A vehicle control method, a vehicle, and a storage medium

Abstract

The application discloses a vehicle control method, a vehicle and a storage medium, and relates to the technical field of vehicle control, and solves the problem that an automatic driving system cannot be safely parked when a fault occurs. The method comprises the following steps: determining lane line information according to image information or map information; determining a parking track according to the lane line information; and controlling the vehicle according to the parking track. The image information or the map information is used as auxiliary information for safe parking, the lane line information of a road where the vehicle is located is determined according to the image information or the map information, and the lane line information is used to assist parking. The parking track is determined according to the lane line information, the vehicle is controlled according to the parking track, safe parking of the vehicle is realized, and the safety of the vehicle and a driver is ensured. Meanwhile, the complexity of a safe parking system is reduced and the economy is improved under the premise of ensuring safe parking.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a vehicle control method, a vehicle, and a storage medium. Background Technology

[0002] In highly automated (driverless) vehicles, the autonomous driving system may malfunction, making safe stopping impossible and potentially dangerous. Current technologies employ two independent, identical autonomous driving systems for redundancy, but this is costly. Other vehicles brake directly when the autonomous driving system fails, without any sensory information to assist in stopping; this design cannot guarantee safe and reliable stopping. Summary of the Invention

[0003] This invention provides a vehicle control method, a vehicle, and a storage medium to address the problem of inability to guarantee parking safety when autonomous driving malfunctions.

[0004] According to one aspect of the present invention, a vehicle control method is provided, the method comprising:

[0005] Determine lane line information based on image or map information;

[0006] Determine the parking trajectory based on lane line information; and

[0007] Vehicles are controlled based on their parking trajectory.

[0008] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0009] Image acquisition device, used to acquire image information;

[0010] At least one processor; and

[0011] A memory that is communicatively connected to at least one processor; wherein,

[0012] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the vehicle control method of any embodiment of the present invention.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the vehicle control method of any embodiment of the present invention.

[0014] The technical solution of this invention solves the problem of unsafe parking in the event of an autonomous driving system malfunction by determining lane line information based on image or map information, determining a parking trajectory based on the lane line information, and controlling the vehicle based on the parking trajectory. It uses image or map information as auxiliary information for safe parking, determining the lane line information of the road where the vehicle is located based on the image or map information, and using the lane line information to assist parking. By determining the parking trajectory using the lane line information and controlling the vehicle based on the parking trajectory, safe parking is achieved, ensuring the safety of the vehicle and the driver. Simultaneously, it reduces the complexity of the safe parking system and improves economic efficiency while ensuring safe parking.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a vehicle control method provided according to Embodiment 1 of the present invention;

[0018] Figure 2 This is a flowchart of a vehicle control method provided according to Embodiment 2 of the present invention;

[0019] Figure 3 This is a flowchart illustrating the implementation of state update for an image acquisition device according to Embodiment 2 of the present invention.

[0020] Figure 4 This is a schematic diagram of the structure of a vehicle that implements the vehicle control method of this invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1

[0024] Figure 1 This is a flowchart illustrating a vehicle control method according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving safe parking control of a vehicle. The method can be executed by a computer device, which can be installed on the vehicle. Figure 1 As shown, the method includes:

[0025] S101. Determine lane line information based on image or map information.

[0026] In this embodiment, image information can specifically be understood as information from images collected during vehicle operation. Image information may include information about the vehicle's surrounding environment, the road the vehicle is traveling on, etc. Image information is collected by an image acquisition device, which can be installed on the vehicle. The image acquisition device can be a camera, video camera, etc. Map information refers to map information of the road the vehicle is traveling on, typically provided to the autonomous driving system by a third-party map provider. For example, the autonomous driving system obtains a map from a third-party map provider and combines it with positioning information returned by the Global Positioning System (GPS) to obtain map information near the vehicle's location. Lane line information can specifically be understood as information related to lane lines on the road the vehicle is traveling on. For example, lane line information can be functions or parameters describing lane lines.

[0027] Specifically, the system acquires image information from the image acquisition device, obtains map information from the autonomous driving system, and evaluates the reliability of both image and map information. Reliable information is then selected to assist the vehicle in safely parking. The reliability of both image and map information is assessed separately, and one type of information is selected to determine lane line information. For example, lane lines are filtered from the image information, and through data processing, lane line information that can represent the lane lines is determined.

[0028] S102. Determine the parking trajectory based on lane line information.

[0029] In this embodiment, the parking trajectory can be specifically understood as the trajectory used to control the vehicle when it stops. For example, when the vehicle is driving on the road, it travels in the middle of the lane lines on both sides according to traffic rules. When the vehicle's automatic driving system malfunctions, the vehicle needs to stop according to the parking trajectory to ensure vehicle safety.

