A method for identifying turning curvature of tracked vehicles based on machine learning

Abstract

The present invention relates to a method for identifying the steering curvature of a tracked vehicle based on machine learning. This method belongs to the field of vehicle driving control and solves the problem of difficulty in real-time calculation of steering curvature in the prior art. The specific steps include: collecting driving data of the tracked vehicle to form a feature vector set; calculating the theoretical slip rates on both sides of the corresponding track to form a historical slip rate set; training an offline two-stage machine learning model based on the feature vector set and the historical slip rate set to obtain a slip rate estimation model for both sides of the tracked vehicle; utilizing an online identification process to pass the real-time collected vehicle driving data through the slip rate estimation model to obtain a real-time estimated value of the slip rate on both sides; and calculating the real-time vehicle speed and yaw angular velocity of the tracked vehicle based on the real-time estimated value of the slip rate on both sides, thereby achieving real-time estimation of the steering curvature of the tracked vehicle.

Description

Technical Field

[0001] The present invention relates to the field of vehicle driving control, and in particular to a method for identifying the turning curvature of a tracked vehicle based on machine learning. Background Art

[0002] Estimating the slip rate and steering curvature of tracked vehicles is a complex problem, strongly dependent on the vehicle's dynamic characteristics and the interaction between the vehicle and the ground. This interaction is difficult to accurately assess using model-based methods. In practical calculations, the vehicle's theoretical motion state is often first accurately calculated, followed by measuring the vehicle's actual state transitions on the road. Finally, the slip rate and steering curvature are accurately estimated based on the deviation between the two. Calculating the theoretical vehicle motion state can be done by measuring underlying driving data to infer the theoretical state changes without considering the slip between the track and the ground. This process is relatively simple and reliable. Measuring the actual state transitions on the road can be done manually or with the help of GPS sensor information. However, manual measurement is difficult to perform under the intense and prolonged driving conditions and is difficult to achieve real-time calculations. The accuracy of the vehicle's GPS position and orientation information is severely affected by signal conditions, making it difficult to apply to various driving conditions. Summary of the Invention

[0003] In view of the above analysis, an embodiment of the present invention aims to provide a method for identifying the turning curvature of a tracked vehicle based on machine learning, so as to solve the problem of difficulty in real-time calculation of the turning curvature in the prior art.

[0004] The purpose of the present invention is mainly achieved through the following technical solutions:

[0005] A method for identifying the turning curvature of a tracked vehicle based on machine learning comprises the following steps:

[0006] Collecting driving data of the tracked vehicle to form a feature vector set τ1 of the tracked vehicle, wherein the driving data includes left and right track winding speeds, left and right track driving torques, left and right driving wheel speeds, yaw angular velocity, longitudinal acceleration, and lateral acceleration;

[0007] By calculating the theoretical slip rates on both sides of the corresponding crawler, a historical slip rate set τ2 is formed, wherein the historical slip rate set τ2 includes the slip rates of the crawlers on both sides;

[0008] Based on the feature vector set τ1 and the historical slip rate set τ2, an offline two-stage machine learning model is trained to obtain a slip rate estimation model for both sides of the tracked vehicle;

[0009] By using an online identification process, the real-time collected vehicle driving data is passed through the two-side slip rate estimation model to obtain a real-time estimated value of the two-side slip rate;

[0010] The real-time vehicle speed of the tracked vehicle is obtained based on the real-time estimated values ​​of the slip rates on both sides and the real-time measured track winding speed; the real-time yaw angular velocity is obtained based on the structural parameters of the tracked vehicle and the vehicle speed; and the real-time estimated value of the steering curvature of the tracked vehicle is obtained based on the vehicle speed and the yaw angular velocity.

[0011] Furthermore, the two-stage machine learning model includes an offline clustering model and an offline regression model. The specific steps of obtaining the two-side slip rate estimation model include:

[0012] Based on the feature vector set τ1, a steering action feature sub-vector set τ3, a steering motivation feature sub-vector set τ4 and a steering acceleration feature sub-vector set τ5 are obtained;

[0013] Based on the three sub-vector sets, an offline clustering model is established. After training, three cluster labels are obtained: the steering action degree label ty1, the steering motivation degree label ty2, and the steering acceleration degree label ty3.

