Vehicle control parameter calibration method and device, vehicle and storage medium

Abstract

The invention discloses a vehicle control parameter calibration method and device, a vehicle and a storage medium. The method comprises the steps that in the process of controlling vehicle driving, driving data of a vehicle are monitored, and a first driving data set is obtained; performing state identification on the vehicle based on the plurality of parameter adjustment rules and the first driving data set, and determining a target parameter adjustment rule matched with the driving state of the vehicle; and the current control parameters of the vehicle are adjusted based on the target parameter adjustment rule, and target control parameters in the vehicle driving process are obtained. According to the invention, the technical problems of high cost and low accuracy of vehicle control parameter calibration in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control and data calibration, and in particular to a method, device, vehicle and storage medium for calibrating vehicle control parameters. Background Art

[0002] With the rapid development of the field of autonomous driving, the accuracy and adaptability of vehicle control algorithms have become the key to technological progress. In order to ensure stable and reliable operation of the vehicle in different working conditions and different natural environments, different control parameters need to be adapted.

[0003] In the related technology, the adaptation of different control parameters is usually done by experienced engineers who manually debug the parameters, which consumes a lot of human resources and has a high adaptation time cost. In addition, due to the intervention of human factors, the calibration accuracy of the vehicle control parameters may be low, thereby affecting the performance and reliability of vehicle driving.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, vehicle and storage medium for calibrating vehicle control parameters, so as to at least solve the technical problems of high cost and low accuracy of vehicle control parameter calibration in related technologies.

[0006] According to one aspect of an embodiment of the present invention, a method for calibrating vehicle control parameters is provided, comprising: during the process of controlling vehicle driving, monitoring the vehicle's driving data to obtain a first driving data set; identifying the vehicle's state based on multiple parameter adjustment rules and the first driving data set, and determining a target parameter adjustment rule that matches the vehicle's driving state; and adjusting the vehicle's current control parameters based on the target parameter adjustment rule to obtain the target control parameters during vehicle driving.

[0007] According to another aspect of an embodiment of the present invention, a device for calibrating vehicle control parameters is also provided, including: a monitoring module, used to monitor the vehicle's driving data during the process of controlling the vehicle's driving, and obtain a first driving data set; a state identification module, used to identify the vehicle's state based on multiple parameter adjustment rules and the first driving data set, and determine a target parameter adjustment rule that matches the vehicle's driving state; an adjustment module, used to adjust the vehicle's current control parameters based on the target parameter adjustment rules, and obtain the target control parameters during the vehicle's driving process.

[0008] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0009] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0010] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0011] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0012] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0013] In an embodiment of the present invention, in the process of controlling the driving of a vehicle, the driving data of the vehicle is monitored to obtain a first driving data set; the state of the vehicle is identified based on multiple parameter adjustment rules and the first driving data set, and a target parameter adjustment rule matching the driving state of the vehicle is determined; the current control parameters of the vehicle are adjusted based on the target parameter adjustment rule to obtain the target control parameters during the driving process of the vehicle. It is easy to notice that the control parameters of the vehicle are adjusted in real time by identifying the state of the vehicle during the driving process of the vehicle, without the need to adjust the control parameters by analyzing the driving data after repeatedly controlling the driving of the vehicle. And the current control parameters of the vehicle can be adjusted by the target parameter adjustment rule corresponding to the current driving state of the vehicle, so that the vehicle can use the control parameters matching the current state to drive under different working conditions, thereby achieving the technical effect of accurately calibrating the vehicle control parameters, thereby solving the technical problems of high cost and low accuracy of vehicle control parameter calibration in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0015] Figure 1 is a flow chart of a method for calibrating vehicle control parameters according to an embodiment of the present invention;

[0016] Figure 2is a schematic diagram of an optional vehicle control parameter calibration system according to an embodiment of the present invention;

[0017] Figure 3 is an optional curve diagram of vehicle speed changing with time according to an embodiment of the present invention;

[0018] Figure 4 is an optional curve diagram of vehicle speed changing with time according to an embodiment of the present invention;

[0019] Figure 5 is an optional curve diagram of vehicle speed changing with time according to an embodiment of the present invention;

[0020] Figure 6 is an optional curve diagram of vehicle speed changing with time according to an embodiment of the present invention;

[0021] Figure 7 is a schematic diagram of a vehicle control parameter calibration device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a method for calibrating vehicle control parameters is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for calibrating vehicle control parameters according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102: During the process of controlling the driving of the vehicle, the driving data of the vehicle is monitored to obtain a first driving data set.

[0027] The above-mentioned vehicle can be a vehicle traveling under different working conditions, for example, the vehicle can be a plateau type mine car, or a rain and snow weather adaptation type mine car; the vehicle can also be a vehicle carrying different items, for example, the vehicle can be a coal mine car, or a metal mine car, and the vehicle is not limited here and can be determined as needed. The vehicle can operate based on different control parameters under different working conditions.

[0028] Different working conditions, such as mining environment, load conditions, driving speed, road slope, slippery or soft ground, etc., will affect the vehicle's power demand, stability control and response characteristics. For example, when heavily loaded or uphill, the vehicle may need more power to maintain speed, while in rainy and snowy weather, more emphasis is placed on stability control to ensure safe driving. In addition, under the same working conditions, the performance indicators that the vehicle needs to achieve will also be different. For example, when driving at a steady speed, the goal of adjusting the control parameters is to minimize speed fluctuations; while under acceleration and deceleration conditions, the goal may be to reduce overshoot and steady-state errors. By configuring the control parameters for the vehicle, the vehicle can operate stably under the corresponding working conditions.

