Automatic driving control system and controller thereof

Abstract

The invention relates to the technical field of automatic driving, and discloses an automatic driving control system and a controller thereof, the system comprises a GNSS module, an I MU module, a sensor fusion module, a high-precision map matching module and an auxiliary positioning module, the GNSS module receives a positioning signal from a satellite; the I MU module is composed of an accelerometer and a gyroscope, the accelerometer measures the acceleration change of a vehicle in each axial direction, the gyroscope detects the angular velocity of the vehicle, the sensor fusion module receives data from the I MU module, pre-processes the data, allocates weights to the data according to the characteristics, precision and real-time performance of the data and the current driving state of the vehicle, and sends the data to the I MU module; the accurate vehicle position, attitude and speed obtained after fusion are output to a high-precision map matching module and an auxiliary positioning module of positioning data, the high-precision map matching module calibrates and refines positioning information fused by the sensor, and the auxiliary positioning module corrects an error source existing in positioning of the GNSS module.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving control system and a controller thereof. Background Art

[0002] With the continuous development of science and technology, the perfect integration of intelligence and automobiles is a hot topic in current research, and autonomous driving is also a current research and development trend. As the core of autonomous driving vehicles, the function coverage, reliability and stability of the autonomous driving controller determine the safety of autonomous driving. Therefore, efficient and high-quality testing is particularly important for autonomous driving controllers.

[0003] The existing Chinese patent with publication number CN112306042B discloses an automatic testing system and method for an autonomous driving controller. It introduces a scenario model and uses scenario restoration to make the autonomous driving adaptable to various driving scenarios with comprehensive test coverage. The system effectively performs key tests on the functions of the autonomous driving controller, improves the efficiency of the test process, enhances the product quality of the autonomous driving controller, and reduces labor costs. A corresponding LOG is formed for each test case, and the test LOG is automatically saved, which can guide developers to analyze the causes of problems based on the LOG playback timing diagram, thereby solving problems more efficiently. Automatic testing implemented through programming can be batch processed to make automatic testing more efficient.

[0004] Regarding the above-mentioned related technologies, when a vehicle encounters special circumstances during autonomous driving and needs to turn and change its route or change the originally designed route, the positioning system will have positioning deviations for a short period of time due to poor coordination, causing the vehicle to judge its own position inaccurately, resulting in a brief stagnation of the vehicle's positioning system. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic driving control system and a controller thereof, which adopts the device to work, thereby solving the problem that when a vehicle encounters a special situation during automatic driving and needs to turn and change the route or change the originally designed established route, the positioning system will have positioning deviations in a short period of time due to poor coordination, making the vehicle's own position inaccurate, causing the vehicle's positioning system to stagnate temporarily.

[0006] To achieve the above object, the present invention provides the following technical solution: an automatic driving control system, comprising a GNSS module: for receiving a positioning signal from a satellite;

[0007] IMU module: It consists of an accelerometer and a gyroscope. The accelerometer measures the acceleration changes of the vehicle in each axis, and the gyroscope is used to detect the angular velocity of the vehicle.

[0008] Sensor fusion module: used to receive data from the IMU module and perform preprocessing operations on the received IMU module. According to the characteristics, accuracy, real-time performance of the IMU module data and the current driving status of the vehicle, the IMU module data is weighted and the accurate vehicle position, posture and speed obtained after fusion are output to the high-precision map matching module and auxiliary positioning module of the positioning data.

[0009] High-precision map matching module: With the help of a high-precision map database, the positioning information after sensor fusion is calibrated and refined;

[0010] Auxiliary positioning module: corrects the error sources existing in GNSS module positioning.

[0011] Furthermore, the sensor fusion module includes a continuous monitoring and feedback adjustment module, a fusion algorithm parameter adjustment module, a real-time data fusion and positioning update module, and a driving state perception and prediction module:

[0012] Continuous monitoring and feedback adjustment module: When the vehicle is driving along the changed route, it continuously monitors the data of the IMU module and the actual driving status of the vehicle, and compares and analyzes the fused positioning information with the actual vehicle position;

[0013] Driving status perception and prediction module: When receiving the route change notification from the navigation system, it quickly determines the current driving status of the vehicle based on the data from the IMU module at the current moment;

[0014] Fusion algorithm parameter adjustment module: Based on the results of driving state perception and prediction, the key parameters in the data fusion algorithm are optimized in real time. It is predicted that the vehicle is about to make a large turn to change the route. In the extended Kalman filter and unscented Kalman filter, the weight of the gyroscope data for steering angle judgment is increased, so that it accounts for a larger proportion in the fusion calculation and captures the changes in vehicle posture.

