Trajectory prediction method and device, electronic equipment and vehicle

Abstract

The invention provides a trajectory prediction method and device, electronic equipment and a vehicle. The trajectory prediction method is applied to the trailer with a tractor, and comprises the following steps: enabling multiple axles of the trailer to be equivalent to an equivalent single axle; a plurality of shafts of the trailer are used for rotating and cannot swing; additional torque generated by the equivalent single shaft and the dynamic attribute of the rotary motion of the trailer are obtained; determining the state of the tractor and the state of the trailer at the current moment based on the additional moment, the dynamic attribute of the rotary motion and the kinematics attribute of an equivalent single shaft of the tractor; and based on the association relationship between the state of the current moment and the state of the next moment, using the states of the tractor and the trailer at the current moment to obtain predicted trajectories of the motion of the tractor and the trailer at the next moment.

Description

Technical Field

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

[0002] Accurately predicting the trajectory of a double-axle trailer while driving a tow vehicle is a challenging task. Traditional prediction methods rely on the driver's experience and judgment, which is prone to human error in prediction. Summary of the invention

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

[0004] The present application provides a trajectory prediction method, which is applied to a trailer with a tractor, comprising:

[0005] The multiple axles of the trailer are equivalent to an equivalent single axle; the multiple axles of the trailer are used for rotation and cannot swing;

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

[0007] 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 axle of the tractor;

[0008] Based on the correlation between the state at the current moment and the state at the next moment, the states of the tractor and the trailer at the current moment are used to obtain the predicted trajectory of the tractor and the trailer at the next moment.

[0009] Furthermore, the step of converting the multiple axles of the trailer into an equivalent single axle includes:

[0010] Any of the multiple axles of the trailer can be converted into an equivalent single axle.

[0011] Furthermore, the step of converting the multiple axles of the trailer into an equivalent single axle includes:

[0012] The middle between the multiple axles of the trailer is equivalent to an equivalent single axle.

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

[0014] The obtaining of the additional torque generated by the equivalent single shaft includes:

[0015] Based on the sum of the central longitudinal force of the front axle and the central lateral force of the rear axle, the central lateral force of the equivalent axle is obtained;

[0016] 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 wheels of the trailer, the yaw angular velocity 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.

[0017] Furthermore, the determining 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:

[0018] Based on the kinematic properties of the equivalent single axle of the tractor and according to the kinematic formula of the equivalent single axle of the tractor, the yaw angular velocity of the equivalent single axle of the tractor is obtained; wherein the kinematic properties of the equivalent single axle include the longitudinal speed of the tractor, the front wheel turning angle of the tractor, the angle between the tractor and the trailer, the distance from the front axle of the tractor to the center of mass of the tractor, and the distance from the center of mass of the tractor to the rear axle of the tractor.

[0019] Furthermore, the dynamic properties of the rotational motion include the speed of the front wheels of the trailer in the longitudinal direction of the trailer, the cornering stiffness of the wheels of the trailer and the moment of inertia of the trailer around its Z axis;

[0020] The determining 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 comprises:

[0021] Based on the additional torque and the dynamic properties of the rotational motion, and according to the rotational motion dynamics formula of the trailer, the current state of the tractor and the trailer is determined.

[0022] Furthermore, after obtaining the predicted trajectory of the tractor and the trailer at the next moment by using the current state of the tractor and the trailer based on the association relationship between the current state and the next state, the trajectory prediction method further includes:

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

[0024] Furthermore, the following steps are used to obtain the dynamic properties of the rotational motion of the trailer:

[0025] When the prompt information is displayed on the vehicle computer, receiving vehicle information input in response to the prompt information; the vehicle information includes size information and mass information of the vehicle and trailer;

[0026] For the vehicle information, display candidate multi-axle trailer types;

[0027] receiving a selection of a multi-axle trailer type from candidate multi-axle trailer types as a target trailer type;

[0028] The moment of inertia and cornering stiffness corresponding to the target trailer type are obtained from the moments of inertia and cornering stiffness corresponding to the preset multi-axle trailer types.