[0014] The feature vector set τ1 is combined with the three cluster labels to form an input training set, and the historical slip rate set τ2 is used as the corresponding output to train an offline regression model of the slip rates on both sides.

[0015] Furthermore, the expressions of the corresponding sub-vectors in the three sub-vector sets are respectively:

[0016]

[0017]

[0018] in, are the i-th subvectors of the training sets τ3, τ4, and τ5 respectively; v nl and v nr are the left and right track winding speeds respectively; M l and M r are the left and right track driving torques respectively; n l and n r are the speeds of the left and right driving wheels respectively; ω yaw is the yaw angular velocity; a1 is the longitudinal acceleration; a2 is the lateral acceleration; the superscript i represents the i-th sampling result.

[0019] Furthermore, the specific steps of training the offline clustering model include:

[0020] The input data sets of the offline clustering model are respectively formed based on the three sub-vector sets;

[0021] Initialize the particle swarm based on the particle swarm optimization algorithm and calculate the fitness of each particle according to its current position;

[0022] Particles update themselves by tracking individual and global extrema while recording the positions of said particles;

[0023] The weights and constraints in the particle swarm optimization algorithm are associated with the particle fitness and time, the updated particles are obtained and the fitness is calculated, and the entire particle swarm is iterated to find the optimal particle position based on the population fitness variance;

[0024] The optimal position is used as the initial center, the input data set is divided, and the K-means clustering algorithm is used for training respectively to obtain the steering action degree label ty1, the steering motivation degree label ty2 and the steering acceleration degree label ty3.

[0025] Furthermore, the calculation formula of the particle fitness is:

[0026]

[0027] Among them, f i is the fitness of the i-th particle; m is the number of clusters set for initialization; C i 、C j are the i-th and j-th clusters respectively; avg(C) represents the average distance operation of the clusters;

[0028] represents the center of cluster i; |C i | represents the number of data in cluster i; dis(x, y) represents the Euclidean distance, and

[0029] j is a number from 1 to m that is not equal to i.

[0030] Furthermore, the specific steps of training the offline regression model include:

[0031] Using the three cluster labels combined with the feature vector set τ1, a training set τ6 is obtained as the input sample of the offline regression model of the slip rates on both sides, and the historical slip rate set τ2 is used as the corresponding true value output;

[0032] Using the DBSCAN clustering algorithm to divide the input samples into normal samples and abnormal samples;

[0033] The sample weights are initialized based on the AdaBoost regression model, and the sample weights are updated by using a weight update strategy in combination with the abnormal samples to train the offline regression model.

[0034] Furthermore, the expression of the offline regression model output is:

[0035]

[0036] Among them, s l 、s r are the estimated values ​​of left and right track slip rates, respectively; Respectively represent the learners for estimating the left and right track slip rates; They represent the weight coefficients of the left and right track slip rate estimation learners respectively; m represents the number of iterations.

[0037] Furthermore, the subset expression of the training set τ6 is:

[0038]

[0039] in, is the i-th subset of the training set τ6; v nl and v nr are the left and right track winding speeds respectively; M l and M r are the left and right track driving torques respectively; n l and n r are the speeds of the left and right driving wheels respectively; ω yaw is the yaw angular velocity; a1 is the longitudinal acceleration; a2 is the lateral acceleration; the superscript i represents the i-th sampling result.

[0040] Furthermore, the specific steps of the online identification process include:

[0041] Extracting real-time feature vectors using real-time collected tracked vehicle driving data;

[0042] Inputting the real-time feature vector into the trained offline clustering model for clustering, assigning labels to the data points of the clustering results, and combining the feature vector to form the input vector of the offline regression model;

[0043] The input vector is input into the trained offline regression model to obtain a real-time estimated value of the slip rate on both sides of the tracked vehicle.

[0044] Furthermore, a real-time estimated value of the steering curvature is obtained based on the following formula:

[0045]

[0046] Among them, ρ i is the steering curvature of the i-th sampling result; ω yaw is the yaw angular velocity; v i is the vehicle speed of the i-th sampling result; v nl and vnr are the left and right track winding speeds respectively; s l 、s r are the estimated values ​​of the left and right track slip rates, respectively; B is the center distance of the tracks on both sides; the superscript i represents the i-th sampling result.