[0030] Specifically, lane line information refers to the lane line information on both sides of the vehicle. However, the lane line information collected by the image acquisition device may have problems such as inaccurate information or missing information (for example, only one side of the lane line). Therefore, after determining the lane line information, it is necessary to judge whether the lane line information is accurate and reliable, and at the same time, determine whether the lane line information is the information of one side of the lane line or the information of both sides of the lane line. Based on the lane line information, the corresponding path is selected as the parking trajectory.

[0031] S103. Control the vehicle based on the parking trajectory.

[0032] After determining the parking trajectory, corresponding control commands can be generated directly based on the parking trajectory to control the vehicle to brake along the parking trajectory and achieve safe parking. The control commands can be steering wheel control commands, deceleration commands, etc. Alternatively, the tracking error of the vehicle relative to the trajectory can be determined based on the parking trajectory, error delay compensation can be performed based on the tracking error, and corresponding control commands can be generated based on the compensated information to control the vehicle to brake safely, so that the vehicle brakes along the parking trajectory with a smaller tracking error.

[0033] This invention provides a vehicle control method that solves the problem of unsafe parking in the event of an autonomous driving system malfunction by determining lane line information based on image or map information, determining a parking trajectory based on the lane line information, and controlling the vehicle based on the parking trajectory. This method uses image or map information as auxiliary information for safe parking, determining the lane line information of the road where the vehicle is located based on the image or map information, and using the lane line information to assist parking. By determining the parking trajectory based on the lane line information and controlling the vehicle according to the parking trajectory, safe parking is achieved, ensuring the safety of the vehicle and the driver. Simultaneously, it reduces the complexity of the safe parking system and improves economic efficiency while ensuring safe parking.

[0034] Example 2

[0035] Figure 2 This is a flowchart of a vehicle control method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiments. Figure 2 As shown, the method includes:

[0036] S201. Obtain image information and map information.

[0037] When the vehicle's autonomous driving system (or host computer) malfunctions and is unable to autonomously control the vehicle to complete an emergency stop, it acquires map and image information and performs vehicle parking control based on the image or map information.

[0038] S202. In response to the availability of map information, determine lane line information based on the map information.

[0039] Determining the availability of map information: Autonomous driving systems typically have monitoring nodes that monitor the map module's status. These nodes forward the map module's status, which reflects the map information's condition. When map information becomes unusable due to low accuracy, missing data, or other issues, it cannot be used reliably to control the vehicle and ensure safe stopping. In such cases, the monitoring node will report an error indicating map information unavailable and send this message to the intelligent devices executing vehicle control methods.

[0040] Specifically, the monitoring node will report an error if any of the following steps of the map information forwarding node of the autonomous driving system fails: 1. Reading the map (failed); 2. Reading the vehicle location (failed); 3. Determining the current lane line from the map (location is outside the map range, lane line not found); 4. Fitting the lane line (too few lane line boundary points); 5. Sending the lane line (failed).

[0041] Alternatively, the intelligent device executing the vehicle control method can determine the availability of map information by monitoring the transmission and reception status of messages related to high-precision map information. When map information is available, it is considered reliable and can be used to assist the vehicle in safely parking. Therefore, lane line information can be determined based on the map information. The methods for determining lane line information based on map information can be as follows: First, determine the vehicle's location on the map. The map will pre-store the lane lines and lane line information for each road. Then, determine the lane line information based on the vehicle's location. Second, to reduce communication overhead, after determining the lane lines based on the vehicle's location, determine the lane line information by fitting data to the lane lines. For example, fit a cubic curve and use the curve parameters as the lane line information.

[0042] When map information is available, the reliability of image information is verified using map information to determine whether the image information is available and then saved. Since both map information and image information are updated in real time, the availability of image information is also updated in real time.

[0043] S203. In response to map information being unavailable but image information being available, determine lane line information based on the image information.

[0044] When map information is unavailable, it cannot be used to assist vehicles in safe parking; image information is required instead. When map information is unavailable, the previous verification result regarding the availability of image information is retrieved to determine its usability. When image information is available, lane lines are extracted from the image, and data fitting is performed on these lane lines to determine their information. Lane lines can be extracted from the image information using algorithms, neural network models, etc., to identify the pixels that constitute the lane lines. Data fitting is then performed based on the coordinates of these pixels to obtain the lane line information.

[0045] It is important to know that S202 and S203 are parallel steps, and in practical applications, one of them should be selected for execution.

[0046] As an optional embodiment of this embodiment, this optional embodiment is further optimized to include: the vehicle includes an image acquisition device, the image acquisition device is used to acquire image information, and the method further includes: determining whether the image information is available;

[0047] Specifically, determining whether the image information is available includes: in response to the image acquisition device being in a normal state, determining that the image information is available.

[0048] In this embodiment, the image acquisition device can be installed at the front left, front right, or center of the vehicle, or it can be a vehicle dashcam. During installation, the image acquisition device should ensure effective acquisition of lane markings and guarantee the accuracy of the image information. The image acquisition device can be configured with an independent power supply to ensure it continues to function normally even if some parts or equipment in the vehicle malfunction, providing reliable information for safe parking.