[0029] The driving data of the above-mentioned vehicle can be used to characterize the performance parameters of the vehicle during driving. Through the driving data, vehicle performance, fault diagnosis, safety monitoring and vehicle control can be analyzed. Driving data may include but is not limited to: position data, speed data, corner data, engine data, battery data, environmental data. The content of driving data is not limited here and can be determined as needed. These data can be collected in real time by sensors and controllers on the vehicle, and transmitted to the central processor or cloud server through the vehicle network system for analysis and processing.

[0030] The first driving data set mentioned above may be a data set related to the vehicle state. The first driving data set may include data related to the vehicle driving state, for example, the vehicle speed, target speed, actual acceleration, target acceleration, etc. The content of the first driving data set is not limited here and can be determined as needed. Through the first driving data set, the driving state of the vehicle can be judged, so as to accurately adjust the control parameters.

[0031] In an optional embodiment, the driving state of the vehicle can be monitored in real time through a sensor system. The sensor system may include, but is not limited to, a global positioning system, a wheel speed sensor, an accelerometer, a gyroscope, a camera, a radar sensor, etc. The sensor system is not limited here and can be determined as needed. Through the sensor system, the position, speed, acceleration, posture, and surrounding environment information of the vehicle can be monitored to obtain the driving data of the vehicle, etc. Further, the driving data can be preprocessed or screened, for example, filtering, outlier removal, coordinate conversion, etc., to obtain a first driving data set.

[0032] In another optional embodiment, the vehicle's driving data can also be monitored through vehicle-to-everything (V2X) communication technology to obtain a first driving data set. V2X can be a vehicle-to-vehicle or vehicle-to-infrastructure communication technology, which is not limited here and can be determined as needed. V2X communication technology can be used to exchange driving data with other vehicles or roadside equipment in real time. Then, a swarm intelligence algorithm, such as an ant colony algorithm or a particle swarm optimization algorithm, can be used to analyze the vehicle's driving data to obtain a first driving data set.

[0033] Step S104: identifying the state of the vehicle based on the multiple parameter adjustment rules and the first driving data set, and determining a target parameter adjustment rule that matches the driving state of the vehicle.

[0034] The above-mentioned parameter adjustment rules can be rules for adjusting the control parameters of the vehicle. The vehicle may operate under a variety of complex working conditions, for example, from flat gravel aggregate mines to undulating metal mines, from dry plains to wet plateaus. Under different working conditions, the dynamic characteristics of the vehicle will be different. Therefore, multiple parameter adjustment rules can be formulated for different working conditions to ensure that the vehicle can have a stable control effect when facing a variety of working conditions. Multiple parameter adjustment rules can be determined by artificial experience or intelligent algorithms. The intelligent algorithm can be machine learning, and the intelligent algorithm can also be fuzzy logic. The intelligent algorithm is not limited here and can be determined as needed. The parameter adjustment rules can respond to changes in the vehicle's driving state in real time, and by accurately adjusting the control parameters, ensure that the vehicle can achieve relatively stable performance under various driving conditions. It is particularly suitable for autonomous driving vehicles to drive efficiently and safely under complex and changeable road conditions.

[0035] The above-mentioned state identification can be a process of identifying and judging the state of the vehicle. Based on the vehicle's driving data, it can be judged whether the current state of the vehicle meets the preset performance indicators, and the control parameters can be adjusted accordingly. The vehicle state may include but is not limited to the vehicle acceleration state, the vehicle deceleration state, the vehicle steady speed driving state, and the deviation between the vehicle parameters and the target parameters, etc. The vehicle state is not limited here and can be determined as needed. By monitoring the vehicle's driving data, the driving condition of the vehicle is identified, such as whether there is speed overshoot, steady-state speed fluctuation, large steady-state error of deceleration or deceleration overshoot, so as to adjust the vehicle control parameters under the condition.

[0036] The driving state of the vehicle described above can be used to characterize the driving condition of the vehicle under the working condition. The driving state of the vehicle can be used to determine the corresponding target parameter adjustment rule to adjust the control parameters of the vehicle in the driving state, thereby controlling the vehicle.

[0037] The above-mentioned target parameter adjustment rules may be rules for adjusting the control parameters of the vehicle under the current vehicle driving state. By adjusting the control parameters through the target parameter adjustment rules, the vehicle can maintain good driving performance under different working conditions, thereby improving overall operating efficiency and safety. For example, when driving at low speeds, if the speed overshoot is large, the target parameter adjustment rules may include reducing the integral term coefficient to reduce the overshoot. When driving at high speeds, if the vehicle speed fluctuates frequently, the target parameter adjustment rules may include reducing the proportional term coefficient to reduce the sensitivity of the proportional control and reduce speed fluctuations.

