A perception sensor parameter calibration method, device, equipment and medium

Abstract

Embodiments of the present application disclose a kind of perception sensor parameter calibration method, device, equipment and medium.The method comprises: obtaining the driving parameter information under the running state of vehicle and the online calibration result of perception sensor, according to driving parameter information and online calibration result, update calibration result list, when detecting that intelligent driving function is opened, determine the target calibration result corresponding to the current collection driving parameter information in calibration result list, according to target calibration result, update the calibration parameter of perception sensor.In embodiments of the present application, driving parameter information and online calibration result of perception sensor are used to update calibration result list, when intelligent driving is opened, the target calibration result corresponding to current driving parameter information is determined from calibration result list as the calibration parameter of perception sensor, which can solve the problem that sensor calibration parameter changes when vehicle is in different states, and then leads to the decline of intelligent driving performance, eliminate parameter error, and improve the subsequent calculation accuracy of perception sensor.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, apparatus, device, and medium for calibrating sensor parameters. Background Technology

[0002] Intelligent driving systems assist drivers in performing various driving operations, including driving and parking functions, thus improving driving safety and convenience. An intelligent driving system can consist of multiple modules, among which the accuracy of the perception module directly determines the performance ceiling of the entire system. To obtain more accurate perception results, the accuracy of sensor calibration is crucial. Currently, existing sensor calibration schemes do not consider changes in sensor installation parameters caused by vehicle load, suspension height, and driving mode when intelligent driving functions are activated. They also fail to cover changes in sensor installation parameters due to factors such as vehicle load and suspension height. Simply using fixed lower-order calibration parameters for perception calculations and the dynamic vehicle sensor installation parameters when intelligent driving functions are activated introduces discrepancies. These discrepancies lead to calculation errors in the perception results. To improve the perception accuracy of the perception module and eliminate this usage error, a solution to this problem is urgently needed. Summary of the Invention

[0003] In view of this, the present invention provides a method, apparatus, device and medium for calibrating sensor parameters, which can solve the problem of the decline in intelligent driving performance indicators caused by changes in sensor calibration parameters under different vehicle states, eliminate calibration parameter errors and improve the accuracy of subsequent calculations by the sensing sensor.

[0004] According to one aspect of the present invention, an embodiment of the present invention provides a method for calibrating parameters of a sensing sensor, the method comprising:

[0005] Acquire driving parameter information of the target vehicle under its operating state, as well as the online calibration results of the sensing sensors in the target vehicle;

[0006] Update the pre-configured calibration result list based on the driving parameter information and the online calibration results;

[0007] When the intelligent driving function is detected to be activated, the target calibration result corresponding to the currently collected driving parameter information is determined in the calibration result list, and the calibration parameters of the perception sensor are updated according to the target calibration result.

[0008] According to another aspect of the present invention, embodiments of the present invention also provide a sensor parameter calibration processing apparatus, the apparatus comprising:

[0009] The acquisition module is used to acquire driving parameter information of the target vehicle under its operating state, as well as the online calibration results of the sensing sensors in the target vehicle;

[0010] The determination module is used to update the pre-configured calibration result list based on the driving parameter information and the online calibration result;

[0011] The update module is used to determine the target calibration result corresponding to the currently collected driving parameter information in the calibration result list when the intelligent driving function is detected to be activated, and update the calibration parameters of the perception sensor according to the target calibration result.

[0012] According to another aspect of the present invention, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the sensor parameter calibration method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the sensor parameter calibration method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the sensor parameter calibration method described in any embodiment of the present invention.

[0018] The technical solution of this invention updates a pre-configured calibration result list by using driving parameter information under vehicle operating conditions and online calibration results of sensing sensors in the vehicle. This allows for the acquisition of multiple sets of accurate calibration result data. When the intelligent driving function is activated, the target calibration result corresponding to the currently collected driving parameter information is determined from the calibration result list as the calibration parameter of the sensing sensor. This provides real-time calibration parameters for the sensing sensor, solving the problem of decreased intelligent driving performance due to changes in sensor calibration parameters under different vehicle conditions. It also eliminates calibration parameter errors and improves the accuracy of subsequent calculations by the sensing sensor.

[0019] 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

[0020] 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.

[0021] Figure 1 A flowchart illustrating a method for calibrating sensor parameters according to an embodiment of the present invention;

[0022] Figure 2 A flowchart illustrating another method for calibrating sensor parameters according to an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of a pre-configured calibration result list provided in an embodiment of the present invention;

[0024] Figure 4 This is a flowchart illustrating another method for calibrating sensor parameters provided in an embodiment of the present invention.

