Automatic tracking control method for engineering vehicle

Abstract

The invention discloses an automatic tracking control method for an engineering vehicle, which relates to the field of engineering vehicle control, and comprises the following steps: collecting real-time data of the engineering vehicle, and constructing an engineering vehicle operation characteristic model by using a deep learning algorithm; inputting the real-time data into the engineering vehicle operation characteristic model, outputting a dynamic behavior index, and carrying out segmentation processing on a driving path of the engineering vehicle; based on the segmentation processing result, the attitude angle and the road condition of the engineering vehicle are calculated through multi-sensor data fusion, and an engineering vehicle track prediction model is established; and according to the engineering vehicle trajectory prediction model, predicting and planning the driving trajectory of the engineering vehicle, and performing cooperative control on an engineering vehicle system through a vehicle-mounted controller to complete automatic tracking control. According to the invention, the precision and reliability of automatic control are improved, and the environment adaptability of the system under complex working conditions is enhanced.

Description

Technical Field

[0001] The invention relates to the field of engineering vehicle control, in particular to an automatic tracking control method for an engineering vehicle. Background Art

[0002] Traditional engineering vehicle control systems mainly rely on manual operation, which is easily affected by subjective factors such as driver experience and fatigue under complex working conditions, making it difficult to ensure operating efficiency and safety. At present, domestic and foreign scholars have conducted extensive research on engineering vehicle automatic control technology and proposed a variety of automatic tracking control schemes based on visual navigation, lidar navigation, etc. However, these schemes still have problems such as insufficient perception accuracy, poor environmental adaptability, and single control strategy in practical applications. Especially under complex road conditions and severe weather conditions, existing technologies are difficult to accurately perceive the operating status and surrounding environment information of engineering vehicles, and cannot achieve stable and reliable automatic tracking control.

[0003] With the rise of deep learning technology, intelligent control methods based on deep neural networks have shown good development prospects. However, most of the existing deep learning control methods are designed for ordinary vehicles and do not fully consider the particularities of engineering vehicles, such as large changes in body posture, complex road conditions, and dynamic changes in load. At the same time, existing technologies often use a single sensor data source for control decisions and lack effective fusion of multi-source data, resulting in insufficient system robustness and reliability. In addition, traditional trajectory planning algorithms fail to make full use of historical data and environmental information, making it difficult to accurately predict and optimize the driving trajectory of engineering vehicles.

[0004] The existing automatic control technology for engineering vehicles mainly has technical problems such as limited perception ability, poor environmental adaptability, and single control strategy. The present invention proposes an automatic tracking control method for engineering vehicles, which builds an operation feature model through a deep learning algorithm, combines multi-sensor data fusion technology to achieve accurate perception of the posture and road conditions of the engineering vehicle, and makes control decisions based on the trajectory prediction model, effectively solving the problem of insufficient control accuracy and reliability of the existing technology under complex working conditions. Summary of the invention

[0005] In view of the fact that the existing automatic tracking control system for engineering vehicles has the problems of insufficient perception accuracy, poor environmental adaptability and single control strategy under complex working conditions, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to provide a method that can accurately sense the operating status of an engineering vehicle and adapt to complex road conditions and environments, and achieve stable and reliable automatic tracking control.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In the first aspect, an embodiment of the present invention provides an automatic tracking control method for an engineering vehicle, which includes collecting real-time data of the engineering vehicle and building an engineering vehicle operation characteristic model using a deep learning algorithm; inputting the real-time data into the engineering vehicle operation characteristic model, outputting dynamic behavior indicators, and segmenting the driving path of the engineering vehicle; based on the segmentation processing results, calculating the posture angle and road conditions of the engineering vehicle through multi-sensor data fusion, and establishing an engineering vehicle trajectory prediction model; predicting and planning the driving trajectory of the engineering vehicle according to the engineering vehicle trajectory prediction model, and collaboratively controlling the engineering vehicle system through the on-board controller to complete automatic tracking control.