[0038] In an optional embodiment, the vehicle state can be identified using a recognition model. Specifically, the recognition model can be a convolutional neural network, a recurrent neural network, etc., and the recognition model is not limited here and can be determined as needed. The recognition model is trained and learned in advance on historical driving data and vehicle states, so that the vehicle state can be accurately identified. The first driving data set can be input into the recognition model to obtain a prediction result of the vehicle state. Then the current driving state of the vehicle is matched with a plurality of parameter adjustment rules to obtain a target parameter adjustment rule to adjust the vehicle control parameters of the current vehicle state. Optionally, the target parameter adjustment rule that matches the driving state of the vehicle can be determined by a preset matching rule. Alternatively, the similarity between the vehicle state corresponding to a plurality of parameter adjustment rules and the current vehicle driving state can be calculated by a similarity algorithm, so as to determine the target parameter adjustment rule that matches the driving state of the vehicle. Alternatively, the target parameter adjustment rule that matches the driving state of the vehicle can be determined by a professional.

[0039] In another optional embodiment, a machine learning model can be used to predict the optimal target parameter adjustment rule based on multiple parameter adjustment rules and the first driving data set. The machine learning model can be used for rule selection, and the machine learning model predicts the optimal parameter adjustment rule by learning the characteristics of the historical rule base and the characteristics of the historical driving data. The machine learning model can predict the target parameter adjustment rule that matches the driving state of the vehicle based on multiple parameter adjustment rules and the first driving data set. The machine learning model can be one of the following: a decision tree, a random forest, or a support vector machine, etc. The machine learning model is not limited here and can be determined as needed.

[0040] Step S106, adjusting the current control parameters of the vehicle based on the target parameter adjustment rule to obtain the target control parameters during the vehicle driving process.

[0041] The above-mentioned current control parameters can be a set of parameter setting values ​​used to control the driving state of the vehicle during the vehicle driving process. The current control parameters can be proportional term coefficients, integral term coefficients, differential term coefficients, filter parameters, gains, response time or steering control parameters, etc. The current control parameters are not limited here and can be determined as needed. Preferably, for longitudinal motion control, the current control parameters can be proportional term coefficients and integral term coefficients of a proportional integral (PI) controller, which control how the vehicle responds to the target values ​​of speed and acceleration. The proportional term coefficient affects the vehicle's immediate response to speed error. When there is a difference between the speed of the vehicle and the target speed, the larger the proportional term coefficient, the greater the control force of the vehicle's throttle or brake will immediately increase or decrease in an attempt to quickly correct the speed deviation. However, an excessively large proportional term coefficient may also cause system instability, resulting in speed overshoot or fluctuation. The role of the integral term coefficient is to eliminate steady-state errors. The size of the integral term coefficient affects the speed and degree of eliminating steady-state errors. A smaller integral term coefficient may cause a long-term steady-state error, while an excessively large integral term coefficient may prevent the system from quickly stabilizing when the target speed is reached, resulting in continuous adjustment and overshoot.

[0042] The output of a PI controller can be the sum of a proportional term and an integral term. The proportional term is proportional to the current error, while the integral term accumulates the integral of the error over time to eliminate steady-state errors in the vehicle control system.

[0043] The above-mentioned target control parameters can be a set of parameter setting values ​​that are expected to control the driving state of the vehicle during the driving process. The setting of the target control parameters is usually determined according to performance requirements, vehicle dynamic characteristics, and safety standards, such as reducing speed overshoot, reducing steady-state errors, improving response speed and stability, etc., to ensure that good control effects can be achieved under various working conditions. The target control parameters can be proportional term coefficients, integral term coefficients, differential term coefficients, filter parameters, gains, response time or steering control parameters, etc. The target control parameters are not limited here and can be determined as needed. Preferably, for longitudinal motion control, the target control parameters can be proportional term coefficients and integral term coefficients.

[0044] The above adjustment can be a process of adjusting the control parameters of the vehicle by adjusting the rules. Through the adjustment, it is helpful to improve the control performance of the vehicle in low-speed driving, acceleration and deceleration stages, reduce speed fluctuations, speed overshoot and deceleration errors, and ensure the safe, stable and efficient operation of the vehicle in a complex mining environment.

[0045] In an optional embodiment, the error value in the current control parameters of the vehicle can be determined according to the target parameter adjustment rule, and then based on the error value, the corresponding target control parameter in the target parameter adjustment rule is queried to control the driving of the vehicle. Optionally, the error value in the current control parameters of the vehicle can be manually determined. Alternatively, the error value in the current control parameters of the vehicle can be detected by an error detection model. Alternatively, the control parameters in the target parameter adjustment rule can be compared with the current control parameters of the vehicle to determine the error value. Then, the corresponding target control parameter in the target parameter adjustment rule can be queried through a decision tree. Alternatively, the corresponding target control parameter in the target parameter adjustment rule can be queried through a fuzzy rule. Alternatively, the corresponding target control parameter in the target parameter adjustment rule can also be queried through a rule engine component.

[0046] In another optional embodiment, the target control parameter can be predicted by a machine learning algorithm according to the target parameter adjustment rule and the current control parameter of the vehicle. Specifically, the machine learning algorithm can be used to predict the target control parameter. The machine learning algorithm is pre-trained and can predict the control parameter of the vehicle according to the target parameter adjustment rule and the current control parameter of the vehicle to obtain the target control parameter during the vehicle driving process. The machine learning algorithm can be one of the following: decision tree, random forest or support vector machine, etc. The machine learning algorithm is not limited here and can be determined as needed.

