural Network), the motion law of the trailer is automatically learned from a large amount of data, and the prediction ability of the neural network model is optimized.

[0051] However, predicting the motion trajectory of the trailer requires a large amount of training materials and a long training time. In addition, GPU is required to assist in inference operation, which requires high computing power of the device (not friendly to low-config devices), and also excessively relies on a large amount of training materials. If the quality of the training materials is not good (for example, containing many errors, missing values, inaccurate or biased annotations), it may also lead to a model with poor effect.

[0052] Compared with related technologies, the trajectory prediction method of the embodiment of the application uses the state of the tractor and the trailer at the current time to obtain the predicted trajectory of the motion of the tractor and the trailer at the next time based on the correlation between the state at the current time and the state at the next time, without relying on model training, without requiring a large amount of training materials, without requiring high computing power, and low-config devices can also be used. In this way, time is saved, processing speed is fast, and efficiency is high.

[0053] In the related art, the kinematics principle of the trailer is used to predict the trajectory of the vehicle based on the current vehicle state (position, speed, acceleration, etc.) and external control input, such as steering angle, throttle, brake, etc. However, since kinematics only focuses on the speed layer and is more focused on describing the motion law of the object, the analysis is performed using position, speed, acceleration, etc.

[0054] However, the motion characteristic parameters considered are less, and therefore, the accuracy of the predicted trajectory for predicting the motion of the trailer is low.

[0055] Compared with the related art, the trajectory prediction method of the embodiments of the present application considers the additional torque generated by the equivalent single shaft and the dynamics property of the rotational motion of the trailer. In this way, not only the kinematic characteristics of the trailer are considered, but also the dynamic characteristics of the trailer are considered. Thus, the current state of the towing vehicle and the trailer is used to more comprehensively consider the characteristics of the trailer, so that the accuracy of the predicted trajectory for predicting the motion of the trailer at the next time is relatively high.

[0056] Figure 1 The figure shows the schematic diagram of the trajectory prediction method of the embodiments of the present application.

[0057] As shown in the figure, the trajectory prediction method in the present application is applied to a trailer with a towing vehicle. The trailer with the towing vehicle involves two trajectory models: Figure 1 1. Towing vehicle system model. The feature of this model is that the steering angle (δ) is fixed, the trajectory is a circle, and the trajectory description is relatively simple.

[0058] 2. Trailer system model. The feature of this model is that the steering angle (θ) is not fixed, so the trajectory is not a specific simple figure, and the trajectory description algorithm is relatively complex.

[0059] In this article, the towing vehicle is used to provide power and drive the trailer.

[0060]

[0061] The figure shows the flowchart of the trajectory prediction method of the embodiments of the present application. Figure 2 As shown in the figure, the trajectory prediction method can include but is not limited to the following steps 110 to 140:

[0062] Figure 2 As shown in the figure, the trajectory prediction method can include but is not limited to the following steps 110 to 140:

[0063] Step 110, the multiple shafts of the trailer are equivalent to an equivalent single shaft; the multiple shafts of the trailer are used for rotation and cannot swing.

[0064] Since the multiple shafts of the trailer are used for rotation and cannot swing, the multiple shafts can be equivalent to an equivalent single shaft through equivalence. In this way, the equivalence is closer to the actual multiple shafts of the trailer, so that the finally predicted motion trajectory is more accurate. ​

[0065] The trailer can include, but is not limited to, a semitrailer.

[0066] In step 120, an additional moment generated by the equivalent single axle is obtained, and a dynamic property of the rotational motion of the trailer is obtained.

[0067] By considering the additional moment generated by the equivalent single axle, the influence of the additional moment on the multiple axles of the trailer can be grasped, and the current state of the trailer can be determined more accurately.

[0068] In step 130, the current state of the towing vehicle and the trailer is determined based on the additional moment, the dynamic property of the rotational motion, and the kinematic property of the equivalent single axle of the towing vehicle.

[0069] In step 130, the current state of the towing vehicle and the trailer is determined, and the variable parameters required include the real-time steering wheel angle of the towing vehicle and the initial angle of the trailer hook.

[0070] In step 140, the current state of the towing vehicle and the trailer is used to obtain the predicted trajectory of the next moment of the towing vehicle and the trailer based on the correlation between the current state and the next state.

[0071] After step 140, the method further includes driving control of the towing vehicle and the trailer according to the predicted trajectory.