[0009] As a preferred solution of the automatic tracking control method for engineering vehicles described in the present invention, the engineering vehicle system includes an engineering vehicle steering system, a braking system and a power system; the engineering vehicle driving trajectory is predicted and planned according to the engineering vehicle trajectory prediction model, and the engineering vehicle system is coordinated controlled by the vehicle-mounted controller to complete the automatic tracking control, including: according to the predicted trajectory data output by the engineering vehicle trajectory prediction model, the optimal driving trajectory of the engineering vehicle is calculated by using a recursive least squares algorithm; according to the optimal driving trajectory, a steering angle instruction, an acceleration instruction and a braking instruction are generated; the steering angle instruction is sent to the electric steering system through the vehicle-mounted controller to perform steering adjustment, and the acceleration instruction and the braking instruction are sent to the power system and the braking system respectively for power output adjustment and braking force adjustment; at the same time, real-time response data of the engineering vehicle system is collected and executed, and the real-time response data and the optimal driving trajectory are subjected to deviation analysis; when the deviation is less than or equal to the second preset threshold value, the current control instruction is kept unchanged and the automatic tracking control is continued; when the deviation is greater than the second preset threshold value, the steering angle instruction, the acceleration instruction and the braking instruction are regenerated according to the deviation until the automatic tracking control of the engineering vehicle is completed.

[0010] As a preferred solution of the automatic tracking control method for engineering vehicles of the present invention, the specific formula of the optimal driving trajectory is as follows:

[0011]

[0012] Among them, T opt is the optimal driving trajectory value, x i is the current position coordinate, x p (i) is the predicted trajectory coordinate, n is the prediction time domain length, λ is the forgetting factor, v is the current vehicle speed, μ is the smoothing factor, δ is the trajectory curvature, and σ is the curvature standard deviation threshold.

[0013] As a preferred solution of the automatic tracking control method for engineering vehicles described in the present invention, the engineering vehicle trajectory prediction model is constructed by using a Kalman filter algorithm to perform fusion operations on real-time data based on the results of segmentation processing to obtain three-dimensional posture angle data of the engineering vehicle; at the same time, the road image data obtained by the camera array is input into a pre-trained semantic segmentation network to extract road texture features, slope features and slippery degree features to form road condition data; the three-dimensional posture angle data and road condition data are input into a long short-term memory network to establish a trajectory prediction model for the engineering vehicle.

[0014] As a preferred solution of the automatic tracking control method for engineering vehicles described in the present invention, the method of segmented processing is as follows: real-time data is input into an engineering vehicle operation characteristic model, wherein the engineering vehicle operation characteristic model includes a distance prediction module, a posture evaluation module and an environment perception module; the distance prediction module is used to calculate the safety distance parameters between the engineering vehicle and surrounding environmental obstacles; the posture evaluation module is used to analyze the pitch angle parameters and roll angle parameters of the engineering vehicle; the environment perception module is used to identify the road surface type parameters and the road condition complexity; the safety distance parameters, pitch angle parameters, roll angle parameters, road surface type parameters and road condition complexity are combined to form a dynamic behavior index; the driving path of the engineering vehicle is divided according to the dynamic behavior index, and when the road condition complexity is greater than a first preset threshold, the corresponding section is divided into a complex section, and the tracking control parameters are dynamically adjusted, and multi-sensor data fusion calculation is started to obtain posture angle data and road condition data; when the road condition complexity is less than or equal to the first preset threshold, the corresponding section is divided into a standard section, and conventional tracking control is performed using preset tracking control parameters.

[0015] As a preferred solution of the automatic tracking control method for engineering vehicles of the present invention, the specific formula of the dynamic behavior index is as follows:

[0016]

[0017] Among them, DBI is the dynamic behavior indicator output value, d s is the safety distance parameter, d max is the preset maximum safety distance threshold, θ p is the pitch angle parameter, θ r is the roll angle parameter, θ th is the angle threshold, R is the road type parameter, C is the road condition complexity, S is the environmental state characteristic value, and α, β and γ are adjustment coefficients.

