Tracking reversing method, device and equipment of vehicle, storage medium and program product

Abstract

The invention relates to the technical field of vehicle control, and discloses a tracking reversing method, device and equipment of a vehicle, a storage medium and a program product. The method comprises the following steps: acquiring inertial attitude data at an initial moment; determining inertial attitude data at a target moment according to historical positioning information and the inertial attitude data at the initial moment, and predicting position information; if the absolute positioning information of the target moment is obtained, the inertial attitude data of the target moment, the predicted position information of the target moment and the absolute positioning information of the target moment are fused, the position information of the vehicle at each moment is determined, and a target reversing path of the vehicle is determined according to the position information of the vehicle at each moment; and adjusting the actual position of the vehicle according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle so as to enable the vehicle to perform tracking reversing.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle tracking and reversing method, device, equipment, storage medium and program product. Background Art

[0002] In modern road traffic environments, reversing is an essential driving operation, especially in narrow roads or complex environments, such as narrow parking spaces, narrow alleys, or sites with a large number of obstacles. However, these environments often place high demands on the driver's technical level and spatial perception ability.

[0003] At present, it is often difficult for drivers to accurately judge the position and direction of the vehicle by intuition, especially when there is a lack of sufficient vision, reversing becomes more difficult. In addition, due to the lack of sufficient spatial perception, drivers are prone to collision with surrounding obstacles when reversing, which increases the risk of vehicle damage and even personal injury.

[0004] Furthermore, traditional reversing operations rely more on the driver's personal experience and skills, and novice drivers may find it difficult to master the correct reversing skills, and reversing in narrow roads or complex environments is a difficult problem. Summary of the invention

[0005] In view of this, the present invention provides a vehicle tracking and reversing method, device, equipment, storage medium and program product.

[0006] In a first aspect, the present invention provides a vehicle tracking and reversing method, the method comprising: acquiring inertial posture data at an initial moment; determining the inertial posture data and predicted position information at a target moment based on historical positioning information and the inertial posture data at an initial moment; if absolute positioning information at the target moment is acquired, fusing the inertial posture data at the target moment, the predicted position information at the target moment, and the absolute positioning information at the target moment to determine the position information of the vehicle at each moment, and determining the target reversing path of the vehicle based on the position information of the vehicle at each moment; adjusting the actual position of the vehicle based on the deviation between the target reversing path of the vehicle and the actual position information of the vehicle so that the vehicle can perform tracking and reversing.

[0007] The vehicle tracking and reversing method provided in this embodiment can accurately determine the vehicle position and direction at multiple times by acquiring the vehicle's inertial posture data and absolute positioning information, thereby solving the limitations of the driver's intuitive judgment. At the same time, by determining the deviation between the target reversing path and the vehicle's position during the actual driving process, the actual position of the vehicle is adjusted, and automatic calculation and path planning can be performed, reducing the dependence on the driver's experience and skills, so that even novice drivers can reverse safely and accurately in narrow road conditions or complex environments.

[0008] In one possible implementation, a target reversing path of the vehicle is determined based on multiple inertial posture data, multiple absolute positioning information, and historical positioning information of the vehicle, including: determining the position information of the vehicle at each moment through a Kalman wave algorithm based on the multiple inertial posture data, multiple absolute positioning information, and historical positioning information of the vehicle; determining multiple initial reversing paths based on the position information of the vehicle at each moment and environmental constraints; and determining a target reversing path that meets preset conditions from the multiple initial reversing paths.

[0009] The vehicle tracking and reversing method provided in this embodiment can fuse the vehicle's inertial posture data and absolute positioning information through the Kalman filter algorithm. The inertial posture data and absolute positioning information are complementary and can provide more comprehensive and accurate vehicle position information. At the same time, the Kalman filter algorithm can update the vehicle's position information in real time according to new observation data through prediction and update steps, thereby realizing real-time tracking and prediction of the vehicle's position. In addition, by combining the vehicle's position information and environmental constraints, the method can generate multiple possible initial reversing paths. Among the multiple initial paths, the optimal target reversing path is selected according to preset conditions to ensure the safety and efficiency of the reversing process.

[0010] In one possible implementation, the actual position information of the vehicle includes: a driving position and a driving direction; wherein, the actual position of the vehicle is adjusted according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle, including: determining the target position and target direction corresponding to the target moment from the target reversing path according to the driving position and the driving direction; determining a position deviation value according to the driving position and the target position, and determining a direction deviation value according to the driving direction and the target direction; and controlling the vehicle to make adjustments according to the position deviation value and the direction deviation value.

