A vehicle control method, a control device and a camera device

Abstract

Embodiments of the present disclosure disclose a vehicle control method, a control device, and a camera device. The vehicle control method may include: a control end obtains a lane centerline equation input by a camera device on the vehicle, and the lane centerline equation is obtained by fitting and calculating the lane lines in front of the vehicle detected by the camera device to obtain the lane centerline equation within a certain time domain in the future after the current moment; the control end plans an expected tracking trajectory of the vehicle according to the lane centerline equation and determines whether the road geometric structure sensed by the camera changes; when it is determined that the road geometric structure sensed by the camera device changes, the lane lines in front of the vehicle detected by the camera device are secondarily fitted to re-linearly fit to obtain a secondarily optimized lane centerline equation. The vehicle control method, the control device, and the camera device disclosed in the embodiments of the present disclosure can secondarily optimize the information in the perception layer and improve the effectiveness and stability of the information in the perception layer.

Description

Technical Field

[0001] The present disclosure relates to, but is not limited to, the field of automobiles, and particularly to a vehicle control method, a control device, and a camera device. Background Art

[0002] Intelligent driving technology can be divided into four modules: perception, decision-making, planning, and control. Among them, the perception layer uses hardware sensors to sense devices, realizes the detection of characteristic targets such as the road conditions, obstacles, and lane lines around the vehicle, and completes the processing and analysis of information through algorithms or modeling, etc., to realize the recognition of the surrounding environment and road condition information, and helps intelligent driving vehicles to effectively make subsequent decisions and execute control. Therefore, the effectiveness and stability of the perception layer information determine the effectiveness and stability of subsequent decision-making and control.

[0003] Currently, intelligent driving vehicles mainly detect and identify the road geometric structure through the detection of lane lines, and the detection and identification of lane lines mainly rely on the camera device installed on the vehicle. The lane line detection algorithm inside the camera device senses and detects the lane lines on both sides of the lane, and finally outputs the fitting lane center line parameters for vehicle control, including the lane center line equation, lane curvature, and the distance between the vehicle and the lane center line. Limited by the limitations of the lane line detection algorithm and the perception performance of the camera device, in the face of changes in the road geometric structure, such as for a road surface with double-sided fishbone lines or single-sided fishbone lines, where there are large changes in the lane line style and width, the camera device is prone to large deviations in the recognition of the lane line width. For example, the deviation in the detection of the width of a single-sided lane line leads to a deviation in the position of the lane center line, which in turn leads to a large error in the vehicle lateral trajectory tracking control.

[0004] Moreover, the current link from the perception layer to the planning layer in intelligent driving is unidirectional. The calculation of the desired steering angle for the vehicle lateral control in the planning layer completely depends on the lane line information input by the camera device, such as the lane center line equation, lane curvature, and the distance between the vehicle and the lane center line. If the performance of the camera device is limited or there are perception errors, it will directly lead to deviations in the calculation of the lateral desired steering angle in the planning layer, which in turn leads to deviations in the vehicle lateral control and deviation from the expected driving trajectory. Therefore, the input of the lane information with a certain deviation jump amount in real time by the camera device will also directly cause the swing and instability of the vehicle lateral trajectory control. Summary of the Invention

[0005] In a first aspect, an embodiment of the present disclosure provides a vehicle control method, including:

[0006] The control end obtains the lane center line equation input by the camera device on the vehicle, and the lane center line equation is the lane center line equation within a certain time domain in the future after the camera device detects and fits the lane lines in front of the vehicle at the current moment;

[0007] The control terminal plans the expected tracking trajectory of the vehicle according to the lane centerline equation, and determines whether the road geometric structure sensed by the camera has changed;

[0008] When it is determined that the road geometric structure sensed by the camera device has changed, the lane lines in front of the vehicle detected by the camera device are secondarily fitted to re-linearly fit and obtain a secondarily optimized lane centerline equation.

[0009] In a second aspect, an embodiment of the present disclosure provides a vehicle control method, including:

[0010] The camera device detects the lane lines in front of the vehicle, fittingly calculates the lane centerline equation within a certain time domain in the future after the current moment, and sends the lane centerline equation to the control terminal;

[0011] The camera device sends the lane line information within a certain distance in front of the detected road and the lane line information in the historical time domain to the control terminal, so that the control terminal re-linearly fits to obtain a secondarily optimized lane centerline equation;

[0012] Or,

[0013] When the camera device receives the second fitting information sent by the control terminal, according to the lane line information within a certain distance in front of the detected road and the lane line information in the historical time domain, it re-linearly fits to obtain a secondarily optimized lane centerline equation, and sends the secondarily optimized lane center equation to the control terminal.