[0029] The present application provides a trajectory prediction device, which is applied to a trailer with a tractor, and the trajectory prediction device includes:

[0030] An equivalent module, used to convert the multiple axles of a trailer into equivalent single axles; the multiple axles of the trailer are used for rotation and cannot swing;

[0031] An acquisition module, used for acquiring the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer;

[0032] A current state determination module, 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;

[0033] The next moment state determination module is used to obtain the predicted trajectory of the tractor and the trailer at the next moment based on the correlation between the state at the current moment and the state at the next moment, using the state of the tractor and the trailer at the current moment.

[0034] The present application provides an electronic device, including one or more processors, for implementing the trajectory prediction method as described above.

[0035] The present application provides a vehicle, comprising one or more processors, for implementing the trajectory prediction method as described above.

[0036] The present application provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the method described in any one of the above items is implemented.

[0037] The present application provides a computer program product, comprising a computer program / instruction, which implements any of the above methods when executed by a processor.

[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 characteristics of the trailer are taken into account, but also the dynamic characteristics of the trailer. In this way, the current state of the tractor and trailer is used to more comprehensively consider the characteristics of the trailer without relying on manual work, so that the accuracy of the predicted trajectory of the trailer movement at the next moment is relatively high. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Shown is a schematic diagram of the application of the trajectory prediction method of an embodiment of the present application;

[0040] Figure 2 Shown is a schematic diagram of the process of the trajectory prediction method of an embodiment of the present application;

[0041] Figure 3 for Figure 2 A schematic diagram of the shape parameters of a double-axle trailer model in the trajectory prediction method shown;

[0042] Figure 4 for Figure 3 A schematic diagram of the equivalent single-axle trailer of the double-axle trailer model shown;

[0043] Figure 5 for Figure 2 A schematic diagram of the motion of a single-axle trailer in the trajectory prediction method shown;

[0044] Figure 6 for Figure 2 A schematic diagram of the rotational motion of a trailer of a double-axle trailer model in the trajectory prediction method shown;

[0045] Figure 7 The figure shows a schematic diagram of the structure of a trajectory prediction device according to an embodiment of the present application;

[0046] Figure 8 Shown is a schematic diagram of the structure of a trajectory prediction system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present specification as detailed in the appended claims.

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

[0049] In order to solve the technical problem of human error in prediction, the embodiment of the present application provides a trajectory prediction method, which simplifies the multiple axes of the trailer into an equivalent single axis, and determines the state of the trailer at the current moment based on the additional torque generated by the equivalent single axis and the dynamic properties of the rotational motion, and obtains the predicted trajectory of the trailer's motion at the next moment. In this way, without relying on the driver's experience and judgment, by combining the actual dynamic characteristics of the multi-axle trailer, the predicted trajectory of the trailer's motion at the next moment can be automatically predicted based on the multi-axle trailer's own data and the state of the trailer at the current moment. In this way, without relying on manual labor, the accuracy of predicting the predicted trajectory of the trailer's motion at the next moment is relatively high.

[0050] In the related technologies, deep learning-based networks and data-driven technologies can be used to rely on neural network models such as convolutional neural networks CNN (Convolutional Neural Network) or CNN (Recurrent Neural Network) to automatically learn the movement patterns of trailers from large amounts of data and optimize the predictive ability of the neural network model.

[0051] However, predicting the trajectory of a trailer requires a lot of training materials and a long training time. In addition, GPU-assisted reasoning operations are required, which places high demands on the computing power of the device (not friendly to low-end devices). At the same time, it is overly dependent on a large amount of training materials. If the quality of the training materials is poor (for example, it contains many errors, missing values, inaccurate or biased labels), it may also lead to the training of a poorly performing model.

[0052] Compared with the related art, the trajectory prediction method of the embodiment of the present application uses the current state of the tractor and trailer to obtain the predicted trajectory of the tractor and trailer at the next moment based on the correlation between the current state and the next state. It does not rely on model training, does not require a large amount of training materials, does not require high computing power, and can be used on low-end equipment. In this way, time is saved, processing speed is fast, and efficiency is high.

[0053] In related technologies, 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 inputs such as steering angle, throttle, brake, etc. However, since kinematics only focuses on the speed layer, it is more focused on describing the motion law of objects and uses descriptive quantities such as position, speed, acceleration, etc. for analysis.

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

[0055] Compared with the related art, the trajectory prediction method of the embodiment of the present application takes into account 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 characteristics of the trailer are taken into account, but also the dynamic characteristics of the trailer. In this way, the current state of the tractor and trailer is used to more comprehensively consider the characteristics of the trailer, so that the accuracy of the predicted trajectory of the trailer movement at the next moment is relatively high.