[0047] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0048] 1. The present invention proposes to accurately estimate the real-time value of the slip rate on both sides of the tracked vehicle, combine the structural parameters of the tracked vehicle and the measured track winding speed to obtain the vehicle speed and yaw angular velocity of the tracked vehicle, and based on the vehicle speed and yaw angular velocity, realize accurate real-time estimation of the steering curvature of the tracked vehicle, thereby solving the problem of difficulty in real-time calculation of the steering curvature.

[0049] 2. A machine learning model based only on the vehicle's underlying driving data and inertial navigation output acceleration is used to obtain the mapping relationship between vehicle driving data and slip rate. The vehicle's real-time driving parameters are input into the model through a linear estimation process to achieve real-time estimation of the slip rate. This eliminates the need for high-precision GPS data and allows for accurate slip rate estimation under any signal conditions, improving applicability and estimation accuracy under various operating conditions.

[0050] In the present invention, the above-mentioned technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of the present invention will be described in the following description, and some advantages will become apparent from the description or be learned through practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like parts throughout the drawings.

[0052] Figure 1 is a flow chart of an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of a design of a turning curvature recognition method according to an embodiment of the present invention;

[0054] Figure 3 Schematic diagram of an offline clustering model according to an embodiment of the present invention;

[0055] Figure 4 Schematic diagram of clustering results according to an embodiment of the present invention;

[0056] Figure 5 Schematic diagram of an offline regression model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0058] A specific embodiment of the present invention discloses a method for identifying the turning curvature of a tracked vehicle based on machine learning, such as Figure 1 As shown, the following steps are included:

[0059] Step S1, collecting driving data of the tracked vehicle to form a feature vector set τ1 of the tracked vehicle, wherein the driving data includes left and right track winding speeds, left and right track driving torques, left and right driving wheel speeds, yaw angular velocity, longitudinal acceleration, and lateral acceleration;

[0060] Step S2, by calculating the theoretical slip rates on both sides of the corresponding crawler, a historical slip rate set τ2 is formed;

[0061] Step S3: Based on the feature vector set τ1 and the historical slip rate set τ2, an offline two-stage machine learning model is trained to obtain a slip rate estimation model for both sides of the tracked vehicle;

[0062] Step S4: using an online identification process, applying the real-time collected vehicle driving data to the two-side slip rate estimation model to obtain a real-time estimated value of the two-side slip rate;

[0063] Step S5: obtaining the real-time speed of the tracked vehicle based on the real-time estimated values ​​of the slip rates on both sides and the real-time measured track winding speed; obtaining the real-time yaw angular velocity based on the structural parameters of the tracked vehicle and the vehicle speed; and obtaining the real-time estimated value of the steering curvature of the tracked vehicle based on the vehicle speed and the yaw angular velocity.

[0064] Through the above method, the real-time values ​​of the slip rates on both sides of the tracked vehicle are estimated. Combined with the structural parameters of the tracked vehicle and the measured track winding speed, the vehicle speed and yaw angular velocity of the tracked vehicle are obtained. Based on the vehicle speed and yaw angular velocity, the real-time estimation of the steering curvature of the tracked vehicle is finally achieved, thereby solving the problem of difficulty in real-time calculation of the steering curvature.

[0065] For example, in step S1, various sensors (including inertial sensors, wheel speed sensors, etc.) and inertial navigation are installed at corresponding positions of the vehicle to collect data such as the vehicle wheel speed during the vehicle's driving process, thereby forming a vehicle feature vector set τ1, where the expression of the i-th feature vector is:

[0066]

[0067] The superscript i represents the i-th sampling result, reflecting the sampling situation at a certain time point under a certain road condition; the collected data includes the left and right track winding speed v nl and v nr , left and right crawler driving torque M l and M r , left and right driving wheel speed n l and n r , yaw angular velocity ω yaw , longitudinal acceleration a1 and lateral acceleration a2.

[0068] It should be noted that in order to ensure that the final curvature is closer to the curvature of the actual road, the vehicle should be kept on the center line of the road as much as possible when driving, and areas with stable and good GPS signals should be selected to collect multi-dimensional driving data of the vehicle on different road surfaces.

[0069] It should be noted that the calculation of the theoretical slip rates on both sides of the track in step S2 may be related to factors such as the track traction force, the ground shear deformation coefficient, and the track ground contact length, resulting in different calculation formulas.