[0014] In a third aspect, an embodiment of the present disclosure provides a vehicle control device, including a memory and a processor. The memory is used to store execution instructions; the processor calls the execution instructions to execute the vehicle control method according to any one of the embodiments in the first aspect.

[0015] In a fourth aspect, an embodiment of the present disclosure provides a camera device, including: a camera, a memory and a processor. The memory is used to store execution instructions; the processor calls the execution instructions to execute the vehicle control method according to any one of the embodiments in the second aspect.

[0016] Compared with the prior art, the vehicle control method, control device and camera device provided by at least one embodiment of the present disclosure have the following beneficial effects: Compared with the situation where the calculation of the lateral control of the vehicle by the planning layer completely depends on the information of the perception layer, the information of the perception layer can be secondarily optimized, the effectiveness and stability of the information of the perception layer are improved, and the risk that the invalid and deviated information of the perception layer is directly executed by the planning and control layer is reduced.

[0017] Other features and advantages of the present disclosure will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present disclosure. Other advantages of the present disclosure may be realized and obtained by the solutions described in the description and the drawings. Description of the Drawings

[0018] The drawings are used to provide an understanding of the technical solutions of the present disclosure, and constitute a part of the description. Together with the embodiments of the present disclosure, they are used to explain the technical solutions of the present disclosure, and do not constitute a limitation to the technical solutions of the present disclosure.

[0019] Figure 1 Flowchart of the vehicle control method provided for an exemplary embodiment of the present disclosure;

[0020] Figure 2 Schematic diagram of vehicle control provided for an exemplary embodiment of the present disclosure;

[0021] Figure 3 Flowchart of the vehicle control method provided for another exemplary embodiment of the present disclosure;

[0022] Figure 4 Block diagram of the vehicle control device provided for an exemplary embodiment of the present disclosure;

[0023] Figure 5 Block diagram of the camera device provided for an exemplary embodiment of the present disclosure. Detailed Description of the Invention

[0024] The present disclosure describes multiple embodiments, but the description is exemplary rather than restrictive, and it will be obvious to those of ordinary skill in the art that there may be more embodiments and implementation solutions within the scope of the embodiments described in the present disclosure. Although many possible feature combinations are shown in the drawings and discussed in the detailed description, many other combination ways of the disclosed features are also possible. Unless specifically restricted, any feature or element of any embodiment can be combined with any other feature or element in any other embodiment, or can replace any other feature or element in any other embodiment.

[0025] The present disclosure includes and contemplates combinations with features and elements known to those of ordinary skill in the art. The disclosed embodiments, features, and elements of the present disclosure may also be combined with any conventional features or elements to form unique inventive solutions defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive solutions to form another unique inventive solution defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in the present disclosure may be implemented alone or in any suitable combination. Therefore, the embodiments are not subject to other limitations except those made in accordance with the appended claims and their equivalents. In addition, various modifications and changes may be made within the scope of the appended claims.

[0026] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a particular sequence of steps. However, to the extent that the method or process does not depend on the particular order of the steps described herein, the method or process should not be limited to the described particular order of steps. As will be understood by those of ordinary skill in the art, other step orders are possible. Therefore, the particular order of steps set forth in the specification should not be construed as a limitation on the claims. In addition, the claims directed to the method and / or process should not be limited to performing their steps in the order written, as those skilled in the art can readily understand that these orders can vary and still remain within the spirit and scope of the embodiments of the present disclosure.

[0027] Figure 1 Flowchart of a vehicle control method provided for an exemplary embodiment of the present disclosure Figure 2 Schematic diagram of vehicle control provided for an exemplary embodiment of the present disclosure. The execution subject of the embodiments of the present disclosure may be the control end of the planning layer, such as Figure 1 and Figure 2 As shown, the vehicle control method may include: S101, S102, and S103.

[0028] S101: The control end obtains the lane centerline equation input by the camera device on the vehicle. The lane centerline equation is obtained by fitting and calculating the detected lane lines in front of the vehicle by the camera device to obtain the lane centerline equation within a certain time domain in the future after the current moment.

[0029] A camera device (which can be called a camera sensor) can be installed on a vehicle as the perception layer of intelligent driving. The camera device can include a camera and a processor. The camera collects road information on both sides of the lane. The lane line detection algorithm inside the processor perceives and detects the lane lines on both sides of the lane, and outputs the fitting lane centerline parameters for vehicle control to the control end of the planning layer. The lane centerline parameters can include the lane centerline equation, lane curvature, and the distance of the vehicle from the lane centerline, etc. The lane centerline equation can be a quadratic mathematical equation, a cubic mathematical equation, etc.

