Closed-loop control method and system for double servo motors of automatic driving steering system

Abstract

The invention discloses a closed-loop control method and system for double servo motors of an automatic driving steering system, and relates to the technical field of automatic driving. According to the method, vehicle information is collected through a sensor module, obstacle detection and lane changing evaluation are conducted through a deep learning algorithm, target torque is calculated through a PID control algorithm, and precise control over the double servo motors is achieved. And through links of torque distribution, clutch control, execution control, feedback adjustment and the like, the safety and the driving stability of the vehicle are improved. The method has the advantages of accurate control, safety, reliability, adaptability to different driving states and the like, and the performance of an automatic driving steering system can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving, and in particular relates to a closed-loop control method and system for dual servo motors of an autonomous driving steering system. Background Art

[0002] With the development of automobile intelligence, autonomous driving technology has attracted more and more attention. The autonomous driving steering system needs to have high precision, high reliability and safety. In the actual driving process, the vehicle faces various complex road conditions and environments, such as obstacles, different vehicle speeds, steering angles, etc.

[0003] Traditional steering systems often fail to achieve precise control in these situations. For example, when encountering an obstacle, it is impossible to accurately determine whether it is safe to change lanes, and it is easy to lose control during the steering process.

[0004] In the existing technology, some steering systems use a single servo motor, which has limited control accuracy and response speed and is difficult to meet the needs of autonomous driving. At the same time, the development of sensor technology has also provided more information collection methods for autonomous driving steering systems, but how to effectively integrate and utilize this information is also a problem that needs to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a dual servo motor closed-loop control method and control system for an autonomous driving steering system, aiming to improve the steering accuracy and safety of an autonomous driving vehicle in a complex road environment.

[0006] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0007] The present invention is a closed-loop control method for dual servo motors of an automatic driving steering system, comprising the following steps:

[0008] S1 Data Collection: The sensor module collects various information data of the vehicle in real time, including but not limited to steering angle, vehicle speed, torque and obstacle distance;

[0009] S2 Obstacle Detection and Changeable Lane Assessment: Based on sensor data, it uses deep learning algorithms to perform obstacle detection and changeable lane assessment;

[0010] S3 command reception: receiving steering commands sent by the autonomous driving central controller;

[0011] S4 calculates target torque: uses PID control algorithm to calculate the target output torque of the dual servo motors based on collected data, obstacle detection and variable lane assessment results, and steering instructions;

[0012] S5 torque distribution and clutch control: distributes the target torque to the two servo motors and controls the electronic clutch according to the characteristics of the dual servo motors and the vehicle steering requirements;

[0013] S6 execution control: Dual servo motors drive the steering mechanism according to the allocated torque to achieve precise control;

[0014] S7 feedback adjustment: The steering status is monitored by the sensor module, and the control algorithm is adjusted based on the feedback signal to achieve closed-loop control.

[0015] As a preferred technical solution of the present invention, in the S1 data acquisition step, the sensor module includes but is not limited to an angle sensor, a torque sensor, a vehicle speed sensor, a camera and an electronic radar. After the vehicle data is acquired through the sensor module in S2, multi-sensor fusion technology is used to integrate the information acquired by different types of sensors, and then obstacle detection is performed.

[0016] As a preferred technical solution of the present invention, the use of a deep learning algorithm to perform variable lane assessment in S2 specifically includes the following steps:

[0017] S21 Data preparation: preprocessing the collected sensor data, including cleaning, removing noise and outliers;

[0018] S22 Feature extraction: extract key features from sensor data, including but not limited to vehicle speed, distance to vehicles in adjacent lanes, speed of vehicles in adjacent lanes, and vehicle acceleration;

[0019] S23 Decision tree construction: Based on the decision tree algorithm, a variable lane evaluation model is established according to the characteristics and decision rules;

[0020] S24 model training: Use a large amount of training data to train the decision tree model and adjust the model parameters;

[0021] S25 Model evaluation: Evaluate the model through test data to verify the performance of the model;

[0022] S26 decision process: input sensor data into the decision tree model to determine whether the lane can be changed;

[0023] S27 outputs the result: outputs the variable lane evaluation result.