[0018] As a preferred solution of the automatic tracking control method for engineering vehicles described in the present invention, the real-time data includes driving trajectory data, vehicle status data and surrounding environment image data; the method for establishing the engineering vehicle operation characteristic model is to collect real-time data obtained by the camera array, GPS positioning module, wheel speed sensor and inertial measurement unit IMU carried by the engineering vehicle; pre-process the real-time data, and input the pre-processed real-time data into a pre-trained deep convolutional neural network to extract the operation characteristic information of the engineering vehicle during operation; construct an engineering vehicle operation characteristic model according to the operation characteristic information, wherein the engineering vehicle operation characteristic model includes using a graph neural network GNN structure to represent the interaction between the operation status of the engineering vehicle and the environment, and optimizing the model parameters through a comparative learning method.

[0019] In the second aspect, an embodiment of the present invention provides an automatic tracking and control system for an engineering vehicle, which includes: an acquisition module, used to collect real-time data of the engineering vehicle, and use a deep learning algorithm to build an engineering vehicle operation characteristic model; a segmentation processing module, used to input the real-time data into the engineering vehicle operation characteristic model, output dynamic behavior indicators, and perform segmentation processing on the engineering vehicle's driving path; an establishment module, based on the segmentation processing result, calculates the posture angle and road condition of the engineering vehicle through multi-sensor data fusion, and establishes an engineering vehicle trajectory prediction model; a collaborative control module, used to predict and plan the engineering vehicle's driving trajectory according to the engineering vehicle trajectory prediction model, and collaboratively control the engineering vehicle system through the on-board controller to complete automatic tracking control.

[0020] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the automatic tracking control method for an engineering vehicle as described in the first aspect of the present invention are implemented.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the automatic tracking control method for an engineering vehicle as described in the first aspect of the present invention are implemented.

[0022] The beneficial effects of the present invention are as follows: feature extraction is achieved by constructing an operation feature model through a deep learning algorithm, the perception accuracy of the posture and road conditions of the engineering vehicle is improved by combining multi-sensor data fusion technology, the segmented processing strategy is used to reduce the complexity of data processing and optimize the calculation efficiency, and the future motion state of the vehicle is accurately predicted based on the trajectory prediction model. Finally, the optimized coordination of steering, acceleration, braking and other actuators is ensured through a collaborative control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0024] Figure 1 This is a flow chart of the automatic tracking control method for an engineering vehicle in Example 1. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0027] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0028] Example 1

[0029] Reference Figure 1 , which is the first embodiment of the present invention, provides an automatic tracking control method for an engineering vehicle, comprising:

[0030] S1: Collect real-time data of engineering vehicles and use deep learning algorithms to build an engineering vehicle operation characteristic model.

[0031] Specifically, real-time data is collected from the camera array, GPS positioning module, wheel speed sensor and inertial measurement unit IMU carried by the engineering vehicle.

[0032] It should be noted that real-time data includes driving trajectory data, vehicle status data and surrounding environment image data. The camera array is arranged in a surround view mode, and a multi-view image fusion algorithm is used to generate 360-degree environmental image data around the engineering vehicle; the GPS positioning module and wheel speed sensor cooperate to measure the geographic coordinates, driving speed and driving trajectory data of the engineering vehicle; and the inertial measurement unit IMU records the vehicle status data of the engineering vehicle's attitude angle, acceleration and angular velocity.

[0033] Furthermore, the real-time data is preprocessed, and the preprocessed real-time data is input into a pre-trained deep convolutional neural network to extract the operating characteristic information of the engineering vehicle during operation; an engineering vehicle operating characteristic model is constructed based on the operating characteristic information, wherein the engineering vehicle operating characteristic model uses a graph neural network (GNN) structure to represent the interactive relationship between the operating status of the engineering vehicle and the environment, and optimizes the model parameters through a comparative learning method.

[0034] S2: Input the real-time data into the engineering vehicle operation characteristic model, output dynamic behavior indicators, and perform segmented processing on the engineering vehicle driving path.

[0035] Specifically, the segmented processing method is to input the real-time data into the engineering vehicle operation characteristic model, wherein the engineering vehicle operation characteristic model includes a distance prediction module, a posture evaluation module and an environment perception module.

[0036] It should be noted that the distance prediction module calculates the safe distance parameters between the engineering vehicle and the surrounding environmental obstacles; the posture assessment module analyzes the pitch angle parameters and roll angle parameters of the engineering vehicle; and the environmental perception module identifies the road type parameters and the complexity of the road conditions.