[0030] The lane line detection algorithm inside the camera device can adopt existing lane line detection algorithms. The lane line detection algorithm is mainly used to perform curve fitting on the collected lane line data to estimate the parameter information of the lane lines, and obtain information such as steering angle, offset, tilt angle, and radius of curvature, so as to predict the trend of the lane lines. Among them, the implementation principle of the lane line detection algorithm for perceiving and detecting the lane lines on both sides of the lane and outputting the fitting lane centerline parameters for vehicle control is the same as that of the prior art, and will not be elaborated in this embodiment.

[0031] For example, the lane line data 100 meters ahead of the vehicle can be obtained through the camera in the camera device. The lane line detection algorithm inside the processor in the camera device can perform curve fitting according to the lane line data 100 meters ahead of the vehicle to obtain the lane centerline equation within a certain future time domain (such as 500 meters ahead) after the previous moment.

[0032] In one example, when the camera device detects the lane lines ahead of the vehicle and performs fitting calculation to obtain the lane centerline equation within a certain future time domain after the current moment, it can include:

[0033] As Figure 2 shown, the camera device detects the lane lines ahead, obtains and stores all discrete target position point information of the lane lines on both sides within a certain distance ahead of the road; the camera device fits and calculates the lane centerline equation within a certain future time domain according to all discrete target position point information of the lane lines on both sides within a certain distance ahead of the road.

[0034] The camera device outputs all discrete target position point information of the lane lines on both sides within a certain distance ahead of the road through the detection and recognition of the lane lines ahead; the vehicle stores all discrete target position point information of the lane lines on both sides within a certain distance ahead of the vehicle at the current moment in real time; the camera device fits and calculates the lane centerline equation within a certain future time domain beyond the current moment according to the discrete target position point information of the lane lines.

[0035] S102: The control end plans the expected tracking trajectory of the vehicle according to the lane centerline equation, and judges whether the road geometric structure perceived by the camera device has changed.

[0036] As Figure 2 shown, the lane centerline equation calculated by the camera device is input to the control end of the planning layer for planning the expected vehicle tracking trajectory. The control end can design a pre-control algorithm for the vehicle tracking trajectory. After the lane centerline equation is input to the vehicle planning layer by the camera device, the pre-control is performed on the planned expected trajectory to pre-identify the error influence of the expected trajectory on the lateral control of the vehicle trajectory, and then judge the effectiveness and stability of the lane centerline sensing and recognition of the camera device.

[0037] In an example, the control end plans the expected vehicle tracking trajectory according to the lane centerline equation and judges whether the road geometric structure sensed by the camera device has changed, which may include:

[0038] According to the lane centerline equation, the expected steering angle of the vehicle lateral control within a certain future time domain is predicted; according to the lateral control steering angle and the vehicle driving state information at the current moment, the expected yaw rate of the vehicle within a certain future time domain is predicted; according to the expected yaw rate, it is judged whether the road geometric structure sensed by the camera device has changed.

[0039] The control end can construct a vehicle dynamics model and a driver model according to the vehicle's own structural parameters and dynamic equations. The driver model can represent the corresponding relationship between the lane centerline and the vehicle lateral control steering angle. The vehicle dynamics model can be obtained according to vehicle dynamics inferences, and can represent the corresponding relationship between the vehicle driving state information, the vehicle lateral control steering angle and the vehicle yaw rate. Among them, the construction principles of the vehicle dynamics model and the driver model are the same as those of the existing solutions, and are not limited and elaborated in this embodiment.

[0040] The expected vehicle tracking trajectory input by the sensing layer, that is, the lane centerline equation input by the camera device, can be input to the driver model to obtain the vehicle lateral control steering angle at the current moment and within a certain future time domain.

[0041] The vehicle driving state information at the current moment, such as longitudinal and lateral vehicle speeds, acceleration, yaw rate, and heading angle, can be obtained through vehicle sensors and observers. The vehicle current state information and the vehicle lateral control steering angle within the future time domain are input to the vehicle dynamics model to predict the expected yaw rate of the vehicle within a certain future time domain.

[0042] In an example, the state information may include at least one of the following: vehicle speed, acceleration, yaw rate, and heading angle.

[0043] S103: When it is determined that the road geometric structure sensed by the camera device has changed, perform a second - order fitting on the lane lines in front of the vehicle detected by the camera device to re - linearly fit and obtain a second - order optimized lane centerline equation.

[0044] When the control end determines that the road geometric structure sensed by the camera device has changed, whether it is due to a change in the actual road geometric structure or a deviation in the camera device's recognition of the road geometric structure, it indicates that the road geometric structure sensed by the camera device has changed.