[0070] For example, the theoretical slip rate of the tracks on both sides is calculated by the following formula:

[0071] Where K is the ground shear deformation coefficient; L is the track ground length; M is the track traction force; R is the driving wheel radius; S c is a constant related to ground conditions; G is the vehicle weight; is the ground friction angle; during the slip rate calculation process on the left and right sides, the values ​​of L, M and R may be different.

[0072] The subset expression of the historical slip rate set τ2 is:

[0073] Furthermore, the slip rate estimation model on both sides in step S3 is as follows: Figure 2As shown in the figure, it includes two offline training processes and one online identification process. In the offline training part, the vehicle driving parameters are first measured by the vehicle sensors and inertial navigation to form a historical feature vector set. The feature vector set is then divided into three sub-vector sets according to different feature attributes. The three sub-vector sets are then clustered using the improved particle swarm optimization K-means algorithm, and labels are assigned according to their respective clustering results. A new data set is formed with the original feature vector set. Using this data set, a regression model is trained to find the relationship between the vehicle driving feature vector and the three steering degree labels and the slip rate. In the online identification part, the trained offline clustering model and offline regression model are combined with various data collected by the vehicle sensors and inertial navigation during the vehicle driving process to form a feature vector. The current slip rate on both sides of the track is estimated online in real time. The real-time estimated value of the vehicle steering curvature (i.e., road curvature) is obtained by combining the calculated relationship between the vehicle speed and the track slip rate as well as the winding speed of the tracks on both sides.

[0074] Exemplarily, the specific implementation steps of the two-side slip ratio estimation model include:

[0075] Step S31, processing the feature vector set τ1 and dividing it into a steering action feature sub-vector set τ3, a steering motivation feature sub-vector set τ4 and a steering acceleration feature sub-vector set τ5 according to different feature attributes;

[0076] Specifically, the left and right track winding speeds and the left and right drive wheel speeds are subtracted and combined with the vehicle yaw angular velocity to form a characteristic subvector set τ3 that represents the vehicle steering action; the left and right track driving torques are subtracted to form a characteristic subvector set τ4 that represents the vehicle steering motivation; the longitudinal and lateral accelerations of the vehicle are extracted from the vehicle characteristic parameter vector set τ1 to form a steering acceleration characteristic subvector set τ5 that represents the steering acceleration characteristics of the vehicle steering process. The corresponding subvector expressions are as follows:

[0077]

[0078] Step S32: establishing offline clustering models based on the three sub-vector sets, and obtaining three cluster labels through training;

[0079] For example, when a car is driving, taking into account the impact of different steering attributes on the steering performance of the entire vehicle, as well as the correlation coupling relationship between steering attributes and slip rate, during offline clustering processing, the three sub-vector sets are clustered separately using the improved particle swarm optimization K-means algorithm to obtain relevant classifications and labels of steering action, steering motivation, and steering acceleration.

[0080] Specifically, the global search capability of the improved particle swarm optimization algorithm (PSO) is used to find a good particle swarm as the center of the K-means algorithm, and then the K-means algorithm is used to search the center to obtain the best clustering result. Figure 3 As shown, the specific steps include:

[0081] Step S321: establishing input data sets for offline clustering models based on the three sub-vector sets;

[0082] For example, the input vector set α=[α1,α2...α k ] is used as the model input data set, α represents the steering action feature sub-vector set τ3, the steering motivation feature sub-vector set τ4 or the steering acceleration feature sub-vector set τ5, and the corresponding sub-vectors are expressed as:

[0083]

[0084] Step S322: Initialize the particle swarm and calculate the fitness of each particle based on the current position of the particle;

[0085] For example, n particles are randomly generated, each of which is an m*k dimensional vector, where m is the number of clusters initially set, and k is the dimension of each data point in the dataset. A random data point is selected as the center, and each particle divides the input model dataset according to the minimum distance principle based on the selected center. The current fitness of each particle is calculated as:

[0086]

[0087] Among them, f i is the fitness of the i-th particle; C i is the i-th cluster; avg(C) represents the average distance operation of the cluster; represents the center of cluster i; |C| represents the number of data in the current cluster; j is a number from 1 to m that is not equal to i; dis(x, y) represents the Euclidean distance, and

[0088]

[0089] Step S323: The particle updates itself by tracking the individual extreme value and the global extreme value, and finds the corresponding particle position at the same time.