[0015] Real-time data fusion and positioning update module: After adjusting the fusion algorithm parameters, continue to receive real-time data from the IMU module and perform data fusion calculations according to the optimized fusion strategy.

[0016] Furthermore, the algorithm of the extended Kalman filter is as follows:

[0017] Extended Kalman filter prediction equation:

[0018]

[0019] in, is the predicted value of the state at time k based on the state estimation at time k-1, is the estimated value of the state at time k-1, u k―1is the control input at time k-1, f is the state transfer function, P k|k―1 is the prediction covariance matrix, F k―1 is the partial derivative of the state transfer matrix with respect to the state, P k―1|k―1 is the state covariance matrix at time k-1, Q k―1 is the process noise covariance matrix;

[0020] Extended Kalman filter update equation:

[0021]

[0022] P k|k =(I-K k H k ) k|k―1 ;

[0023] Among them, K k is the Kalman gain, z k is the measured value at time k, h is the measurement function, H k is the measurement matrix, describing the relationship between the measurement value and the state vector, R k is the measurement noise covariance matrix, which represents the error characteristics of the measurement data itself, is the estimated value of the state at the moment, P k|k is the updated state covariance matrix, and I is the identity matrix.

[0024] Furthermore, the GNSS module uses the triangulation positioning principle to calculate the approximate geographical coordinates of the vehicle. The triangulation positioning principle is as follows: Assume the position coordinates of the satellite are (x i ,y i , z i ), the receiver’s position coordinates are (x, y, z), and the propagation time from the satellite signal to the receiver is t i , the propagation speed of radio waves c;

[0025] According to the distance formula, the distance from the satellite to the receiver is:

[0026] r i =c×t i

[0027] At the same time, according to the distance formula between two points in space:

[0028]

[0029] By simultaneously receiving signals from at least four satellites, the vehicle's position coordinates (x, y, z) can be obtained. The GNSS receiving module parses and processes the received satellite signals, and uses triangulation and other principles to calculate the approximate geographic location coordinates of the vehicle, and transmits this preliminary location information to the sensor fusion module. At the same time, it also passes some parameters related to the satellite signal quality to the sensor fusion module so that subsequent modules can judge the reliability of the data and the accuracy of positioning.

[0030] Furthermore, the IMU module is based on the measurement data generated by the accelerometer and the gyroscope. The IMU module can calculate the vehicle's posture and relative position in a short period of time through integration operations. The principle of the accelerometer is as follows: let the acceleration along a certain axis measured by the accelerometer be a(t), the initial time t 0 The speed is v 0 , after time t, the speed v(t) is calculated by integral operation:

[0031]

[0032] The calculation formula of displacement s(t) is also based on integration, based on velocity v(t):

[0033] s 0 is the initial position;

[0034] The IMU module will transmit the vehicle acceleration, angular velocity, posture, relative position change and other data obtained from the above measurements to the sensor fusion module in real time at certain time intervals, providing data support for vehicle dynamics for subsequent fusion processing.

[0035] Furthermore, the gyroscope measurement principle is as follows:

[0036] Assume the angular velocity measured by the gyroscope is w(t), and the initial angle θ 0 , after time t, the angle θ(t) is calculated as Based on these measurement data, the IMU module calculates the vehicle's posture and changes in relative position over a short period of time through integration operations and other methods. Especially when the satellite signal is temporarily interrupted or blocked, the IMU module can continue to calculate the vehicle's position based on the previously accumulated status, ensuring the continuity of positioning information and avoiding blank periods of positioning data. However, as time goes by, its integration operations will cause errors to accumulate continuously, so relying solely on it for a long time will reduce the accuracy of positioning.