[0072] The embodiment of the present application uses an equivalent single axle trailer model to simplify the prediction process. At the same time, the correlation between the current state and the next state can improve the accuracy of the prediction result with little additional computational power consumption. Thus, the predicted trajectory of the next moment of the trailer motion is directly predicted based on physical rules, rather than based on model training, which requires less computational power and can provide more accurate prediction of the predicted trajectory of the next moment of the trailer motion in complex driving environments.

[0073] The multiple axles of the trailer can be dual axles or more than three axles.

[0074] Continue to combine Figure 2 As shown in the figure, the equivalent single axle can be obtained by at least one of the following equivalent embodiments.

[0075] In the first optional equivalent embodiment, any axle of the multiple axles of the trailer is equivalent to the equivalent single axle.

[0076] Figure 3 For Figure 2 The schematic diagram of the shape parameters of the dual axle trailer model in the trajectory prediction method. Figure 4 For Figure 3A schematic diagram of an equivalent single axle trailer model for the illustrated dual axle trailer model.

[0077] As Figure 3 and Figure 4 illustrated in a second alternative embodiment, the middle between the multiple axles of the trailer is equivalent to the equivalent single axle.

[0078] Continuing with Figure 3 and Figure 4 illustrated, the multiple axles include a front axle of the trailer and a rear axle of the trailer.

[0079] The step 120 can further include a first step and a second step as follows:

[0080] The first step is to obtain the force in the center transverse direction of the equivalent axle based on the sum of the force in the center longitudinal direction of the front axle and the force in the center transverse direction of the rear axle.

[0081] The second step is to obtain the additional moment generated by the equivalent single axle based on a dynamic formula of the additional moment and the dynamic properties of the trailer; wherein the dynamic properties of the trailer include the cornering stiffness of the wheels of the trailer, the yaw rate of the trailer, the speed of the front wheels of the trailer in the longitudinal direction of the trailer, the distance from the equivalent axle of the trailer to the front axle of the trailer, the distance between the front axle of the trailer and the center of mass of the trailer, and the distance between the rear axle of the trailer and the center of mass of the trailer.

[0082] For this purpose, the dynamic formula of the additional moment is as follows:

[0083] Y gd = Y gf + Y gr (1)

[0084]

[0085] wherein M gd is the additional moment generated by replacing the dual axles with the equivalent axle of the trailer, ω2 is the yaw rate of the trailer, v x3 is the speed of the front wheels of the trailer in the longitudinal direction of the trailer, C y is the cornering stiffness of the wheels of the trailer. When the speed and the yaw rate are positive, the equivalent axle is between the two axles, and the additional moment thereof is the smallest; wherein d3 is the distance from the equivalent axle of the trailer to the front axle of the trailer, a2 is the distance between the front axle of the trailer and the center of mass of the trailer, and b2 is the distance between the rear axle of the trailer and the center of mass of the trailer.

[0086] In this way, the average of the first distance between the front axle and the center of mass of the trailer and the second distance between the rear axle and the center of mass of the trailer can be determined as the distance between the equivalent axle and the front axle by the formula 2.

[0087] From the dynamics formula, the motion of the double-axle trailer can be equivalent to the motion of the single-axle trailer with an additional moment M gd , where d2 is the distance from the front axle of the trailer to the hinge point, and d3 is the distance from the equivalent axle of the trailer to the front axle of the trailer.

[0088] Figure 5 is a schematic diagram of the motion of the single-axle trailer in the trajectory prediction method shown in Figure 2 . Figure 6 is a schematic diagram of the rotational motion of the trailer of the double-axle trailer model in the trajectory prediction method shown in Figure 2 .

[0089] The motion of the double-axle trailer in this paper is divided into two parts. One part is the motion of the single-axle trailer with a distance of d2+d3 from the hinge point as shown in Figure 5 . The other part is the rotational motion of the trailer around the center of mass (rotational motion of the trailer) with a moment of M gd as shown in Figure 6 .

[0090] In combination with Figure 1 and Figure 2 , the above step 130 can further include the following based on the kinematic properties of the equivalent single axle of the towing vehicle, obtaining the yaw angular velocity of the equivalent single axle of the towing vehicle according to the kinematic formula of the equivalent single axle of the towing vehicle; wherein the kinematic properties of the equivalent single axle include the speed of the towing vehicle in the longitudinal direction, the front wheel steering angle of the towing vehicle, the included angle between the towing vehicle and the trailer, the distance between the front axle of the towing vehicle and the center of mass of the towing vehicle, and the distance between the center of mass of the towing vehicle and the rear axle of the towing vehicle.