[0090] Specifically, in each iteration, if the current fitness value is better than the individual extreme value or the global extreme value, the fitness value of the particle is updated to the extreme value and the corresponding position is recorded, otherwise it remains unchanged. The calculation formula for iterative update of the entire particle swarm is:

[0091] v i (t) = ω i*v i (t-1)+C1*r1*(P i (t-1)-X i (t-1))+C2*r2*(g(t-1)-X i (t-1)),

[0092] X i (t) = X i (t-1)+v i (t),

[0093] Among them, v i (t) represents the velocity of particle i during the t-th iteration process, which indicates the direction and distance that the particle moves in the solution space and determines how the particle moves in the solution space to find a better solution; X i (t) represents the position of particle i in the t-th iteration process, which directly corresponds to a potential solution in the data set; P i (t) and g(t) represent the individual extreme position and global optimal position of particle i in the t-th iteration process respectively; ω i is the inertia weight of particle i; C1 and C2 are the constraint factors of the particle; r1 and r2 are random numbers uniformly distributed between 0 and 1.

[0094] Step S324: Associating the weights and constraints in the PSO algorithm with the particle fitness and time, obtaining updated particles and calculating their fitness, and iterating the entire particle swarm to find the optimal particle position based on the population fitness variance;

[0095] Exemplary, improved weight and constraint factor calculation formulas are:

[0096]

[0097] Among them, g B es t is the global extreme value; tmax is the maximum time allowed, which is related to the maximum number of iterations; time is the current time.

[0098] Based on the improved weights and constraint factors, a new iterative update formula is formed. The updated particles are used as cluster centers to re-cluster the data set and recalculate the fitness of each particle. The current population fitness variance θ is calculated using the following formula:

[0099]

[0100] Among them, f avg is the fitness f i The average value of .

[0101] The variance θ is higher than the set threshold or the maximum number of iterations N is not reachedmax , then readjust the weights and constraint factors and repeat the iterative process until the optimal position is obtained using the particle swarm algorithm.

[0102] Through the above improvements to PSO, the weights and constraint factors can be dynamically adjusted, which can promote the convergence and search efficiency of the algorithm and thus find the optimal solution more quickly.

[0103] Step S325: Using the obtained optimal position as the initial center, re-divide the input data set, and use the K-means clustering algorithm to train them separately to obtain three related classification clusters. By assigning cluster labels to the classification clusters, the different degrees of the three attributes are characterized, and the steering action degree label ty1, the steering motivation degree label ty2 and the steering acceleration degree label ty3 are obtained, as shown in FIG. Figure 4 As shown in Figure 2. Sort the data in the cluster by its mean value, and assign labels to each cluster and its data points.

[0104] Specifically, the best position is used as the initial center to establish the category matrix M n*k , the data set is re-divided and clustered according to the nearest distance principle of the K-means algorithm, and the category matrix is ​​updated based on the following formula:

[0105]

[0106] According to the division results, the average value of each cluster is calculated as the new cluster center. The calculation formula is:

[0107]

[0108] The iteration is considered to be completed when the category matrix does not change or the maximum number of iterations is exceeded.

[0109] In step S33 , the vehicle feature vector set τ1 is combined with the three cluster labels to form a training set τ6 for the offline regression model of the slip rate on both sides. The historical slip rate set τ2 is used as the corresponding true value output to train the offline regression model of the slip rate on both sides.

[0110] For example, assuming that the training set τ6 contains N training subsets, the expression of the i-th training subset is:

[0111]

[0112] Furthermore, the improved AdaBoost regression model based on the DBSCAN algorithm is used for training to find the relationship between the vehicle driving feature vector and the three-category degree labels and the slip rate, and the estimated results of the slip rate on both sides are obtained, such as Figure 5 shown.

[0113] It should be noted that the track slip rates on the left and right sides of the tracked vehicle are different, so the offline regression models are trained separately. For example, taking the left side as an example, the specific steps include:

[0114] Step S331: Utilize the three cluster labels in combination with the vehicle feature vector set τ1 to obtain a training set τ6. Use the data in the training set τ6 as input samples for an offline regression model of the slip rates on both sides, and output the historical slip rate set τ2 as the true value.