[0049] Specifically, image acquisition devices are installed on vehicles to collect image information and assist in safe parking. The status of the image acquisition device is determined, and its status can be divided into normal and abnormal. An image acquisition device in a normal state acquires usable image information, while an image acquisition device in an abnormal state acquires unusable image information. The status of the image acquisition device can be determined and updated based on map information and image data. The most recent status of the image acquisition device is obtained; if the status of the image acquisition device is normal, the image information is determined to be usable.

[0050] As an optional embodiment of this example, this optional embodiment is further optimized to include: the vehicle includes an image acquisition device, and the method further includes: updating the state of the image acquisition device based on the map information and image information in response to the availability of map information.

[0051] Specifically, the status of the image acquisition device can be determined based on map and image information. When map information is available, if the map information determines that the image information is unreliable, the status of the image acquisition device is determined to be abnormal, and the status is updated to abnormal. If the map information determines that the image information is reliable, the status of the image acquisition device is determined to be normal, and the status is updated to normal. A way to determine the reliability of image information using map information is if the lane line information in the map information and the image information differs significantly and is outside the allowable error range.

[0052] By updating the status of the image acquisition device in real time, it is possible to avoid using the image information from the image acquisition device to stop the vehicle even when the device malfunctions due to angle shift or functional damage.

[0053] Optional, Figure 3 The flowchart illustrates the implementation of a state update for an image acquisition device according to an embodiment of this application. The image information includes image lane line parameters, and the map information includes map lane line parameters. Updating the state of the image acquisition device based on the map information and the image information includes the following steps:

[0054] S301. Determine the lane line deviation of the image lane line parameters based on the map lane line parameters.

[0055] In this embodiment, the image lane line parameters can be specifically understood as the parameters of the lane lines in the image, which can uniquely identify a lane line; the map lane line parameters can be specifically understood as the parameters of the lane lines in the map. Here, lane line deviation can be specifically understood as the deviation of the lane lines in the image acquired by the image acquisition device from the lane lines in the map.

[0056] For example, the lane lines in this application are preferably represented using cubic curve parameters, and the relationship between the lane lines and the lane line parameters is as follows: y = c0 + c1*x + c2*x 2 +c3*x 3 Where y represents the lane line, and c0, c1, c2, and c3 are lane line parameters. For ease of calculation, the same location is used as the origin when determining the lane line parameters in both the image and the map.

[0057] Specifically, when map information is available, the map lane line parameters are used as a benchmark to determine the accuracy of the image lane line parameters, thereby confirming the reliability of the image acquisition device and its proper functioning. Alternatively, map lane line parameters can be determined by processing the lane lines in the map information, or the map lane line parameters can be obtained directly from the map information if they have been pre-processed. Image lane line parameters can also be determined by processing the lane lines in the image information, or the image acquisition device can identify and process the lane lines in the image information after acquisition to obtain the image lane line parameters directly. The deviation between the two lane lines is calculated using both the image lane line parameters and the map lane line parameters; for example, the average deviation between the image lane lines and the map lane lines within a preset distance can be calculated.

[0058] S302. Determine the probability parameters based on lane line deviation.

[0059] In this embodiment, the probability parameter can be specifically understood as a parameter used to evaluate the magnitude of the deviation between map lane lines and image lane lines. Assuming that the map lane lines and image lane lines conform to a parameter distribution type, the probability calculation formula is determined based on the parameter distribution type. The probability parameter is obtained by calculating the lane line deviation using the probability calculation formula.

[0060] For example, this application provides a method for calculating a probability parameter, comparing image lane lines with map lane lines based on the 3-Sigma criterion. Assuming the map lane lines are used as a reference, the deviation between the image acquisition device's lane lines and the map lane lines follows a normal distribution with a mean of 0 and a standard deviation of sigma. The average deviation *e* between the image lane lines and the map lane lines within a preset distance is calculated. *e* is used as the lane line deviation, and a probability parameter *P* with a value distributed in (-∞, -e)∪(e, ∞) is calculated. The probability parameter *P* can be used as an evaluation index for image lane lines; the larger the probability *P*, the smaller the deviation *e*. The preset distance can be any value or determined based on the safe distance during vehicle travel; for example, if the safe distance is 30-40m, the preset distance is 50m. The preset distance can also consider the effective recognition range of the image acquisition device.

[0061] S303. Update the count value according to the current vehicle speed, probability parameters and corresponding probability thresholds, wherein the count value is used to represent the state of the image acquisition device.

[0062] In this embodiment, the current vehicle speed can be specifically understood as the vehicle's speed at the current data processing moment. The probability threshold can be specifically understood as the boundary value of the probability, used to determine whether the probability parameters meet the requirements.

