A control method, control system, storage medium, and electronic device for cornering.

Abstract

This invention discloses a control method, control system, storage medium, and electronic device for cornering, comprising: receiving voice commands; collecting vehicle information; determining the deviation distance between the vehicle's centerline and the lane's centerline based on the vehicle information, and determining a vehicle direction adjustment strategy based on the deviation distance; determining whether the voice command is correct according to the adjustment strategy; if correct, determining the vehicle direction adjustment angle based on the deviation distance, and performing cornering control based on the adjustment angle; receiving voice commands based on the driver's voice and determining different adjustment strategies to avoid misoperation problems; when turning, only one command needs to be sent for adaptive adjustment; after completing one vehicle direction adjustment, the system can determine in real time whether the vehicle is currently centered and then decide whether to continue to execute the next adjustment, improving the system's adaptability and stability.

Description

Technical Field

[0001] This invention relates to the field of automotive driver assistance systems, and more particularly to a control method, control system, storage medium, and electronic device for cornering. Background Technology

[0002] In the field of autonomous driving or assisted driving, centering control of vehicles when driving on high-curvature curves is an important research direction. Traditional curve centering control methods are usually based on data collected by sensors and preset control algorithms, such as PID control, MPC control, or LQR control. These algorithms are designed based on certain assumptions and typical operating conditions, but the actual driving environment is complex and varied. For example, the curvature of road curves varies greatly in different regions, ranging from relatively gentle curves to extremely sharp high-curvature curves. Once the preset control algorithm parameters are determined, it is difficult to adjust flexibly in the face of these complex changes, resulting in insufficient adaptability. Because the preset control algorithm cannot be adjusted in real time according to specific curve characteristics, such as the rate of curvature change and curve length, understeer or oversteer may occur when driving on high-curvature curves. Fixed control algorithms also cannot flexibly adapt to different driver styles and curve conditions. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of existing technologies by proposing a control method, control system, storage medium, and electronic device for cornering.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: a control method for cornering, comprising:

[0005] Receive voice commands;

[0006] Collect vehicle information;

[0007] Based on the vehicle information, the deviation distance between the vehicle centerline and the lane centerline is determined, and the vehicle direction adjustment strategy is determined based on the deviation distance.

[0008] Based on the adjustment strategy, determine whether the voice command is correct;

[0009] If correct, determine the adjustment angle of the vehicle direction based on the deviation distance;

[0010] Curve control is performed based on the adjusted angle.

[0011] As a further description of the above technical solution: Based on the vehicle information, the deviation distance between the vehicle centerline and the lane centerline is determined, including...

[0012] Determine if the vehicle is turning;

[0013] The methods for making the determination include:

[0014] Based on the vehicle information, a distance function between the vehicle and the lane line is fitted to obtain the curve radius;

[0015] A radius threshold is set. If the radius of the curve is less than the radius threshold, the vehicle is determined to be traveling on a curve.

[0016] As a further description of the above technical solution: the adjustment strategy includes:

[0017] When the deviation distance is positive, the vehicle moves towards the lane line that is away from the marked direction;

[0018] When the deviation distance is negative, the vehicle moves towards the lane line closer to the marked direction.

[0019] As a further description of the above technical solution: determining the deviation distance between the vehicle centerline and the lane centerline based on the vehicle information includes:

[0020] The direction of the lane line on either side is set as the marked direction. Based on the distance function, the difference between half of the sum of the distances of the lane lines on both sides and the distance of the vehicle from the lane line in the marked direction is calculated to obtain the deviation distance.

[0021] As a further description of the above technical solution: determining the adjustment angle of the vehicle direction based on the deviation distance includes:

[0022] Set the correction angle threshold;

[0023] Based on the deviation distance, determine the correction value for the vehicle direction and then determine whether the correction value is less than the correction angle threshold;

[0024] If it is less than the correction angle threshold, then the adjustment angle is the correction value;

[0025] If it is not less than the correction angle threshold, then the adjustment angle is the correction angle threshold.