[0047] In an embodiment of the present invention, in the process of controlling the driving of a vehicle, the driving data of the vehicle is monitored to obtain a first driving data set; the state of the vehicle is identified based on multiple parameter adjustment rules and the first driving data set, and a target parameter adjustment rule matching the driving state of the vehicle is determined; the current control parameters of the vehicle are adjusted based on the target parameter adjustment rule to obtain the target control parameters during the driving process of the vehicle. It is easy to notice that the control parameters of the vehicle are adjusted in real time by identifying the state of the vehicle during the driving process of the vehicle, without the need to adjust the control parameters by analyzing the driving data after repeatedly controlling the driving of the vehicle. And the current control parameters of the vehicle can be adjusted by the target parameter adjustment rule corresponding to the current driving state of the vehicle, so that the vehicle can use the control parameters matching the current state to drive under different working conditions, thereby achieving the technical effect of accurately calibrating the vehicle control parameters, thereby solving the technical problems of high cost and low accuracy of vehicle control parameter calibration in related technologies.

[0048] Optionally, the vehicle state is identified based on multiple parameter adjustment rules and the first driving data set to determine a target parameter adjustment rule that matches the vehicle's driving state, including: performing statistical analysis on the first driving data set to determine the vehicle's state characteristics; matching the state characteristics with multiple parameter adjustment rules to determine a target parameter adjustment rule that successfully matches the state characteristics.

[0049] In an optional embodiment, statistical analysis is performed on the first driving data set, and the state characteristics of the vehicle can be determined by cluster analysis, regression analysis, or spectrum analysis. For example, the state characteristics of the vehicle can be the average value, variance value, standard deviation value, etc. of the current vehicle speed. Through statistical analysis, the driving state of the vehicle can be more accurately identified, so as to select the most appropriate parameter adjustment rule, thereby improving the pertinence and effectiveness of the adjustment.

[0050] Then, the state feature is matched with multiple parameter adjustment rules to determine the target parameter adjustment rule that successfully matches the state feature. Optionally, the technician can match the target parameter adjustment rule from multiple parameter adjustment rules based on the state feature. Alternatively, the target parameter adjustment rule can be matched from multiple parameter adjustment rules through a preset matching rule. Alternatively, the similarity between the state feature and multiple parameter adjustment rules can be calculated through a similarity algorithm, and the parameter adjustment rule with the highest similarity to the state feature can be determined as the target parameter adjustment rule.

[0051] Optionally, a statistical analysis is performed on the first driving data set to determine the state characteristics of the vehicle, including: eliminating outliers in the first driving data set to obtain a processed driving data set; determining statistical characteristics of multiple driving data in the processed driving data set, wherein the statistical characteristics include at least one of the following: a mean value, a variance value, and a standard deviation value; based on the multiple driving data in the processed driving data set, determining the operating condition characteristics of the vehicle, wherein the operating condition characteristics include one of the following: accelerating to a first vehicle speed, decelerating to a second vehicle speed, and maintaining the speed unchanged; based on the statistical characteristics and the operating condition characteristics, obtaining the state characteristics of the vehicle.

[0052] In an optional embodiment, a statistical analysis is performed on the first driving data set. First, outliers in the first driving data set can be eliminated. For example, outliers can be eliminated manually, or outliers can be identified and eliminated by using a box plot. Alternatively, outliers can also be filtered by a filter. Then, the statistical features in the processed driving data set are determined, and the statistical features can be predicted by a machine learning regression model. Alternatively, statistical features can also be extracted by a sliding window. Alternatively, statistical features can also be extracted by spectrum analysis or wavelet transform. And the operating condition characteristics are determined from the processed driving data set. The operating condition characteristics can be determined by cluster analysis, or the operating condition characteristics can be identified by a pattern recognition algorithm, or the processed driving data set is analyzed by principal component analysis to obtain the operating condition characteristics of the vehicle. Thus, the state characteristics of the vehicle can be obtained based on the statistical characteristics and the operating condition characteristics. By eliminating outliers and combining statistical characteristics and operating condition characteristics for state identification, the interference of data anomalies on driving state judgment can be effectively avoided, ensuring the accurate application of parameter adjustment rules.

[0053] Optionally, current control parameters of the vehicle are adjusted based on target parameter adjustment rules to obtain target control parameters, including: monitoring the vehicle's driving data to obtain a second driving data set; processing the second driving data set based on the target parameter adjustment rules to obtain monitoring indicators; and adjusting the vehicle's current control parameters based on the monitoring indicators and the target parameter adjustment rules to obtain target control parameters.

[0054] The above-mentioned second driving data set may be a data set related to vehicle control. The second driving data set may include data related to vehicle driving control, such as the vehicle speed, target speed, actual acceleration, target acceleration, etc. The content of the second driving data set is not limited here and can be determined as needed. Through the second driving data set, it is possible to identify whether the performance of the vehicle under different working conditions meets expectations, such as whether there are speed overshoot, steady-state error or deceleration steady-state error. So that when problems arise, the control parameters of the vehicle can be adjusted in time, the control performance of the vehicle can be optimized, and the driving efficiency and safety of the unmanned mining car can be improved.