[0037] Furthermore, the safety distance parameter, pitch angle parameter, roll angle parameter, road surface type parameter and road condition complexity are combined to form a dynamic behavior index. The specific formula is as follows:

[0038]

[0039] Among them, DBI is the dynamic behavior indicator output value, d s is the safety distance parameter, d max is the preset maximum safety distance threshold, θ p is the pitch angle parameter, θ r is the roll angle parameter, θ th is the angle threshold, R is the road type parameter, C is the road condition complexity, S is the environmental state characteristic value, α, β and γ are adjustment coefficients and satisfy α+β+γ=1.

[0040] Furthermore, the driving path of the engineering vehicle is divided according to the dynamic behavior indicators. When the complexity of the road condition is greater than a first preset threshold, the corresponding section is divided into a complex section, and the tracking control parameters are dynamically adjusted, and the multi-sensor data fusion calculation is started to obtain attitude angle data and road condition data; when the complexity of the road condition is less than or equal to the first preset threshold, the corresponding section is divided into a standard section, and the preset tracking control parameters are used for conventional tracking control.

[0041] It should be noted that the first preset threshold is a boundary value set based on the road condition complexity distribution statistics in the historical operation data of the engineering vehicle.

[0042] S3: Based on the segment processing results, the posture angle and road conditions of the engineering vehicle are calculated through multi-sensor data fusion, and a trajectory prediction model for the engineering vehicle is established.

[0043] Specifically, the construction method of the engineering vehicle trajectory prediction model is to use the Kalman filter algorithm to fuse the real-time data based on the results of segmentation processing to obtain the three-dimensional posture angle data of the engineering vehicle; at the same time, the road image data obtained by the camera array is input into the pre-trained semantic segmentation network to extract the road texture features, slope features and wetness features to form road condition data.

[0044] Furthermore, the three-dimensional posture angle data and road condition data are input into a long short-term memory network to establish a construction vehicle trajectory prediction model.

[0045] S4: Predict and plan the driving trajectory of the engineering vehicle based on the engineering vehicle trajectory prediction model, and coordinately control the steering system, braking system and power system of the engineering vehicle through the on-board controller to complete automatic tracking control.

[0046] Specifically, based on the predicted trajectory data output by the engineering vehicle trajectory prediction model, a recursive least squares algorithm is used to calculate the optimal driving trajectory of the engineering vehicle; and a steering angle instruction, an acceleration instruction and a braking instruction are generated according to the optimal driving trajectory.

[0047] Furthermore, the specific formula of the optimal driving trajectory is as follows:

[0048]

[0049] Among them, T opt is the optimal driving trajectory value, x i is the current position coordinate, x p (i) is the predicted trajectory coordinate, n is the prediction time domain length, λ is the forgetting factor, v is the current vehicle speed, μ is the smoothing factor, δ is the trajectory curvature, and σ is the curvature standard deviation threshold.

[0050] It should be noted that the engineering vehicle system includes the engineering vehicle steering system, braking system and power system.

[0051] Furthermore, the steering angle command is sent to the electric steering system through the vehicle controller to perform steering adjustment, and the acceleration command and the braking command are sent to the power system and the braking system respectively to perform power output adjustment and braking force adjustment.

[0052] Specifically, real-time response data of the engineering vehicle system is collected and executed at the same time, and deviation analysis is performed between the real-time response data and the optimal driving trajectory.

[0053] Furthermore, when the deviation is less than or equal to the second preset threshold, the current control instruction is kept unchanged and the automatic tracking control is continued; wherein, according to the optimal driving trajectory value T opt Comparison with trajectory threshold: If the optimal driving trajectory value T opt ≤1, it indicates that the operation trajectory of the engineering vehicle is completely in line with expectations and the current control strategy continues to be executed; if 1<optimal driving trajectory value T opt ≤3, the trajectory deviation is within the acceptable range, the system maintains the current control parameters and strengthens monitoring.

[0054] Furthermore, when the deviation is greater than the second preset threshold, the steering angle command, acceleration command and braking command are regenerated according to the deviation until the automatic tracking control of the engineering vehicle is completed. The steering angle command is dynamically adjusted according to the lateral deviation, and the expected steering angle is calculated using the preview point tracking algorithm; the acceleration command is based on the longitudinal deviation and speed error, and the engineering vehicle trajectory prediction model predictive control method is used to optimize the acceleration output; the braking command analyzes the deviation between the current speed and the expected speed, and dynamically adjusts the braking torque in combination with the road conditions.