[0011] The vehicle tracking and reversing method provided in this embodiment can accurately identify the position deviation and direction deviation by accurately calculating the target position and target direction corresponding to the target time and comparing them with the actual driving position and driving direction. According to these deviation values, the vehicle can be controlled and adjusted in a targeted manner, thereby improving the accuracy and efficiency of reversing. In addition, by accurately calculating and adjusting the position and direction of the vehicle, the method can effectively avoid the risk of collision with surrounding obstacles or other vehicles. This is particularly important for reversing in narrow or complex environments, and can significantly improve driving safety.

[0012] In a possible implementation, the method further includes: while the vehicle is traveling along a target reversing path, detecting whether there is an obstacle on the target reversing path; if there is an obstacle on the target reversing path, obtaining the state of the obstacle; if the state of the obstacle is a stationary state, detecting whether the obstacle exists on the route of the target reversing path; if the obstacle exists on the route of the target reversing path, adjusting the target reversing path so that the vehicle avoids the obstacle.

[0013] The vehicle tracking and reversing method provided in this embodiment can detect in real time whether there are obstacles on the target reversing path during the reversing process, so as to timely discover potential dangers and avoid collisions with obstacles. For obstacles in a stationary state, it is detected whether the obstacles exist on the route of the target reversing path. If the obstacles exist on the route of the target reversing path, a safe reversing path is planned to ensure that the vehicle can smoothly bypass the obstacles.

[0014] In a possible implementation, if the state of the obstacle is a moving state, the vehicle reversing action is stopped.

[0015] The vehicle tracking and reversing method provided in this embodiment stops the vehicle reversing action when the obstacle is in a moving state, thereby ensuring safety.

[0016] In a second aspect, the present invention provides a vehicle tracking and reversing device, which includes: an acquisition module, used to acquire inertial posture data at an initial moment; a first determination module, used to determine the inertial posture data and predicted position information at a target moment based on historical positioning information and the inertial posture data at an initial moment; a second determination module, used to, if the absolute positioning information at the target moment is acquired, fuse the inertial posture data at the target moment, the predicted position information at the target moment, and the absolute positioning information at the target moment, to determine the position information of the vehicle at each moment, and determine the target reversing path of the vehicle based on the position information of the vehicle at each moment; a tracking and reversing module, used to adjust the actual position of the vehicle based on the deviation between the target reversing path of the vehicle and the actual position information of the vehicle, so that the vehicle can perform tracking and reversing.

[0017] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the vehicle tracking and reversing method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the vehicle tracking and reversing method of the first aspect or any corresponding embodiment thereof.

[0019] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the vehicle tracking and reversing method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 is a schematic diagram of a vehicle tracking and reversing system provided in an embodiment of the present invention;

[0022] Figure 2 is a schematic flow chart of a vehicle tracking and reversing method according to an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of a vehicle tracking backing method according to an embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of a vehicle tracking backing method according to an embodiment of the present invention;

[0025] Figure 5 is a structural block diagram of a vehicle tracking and reversing device according to an embodiment of the present invention;

[0026] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] Based on relevant technologies, it is known that in modern road traffic environments, reversing is an essential driving operation, especially in narrow road conditions or complex environments, such as narrow parking spaces, narrow alleys, or sites with a large number of obstacles. However, these environments often place high demands on the driver's technical level and spatial perception ability.

[0029] At present, it is often difficult for drivers to accurately judge the position and direction of the vehicle by intuition, especially when there is a lack of sufficient vision, reversing becomes more difficult. In addition, due to the lack of sufficient spatial perception, drivers are prone to collision with surrounding obstacles when reversing, which increases the risk of vehicle damage and even personal injury.

[0030] Furthermore, traditional reversing operations rely more on the driver's personal experience and skills, and novice drivers may find it difficult to master the correct reversing skills, and reversing in narrow roads or complex environments is a difficult problem.

[0031] Based on this, the present invention provides a vehicle tracking reversing method, which can accurately calculate the vehicle position and direction at multiple times by acquiring the vehicle's inertial posture data and absolute positioning information, thereby solving the limitations of the driver's intuitive judgment. At the same time, by determining the deviation between the target reversing path and the position of the vehicle during the actual driving process, the actual position of the vehicle is adjusted, and the calculation and path planning can be automated, reducing the dependence on the driver's experience and skills, so that even novice drivers can reverse safely and accurately in narrow road conditions or complex environments.

[0032] Please refer to Figure 1 , Figure 1 Schematic diagram of a vehicle tracking and reversing system provided according to an embodiment of the present invention.

[0033] The vehicle tracking and reversing system may include: a main controller, an environmental detection sensor, and a heading sensor. The heading sensor includes: a three-axis gyroscope, an accelerometer, a magnetometer and other core components. These components work together to provide the measured object with attitude information such as heading, pitch and roll angle.

[0034] More specifically, the main controller can receive the absolute positioning information sent by the Beidou satellite and the inertial attitude data sent by the heading sensor, and then fuse the absolute positioning information and the inertial attitude data sent by the heading sensor to obtain the target reversing path.