[0056] Figure 1 Shown is a schematic diagram of the application of the trajectory prediction method according to an embodiment of the present application.

[0057] like Figure 1 As shown, the system used in the trajectory prediction method in this article is applied to a trailer with a tractor. The trailer with a tractor involves two trajectory models:

[0058] 1. Tractor system model. The characteristics of this model are that the steering angle (δ) is fixed, the trajectory is a circle, and the trajectory description is relatively simple.

[0059] 2. Trailer system model. The characteristic of this model is that the steering angle (θ) is not fixed, so the trajectory is not a specific simple graph, and the trajectory description algorithm is relatively complex.

[0060] In this article, the tractor is used to provide power and drive the trailer.

[0061] Figure 2 The figure is a schematic flow chart of the trajectory prediction method according to an embodiment of the present application.

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

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

[0064] Since the multiple axles of the trailer are used for rotation and cannot swing, the multiple axles can be equivalent to the equivalent single axle through equivalence. This equivalence is closer to the actual multiple axles of the trailer, making the final predicted motion trajectory more accurate.

[0065] The trailer may include but is not limited to a trailer.

[0066] Step 120, obtaining the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer.

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

[0068] Step 130, 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 axle of the tractor.

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

[0070] Step 140, based on the correlation between the state at the current moment and the state at the next moment, using the state of the tractor and the trailer at the current moment, obtain the predicted trajectory of the tractor and the trailer at the next moment.

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

[0072] The embodiment of the present application uses a double-axle trailer model that is equivalent to a single-axle trailer model, thereby simplifying the prediction process. At the same time, the correlation between the state at the current moment and the state at the next moment can improve the accuracy of the prediction result, and the additional computing power consumption is very small. In this way, the predicted trajectory of the trailer movement at the next moment is predicted directly based on physical rules, rather than based on model training. This requires less computing power and can provide a more accurate prediction of the predicted trajectory of the trailer movement at the next moment in a complex driving environment.

[0073] The multiple axles of the trailer mentioned in this article can be double axles or more than three axles.

[0074] Continue to combine Figure 2 As shown, the above step 110 can obtain an equivalent single axis through at least one of the following equivalent embodiments.

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

[0076] Figure 3 for Figure 2 A schematic diagram of the shape parameters of the double-axle trailer model in the trajectory prediction method shown. Figure 4 for Figure 3Schematic diagram of the equivalent single-axle trailer of the double-axle trailer model shown.

[0077] like Figure 3 and Figure 4 In the second optional embodiment shown, the middle between the multiple axles of the trailer is equivalent to an equivalent single axle.

[0078] Continue to combine Figure 3 and Figure 4 As shown, the above-mentioned multiple axles include the front axle of the trailer and the rear axle of the trailer.

[0079] The above step 120 may further include the following first step and second step:

[0080] In the first step, the central lateral force of the equivalent axle is obtained based on the sum of the central longitudinal force of the front axle and the central lateral force of the rear axle.

[0081] The second step is to obtain the additional torque generated by the equivalent single axle based on the dynamic properties of the trailer and the dynamic formula of the additional torque; wherein the dynamic properties of the trailer include the lateral stiffness of the wheels of the trailer, the yaw angular velocity 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] In this regard, the dynamic formula of the above additional torque is as follows:

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

[0084]

[0085] Among them, M gd is the additional torque generated by replacing the double axles with the trailer equivalent axle, ω2 is the yaw rate of the trailer, and 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 trailer wheel. When the speed and yaw rate are positive, the equivalent axis is between the two axes, and its additional torque is the smallest; among them, d3 is the distance from the equivalent axis of the trailer to the front axle of the trailer, a2 is the distance from the front axle of the trailer to the center of mass of the trailer, and b2 is the distance from the rear axle of the trailer to the center of mass of the trailer.

[0086] In this way, the distance from the equivalent axle to the front axle can be determined by the above formula 2 as 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.

[0087] According to the dynamics formula, the motion of the double-axle trailer can be equivalent to adding an additional torque M gd The single-axle trailer moves at a distance d2+d3 from the articulation point, where d2 is the distance from the front axle of the trailer to the articulation point, and d3 is the distance from the equivalent axle of the trailer to the front axle of the trailer.