[0024] As a preferred technical solution of the present invention, the PID control algorithm for calculating the target torque includes the following steps:

[0025] Parameter setting: Set the proportional coefficient K according to the vehicle's driving status and steering requirements. p , integral coefficient K i and the differential coefficient K dThe value of

[0026] Calculation process: According to the vehicle's driving state, steering angle and obstacle distance, the target torque M is calculated by the formula as follows:

[0027]

[0028] Adjustment process: Adjust the PID control algorithm according to the actual driving conditions and feedback signals of the vehicle.

[0029] As a preferred technical solution of the present invention, S5 comprises the following steps:

[0030] Motor characteristic analysis: Equipped with dual servo motors with different torque output characteristics, the dual servo motors are divided into high-torque motors and low-torque motors according to the motor characteristics. The high-torque motor is used to provide a large torque output during high-speed driving and steering, while the low-torque motor is used to provide a stable torque output during low-speed driving and precise steering control;

[0031] Distribution strategy: formulate torque distribution strategy according to the vehicle's steering mode and torque requirements, and dynamically adjust the torque distribution ratio according to the vehicle's driving status and steering requirements;

[0032] Clutch control: The working state of the motor is controlled by the electronic clutch. When the motor needs to be switched, the controller module sends a control signal to the electronic clutch to engage the clutch, thereby achieving the switching of the motor.

[0033] As a preferred technical solution of the present invention, S6 specifically includes the following operations:

[0034] Motor drive: The drive circuit outputs current and voltage according to the instructions of the controller module to drive the motor to rotate. The speed and torque of the motor are adjusted according to the control signal to ensure that the steering mechanism can steer according to the predetermined trajectory;

[0035] Steering mechanism: The motor drives the steering knuckle, which drives the steering rod and steering wheel to achieve steering action. During the steering process, the angle and position of the steering mechanism are adjusted according to the vehicle's driving status and steering requirements.

[0036] As a preferred technical solution of the present invention, feedback adjustment is performed in the step S7 in the following manner:

[0037] Sensor feedback: The sensor module monitors the steering state of the vehicle in real time to obtain steering information, and feeds the steering information back to the controller module, which adjusts the control parameters according to the feedback signal;

[0038] Control algorithm adjustment: Adjust the control algorithm according to the actual driving conditions of the vehicle and feedback signals.

[0039] As a preferred technical solution of the present invention, maintain the current state: continuously monitor the vehicle's surrounding environment and obstacles, keep the vehicle driving stably, and avoid dangers caused by lane changes; take safety measures: according to the vehicle's driving state and obstacle conditions, take appropriate braking measures, warning reminders and avoidance strategies.

[0040] The present invention also provides a closed-loop control system of a dual servo motor of an automatic driving steering system, which is used to implement the above-mentioned closed-loop control method of a dual servo motor of an automatic driving steering system, including a hardware architecture and a software algorithm. The hardware architecture includes dual servo motors, a controller module, a sensor module, a power module, a communication module, an electronic clutch, an electronic brake, and a mechanical structure; the software algorithm adopts a PID control algorithm to realize closed-loop control of the dual servo motors according to the information feedback from the sensors and the driving status of the vehicle.

[0041] The present invention has the following beneficial effects:

[0042] Precise control: Through the PID control algorithm, the target output torque of the dual servo motors is accurately calculated according to the vehicle's driving status, steering angle, obstacle distance and other information to ensure the accuracy of steering.

[0043] Safe and reliable: Using deep learning algorithms for obstacle detection and lane change assessment can accurately determine whether the vehicle can change lanes safely and avoid danger caused by lane changes. At the same time, the sensor module monitors the vehicle's steering status in real time and achieves closed-loop control through feedback adjustment, thereby improving the reliability of the system.