[0035] The main controller can also receive the vehicle's environmental information and the vehicle's obstacle information through the environmental detection sensor. The main controller determines the target reversing path based on the absolute positioning information and the inertial attitude data sent by the heading sensor, combined with the vehicle's environmental information, and adjusts the target reversing path based on the obstacle information.

[0036] According to an embodiment of the present invention, an embodiment of a vehicle tracking and reversing method 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.

[0037] In this embodiment, a vehicle tracking and reversing method is provided, which can be used for the above-mentioned vehicle tracking and reversing system. Figure 2 is a flow chart of a vehicle tracking and reversing method according to an embodiment of the present invention, such as Figure 2 As shown, the process includes the following steps:

[0038] Step S101, obtaining inertial posture data at an initial moment.

[0039] Inertial attitude data can refer to acceleration, angular velocity and other data obtained by the vehicle through an inertial navigation system (such as IMU), which is used to calculate the vehicle's real-time attitude (such as pitch angle, yaw angle, roll angle) and relative position change. Absolute positioning information can be the vehicle's global position information obtained by satellite navigation systems such as Beidou or base station positioning technologies, including longitude, latitude, altitude, etc. The vehicle's inertial attitude data and absolute positioning information can be collected through the vehicle's inertial navigation system and satellite navigation system.

[0040] Step S102, determining the inertial posture data and predicted position information at the target time according to the historical positioning information and the inertial posture data at the initial time.

[0041] Historical positioning information can represent the location information record of the vehicle at past moments, and can come from GPS, inertial navigation or other positioning systems. Taking inertial attitude data, absolute positioning information and historical positioning information as input, the Kalman filter algorithm is used to estimate the vehicle's location information to obtain the optimal position estimate of the vehicle at each moment. The Kalman filter algorithm comprehensively considers the current measurement value (absolute positioning information and inertial attitude data) and the estimated value at the previous moment (including historical positioning information) to minimize the error of the position estimate.

[0042] As an example, the Kalman filter algorithm can be set to run continuously to update the vehicle's position information in real time. The parameters of the Kalman filter algorithm (such as the covariance matrix of process noise and measurement noise) can be dynamically adjusted according to the vehicle's motion state and environmental changes to improve the accuracy of the position estimate. The robustness of the position estimate can be enhanced by combining other sensor data (such as cameras, radars, lidars, etc.), which can be input into the Kalman filter algorithm as additional measurements.

[0043] For example, when a vehicle is reversing, the inertial navigation system provides the acceleration and angular velocity data of the vehicle, the GPS system provides the latitude and longitude information of the vehicle, and the system also saves the location record of the vehicle in the past period of time (historical positioning information). Through the Kalman filter algorithm, these data are integrated to obtain the optimal position estimate of the vehicle at each moment. This estimate takes into account both the current measurement data and the historical position information.

[0044] The target moment can be any moment in the next reversing process, among which the next moment of the initial moment can be determined by the historical positioning information and the inertial posture data of the initial moment, and the next moment of the next moment of the initial moment can be determined according to the data determined at the next moment, thereby determining the position of all moments.

[0045] As an example, the process of determining the vehicle's position information at each moment is: determine the predicted positioning information at the next moment, combine the absolute positioning information, predicted positioning information, and inertial posture information at the next moment, and then determine the predicted positioning information and inertial posture information at the next moment. That is, at the very beginning, predict the first predicted positioning information and predicted inertial posture data through the vehicle's inertial posture data and historical positioning information, and then determine the inertial posture data and absolute positioning information at the next moment based on the predicted positioning information and inertial posture data combined with the absolute positioning information, and repeat the process until all position points from the beginning to the end are determined.

[0046] That is, using the initial inertial posture data and historical positioning information, through a certain prediction algorithm (such as Kalman filtering, machine learning model, etc.), the positioning information (predicted positioning information) and inertial posture data (predicted inertial posture data) at the first moment are predicted.

[0047] For each of the following moments:

[0048] Q1, prediction: Based on the predicted positioning information and predicted inertial posture data of the previous moment, the prediction algorithm is used again to predict the positioning information and inertial posture data of the next moment.

[0049] Q2, correction: when new absolute positioning information (such as real-time positioning information obtained through GPS or other sensors) is available, it is compared with the predicted positioning information, and the absolute positioning information and inertial attitude data at the current moment are updated and determined through a correction algorithm (such as error correction, data fusion, etc.). Q3, iteration: the corrected absolute positioning information and inertial attitude data are used as input for the next moment prediction, and the above prediction and correction process is repeated until all position points from the beginning to the end are determined.

[0050] Step S103, if the absolute positioning information at the target moment is obtained, the inertial posture data at the target moment, the predicted position information at the target moment, and the absolute positioning information at the target moment are integrated to determine the position information of the vehicle at each moment, and the target reversing path of the vehicle is determined based on the position information of the vehicle at each moment.