[0025] Figure 5 This is a structural block diagram of a sensor parameter calibration device provided in an embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] 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.

[0028] 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.

[0029] In one embodiment, Figure 1 This is a flowchart of a sensor parameter calibration method according to an embodiment of the present invention. This embodiment is applicable to the case of calibrating the installation parameters of a sensor. The method can be executed by a sensor parameter calibration processing device, which can be implemented in hardware and / or software and can be configured in an electronic device.

[0030] like Figure 1 As shown, the specific steps of this method include:

[0031] S110. Obtain the driving parameter information of the target vehicle under its operating status, as well as the online calibration results of the sensing sensors in the target vehicle.

[0032] The driving parameter information refers to the relevant parameter information of the vehicle when it is in motion, which may include, but is not limited to, the vehicle's suspension height, load condition, driving mode, and posture information. The sensing sensor can be understood as a device installed on the vehicle for acquiring images; for example, the sensing sensor can be a camera, millimeter-wave radar, lidar, etc. It should be noted that the target vehicle may have one or more sensing sensors, but this embodiment does not impose any limitations. The online calibration result can be understood as the calibration result of the sensing sensor corresponding to the vehicle's driving state, that is, the parameter information of the sensing sensor under the vehicle's driving state.

[0033] In this embodiment, when the calibration trigger condition is met, the suspension height, load condition, driving mode, and pose information of the target vehicle can be acquired. Based on this suspension height, load condition, driving mode, and pose information, the sensing sensor is calibrated online according to the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates to generate an online calibration result. It should be noted that the online calibration result of the sensing sensor may include the coordinate information and angle information of the sensing sensor. Of course, the coordinate information can be two-dimensional or three-dimensional; the angle information may include, but is not limited to, rotation angle, pitch angle, and yaw angle. In some embodiments, the driving parameter information of the target vehicle under its operating state can also be acquired periodically according to a certain time pattern. Images are detected and scene reconstructed under at least two different types of sensing sensors. Based on the scene reconstruction results, the intrinsic parameters of each sensing sensor and the extrinsic parameters of each sensing sensor relative to the main camera are calculated, and the intrinsic and extrinsic parameters are used as the online calibration results for each sensing sensor.

[0034] S120. Update the pre-configured calibration result list based on driving parameter information and online calibration results.

[0035] The calibration result list can be understood as the list of calibration results obtained when a vehicle is about to roll off the production line, that is, when the vehicle has completed design, manufacturing, and testing and is about to be launched on the market. This is achieved by calibrating the vehicle's sensing sensors under different vehicle loads, suspension heights, driving modes, and vehicle positions. The list includes the calibration results for different vehicle loads, suspension heights, driving modes, and vehicle positions.

[0036] In this embodiment, online calibration result information can be composed of suspension height, load condition, driving mode, and position information from the online calibration results and driving parameter information. This online calibration result information is then compared with each suspension height, load condition, driving mode, and position information in the calibration result list, along with the corresponding calibration result, to update the pre-configured calibration result list based on the comparison results. In some embodiments, fields matching the driving parameter information and online calibration results can be searched in the calibration result list. If the data value corresponding to the matching field meets a certain threshold, the pre-configured calibration result list is updated. In this embodiment, other methods can also be used to update the pre-configured calibration result list; this embodiment does not impose any limitations on these methods.

[0037] In one embodiment, the pre-configuration of the calibration result list includes:

[0038] Connect the communication interface of the vehicle monitoring system in the target vehicle through the vehicle controller production line.

[0039] The vehicle information of the target vehicle is read through the communication interface, and the information of the target vehicle under each suspension height, each load condition, each driving mode and each posture information is combined into a first data list;

[0040] According to the preset operation instructions, one of the driving modes is selected from the first data list and the driving mode is set as the current driving mode. The perception sensor in the current driving mode is calibrated to determine the calibration result. The calibration result includes at least the coordinate information and angle information of the perception sensor.

[0041] If the calibration result is successful, store the calibration result in the current driving mode, select the next driving mode and set the next driving mode as the current driving mode, return to execute the operation of calibrating the perception sensor, until all driving modes in the first data list have been calibrated.

[0042] If the calibration result is a calibration failure, repeat the calibration operation of the sensor until the sensor is successfully calibrated;

[0043] The coordinate and angle information from the calibration results corresponding to each driving mode are written into the corresponding first data list to form a calibration result list.

[0044] The first data list refers to the data list of the target vehicle under different suspension heights, different load conditions, different driving modes, and different position information. The data list includes at least three suspension heights: high, medium, and low; at least three load conditions: unloaded, half-loaded, and fully loaded; at least five driving modes: normal mode, economy mode, comfort mode, sport mode, and off-road mode; and at least three vehicle position information.