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

[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 d2+d3 from the hinge point. Figure 5 The other part is the moment M gd The rotational motion of the trailer around the center of mass (the rotational motion of the trailer) is as follows Figure 6 shown.

[0090] Combination Figure 1 and Figure 2 As shown, the above step 130 may further include obtaining the yaw angular velocity of the equivalent single axis of the tractor based on the kinematic properties of the equivalent single axis of the tractor according to the kinematic formula of the equivalent single axis of the tractor; wherein the kinematic properties of the equivalent single axis include the longitudinal speed 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.

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

[0092]

[0093] Among them, ω ′ 2 is the angular velocity of the tractor equivalent single-axle trailer, v x2 is the speed of the tractor in its longitudinal direction, which is known, δ is the front wheel turning angle, which is known, θ is the angle between the tractor and the trailer, which is known, a1 is the distance from the front axle of the tractor to the center of mass of the tractor, which is known, and b1 is the distance from the center of mass of the tractor to the rear axle of the tractor, which is known.

[0094] Combination Figure 1 and Figure 2As shown, the dynamic properties of the rotational motion include the speed of the front wheels of the trailer in the longitudinal direction of the trailer, the lateral stiffness of the wheels of the trailer, and the moment of inertia of the trailer around its Z axis. Accordingly, the above step 130 may further include 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 rotational motion dynamics formula of the trailer.

[0095] In this regard, the rotational motion dynamics formula of the above trailer is as follows:

[0096]

[0097] Where, ω2 is the yaw rate of the trailer (obtained from the above formula 2), ω ′ 2 ′ is the yaw rate generated by the additional torque of the trailer, v x3 is the speed of the front wheel of the trailer in the longitudinal direction of the trailer, which is known, C y is the cornering stiffness of the trailer wheel, which is known, I g is the moment of inertia of the trailer about its Z axis, which is known.

[0098] In the embodiment of the present application, based on the input appearance parameters of the tractor and trailer, the real-time steering wheel angle of the tractor, and the angle between the tractor and the trailer, an accurate trajectory prediction is achieved through a method based on the dynamic properties of the trailer's rotational motion and the kinematic properties of the tractor's equivalent single axis. The main advantage of the embodiment of the present application is that the prediction accuracy is higher than the prediction method based on kinematics alone, and the computing resources occupied are very small.

[0099] Combination Figure 2 As shown, the association relationship between the state at the current moment and the state at the next moment in the above step 140 may include a state transition relationship between the trailer system state at the current moment and the trailer system state at the next moment, such as the state transition relationship between the real-time steering wheel angle of the tractor and the initial angle of the trailer at the current moment and the real-time steering wheel angle of the tractor and the initial angle of the trailer at the next moment.

[0100] Specifically, when k>=1, the trailer system state at the next moment k is inferred based on the initial state and the state transition relationship. The specific derivation is as follows:

[0101] set up The time interval between two points is T, and the total time of the predicted path is 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 tractor is Center position of rear axle of tractor (xqr (0),y qr (0)), the tractor front wheel turning angle δ, the initial angle between the tractor and the trailer θ(0), the rate of change of the initial angle between the tractor and the trailer And, the longitudinal velocity of the tractor is v x2 .

[0104] First, based on the known state parameter values, the initial position of the front axle center of the trailer (x gf (0),y gf (0)), that is:

[0105]

[0106] Second, according to the above known state parameter values, the longitudinal speed of the tractor is v x2 The yaw angle of the tractor is The initial speed of the rear axle center of the tractor is calculated. Right now:

[0107]

[0108] Third, according to the initial angle θ(0) between the tractor and the trailer in the known state parameter values, the longitudinal speed of the tractor is v x2 , the distance from the front axle of the trailer to the hinge point is d2, the distance from the equivalent axle of the trailer to the front axle of the trailer is d3, the distance from the front axle of the tractor to the center of mass of the tractor is a1, the distance from the center of mass of the tractor to the hinge point is d1, and the distance from the center of mass of the tractor to the rear axle of the tractor is b1. The initial angular velocity ω of the equivalent single-axle trailer is calculated ′ 2(0), that is:

[0109]