[0044] Adapt to different driving conditions: According to the characteristics of dual servo motors, the motors are divided into high-torque motors and low-torque motors, which are used for steering control during high-speed driving and low-speed driving respectively, to meet the needs of the vehicle under different driving conditions.

[0045] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0047] Figure 1 Schematic diagram of the process of the present invention;

[0048] Figure 2 It is a specific flow chart of the variable lane evaluation in S2 of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0050] See also Figure 1-2 As shown, the present invention is a closed-loop control method for dual servo motors of an automatic driving steering system, comprising the following steps:

[0051] S1 Data Collection: The sensor module collects various information data of the vehicle in real time, including but not limited to steering angle, vehicle speed, torque and obstacle distance;

[0052] S2 Obstacle Detection and Changeable Lane Assessment: Based on sensor data, it uses deep learning algorithms to perform obstacle detection and changeable lane assessment;

[0053] S3 command reception: receiving steering commands sent by the autonomous driving central controller;

[0054] S4 calculates target torque: uses PID control algorithm to calculate the target output torque of the dual servo motors based on collected data, obstacle detection and variable lane assessment results, and steering instructions;

[0055] S5 torque distribution and clutch control: distributes the target torque to the two servo motors and controls the electronic clutch according to the characteristics of the dual servo motors and the vehicle steering requirements;

[0056] S6 execution control: Dual servo motors drive the steering mechanism according to the allocated torque to achieve precise control;

[0057] S7 feedback adjustment: The steering status is monitored by the sensor module, and the control algorithm is adjusted based on the feedback signal to achieve closed-loop control.

[0058] A specific application of this embodiment is:

[0059] Embodiment 1

[0060] The present invention comprises the following steps, which are specifically implemented as follows:

[0061] S1 Data Collection

[0062] A sensor module is installed in the vehicle's steering system. The module contains multiple sensors. The specific installation locations and quantities are as follows:

[0063] Angle sensor: One sensor is installed at the rotation axis of the steering wheel. Its main function is to accurately measure the rotation angle of the steering wheel and provide basic data for subsequent steering control.

[0064] Torque sensor: One sensor is installed on the steering column to monitor the steering torque in real time and help understand the power requirements of the vehicle when steering.

[0065] Vehicle speed sensor: installed near the wheels, one sensor is installed on each wheel, for a total of four sensors, which obtains vehicle speed information by sensing the rotation speed of the wheels;

[0066] Cameras: Installed in front and on the sides of the vehicle, two in the front and one on each side, for a total of four. The cameras are used to capture images of the environment around the vehicle and provide visual information for obstacle detection and variable lane assessment;

[0067] Electronic radar: installed on the front and rear bumpers of the vehicle, one each, for a total of two. The electronic radar can detect the distance to obstacles and assist in obtaining obstacle information around the vehicle;

[0068] When collecting data, the signals of each sensor are connected to the controller module through cables. The signals of the angle sensor, torque sensor and vehicle speed sensor are transmitted in the form of analog signals, while the signals of the camera and electronic radar are transmitted via digital signals. The controller module converts the sensor data into digital signals through a specific interface for subsequent processing.

[0069] S2 uses deep learning algorithms to detect obstacles and evaluate lane changes based on sensor data. The use of multi-sensor fusion technology for obstacle detection includes the following steps:

[0070] Data preprocessing and calibration

[0071] For the image data collected by the camera, preprocessing is first performed, which includes grayscale processing of the image, converting the color image into a grayscale image to reduce the amount of data and improve processing efficiency. At the same time, image filtering is performed to remove noise, such as using Gaussian filtering to reduce salt and pepper noise and Gaussian noise in the image.

[0072] The data obtained by the electronic radar is calibrated for distance and speed. Since the measurement accuracy of the electronic radar may be affected by environmental factors (such as temperature and humidity) and its own hardware characteristics, it needs to be calibrated regularly. For example, by measuring in front of a standard reflector at a known distance, the radar parameters can be adjusted to ensure the accuracy of the distance measurement.