[0045] In this embodiment, the current driving mode can be understood as the driving mode currently being used by the vehicle, and the current driving mode is a driving mode. The next driving mode can be understood as the next driving mode for which the perception sensor calibration is to be performed. In this embodiment, each driving mode corresponds to a corresponding suspension height, load condition, and pose information, and each driving mode corresponds to a calibration result for the perception sensor, which includes at least the coordinate information and angle information of the perception sensor.

[0046] In this embodiment, when the vehicle is about to roll off the production line, the sensing sensors of the vehicle under different vehicle loads, different suspension heights, different driving modes, and different vehicle postures can be calibrated to obtain the corresponding calibration results and form a list of calibration results. Specifically, the communication interface of the vehicle monitoring system in the target vehicle can be connected through the vehicle controller production line. Vehicle information is read from the target vehicle via this interface, and a first data list is compiled from the information of the target vehicle under various suspension heights, load conditions, driving modes, and posture information. Based on preset operation instructions, one driving mode is selected from the first data list and set as the current driving mode. The sensing sensors in the current driving mode are calibrated to determine the calibration result. If the calibration is successful, the calibration result for the current driving mode is stored. The next driving mode is selected and set as the current driving mode, and the calibration operation for the sensing sensors is repeated until all sensing sensors in the first data list for all driving modes are calibrated. If the calibration fails, the calibration operation for the sensing sensors is repeated until the calibration is successful. Finally, the coordinate and angle information from the calibration results for each driving mode are written into the corresponding first data list to form a calibration result list.

[0047] S130. When the intelligent driving function is detected to be activated, determine the target calibration result corresponding to the currently collected driving parameter information in the calibration result list, and update the calibration parameters of the perception sensor according to the target calibration result.

[0048] The currently collected driving parameter information refers to the vehicle driving parameter information corresponding to the activation of the intelligent driving function. This driving parameter information may include, but is not limited to, the vehicle's suspension height, load condition, driving mode, and position information. The target calibration result refers to the target calibration result corresponding to the currently collected suspension height, load condition, driving mode, and position information in the calibration result list.

[0049] In this embodiment, when the intelligent driving function is detected to be activated, the current driving parameter information of the target vehicle can be obtained in real time, and the target calibration result of the perception sensor can be determined by searching the updated calibration result list based on the current driving parameter information. This target calibration result is then used as the calibration parameter of the perception sensor. In some embodiments, the values ​​corresponding to each piece of information in the current driving parameter information can also be extracted, and the current driving parameter information and the values ​​corresponding to each piece of current driving parameter information can be mapped to the updated calibration result list through data mapping to determine the target calibration result of the perception sensor. It should be noted that the suspension height, load condition, driving mode, and posture information currently collected in this embodiment are only one type of suspension height, load condition, driving mode, and posture information corresponding to the current target vehicle.

[0050] The technical solution of this invention updates the pre-configured calibration result list by using the driving parameter information of the vehicle under operating conditions and the online calibration results of the sensing sensors in the vehicle. This allows for the acquisition of multiple sets of accurate calibration result data. When the intelligent driving function is activated, the target calibration result corresponding to the currently collected driving parameter information is determined in the calibration result list as the calibration parameter of the sensing sensor. This provides real-time calibration parameters for the sensing sensor, which solves the problem of changes in sensor calibration parameters under different vehicle conditions leading to a decline in intelligent driving performance indicators. It also eliminates parameter errors and improves the accuracy of subsequent calculations by the sensing sensor.

[0051] In one embodiment, the driving parameter information includes at least one of the following: the suspension height, load condition, driving mode, and pose information of the target vehicle; the target calibration result includes at least the coordinate information and angle information of the sensing sensor.

[0052] Among them, a suspension height reaching the first threshold is considered low; a suspension height reaching the second threshold is considered medium; a suspension height reaching the third threshold is considered high; the first threshold is less than the second threshold and less than the third threshold; the load condition includes at least one of the following: unloaded, half-loaded, and fully loaded; the driving modes include at least: normal mode, economy mode, comfort mode, sport mode and off-road mode.

[0053] In this embodiment, the target vehicle's driving parameter information includes at least one of the following: suspension height, load condition, driving mode, and pose information; the target calibration result includes at least the coordinate and angle information of the sensing sensors. The vehicle's suspension height can be divided into at least three ranges: if the vehicle's suspension height reaches a first threshold, it is considered a low suspension height; if the vehicle's suspension height reaches a second threshold, it is considered a medium suspension height; and if the vehicle's suspension height reaches a third threshold, it is considered a high suspension height. It should be noted that the relationship between the first, second, and third thresholds can be expressed as: the first threshold is less than the second threshold, which is less than the third threshold. The vehicle's load condition may include, but is not limited to, being unloaded, partially loaded, or fully loaded. The vehicle's driving mode may include, but is not limited to, normal mode, economy mode, comfort mode, sport mode, and off-road mode.