[0037] Furthermore, the high-precision map matching module will match and compare the current positioning information of the vehicle with the map data, and perform calculations using a common map matching algorithm. The calculation principle is as follows:

[0038] Assume that the position coordinates obtained by vehicle positioning are (x, y), and the road node coordinates on the high-precision map are (x i ,y i ) and the corresponding road topology information, first calculate the distance d from the vehicle position to each road node i , using the Euclidean distance formula: After receiving the vehicle position, posture and other positioning information from the sensor fusion module, the high-precision map matching module matches and compares this information with the high-precision map data stored in itself, and determines the road and specific location where the vehicle is most likely to be located by calculating the distance from the vehicle position to each road node, combining road weights, and using probability-based map matching algorithms. The module further calibrates the vehicle's precise position on the map, and feeds back key positioning results such as the precise position information and vehicle lane information after map matching calibration to the vehicle's navigation system and other application modules that need to use positioning data.

[0039] Furthermore, the auxiliary positioning module receives differential correction data from ground base stations and network transmissions, and compares it with the original positioning data obtained by the GNSS receiving module to reduce the positioning deviation caused by satellite signal errors and atmospheric refraction. The principle is as follows:

[0040] Assume the coordinates of the base station are (x b ,y b , z b ), the pseudorange calculated by the received satellite signal is The pseudorange received by the vehicle from the same satellite is

[0041]

[0042]

[0043] in and They are the pseudo-range errors caused by satellite clock error and atmospheric refraction at the base station and vehicle respectively;

[0044] Differential positioning is to calculate the difference Δp between the two pseudo-ranges i To eliminate the common error part:

[0045] And then you will get the exact coordinates.

[0046] Further, the auxiliary positioning module includes a wheel speed odometer module and a zero speed determination module;

[0047] The wheel speed odometer module provides the positioning system with the vehicle's travel distance and speed based on the vehicle's own mechanical motion characteristics. It detects the rotation speed of the wheel through the sensor. When the wheel rotates, the sensor generates a corresponding pulse signal, and its pulse frequency is proportional to the wheel rotation speed. The basic principle is as follows:

[0048] S = 2πrN, s represents the distance traveled by the vehicle, r is the wheel radius, and N is the number of revolutions of the wheel; assuming that m pulses are generated per revolution, the travel distance can be expressed as

[0049] The zero speed determination module performs different operations and processing on the auxiliary positioning system in different states according to the vehicle's motion state information. Its working principle is as follows:

[0050] Set a speed threshold v th When the speed v measured by the wheel speed odometer module is lower than the threshold, the vehicle is considered to be stationary, that is, v <v th , make a simple judgment on the wheel speed;

[0051] When the zero-speed determination module determines that the vehicle is stationary, it will notify other positioning modules to enter the corresponding low-power or calibration mode to avoid unnecessary calculations and error accumulation. When the vehicle stops and waits for traffic lights, the IMU module can suspend some complex integral operations to prevent error accumulation caused by long-term stationary state; the sensor fusion module can suspend unnecessary data fusion operations to reduce computing resource consumption. When the vehicle restarts and enters the driving state, the zero-speed determination module can detect the state change in time and notify other modules to resume normal work, so that the positioning system can quickly resume the normal positioning information collection and processing process, ensuring the accuracy and continuity of positioning information during the transition from stationary to driving.

[0052] In some scenarios, when the global satellite navigation system signal is weak or temporarily unavailable, the wheel speed odometer module can provide the vehicle's travel distance and speed information, assist other positioning modules in estimating the vehicle's position, and integrate the data from modules such as the IMU to jointly determine the vehicle's position. It can verify each other with other positioning information, and by comparing speed and position information from different sources, it can be used to detect whether there are any abnormalities in the positioning system.

[0053] Furthermore, a controller comprises an automatic driving control system as described in any one of claims 1-9.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention proposes an automatic driving control system, which can ensure the real-time and continuity of positioning information. During the route change process, the vehicle's driving state is changeable. The sensor fusion module optimizes the fusion algorithm and dynamically adjusts the weight and fusion strategy of each sensor data according to the real-time driving state of the vehicle, so that the data of different sensors can be efficiently coordinated. When the vehicle turns to change the route, the I The weight of MU data for posture judgment allows the positioning system to quickly and accurately track vehicle posture and position changes, so that the navigation system can always guide the vehicle forward based on the latest accurate position. At the same time, the use of extended Kalman filtering and unscented Kalman filtering for fusion processing overcomes the limitations of a single sensor. Through fusion, it can output more accurate status information of vehicle position, posture and speed, avoiding stagnation caused by repeated adjustments and re-planning of navigation due to inaccurate positioning. By perceiving and predicting the vehicle's driving status in advance, the sensor fusion module can adjust the fusion algorithm parameters in advance to prepare for the upcoming route changes, so that the entire positioning system can adapt to the new driving route requirements more quickly. When the navigation system issues a route change instruction, the positioning information can be quickly updated and passed to the navigation, reducing the system response delay caused by positioning adjustment, avoiding navigation jams and stagnation, and ensuring that the vehicle can travel along the new route in a timely and smooth manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the driving operation steps of a vehicle in the prior art;