[0051] The inertial posture data and absolute positioning information are input into the path planning algorithm, and the target reversing path is calculated in combination with the starting position and destination of the vehicle. Specifically, the path planning algorithm can be a map-based algorithm or a sensor-based algorithm. Kalman filtering, particle filtering and other algorithms can be used to fuse inertial posture data and absolute positioning information to improve the accuracy of path planning. The path planning algorithm can also take into account the dynamic characteristics of the vehicle, such as turning radius, braking distance, etc., which are not specifically limited here and can be implemented by those skilled in the art.

[0052] In a possible implementation, if the absolute positioning information at the target time is not obtained, the position information of the vehicle at each time is determined based on the position information at the target time and the absolute positioning information at the target time.

[0053] When the absolute positioning information at the target time cannot be obtained, the vehicle's position is predicted or updated based on the data and historical positioning information provided by the inertial navigation system and possible motion models. This improves the anti-interference capability of BDS-SPP and reduces positioning errors, which can help passenger cars provide positioning in the absence of RTK links. When the BDS signal is blocked or interfered with, INS can provide continuous position and attitude information in a short time, ensuring the stability and continuity of the reversing trajectory, and is suitable for complex loops such as parking lots or narrow alleys.

[0054] Please refer to Figure 3 , Figure 3 It is a schematic diagram of a vehicle tracking and reversing method provided according to an embodiment of the present invention.

[0055] As an example, combining Figure 3 As shown in the figure, the fusion positioning method (Kalman Filter Fusion) based on the AHRS and BDS-SPP sensor information fusion Kalman Filter method (Kalman Filter Fusion) can provide sufficient accuracy for recording the vehicle's driving path. In the scenario of tracking and reversing, accurate reversing path tracking can be achieved based on the vehicle's historical driving trajectory.

[0056] The specific fusion positioning method is to estimate a signal with higher confidence from a signal with error by establishing a physical system model and using a filtering algorithm, and then correct the inertial navigation system with the obtained error estimate.

[0057] The Kalman filter algorithm can be based on two assumptions: the information process is model-based and excited by white noise; each measurement signal contains an additional white noise component. For systems that meet these conditions, the Kalman filter is the optimal information fusion. The process of the Kalman filter algorithm includes 5 core update iteration formulas.

[0058] Extrapolate state variables forward:

[0059] (1);

[0060] in, is the prior state estimation result at time k, and are the posterior state estimation results at time k and k-1 respectively, u k and u k-1 are the state equation inputs at time k and k-1 respectively.

[0061]

[0062] (3); Among them, x is the horizontal coordinate, y is the vertical coordinate, θ is the angle, v is the speed, is the acceleration of the vehicle coordinate system along the X axis, m / s2; is the acceleration of the Y axis of the vehicle coordinate system, m / s2.

[0063] (4);

[0064] Among them, A is the state transfer matrix and t is the time step, s.

[0065] (5);

[0066] Among them, B is the matrix that converts input into state (uk control matrix).

[0067] Forward error s covariance:

[0068] (6);

[0069] in, is the prior estimated covariance at time k; P K is the posterior estimated covariance at time k; P k-1 Is it the posterior estimated covariance at time K-1? Q is the process excitation noise covariance;

[0070] Calculate the Kalman gain:

[0071] (7);

[0072] Among them, K k is the filter gain matrix; H is the conversion matrix from state variables to measurements; R is the measurement noise covariance.

[0073] From the observed variable z k Updated estimate:

[0074] (8);

[0075] in, is the residual between the actual observation and the predicted observation.

[0076] Update the covariance estimate:

[0077] (9);

[0078] Among them, z k It is the input of the measured value filter;

[0079] The Kalman filter is designed based on the above recursive equation and state equation. In the formula (1), the posterior state estimate of the system at time k-1 is To predict the state value of the system at time k, and at the same time, the error covariance P at time k-1 k-1 and the process noise Q predicts the prior error covariance of the new k time Formula (6) is obtained, and combined with formula (1) (6) to form the time update equation; Formula (1) is corrected and updated to perform the iterative update operation of estimating the system state value at time k+1 in the next step, and P is updated K The value is obtained by formula (9), which uses the Kalman gain parameter to update and achieve more accurate prediction and estimation of the system state value. In (2), x, y, θ and v are obtained by the BDS-SPP positioning system, and in (3) θ is obtained by the attitude sensor system AHRS. Through the preliminary test, the process excitation noise covariance Q and the measurement noise covariance matrix R are adjusted to minimize the variance of the estimation error and obtain the optimal estimation.