[0026] As a further description of the above technical solution: Determining whether the voice command is correct based on the adjustment strategy includes:

[0027] Identify the adjustment direction of the voice command;

[0028] Determine whether the adjustment direction of the voice command is consistent with the vehicle direction of the adjustment strategy;

[0029] If they match, then the voice command is correct;

[0030] If they are inconsistent, then the voice command is incorrect.

[0031] As a further description of the above technical solution: the adjustment angle of the vehicle direction is determined based on the deviation distance, and then...

[0032] The deviation distance between the vehicle centerline and the lane centerline is determined again, and it is then detected whether the deviation distance is zero.

[0033] If it is not zero, then the adjustment angle of the vehicle direction is determined based on the deviation distance;

[0034] If the value is zero, the vehicle direction is maintained.

[0035] It also includes a control system, which is applicable to the control method described in any of the above technical solutions, comprising:

[0036] The receiving module generates voice commands using a speech recognition algorithm and then sends them.

[0037] The monitoring module monitors the position of the vehicle centerline, lane centerline, and lane lines to obtain position information;

[0038] The judgment module receives the voice command, determines the adjustment strategy based on the location information, and judges whether the voice command is correct based on the adjustment strategy. If it is correct, it sends adjustment information; if it is incorrect, it sends feedback information.

[0039] The execution module receives the adjustment information and adjusts the vehicle's direction.

[0040] The feedback module receives the feedback information and provides feedback reminders.

[0041] It also includes a computer-readable storage medium storing a computer program for running the control method, wherein the computer program causes a computer to perform the control method as described in any of the above technical solutions.

[0042] It also includes an electronic device, comprising:

[0043] One or more processors; memory; and

[0044] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including control methods for performing any of the above-described technical solutions.

[0045] The above technical solution has the following advantages or beneficial effects:

[0046] Based on the driver's voice commands, the system determines different adjustment strategies to avoid misoperation. When turning, only one command needs to be sent for adaptive adjustment. After completing one vehicle direction adjustment, the system can determine in real time whether the vehicle is centered and then decide whether to continue with the next adjustment, thus improving the system's adaptability and stability. Attached Figure Description

[0047] Figure 1 This is a flowchart of the control method proposed in this invention;

[0048] Figure 2 This is a schematic diagram of vehicle curve control in this invention;

[0049] Figure 3 This is a diagram illustrating the correspondence between the deviation distance and the adjustment angle value in this invention.

[0050] Figure 4 This is a schematic diagram of the control system proposed in this invention.

[0051] Legend:

[0052] 1. Receiving module; 2. Monitoring module; 3. Judgment module; 4. Execution module; 5. Feedback module. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Cornering centering control methods typically rely on sensor-collected data and preset control algorithms, such as PID control, MPC control, or LQR control. These algorithms are designed based on certain assumptions and typical operating conditions, but actual driving environments are complex and varied. For example, the curvature of road curves varies greatly in different regions, ranging from relatively gentle curves to extremely sharp curves. Once the preset control algorithm parameters are determined, they are difficult to adjust flexibly to cope with these complex changes, resulting in insufficient adaptability. Because the preset control algorithm cannot adjust in real time according to specific curve characteristics, such as the rate of curvature change and curve length, understeer or oversteer may occur when driving on curves with high curvature. Fixed control algorithms also cannot flexibly adapt to different driver styles and curve conditions.

[0055] One embodiment of the present invention provides a method for controlling driving on curves, comprising: receiving voice commands;

[0056] Collect vehicle information;

[0057] The deviation distance between the vehicle's centerline and the lane's centerline is determined based on vehicle information, and the vehicle's direction adjustment strategy is determined based on the deviation distance.

[0058] Based on the adjustment strategy, determine whether the voice command is correct;

[0059] If correct, determine the adjustment angle for the vehicle's direction based on the deviation distance;

[0060] Curve control is performed based on the adjusted angle.