[0055] In an optional embodiment, first, the driving data of the vehicle can be monitored by a sensor system or V2X communication technology to obtain a second driving data set. Then, according to the target parameter adjustment rule, the monitoring index is processed from the second driving data set to obtain an adjustment strategy from the target parameter adjustment rule through the monitoring index to adjust the control parameters of the vehicle. The monitoring index can be a speed error, an acceleration error, or a deceleration error, etc. The monitoring index is not limited here and can be determined as needed. Optionally, the second driving data set can be processed manually to obtain a monitoring index, or a supervised learning model can be used to predict the monitoring index based on the second driving data set. Alternatively, the monitoring index can be extracted by an adaptive algorithm. Furthermore, the current control parameters of the vehicle can be adjusted based on the monitoring index and the target parameter adjustment rule to obtain the target control parameters. Optionally, the monitoring index can be compared with the preset threshold of the monitoring index in the target parameter adjustment rule to adjust the current control parameters of the vehicle, thereby determining the target control parameters. Alternatively, the current control parameters of the vehicle can be iteratively adjusted by a gradient descent algorithm until the adjusted target control parameters meet the target parameter adjustment rule. By monitoring the feedback of indicators, closed-loop control can be achieved to ensure that the adjusted control parameters can effectively respond to the current driving state. It is suitable for real-time parameter adjustment during dynamic driving of the vehicle to improve driving efficiency and safety.

[0056] Optionally, based on monitoring indicators and target parameter adjustment rules, current control parameters are adjusted to obtain target control parameters, including: determining a driving scenario of the vehicle, wherein the driving scenario includes: an acceleration scenario or a deceleration scenario; based on the target adjustment rules, a target adjustment direction is determined; based on the driving scenario and monitoring indicators, a target adjustment ratio is determined; based on the target adjustment direction and the target adjustment ratio, the current control parameters are adjusted to obtain the target control parameters.

[0057] In an optional embodiment, in a driving environment with complex working conditions, the vehicle may experience alternating scenes of acceleration and deceleration at the same time. The driving scene of the vehicle can be determined by the change trend of the vehicle speed or acceleration, or the driving scene of the vehicle can also be determined by the sensor system. Further, based on the driving scene and the monitoring index, the target adjustment ratio for adjusting the vehicle control parameters can be determined to optimize the driving performance and control performance of the vehicle. Optionally, the target adjustment ratio corresponding to the driving scene and the monitoring index can be queried from the target parameter adjustment rule. Alternatively, the target adjustment ratio can be determined manually. Alternatively, the target adjustment ratio can also be determined according to the driving scene and the monitoring index through an adaptive algorithm. Then, the corresponding target adjustment direction in the target parameter adjustment rule can be queried through a decision tree. Alternatively, the corresponding target adjustment direction in the target parameter adjustment rule can also be queried through a fuzzy rule. Alternatively, the corresponding target adjustment direction in the target parameter adjustment rule can also be queried through a rule engine component. Furthermore, the current control parameter can be adjusted based on the determined target adjustment direction and target adjustment ratio to obtain the target control parameter. Optionally, the current control parameters can be adjusted through fuzzy logic control, or can be adjusted through genetic algorithms or particle swarm optimization, or can be adjusted through autoregressive sliding average models to obtain target control parameters. In the above manner, the control parameters can be flexibly adjusted according to different driving scenarios, especially in acceleration or deceleration scenarios, and can respond quickly to ensure a smooth transition of the vehicle, which is suitable for rapid adaptation and optimized control of the vehicle under different driving conditions. By adjusting the current control parameters to obtain the target control parameters, it can be ensured that the vehicle can achieve accurate and stable speed control under different working conditions, reduce overshoot and steady-state errors, and improve driving safety.

[0058] Optionally, the current control parameter includes multiple parameters; based on the target adjustment direction and the target adjustment ratio, the current control parameter is adjusted to obtain the target control parameter, including: determining the target parameter corresponding to the target parameter adjustment rule from multiple parameters; based on the target adjustment ratio, the target parameter is adjusted along the target adjustment direction to obtain the target control parameter.

[0059] Multiple parameter adjustment rules may have different adjustment contents. Therefore, after determining the target parameter adjustment rule, it is also necessary to determine the target parameter corresponding to the target parameter adjustment rule from the current control parameters to adjust the target parameter. By accurately adjusting the control parameters related to the current driving state of the vehicle, the driving performance of the vehicle can be effectively improved, unnecessary parameter adjustments can be reduced, and the adjustment efficiency can be improved.

[0060] In an optional embodiment, a target parameter corresponding to the target parameter adjustment rule can be determined from multiple parameters through a decision tree, and then the target parameter is adjusted along the target adjustment direction based on the target adjustment ratio to obtain the target control parameter. Alternatively, a target parameter corresponding to the target parameter adjustment rule can be determined from multiple parameters through a fuzzy rule, and then the target parameter is adjusted along the target adjustment direction based on the target adjustment ratio to obtain the target control parameter. Alternatively, a target parameter corresponding to the target parameter adjustment rule can be determined from multiple parameters through a rule engine component, and then the target parameter is adjusted along the target adjustment direction based on the target adjustment ratio to obtain the target control parameter.

[0061] Optionally, the vehicle's driving data is monitored to obtain a first driving data set, including: determining a parameter calibration scenario for the vehicle; monitoring the vehicle's driving data based on the parameter calibration scenario to obtain a first driving data set that matches the parameter calibration scenario; preferably, the current control parameters are used to characterize the control parameters that match the parameter calibration scenario when the first driving data set is monitored.