[0091] In this regard, the kinematic formula of the equivalent single axle of the towing vehicle is as follows:

[0092]

[0093] where ω ′ 2 is the angular velocity of the equivalent single-axle trailer of the towing vehicle, v x2 is the speed of the towing vehicle in the longitudinal direction, δ is the front wheel steering angle, θ is the included angle between the towing vehicle and the trailer, a1 is the distance between the front axle of the towing vehicle and the center of mass of the towing vehicle, and b1 is the distance between the center of mass of the towing vehicle and the rear axle of the towing vehicle.

[0094] In combination with Figure 1 and Figure 2As shown, the dynamic properties of the rotational motion include the speed of the front wheel of the trailer in the longitudinal direction of the trailer, the cornering stiffness of the wheel of the trailer, and the moment of inertia of the trailer around its Z axis. Correspondingly, the step 130 can further include determining the state of the towing vehicle and the trailer at the current time according to the rotational motion dynamics formula of the trailer based on the additional moment and the dynamic properties of the rotational motion.

[0095] For this purpose, the rotational motion dynamics formula of the trailer is as follows:

[0096]

[0097] where ω 2 is the yaw rate of the trailer (obtained from the formula 2), ω ′ 2 ′ is the yaw rate generated by the additional moment of the trailer, v x3 is the speed of the front wheel of the trailer in the longitudinal direction of the trailer, C y is the cornering stiffness of the wheel of the trailer, and I g is the moment of inertia of the trailer around its Z axis.

[0098] In the embodiments of the present application, according to the input shape parameters of the towing vehicle and the trailer, the real-time steering wheel angle of the towing vehicle, and the included angle between the towing vehicle and the trailer, the accurate trajectory prediction is realized by the method based on the dynamic properties of the rotational motion of the trailer and the kinematic properties of the equivalent single axis of the towing vehicle. The main advantage of the embodiments of the present application is that the prediction accuracy is higher than the prediction method based on only kinematics, and the occupied computing resources are very small.

[0099] In combination Figure 2 As shown, the association relationship between the state at the current time and the state at the next time in the step 140 can include the state transition relationship between the trailer system state at the current time and the trailer system state at the next time, such as the state transition relationship between the real-time steering wheel angle of the towing vehicle and the initial angle of the trailer at the current time and the real-time steering wheel angle of the towing vehicle and the initial angle of the trailer at the next time.

[0100] Specifically, the process of inferring the trailer system state at the next time k according to the initial state and the state transition relationship when k >= 1 is implemented as follows:

[0101] Let the motion time interval between two points be T, and the total prediction path time be t.

[0102] First, when t is equal to 0, the current state of the trailer system is known, including the following known state parameter values:

[0103] the yaw angle of the towing vehicle is the center position of the rear axle of the towing vehicle (xqr (0),y qr (0)), the front wheel rotation angle δ of the tractor, the initial angle between the tractor and the trailer θ(0), and the rate of change of the initial angle between the tractor and the trailer. And, the longitudinal speed of the tractor is v x2 .

[0104] First, based on the known state parameter values ​​mentioned above, the initial position (x) of the trailer's front axle center can be calculated. gf (0),y gf (0)), that is:

[0105]

[0106] Second, based on the known state parameter values ​​mentioned above, the longitudinal speed of the tractor is v. x2 The yaw angle of the tractor is The calculations show that the center of the rear axle of the tractor unit is at the initial velocity. Right now:

[0107]

[0108] Third, based on the initial angle θ(0) between the tractor and trailer in the known state parameter values ​​mentioned above, the longitudinal velocity of the tractor is v. x2 Let d2 be the distance from the front axle of the trailer to the articulation point, d3 be the distance from the equivalent axle of the trailer to the front axle of the trailer, a1 be the distance from the front axle of the tractor to the center of mass of the tractor, d1 be the distance from the center of the rear axle of the tractor to the articulation point, and b1 be the distance from the center of mass of the tractor to the rear axle of the tractor. Calculate the initial angular velocity ω of the equivalent single-axle trailer. ′ 2(0), that is:

[0109]

[0110] Fourth, based on the initial angle θ(0) between the tractor and trailer in the known state parameter values ​​mentioned above, the longitudinal velocity of the tractor is v. x2 Let b1 be the distance from the center of gravity of the tractor to the rear axle of the tractor, d1 be the distance from the center of the rear axle of the tractor to the hinge point, and a1 be the distance from the front axle of the tractor to the center of gravity of the tractor. Calculate the initial longitudinal velocity v of the equivalent single-axle trailer. x3 (0), that is:

[0111]

[0112] Fifth, based on the known state parameter values ​​above, the rate of change of the included angle... The longitudinal speed of the tractor is v x2, the distance from the trailer mass center to the trailer rear axle is b1, and the distance from the trailer front axle to the trailer mass center is a1, the initial total angular velocity ω2(0) of the trailer is calculated, i.e.

[0113]

[0114] wherein the initial rotational angular acceleration of the equivalent rotating trailer is i.e.

[0115]

[0116] Thus, the formula h is substituted into the above trailer rotational motion dynamics formula 4 to obtain the following formula.

[0117] Secondly, when k >= 1, the trailer system state at the next time k is inferred according to the initial state and the state transition relationship: first, according to the current time k-1 position of the trailer front axle center and the motion time interval T between two points, the next time k position (x qr (k), y qr (k)) of the trailer rear axle center is calculated, wherein the next time k position (x qr (k), y qr (k)) is the position in the geodetic coordinate system, i.e.

[0118]

[0119] wherein is the velocity of the x-axis direction of the trailer rear axle center in the geodetic coordinate system at the k-1 time, is the velocity of the y-axis direction of the trailer rear axle center in the geodetic coordinate system at the k-1 time. Thus, the next time k position is calculated.

[0120] Secondly, according to the current time k-1 yaw angle of the trailer, the longitudinal velocity v x2 of the trailer, the front wheel turning angle δ of the trailer, the distance b1 from the trailer mass center to the trailer rear axle, and the distance a1 from the trailer front axle to the trailer mass center, the next time k yaw angle of the trailer is calculated, i.e.

[0121]

[0122] Thirdly, according to the current time k-1 rotational angular acceleration of the equivalent rotating trailer and the motion time interval T between two points, the next time k yaw angle velocity increment Δω ′ 2 ′ (k) of the equivalent rotating trailer is calculated, i.e. ​

[0123]

[0124] Fourthly, according to the angle θ(k-1) between the tractor and the trailer at the current time k-1, the initial angle change rate between the tractor and the trailer at the current time k-1 and the motion time interval between the two points is T, the angle θ(k) between the tractor and the double-axle trailer at the next time k is calculated, i.e.

[0125]

[0126] Fifthly, according to the angle θ(k) between the tractor and the double-axle trailer at the next time k, the longitudinal speed v x2 of the tractor, the distance d2 from the front axle of the trailer to the hinged point, the distance d3 from the equivalent axle of the trailer to the front axle of the trailer, the distance b1 from the mass center of the tractor to the rear axle of the tractor, the distance d1 from the center of the rear axle of the tractor to the hinged point, and the distance a1 from the front axle of the tractor to the mass center of the tractor, the yaw angular speed ω ′ 2(k) of the equivalent single-axle trailer at the next time k is calculated, i.e.

[0127]

[0128] Sixthly, according to the angular speed ω ′ 2(k) of the equivalent single-axle trailer at the next time k, and the yaw angular speed increment Δω ′ 2 ′ (k) of the equivalent rotating trailer at the next time k, the yaw angular speed ω2(k) of the double-axle trailer at the next time k is calculated, i.e.

[0129] o)ω2(k)=ω ′ 2(k)+Δω ′ 2 ′ (k)

[0130] Seventhly, according to the angle θ(k) between the tractor and the double-axle trailer at the next time k, the distance d1 from the center of the rear axle of the tractor to the hinged point, and the longitudinal speed v x2 of the tractor, the longitudinal speed v x3 (k) of the double-axle trailer at the next time k is calculated, i.e.