[0073] The data of all sensors are synchronized in time, because the acquisition frequency and data transmission delay of different sensors may be different. In order to ensure the accuracy of the fused data, they need to be aligned on the time axis. This can be done by adding a timestamp to the header of each sensor data packet and then synchronizing the data according to the timestamp.

[0074] Feature extraction and association

[0075] Extract features from camera images: Use computer vision algorithms, such as edge detection algorithms (e.g., Canny edge detection) to extract edge information of objects in the image. These edges may represent the outlines of obstacles. At the same time, use object detection algorithms (e.g., YOLOv5) to identify potential obstacles in the image, such as other vehicles, pedestrians, or traffic signs, and extract their location, size, and other feature information.

[0076] Extract features from radar data: Radar data mainly contains distance, speed, and angle information of target objects. Extract the distance and angle features of each detected target, which will be used to associate with the object in the camera image.

[0077] Feature association: Associate the object position information (two-dimensional plane coordinates) extracted from the camera image with the distance and angle information (polar coordinates) of the target detected by the electronic radar. Through coordinate transformation and spatial geometric relationships, the features of the two different sensors are mapped to the same spatial coordinate system. For example, based on the angle and distance of the target detected by the radar, the position of the target in the vehicle coordinate system is calculated and then matched with the position of the object identified in the camera image.

[0078] Data fusion algorithm application

[0079] Fusion method based on Bayesian reasoning: Using Bayesian reasoning, the detection probabilities of the camera and the electronic radar for the same target are fused. Assume that the probability that the camera detects an obstacle in a certain area is P(C / I) (where C represents the existence of an obstacle and I represents the camera image information), and the probability that the electronic radar detects an obstacle in the same area is P(R / D) (where R represents the existence of an obstacle and D represents the radar data). According to the Bayesian formula, the probability of the existence of an obstacle after the fusion of the two sensor data is calculated. This method can comprehensively consider the uncertainty of the two sensors and improve the accuracy of obstacle detection.

[0080] Kalman filter fusion method: For dynamic obstacles (such as moving vehicles), Kalman filtering can be used for data fusion. Kalman filtering fuses the position and speed information of dynamic obstacles from the camera and electronic radar through prediction and update steps. First, based on the state estimation and system model of the previous moment, the position and speed of the obstacle at the current moment are predicted (prediction step). Then, the measured values ​​and predicted values ​​of the camera and electronic radar are weighted and fused to obtain a more accurate estimate of the state of the obstacle at the current moment (update step). For example, for a leading vehicle approaching a vehicle, the radar can provide the distance and relative speed information of the leading vehicle, and the camera can provide the position change information of the leading vehicle in the image. The Kalman filter fuses these two types of information to more accurately track the motion state of the leading vehicle.

[0081] Obstacle identification and classification

[0082] After data fusion, the existence of obstacles is confirmed based on the fused features and probability information. If the fused probability of obstacle existence exceeds the set threshold (for example), it is considered that there is an obstacle at that location.

[0083] Classify the confirmed obstacles, combine the visual features such as object shape and texture in the camera image and the object motion features detected by the radar, and use machine learning classification algorithms (such as support vector machines or deep learning classifiers) to classify the obstacles. For example, distinguish whether the obstacle is a vehicle, pedestrian, bicycle or other object, so that the vehicle can make more appropriate decisions.

[0084] When S2 uses the deep learning algorithm to perform variable lane assessment, the following steps are specifically included:

[0085] Data preparation: Clean the collected sensor data to remove noise and outliers. This step aims to ensure the quality of the data and avoid the subsequent analysis being affected by impurities or interference signals. For example, impurities and abnormal voltage fluctuations in sensor data can be removed.

[0086] Feature extraction: Extract key features from sensor data, including vehicle speed, distance to vehicles in adjacent lanes, speed of vehicles in adjacent lanes, and vehicle acceleration. These features are crucial for determining lane change situations. For example, vehicle speed is an important factor in determining whether a lane change can be made safely in the current state; the distance to vehicles in adjacent lanes determines whether the vehicle has enough space to change lanes.