[0057] Figure 2 It is a schematic diagram of a controller module of the present invention;

[0058] Figure 3 This is a schematic diagram of the operation flow of the controller module of the present invention;

[0059] Figure 4 It is a front structural schematic diagram of the controller of the present invention;

[0060] Figure 5 It is a bottom view structural schematic diagram of the controller of the present invention. DETAILED DESCRIPTION

[0061] 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.

[0062] In order to solve the problem that in an existing automatic driving control system, when a vehicle encounters a special situation during the automatic driving process and needs to turn and change the route or change the originally designed established route, the positioning system will have positioning deviations in a short period of time due to poor coordination, making the vehicle's judgment of its own position inaccurate, causing the vehicle's positioning system to stagnate temporarily, such as Figure 1-Figure 5 As shown, the following preferred technical solutions are provided:

[0063] An automatic driving control system includes a GNSS module: for receiving a positioning signal from a satellite;

[0064] IMU module: It consists of an accelerometer and a gyroscope. The accelerometer measures the acceleration changes of the vehicle in each axis, and the gyroscope is used to detect the angular velocity of the vehicle.

[0065] Sensor fusion module: used to receive data from the IMU module and perform preprocessing operations on the received IMU module. According to the characteristics, accuracy, real-time performance of the IMU module data and the current driving status of the vehicle, the IMU module data is weighted and the accurate vehicle position, posture and speed obtained after fusion are output to the high-precision map matching module and auxiliary positioning module of the positioning data.

[0066] High-precision map matching module: With the help of a high-precision map database, the positioning information after sensor fusion is calibrated and refined;

[0067] Auxiliary positioning module: corrects the error sources existing in GNSS module positioning.

[0068] The sensor fusion module includes a continuous monitoring and feedback adjustment module, a fusion algorithm parameter adjustment module, a real-time data fusion and positioning update module, and a driving status perception and prediction module:

[0069] Continuous monitoring and feedback adjustment module: When the vehicle is driving along the changed route, it continuously monitors the data of the IMU module and the actual driving status of the vehicle, and compares and analyzes the fused positioning information with the actual vehicle position;

[0070] Driving status perception and prediction module: When receiving the route change notification from the navigation system, it quickly determines the current driving status of the vehicle based on the data from the IMU module at the current moment;

[0071] Fusion algorithm parameter adjustment module: Based on the results of driving state perception and prediction, the key parameters in the data fusion algorithm are optimized in real time. It is predicted that the vehicle is about to make a large turn to change the route. In the extended Kalman filter and unscented Kalman filter, the weight of the gyroscope data for steering angle judgment is increased, so that it accounts for a larger proportion in the fusion calculation and captures the changes in vehicle posture.

[0072] Real-time data fusion and positioning update module: After adjusting the fusion algorithm parameters, continue to receive real-time data from the IMU module and perform data fusion calculations according to the optimized fusion strategy;

[0073] The algorithm of the extended Kalman filter is as follows:

[0074] Extended Kalman filter prediction equation:

[0075]

[0076] in, is the predicted value of the state at time k based on the state estimation at time k-1, is the estimated value of the state at time k-1, u k―1 is the control input at time k-1, f is the state transfer function, P k|k―1 is the prediction covariance matrix, F k―1 is the partial derivative of the state transfer matrix with respect to the state, P k―1|k―1 is the state covariance matrix at time k-1, Q k―1 is the process noise covariance matrix;

[0077] Extended Kalman filter update equation:

[0078]

[0079] P k|k =(I-K k H k ) k|k―1 ;

[0080] Among them, K k is the Kalman gain, z k is the measured value at time k, h is the measurement function, H k is the measurement matrix, describing the relationship between the measurement value and the state vector, R k is the measurement noise covariance matrix, which represents the error characteristics of the measurement data itself, is the estimated value of the state at the moment, P k|k is the updated state covariance matrix, and I is the identity matrix.