[0061] Reference Figure 1 The specific control methods are as follows:

[0062] S1: Uses speech recognition algorithms to identify individuals, verify their identities, and receive voice commands;

[0063] In this embodiment, the speech recognition algorithm analyzes the acoustic features of the driver's voice commands, such as pitch, timbre, speech rate, intonation, and pronunciation habits, and compares them with driver voice samples pre-stored in the vehicle system. These voice samples are recorded when the driver first uses the function or during the system setup phase. Through pattern matching and feature extraction techniques, it determines whether the voice is from an authorized driver, thus completing the identity verification task. The algorithm then converts the driver's spoken words into voice commands that the computer can understand and process. Using its built-in acoustic and language models, the speech recognition algorithm processes the speech signal, determines the command text content, and receives it as a voice command.

[0064] Voice recognition technology is used to identify the voice commands issued by the driver, including adjusting direction or adjustment range. When the driver issues a voice command to center to the left or center to the right, the cockpit controller (DHU) receives and verifies the driver's identity, and then converts it into a bus signal to be sent to the automated driving controller (ADCU). When the automated driving controller receives the signal, it makes a judgment based on the current position of the vehicle.

[0065] S2: Determine the deviation distance between the vehicle centerline and the lane centerline based on vehicle information, and determine the vehicle direction adjustment strategy based on the deviation distance;

[0066] In this embodiment, the vehicle itself determines the position of its centerline using sensors. For example, wheel speed sensors installed near the front and rear axles can acquire the rotational speed information of each wheel. Combined with geometric parameters such as the vehicle's wheelbase and track width, a kinematic model is used to calculate the vehicle's real-time position and attitude, thereby determining the position of the vehicle's centerline. Furthermore, cameras on the vehicle (such as front-view and rear-view cameras) can also image the surrounding environment, and image recognition technology can be used to analyze the vehicle's contour features, further assisting in determining the position of the vehicle's centerline.

[0067] The determination of the lane centerline position primarily relies on the vehicle's vision system, which uses a forward-facing camera and image processing algorithms for identification. The forward-facing camera captures and identifies images of the road ahead of the vehicle, and then image processing algorithms analyze these images. For example, edge detection algorithms can identify road edge lines, and combined with lane geometry models (such as straight lanes and curved lanes) and road markings (such as lane dividers), the position of the lane centerline is determined.

[0068] Calculate the deviation distance based on the vehicle's centerline and the lane's centerline. Once the deviation distance is calculated, determine the direction the vehicle needs to turn based on the direction of the deviation. If the vehicle's centerline is to the left of the lane's centerline, the vehicle may need to turn right to reduce the deviation; conversely, if the vehicle's centerline is to the right of the lane's centerline, the vehicle may need to turn left to ensure the vehicle adjusts in the direction that reduces the deviation. If the deviation distance is small and the curve curvature is relatively small, only a slight steering adjustment is needed; however, if the deviation distance is large, or the curve curvature is large (such as in the case of a high-curvature curve), then a larger steering adjustment is required.

[0069] S3: Based on the adjustment strategy, determine whether the voice command is correct. If correct, control the vehicle to adjust according to the adjustment angle; check whether the deviation distance is zero. If not, continue to adjust the vehicle direction.

[0070] In this embodiment, the voice command is compared with the adjustment strategy to determine whether the voice command is correct. If correct, the vehicle is controlled to drive in a centered manner. The system will establish a correspondence model between the deviation distance and the required adjustment angle based on the characteristics of the vehicle, such as the characteristics of the vehicle's steering system, the steering response at different speeds, and common situations of driving on curves, as well as the reasonable adjustment range corresponding to curves with different curvatures. The system sets the angle value that needs to be adjusted for each deviation distance. In this embodiment, each deviation of 0.7cm corresponds to an adjustment of 5°, thereby adjusting the vehicle's direction.

[0071] Based on the vehicle information, determine the deviation distance between the vehicle centerline and the lane centerline, including determining whether the vehicle is driving on a curve.

[0072] The methods for making the determination include:

[0073] Based on the vehicle information, a distance function between the vehicle and the lane line is fitted to obtain the curve radius;

[0074] A radius threshold is set. If the radius of the curve is less than the radius threshold, the vehicle is determined to be traveling on a curve.