[0062] In an optional embodiment, when the vehicle is in different parameter calibration scenarios, the emphasis on vehicle control is different, so the driving data of the vehicle to be monitored will also be different. Therefore, the driving data of the vehicle is monitored to obtain a first driving data set. First, the parameter calibration scenario in which the vehicle is currently located can be determined by the sensor system, or the parameter calibration scenario of the vehicle can be determined by expert knowledge. Then, the driving data of the vehicle is monitored based on the parameter calibration scenario to obtain a first driving data set that matches the parameter calibration scenario. Optionally, the monitoring parameters corresponding to the parameter calibration scenario can be determined from the preset calibration rules, so as to obtain the driving data of the vehicle based on the monitoring parameters to obtain the first driving data set. Alternatively, the driving data of the vehicle monitored under the parameter calibration scenario can also be manually selected to obtain a first driving data set that matches the parameter calibration scenario.

[0063] Preferably, the current control parameters can be used to characterize the control parameters that match the parameter calibration scenario when the first driving data set is monitored, so that the control parameters of the vehicle are optimally calibrated to ensure adaptive adjustment of the vehicle, such as optimizing the driving control parameters of the vehicle on icy and snowy roads.

[0064] Optionally, the method further includes: monitoring the driving data of the vehicle to obtain a third driving data set; determining a control instruction of the vehicle based on the target control parameter and the third driving data set; and controlling the vehicle to continue driving based on the control instruction.

[0065] The third driving data set mentioned above may be a data set related to the current driving process of the vehicle. The third driving data set may include data related to vehicle driving control, for example, the vehicle speed, target speed, actual acceleration, target acceleration, etc. The content of the third driving data set is not limited here and can be determined as needed. The control instructions of the vehicle can be further determined based on the target control parameters and the third driving data set, so as to control the vehicle to continue driving based on the control instructions. Through continuous monitoring and adjustment, dynamic optimization of the vehicle driving state can be achieved, ensuring that the vehicle maintains optimal performance in a continuously changing driving environment and achieving closed-loop control.

[0066] In an optional embodiment, the driving data of the vehicle can be monitored by a sensor system or V2X communication technology to obtain a third driving data set. Then, based on the target control parameters and the third driving data set, the control instructions of the vehicle are determined to achieve closed-loop control. Optionally, the control algorithm can be used to calculate the control index and generate the control instructions based on the target control parameters and the third driving data set to ensure that the vehicle can travel smoothly according to the target control parameters. Alternatively, the control instructions can be set manually based on the target control parameters and the third driving data set. The vehicle can then be controlled to travel based on the control instructions by a PI controller. Alternatively, the vehicle can be controlled to continue traveling based on the control instructions by drive-by-wire technology.

[0067] Figure 2 is a schematic diagram of an optional vehicle control parameter calibration system according to an embodiment of the present invention, such as Figure 2 As shown, the system includes: an automatic calibration module and a PI controller.

[0068] The automatic calibration module can be used to monitor the vehicle through the monitor, obtain the vehicle data returned by the vehicle, and generate calibration rules, wherein the calibration rules can adjust the vehicle control parameters for vehicle driving performance problems such as large speed overshoot and large steady-state error. In addition, the automatic calibration module can also determine the target adjustment rule through the vehicle data and the calibration rule, so as to set the adjustment parameters of the PI controller based on the target adjustment rule.

[0069] Among them, the PI controller can be used to receive the current driving information sent by the vehicle and perform closed-loop control of the vehicle based on adjustment parameters.

[0070] This calibration system continuously monitors vehicle data and performs online parameter adjustments based on multiple calibration rules to improve the vehicle's driving performance and control accuracy under different operating conditions.

[0071] For example, the process of parameter calibration is explained by taking the longitudinal motion control of an autonomous mining truck as an example. When the longitudinal motion control of an autonomous mining truck is performed, the proportional term coefficient and the integral term coefficient are the parameters that need to be calibrated.

[0072] The calibration parameters are determined by the following formula:

[0073] U=K P a error +K I ∑a error ;

[0074] In the formula, U is the control output, K P is the proportional term coefficient, K I is the integral term coefficient, a error is the difference between the target longitudinal acceleration and the actual acceleration, and ∑ is the summation operation.

[0075] First, the automatic calibration module monitors the current vehicle's driving performance and records the following four parameters every 200ms within 10 seconds: actual vehicle speed v act 、Target vehicle speed v dsr , actual acceleration a act 、Target acceleration a dsr .

[0076] Then the four parameters are processed to calculate the vehicle characteristics. Specifically, the actual vehicle speed v act 、Target vehicle speed v dsr , actual acceleration a act 、Target acceleration a dsr The corresponding mean, variance and standard deviation values ​​are saved in the cache for subsequent online parameter adjustment.

[0077] Whether the vehicle control parameters need to be calibrated can be determined by one of the following conditions: low speed overshoot <1.5km / h, medium and high speed overshoot <10% target vehicle speed, speed error at steady speed <1km / h (when the vehicle speed is not less than 2km / h), or acceleration and deceleration overshoot <10% target acceleration and deceleration, etc. When any of the above conditions is met, the vehicle control parameters are calibrated.

[0078] Furthermore, there are 4 calibration rules preset in the automatic calibration module.

[0079] First, for overshoot when accelerating / decelerating to the target speed. Figure 3 As shown in Figure 1, the curve of the vehicle speed changing with time when accelerating to the target speed. At the same time, the difference between the ordinates of the two lines is the overshoot, reflecting the overshoot situation.

[0080] The recognition condition of this situation is that the vehicle speed reaches the target speed when it is accelerated or decelerated, and the target speed v dsr and actual vehicle speed v act The standard deviations are all less than 0.2.