[0081] The GNSS module uses the triangulation positioning principle to calculate the approximate geographic location coordinates of the vehicle. The triangulation positioning principle is as follows: Let the satellite position coordinates be (x i ,y i , z i ), the receiver’s position coordinates are (x, y, z), and the propagation time from the satellite signal to the receiver is t i , the propagation speed of radio waves c;

[0082] According to the distance formula, the distance from the satellite to the receiver is:

[0083] r i =c×t i

[0084] At the same time, according to the distance formula between two points in space:

[0085]

[0086] By receiving signals from at least four satellites at the same time, the vehicle's position coordinates (x, y, z) can be obtained. The GNSS receiving module analyzes and processes the received satellite signals, and uses triangulation and other principles to calculate the approximate geographical coordinates of the vehicle, and transmits this preliminary position information to the sensor fusion module. At the same time, it will also pass some parameters related to the quality of satellite signals to the sensor fusion module so that subsequent modules can judge the reliability of the data and the accuracy of positioning.

[0087] Based on the measurement data generated by the accelerometer and gyroscope, the IMU module can calculate the vehicle's posture and relative position in a short period of time through integration operations. The principle of the accelerometer is as follows: Let the acceleration along a certain axis measured by the accelerometer be a(t), and the initial time t 0 The speed is v 0 , after time t, the speed v(t) is calculated by integral operation:

[0088]

[0089] The calculation formula of displacement s(t) is also based on integration, based on velocity v(t):

[0090] s 0 is the initial position;

[0091] The IMU module will transmit the vehicle acceleration, angular velocity, posture, relative position change and other data obtained from the above measurements to the sensor fusion module in real time at certain time intervals, providing data support for vehicle dynamics for subsequent fusion processing.

[0092] The gyroscope measurement principle is as follows:

[0093] Assume the angular velocity measured by the gyroscope is w(t), and the initial angle θ 0 , after time t, the angle θ(t) is calculated as Based on these measurement data, the IMU module calculates the vehicle's posture and changes in relative position over a short period of time through integration operations and other methods. Especially when the satellite signal is temporarily interrupted or blocked, the IMU module can continue to calculate the vehicle's position based on the previously accumulated status, ensuring the continuity of positioning information and avoiding blank periods of positioning data. However, as time goes by, its integration operations will cause errors to accumulate continuously, so relying solely on it for a long time will reduce the accuracy of positioning.

[0094] The high-precision map matching module will match and compare the vehicle's current positioning information with the map data and perform calculations using the commonly used map matching algorithm. The calculation principle is as follows:

[0095] Assume that the position coordinates obtained by vehicle positioning are (x, y), and the road node coordinates on the high-precision map are (x i ,y i ) and the corresponding road topology information, first calculate the distance d from the vehicle position to each road node i , using the Euclidean distance formula: After receiving the vehicle position, posture and other positioning information from the sensor fusion module, the high-precision map matching module matches and compares this information with the high-precision map data stored in itself, and determines the road and specific location where the vehicle is most likely to be located by calculating the distance from the vehicle position to each road node, combining road weights, and using probability-based map matching algorithms. The module further calibrates the vehicle's precise position on the map, and feeds back key positioning results such as the precise position information and vehicle lane information after map matching calibration to the vehicle's navigation system and other application modules that need to use positioning data.

[0096] The auxiliary positioning module receives differential correction data from ground base stations and network transmissions, and compares it with the original positioning data obtained by the GNSS receiving module to reduce positioning deviations caused by satellite signal errors and atmospheric refraction. The principle is as follows:

[0097] Assume the coordinates of the base station are (x b ,y b , z b ), the pseudorange calculated by the received satellite signal is The pseudorange received by the vehicle from the same satellite is

[0098]

[0099] in and They are the pseudo-range errors caused by satellite clock error and atmospheric refraction at the base station and vehicle respectively;

[0100] Differential positioning is to calculate the difference Δp between the two pseudo-ranges i To eliminate the common error part:

[0101] And then you will get the exact coordinates.