[0087] Decision tree construction: Based on the decision tree algorithm, a variable lane assessment model is established according to the features and decision rules. The root node of the decision tree can be whether the distance between the vehicle and the vehicle in the adjacent lane is greater than a certain set value. For example, the root node is set to be greater than 5 meters between the vehicle and the vehicle in the adjacent lane, and then judgment is made based on different branches. Branch nodes can be factors such as vehicle speed and acceleration. For example, when the root node determines that the distance between the vehicle and the vehicle in the adjacent lane is greater than 5 meters, it further determines whether the vehicle speed is greater than 30 kilometers per hour. If so, it further determines whether the vehicle acceleration is greater than 2 meters per second 2.

[0088] Model training: Use a large amount of training data to train the decision tree model and adjust the model parameters. The training data includes vehicle status, driving data, and obstacle information in various scenarios. Through training, the model can accurately identify variable lane situations. For example, the training data includes vehicle status at different speeds, different distances, and different accelerations, as well as the corresponding variable lane results.

[0089] Model evaluation: The model is evaluated through test data to verify the model's performance. The test data is similar to the training data, but has a certain degree of independence. For example, the test data contains some vehicle states and scenarios that have not appeared in the training data. By evaluating the model's performance on the test data, the accuracy and reliability of the model are determined.

[0090] Decision-making process: Input sensor data into the decision tree model to determine whether the lane can be changed. According to the judgment result of the model, the possibility of lane change is determined. For example, after the sensor data is input into the model, the model makes a judgment based on the decision rules. If the distance between the vehicle and the vehicle in the adjacent lane is greater than the set value and the vehicle speed, acceleration and other conditions meet certain requirements, it is judged as a lane change.

[0091] Output results: Output the lane change assessment results, for example, the possibility of lane change, related decision information, etc. The decision information may include the speed and steering angle that the vehicle needs to adjust.

[0092] S3 command reception

[0093] The steering command sent by the autonomous driving central controller is received through the communication module. The communication module uses wireless communication methods such as Bluetooth, Wi-Fi, etc. to ensure a stable connection with the autonomous driving central controller. After receiving the command, the controller module parses and verifies the command to ensure the correctness and integrity of the command.

[0094] S4 Calculate target torque

[0095] Using the PID control algorithm, the target output torque of the dual servo motors is calculated based on the collected data, obstacle detection and variable lane assessment results, and steering instructions.

[0096] The PID control algorithm is a closed-loop control algorithm, the principle of which is to adjust the control signal through proportional, integral and differential operations on the error. In this embodiment, the error e is the deviation between the actual steering angle of the vehicle and the target steering angle.

[0097] Parameter settings:

[0098] Proportional coefficient K p : Determines the controller's response speed to the error. A larger K p The controller will be more sensitive to the error and can quickly adjust the motor torque to reduce the error. For example, when the vehicle is driving at high speed, in order to quickly respond to steering commands, K can be appropriately increased. p But if K p If it is too large, it may cause system instability and oscillation.

[0099] Integration coefficient K i :Used to eliminate the steady-state error of the system. It enables the controller to accumulate the error by integrating the error, thereby adjusting the motor torque to eliminate the error. For example, when the vehicle is driving at a low speed or requires precise steering control, increasing K i It can make the motor output more stable and eliminate errors caused by system friction and other factors. However, if the integral coefficient is too large, the system response may become slower and even integral saturation may occur.

[0100] Differential coefficient K d :Can adjust the control signal according to the rate of change of the error. It can make the controller respond quickly to the changing trend of the error and improve the response speed and stability of the system. For example, when a rapidly changing error occurs during the vehicle steering process, K d The motor torque can be adjusted quickly, allowing the vehicle to quickly track the target steering angle. However, if the differential coefficient is too large, it may be sensitive to noise and cause system instability.

[0101] Calculation process:

[0102] According to the vehicle's driving state, steering angle and obstacle distance, the formula

[0103]

[0104] Calculate the target torque M. Where e is the error between the actual steering angle of the vehicle and the target steering angle, and t is the time. For example, when the steering angle deviates during vehicle driving, the proportional coefficient, integral coefficient, and differential coefficient are combined to calculate according to the size and direction of the deviation.