[0110] Fourth, according to the initial angle θ(0) between the tractor and the trailer in the known state parameter values, the longitudinal speed of the tractor is v x2 , the distance from the center of mass of the tractor to the rear axle of the tractor is b1, the distance from the center of the rear axle of the tractor to the hinge point is d1, and the distance from the front axle of the tractor to the center of mass of the tractor is a1. The initial longitudinal velocity v of the equivalent single-axle trailer is calculated x3 (0), that is:

[0111]

[0112] Fifth, according to the angle change rate in the above known state parameter values The longitudinal velocity of the tractor is v x2, the tractor front wheel turning angle δ, the distance from the tractor mass center to the tractor rear axle is b1 and the distance from the tractor front axle to the tractor mass center is a1, the total angular velocity ω2(0) of the initial rotation of the trailer is calculated, that is:

[0113]

[0114] Among them, the initial rotation angular acceleration of the equivalent rotating trailer is Right now:

[0115]

[0116] Thus, this formula h is Substitute it into the trailer's rotational motion dynamics formula 4 above and simplify it.

[0117] Secondly, when k>=1, the trailer system state at the next moment k is inferred based on the initial state and state transition relationship: First, according to the current position k-1 of the trailer front axle center and the time interval T between the two points, the position of the tractor rear axle center at the next moment k (x qr (k),y qr (k)), where the next moment k position (x qr (k),y qr (k)) is the position in geodetic coordinates, that is:

[0118]

[0119] in, is the speed of the tractor's rear axle center in the x-axis direction in the geodetic coordinate system at time k-1, is the velocity of the tractor's rear axle center in the y-axis direction in the geodetic coordinate system at time k-1. In this way, the position k at the next time is calculated.

[0120] Second, according to the yaw angle of the tractor at the current moment k-1 The longitudinal velocity of the tractor is v x2 , the tractor front wheel turning angle δ, the distance from the tractor mass center to the tractor rear axle is b1 and the distance from the tractor front axle to the tractor mass center is a1, and the yaw angle of the tractor at the next moment k is calculated Right now:

[0121]

[0122] Third, according to the rotational angular acceleration of the equivalent rotating trailer at the current time k-1 and the time interval between the two points T, the increase in the yaw angular velocity Δω of the equivalent rotating trailer at the next time k is calculated. ′ 2 ′ (k), namely:

[0123]

[0124] Fourth, 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 The time interval between the two points is T, and the angle θ(k) between the tractor and the double-axle trailer at the next moment k is calculated, that is:

[0125]

[0126] Fifth, according to the angle θ(k) between the tractor and the two-axle trailer at the next moment k, the longitudinal speed of the tractor is v x2 , the distance from the front axle of the trailer to the hinge point is d2, the distance from the equivalent axle of the trailer to the front axle of the trailer is d3, the distance from the center of mass of the tractor to the rear axle of the tractor is b1, the distance from the center of the rear axle of the tractor to the hinge point is d1, and the distance from the front axle of the tractor to the center of mass of the tractor is a1. The yaw angular velocity ω of the equivalent single-axle trailer at the next moment k is calculated ′ 2(k), that is:

[0127]

[0128] Sixth, according to the angular velocity ω of the equivalent single-axle trailer at the next moment k ′ 2(k), and the equivalent rotation trailer's yaw rate increase Δω at the next moment k ′ 2 ′ (k), and the yaw angular velocity ω2(k) of the double-axle trailer at the next moment k is calculated, that is:

[0129] o)ω2(k)=ω ′ 2(k)+Δω ′ 2 ′ (k)

[0130] Seventh, according to the angle θ(k) between the tractor and the double-axle trailer at the next moment k, the distance from the center of the tractor's rear axle to the hinge point is d1, and the longitudinal speed of the tractor is v x2 , calculate the longitudinal velocity v of the double-axle trailer at the next moment k x3 (k) namely:

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

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

[0133]

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

[0135]

[0136] Tenth, according to the yaw angle k of the tractor at the next moment and the longitudinal velocity of the tractor is v x2 , calculate the speed of the tractor at the next moment k Right now:

[0137]

[0138] Eleventh, according to the yaw angle k of the tractor at the next moment The angle between the tractor and the two-axle trailer at the next moment k is θ(k), and the longitudinal speed of the tractor is v x2 , the distance from the rear axle center of the tractor to the hinge point is d1, and the position of the rear axle center of the tractor at the next moment k (x qr (k),y qr (k)), calculate the next moment k position of the trailer front wheel center (x gf (k),y gf (k)), namely:

[0139]

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

[0141] As an embodiment, after obtaining the predicted trajectory of the tractor and trailer at the next moment based on the correlation between the state at the current moment and the state at the next moment using the state of the tractor and the trailer at the current moment, the trajectory prediction method further includes:

[0142] When the trailer is reversing, the predicted trajectory of the trailer's movement is displayed on the vehicle computer.