[0054] In one embodiment, Figure 2 This is a flowchart of another sensor parameter calibration method provided in an embodiment of the present invention. Based on the above embodiments, this embodiment further refines the following steps: acquiring driving parameter information of the target vehicle under operating conditions and online calibration results of the sensor in the target vehicle; updating a pre-configured calibration result list based on the driving parameter information and online calibration results; determining the target calibration result corresponding to the currently collected driving parameter information in the calibration result list; and updating the calibration parameters of the sensor according to the target calibration result.

[0055] like Figure 2 As shown, the sensor parameter calibration method in this embodiment may specifically include the following steps:

[0056] S210. When the triggering condition is met, obtain the suspension height, load condition, driving mode and position information of the target vehicle, and use the suspension height, load condition, driving mode and position information as driving parameter information.

[0057] In this embodiment, the vehicle's online calibration function requires certain triggering conditions to be met, which can be understood as triggering the vehicle's online calibration function under some special scenarios. When the triggering conditions are met, the suspension height, load, driving mode, and posture information of the target vehicle in the driving state are acquired, and the suspension height, load, driving mode, and posture information are used as driving parameter information. In this embodiment, the triggering condition can be that the time for detecting lane lines during vehicle driving reaches a preset time; of course, it can also be some other special scenarios, and the triggering condition can be manually set by experience. For example, if the vehicle is driving on a road surface with clear lane lines, and the time for detecting clear lane lines is maintained for 100 meters, the online calibration triggering condition is manually met, and the perception sensor is calibrated online to correct the calibration result value of the perception sensor.

[0058] S220. Under the driving parameter information, the sensing sensor is calibrated online based on the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates to generate online calibration results.

[0059] The online calibration results include the coordinate and angle information of the sensing sensor. The coordinate information can include the sensor's three-dimensional coordinates, and the angle information includes rotation, pitch, and yaw angles.

[0060] In this embodiment, the suspension height, load, driving mode, and pose information of the target vehicle in motion are obtained. Based on these driving parameters, the sensor can be calibrated online using image feature points corresponding to the images collected by the sensing sensor, as well as the coordinate transformation relationship between image coordinates and physical coordinates, to generate corresponding online calibration results. For example, if the vehicle's suspension height is low, load is full, driving mode is normal, and pose is normal, then by collecting image information from the road ahead using the sensing sensor, and performing online calibration based on the image features of this image information, an online calibration result is generated for the sensing sensor in the low suspension height, full load, normal driving mode, and normal pose state.

[0061] S230. The online calibration result information is composed of the suspension height, load condition, driving mode and position information in the online calibration result and driving parameter information.

[0062] In this embodiment, the online calibration result information can be composed of the vehicle's suspension height, load condition, driving mode, and position information while in motion, as well as the corresponding online calibration results under these conditions. Of course, this online calibration result information includes suspension height, load condition, driving mode, position information, and the corresponding online calibration result information.

[0063] S240: Read the calibration result list from the memory.

[0064] In this embodiment, since the pre-configured calibration result list is stored in the domain-controlled storage unit, the calibration result list needs to be read from the storage unit when it is necessary to use the calibration result list for searching.

[0065] S250. Find the first calibration result in the calibration result list that reaches the preset threshold compared with the online calibration result information.

[0066] The preset threshold refers to a pre-defined threshold for calibration results. By setting the preset threshold, the calibration results that are closest to the online calibration results can be found in the calibration result list. The first calibration result information refers to the set of calibration result information in the calibration result list that is closest to the online calibration result information.

[0067] In this embodiment, the first calibration result information that reaches a preset threshold compared with the online calibration result information can be found in the calibration result list by traversing or comparing the results. This can be understood as comparing the online calibration result information with each suspension height, load condition, driving mode, position information and corresponding calibration result in the pre-configured calibration result list, and finding the set of suspension height, load condition, driving mode, position information and corresponding calibration result that is closest to the online calibration result information.

[0068] S260. Update the pre-configured calibration result list based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information.

[0069] The first calibration result refers to the calibration result in the calibration result list that is closest to the online calibration result.

[0070] In this embodiment, the pre-configured calibration result list can be updated based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information. Specifically, if the error between the first calibration result and the online calibration result is within a preset calibration error threshold, the first calibration result is deleted, and the online calibration result is written into the calibration result list to update the calibration result list. If the error between the first calibration result and the online calibration result is not within the preset calibration error threshold, no update operation is performed.