[0055] It should be noted that the second preset threshold is based on the optimal driving trajectory value T opt The indicator is the evaluation result after comprehensively considering the position deviation, speed influence and trajectory smoothness.

[0056] Furthermore, the present embodiment also provides an automatic tracking and control system for engineering vehicles, including: an acquisition module, used to collect real-time data of the engineering vehicle, and use a deep learning algorithm to build an engineering vehicle operation characteristic model; a segmentation processing module, used to input the real-time data into the engineering vehicle operation characteristic model, output dynamic behavior indicators, and perform segmentation processing on the engineering vehicle's driving path; an establishment module, based on the segmentation processing result, calculates the posture angle and road condition of the engineering vehicle through multi-sensor data fusion, and establishes an engineering vehicle trajectory prediction model; a collaborative control module, used to predict and plan the engineering vehicle's driving trajectory according to the engineering vehicle trajectory prediction model, and collaboratively control the engineering vehicle system through the on-board controller to complete automatic tracking control.

[0057] This embodiment also provides a computer device, which is suitable for the automatic tracking control method for engineering vehicles, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the automatic tracking control method for engineering vehicles proposed in the above embodiment.

[0058] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0059] In summary, the present invention constructs an operation feature model through a deep learning algorithm to realize feature extraction, combines multi-sensor data fusion technology to improve the perception accuracy of the engineering vehicle posture and road conditions, adopts a segmented processing strategy to reduce data processing complexity and optimize calculation efficiency, and realizes accurate prediction of the vehicle's future motion state based on the trajectory prediction model. Finally, the optimized coordination of steering, acceleration, braking and other actuators is ensured through a collaborative control method.

[0060] Example 2

[0061] Referring to Table 1, which is a second embodiment of the present invention, this embodiment provides an automatic tracking control method for an engineering vehicle. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0062] Specifically, a certain model of mining dump truck was selected as the test object. The vehicle was equipped with Nvidia Xavier NX edge computing platform, 8-channel high-definition camera array, RTK-GPS positioning module, 6-axis IMU sensor and distributed wheel speed sensor network. The test site includes two road conditions: standard road and complex terrain. The complex terrain includes 15° to 30° slope area, muddy road section and sharp turn area. The data set of the vehicle running under different working conditions was collected, including 100 hours of driving trajectory data, vehicle status data and environmental image data. Using the PyTorch deep learning framework, a deep convolutional neural network based on the ResNet-50 backbone network was constructed, and pre-trained by transfer learning method to extract the key operation characteristics of the engineering vehicle. On this basis, a GNN structure with 6 layers of graph convolution layers was designed to model the interactive relationship between vehicle status and environment. The model parameters were optimized by contrastive learning method to obtain the operation characteristic model of the engineering vehicle.

[0063] Furthermore, after the real-time data is input into the running feature model, the distance prediction module calculates the safe distance in real time based on the lidar point cloud data, the posture assessment module uses the IMU data to analyze the body posture, and the environmental perception module identifies the road conditions through the semantic segmentation network. According to the output dynamic behavior indicators, the system adaptively divides the road section type. For complex sections, the improved Kalman filter algorithm is used to fuse multi-source sensor data to achieve centimeter-level positioning accuracy; at the same time, the road image is input into the semantic segmentation network based on the DeepLab v3+ architecture to extract road surface features. The fused posture data and road condition data are input into the bidirectional LSTM network to build a trajectory prediction model.

[0064] Furthermore, based on the trajectory data output by the prediction model, an improved recursive least squares algorithm is used to calculate the optimal driving trajectory, and control instructions are generated through the model predictive control (MPC) method. The on-board controller uses the CAN bus to send the control instructions to the electric steering system, power system and braking system for execution. At the same time, the system collects execution data in real time and performs deviation analysis. When the deviation exceeds the second preset threshold, the online optimization update of the control instructions is triggered.