[0045] The control end designs a lane - line sensing and recognition feedback optimization algorithm, feeds the results of the vehicle planning and control layer back to the sensing algorithm layer, performs a second - order optimization on the lane centerline parameters of the camera device, and outputs lane centerline parameters that can reduce the lateral control error of vehicle trajectory tracking.

[0046] Compared with the situation where the planning layer's lateral control of the vehicle completely depends on the information of the sensing layer, the information of the sensing layer can be second - order optimized, improving the effectiveness and stability of the sensing layer information and reducing the risk that invalid and deviated information of the sensing layer is directly executed by the planning and control layer.

[0047] In one example, performing a second - order fitting on the lane lines in front of the vehicle detected by the camera device to re - linearly fit and obtain a second - order optimized lane centerline equation may include:

[0048] Obtain the lane - line information within a certain distance in front of the road required for the second - order fitting from the camera device, as well as the lane - line information in the historical time domain, to re - linearly fit and obtain a second - order optimized lane centerline equation.

[0049] In this embodiment, a lane - line second - order optimization module can be set at the control end. When it is determined that the road geometric structure sensed by the camera sensing device has changed, obtain the information required for the second - order fitting (historical lane - line information and lane - line information in the future time domain) from the camera device to re - linearly fit and obtain a second - order optimized lane centerline equation.

[0050] In one example, performing a second - order fitting on the lane lines in front of the vehicle detected by the camera device to re - linearly fit and obtain a second - order optimized lane centerline equation may include:

[0051] Send second - order fitting information to the camera device to instruct the camera device to re - linearly fit and obtain a second - order optimized lane centerline equation.

[0052] In this embodiment, a lane line secondary optimization module can be set in the camera device. When the camera device receives the secondary fitting information sent by the control end, the camera device re-performs linear fitting to obtain a lane center line equation with secondary optimization. Compared with the current one-way information transmission link structure from the intelligent driving perception layer to the planning and control layer, the result of the planning and control layer (control end) can be fed back to the perception layer (camera device), the information of the perception layer is secondarily optimized, the effectiveness and stability of the perception layer information are improved, and the risk that the invalid and deviated information of the perception layer is directly executed by the planning and control layer is reduced.

[0053] In one example, re-performing linear fitting to obtain a lane center line equation with secondary optimization may include:

[0054] Obtain all discrete target position point information of the lane lines on both sides within a certain distance in front of the road detected by the camera device as the first discrete target position point information; obtain all discrete target position points of the lane lines on both sides in the historical time domain detected by the camera device as the second discrete target position point information; after fusing the first discrete target position point information and the second discrete target position point information together, re-perform linear fitting to obtain a lane line equation with secondary optimization.

[0055] During secondary optimization, all discrete target position point information of the lane lines on both sides within a future time domain (such as 100 meters ahead) detected by the camera device and all discrete target position point information of the lane lines on both sides within a certain time domain before this future time domain (historical time domain) can be fused together and input into the lane line secondary optimization module in the control end or the camera device; the lane line secondary optimization module can remove the noise (deviated points) from all discrete target position point information within the extended time domain and re-perform linear fitting to obtain a lane center line equation with secondary optimization.

[0056] The vehicle control method provided by the embodiments of the present disclosure can feed back the result of the planning and control layer to the perception layer, secondarily optimize the information of the perception layer, improve the effectiveness and stability of the perception layer information, and reduce the risk that the invalid and deviated information of the perception layer is directly executed by the planning and control layer.

[0057] In an exemplary embodiment of the present disclosure, determining whether the road geometry structure perceived by the camera device has changed according to the expected yaw rate may include:

[0058] Calculate the variance of the expected yaw rate within a certain future time domain; compare the variance of the expected yaw rate with a set threshold, and when the variance of the expected yaw rate is greater than the set threshold, determine that the road geometry structure perceived by the camera device has changed.

[0059] When the variance of the expected yaw rate exceeds a certain threshold, it is determined that the road geometry structure perceived by the camera device has changed.

[0060] When the control end pre-identifies that the variance of the desired yaw rate of the vehicle in the future time domain exceeds a certain threshold, whether the actual road geometric structure changes or the camera device's recognition of the road geometric structure has a deviation, it indicates that the road geometric structure perceived by the camera device has changed.

[0061] In an exemplary embodiment of the present disclosure, the quadratic fitting information may include: the time period when the variance of the desired yaw rate is greater than the set threshold, and the quadratic fitting information is used to instruct the camera device to re-linearly fit the lane line information within this time period to obtain a quadratically optimized lane centerline equation.