[0063] Specifically, the current vehicle speed can be obtained from the autonomous driving system or from sensors and other devices. A probability threshold corresponding to a probability parameter is determined, and the degree of match between the image lane lines and the map lane lines is determined by comparing the probability parameter and the probability threshold. Since a larger probability parameter results in a smaller deviation, a match can be defined as the image lane lines matching the map lane lines when the probability parameter is greater than or equal to the corresponding probability threshold; otherwise, it is defined as a mismatch. When the current vehicle speed meets certain conditions, if the image lane lines match the map lane lines, the count value is updated, for example, by decreasing the count value; if the image lane lines do not match the map lane lines, the count value is updated by increasing the count value.

[0064] Image acquisition devices are susceptible to temporary algorithmic failures, such as unstable lane line detection during curves and lane changes, or difficulties in lane line recognition when lane lines are absent or unclear. In such cases, it's inappropriate to conclude the camera is malfunctioning simply because the temporarily misidentified image lane lines don't match the map lane lines. Therefore, when monitoring the image acquisition device's status in real-time, a counter can be used to represent the number of times the image lane lines acquired by the device do not match the map lane lines over a given period. When the counter reaches a certain threshold, the image acquisition device can be considered abnormal, and the provided image lane line parameters are deemed unusable.

[0065] As an optional embodiment of this example, this optional embodiment is further optimized to include: the probability parameters include a first probability parameter, a second probability parameter, and a third probability parameter, wherein the first probability parameter is the probability parameter of the left lane line, the second probability parameter is the probability parameter of the right lane line, and the third probability parameter is the probability parameter of the middle lane line; the image information also includes a self-diagnostic signal, which includes the status information of the image lane line parameters.

[0066] In this embodiment, the first probability parameter, the second probability parameter, and the third probability parameter are all probability parameters used to represent the probability parameters of different lane lines. The left lane line and the right lane line are the lane lines on the left and right sides of the vehicle during driving. Left and right can be distinguished according to the vehicle's front direction or driving direction. The self-diagnostic signal can be specifically understood as a signal determining the validity of the image acquired by the image acquisition device. The self-diagnostic signal can include the effective recognition range, quality, and data validity of the lane lines on both sides. The self-diagnostic signal provided in this embodiment preferably includes state information of the image lane line parameters, used to indicate the state of the image lane line parameters. Normal state image lane line parameter information can be used to indicate the normal state of the image acquisition device and for safe parking.

[0067] This optional embodiment further uses A1-A2 to update the count value based on the current vehicle speed, probability parameters, and the corresponding probability threshold:

[0068] A1. In response to the current vehicle speed being greater than the speed threshold and the third probability parameter being less than the first probability threshold, the count value is incremented according to a preset step size.

[0069] In this embodiment, the speed threshold can be understood as a boundary value used to measure speed, and the speed threshold can be preset according to actual needs. The magnitude of the first probability threshold can be set according to needs. The preset step size can be understood as a preset value, such as 1, 2, etc.

[0070] The current vehicle speed is compared with a speed threshold. If the current vehicle speed is greater than the speed threshold, the third probability parameter and its corresponding first probability threshold are further compared. If the current vehicle speed is greater than the speed threshold and the third probability parameter is less than the first probability threshold, the lane lines in the image do not match the lane lines on the map. The count value is then incremented by a preset step size, for example, the count value can be incremented by one.

[0071] A2. In response to the current vehicle speed being greater than the speed threshold and the third probability parameter being not less than the first probability threshold, the count value is updated based on the image lane line parameters, the self-diagnostic signal, the first probability parameter, and the second probability parameter.

[0072] The current vehicle speed is compared to a speed threshold. If the current vehicle speed is greater than the speed threshold, the third probability parameter and its corresponding first probability threshold are compared. If the current vehicle speed is greater than the speed threshold and the third probability parameter is greater than or equal to the first probability threshold, the image lane line matches the map lane line, and the count value is updated. This update includes decrementing the count value. Since the matching of image lane lines with map lane lines includes different cases such as matching the middle lane line, the left lane line, and the right lane line, the count value is further updated based on the image lane line parameters, self-diagnostic signals, the first probability parameter, and the second probability parameter. For example, when the left lane line or the right lane line matches, the count value is decremented respectively; when the middle lane line matches and the data for both left and right lane lines are normal, the count value is decremented.

[0073] As an optional embodiment of this example, this optional embodiment can further implement the updating of the count value based on the image lane line parameters, self-diagnostic signal, first probability parameter and second probability parameter through B1-B3:

[0074] B1. In response to the image lane line parameters and self-diagnostic signal meeting the first preset condition, the count value is decreased according to a preset step size.

[0075] In this embodiment, the first preset condition can be specifically understood as a pre-set condition, such as the valid range of data. It is determined whether the image lane line parameters and the self-diagnostic signal meet the first preset condition. For example, it is determined whether the image lane line parameters, such as the left lane line parameters and the right lane line parameters, are within the set valid range, and whether the self-diagnostic signal is within the set valid range. If so, it is determined that the first preset condition is met. When it is determined that the first preset condition is met, the count value is decremented according to a preset step size.