[0102] The auxiliary positioning module includes a wheel speed odometer module and a zero speed determination module;

[0103] The wheel speed odometer module provides the positioning system with the vehicle's travel distance and speed based on the vehicle's own mechanical motion characteristics. It detects the rotation speed of the wheel through the sensor. When the wheel rotates, the sensor generates a corresponding pulse signal, and its pulse frequency is proportional to the wheel rotation speed. The basic principle is as follows:

[0104] S = 2πrN, s represents the distance traveled by the vehicle, r is the wheel radius, and N is the number of revolutions of the wheel; assuming that m pulses are generated per revolution, the travel distance can be expressed as

[0105] The zero speed determination module performs different operations and processing on the auxiliary positioning system in different states according to the vehicle's motion state information. Its working principle is as follows:

[0106] Set a speed threshold v th When the speed v measured by the wheel speed odometer module is lower than the threshold, the vehicle is considered to be stationary, that is, v <v th , make a simple judgment on the wheel speed;

[0107] When the zero-speed determination module determines that the vehicle is stationary, it will notify other positioning modules to enter the corresponding low-power or calibration mode to avoid unnecessary calculations and error accumulation. When the vehicle stops and waits for traffic lights, the IMU module can suspend some complex integral operations to prevent error accumulation caused by long-term stationary state; the sensor fusion module can suspend unnecessary data fusion operations to reduce computing resource consumption. When the vehicle restarts and enters the driving state, the zero-speed determination module can detect the state change in time and notify other modules to resume normal work, so that the positioning system can quickly resume the normal positioning information collection and processing process, ensuring the accuracy and continuity of positioning information during the transition from stationary to driving.

[0108] In some scenarios, when the global satellite navigation system signal is weak or temporarily unavailable, the wheel speed odometer module can provide the vehicle's travel distance and speed information, assist other positioning modules in estimating the vehicle's position, and integrate the data with the IMU and other modules to jointly determine the vehicle's position. It can verify each other with other positioning information, and by comparing the speed and position information from different sources, it can be used to detect whether there are any abnormalities in the positioning system.

[0109] A controller includes an automatic driving control system. The entire controller is a rectangular parallelepiped, about 205 mm long, about 190 mm wide, and about 57 mm high. It has a beautiful and simple appearance, is small and light, and is easy to install and place.

[0110] It should be noted that, in the description of the present application, it should be understood that the terms "length", "thickness", "inside", "outside", "axial", "radial", etc., indicating orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0111] In addition, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises", or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0112] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An automatic driving control system, characterized in that: include GNSS module: used to receive positioning signals from satellites; IMU module: It consists of an accelerometer and a gyroscope. The accelerometer measures the acceleration changes of the vehicle in each axis, and the gyroscope is used to detect the angular velocity of the vehicle. Sensor fusion module: used to receive data from the IMU module and perform preprocessing operations on the received IMU module. According to the characteristics, accuracy, real-time performance of the IMU module data and the current driving status of the vehicle, the sensor fusion module assigns weights to the IMU module data and outputs the accurate vehicle position, posture and speed obtained after fusion to the high-precision map matching module and auxiliary positioning module of the positioning data. High-precision map matching module: With the help of a high-precision map database, the positioning information after sensor fusion is calibrated and refined; Auxiliary positioning module: corrects the error sources existing in GNSS module positioning.

2. An automatic driving control system according to claim 1, characterized in that: The sensor fusion module includes a continuous monitoring and feedback adjustment module, a fusion algorithm parameter adjustment module, a real-time data fusion and positioning update module, and a driving state perception and prediction module: Continuous monitoring and feedback adjustment module: When the vehicle is driving along the changed route, it continuously monitors the data of the IMU module and the actual driving status of the vehicle, and compares and analyzes the fused positioning information with the actual vehicle position; Driving status perception and prediction module: When receiving the route change notification from the navigation system, the current driving status of the vehicle is quickly determined based on the data from the IMU module at the current moment; Fusion algorithm parameter adjustment module: Based on the results of driving state perception and prediction, the key parameters in the data fusion algorithm are optimized in real time. It is predicted that the vehicle is about to make a large turn to change the route. In the extended Kalman filter and unscented Kalman filter, the weight of the gyroscope data for steering angle judgment is increased, so that it accounts for a larger proportion in the fusion calculation and captures the changes in vehicle posture. Real-time data fusion and positioning update module: After adjusting the fusion algorithm parameters, continue to receive real-time data from the IMU module and perform data fusion calculations according to the optimized fusion strategy.