[0062] The control end can return the time period when the variance of the desired yaw rate is greater than the set threshold to the camera device, and the camera device re-linearly fits the lane line information within this time period to obtain a quadratically optimized lane centerline equation. For example, the camera device obtains the lane line data 100 meters in front of the vehicle, and the control end predicts and determines that the time period when the variance of the desired yaw rate is greater than the set threshold is from 40 meters to 50 meters in front. The control end returns the corresponding time period from 40 meters to 50 meters in front to the camera device. The camera device combines all the discrete target position point information of the two-side lane lines within this future time domain (from 40 meters to 50 meters in front) and all the discrete target position point information of the two-side lane lines within a certain time domain before this future time domain (historical time domain), and inputs it into the lane line information quadratic optimization module; the lane line information quadratic optimization module removes the noise (deviation points) from all the discrete target position point information within the extended time domain and re-linearly fits to obtain the quadratically optimized lane line information.

[0063] Figure 3 The flowchart of the vehicle control method provided for another exemplary embodiment of the present disclosure. The execution subject of the embodiment of the present disclosure can be the control end of the planning layer, such as Figure 3 shown, the vehicle control method may include: S301 and S302.

[0064] S301: The camera device detects the lane lines in front of the vehicle, fits and calculates the lane centerline equation within a certain future time domain after the current moment, and sends the lane centerline equation to the control end.

[0065] A camera device can be installed on a vehicle as the perception layer of intelligent driving. The camera device can include a camera and a processor. The camera collects road information on both sides of the lane. The lane line detection algorithm inside the processor outputs the fitted lane centerline parameters for vehicle control to the control end of the planning layer through the perception and detection of the lane lines on both sides of the lane. The lane centerline parameters can include the lane centerline equation, lane curvature, and the distance of the vehicle from the lane centerline, etc. The lane centerline equation can be a quadratic mathematical equation, a cubic mathematical equation, etc.

[0066] The lane line detection algorithm inside the camera device can adopt existing lane line detection algorithms. The lane line detection algorithm is mainly used to perform curve fitting on the collected lane line data to estimate the parameter information of the lane lines, and obtain information such as steering angle, offset, tilt angle, and radius of curvature, so as to predict the trend of the lane lines. Among them, the implementation principle of the lane line detection algorithm for perceiving and detecting the lane lines on both sides of the lane and outputting the fitted lane centerline parameters for vehicle control is the same as that of the prior art, and will not be elaborated in this embodiment.

[0067] For example, the lane line data 100 meters ahead of the vehicle can be obtained through the camera in the camera device. The lane line detection algorithm inside the processor in the camera device can perform curve fitting based on the lane line data 100 meters ahead of the vehicle to obtain the lane centerline equation within a certain future time domain (such as 500 meters ahead) after the previous moment.

[0068] The camera device outputs all discrete target position point information of the lane lines on both sides within a certain distance ahead of the road through the detection and recognition of the lane lines ahead; the vehicle will store all discrete target position point information of the lane lines on both sides within a certain distance ahead of the vehicle at the current moment in real time; the camera device fits and calculates to obtain the lane centerline equation within a certain future time domain beyond the current moment according to the discrete target position point information of the lane lines.

[0069] S302: When the camera device receives the quadratic fitting information sent by the control end, according to the detected lane line information within a certain distance ahead of the road and the lane line information in the historical time domain, re-linearly fit to obtain a quadratic optimized lane centerline equation, and send the quadratic optimized lane center equation to the control end.

[0070] In this embodiment, a lane line quadratic optimization module can be set in the camera device. When the camera device receives the quadratic fitting information sent by the control end, the camera device re-linearly fits to obtain a quadratic optimized lane centerline equation.

[0071] In an example, re-linearly fitting to obtain a quadratic optimized lane centerline equation can include:

[0072] The camera device obtains all the discrete target position point information of the lane lines on both sides within a certain distance in front of the road as the first discrete target position point information; the camera device obtains all the discrete target position points of the lane lines on both sides in the historical time domain as the second discrete target position point information; after fusing the first discrete target position point information and the second discrete target position point information together, a quadratic optimized lane line equation is obtained by re-linear fitting.

[0073] The camera device receives the quadratic fitting information sent by the control terminal. The camera device fuses all the discrete target position point information of the lane lines on both sides within a future time domain (such as 100 meters in front) and all the discrete target position point information of the lane lines on both sides within a certain time domain (historical time domain) before this future time domain, and inputs it into the lane line information quadratic optimization module; the lane line information quadratic optimization module removes the noise (deviation points) from all the discrete target position point information within the extended time domain, and re-linearly fits to obtain a quadratic optimized lane center line equation.

[0074] In an alternative embodiment, the camera device sends the detected lane line information within a certain distance in front of the road and the lane line information in the historical time domain to the control terminal, so that the control terminal re-linearly fits to obtain a quadratic optimized lane center line equation.