[0075] In this embodiment, vehicle sensors, such as cameras, millimeter-wave radar, and lidar, are used to collect real-time environmental and positional information about the vehicle, including road curvature, vehicle position, and speed. To facilitate the analysis of the relative relationship between the vehicle and the lane lines, a suitable coordinate system needs to be established. Lane lines generally have a certain geometric shape, commonly including straight lines, circular curves, spiral curves, or combinations thereof. The distance between the vehicle and the lane lines is fitted as a function by combining the vehicle's position parameters (coordinates and attitude information) and motion parameters (vehicle speed, acceleration, etc.).

[0076] A double helix curve model is established based on the lane lines of the curve. The parameters a, b, c, and d1 of the left and right lane lines detected by the camera are fitted, and the distance between the vehicle and the lane lines is obtained as a function with the vehicle coordinate system as the axis:

[0077] F(x) = a + bx + cx^2 + d1x^3;

[0078] Where a is the lateral offset, b is the heading angle, c is the initial curvature of the starting position, d1 is the rate of change of the curvature of the starting position, and x is the vehicle coordinate position, the curve radius in the curve centering control can be calculated as 1 / c.

[0079] Double helix curves can better simulate the complex curvature of lane lines in real-world curves. Compared to simple geometric curve models (such as circular curves and parabolas), they can more accurately capture the curvature changes of a curve from its starting position to different subsequent positions.

[0080] Lateral offset 'a' is calculated by identifying the pixel position of the lane line in the image and comparing it with the vehicle centerline in the vehicle coordinate system to determine the offset perpendicular to the vehicle's direction of travel. For the heading angle 'b', it is determined based on the angle between the direction of the lane line in the image and the reference line of the vehicle's direction of travel. The initial curvature 'c' and the rate of change of curvature 'd1' need to be calculated by image processing algorithms to determine the degree of curvature and its changes in the lane line at the starting position and in the surrounding area.

[0081] There is an inverse proportional relationship between curvature k and radius r, i.e., k = 1 / r. The initial curvature c at the starting position can be considered as the curve curvature k of the curve at the starting position. Taking the reciprocal 1 / c yields the corresponding curve radius r, allowing for quick determination of the curve radius and preliminary assessment of the size of the curve the vehicle is about to enter or is already in. For curves with smaller radii, the curvature is greater, and the vehicle may need to reduce speed and increase steering angle earlier to ensure safe and smooth passage through the curve and maintain an ideal centered position. For curves with larger radii, the vehicle control strategy may be more relaxed, and the vehicle direction can be adjusted promptly based on the adjustment strategy during centering control. A judgment module determines whether the vehicle is currently turning. A radius threshold is set; if the radius 1 / c is less than the threshold, the vehicle is considered to be in a large turn, and adjustments are made based on a function of the distance between the vehicle and the lane lines.

[0082] The adjustment strategies include:

[0083] When the deviation distance is positive, the vehicle moves towards the lane line that is away from the marked direction.

[0084] When the deviation distance is negative, the vehicle moves towards the lane line closer to the marked direction.

[0085] In this embodiment, the distance between the vehicle and the lane lines on both the left and right is used to determine whether the vehicle's centerline deviates from the lane centerline. This is determined based on the marked direction. If the marked direction is the left lane line and the deviation distance is a positive value greater than 0, the vehicle is determined to be veering to the left and needs to be moved to the right lane line. If the deviation distance is a negative value less than 0, the vehicle is determined to be veering to the right and needs to be moved to the left lane line. The vehicle's adjustment strategy is determined by the deviation distance. In autonomous driving or assisted driving systems, this adjustment strategy can automatically correct situations where the vehicle is slightly veering towards one lane line. By rationally controlling the vehicle's movement in different directions based on the positive or negative deviation distance, the vehicle can be effectively centered within the lane, avoiding the risk of collisions with adjacent vehicles or obstacles that may occur due to the vehicle being too close to one lane line.