[0076] B2. In response to the image lane line parameters and self-diagnostic signal satisfying the first preset condition, and the first probability parameter not being less than the second probability threshold, the count value is decreased according to a preset step size.

[0077] When the image lane line parameters and self-diagnostic signals meet the first preset conditions, the first probability parameter and the second probability threshold are further compared. When the first probability parameter is not less than the second probability threshold, the left lane line in the image matches the left lane line on the map, and the count value is decreased according to the preset step size.

[0078] B3. In response to the image lane line parameters and self-diagnostic signal satisfying the first preset condition and the second probability parameter not being less than the third probability threshold, the count value is decreased according to a preset step size.

[0079] When the image lane line parameters and self-diagnostic signals meet the first preset condition, the second probability parameter and the third probability threshold are compared. When the second probability parameter is not less than the third probability threshold, the right lane line in the image matches the right lane line on the map, and the count value is decreased according to the preset step size.

[0080] In this embodiment, both the second probability threshold and the third probability threshold can be preset. The first probability threshold, the second probability threshold, and the third probability threshold have the same function: to measure whether the magnitude of the probability parameter meets the conditions.

[0081] Steps B1-B3 can be used to decrease the count value. The count decreases as conditions in different steps are met, and two or three of the steps can be met simultaneously. For example, assuming the image lane line parameters and self-diagnostic signal meet the first preset condition, the first probability parameter is not less than the second probability threshold, and the second probability parameter is not less than the third probability threshold, with a preset step size of 1; the image lane line parameters and self-diagnostic signal meet the first preset condition (execute step B1), and the count value decreases by 1; then it is determined that the first probability parameter is not less than the second probability threshold (execute step B2), and the count value decreases by 1 again; further, it is determined that the second probability parameter is not less than the third probability threshold (execute step B3), and the count value continues to decrease by 1, for a total decrease of 3.

[0082] In this embodiment, the first probability parameter, the second probability parameter, and the third probability parameter can be the same or different, and can be set according to actual needs.

[0083] In other cases, the count remains unchanged. For example, if the current vehicle speed is less than or equal to the speed threshold, the count will not be increased or decreased.

[0084] S304. In response to the updated count value not being greater than the count threshold, the status of the image acquisition device is determined to be normal.

[0085] In this embodiment, the counting threshold can be specifically understood as the boundary value of the count value, used to determine whether the count value meets the condition. When the updated count value is not greater than the counting threshold, the image acquisition device is determined to be in normal condition; when the updated count value is greater than or equal to the counting threshold, the image acquisition device is determined to be in abnormal condition.

[0086] After determining the lane line information, the parking trajectory is determined based on this information. When lane line information is determined from image information, it includes image lane line parameters and self-diagnostic signals. The self-diagnostic signals include the status information of the image lane line parameters. In this case, steps S204-S206 are executed to determine the parking trajectory. If the lane line information originates from image information, the parking trajectory is further selected. When lane line information is determined from map information, it includes map lane line parameters. In this case, step S207 is executed to determine the parking trajectory. It should be noted that steps S204-S206 and S207 are parallel processes.

[0087] S204. In response to the image lane line parameters and self-diagnostic signal satisfying the first preset condition, determine the first lane line according to the image lane line parameters, and determine the first lane line as the parking trajectory.

[0088] In this embodiment, the first lane line can be specifically understood as the lane line selected based on the image lane line parameters. The first preset condition can be that the left lane line parameters and the right lane line parameters in the image lane line parameters, as well as the self-diagnostic signal, are all within a set valid range. When the image lane line parameters and the self-diagnostic signal meet the first preset condition, the left lane line and the right lane line of the vehicle can be determined based on the image lane line parameters. Based on the left lane line and the right lane line, any lane line located between the left and right lane lines is selected as the first lane line. For example, the middle lane line is determined based on the left lane line and the right lane line, and the middle lane line is used as the first lane line, which is then determined as the parking trajectory.

[0089] S205. In response to the image lane line parameters and self-diagnostic signal satisfying the second preset condition, determine the second lane line according to the image lane line parameters, and determine the second lane line as the parking trajectory.

[0090] In this embodiment, the second preset condition may be that the self-diagnostic signal is within the effective range, and only one side of the left and right lane line parameters in the image lane line parameters is normal, that is, only one side of the lane line parameters is within the effective range. When the image lane line parameters and the self-diagnostic signal meet the second preset condition, the normal lane line parameters and abnormal lane line parameters in the image lane line parameters are determined, and the normal lane line parameters are selected as the second lane line; or, the abnormal lane line parameters can be corrected using the normal lane line parameters, and the corrected lane line parameters on both sides are considered normal, and the second lane line is determined based on the lane line parameters on the left and right sides, as described in S204.