[0081] By monitoring the first monitoring time T R1 The speed error Δv of each frame in the first monitoring time T R1 It can be 5 seconds, which is not limited here and can be determined as needed. The corresponding rule adjustment measures are: if in the first monitoring time T R1 Inside, happens In this case, reduce the integral coefficient.

[0082] Optionally, the speed error is determined by the following formula:

[0083] Δv=v act -v dsr ;

[0084] Where Δv is the speed error, v dsr is the target vehicle speed, v act is the actual vehicle speed.

[0085] Second, for the steady speed fluctuation. Figure 4 As shown in the figure, the curve of vehicle speed changing with time under steady speed driving condition. At the same time, the difference between the ordinates of the two lines is the speed error, which reflects the steady speed fluctuation.

[0086] The identification conditions for this situation are steady speed driving, v dsr The average value of v act The difference in the average value of the speed is less than 1km / h within 2s, and v dsr and v act The standard deviations are all less than 0.2.

[0087] By monitoring the second monitoring time T R2 The deceleration error Δv of each frame in the second monitoring time T R2 It can be 10 seconds, which is not limited here and can be determined as needed. The corresponding rule adjustment measures are: if in the second monitoring time T R2 Internal speed error Δv> vehicle speed error value V criticR2 The number of times exceeds N criticR2 Second, adjust the proportional parameter to a smaller value. Among them, the speed error value V criticR2 is a positive value, N criticR2 is the number of times the speed error exceeds the vehicle speed error value, N criticR2 The larger the value is, the greater the vehicle speed fluctuation is. For example, it can be taken 3 times within 10s.

[0088] Third, for the case where the steady-state error of deceleration is large during the deceleration stage. Figure 5 As shown in Figure 1, the curve of vehicle speed changing with time during the deceleration stage. At the same time, the difference between the ordinates of the two lines is the deceleration error, which reflects the deceleration steady-state error.

[0089] The recognition condition for this situation is the target acceleration a during acceleration and deceleration. dsr and the actual acceleration a act The standard deviations were all less than 0.05.

[0090] By monitoring the third monitoring time T R3 The deceleration error Δa of each frame in the third monitoring time T R3 It can be 5 seconds, which is not limited here and can be determined as needed. The corresponding rule adjustment measures are: if within the third monitoring time T R3 Within, Δa> maximum deceleration error value A maxR3 , or Δa<-A maxR3 The time is greater than (80% * total monitoring time T maxR3 ), then when the current vehicle speed is greater than 15km / h, increase the proportional item parameter, or when the current vehicle speed is less than or equal to 15km / h, increase the integral item parameter.

[0091] Optionally, the deceleration error is determined by the following formula:

[0092] Δa=a act -a dsr ;

[0093] In the formula, Δa is the deceleration error, a act is the actual acceleration, a dsr is the target acceleration.

[0094] Fourth, for the deceleration overshoot situation. Figure 6 As shown in the figure, the curve of vehicle speed changing with time under deceleration. At the same time, the difference between the vertical coordinates of the two lines is the deceleration overshoot, which reflects the overshoot situation.

[0095] The identification condition of this situation is that the target vehicle speed a is under deceleration condition. dsr The average value is less than -0.3m / s within 1s 2 .

[0096] By monitoring the fourth monitoring time T R4 The deceleration error Δa of each frame in the fourth monitoring time T R4 It can be 5 seconds, which is not limited here and can be determined as needed. The corresponding rule adjustment measures are: if within the fourth monitoring time T R4 Inside, Reduce the scale parameter.

[0097] According to an embodiment of the present invention, a device embodiment of a vehicle control parameter calibration device is provided. It should be noted that the device can be used to execute the above-mentioned vehicle control parameter calibration method.

[0098] Figure 7 is a schematic diagram of a vehicle control parameter calibration device according to an embodiment of the present invention, such as Figure 7 As shown, the device comprises:

[0099] The monitoring module 72 is used to monitor the vehicle's driving data during the process of controlling the vehicle's driving to obtain a first driving data set; the state identification module 74 is used to identify the vehicle's state based on multiple parameter adjustment rules and the first driving data set, and determine the target parameter adjustment rules that match the vehicle's driving state; the adjustment module 76 is used to adjust the vehicle's current control parameters based on the target parameter adjustment rules to obtain the target control parameters during the vehicle's driving process.

[0100] Optionally, the state identification module is further used to perform statistical analysis on the first driving data set to determine the state characteristics of the vehicle; match the state characteristics with multiple parameter adjustment rules to determine the target parameter adjustment rules that successfully match the state characteristics.

[0101] Optionally, the state identification module is also used to eliminate abnormal values ​​in the first driving data set to obtain a processed driving data set; determine statistical characteristics of multiple driving data in the processed driving data set, wherein the statistical characteristics include at least one of the following: mean value, variance value and standard deviation value; based on the multiple driving data in the processed driving data set, determine the operating condition characteristics of the vehicle, wherein the operating condition characteristics include one of the following: accelerating to a first vehicle speed, decelerating to a second vehicle speed, and keeping the speed unchanged; based on the statistical characteristics and the operating condition characteristics, obtain the state characteristics of the vehicle.

[0102] Optionally, the adjustment module is also used to monitor the vehicle's driving data to obtain a second driving data set; based on the target parameter adjustment rules, the second driving data set is processed to obtain monitoring indicators; based on the monitoring indicators and the target parameter adjustment rules, the current control parameters of the vehicle are adjusted to obtain target control parameters.