[0086] Determining the deviation distance between the vehicle's centerline and the lane centerline based on vehicle information includes:

[0087] Set the direction of the lane line on either side as the marked direction. Calculate the difference between half the sum of the distances of the lane lines on both sides and the distance of the vehicle from the lane line in the marked direction, based on the distance function, to obtain the deviation distance.

[0088] In this embodiment, a vehicle coordinate system axis is established, and the direction of the lane line on either side is set as the marking direction. Based on the function of the distance between the vehicle and the lane line, FL(x) represents the equation of the left lane line and FR(x) represents the equation of the right lane line. The left direction of the vehicle is set as the marking direction, and the deviation distance is calculated. The deviation distance is the distance between the center line of the vehicle and the center line of the lane in the image generated by the monitoring.

[0089] Deviation distance = 1 / 2[FL(x0) + |FR(x0)|] - FL(x0);

[0090] After establishing the vehicle coordinate system, the direction of either lane line needs to be selected as the marking direction. This marking direction is primarily for providing a clear reference standard when calculating the deviation distance, allowing for a clearer comparison of the relative positions of the vehicle and the lane lines. The choice of marking direction can be arbitrary, depending on the actual situation and the lane line direction that is easier to calculate or better suited to the analysis requirements. If the relevant data for the left lane line is easier to obtain or process in subsequent calculations or analyses, then the direction of the left lane line can be selected as the marking direction. This embodiment uses the direction of the left lane line as the marking direction and provides the aforementioned deviation distance calculation function.

[0091] Adjusting the vehicle's direction based on the deviation distance includes:

[0092] Set a correction angle threshold. Based on the deviation distance, output an angle adjustment request and compare it with the correction angle threshold. If it is less than the correction angle threshold, make an adjustment. If it is greater than the correction angle threshold, make an adjustment based on the set correction angle threshold.

[0093] In this embodiment, setting a correction angle threshold is used to regulate and limit the magnitude of each angle adjustment. This ensures that when adjusting the vehicle's direction, it can effectively correct deviations and achieve the requirement of centering the vehicle, while also guaranteeing the stability and safety of the vehicle. Different vehicle types, driving scenarios, and road conditions may require different correction angle threshold settings. For example, in high-speed driving scenarios, vehicle stability is crucial for driving safety. In this case, the correction angle threshold may be relatively small to avoid excessive lateral acceleration caused by excessive angle adjustments, which could lead to loss of control. In low-speed driving scenarios with complex road conditions, the correction angle threshold can be set relatively larger so that the vehicle can more flexibly respond to various positional deviations and quickly adjust to a suitable driving position. The correction angle threshold is set for each angle adjustment. Based on the deviation distance, the required adjustment angle is calculated. It is then determined whether the angle exceeds the correction angle threshold. If it is less than the correction angle threshold, the angle can be adjusted directly. If it is greater than the correction angle threshold, the vehicle's direction is adjusted to the set threshold angle. After the adjustment is completed, monitoring is performed again.

[0094] Reference Figure 3 In a specific embodiment, assuming that the vehicle is driving on a curve and the deviation between the vehicle's centerline and the lane's centerline is detected to be 2.1cm, according to the preset correspondence model between the deviation distance and the required adjustment angle, each deviation of 0.7cm corresponds to an adjustment of 5°. At this time, the system will output an angle adjustment request, requesting that the vehicle's direction be adjusted by 15° (2.1cm / 0.7cm×5°=15°) in order to try to bring the vehicle back to the center position in the curve.

[0095] If the output angle adjustment request is to adjust by 10°, and the set correction angle threshold is 15°, since 10° is less than 15°, the system will adjust the vehicle direction by 10°, so that the vehicle moves in the direction that reduces the deviation distance.

[0096] If the output angle adjustment request is to adjust by 20°, and the set correction angle threshold is 15°, the vehicle's steering angle is limited by the angle limiter, and the vehicle's direction is adjusted by 15°. At this time, the vehicle's angle at the turning point is the sum of the vehicle's direction output by the ADCU control algorithm and the adjustment angle.