[0143] In an embodiment of the present application, when a user connects a trailer and reverses, the predicted trajectory of the trailer's movement is displayed on the vehicle computer, providing the user with a reference to the trailer's future movement trajectory and assisting the user in driving safely.

[0144] Under normal circumstances, the actual driving trajectory is roughly the same as the ideal one. When operating a vehicle with a trailer, the overall size of the vehicle increases. When turning, special attention should be paid to the movement trajectory of the trailer to avoid collision.

[0145] However, when reversing, the direction of the trailer's movement is different from the conventional intuition of reversing without a trailer. This article provides users with a predicted trajectory of the trailer's movement as a reference for the trailer's future movement trend, helping users to operate vehicles with trailers more safely and efficiently.

[0146] However, in extreme cases, if the vehicle slips or a wheel of the trailer is stuck by a stone, the actual driving trajectory will be significantly 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 also includes: Step 1, when the prompt information is displayed on the vehicle computer, receiving the vehicle information input for the prompt information; the vehicle information includes the size information and mass information of the vehicle and trailer. Among them, the prompt information is used to indicate the vehicle information that needs to be input for the predicted trajectory. Step 2, for the vehicle information, displaying the candidate multi-axle trailer types. Step 3, receiving the selection of a multi-axle trailer type from the candidate multi-axle trailer types as the target trailer type. Step 4, obtaining the moment of inertia and lateral stiffness corresponding to the target trailer type from the preset moments of inertia and lateral stiffness corresponding to the multi-axle trailer types.

[0148] According to the moment of inertia and cornering stiffness and the current state of the vehicle, the above steps 130 and 140 are executed to obtain the measured trajectory, and the predicted trajectory is displayed on the vehicle computer.

[0149] In an actual application example, 1) the user inputs the size information and mass information of the vehicle and trailer according to the prompt information of the vehicle computer.

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

[0151] 3) From the preset moments of inertia and cornering stiffness corresponding to the multi-axle trailer types, the moments of inertia and cornering stiffness corresponding to the target trailer type are obtained. These moments of inertia and cornering stiffness may be preset empirical values.

[0152] 4) Calculate the predicted trajectory based on the moment of inertia and cornering stiffness and the vehicle state at the current moment, and display the trajectory in the vehicle view on the vehicle computer.

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

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

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

[0156] Based on the same inventive concept as the above method, the present application embodiment also proposes a trajectory prediction device, such as Figure 7 As shown, the device may include the following modules:

[0157] The equivalent module 31 is used to convert the multiple axles of the trailer into equivalent single axles; the multiple axles of the trailer are used for rotation and cannot swing;

[0158] An acquisition module 32, for acquiring the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer;

[0159] A current state determination module 33, for 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 axle of the tractor;

[0160] The next moment state determination module 34 is used to obtain the predicted trajectory of the tractor and trailer at the next moment based on the correlation between the state at the current moment and the state at the next moment, using the state of the tractor and trailer at the current moment.

[0161] As an embodiment, the trajectory prediction device can also include but is not limited to: a display module, which is used to obtain the predicted trajectory of the tractor and trailer at the next moment based on the correlation between the state at the current moment and the state at the next moment, using the state of the tractor and the trailer at the current moment, and then display the predicted trajectory of the trailer movement on the vehicle computer when the trailer is reversing.

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

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

[0164] An embodiment of the present application provides a vehicle, comprising the above-mentioned trajectory prediction device.

[0165] Figure 8 Shown is a schematic diagram of the structure of a trajectory prediction system 50 provided in an embodiment of the present application.