[0075] Compared with the unidirectional information transmission link structure from the intelligent driving perception layer to the planning and control layer currently, the vehicle control method provided by the embodiments of the present disclosure can feedback the results of the planning and control layer to the perception layer, perform quadratic optimization on the perception layer information, improve the effectiveness and stability of the perception layer information, and reduce the risk that the invalid and deviated information of the perception layer is directly executed by the planning and control layer.

[0076] In an exemplary embodiment of the present disclosure, the camera device detects the lane lines in front of the vehicle, and the fitting calculation to obtain the lane center line equation within a certain future time domain after the current moment may include:

[0077] The camera device detects the front lane lines, obtains and stores all the discrete target position point information of the lane lines on both sides within a certain distance in front of the road; the camera device fits and calculates the lane center line equation within a certain future time domain according to all the discrete target position point information of the lane lines on both sides within a certain distance in front of the road.

[0078] The camera device outputs all the discrete target position point information of the lane lines on both sides within a certain distance in front of the road through the detection and recognition of the front lane lines; the vehicle stores in real time all the discrete target position point information of the lane lines on both sides within a certain distance in front of the vehicle at the current moment; the camera device fits and calculates the lane center line equation within a certain future time domain beyond the current moment according to the discrete target position point information of the lane lines.

[0079] In an exemplary embodiment of the present disclosure, the quadratic fitting information may include: a time period during which the variance of the desired yaw rate of the vehicle is greater than a set threshold, and the desired yaw rate is predicted by the control end according to the lane centerline equation. The first discrete target position point information may include: all discrete target position point information of the lane lines on both sides corresponding to a time period within a certain distance in front of the road acquired by the camera device.

[0080] The control end may return the time period during which the variance of the desired yaw rate is greater than the set threshold to the camera device, and the camera device re-linearly fits the lane line information within this time period to obtain a quadratic optimized lane centerline equation. For example, the camera device acquires lane line data 100 meters in front of the vehicle, and the control end predicts and determines that the time period during which the variance of the desired yaw rate is greater than the set threshold is from 40 meters to 50 meters in front. The control end returns the corresponding time period from 40 meters to 50 meters in front to the camera device. The camera device combines all the discrete target position point information of the lane lines on both sides within the future time domain (from 40 meters to 50 meters in front) and all the discrete target position point information of the lane lines on both sides within a certain time domain before this future time domain (historical time domain), and inputs it into the lane line information quadratic optimization module; the lane line information quadratic optimization module removes noise (deviating points) from all the discrete target position point information within the extended time domain and re-linearly fits to obtain the quadratic optimized lane line information.

[0081] Figure 4 The structural block diagram of the vehicle control device provided for an exemplary embodiment of the present disclosure is as Figure 4 shown. The vehicle control device may include a memory 41 and a processor 42.

[0082] The memory is used to store execution instructions. The processor may be a central processing unit (CPU for short), or an application specific integrated circuit (ASIC for short), or one or more integrated circuits for implementing the embodiments of the present disclosure. When the vehicle control device runs, communication occurs between the processor and the memory, and the processor calls the execution instructions to perform the following operations:

[0083] The control end acquires the lane centerline equation input by the camera device on the vehicle, and the lane centerline equation is obtained by the camera device through detection and fitting calculation of the lane lines in front of the vehicle to obtain the lane centerline equation within a certain future time domain after the current moment;

[0084] The control end plans the desired tracking trajectory of the vehicle according to the lane centerline equation and determines whether the road geometric structure sensed by the camera device has changed;

[0085] When it is determined that the road geometry structure sensed by the camera device has changed, perform a second-order fitting on the lane lines in front of the vehicle detected by the camera device to re-linearly fit and obtain a second-order optimized lane centerline equation.

[0086] In an exemplary embodiment of the present disclosure, when the processor plans the expected tracking trajectory of the vehicle according to the lane centerline equation and determines whether the road geometry structure sensed by the camera device has changed, it may include:

[0087] According to the lane centerline equation, predict the expected steering angle for lateral control of the vehicle within a certain future time domain;

[0088] According to the lateral control steering angle and the state information of the vehicle's travel at the current moment, predict the expected yaw rate of the vehicle within a certain future time domain;

[0089] Determine whether the road geometry structure sensed by the camera device has changed according to the expected yaw rate.

[0090] In an exemplary embodiment of the present disclosure, when the processor determines whether the road geometry structure sensed by the camera device has changed according to the expected yaw rate, it may include:

[0091] Calculate the variance of the expected yaw rate within a certain future time domain; compare the variance of the expected yaw rate with a set threshold, and when the variance of the expected yaw rate is greater than the set threshold, determine that the road geometry structure sensed by the camera device has changed.