[0115] For example, the feature vector and common vector dimension on the left side of the slip rate regression training set τ6 are extracted to form a feature data set τ l , the expression is:

[0116] τ l =[ω yaw ,v nl ,M l ,n l ,a1,a2,ty1,ty2,ty3],

[0117] Wherein, the subscript l represents the relevant eigenvector of the left track.

[0118] Step S332: using the DBSCAN clustering algorithm to divide all the input samples into normal samples and abnormal samples;

[0119] For example, the abnormal samples are identified according to the DBSCAN clustering algorithm, that is, by examining the data set τ l Any point in Search by the set minimum number All density-reachable objects in the ε neighborhood of Regarding the ε neighborhood and the minimum number of classes, in the next iteration, other points in the ε neighborhood are examined for expansion until a complete class is found. The number of points contained in the ε neighborhood of is less than the minimum number, that is, is the boundary point, will be temporarily marked as an outlier. After the iteration is completed, the remaining points that do not belong to any class are outliers and are marked accordingly. Based on this, all samples are divided into normal samples and abnormal samples. Here, ε is a manually set parameter.

[0120] Step S333: Initialize sample weights based on the AdaBoost regression model, use the weight update strategy in combination with the abnormal samples to update the weights, and train to obtain an offline regression model.

[0121] For example, let the initialization sample weight be Set the sampling generalization of the i-th data sample to And extract n (n is not greater than N) samples from the training set with replacement, and train the base learner G according to the training data m Get the regression model, base learner G m It can be a decision tree, Bayesian classifier, etc.

[0122] For example, a decision tree is selected to learn the regression model That is, traverse all the eigenvalues ​​of all features, divide the data set once for each eigenvalue, and then calculate the sum of the total variance of the two subsets after the division, find the eigenvalue that can minimize the sum of the total variance, and then divide it again to get two trees, and recursively perform the same operation on the two trees. Then, calculate the maximum deviation of the learner's prediction value on the training sample based on the following formula

[0123]

[0124] Calculate the relative error for each training sample The formula is:

[0125]

[0126] Calculate the loss value of each training sample The formula is:

[0127]

[0128] Calculate the error value of the learner The formula is:

[0129]

[0130] It should be noted that if e m >1 / 2, the effect of the learner is worse than random guessing. In this case, delete the learner and iterate again. Therefore, the correct iteration condition requires 0 <e m <1 / 2.

[0131] Calculate the weight coefficient α of the learner m The formula is:

[0132]

[0133] Specifically, according to the weight update strategy formula, combined with the abnormal samples identified by the DBSCAN clustering algorithm, the weight of the sample is updated:

[0134]

[0135] Where m represents the number of iterations; ω m,i is the weight of the i-th sample at the m-th iteration; lossm,i is the loss value of the i-th sample at the m-th iteration; e m is the prediction error rate of the learner; RE i is the relative error of abnormal samples; The input sample data for the left slip rate estimation; the superscript 1 represents the relevant parameters for the left slip rate estimation.

[0136] After completing the number of iterations m, the weighted average of the prediction results of the m learners is calculated as the output. After the training of both sides is completed, the final strong regression function is output through the offline regression model:

[0137]

[0138] Based on this, the final offline regression model is obtained through training, which can achieve a more accurate estimation of the vehicle slip rate by combining the characteristic parameters of the tracked vehicle during driving with the degree of slip obtained by classification.

[0139] In the online identification process of step S4, the real-time collected tracked vehicle driving data is used for feature extraction to form a feature vector. The feature vector is used as input to cluster the data through the offline clustering model of the slip rate on both sides obtained by training, and labels are assigned to the data points. The feature vector is combined with the offline regression data set τ of the slip rate. on , where the subset expression is:

[0140]

[0141] The dataset τ on The offline regression model of the slip rates on both sides is input, and the real-time slip rates on both sides of the tracked vehicle are estimated and output by the offline regression model of the slip rates on both sides.

[0142] It should be noted that after the online identification process is completed, in order to improve the accuracy of the model, the estimated values ​​of the track slip rates on both sides obtained by the model are recorded. At the same time, the theoretical true slip rate of the tracks on both sides is calculated, and the estimated value is compared with the true value to obtain the relative error data set γ. When the mean and variance of the error set are less than the set threshold, the model is considered accurate. Otherwise, the model is retrained by calculating the true slip rate until it is accurate.