[0131] p)v x3 (k)=v x2 cos(θ(k))-v x2 d1 sin(θ(k))

[0132] Eighthly, according to the longitudinal speed v x3 (k) of the double-axle trailer at the next time k, the moment of inertia I g of the trailer around its Z axis, and the cornering stiffness Cy , the distance from the trailer rear axle to the trailer mass center is b2, the distance from the trailer front axle to the trailer mass center is a2, and the yaw angular velocity of the double-axle trailer at the next moment k is ω2(k), the equivalent rotational trailer yaw angular acceleration at the next moment k is calculated as That is,

[0133]

[0134] Ninth, according to the distance from the trailer mass center to the trailer rear axle is b1, the distance from the trailer front axle to the trailer mass center is a1, the longitudinal speed of the trailer is v x2 and the yaw angular velocity of the double-axle trailer at the next moment k is ω2(k), the angle change rate of the trailer and the double-axle trailer at the next moment k is calculated as That is,

[0135]

[0136] Tenth, according to the yaw angle of the trailer at the next moment k and the longitudinal speed of the trailer is v x2 , the speed of the trailer at the next moment k is calculated as That is,

[0137]

[0138] Eleventh, according to the yaw angle of the trailer at the next moment k the angle of the trailer and the double-axle trailer at the next moment k is θ(k), the longitudinal speed of the trailer is v x2 , the distance from the trailer rear axle center to the hinge point is d1, and the position of the trailer rear axle center at the next moment k (x qr (k), y qr (k)) is calculated as the position of the trailer front wheel center at the next moment k (x gf (k), y gf (k)), that is,

[0139]

[0140] According to the above derivation process, when k = 0, that is, at the initial position, the coordinates of the trailer front axle center (x gf (k), y gf (k)), the coordinates of the trailer rear axle center (x qr (k), y qr (k)), the yaw angle of the trailer and the angle of the trailer and the trailer θ(k) can be obtained according to formulas a to h, and when k >= 1, the state of the trailer system can be derived according to formulas i to v, including the position, angular velocity, direction, and other states of the trailer.

[0141] As an embodiment, after using the current state of the tractor and trailer to obtain the predicted trajectory of the next moment movement of the tractor and trailer based on the association between the current moment state and the next moment state, the trajectory prediction method further comprises:

[0142] When the trailer is reversing, the predicted trajectory of the trailer movement is displayed on the car machine.

[0143] In the embodiments of the present application, when the user connects the trailer to reverse, the predicted trajectory of the trailer movement is displayed on the car machine, providing a reference for the user to predict the future movement trajectory of the trailer and assisting the user in safe driving.

[0144] Under normal circumstances, the actual trajectory basically coincides with the ideal trajectory. When the vehicle with the trailer is moving forward, the overall size of the vehicle increases, and special attention should be paid to the movement trajectory of the trailer when turning to avoid collision,

[0145] When reversing, the direction of the trailer movement is different from the conventional intuition when reversing without the trailer. The predicted trajectory of the trailer movement provided herein serves as a reference for the future movement trend of the trailer, helping the user to operate the vehicle with the trailer more safely and efficiently.

[0146] Under extreme circumstances, if the vehicle slips or a wheel of the trailer is stuck by a stone, etc., the actual trajectory is greatly different from the ideal trajectory, and the movement trend of the trailer cannot be accurately predicted at this time.

[0147] As an embodiment, the above method further comprises: step 1, receiving vehicle information input for prompt information displayed on the car machine; the vehicle information includes size information and mass information of the vehicle and the trailer. The prompt information is used to indicate the vehicle information required to obtain the predicted trajectory. Step 2, displaying candidate multi-axle trailer types for the vehicle information. Step 3, receiving a multi-axle trailer type selected from the candidate multi-axle trailer types as a target trailer type. Step 4, obtaining the moment of inertia and side stiffness corresponding to the target trailer type from the moment of inertia and side stiffness corresponding to the pre-set multi-axle trailer type.

[0148] According to the moment of inertia and side stiffness and the current state of the vehicle, steps 130 and 140 are performed to obtain the predicted trajectory, and the predicted trajectory is displayed on the car machine.

[0149] In actual application examples, 1) the user inputs the size information and mass information of the vehicle and the trailer according to the prompt information of the car machine.

[0150] 2) The user selects a multi-axle trailer type as a target trailer type according to the actual situation.

[0151] 3) From the pre-set inertia and cornering stiffness corresponding to the multi-axle trailer type, the inertia and cornering stiffness corresponding to the target trailer type are obtained. These inertia and cornering stiffness can be pre-set empirical values.