[0092] In an exemplary embodiment of the present disclosure, the state information may include at least one of the following: vehicle speed, acceleration, yaw rate, and heading angle.

[0093] In an exemplary embodiment of the present disclosure, when the processor performs a second-order fitting on the lane lines in front of the vehicle detected by the camera device to re-linearly fit and obtain a second-order optimized lane centerline equation, it may include:

[0094] Obtain the lane line information within a certain distance in front of the road required for the second-order fitting and the lane line information in the historical time domain from the camera device to re-linearly fit and obtain a second-order optimized lane centerline equation;

[0095] Or,

[0096] Send second-order fitting information to the camera device for instructing the camera device to re-linearly fit and obtain a second-order optimized lane centerline equation.

[0097] In an exemplary embodiment of the present disclosure, the processor re - linearly fits to obtain a quadratic - optimized lane centerline equation, which may include:

[0098] Obtain all discrete target position point information of the two - side lane lines within a certain distance in front of the road detected by the camera device as the first discrete target position point information;

[0099] Obtain all discrete target positions of the two - side lane lines in the historical time domain detected by the camera device as the second discrete target position point information;

[0100] After fusing the first discrete target position point information and the second discrete target position point information together, re - linearly fit to obtain a quadratic - optimized lane line equation.

[0101] In an exemplary embodiment of the present disclosure, the quadratic fitting information may include: the time period when the variance of the expected yaw rate is greater than a set threshold, and the quadratic fitting information is used to instruct the camera device to re - linearly fit the lane line information within this time period to obtain a quadratic - optimized lane centerline equation.

[0102] Figure 5 The structural block diagram of the camera device provided by an exemplary embodiment of the present disclosure is as Figure 5 shown. The camera device may include a camera 51, a memory 52, and a processor 53.

[0103] The camera is used to collect the lane line information in front of the vehicle and send it to the processor.

[0104] The memory is used to store execution instructions. The processor may be a central processing unit (CPU for short), or an application - specific integrated circuit (ASIC for short), or one or more integrated circuits for implementing the embodiments of the present disclosure. When the camera device runs, the processor communicates with the memory, and the processor calls the execution instructions to perform the following operations:

[0105] The camera device detects the lane lines in front of the vehicle, fits and calculates to obtain the lane centerline equation within a certain future time domain after the current moment, and sends the lane centerline equation to the control end;

[0106] The camera device sends the lane line information within a certain distance in front of the road detected and the lane line information in the historical time domain to the control end, so that the control end re - linearly fits to obtain a quadratic - optimized lane centerline equation;

[0107] Or,

[0108] When the camera device receives the quadratic fitting information sent by the control terminal, according to the lane line information within a certain distance in front of the detected road and the lane line information in the historical time domain, it re-linearly fits to obtain a quadratic-optimized lane center line equation, and sends the quadratic-optimized lane center equation to the control terminal.

[0109] In an exemplary embodiment of the present disclosure, the processor detects the lane lines in front of the vehicle and fits and calculates the lane center line equation within a certain future time domain after the current moment, which may include:

[0110] The camera device detects the front lane lines and obtains and stores all discrete target position point information of the two side lane lines within a certain distance in front of the road;

[0111] The camera device fits and calculates the lane center line equation within the certain future time domain according to all discrete target position point information of the two side lane lines within a certain distance in front of the road.

[0112] In an exemplary embodiment of the present disclosure, the processor re-linearly fits to obtain a quadratic-optimized lane center line equation, which may include:

[0113] Obtain all discrete target position point information of the two side lane lines within a certain distance in front of the road as the first discrete target position point information;

[0114] Obtain all discrete target position points of the two side lane lines in the historical time domain as the second discrete target position point information;

[0115] After combining the first discrete target position point information and the second discrete target position point information, re-linearly fit to obtain a quadratic-optimized lane line equation.

[0116] In an exemplary embodiment of the present disclosure, the quadratic fitting information may include: the time period when the variance of the expected yaw angular velocity of the vehicle is greater than a set threshold, and the expected yaw angular velocity is predicted by the control terminal according to the lane center line equation;

[0117] The first discrete target position point information may include: all discrete target position point information of the two side lane lines corresponding to the time period within a certain distance in front of the road obtained by the camera device.