[0143] Furthermore, in step S5, the estimated value of the slip ratio is used to estimate the vehicle speed and yaw rate through the vehicle kinematic relationship, and the calculation formula is:

[0144]

[0145] Where, are the estimated values ​​of the track slip rates on both sides. When the slip rate is greater than 0, the track is slipping; when the slip rate is less than 0, the track is slipping. nl 、v nr are the directly measured winding speeds of the left and right tracks, B is the center distance of the tracks on both sides, v is the estimated result of the vehicle speed, ω yaw is the yaw rate.

[0146] In addition, the turning curvature is the inverse of the turning radius. The real-time turning curvature of the current tracked vehicle can be estimated by the estimated vehicle speed and the actual measured yaw rate. The calculation formula is:

[0147]

[0148] Among them, ρ i is the steering curvature of the i-th sampling result.

[0149] It should be noted that during the movement of a tracked vehicle, a large amount of slip and sliding motion occurs between the tracks and the ground. This makes the tracked vehicle dynamics model, which includes a large number of unstructured road parameters, very complex and unsuitable for research with high real-time requirements. Therefore, accurately estimating the vehicle speed is somewhat difficult. However, the above method can estimate the real-time slip rate of the tracks on both sides. The structural parameters of the tracked vehicle and the measured track winding speed can be used to obtain the vehicle speed and yaw angular velocity, and then identify the real-time steering curvature.

[0150] Compared to existing technologies, this embodiment provides a machine learning-based method for identifying the steering curvature of a tracked vehicle. By estimating the real-time slip ratio on both sides of the tracked vehicle and combining it with the vehicle's structural parameters and the measured track winding speed, the method derives the vehicle's speed and yaw rate. Based on these values, the method accurately and in real time estimates the steering curvature of the tracked vehicle, thereby resolving the difficulty of calculating the steering curvature in real time. This method ensures the applicability and accuracy of the slip ratio estimation method under various operating conditions. It utilizes a machine learning model based solely on the vehicle's underlying driving data and inertial navigation output acceleration. By constructing a two-stage machine learning model, the method maps the vehicle driving data to the slip ratio, achieving precise estimation. Furthermore, during the online estimation process, slip ratio estimation can be achieved simply by inputting the vehicle's real-time driving parameters into the model. This process eliminates the need for high-precision GPS data and enables accurate slip ratio estimation under all conditions.

[0151] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0152] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for identifying the turning curvature of a tracked vehicle based on machine learning, characterized in that: The steps include: Collecting driving data of the tracked vehicle to form a feature vector set τ1 of the tracked vehicle, wherein the driving data includes left and right track winding speeds, left and right track driving torques, left and right driving wheel speeds, yaw angular velocity, longitudinal acceleration, and lateral acceleration; By calculating the theoretical slip rates on both sides of the corresponding crawler, a historical slip rate set τ2 is formed, wherein the historical slip rate set τ2 includes the slip rates of the crawlers on both sides; Based on the feature vector set τ1 and the historical slip rate set τ2, an offline two-stage machine learning model is trained to obtain a slip rate estimation model for both sides of the tracked vehicle; By using an online identification process, the real-time collected vehicle driving data is passed through the two-side slip rate estimation model to obtain a real-time estimated value of the two-side slip rate; Based on the real-time estimated values ​​of the slip rates on both sides and the real-time measured track winding speed, a real-time speed of the tracked vehicle is obtained; based on the structural parameters of the tracked vehicle and the speed, a real-time yaw rate is obtained; based on the speed and the yaw rate, a real-time estimated value of the turning curvature of the tracked vehicle is obtained; The two-stage machine learning model includes an offline clustering model and an offline regression model. The specific steps of obtaining the two-side slip rate estimation model include: Based on the feature vector set τ1, a steering action feature sub-vector set τ3, a steering motivation feature sub-vector set τ4 and a steering acceleration feature sub-vector set τ5 are obtained; Based on the three sub-vector sets, an offline clustering model is established. After training, three cluster labels are obtained: the steering action degree label ty1, the steering motivation degree label ty2, and the steering acceleration degree label ty3. The feature vector set τ1 is combined with the three cluster labels to form an input training set, and the historical slip rate set τ2 is used as the corresponding output to train an offline regression model of the slip rates on both sides.