[0091] Specifically, correcting abnormal lane line parameters can be done by: determining the direction (left or right) of the abnormal lane line parameters, generating lane lines in the corresponding direction (right or left) of the normal lane lines according to certain rules, and using the parameters of the generated lane lines as the corrected lane line parameters. For example, if the lane width is known in advance, and the lane lines on both sides are usually parallel, then by shifting the normal lane lines in the direction of the abnormal lane lines according to a certain width, the corrected lane lines can be obtained.

[0092] S206. In response to the image lane line parameters and self-diagnostic signal satisfying the third preset condition, a third lane line is generated according to the first preset rule, and the third lane line is determined as the parking trajectory.

[0093] In this embodiment, the third preset condition can be that the self-diagnostic signal is within the valid range, and the left lane line parameters and right lane line parameters in the image lane line parameters are both outside the valid range. The first preset rule can be specifically understood as a pre-set lane line generation rule.

[0094] When the image lane line parameters and self-diagnostic signals meet the third preset condition, a pre-set first preset rule is determined, and a third lane line is generated according to the first preset rule, which is then used as the parking trajectory. The first preset rule can be a selection rule for the cubic curve parameters c0, c1, c2, and c3 of the lane line. For example, if c0, c1, c2, and c3 are all 0, then the third lane line is a straight line starting from the center point of the vehicle's front and always pointing directly forward.

[0095] S207. Determine the fourth lane line based on the map lane line parameters, and define the fourth lane line as the parking trajectory.

[0096] The map lane line parameters can also include the lane line parameters on the left and right sides. Based on the map lane line parameters, a lane line is selected as the fourth lane line. For example, any lane line between the two lane lines can be selected as the fourth lane line. Preferably, the middle lane line of the map lane lines is selected as the fourth lane line, and the fourth lane line is used as the parking trajectory.

[0097] As an optional embodiment of this embodiment, this optional embodiment is further optimized to include: in response to the unavailability of map information and image information, generating a fifth lane line according to a second preset rule, and determining the fifth lane line as a parking trajectory.

[0098] In this embodiment, the second preset rule can be the same as or different from the first preset rule. When map information is unavailable and image information is unavailable, lane line information cannot be directly determined based on map information and image information. In this case, the second preset rule is obtained, a fifth lane line is generated according to the second preset rule, and the fifth lane line is determined as the parking trajectory.

[0099] S208. Determine the lateral error and heading error based on the parking trajectory.

[0100] In this embodiment, lateral error can be specifically understood as the error in the horizontal direction of the vehicle; heading error can be specifically understood as the error in the change of the vehicle's heading angle.

[0101] Once the parking trajectory is determined, its parameters are also determined. The expression for the parking trajectory is the same as that for the lane lines; therefore, the parameters of the parking trajectory are the same as those of the lane lines, including c0, c1, c2, and c3. The negative value of the zero-order parameter c0 is determined as the lateral error, and the arctangent function (arctan(-c1)) of the negative value of the first-order parameter c1 is determined as the heading error.

[0102] This application derives the meanings of c0 and c1 in the following embodiments: Assume the image acquisition device is positioned at x = 0, y = 0, with the y-axis pointing to the left of the vehicle and the x-axis pointing directly forward. The heading error is the angle between the lane line direction at x = 0 and the vehicle direction (i.e., the positive x-axis direction), which is equal to the arctangent function of the derivative of the curve at that point, i.e., heading error = arctan(0 - y'(x = 0)) = arctan(-c1). Considering that the heading error is usually very small, the lateral error is considered to be the distance (intercept) from the intersection of the curve and the line at x = 0 to the image acquisition device, which is equal to 0 - y(x = 0) = -c0.

[0103] S209. Compensate for heading errors based on vehicle driving information.

[0104] In this embodiment, vehicle driving information can be specifically understood as information related to the vehicle's driving process, such as yaw rate, steering wheel angle, and lane curvature data. The yaw rate can be collected by a yaw rate sensor, and the steering wheel angle can be collected by a steering wheel angle sensor. Lane curvature can be determined using an image acquisition device or a map. When a sensor fails, no compensation is required; that is, the compensated heading error is equal to the original heading error.

[0105] Assuming a delay duration of t_d, the delay compensation module calculates the vehicle's heading angle change delta_yaw and lane orientation change delta_lane_heading over the past t_d time using data from other sensors, and then adds this change to the heading error e_heading_camera calculated based on the lane line parameter c1.