[0166] like Figure 8 As shown, 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 may include a storage medium 59. For example, the computer-readable storage medium may store a program that can be called by the processor 51, and may include a non-volatile storage medium. In some embodiments, the trajectory prediction system 50 may include a memory 58 and an interface 57. In some embodiments, the trajectory prediction system 50 may also include other hardware according to actual applications.

[0168] The computer-readable storage medium of the embodiment of the present application stores a program thereon, and when the program is executed by the processor 51, it is used to implement the trajectory prediction method described above.

[0169] The present application provides a computer program product, comprising a computer program / instruction, which implements any of the above methods when executed by a processor.

[0170] The present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0171] An embodiment of the present application provides a vehicle, comprising one or more processors, for implementing the trajectory prediction method as described above.

[0172] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

[0173] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the phrase "includes a ..." defines an element, and does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

Claims

1. A trajectory prediction method, characterized in that: Applicable to trailers with tractors, including: The multiple axles of the trailer are equivalent to an equivalent single axle; the multiple axles of the trailer are used for rotation and cannot swing; Obtaining the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer; 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 axle of the tractor; Based on the correlation between the state at the current moment and the state at the next moment, the states of the tractor and the trailer at the current moment are used to obtain the predicted trajectory of the tractor and the trailer at the next moment.

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

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

4. The trajectory prediction method according to claim 3, characterized in that: The multi-axle includes a front axle of the trailer and a rear axle of the trailer; The obtaining of the additional torque generated by the equivalent single shaft includes: Based on the sum of the central longitudinal force of the front axle and the central lateral force of the rear axle, the central lateral force of the equivalent axle is 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 wheels of the trailer, the yaw angular velocity 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.

5. The trajectory prediction method according to claim 3, characterized in that: The determining 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 comprises: Based on the kinematic properties of the equivalent single axle of the tractor and according to the kinematic formula of the equivalent single axle of the tractor, the yaw angular velocity of the equivalent single axle of the tractor is obtained; wherein the kinematic properties of the equivalent single axle include the longitudinal speed of the tractor, the front wheel turning angle of the tractor, the angle between the tractor and the trailer, the distance from the front axle of the tractor to the center of mass of the tractor, and the distance from the center of mass of the tractor to the rear axle of the tractor.

6. The trajectory prediction method according to claim 1, characterized in that: The dynamic properties of the rotational motion include the speed of the front wheels of the trailer in the longitudinal direction of the trailer, the lateral stiffness of the wheels of the trailer and the moment of inertia of the trailer around its Z-axis; the determining the states of the tractor and the trailer at a current moment 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 states of the tractor and the trailer at a current moment according to the dynamic formula of the rotational motion of the trailer based on the additional torque and the dynamic properties of the rotational motion.

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 the trailer at the next moment based on the association between the state at the current moment and the state at the next moment, using the state of the tractor and the trailer at the current moment, the trajectory prediction method also includes: when the trailer is reversing, displaying the predicted trajectory of the trailer's movement on the vehicle computer.

8. The trajectory prediction method according to any one of claims 1 to 6, characterized in that: The following steps are used to obtain the dynamic properties of the rotational motion of the trailer: When the prompt information is displayed on the vehicle computer, receiving vehicle information input in response to the prompt information; the vehicle information includes size information and mass information of the vehicle and trailer; For the vehicle information, display candidate multi-axle trailer types; receiving a selection of a multi-axle trailer type from candidate multi-axle trailer types as a target trailer type; The moment of inertia and cornering stiffness corresponding to the target trailer type are obtained from the moments of inertia and cornering stiffness corresponding to the preset multi-axle trailer types.

9. A trajectory prediction device, characterized in that: Applied to a trailer with a tractor, the trajectory prediction device comprises: An equivalent module, used to convert the multiple axles of a trailer into equivalent single axles; the multiple axles of the trailer are used for rotation and cannot swing; An acquisition module, used for acquiring the additional torque generated by the equivalent single axle and the dynamic properties of the rotational motion of the trailer; A current state determination module, 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 the trailer at the next moment based on the correlation between the state at the current moment and the state at the next moment, using the state of the tractor and the trailer at the current moment.

10. An electronic device, characterized in that: The method comprises one or more processors, and is used to implement the trajectory prediction method according to any one of claims 1 to 8.

11. A vehicle, characterized in that: The method comprises one or more processors, and is used to implement the trajectory prediction method according to any one of claims 1 to 8.

Images