3. An automatic driving control system according to claim 2, characterized in that: The algorithm of the extended Kalman filter is as follows: Extended Kalman filter prediction equation: in, is the predicted value of the state at time k based on the state estimation at time k-1, is the estimated value of the state at time k-1, u k―1 is the control input at time k-1, f is the state transfer function, P k|k―1 is the prediction covariance matrix, F k―1 is the partial derivative of the state transfer matrix with respect to the state, P k―1|k―1 is the state covariance matrix at time k-1, Q k―1 is the process noise covariance matrix; Extended Kalman filter update equation: P k|k =(I―K k H k )P k|k―1 ; Among them, K k is the Kalman gain, z k is the measured value at time k, h is the measurement function, H k is the measurement matrix, describing the relationship between the measurement value and the state vector, R k is the measurement noise covariance matrix, which represents the error characteristics of the measurement data itself, is the estimated value of the state at the moment, P k|k is the updated state covariance matrix, and I is the identity matrix.

4. The automatic driving control system according to claim 1, characterized in that: The GNSS module uses the triangulation positioning principle to calculate the approximate geographic location coordinates of the vehicle. The triangulation positioning principle is as follows: Assume the position coordinates of the satellite are (x i ,y i , z i ), the receiver’s position coordinates are (x, y, z), and the propagation time from the satellite signal to the receiver is t i , the propagation speed of radio waves c; According to the distance formula, the distance from the satellite to the receiver is: r i =c×t i At the same time, according to the distance formula between two points in space: By simultaneously receiving signals from at least 4 satellites, the vehicle's position coordinates (x, y, z) can be obtained.

5. The automatic driving control system according to claim 1, characterized in that: The IMU module is based on the measurement data generated by the accelerometer and gyroscope. The IMU module can calculate the vehicle's posture and relative position in a short period of time through integration operations. The principle of the accelerometer is as follows: Assume that the acceleration along a certain axis measured by the accelerometer is a(t), and the velocity at the initial time t0 is v0. After t time, the velocity v(t) is calculated by the integral operation: The calculation formula of displacement s(t) is also based on integration, based on velocity v(t): s0 is the initial position.

6. An automatic driving control system according to claim 5, characterized in that: The gyroscope measurement principle is as follows: Assume the angular velocity measured by the gyroscope is w(t), the initial angle is θ0, and after time t, the angle θ(t) is calculated by:

7. The automatic driving control system according to claim 1, characterized in that: The high-precision map matching module will match and compare the vehicle's current positioning information with the map data and calculate it through a map matching algorithm. The algorithm formula is as follows: Assume that the position coordinates obtained by vehicle positioning are (x, y), and the road node coordinates on the high-precision map are (x i ,y i ) and the corresponding road topology information, first calculate the distance d from the vehicle position to each road node i , using the Euclidean distance formula:

8. The automatic driving control system according to claim 1, characterized in that: The auxiliary positioning module receives differential correction data from ground base stations and network transmissions, and compares it with the original positioning data obtained by the GNSS receiving module to reduce the positioning deviation caused by satellite signal errors and atmospheric refraction. The correction data algorithm is as follows: Assume the coordinates of the base station are (x b ,y b , z b ), the pseudorange calculated by the received satellite signal is The pseudorange received by the vehicle from the same satellite is in and They are the pseudo-range errors caused by satellite clock error and atmospheric refraction at the base station and vehicle respectively; Differential positioning is to calculate the difference Δp between the two pseudo-ranges i To eliminate the common error part: And then get the accurate coordinates.

9. An automatic driving control system according to claim 8, characterized in that: The auxiliary positioning module includes a wheel speed odometer module and a zero speed determination module; Wheel speed odometer module: Based on the mechanical motion characteristics of the vehicle itself, it provides the positioning system with the distance and speed of the vehicle. The sensor detects the rotation speed of the wheel. When the wheel rotates, the sensor generates a pulse signal, and its pulse frequency is proportional to the rotation speed of the wheel. The calculation formula is as follows: S = 2πrN, s is the distance traveled by the vehicle, r is the wheel radius, and N is the number of revolutions of the wheel; The zero-speed determination module performs different operations and processing on the auxiliary positioning system in different states according to the vehicle's motion state information. The calculation formula is as follows: Set a speed threshold v th When the speed v measured by the wheel speed odometer module is lower than the threshold, the vehicle is considered to be stationary, that is, v <v th , make a simple judgment on the wheel speed.

10. A controller, characterized in that: Comprising an automatic driving control system as described in any one of claims 1-9.

Images