[0097] Based on the adjustment strategy, determine whether the voice command is correct, including:

[0098] Recognize the adjustment direction of voice commands;

[0099] Determine whether the adjustment direction of the voice command is consistent with the vehicle direction of the adjustment strategy;

[0100] If they match, the voice command is correct;

[0101] If they don't match, the voice command is incorrect.

[0102] In this embodiment, the system determines the correctness of the voice command based on whether the driver's voice command is to turn left or right, and whether the vehicle's centerline is deviated to the left or right of the lane's centerline. If correct, the system calculates and outputs a corresponding angle adjustment request based on the correspondence model between the actual deviation distance and the required adjustment angle. The angle value is a recommended value. In practice, due to the dynamic differences of different vehicle models, it is necessary to determine the correspondence model based on the actual situation before adjusting the angle. If incorrect, the voice command is not executed, and the human-machine interface (HMI) prompts the driver not to execute the command.

[0103] During vehicle driving control, accurately determining whether voice commands are consistent with pre-set adjustment strategies is crucial. If commands that do not conform to the actual situation or adjustment strategy are executed incorrectly, the vehicle may deviate from the expected driving trajectory, leading to the risk of collisions with other vehicles or obstacles, or failing to achieve the expected driving goal. It is necessary to analyze the received voice commands in detail to clarify the specific requirements for adjusting the vehicle's driving direction. For example, the voice command may be expressed as "drive to the left and center" or "drive to the right and center." The content regarding the direction adjustment (left, right) and the degree of adjustment (center) should be extracted. Based on the content of the voice command, the corresponding adjustment information should be generated and sent to the vehicle's execution module (such as the electric power steering system, vehicle power control system, etc.) to execute the adjustment action of the vehicle's driving direction.

[0104] Reference Figure 2 In one specific embodiment, if the vehicle is in position 1, the center line of the lane can be calculated from the left and right lanes detected by the camera. If the calculated deviation distance is greater than 0, it can be determined that the vehicle is veering to the left in the lane. If the driver inputs a command to center to the left, it is considered an incorrect command. Similarly, if the vehicle is in position 2, the center line of the lane can be calculated from the left and right lanes detected by the camera. If the calculated deviation distance is less than 0, it can be determined that the vehicle is veering to the right in the lane. If the driver inputs a command to center to the right, it is considered an incorrect command.

[0105] If the vehicle is in position 1, the center line of the lane can be calculated from the left and right lanes detected by the camera. If the calculated deviation distance is greater than 0, it can be determined that the vehicle is veering to the left in the lane. If the driver inputs a command to center to the right, it is considered a correct command. Similarly, if the vehicle is in position 2, the center line of the lane can be calculated from the left and right lanes detected by the camera. If the calculated deviation distance is less than 0, it can be determined that the vehicle is veering to the right in the lane. If the driver inputs a command to center to the left, it is considered a correct command.

[0106] The adjustment angle for the vehicle direction is determined based on the aforementioned deviation distance, and then...

[0107] The deviation distance between the vehicle centerline and the lane centerline is determined again, and it is then detected whether the deviation distance is zero.

[0108] If it is not zero, then the adjustment angle of the vehicle direction is determined based on the deviation distance;

[0109] If the value is zero, the vehicle direction will be maintained.

[0110] In this embodiment, the deviation distance between the adjusted vehicle centerline and the lane centerline is detected. If the deviation distance is zero, the vehicle centerline and the lane centerline coincide, and the vehicle is in a centered driving state. The vehicle direction is maintained at this time for driving control.

[0111] If the deviation distance is not zero, the vehicle centering control has not been completed. Adjustments are then made again based on the detected deviation distance between the vehicle's centerline and the lane's centerline. The position information of the vehicle's centerline and the lane's centerline is updated, the deviation distance is recalculated, and based on the recalculated deviation distance and the vehicle's current driving state, the vehicle's direction is adjusted according to the adjustment strategy. By continuously updating the position information, recalculating the deviation distance, and adjusting the vehicle's direction, the vehicle can gradually approach the centering position, achieving precise vehicle control. The driver only needs to send one command. After one adjustment, the monitoring module continuously judges whether FL(x) and FR(x) are equal, i.e., whether the vehicle is currently centered, and determines whether further adjustments are needed, improving the system's adaptability and stability.