[0071] In one embodiment, updating the pre-configured calibration result list based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information includes:

[0072] Determine whether the error between the first calibration result and the online calibration result is within the preset calibration error threshold;

[0073] If so, delete the first calibration result and write the online calibration result to the calibration result list to update the calibration result list;

[0074] If not, no update operation will be performed.

[0075] In this embodiment, it is determined whether the error between the first calibration result and the online calibration result is within a preset calibration error threshold. If the error between the first calibration result and the online calibration result is within the preset calibration error threshold, the first calibration result is deleted and the online calibration result is written into the calibration result list to update the calibration result list. If the error between the first calibration result and the online calibration result is not within the preset calibration error threshold, no update operation is performed.

[0076] S270: When the intelligent driving function is detected to be activated, the suspension height, load, driving mode and position information in the currently collected driving parameter information are obtained in real time.

[0077] In this embodiment, when the intelligent driving function is detected to be activated, the suspension height, load, driving mode, and position information from the currently collected driving parameter information are acquired in real time. For example, the currently collected suspension height, load, driving mode, and position information can be a suspension height of medium, a load of half load, a driving mode of sport mode, and a position information of tilt of 3 degrees, or other situations. This embodiment does not impose any limitations on these situations.

[0078] S280. Find the target calibration result corresponding to the suspension height, load condition, driving mode and position information in the updated calibration result list, and use the target calibration result as the calibration parameter of the perception sensor.

[0079] In this embodiment, the suspension height, load, driving mode, and pose information from the currently collected driving parameter information obtained when the intelligent driving function is activated can be used to find the target calibration result corresponding to the suspension height, load, driving mode, and pose information in the updated calibration result list, and the target calibration result is used as the calibration parameter of the perception sensor. For example, the currently collected suspension height, load, driving mode, and pose information correspond to the following information: suspension height is medium, load is half load, driving mode is sport mode, and pose information is tilted at 5 degrees. This information is then compared with the data information in the calibration result list to find the closest set of suspension height, load, driving mode, and pose information, and the calibration result corresponding to the closest set of driving parameter information is used as the target calibration result of the perception sensor at this time.

[0080] The above-described technical solution of this invention acquires the driving parameter information of the target vehicle when a trigger condition is met. Based on the driving parameter information, the sensing sensor is calibrated online according to the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates to generate an online calibration result. The online calibration result, along with suspension height, load condition, driving mode, and pose information from the driving parameter information, forms the online calibration result information. A first calibration result information that reaches a preset threshold compared to the online calibration result information is searched in the calibration result list. The first calibration result information is then compared with the online calibration result information. The system updates the pre-configured calibration result list based on the error between the online calibration results in the result information. When the intelligent driving function is detected to be activated, it acquires the suspension height, load, driving mode, and pose information from the currently collected driving parameters in real time. It then searches the updated calibration result list for the target calibration result corresponding to the suspension height, load, driving mode, and pose information, and uses the target calibration result as the calibration parameter for the perception sensor. This can further solve the problem of the decline in intelligent driving performance indicators caused by changes in sensor calibration parameters under different vehicle states, eliminate parameter errors, and improve the accuracy of subsequent calculations by the perception sensor.

[0081] In one embodiment, to facilitate a better understanding of the specific method for pre-configuring the calibration result list, Figure 3 This is a schematic flowchart illustrating the pre-configuration of a calibration result list according to an embodiment of the present invention. This embodiment further explains the pre-configuration process of the calibration result list. In this embodiment, when the vehicle is about to roll off the production line, that is, when the vehicle is about to be launched on the market after completing design, manufacturing, and testing, the sensing sensors of the vehicle under different vehicle loads, different suspension heights, different driving modes, and different vehicle postures are calibrated to obtain corresponding calibration results.

[0082] like Figure 3 As shown, the specific steps for pre-configuring the calibration result list are as follows:

[0083] S310, Drive the vehicle onto the control panel at the designated location.

[0084] S320, the control console adjusts the vehicle's position to center the vehicle.

[0085] S330: Connect the vehicle's OBD interface and read the vehicle information of the target vehicle.

[0086] S340: Select a driving mode and the corresponding vehicle load, suspension height, and position information, and set this driving mode as the current driving mode.

[0087] S350 performs calibration operations on the perception sensors under the current driving mode and the corresponding vehicle load, suspension height, and posture information to determine the corresponding calibration results.

[0088] S360. Determine whether the calibration result is successful. If yes, proceed to S370. If no, return to S350 and repeat the calibration operation of the sensing sensor until the calibration of the sensing sensor is successful.