[0105] Assuming that the actual steering angle of the vehicle at a certain moment is θ1 and the target steering angle is θ0, the error e = θ1-θ 01In the calculation process, the integral term Represents the accumulation of error over time, the differential term Indicates the rate of change of error.

[0106] Adjustment process:

[0107] Adjust the proportionality factor K p :When the vehicle speed increases, in order to enable the motor to respond quickly to the steering command, K can be appropriately increased. p For example, when driving at high speed, increasing K p The motor can adjust the torque quickly and improve the response speed of the steering system. p If it is too large, it may cause the system to overreact and become unstable.

[0108] Adjust the integral coefficient K i : When a large error occurs during vehicle steering, increase K i It can make the motor output more stable and eliminate errors. For example, when the vehicle is driving at a low speed or needs to control the steering precisely, increasing K i The motor torque can be adjusted more smoothly and the error can be reduced. However, if K i If it is too large, the system response may become slow or even integral saturation may occur.

[0109] Adjust the differential coefficient K d :When the vehicle steering process has a rapidly changing error, K d The motor torque can be adjusted quickly to enable the vehicle to quickly track the target steering angle. For example, when the vehicle encounters a sudden obstacle or turns, K d The motor torque can be adjusted in time according to the error change rate to improve the stability of the system. d If it is too large, it may be sensitive to noise and cause system instability.

[0110] By adjusting the parameters of the PID control algorithm, the dual servo motors can accurately output the target torque according to the vehicle's driving state and steering requirements, thereby achieving precise control of the steering system.

[0111] S5 torque distribution and clutch control

[0112] According to the characteristics of the dual servo motors and the vehicle steering requirements, the target torque is distributed to the two servo motors and the electronic clutch is controlled.

[0113] Motor characteristic analysis: Equipped with dual servo motors with different torque output characteristics, dual servo motors are divided into high-torque motors and low-torque motors according to motor characteristics. High-torque motors are used to provide large torque output during high-speed driving and steering, while low-torque motors are used to provide stable torque output during low-speed driving and precise steering control. For example, high-torque motors can provide strong torque when driving at high speeds, allowing the vehicle to turn quickly; low-torque motors can provide stable torque when driving at low speeds, ensuring the smooth driving of the vehicle.

[0114] Distribution strategy: According to the vehicle's steering mode and torque requirements, a torque distribution strategy is formulated. At the same time, the torque distribution ratio is dynamically adjusted according to the vehicle's driving state and steering requirements. For example, when driving at high speed, a larger torque is distributed to the high-torque motor; when driving at low speed or when precise steering control is required, the torque is distributed to the low-torque motor. The specific distribution ratio can be adjusted according to actual conditions.

[0115] Clutch control: The working state of the motor is controlled by the electronic clutch. When the motor needs to be switched, the controller module sends a control signal to the electronic clutch to engage the clutch, thereby achieving the switching of the motor. During the switching process, the motor torque output is ensured to have a smooth transition to avoid torque fluctuations and shocks.

[0116] S6 Execution Control

[0117] Dual servo motors drive the steering mechanism according to the allocated torque to achieve precise control.

[0118] Motor drive: The drive circuit outputs current and voltage according to the instructions of the controller module to drive the motor to rotate. The motor speed and torque are adjusted according to the control signal to ensure that the steering mechanism can turn according to the predetermined trajectory. For example, during the steering process, the motor speed and torque are adjusted according to the vehicle's driving state and steering requirements. When the vehicle needs to turn quickly, the motor increases the torque output and speed.

[0119] Steering mechanism: The motor drives the steering knuckle, which drives the steering rod and the steering wheel to achieve steering action. During the steering process, the angle and position of the steering mechanism are adjusted according to the driving state and steering requirements of the vehicle. For example, during the steering process, the angle and position of the steering mechanism are adjusted according to the driving state and steering requirements of the vehicle. When the vehicle needs to turn, the steering knuckle drives the steering rod and the steering wheel to rotate accordingly.