[0065] Specifically, as shown in Table 1, under standard road conditions, the trajectory tracking error of the method of the present invention is 0.25m, which is 40.5% lower than the 0.42m of the traditional method; the attitude estimation accuracy is improved to 0.6°, which is 50% higher than the 1.2° of the traditional method; the system response delay is reduced from 145ms to 85ms, and the processing efficiency is improved by 41.4%. In terms of environmental perception, the road condition recognition accuracy rate reaches 94.2%, which is 7.7 percentage points higher than the traditional method; the control stability reaches 95.8%, which is 6.6 percentage points higher than the 89.2% of the traditional method. At the same time, the energy consumption index is reduced to 2.3kWh / km, which saves 14.8% of energy consumption compared with the traditional method. It is particularly noteworthy that the safety distance accuracy is improved from 0.85m to 0.45m, an increase of 47.1%; the dynamic response time is shortened from 1.2s to 0.6s, and the reaction speed is doubled.

[0066] Table 1. Comparison between the method of the present invention and the traditional method

[0067]

[0068] Furthermore, under complex terrain conditions, the advantages of the method of the present invention are more prominent. The trajectory tracking error is reduced from 1.65m to 0.68m, with an improvement of 58.8%; the attitude estimation accuracy is increased from 2.8° to 1.1°, and the accuracy is improved by 60.7%; the system response delay is reduced from 175ms to 95ms, and the real-time performance is improved by 45.7%. The road condition recognition accuracy is increased from 73.5% to 91.8%, an increase of 18.3 percentage points, indicating that the method of the present invention has stronger environmental perception ability in complex environments; the control stability is increased from 76.8% to 93.5%, an increase of 16.7 percentage points, ensuring the smooth operation of the vehicle under complex terrain. The energy consumption index is reduced from 3.8kWh / km to 2.9kWh / km, and the energy saving effect reaches 23.7%. In terms of safety performance, the safety distance accuracy is increased from 1.55m to 0.72m, an increase of 53.5%; the dynamic response time is shortened from 1.8s to 0.8s, an increase of 55.6%.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automatic tracking control method for an engineering vehicle, characterized in that: include, Collect real-time data of engineering vehicles and use deep learning algorithms to build engineering vehicle operation feature models; Input the real-time data into the engineering vehicle operation characteristic model, output dynamic behavior indicators, and perform segmented processing on the engineering vehicle driving path; Based on the segment processing results, the posture angle and road conditions of the engineering vehicle are calculated through multi-sensor data fusion, and the engineering vehicle trajectory prediction model is established; The driving trajectory of the engineering vehicle is predicted and planned according to the engineering vehicle trajectory prediction model, and the engineering vehicle system is cooperatively controlled through the on-board controller to complete automatic tracking control.

2. The automatic tracking control method for an engineering vehicle according to claim 1, characterized in that: The engineering vehicle system includes an engineering vehicle steering system, a braking system and a power system; the driving trajectory of the engineering vehicle is predicted and planned according to the engineering vehicle trajectory prediction model, and the engineering vehicle system is collaboratively controlled through the on-board controller to complete automatic tracking control, including: According to the predicted trajectory data output by the engineering vehicle trajectory prediction model, the optimal driving trajectory of the engineering vehicle is calculated using a recursive least squares algorithm; generating a steering angle command, an acceleration command and a braking command according to the optimal driving trajectory; The steering angle command is sent to the electric steering system through the vehicle controller to perform steering adjustment, and the acceleration command and the braking command are sent to the power system and the braking system respectively to perform power output adjustment and braking force adjustment; At the same time, real-time response data of the engineering vehicle system is collected and executed, and deviation analysis is performed between the real-time response data and the optimal driving trajectory; When the deviation is less than or equal to the second preset threshold, the current control instruction is kept unchanged and the automatic tracking control is continued; When the deviation is greater than a second preset threshold, the steering angle command, the acceleration command and the braking command are regenerated according to the deviation until the automatic tracking control of the engineering vehicle is completed.

3. The automatic tracking control method for an engineering vehicle according to claim 2, characterized in that: The specific formula of the optimal driving trajectory is as follows: Among them, T opt is the optimal driving trajectory value, x i is the current position coordinate, x p (i) is the predicted trajectory coordinate, n is the prediction time domain length, λ is the forgetting factor, v is the current vehicle speed, μ is the smoothing factor, δ is the trajectory curvature, and σ is the curvature standard deviation threshold.