[0089] S370, Stores the calibration results generated in the current driving mode.

[0090] S380: Determine whether all driving modes and the corresponding vehicle load, suspension height, and position information perception sensors have been calibrated. If yes, proceed to S3100; otherwise, proceed to S390.

[0091] S390: Switch to the next driving mode and the corresponding vehicle load, suspension height, and position information, and set the next driving mode as the current driving mode and the corresponding vehicle load, suspension height, and position information, and return to execute S340.

[0092] S3100, the vehicle off-line process feedback and calibration process is complete.

[0093] S3110, release the control of the OBD interface and align the vehicle, and drive out of the vehicle.

[0094] In one embodiment, to facilitate a better understanding of the sensor parameter calibration method, Figure 4This is a flowchart illustrating another sensor parameter calibration method provided by an embodiment of the present invention. This embodiment can be used as a preferred embodiment to further explain the sensor parameter calibration method. This embodiment addresses the problem of inconsistency between the calibration parameters after the vehicle is manufactured and the calibration parameters used in actual autonomous driving functions. Since changes in vehicle load and suspension height during vehicle operation can cause changes in the vehicle's body height and posture, this invention calibrates the sensor under various suspension heights, load conditions, driving modes, and posture information when the vehicle is manufactured to obtain multiple corresponding calibration results. The calibration results under these conditions are then compiled into a calibration result list. Simultaneously, the online calibration results triggered during vehicle operation, along with the corresponding vehicle height and posture information, are collected in real time. Attitude and other parameter information are verified through a calibration result list during online calibration parameter updates. This results in multiple accurate calibration results corresponding to different suspension heights, load conditions, driving modes, and vehicle attitudes, which are then stored in the intelligent driving controller. When the intelligent driving function is used, the corresponding target calibration result is found in the updated calibration result list by real-time detection of the current suspension height, load condition, driving mode, and attitude information. The target calibration result is then used as the calibration parameter for the perception sensors. The target calibration parameter is then used to perform coordinate transformations, distance calculations, speed calculations, etc., to adapt to the normal application of intelligent driving functions under various heights and vehicle attitudes, thereby improving the performance indicators of intelligent driving.

[0095] like Figure 4 As shown, the specific steps are as follows:

[0096] S410, online calibration in real time.

[0097] S420: Determine in real time whether the online calibration trigger condition is met. If yes, execute S430; otherwise, return to execute S410.

[0098] S430: Acquire and record the suspension height, load condition, driving mode and position information of the target vehicle, and under the above parameters, perform online calibration of the sensing sensor based on the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates to generate online calibration results.

[0099] S440 combines the online calibration results with suspension height, load conditions, driving mode, and position information to form online calibration result information.

[0100] S450 compares the online calibration results with the pre-configured calibration results list for each suspension height, load condition, driving mode, and posture information, as well as the corresponding calibration results.

[0101] S460. Based on the comparison results, determine whether the calibration result of the sensing sensor is within the preset calibration error threshold. If yes, execute S470; otherwise, return to execute S410.

[0102] S470. Write the calibration results of the sensing sensor into a pre-configured calibration result list to update the pre-configured calibration result list.

[0103] S480: When the intelligent driving function is detected to be activated, obtain the currently collected suspension height, load status, driving mode and position information;

[0104] S490. Locate the target calibration result corresponding to the suspension height, load condition, driving mode, and position information in the updated calibration result list, and use the target calibration result as the calibration parameter of the perception sensor.

[0105] In one embodiment, Figure 5 This is a structural block diagram of a sensor parameter calibration device according to an embodiment of the present invention. This device is suitable for calibrating the installation parameters of a sensor and can be implemented in hardware or software. It can be configured in an electronic device to implement a sensor parameter calibration processing method according to an embodiment of the present invention.

[0106] like Figure 5 As shown, the device includes: an acquisition module 510, an update module 520, and a result determination module 530.

[0107] The acquisition module 510 is used to acquire driving parameter information of the target vehicle under its operating state, as well as the online calibration results of the sensing sensors in the target vehicle.

[0108] The update module 520 is used to update the pre-configured calibration result list based on the driving parameter information and the online calibration result;

[0109] The result determination module 530 is used to determine the target calibration result corresponding to the currently collected driving parameter information in the calibration result list when the intelligent driving function is detected to be activated, and to update the calibration parameters of the perception sensor according to the target calibration result.