[0080]

[0081] The initialization time of the inertial sensor is 15s. When the device is started, the BDS and AHRS modules are initialized synchronously. After all modules are initialized, the fusion positioning work begins. The board will provide a flag bit according to the positioning quality. There is a positioning status flag bit in the $GPRMC communication protocol. The flag "A" indicates a normal positioning state, while the flag "F" indicates a disturbed state. This state is automatically determined by the positioning board.

[0082] When the flag is "A" and the satellite signal is stable, the R matrix in formula (11) is used to perform fusion positioning normally to obtain more accurate heading information; when the flag is "F" and the satellite positioning signal is interfered, the Kalman filter immediately switches the R matrix to the measurement noise covariance matrix R' as shown in formula (12) according to the flag, reducing the weight of the satellite positioning signal and relatively increasing the weight of the AHRS sensor signal; the initial heading uses the heading information before the switch, which can better improve the inertial positioning accuracy and achieve seamless connection between the two signal sources. The switch occurs in the sampling period (0.1s) when the flag changes.

[0083]

[0084] Step S103, adjusting the actual position of the vehicle according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle, so that the vehicle performs tracking reversing.

[0085] By comparing the target reversing path and the actual position information, the deviation is calculated, and the actual position of the vehicle is adjusted by controlling the steering and braking systems of the vehicle so that the vehicle can reverse along the target path. Specifically, algorithms such as PID control, fuzzy control, and neural network control can be used to achieve vehicle tracking control. Among them, the tracking control algorithm can update the deviation between the target path and the actual position information in real time, and adjust the control instructions of the vehicle according to the deviation. Sensors (such as cameras, radars, etc.) can also be used to detect obstacles and road conditions so that the reversing path can be adjusted when necessary.

[0086] The vehicle tracking and reversing method provided in this embodiment can accurately calculate the vehicle position and direction at multiple times by acquiring the vehicle's inertial posture data and absolute positioning information, thereby solving the limitations of the driver's intuitive judgment. At the same time, by determining the deviation between the target reversing path and the position of the vehicle during the actual driving process, the actual position of the vehicle is adjusted, and the calculation and path planning can be automated, reducing the dependence on the driver's experience and skills, so that even novice drivers can reverse safely and accurately in narrow roads or complex environments.

[0087] In a possible implementation, the above step S102 includes:

[0088] Step a1, obtaining environmental constraints.

[0089] Step a2, determining multiple initial reversing paths according to the position information of the vehicle at each time and environmental constraints.

[0090] Environmental constraints can represent external factors that affect vehicle reversing, such as road width, obstacle location, parking space size, traffic rules, etc. Using the path planning algorithm, multiple possible reversing paths are preliminarily planned based on the vehicle's position information at each moment and environmental constraints (such as road width, obstacle location, parking space size, etc.). These paths should avoid collisions with obstacles and comply with traffic rules.

[0091] As an example, a path planning algorithm can make plans based on factors such as map information, obstacle locations, and vehicle size.

[0092] Heuristic search algorithms (such as A* algorithm), genetic algorithms, ant colony algorithms and other intelligent optimization algorithms can be used to plan the initial reversing path. Dynamic characteristics such as the vehicle's turning radius and braking distance can be considered to ensure the feasibility of the path. Real-time sensor data (such as cameras, radars, etc.) can be combined to dynamically adjust the path planning to adapt to environmental changes.

[0093] Step a3: determining a target reversing path that meets preset conditions from a plurality of initial reversing paths.

[0094] According to preset conditions (such as shortest path length, highest safety, compliance with traffic rules, path smoothness, etc.), multiple initial reversing paths are evaluated and screened to determine the target reversing path that meets the conditions. The evaluation process may include calculating the path length, analyzing the distance between the path and obstacles, and checking whether the path complies with traffic rules.

[0095] For example, the preset conditions are the shortest path length and the highest safety, and the requirements are to comply with traffic rules and keep the path smooth. By evaluating and screening the three initial reversing paths, a target reversing path that meets these conditions is finally determined. This path is not only short in length, but also has a large enough distance from obstacles to ensure safety, while complying with traffic rules and maintaining the smoothness of the path.

[0096] The vehicle tracking and reversing method provided in this embodiment can fuse the vehicle's inertial posture data and absolute positioning information through the Kalman filter algorithm. The inertial posture data and absolute positioning information are complementary and can provide more comprehensive and accurate vehicle position information. At the same time, the Kalman filter algorithm can update the vehicle's position information in real time according to new observation data through prediction and update steps, thereby realizing real-time tracking and prediction of the vehicle's position. In addition, by combining the vehicle's position information and environmental constraints, the method can generate multiple possible initial reversing paths. Among the multiple initial paths, the optimal target reversing path is selected according to preset conditions to ensure the safety and efficiency of the reversing process.