[0118] Those of ordinary skill in the art will understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In the hardware implementation, the division of functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be executed by several physical components in cooperation. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

Claims

1. A vehicle control method, characterized in that, Including: The control end obtains the lane centerline equation input by the camera device on the vehicle. The lane centerline equation is obtained by fitting and calculating the lane lines in front of the vehicle detected by the camera device to obtain the lane centerline equation within a certain future time domain after the current moment; The control end plans the expected tracking trajectory of the vehicle according to the lane centerline equation and determines whether the road geometric structure sensed by the camera changes; When it is determined that the road geometric structure sensed by the camera device changes, the lane lines in front of the vehicle detected by the camera device are secondarily fitted to re-linearly fit and obtain a secondarily optimized lane centerline equation; Among them, the re-linearly fitting to obtain the secondarily optimized lane centerline equation includes: Obtaining all discrete target position point information of the lane lines on both sides within a certain distance in front of the road detected by the camera device as the first discrete target position point information; Obtaining all discrete target position points of the lane lines on both sides in the historical time domain detected by the camera device as the second discrete target position point information; After fusing the first discrete target position point information and the second discrete target position point information together, re-linearly fitting to obtain a secondarily optimized lane line equation.

2. The method according to claim 1, characterized in that, The control end plans the expected tracking trajectory of the vehicle according to the lane centerline equation and determines whether the road geometric structure sensed by the camera device changes, including: According to the lane centerline equation, predicting the expected steering angle of the vehicle's lateral control within the certain future time domain; According to the lateral control steering angle and the vehicle driving state information at the current moment, predicting the expected yaw angular velocity of the vehicle within the certain future time domain; Judging whether the road geometric structure sensed by the camera device changes according to the expected yaw angular velocity.

3. The method according to claim 2, wherein The judging whether the road geometric structure sensed by the camera device changes according to the expected yaw angular velocity includes: Calculating the variance of the expected yaw angular velocity within the certain future time domain; Comparing the variance of the expected yaw angular velocity with a set threshold. When the variance of the expected yaw angular velocity is greater than the set threshold, it is determined that the road geometric structure sensed by the camera device changes.

4. The method according to claim 2 or 3, characterized in that, The state information includes at least one of the following: vehicle speed, acceleration, yaw angular velocity, and heading angle.

5. The method according to any one of claims 1 to 3, characterized in that, The secondarily fitting the lane lines in front of the vehicle detected by the camera device to re-linearly fit and obtain a secondarily optimized lane centerline equation includes: Obtaining the lane line information within a certain distance in front of the road required for the second fitting from the camera device and the lane line information in the historical time domain to re-linearly fit and obtain a secondarily optimized lane centerline equation; Or, Sending second fitting information to the camera device for instructing the camera device to re-linearly fit and obtain a secondarily optimized lane centerline equation.

6. A vehicle control method, characterized in that, Including: The camera device detects the lane lines in front of the vehicle, fits and calculates the lane centerline equation within a certain future time domain after the current moment, and sends the lane centerline equation to the control end; The camera device sends the lane line information within a certain distance in front of the detected road and the lane line information in the historical time domain to the control terminal, so that the control terminal re-performs linear fitting to obtain a secondarily optimized lane centerline equation; Or, When the camera device receives the second fitting information sent by the control terminal, it re-performs linear fitting based on the lane line information within a certain distance in front of the detected road and the lane line information in the historical time domain to obtain a secondarily optimized lane centerline equation, and sends the secondarily optimized lane center equation to the control terminal; The re-performing linear fitting to obtain a secondarily optimized lane centerline equation includes: The camera device acquires all discrete target position point information of the lane lines on both sides within a certain distance in front of the road as the first discrete target position point information; The camera device acquires all discrete target position points of the lane lines on both sides in the historical time domain as the second discrete target position point information; After fusing the first discrete target position point information and the second discrete target position point information together, re-perform linear fitting to obtain a secondarily optimized lane line equation.

7. The method according to claim 6, wherein The camera device detects the lane lines in front of the vehicle and performs fitting calculation to obtain a lane centerline equation within a certain future time domain after the current moment, including: The camera device detects the lane lines in front, and obtains and stores all discrete target position point information of the lane lines on both sides within a certain distance in front of the road; The camera device performs fitting calculation based on all discrete target position point information of the lane lines on both sides within a certain distance in front of the road to obtain the lane centerline equation within the certain future time domain.

8. The method according to claim 6, wherein The second fitting information includes: the time period when the variance of the expected yaw rate of the vehicle is greater than a set threshold, and the expected yaw rate is predicted by the control terminal according to the lane centerline equation; The first discrete target position point information includes: all discrete target position point information of the lane lines on both sides corresponding to the time period within a certain distance in front of the road acquired by the camera device.

9. A vehicle control device, characterized in that, It includes a memory and a processor. The memory is used to store execution instructions; the processor calls the execution instructions to execute the vehicle control method according to any one of claims 1-5.

10. A camera device, characterized in that, It includes: A camera, a memory and a processor. The memory is used to store execution instructions; The processor calls the execution instructions to execute the vehicle control method according to any one of claims 6-8.

Images