[0106] e_heading_corrected=

[0107] e_heading_camera+delta_yaw–delta_lane_heading;

[0108] The calculation method for delta_yaw is as follows:

[0109] The change in vehicle heading angle is obtained by integrating the yaw rate. In this embodiment, the yaw rate can be directly measured by vehicle sensors. However, due to the limited accuracy of the sensors, a significant error, known as "zero-point offset," occurs after integrating the measured yaw rate (yaw_rate_sensor). Therefore, this application also uses the vehicle steering wheel angle and basic vehicle parameters to calculate the yaw rate (yaw_rate_model) (based on a two-wheel linear vehicle model):

[0110]

[0111] Where velocity is vehicle speed, L is vehicle wheelbase, δ is steering wheel angle, steering_ratio is steering ratio, and K is handling stability coefficient, calculated as follows:

[0112]

[0113] Where m is the vehicle mass, Lf is the distance from the vehicle's center of gravity to the front axle, Lr is the distance from the vehicle's center of gravity to the rear axle, C_alpha_f is the front wheel lateral stiffness, and C_alpha_r is the rear wheel lateral stiffness.

[0114] The rotation of the vehicle's steering wheel causes the vehicle to rotate, generating a yaw rate, which is then measured by a sensor. Therefore, let t_steering be the delay between the vehicle's actual yaw rate and the sensor's measurement signal, and t_sensor be the delay between the sensor's measured yaw rate and the actual yaw rate. Typically, t_sensor is less than t_d. Let the current time be t_0, then the heading error calculated by the camera corresponds to time (t_0-t_d). The change in the vehicle's heading angle within time t_d is calculated using the following method:

[0115] 1) Select all yaw rate measurements from time (t_0-t_d+t_sensor) to time t_0, accumulate them, and multiply them by the sampling period of the measurement signal to obtain the heading compensation delta_yaw_sensor.

[0116] 2) Select all vehicle steering wheel angle measurement signals from time (t_0-t_steering-t_sensor) to time (t_0-t_steering), calculate the corresponding yaw rate yaw_rate_model and accumulate them, and finally multiply by the sampling period of the measurement signal to obtain the heading compensation delta_yaw_steering.

[0117] 3) By superimposing the two compensation values, we obtain the vehicle heading angle change delta_yaw:

[0118] delta_yaw=delta_yaw_sensor+delta_yaw_steering

[0119] The calculation method for delta_lane_heading is as follows:

[0120] The change in lane orientation is calculated using the lane curvature (curvature) identified by the image acquisition device and the vehicle speed over a historical time period (t_d). Since the road curvature changes slowly, the quadratic parameter c2 and the linear parameter c1 from the current lane line parameters are selected to calculate the lane curvature.

[0121] According to the formula y = c0 + c1x + c2x 2 +c3*x 3 When x = 0, y' = c1, y” = 2c2.

[0122]

[0123] All vehicle speed measurement signals from time (t_0-t_d) to time t_0 are selected, accumulated, and multiplied by the lane curvature and the sampling period of the measurement signal to obtain the lane orientation change delta_lane_heading.

[0124] S210. Determine control commands and control the vehicle based on the compensated heading error and lateral error.

[0125] The control commands in this embodiment preferably include steering wheel angle commands and deceleration commands, which are sent to the lateral control system (which can be lateral control via the steering wheel, or steering by applying different braking forces to the left and right wheels) and the longitudinal control system (e.g., pneumatic and mechanical braking systems), respectively. The deceleration command can be a pre-determined deceleration in magnitude and direction. For example, to ensure the vehicle can stop safely under different road surface adhesion conditions, the deceleration command is selected as -3m / s². 2 The original steering wheel angle command is calculated based on the compensated heading and lateral errors using a given formula. The maximum safe steering wheel angle is then calculated based on the current vehicle speed. This maximum safe steering wheel angle is used to limit the original steering wheel angle command, resulting in a limited steering wheel angle command. If the difference between the limited steering wheel angle command and the current steering wheel angle exceeds a safe difference value defined for the current vehicle speed, the limit is applied again to obtain the final steering wheel angle command. The vehicle's lateral control system manipulates a motor connected to the steering column based on the steering wheel angle command, thereby controlling the steering wheel angle. The longitudinal control system uses the service brake or parking brake based on the deceleration command to slow the vehicle to a stop.

[0126] This application provides a vehicle control method that refines the process of determining lane line information. Lane line information is determined by judging whether map information and image information are available. The availability of image information is determined based on the status of the image acquisition device, preventing the acquisition of image information for safe parking even when the image acquisition device is malfunctioning due to angle deviation or functional damage, thus improving data reliability. This application further refines the status update of the image acquisition device, using a count value to represent the status of the image acquisition device. Lane line deviation is determined using map information and image information, and probability parameters are determined based on the lane line deviation. The count value is then updated based on the current vehicle speed, probability parameters, and corresponding probability thresholds. By setting a count value to represent the status of the image acquisition device, unreasonable status updates caused by unstable lane line detection can be avoided. Simultaneously, lateral and heading errors are determined based on the parking trajectory, and heading errors are compensated for to reduce errors, enabling accurate vehicle control and ensuring safe parking.