[0110] In this embodiment of the invention, the update module updates the pre-configured calibration result list using driving parameter information under vehicle operating conditions and online calibration results of sensing sensors in the vehicle, thereby obtaining multiple sets of accurate calibration result data. The result determination module, when the intelligent driving function is activated, determines the target calibration result corresponding to the currently collected driving parameter information in the calibration result list as the calibration parameter of the sensing sensor, thereby obtaining the real-time calibration parameters of the sensing sensor. This can solve the problem of changes in sensor calibration parameters under different vehicle states, which leads to a decline in intelligent driving performance indicators, eliminate calibration parameter errors, and improve the accuracy of subsequent calculations by the sensing sensor.

[0111] In one embodiment, the pre-configuration of the calibration result list includes:

[0112] The communication interface of the vehicle monitoring system in the target vehicle is connected through the vehicle controller production line.

[0113] The vehicle information of the target vehicle is read according to the communication interface, and the information of the target vehicle under each suspension height, each load condition, each driving mode and each posture information is combined into a first data list;

[0114] According to a preset operation instruction, one of the driving modes is selected from the first data list, and the driving mode is taken as the current driving mode. The perception sensor in the current driving mode is calibrated to determine the calibration result; wherein, the calibration result includes at least the coordinate information and angle information of the perception sensor.

[0115] If the calibration result is successful, store the calibration result in the current driving mode, select the next driving mode and use the next driving mode as the current driving mode, return to perform the calibration operation on the perception sensor, until all driving modes in the first data list have been calibrated.

[0116] If the calibration result is a calibration failure, the calibration operation of the sensing sensor is repeated until the calibration of the sensing sensor is successful;

[0117] The coordinate and angle information from the calibration results corresponding to each driving mode are written into the corresponding first data list to form a calibration result list.

[0118] In one embodiment, the acquisition module 510 includes:

[0119] The information acquisition unit is used to acquire the suspension height, load status, driving mode and position information of the target vehicle when the triggering condition is met, and to use the suspension height, load status, driving mode and position information as the driving parameter information.

[0120] The result determination unit is used to perform online calibration of the sensing sensor based on the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates under the driving parameter information, so as to generate an online calibration result. The online calibration result includes the coordinate information and angle information of the sensing sensor.

[0121] In one embodiment, the update module 520 further includes:

[0122] An information composition unit is used to combine the online calibration results and the suspension height, load condition, driving mode and posture information in the driving parameter information to form online calibration result information;

[0123] A reading unit is used to read the calibration result list from the memory;

[0124] The search unit is used to search the calibration result list for a first calibration result that reaches a preset threshold compared with the online calibration result information;

[0125] An update unit is used to update the pre-configured calibration result list based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information.

[0126] In one embodiment, the updating unit includes:

[0127] The judgment subunit is used to determine whether the error between the first calibration result and the online calibration result is within a preset calibration error threshold.

[0128] The first update subunit is configured to delete the first calibration result and write the online calibration result into the calibration result list if the condition is met, so as to update the calibration result list.

[0129] The second update subunit is used to perform no update operation if no.

[0130] In one embodiment, the result determination module 530 includes:

[0131] The acquisition unit is used to acquire, in real time, the suspension height, load status, driving mode and position information from the currently collected driving parameter information;

[0132] The result determination unit is used to find the target calibration result corresponding to the suspension height, the load condition, the driving mode and the pose information in the updated calibration result list, and use the target calibration result as the calibration parameter of the perception sensor.

[0133] In one embodiment, the driving parameter information includes at least one of the following: the suspension height, load condition, driving mode, and pose information of the target vehicle; the target calibration result includes at least the coordinate information and angle information of the sensing sensor.

[0134] Wherein, the suspension height reaching a first threshold is low; the suspension height reaching a second threshold is medium; the suspension height reaching a third threshold is high; the first threshold is less than the second threshold and less than the third threshold; the load condition includes at least one of the following: unloaded state, half-loaded state, and fully loaded state; the driving mode includes at least: normal mode, economy mode, comfort mode, sport mode and off-road mode.

[0135] The sensor parameter calibration processing device provided in this embodiment of the invention can execute the sensor parameter calibration processing method for financial systems provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0136] In one embodiment, Figure 6 This is a schematic diagram of an electronic device provided for an embodiment of the present invention. The electronic device 10 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as 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.

[0137] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0139] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 11 performs the various methods and processes described above, such as sensor parameter calibration methods.

[0140] In some embodiments, the sensor parameter calibration processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the sensor parameter calibration method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the sensor parameter calibration method by any other suitable means (e.g., by means of firmware).

[0141] 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.

[0142] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable sensing sensor parameter calibration 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 implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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 no limitation is imposed herein.