[0120] S7 Feedback Adjustment

[0121] The steering status is monitored through the sensor module, and the control algorithm is adjusted based on the feedback signal to achieve closed-loop control.

[0122] Sensor feedback: The sensor module monitors the vehicle's steering state in real time to obtain steering information, and feeds the steering information back to the controller module. The controller module adjusts the control parameters based on the feedback signal. For example, when the steering wheel speed is too fast or the steering angle is too large, the controller module adjusts the motor speed and torque based on the feedback signal. When the steering wheel speed is too fast, the controller module increases the motor speed to slow down the steering wheel.

[0123] Control algorithm adjustment: The control algorithm is adjusted according to the actual driving conditions and feedback signals of the vehicle. For example, when a large error occurs in the steering system during driving, the parameters of the PID control algorithm are adjusted so that the system can adjust to the target state more quickly. When a large error occurs in the steering system, the controller module adjusts the parameters of the PID control algorithm so that the system can adjust to the target state more quickly.

[0124] In addition, in order to implement the above method, the present invention also includes a dual servo motor closed-loop control system for an automatic driving steering system, including a hardware architecture and a software algorithm.

[0125] The hardware architecture includes dual servo motors, controller module, sensor module, power module, communication module, electronic clutch, electronic brake, and mechanical structure.

[0126] Dual servo motors: with high torque output capability and precise control performance, each motor has an independent drive circuit;

[0127] Controller module: responsible for receiving sensor data, processing data, and outputting control signals to the dual servo motors according to the control algorithm;

[0128] Sensor module: including angle sensor, torque sensor, vehicle speed sensor, camera, electronic radar, etc.;

[0129] Power module: provides stable power supply for the entire system;

[0130] Communication module: realizes the communication between the controller module and other systems;

[0131] Electronic clutch: controls the working status of dual servo motors;

[0132] Electronic brake: During the vehicle steering process, when the turning angle is in place or needs to be reversed, the electronic brake will work first to prevent the steering wheel from turning excessively or losing control;

[0133] Mechanical structure: including steering column, steering knuckle, steering tie rod and steering wheel, etc.;

[0134] Software algorithm: PID control algorithm is used to achieve closed-loop control of the dual servo motors based on the information fed back by the sensors and the driving status of the vehicle.

[0135] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0136] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A closed-loop control method for dual servo motors of an automatic driving steering system, characterized in that: The following steps are involved: S1 Data Collection: The sensor module collects various information data of the vehicle in real time, including but not limited to steering angle, vehicle speed, torque and obstacle distance; S2 Obstacle Detection and Changeable Lane Assessment: Based on sensor data, it uses deep learning algorithms to perform obstacle detection and changeable lane assessment; S3 command reception: receiving steering commands sent by the autonomous driving central controller; S4 calculates target torque: uses PID control algorithm to calculate the target output torque of the dual servo motors based on collected data, obstacle detection and variable lane assessment results, and steering instructions; S5 torque distribution and clutch control: distributes the target torque to the two servo motors and controls the electronic clutch according to the characteristics of the dual servo motors and the vehicle steering requirements; S6 execution control: Dual servo motors drive the steering mechanism according to the allocated torque to achieve precise control; S7 feedback adjustment: The steering status is monitored by the sensor module, and the control algorithm is adjusted based on the feedback signal to achieve closed-loop control.

2. The closed-loop control method of dual servo motors of an automatic driving steering system according to claim 1, characterized in that: In the S1 data collection step, the sensor module includes but is not limited to an angle sensor, a torque sensor, a vehicle speed sensor, a camera and an electronic radar. After acquiring the vehicle data through the sensor module in S2, multi-sensor fusion technology is used to integrate the information acquired by different types of sensors, and then obstacle detection is performed.