[0097] In a possible implementation, the actual position information of the vehicle includes: a driving position and a driving direction; wherein, in the above step S103, adjusting the actual position of the vehicle according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle includes:

[0098] Step b1, determining a target position and a target direction corresponding to a target time from a target reversing path according to the driving position and the driving direction.

[0099] Driving information refers to the driving position and driving direction of a vehicle at a certain moment. The driving information may include the driving position and driving direction.

[0100] As an example, the driving position (latitude and longitude, altitude, etc.) and driving direction (angle of the vehicle's front direction) at the target time can be obtained through the vehicle's GPS positioning system, sensors, etc.

[0101] As an example, the driving direction can be calculated by using sensors inside the vehicle (such as a gyroscope, accelerometer) combined with an algorithm.

[0102] As an example, on-board cameras and image recognition technology can be used to identify road signs and lane lines to assist in determining the direction of travel.

[0103] Step b2, determining a position deviation value according to the driving position and the target position, and determining a direction deviation value according to the driving direction and the target direction.

[0104] The position deviation value refers to the physical distance or spatial offset between the current driving position of the vehicle and the target position. The position deviation value can be calculated by a variety of methods: the straight-line distance between the current position of the vehicle (such as GPS coordinates) and the target position can be calculated. Specifically, it may involve distance formulas in two-dimensional or three-dimensional space. If the path planning route is a curve, the current position of the vehicle can be projected onto the path curve, and then the distance between the projection point and the target position is calculated. In the path planning route, find the path point closest to the current position of the vehicle, and then calculate the distance between the path point and the target position. This method is applicable to the case of discrete path points, etc., and is not specifically limited here, and can be implemented by those skilled in the art.

[0105] The direction deviation value is the angular difference between the vehicle's current direction and the target direction. The direction deviation value can be calculated in a variety of ways: the vehicle's current direction and the target direction are represented as vectors, and then the angle between the two vectors is calculated. This usually involves the dot product and modulus of the vectors. If the path planning route is a curve, the tangent direction of the curve can be calculated at the target position and compared with the vehicle's current direction to obtain the direction deviation value. In the path planning route, find the path points that are closest to the vehicle's current position and the target position, respectively, and then calculate the angle between the direction of the line between the two path points and the vehicle's current direction.

[0106] Step b3, controlling the vehicle to adjust according to the position deviation value and the direction deviation value.

[0107] In autonomous driving or vehicle navigation systems, position deviation values ​​and direction deviation values ​​are used as important indicators to evaluate the difference between the vehicle's current state and the target state. These deviation values ​​are obtained by comparing the vehicle's current driving position and driving direction with the target position and target direction. Once these deviation values ​​are calculated, the system needs to adjust the vehicle's driving trajectory based on these values ​​to make it closer to the target path.

[0108] As an example, the adjustment can be performed by controlling the vehicle based on PID. Specifically, the position deviation value and the direction deviation value are calculated. According to the PID control algorithm, the control instruction (such as steering angle, vehicle speed adjustment, etc.) is calculated. The control instruction is sent to the control system of the vehicle to perform the adjustment operation.

[0109] As an example, the adjustment can be made by controlling the vehicle based on a mathematical model. Specifically, a dynamic model and a road model of the vehicle are established. The future driving state is calculated based on the position deviation value and the direction deviation value, as well as the prediction model. The optimal control command is solved through the optimization algorithm. The control command is sent to the control system of the vehicle to perform the adjustment operation.

[0110] As an example, adjustments can be made by controlling the vehicle based on a neural network model. Specifically, the vehicle's historical driving data and current driving status are collected. Using machine learning algorithms, the data is analyzed and control instructions are optimized. The optimized control instructions are sent to the vehicle's control system to perform adjustment operations. Continuous monitoring and adjustment are performed to continuously optimize control performance.

[0111] As an example, the vehicle can be adjusted by controlling the vehicle based on multi-sensor fusion. Specifically, information from multiple sensors (such as position information, direction information, obstacle information, etc.) is collected. The sensor information is fused and processed to obtain more accurate vehicle status and surrounding environment information. Based on the fused information, control instructions are calculated. The control instructions are sent to the vehicle's control system to perform the adjustment operation.

[0112] The vehicle tracking and reversing method provided in this embodiment can accurately identify the position deviation and direction deviation by accurately calculating the target position and target direction corresponding to the target time and comparing them with the actual driving position and driving direction. According to these deviation values, the vehicle can be controlled and adjusted in a targeted manner, thereby improving the accuracy and efficiency of reversing. In addition, by accurately calculating and adjusting the position and direction of the vehicle, the method can effectively avoid the risk of collision with surrounding obstacles or other vehicles. This is particularly important for reversing in narrow or complex environments, and can significantly improve driving safety.

[0113] In a possible implementation, the method further includes:

[0114] Step c1, when the vehicle is traveling along the target reversing path, detecting whether there is an obstacle on the target reversing path.