[0152] 4) According to the inertia and cornering stiffness and the state of the vehicle at the current time, the predicted trajectory is calculated, and the trajectory is displayed in the vehicle view on the vehicle machine.

[0153] In this way, the user inputs and selects the vehicle and trailer information through the vehicle machine, and then the trajectory prediction function starts to work and displays the predicted trajectory in the vehicle machine.

[0154] In this paper, according to the step-by-step iterative calculation according to the time interval T as above, the trailer trajectory in a certain period of time in the future can be predicted.

[0155] According to the comparison of simulation experiments, the accuracy of this method is improved compared with the trajectory prediction method based on kinematics. According to the simulation experiment in which the wheel angle is-35° to 35° and the vehicle speed is-5km / h to 5km / h, the lateral error and yaw angle of this method are improved by about 50% compared with the trajectory prediction method based on kinematics, and the yaw angle accuracy is improved by about 60%.

[0156] Based on the same inventive concept as the above method, the embodiments of the present application also propose a trajectory prediction device, as shown in Figure 7 The device can include the following modules:

[0157] The equivalent module 31 is used to equivalently convert the multi-axle of the trailer into an equivalent single axle. The multi-axle of the trailer is used for rotation and cannot swing;

[0158] The acquisition module 32 is used to acquire the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer;

[0159] The current state determination module 33 is used to determine the current state of the towing vehicle and the trailer based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axle of the towing vehicle;

[0160] The next state determination module 34 is used to obtain the predicted trajectory of the next movement of the towing vehicle and the trailer based on the association between the current state and the next state, and using the current state of the towing vehicle and the trailer.

[0161] As an embodiment, the trajectory prediction device can also but not limited to: a display module, used to display the predicted trajectory of the movement of the trailer on the vehicle machine after obtaining the predicted trajectory of the next movement of the towing vehicle and the trailer based on the association between the current state and the next state, and using the current state of the towing vehicle and the trailer.

[0162] The implementation process of the functions and roles of each module in the above device is specifically described in the implementation process of the corresponding steps in the above method, and the same technical effects can be achieved, which will not be described here.

[0163] The embodiment of the present application provides an electronic device, including the above trajectory prediction device or the following trajectory prediction system.

[0164] The embodiment of the present application provides a vehicle, including the above trajectory prediction device.

[0165] Figure 8 As shown in the structure schematic diagram of the trajectory prediction system 50 provided by the embodiment of the present application.

[0166] As Figure 8 The trajectory prediction system 50 includes one or more processors 51 for implementing the trajectory prediction method as described above.

[0167] In some embodiments, the trajectory prediction system 50 can include a storage medium 59. For example, the computer readable storage medium can store programs that can be called by the processor 51, and can include a non-volatile storage medium. In some embodiments, the trajectory prediction system 50 can include a memory 58 and an interface 57. In some embodiments, the trajectory prediction system 50 can also include other hardware according to actual application.

[0168] The computer readable storage medium of the embodiment of the present application has programs stored thereon, and the programs are executed by the processor 51 to implement the trajectory prediction method as described above.

[0169] The present application provides a computer program product, including computer programs / instructions, which are executed by the processor to implement the method described in any one of the above.

[0170] The application can take the form of a computer program product accessible from a computer- readable storage medium (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing program code for use by or in connection with a computer or any in one or more computer systems. The computer-readable storage medium can be a permanent or non-permanent, movable or non-movable medium, and can be implemented in any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0171] The embodiment of the present application provides a vehicle, comprising one or more processors, used to implement the trajectory prediction method as described above.

[0172] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0173] It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, product or device. Without more limitations, the statement "including a…" limited element does not exclude the existence of other identical elements in the process, method, product or device including the element.

Claims

1. A trajectory prediction method, characterized in that, For use with trailers equipped with tractor units, including: The multi-axle trailer is equivalent to an equivalent single axle; the multi-axle trailer is for rotation and cannot swing. Obtain the additional torque generated by the equivalent single axis, as well as the dynamic properties of the trailer's rotational motion; Based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axle of the tractor, the current state of the tractor and the trailer is determined. Based on the correlation between the current state and the next state, the predicted trajectory of the tractor and trailer at the next moment is obtained using the current state of the tractor and trailer.