3. The closed-loop control method of dual servo motors of an automatic driving steering system according to claim 2, characterized in that: The use of the deep learning algorithm to perform variable lane assessment in S2 specifically includes the following steps: S21 Data preparation: preprocessing the collected sensor data, including cleaning, removing noise and outliers; S22 Feature extraction: extract key features from sensor data, including but not limited to vehicle speed, distance to vehicles in adjacent lanes, speed of vehicles in adjacent lanes, and vehicle acceleration; S23 Decision tree construction: Based on the decision tree algorithm, a variable lane evaluation model is established according to the characteristics and decision rules; S24 model training: Use a large amount of training data to train the decision tree model and adjust the model parameters; S25 Model evaluation: Evaluate the model through test data to verify the performance of the model; S26 decision process: input sensor data into the decision tree model to determine whether the lane can be changed; S27 outputs the result: outputs the variable lane evaluation result.

4. The closed-loop control method for dual servo motors of an automatic driving steering system according to claim 1, characterized in that: The PID control algorithm for calculating the target torque includes the following steps: Parameter setting: Set the proportional coefficient K according to the vehicle's driving status and steering requirements. p , integral coefficient K i and the differential coefficient K d The value of Calculation process: According to the vehicle's driving state, steering angle and obstacle distance, the target torque M is calculated by the formula as follows: Adjustment process: Adjust the PID control algorithm according to the actual driving conditions and feedback signals of the vehicle.

5. The closed-loop control method of dual servo motors of an automatic driving steering system according to claim 1, characterized in that: The S5 comprises the following steps: Motor characteristic analysis: Equipped with dual servo motors with different torque output characteristics, the dual servo motors are divided into high-torque motors and low-torque motors according to the motor characteristics. The high-torque motor is used to provide a large torque output during high-speed driving and steering, while the low-torque motor is used to provide a stable torque output during low-speed driving and precise steering control; Distribution strategy: formulate torque distribution strategy according to the vehicle's steering mode and torque requirements, and dynamically adjust the torque distribution ratio according to the vehicle's driving status and steering requirements; Clutch control: The working state of the motor is controlled by the electronic clutch. When the motor needs to be switched, the controller module sends a control signal to the electronic clutch to engage the clutch, thereby achieving the switching of the motor.

6. The closed-loop control method of dual servo motors of an automatic driving steering system according to claim 1, characterized in that: The S6 specifically includes the following operations: Motor drive: The drive circuit outputs current and voltage according to the instructions of the controller module to drive the motor to rotate. The speed and torque of the motor are adjusted according to the control signal to ensure that the steering mechanism can steer according to the predetermined trajectory; Steering mechanism: The motor drives the steering knuckle, which drives the steering rod and steering wheel to achieve steering action. During the steering process, the angle and position of the steering mechanism are adjusted according to the vehicle's driving status and steering requirements.

7. The closed-loop control method for dual servo motors of an automatic driving steering system according to claim 1, characterized in that: In step S7, feedback adjustment is performed in the following manner: Sensor feedback: The sensor module monitors the steering state of the vehicle in real time to obtain steering information, and feeds the steering information back to the controller module, which adjusts the control parameters according to the feedback signal; Control algorithm adjustment: Adjust the control algorithm according to the actual driving conditions of the vehicle and feedback signals.

8. The closed-loop control method for dual servo motors of an automatic driving steering system according to claim 1, characterized in that: Maintain the current state: continuously monitor the vehicle's surrounding environment and obstacles, keep the vehicle driving steadily, and avoid dangers caused by lane changes; take safety measures: take appropriate braking measures, warning reminders, and avoidance strategies according to the vehicle's driving status and obstacles.

9. A dual servo motor closed-loop control system for an automatic driving steering system, used to implement a dual servo motor closed-loop control method for an automatic driving steering system as described in any one of claims 1 to 8, characterized in that: It includes hardware architecture and software algorithm. The hardware architecture includes dual servo motors, controller module, sensor module, power module, communication module, electronic clutch, electronic brake, and mechanical structure. The software algorithm adopts PID control algorithm to realize closed-loop control of the dual servo motors according to the information feedback from the sensor and the driving status of the vehicle.

Images