[0115] Any object that may hinder the vehicle's progress during its travel, including dynamic obstacles (such as pedestrians, bicycles, other moving vehicles, etc.). Specifically, sensors on the vehicle (such as cameras, radars, laser radars, etc.) can be used to detect in real time whether there are obstacles on the target reversing path.

[0116] Step c2: if there is an obstacle on the target reversing path, obtain the state of the obstacle.

[0117] After detecting an obstacle, the sensor data is used to further analyze the movement state of the obstacle to determine whether it is stationary or dynamic. Specifically, the movement of the obstacle can be determined by analyzing the image sequence captured by the camera. Radar or lidar can also be used for continuous measurement to analyze the speed change of the obstacle. The vehicle's inertial navigation data can also be combined to assist in determining the movement state of the obstacle.

[0118] Step c3: if the state of the obstacle is static, detect whether the obstacle exists on the route of the target reversing path.

[0119] After confirming that the obstacle is stationary, it is further determined whether the obstacle is located on the target reversing path that the vehicle needs to travel. Specifically, the position of the obstacle can be compared with the map data of the target reversing path. The relative position relationship between the vehicle and the obstacle can be calculated in real time using sensor data. It can be determined whether the obstacle affects the path by combining the current position and posture of the vehicle and the curvature and direction of the target reversing path.

[0120] Step c4: if an obstacle exists on the route of the target reversing path, the target reversing path is adjusted so that the vehicle avoids the obstacle.

[0121] After confirming that the obstacle is located on the target reversing path, a reversing path that can avoid the obstacle is replanned. Specifically, a path planning algorithm can be used to replan a path that avoids the obstacle according to the location of the obstacle and the starting point and end point of the target reversing path, etc., which is not specifically limited here and can be implemented by those skilled in the art.

[0122] Step c5: If the state of the obstacle is in motion, stop executing the vehicle reversing action.

[0123] If the obstacle is in motion, stop reversing the vehicle.

[0124] The vehicle tracking and reversing method provided in this embodiment can detect in real time whether there are obstacles on the target reversing path during the reversing process, so as to timely discover potential dangers and avoid collisions with obstacles. For obstacles in a stationary state, it is detected whether the obstacles exist on the route of the target reversing path. If the obstacles exist on the route of the target reversing path, a safe reversing path is planned to ensure that the vehicle can smoothly bypass the obstacles. When the state of the obstacle is in a moving state, the reversing action of the vehicle is stopped, thereby ensuring safety.

[0125] Please refer to Figure 4 , Figure 4 It is a schematic diagram of a vehicle tracking and reversing method provided according to an embodiment of the present invention.

[0126] After the system is started, it enters the reversing assistance mode. Module initialization: The positioning module, sensor module, data fusion module and path planning module are initialized, and the system enters the standby state. BDS receiving module: Start the BDS receiving module, receive Beidou satellite (BDS) signals in real time, obtain the current absolute position of the vehicle (latitude and longitude information), and input the system as the initial positioning data. INS inertial navigation module: Start the INS module of the vehicle module itself, and collect the vehicle's motion information in real time through the accelerometer and gyroscope, including acceleration, angular velocity and attitude changes. Data synchronization acquisition: The system synchronously receives the data of BDS and INS sensors, and inputs it into the fusion module as the basis for subsequent positioning and analysis. Data fusion processing: The Kalman filter algorithm is used to perform real-time fusion of the absolute positioning information provided by BDS and the inertial attitude data provided by INS. BDS data: Provides accurate static absolute position for system calibration. INS data: Supplements dynamic position and attitude changes during movement to make up for the shortcomings of short-term BDS signals. Through data fusion, the high-precision real-time position and motion trajectory of the vehicle are obtained, providing reliable input for reversing path planning. The system detects BDS signal quality parameters (such as signal strength and signal-to-noise ratio) in real time to identify whether there is signal failure caused by occlusion, reflection or interference. When the BDS signal fails or the accuracy is reduced, the system switches to INS data mode and uses inertial sensors to calculate the vehicle's motion trajectory to ensure continuous positioning data in a short time. The system periodically re-detects the BDS signal status, and once it returns to normal, it re-integrates BDS and INS data to improve positioning accuracy. Based on high-precision real-time location information, the system can combine 100m of driving information on the vehicle (a path point is recorded every 5m, and the actual distance of 100m is the final point of the reversing target) and surrounding environment data to generate the optimal reversing path. The path planning algorithm considers the following factors: The relative relationship between the current vehicle position and the target position. Environmental constraints (such as obstacles, lane lines or narrow spaces). Dynamic changes that may occur during reversing. The system generates multiple executable reversing paths (the minimum unit is 5m), mainly smooth curves, to form a final path, which ensures that the vehicle can reverse safely according to the planned trajectory. The system dynamically adjusts the reversing path by monitoring the deviation between the vehicle's current position and the planned path in real time to ensure that the vehicle always moves along the optimal path. The system continuously scans for obstacles in the path, such as dynamic pedestrians, other vehicles, or obstacles. When a fixed obstacle is detected, the system activates the obstacle avoidance mechanism and replans the path to ensure safety during the reversing process. When a dynamic obstacle is detected, the parking waiting logic is executed. During the reversing process, the system continuously updates the vehicle's current position and adjusts the path according to environmental changes and the target position to avoid deviation from the planned route. When the vehicle completes reversing and reaches the target position, the system records the final status and confirms that the reversing task is completed. The system exits the tracking reversing mode, and the sensor enters the standby state, waiting for the next operation instruction.