[0103] Optionally, the adjustment module is also used to determine the driving scenario of the vehicle, wherein the driving scenario includes: acceleration scenario or deceleration scenario; based on the target adjustment rule, determine the target adjustment direction; based on the driving scenario and the monitoring indicators, determine the target adjustment ratio; based on the target adjustment direction and the target adjustment ratio, adjust the current control parameters to obtain the target control parameters.

[0104] Optionally, the adjustment module is further used to determine a target parameter corresponding to the target parameter adjustment rule from multiple parameters; based on the target adjustment ratio, adjust the target parameter along the target adjustment direction to obtain the target control parameter.

[0105] Optionally, the monitoring module is also used to determine a parameter calibration scenario of the vehicle; based on the parameter calibration scenario, the vehicle's driving data is monitored to obtain a first driving data set that matches the parameter calibration scenario; preferably, the current control parameters are used to characterize the control parameters that match the parameter calibration scenario when the first driving data set is monitored.

[0106] Optionally, the above-mentioned device also includes: a control module, used to monitor the vehicle's driving data to obtain a third driving data set; determine the vehicle's control instructions based on the target control parameters and the third driving data set; and control the vehicle to continue driving based on the control instructions.

[0107] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0108] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0109] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0110] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0111] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0112] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0117] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for calibrating vehicle control parameters, characterized in that: include: In the process of controlling the driving of the vehicle, the driving data of the vehicle is monitored to obtain a first driving data set; Identifying the state of the vehicle based on a plurality of parameter adjustment rules and the first driving data set, and determining a target parameter adjustment rule that matches the driving state of the vehicle; The current control parameters of the vehicle are adjusted based on the target parameter adjustment rule to obtain the target control parameters during the driving process of the vehicle.

2. The method according to claim 1, characterized in that The step of identifying the state of the vehicle based on the plurality of parameter adjustment rules and the first driving data set to determine a target parameter adjustment rule that matches the driving state of the vehicle includes: Performing statistical analysis on the first driving data set to determine the state characteristics of the vehicle; The state feature is matched with a plurality of parameter adjustment rules to determine a target parameter adjustment rule that successfully matches the state feature.

3. The method according to claim 2, characterized in that The performing statistical analysis on the first driving data set to determine the state characteristics of the vehicle includes: Eliminating abnormal values ​​in the first driving data set to obtain a processed driving data set; Determining statistical features of a plurality of driving data in the processed driving data set, wherein the statistical features include at least one of the following: a mean value, a variance value, and a standard deviation value; Determine the operating condition characteristics of the vehicle based on the plurality of driving data in the processed driving data set, wherein the operating condition characteristics include one of: accelerating to a first vehicle speed, decelerating to a second vehicle speed, and keeping the speed constant; Based on the statistical characteristics and the operating condition characteristics, the state characteristics of the vehicle are obtained.

4. The method according to claim 1, characterized in that The adjusting the current control parameter of the vehicle based on the target parameter adjustment rule to obtain the target control parameter includes: Monitoring the driving data of the vehicle to obtain a second driving data set; Based on the target parameter adjustment rule, processing the second driving data set to obtain a monitoring indicator; Based on the monitoring index and the target parameter adjustment rule, the current control parameter of the vehicle is adjusted to obtain the target control parameter.

5. The method according to claim 4, characterized in that The adjusting the current control parameter based on the monitoring index and the target parameter adjustment rule to obtain the target control parameter includes: Determining a driving scenario of the vehicle, wherein the driving scenario includes: an acceleration scenario or a deceleration scenario; Based on the target adjustment rule, determining a target adjustment direction; Determining a target adjustment ratio based on the driving scenario and the monitoring indicator; Based on the target adjustment direction and the target adjustment ratio, the current control parameter is adjusted to obtain the target control parameter.

6. The method according to claim 5, characterized in that The current control parameter includes a plurality of parameters; the current control parameter is adjusted based on the target adjustment direction and the target adjustment ratio to obtain the target control parameter, including: Determining a target parameter corresponding to the target parameter adjustment rule from the multiple parameters; Based on the target adjustment ratio, the target parameter is adjusted along the target adjustment direction to obtain the target control parameter.

7. The method according to any one of claims 1 to 6, characterized in that: The monitoring of the driving data of the vehicle to obtain a first driving data set includes: Determining a parameter calibration scenario for the vehicle; Monitoring the driving data of the vehicle based on the parameter calibration scenario to obtain a first driving data set matching the parameter calibration scenario; Preferably, the current control parameter is used to characterize the control parameter that matches the parameter calibration scenario when the first driving data set is monitored.

8. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Monitoring the driving data of the vehicle to obtain a third driving data set; determining a control instruction for the vehicle based on the target control parameter and the third driving data set; The vehicle is controlled to continue traveling based on the control instruction.

9. A vehicle control parameter calibration device, characterized in that: include: A monitoring module, used for monitoring the driving data of the vehicle during the process of controlling the driving of the vehicle to obtain a first driving data set; a state identification module, configured to identify the state of the vehicle based on a plurality of parameter adjustment rules and the first driving data set, and determine a target parameter adjustment rule that matches the driving state of the vehicle; The adjustment module is used to adjust the current control parameters of the vehicle based on the target parameter adjustment rule to obtain the target control parameters during the driving process of the vehicle.

10. A vehicle, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 8 when running.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images