[0112] Reference Figure 4 It also includes an embodiment of a control system, which is applicable to any of the control methods described above, including:

[0113] Receiver module 1 generates voice commands using a speech recognition algorithm and sends them out;

[0114] Monitoring module 2 monitors the positions of the vehicle centerline, lane centerline, and lane lines to obtain position information;

[0115] Judgment module 3 receives voice commands, determines adjustment strategies based on location information, and judges whether the voice commands are correct based on the adjustment strategies. If correct, it sends adjustment information; if incorrect, it sends feedback information.

[0116] Execution module 4 receives the adjustment information and adjusts the vehicle's direction.

[0117] Feedback module 5 receives feedback information and provides feedback reminders.

[0118] In this embodiment, the receiving module 1 uses a speech recognition algorithm to convert the driver's voice commands into voice commands that the computer can understand and process, and then sends them for further processing by subsequent modules.

[0119] Monitoring module 2 monitors the positions of the vehicle centerline, lane centerline, and lane lines in real time to obtain accurate location information. For monitoring the vehicle centerline, various sensors on the vehicle, such as wheel speed sensors, are used in conjunction with the vehicle's geometric parameters (wheelbase, track width, etc.) to calculate the vehicle's real-time position and attitude through a kinematic model, thereby determining the vehicle centerline position. Simultaneously, the onboard camera can also assist in determining the vehicle centerline position by imaging the surrounding environment and using image recognition technology to analyze the vehicle's own contour features. For monitoring the lane centerline and lane lines, the onboard vision system (usually composed of a forward-facing camera and related image processing software) is primarily used. Image processing algorithms such as edge detection, lane geometry modeling, and road sign recognition are employed to accurately determine the positions of the lane centerline and lane lines from the captured road images.

[0120] The judgment module 3 receives voice commands from the receiving module and obtains location information provided by the monitoring module. Then, it determines the adjustment strategy based on this information and judges whether the voice command is correct based on the determined adjustment strategy.

[0121] The execution module 4 receives adjustment information from the judgment module 3 and adjusts the vehicle's direction. After receiving the adjustment information, the execution module 4 interacts with the vehicle's steering system (such as an electric power steering system) and converts the specific requirements in the adjustment information, such as the direction and angle values ​​to be adjusted, into operating instructions that the steering system can execute, thereby realizing the actual adjustment of the vehicle's direction.

[0122] Feedback module 5 receives feedback information from judgment module 3 and provides feedback reminders. The feedback information usually includes the reason why the voice command is incorrect. This information is fed back to the human-machine interface (HMI) to remind the driver.

[0123] It also includes a computer-readable storage medium storing a computer program for operating the control method, wherein the computer program causes the computer to perform the following steps:

[0124] S1: Uses speech recognition algorithms to identify individuals, verify their identities, and receive voice commands;

[0125] S2: Determine the deviation distance between the vehicle centerline and the lane centerline based on vehicle information, and determine the vehicle direction adjustment strategy based on the deviation distance;

[0126] S3: Based on the adjustment strategy, determine whether the voice command is correct. If correct, control the vehicle to adjust according to the adjustment angle; check whether the deviation distance is zero. If not, continue to adjust the vehicle direction.

[0127] The computer-readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of a computer program from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a computer-readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the ASIC can reside in a user equipment. Of course, the processor and the computer-readable storage medium can also exist as discrete components in a communication device.

[0128] Specifically, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0129] It also includes an electronic device, comprising:

[0130] One or more processors; memory; and

[0131] One or more programs, wherein the programs are stored in memory and configured to be executed by one or more processors, the programs including steps for performing the following:

[0132] S1: Uses speech recognition algorithms to identify individuals, verify their identities, and receive voice commands;

[0133] S2: Determine the deviation distance between the vehicle centerline and the lane centerline based on vehicle information, and determine the vehicle direction adjustment strategy based on the deviation distance;

[0134] S3: Based on the adjustment strategy, determine whether the voice command is correct. If correct, control the vehicle to adjust according to the adjustment angle; check whether the deviation distance is zero. If not, continue to adjust the vehicle direction.