[0127] Example 3

[0128] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0129] like Figure 4 As shown, vehicle 40 includes an image acquisition device 400, at least one processor 401, and a memory, such as a read-only memory (ROM) 402 or a random access memory (RAM) 403, communicatively connected to the at least one processor 401. The image acquisition device 400 is used to acquire image information, and the number of image acquisition devices 400 can be one or more. The memory stores computer programs executable by at least one processor. The processor 401 can perform various appropriate actions and processes based on the computer program stored in the read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into the random access memory (RAM) 403. The RAM 403 can also store various programs and data required for the operation of vehicle 40. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0130] Multiple components in vehicle 40 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows vehicle 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0131] Processor 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 401 performs the various methods and processes described above, such as vehicle control methods.

[0132] In some embodiments, the vehicle control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on vehicle 40 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the vehicle control method described above may be performed. Alternatively, in other embodiments, processor 401 may be configured to perform the vehicle control method by any other suitable means (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0137] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0138] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0139] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0140] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle control method, comprising: Determine lane line information based on image or map information; The parking trajectory is determined based on the lane line information; as well as The vehicle is controlled according to the parking trajectory; The vehicle includes an image acquisition device, and the method further includes: When the map information becomes available, the state of the image acquisition device is updated based on the map information and the image information; The image information includes image lane line parameters, the map information includes map lane line parameters, and updating the state of the image acquisition device based on the map information and the image information includes: Based on the map lane line parameters, determine the lane line deviation of the image lane line parameters; The probability parameters are determined based on the lane line deviation. The count value is updated based on the current vehicle speed, the probability parameter, and the corresponding probability threshold, wherein the count value represents the state of the image acquisition device; and If the updated count value is not greater than the count threshold, the image acquisition device is determined to be in normal condition.

2. The method according to claim 1, wherein determining lane line information based on image information or map information includes: In response to the availability of the map information, lane line information is determined based on the map information; as well as In response to the map information being unavailable and the image information being available, lane line information is determined based on the image information.

3. The method according to claim 2, wherein the vehicle includes an image acquisition device for acquiring the image information, and the method further includes: Determine whether the image information is available; Specifically, determining whether the image information is usable includes: In response to the image acquisition device being in normal condition, it is determined that the image information is available.

4. The method according to claim 1, wherein the probability parameters include a first probability parameter, a second probability parameter, and a third probability parameter, wherein, The first probability parameter is the probability parameter of the left lane line, the second probability parameter is the probability parameter of the right lane line, and the third probability parameter is the probability parameter of the middle lane line. The image information also includes a self-diagnostic signal, which includes the status information of the image lane line parameters. The step of updating the count value based on the current vehicle speed, the probability parameter, and the corresponding probability threshold includes: In response to the current vehicle speed being greater than a speed threshold and the third probability parameter being less than a first probability threshold, the count value is incremented by a preset step size; In response to the current vehicle speed being greater than a speed threshold and the third probability parameter being not less than a first probability threshold, the count value is updated based on the image lane line parameters, the self-diagnostic signal, the first probability parameter, and the second probability parameter.

5. The method according to claim 4, wherein updating the count value based on the image lane line parameters, the self-diagnostic signal, the first probability parameter, and the second probability parameter comprises: In response to the image lane line parameters and self-diagnostic signal satisfying a first preset condition, the count value is decreased by a preset step size. In response to the image lane line parameters and self-diagnostic signal satisfying a first preset condition and the first probability parameter not being less than a second probability threshold, the count value is decreased by a preset step size. In response to the image lane line parameters and self-diagnostic signal satisfying the first preset condition and the second probability parameter not being less than the third probability threshold, the count value is decreased by a preset step size.

6. The method according to claim 1, wherein the lane line information includes image lane line parameters and a self-diagnostic signal, the self-diagnostic signal including status information of the image lane line parameters, and determining the parking trajectory based on the lane line information includes: In response to the image lane line parameters and self-diagnostic signal satisfying a first preset condition, a first lane line is determined according to the image lane line parameters, and the first lane line is determined as a parking trajectory; In response to the image lane line parameters and self-diagnostic signal satisfying the second preset condition, a second lane line is determined according to the image lane line parameters, and the second lane line is determined as the parking trajectory; In response to the image lane line parameters and self-diagnostic signals satisfying a third preset condition, a third lane line is generated according to a first preset rule, and the third lane line is determined as the parking trajectory.

7. The method according to claim 1, wherein the lane line information includes map lane line parameters, and determining the parking trajectory based on the lane line information includes: The fourth lane line is determined based on the map lane line parameters, and the fourth lane line is identified as the parking trajectory.

8. The method according to claim 1, wherein controlling the vehicle based on the parking trajectory comprises: The lateral error and heading error are determined based on the parking trajectory. The heading error is compensated based on the vehicle driving information; as well as The control command is determined and the vehicle is controlled based on the compensated heading error and the lateral error.

9. A vehicle comprising: Image acquisition device, used to acquire image information; At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle control method according to any one of claims 1-8.

10. A computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle control method of any one of claims 1-8.

Images