2. The method for identifying the turning curvature of a tracked vehicle based on machine learning according to claim 1, characterized in that: The expressions of the corresponding sub-vectors in the three sub-vector sets are: in, are the i-th subvectors of the training sets τ3, τ4, and τ5 respectively; v nl and v nr are the left and right track winding speeds respectively; M l and M r are the left and right track driving torques respectively; n l and n r are the speeds of the left and right driving wheels respectively; ω yaw is the yaw angular velocity; a1 is the longitudinal acceleration; a2 is the lateral acceleration; the superscript i represents the i-th sampling result.

3. The method for identifying turning curvature of a tracked vehicle based on machine learning according to claim 1, characterized in that: The specific steps of training the offline clustering model include: The input data sets of the offline clustering model are respectively formed based on the three sub-vector sets; Initialize the particle swarm based on the particle swarm optimization algorithm and calculate the fitness of each particle according to its current position; Particles update themselves by tracking individual and global extrema while recording the positions of said particles; The weights and constraints in the particle swarm optimization algorithm are associated with the particle fitness and time, the updated particles are obtained and the fitness is calculated, and the entire particle swarm is iterated to find the optimal particle position based on the population fitness variance; The optimal position is used as the initial center, the input data set is divided, and the K-means clustering algorithm is used for training respectively to obtain the steering action degree label ty1, the steering motivation degree label ty2 and the steering acceleration degree label ty3.

4. The method for identifying the turning curvature of a tracked vehicle based on machine learning according to claim 3, characterized in that: The calculation formula of the particle fitness is: Among them, f i is the fitness of the i-th particle; m is the number of clusters set for initialization; C i 、C j are the i-th and j-th clusters respectively; avg(C) represents the average distance operation of the cluster; |C| represents the number of data in the current cluster; represents the center of cluster i; |C i | represents the number of data in cluster i; dis(x, y) represents the Euclidean distance, and j is a number from 1 to m that is not equal to i.

5. The method for identifying turning curvature of a tracked vehicle based on machine learning according to claim 1, characterized in that: The specific steps of training the offline regression model include: Using the three cluster labels combined with the feature vector set τ1, a training set τ6 is obtained as the input sample of the offline regression model of the slip rates on both sides, and the historical slip rate set τ2 is used as the corresponding true value output; Using the DBSCAN clustering algorithm to divide the input samples into normal samples and abnormal samples; The sample weights are initialized based on the AdaBoost regression model, and the sample weights are updated by using a weight update strategy in combination with the abnormal samples to train the offline regression model.

6. The method for identifying turning curvature of a tracked vehicle based on machine learning according to claim 5, characterized in that: The expression of the offline regression model output is: Among them, s l 、s r are the estimated values ​​of left and right track slip rates, respectively; Respectively represent the learners for estimating the left and right track slip rates; They represent the weight coefficients of the left and right track slip rate estimation learners respectively; m represents the number of iterations.

7. The method for identifying turning curvature of a tracked vehicle based on machine learning according to claim 5, characterized in that: The subset expression of the training set τ6 is: in, is the i-th subset of the training set τ6; v nl and v nr are the left and right track winding speeds respectively; M l and M r are the left and right track driving torques respectively; n l and n r are the speeds of the left and right driving wheels respectively; ω yaw is the yaw angular velocity; a1 is the longitudinal acceleration; a2 is the lateral acceleration; the superscript i represents the i-th sampling result.

8. The method for identifying turning curvature of a tracked vehicle based on machine learning according to claim 1, characterized in that: The specific steps of the online identification process include: Extracting real-time feature vectors using real-time collected tracked vehicle driving data; Inputting the real-time feature vector into the trained offline clustering model for clustering, assigning labels to the data points of the clustering results, and combining the feature vector to form the input vector of the offline regression model; The input vector is input into the trained offline regression model to obtain a real-time estimated value of the slip rate on both sides of the tracked vehicle.

9. The method for identifying turning curvature of a tracked vehicle based on machine learning according to any one of claims 1 to 8, characterized in that: The real-time estimated value of the steering curvature is obtained based on the following formula: Among them, ρ i is the steering curvature of the i-th sampling result; ω yaw is the yaw angular velocity; v i is the vehicle speed of the i-th sampling result; v nl and v nr are the left and right track winding speeds respectively; s l 、s r are the estimated values ​​of the left and right track slip rates, respectively; B is the center distance of the tracks on both sides; the superscript i represents the i-th sampling result.

Images