[0135] A memory is used to store computer programs. This memory may include high-speed random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0136] A processor is used to execute a computer program stored in memory to implement the control method described in the above embodiments. The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0137] Alternatively, the memory can be either standalone or integrated with the processor.

[0138] When memory is a device independent of the processor, electronic devices may also include a bus. This bus is used to connect the memory and the processor. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc.

[0139] It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments. In this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0140] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method for cornering, characterized in that, include: Receive voice commands; Collect vehicle information; Based on the vehicle information, the deviation distance between the vehicle centerline and the lane centerline is determined, and the vehicle direction adjustment strategy is determined based on the deviation distance. Based on the adjustment strategy, determine whether the voice command is correct; If correct, determine the adjustment angle of the vehicle direction based on the deviation distance; Curving control is performed based on the aforementioned adjustment angle; Determining the deviation distance between the vehicle centerline and the lane centerline based on the vehicle information includes: Determine if the vehicle is turning; The methods for making the determination include: Based on the vehicle information, a distance function between the vehicle and the lane line is fitted to obtain the curve radius; A radius threshold is set; if the radius of the curve is less than the radius threshold, the vehicle is determined to be traveling on a curve. The adjustment strategy includes: When the deviation distance is positive, the vehicle moves towards the lane line that is away from the marked direction; When the deviation distance is negative, the vehicle moves towards the lane line closer to the marked direction; Determining the deviation distance between the vehicle centerline and the lane centerline based on the vehicle information includes: The direction of the lane line on either side is set as the marked direction. Based on the distance function, the difference between half of the sum of the distances of the lane lines on both sides and the distance of the vehicle from the lane line in the marked direction is calculated to obtain the deviation distance.

2. The control method according to claim 1, characterized in that: Determining the adjustment angle of the vehicle direction based on the aforementioned deviation distance includes: Set the correction angle threshold; Based on the deviation distance, determine the correction value for the vehicle direction and then determine whether the correction value is less than the correction angle threshold; If it is less than the correction angle threshold, then the adjustment angle is the correction value; If it is not less than the correction angle threshold, then the adjustment angle is the correction angle threshold.

3. The control method according to claim 1, characterized in that: Based on the adjustment strategy, determining whether the voice command is correct includes: Identify the adjustment direction of the voice command; Determine whether the adjustment direction of the voice command is consistent with the vehicle direction of the adjustment strategy; If they match, then the voice command is correct; If they are inconsistent, then the voice command is incorrect.

4. The control method according to claim 1, characterized in that: The adjustment angle for the vehicle direction is determined based on the aforementioned deviation distance, and then... The deviation distance between the vehicle centerline and the lane centerline is determined again, and it is checked whether the deviation distance is zero. If it is not zero, then the adjustment angle of the vehicle direction is determined based on the deviation distance; If the value is zero, the vehicle direction is maintained.

5. A control system, characterized in that, The control system is applicable to the control method described in any one of claims 1-4, comprising: The receiving module generates voice commands using a speech recognition algorithm and then sends them. The monitoring module monitors the position of the vehicle centerline, lane centerline, and lane lines to obtain position information; The judgment module receives the voice command, determines the adjustment strategy based on the location information, and judges whether the voice command is correct based on the adjustment strategy. If it is correct, it sends adjustment information; if it is incorrect, it sends feedback information. The execution module receives the adjustment information and adjusts the vehicle's direction. The feedback module receives the feedback information and provides feedback reminders.

6. A computer-readable storage medium, characterized in that, It stores a computer program for running a control method, wherein the computer program causes a computer to perform the control method as described in any one of claims 1-4.

7. An electronic device, characterized in that, include: One or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including a control method as described in any one of claims 1-4.

Images