4. The automatic tracking control method for an engineering vehicle according to claim 2, characterized in that: The construction method of the engineering vehicle trajectory prediction model is as follows: Based on the results of segmented processing, the Kalman filter algorithm is used to perform fusion operations on real-time data to obtain the three-dimensional attitude angle data of the engineering vehicle; At the same time, the road surface image data acquired by the camera array is input into the pre-trained semantic segmentation network to extract the road surface texture features, slope features and wetness features to form road surface condition data; The three-dimensional posture angle data and road condition data are input into a long short-term memory network to establish a construction vehicle trajectory prediction model.

5. The automatic tracking control method for an engineering vehicle according to claim 4, characterized in that: The segmentation processing method is: Input the real-time data into the engineering vehicle operation characteristic model, wherein the engineering vehicle operation characteristic model includes a distance prediction module, a posture evaluation module and an environment perception module; the distance prediction module is used to calculate the safe distance parameters between the engineering vehicle and the surrounding environmental obstacles; the posture evaluation module is used to analyze the pitch angle parameters and roll angle parameters of the engineering vehicle; the environment perception module is used to identify the road surface type parameters and the complexity of the road conditions; The safety distance parameter, the pitch angle parameter, the roll angle parameter, the road surface type parameter and the road condition complexity are combined to form a dynamic behavior index; The driving path of the engineering vehicle is divided according to the dynamic behavior index. When the complexity of the road condition is greater than a first preset threshold, the corresponding road section is divided into a complex road section, and the tracking control parameters are dynamically adjusted, and multi-sensor data fusion calculation is started to obtain attitude angle data and road condition data; When the road condition complexity is less than or equal to the first preset threshold, the corresponding road section is divided into a standard road section, and conventional tracking control is performed using preset tracking control parameters.

6. The automatic tracking control method for an engineering vehicle according to claim 5, characterized in that: The specific formula of the dynamic behavior indicator is as follows: Among them, DBI is the output value of dynamic behavior index, d s is the safety distance parameter, d max is the preset maximum safety distance threshold, θ p is the pitch angle parameter, θ r is the roll angle parameter, θ th is the angle threshold, R is the road type parameter, C is the road condition complexity, S is the environmental state characteristic value, and α, β and γ are adjustment coefficients.

7. The automatic tracking control method for an engineering vehicle according to claim 5, characterized in that: The real-time data includes driving trajectory data, vehicle status data and surrounding environment image data; the method for establishing the engineering vehicle operation characteristic model is: Collect real-time data from the camera array, GPS positioning module, wheel speed sensor and inertial measurement unit (IMU) on the engineering vehicle; Preprocessing the real-time data, and inputting the preprocessed real-time data into a pre-trained deep convolutional neural network to extract operation characteristic information during the operation of the engineering vehicle; An engineering vehicle operation characteristic model is constructed based on the operation characteristic information, wherein the engineering vehicle operation characteristic model includes using a graph neural network (GNN) structure to represent the interaction between the operation status of the engineering vehicle and the environment, and optimizing model parameters through a comparative learning method.

8. An automatic tracking control system for an engineering vehicle, based on the automatic tracking control method for an engineering vehicle according to any one of claims 1 to 7, characterized in that: include, The acquisition module is used to collect real-time data of engineering vehicles and build an engineering vehicle operation feature model using a deep learning algorithm; A segmentation processing module, used to input the real-time data into the engineering vehicle operation characteristic model, output dynamic behavior indicators, and perform segmentation processing on the engineering vehicle driving path; Establish a module, based on the segment processing results, calculate the posture angle and road conditions of the engineering vehicle through multi-sensor data fusion, and establish an engineering vehicle trajectory prediction model; The collaborative control module is used to predict and plan the driving trajectory of the engineering vehicle according to the engineering vehicle trajectory prediction model, and to collaboratively control the engineering vehicle system through the on-board controller to complete automatic tracking control.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automatic tracking control method for an engineering vehicle according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automatic tracking control method for an engineering vehicle according to any one of claims 1 to 7 are implemented.

Images