2. The trajectory prediction method as described in claim 1, characterized in that, The method of converting the multi-axle trailer into an equivalent single axle includes: Any axle in a trailer with multiple axles can be equivalent to a single axle.

3. The trajectory prediction method as described in claim 1, characterized in that, The method of converting the multi-axle trailer into an equivalent single axle includes: The middle section between the multiple axles of the trailer is equivalent to an equivalent single axle.

4. The trajectory prediction method as described in claim 3, characterized in that, The multi-axle includes the front axle of the trailer and the rear axle of the trailer; The step of obtaining the additional torque generated by the equivalent single axis includes: Based on the sum of the forces on the center longitudinal direction of the front axle and the forces on the center transverse direction of the rear axle, the forces on the center transverse direction of the equivalent single axle are obtained. Based on the dynamic properties of the trailer and the dynamic formula of the additional torque, the additional torque generated by the equivalent single axle is obtained; wherein, the dynamic properties of the trailer include the lateral stiffness of the trailer wheels, the yaw rate of the trailer, the velocity of the front wheel of the trailer in the longitudinal direction of the trailer, the distance from the equivalent axle of the trailer to the front axle of the trailer, the distance between the front axle of the trailer and the center of gravity of the trailer, and the distance between the rear axle of the trailer and the center of gravity of the trailer.

5. The trajectory prediction method as described in claim 3, characterized in that, The determination of the current state of the tractor and the trailer based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axle of the tractor includes: Based on the kinematic properties of the equivalent single axle of the tractor, the yaw rate of the equivalent single axle of the tractor is obtained according to the kinematic formula of the equivalent single axle of the tractor; wherein, the kinematic properties of the equivalent single axle include the longitudinal velocity of the tractor, the front wheel turning angle of the tractor, the angle between the tractor and the trailer, the distance between the front axle of the tractor and the center of mass of the tractor, and the distance between the center of mass of the tractor and the rear axle of the tractor.

6. The trajectory prediction method as described in claim 1, characterized in that, The dynamic properties of the rotational motion include the velocity of the front wheels of the trailer in the longitudinal direction of the trailer, the lateral stiffness of the trailer wheels, and the moment of inertia of the trailer about its Z-axis; determining the current state of the tractor and the trailer based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axis of the tractor includes: determining the current state of the tractor and the trailer based on the additional torque and the dynamic properties of the rotational motion, according to the dynamic formula of the rotational motion of the trailer.

7. The trajectory prediction method according to any one of claims 1 to 6, characterized in that, After obtaining the predicted trajectory of the tractor and trailer's movement at the next moment based on the correlation between the current state and the next moment's state, the trajectory prediction method further includes: displaying the predicted trajectory of the trailer's movement on the vehicle's infotainment system when the trailer is reversing.

8. The trajectory prediction method according to any one of claims 1 to 6, characterized in that, The dynamic properties of the trailer's rotational motion are obtained using the following steps: When a prompt message is displayed on the vehicle's infotainment system, the system receives vehicle information input in response to the prompt message; the vehicle information includes the dimensions and weight of the vehicle and trailer. Based on the vehicle information, candidate multi-axle trailer types are displayed; Receive the selection of a multi-axle trailer type from the candidate multi-axle trailer types as the target trailer type; The rotational inertia and lateral stiffness corresponding to the target trailer type are obtained from the pre-set rotational inertia and lateral stiffness corresponding to the multi-axle trailer type.

9. A trajectory prediction device, characterized in that, The trajectory prediction device, applicable to trailers with tractor units, includes: An equivalent module is used to convert the multi-axle of a trailer into an equivalent single axle; the multi-axle of the trailer is for rotation and cannot swing. The acquisition module is used to acquire the additional torque generated by the equivalent single shaft, as well as the dynamic properties of the trailer's rotational motion; The current state determination module is used to determine the current state of the tractor and the trailer based on the additional torque, the dynamic properties of the rotational motion, and the kinematic properties of the equivalent single axle of the tractor. The next moment state determination module is used to obtain the predicted trajectory of the tractor and trailer's movement at the next moment based on the correlation between the current moment state and the next moment state, using the current moment state of the tractor and trailer.

10. An electronic device, characterized in that, It includes one or more processors for implementing the trajectory prediction method as described in any one of claims 1-8.

11. A vehicle, characterized in that, It includes one or more processors for implementing the trajectory prediction method as described in any one of claims 1-8.

Images