[0127] In this embodiment, a vehicle tracking and reversing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0128] This embodiment provides a vehicle tracking and reversing device, such as Figure 5 As shown, it includes: an acquisition module 501, which is used to acquire the inertial posture data at the initial moment; a first determination module 502, which is used to determine the inertial posture data and predicted position information at the target moment according to the historical positioning information and the inertial posture data at the initial moment; a second determination module 503, which is used to obtain the absolute positioning information at the target moment, fuse the inertial posture data at the target moment, the predicted position information at the target moment, and the absolute positioning information at the target moment, to determine the position information of the vehicle at each moment, and determine the target reversing path of the vehicle according to the position information of the vehicle at each moment; a tracking reversing module 504, which is used to adjust the actual position of the vehicle according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle, so that the vehicle can perform tracking reversing.

[0129] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0130] The tracking reversing device of the vehicle in this embodiment is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0131] The embodiment of the present invention also provides a computer device having the above Figure 5 The tracking reversing device of the vehicle shown.

[0132] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0133] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0134] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0135] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0137] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0138] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0139] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0140] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A vehicle tracking and reversing method, characterized in that: The method comprises: Get the inertial attitude data at the initial moment; Determine the inertial posture data and predicted position information at the target time based on the historical positioning information and the inertial posture data at the initial time; If the absolute positioning information at the target time is obtained, the inertial posture data at the target time, the predicted position information at the target time, and the absolute positioning information at the target time are integrated to determine the position information of the vehicle at each time, and the target reversing path of the vehicle is determined based on the position information of the vehicle at each time; According to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle, the actual position of the vehicle is adjusted so that the vehicle performs tracking reversing.

2. The vehicle tracking backing method according to claim 1, characterized in that: The target reversing path of the vehicle is determined according to the position information of the vehicle at each time, including: Get environmental constraints; Determining multiple initial reversing paths according to the position information of the vehicle at each time and environmental constraints; A target reversing path satisfying a preset condition is determined from the plurality of initial reversing paths.

3. The vehicle tracking backing method according to claim 1, characterized in that: The actual position information of the vehicle includes: driving position and driving direction; wherein, adjusting the actual position of the vehicle according to the deviation between the target reversing path of the vehicle and the actual position information of the vehicle includes: Determining a target position and a target direction corresponding to a target time from a target reversing path according to the driving position and the driving direction; Determining a position deviation value according to the driving position and the target position, and determining a direction deviation value according to the driving direction and the target direction; The vehicle is controlled to be adjusted according to the position deviation value and the direction deviation value.

4. The vehicle tracking backing method according to claim 2, characterized in that: The method further comprises: When the vehicle is traveling along a target reversing path, detecting whether there is an obstacle on the target reversing path; If there is an obstacle on the target reversing path, obtaining the state of the obstacle; If the state of the obstacle is a stationary state, detecting whether the obstacle exists on the route of the target reversing path; If the obstacle exists on the route of the target reversing path, the target reversing path is adjusted so that the vehicle avoids the obstacle.

5. The vehicle tracking backing method according to claim 4, characterized in that: The method further comprises: If the state of the obstacle is a moving state, the vehicle reversing action is stopped.

6. A vehicle tracking and reversing device, characterized in that: The device comprises: An acquisition module is used to obtain the inertial attitude data at the initial moment; A first determination module is used to determine the inertial posture data and predicted position information at the target time according to the historical positioning information and the inertial posture data at the initial time; The second determination module is used to obtain the absolute positioning information at the target time, fuse the inertial posture data at the target time, the predicted position information at the target time, and the absolute positioning information at the target time, determine the position information of the vehicle at each time, and determine the target reversing path of the vehicle according to the position information of the vehicle at each time; The tracking reverse module is used to adjust the actual position of the vehicle according to the deviation between the target reverse path of the vehicle and the actual position information of the vehicle, so that the vehicle can perform tracking reverse.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the tracking and reversing method for a vehicle according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the vehicle tracking and reversing method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the vehicle tracking and reversing method according to any one of claims 1 to 5.

Images