[0148] 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 method for calibrating parameters of a sensing sensor, characterized in that, include: Acquire driving parameter information of the target vehicle under its operating state, as well as the online calibration results of the sensing sensors in the target vehicle; Update the pre-configured calibration result list based on the driving parameter information and the online calibration results; When the intelligent driving function is detected to be activated, the target calibration result corresponding to the currently collected driving parameter information is determined in the calibration result list, and the calibration parameters of the perception sensor are updated according to the target calibration result; The step of updating the pre-configured calibration result list based on the driving parameter information and the online calibration results includes: The online calibration results and the suspension height, load condition, driving mode and posture information in the driving parameter information are combined to form the online calibration result information; Read the list of calibration results from the memory; Find the first calibration result in the calibration result list that reaches a preset threshold compared to the online calibration result information; The pre-configured calibration result list is updated based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information.

2. The method according to claim 1, characterized in that, The pre-configured list of calibration results includes: The communication interface of the vehicle monitoring system in the target vehicle is connected through the vehicle controller production line. The vehicle information of the target vehicle is read according to the communication interface, and the information of the target vehicle under each suspension height, each load condition, each driving mode and each posture information is combined into a first data list; According to a preset operation instruction, one of the driving modes is selected from the first data list, and the driving mode is taken as the current driving mode. The perception sensor in the current driving mode is calibrated to determine the calibration result; wherein, the calibration result includes at least the coordinate information and angle information of the perception sensor. If the calibration result is successful, store the calibration result in the current driving mode, select the next driving mode and use the next driving mode as the current driving mode, return to perform the calibration operation on the perception sensor, until all driving modes in the first data list have been calibrated. If the calibration result is a calibration failure, the calibration operation of the sensing sensor is repeated until the calibration of the sensing sensor is successful; The coordinate and angle information from the calibration results corresponding to each driving mode are written into the corresponding first data list to form a calibration result list.

3. The method according to claim 1, characterized in that, The acquisition of driving parameter information of the target vehicle under its operating state, and the online calibration results of the sensing sensors in the target vehicle, includes: When the triggering condition is met, the suspension height, load condition, driving mode and position information of the target vehicle are obtained, and the suspension height, load condition, driving mode and position information are used as the driving parameter information; Under the driving parameter information, the sensing sensor is calibrated online based on the image feature points collected by the sensing sensor and the coordinate transformation relationship between image coordinates and physical coordinates to generate online calibration results. The online calibration results include the coordinate information and angle information of the sensing sensor.

4. The method according to claim 1, characterized in that, The step of updating the pre-configured calibration result list based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information includes: Determine whether the error between the first calibration result and the online calibration result is within a preset calibration error threshold; If so, delete the first calibration result and write the online calibration result into the calibration result list to update the calibration result list; If not, no update operation will be performed.

5. The method according to claim 1, characterized in that, The step of determining the target calibration result corresponding to the currently collected driving parameter information within the calibration result list, and updating the calibration parameters of the sensing sensor according to the target calibration result, includes: Real-time acquisition of suspension height, load status, driving mode, and position information from currently collected driving parameter information; The target calibration result corresponding to the suspension height, load condition, driving mode and pose information is found in the updated calibration result list, and the target calibration result is used as the calibration parameter of the perception sensor.

6. The method according to claim 1, characterized in that, The driving parameter information includes at least one of the following: the suspension height, load condition, driving mode, and posture information of the target vehicle; the target calibration result includes at least the coordinate information and angle information of the sensing sensor. Wherein, the suspension height reaching a first threshold is low; the suspension height reaching a second threshold is medium; the suspension height reaching a third threshold is high; the first threshold is less than the second threshold and less than the third threshold; the load condition includes at least one of the following: unloaded state, half-loaded state, and fully loaded state; the driving mode includes at least: normal mode, economy mode, comfort mode, sport mode and off-road mode.

7. A device for calibrating parameters of a sensing sensor, characterized in that, include: The acquisition module is used to acquire driving parameter information of the target vehicle under its operating state, as well as the online calibration results of the sensing sensors in the target vehicle; The update module is used to update the pre-configured calibration result list based on the driving parameter information and the online calibration results; The result determination module is used to determine the target calibration result corresponding to the currently collected driving parameter information in the calibration result list when the intelligent driving function is detected to be activated, and to update the calibration parameters of the perception sensor according to the target calibration result. The update module also includes: An information composition unit is used to combine the online calibration results and the suspension height, load condition, driving mode and posture information in the driving parameter information to form online calibration result information; A reading unit is used to read the calibration result list from the memory; The search unit is used to search the calibration result list for a first calibration result that reaches a preset threshold compared with the online calibration result information; An update unit is used to update the pre-configured calibration result list based on the error between the first calibration result in the first calibration result information and the online calibration result in the online calibration result information.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and 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 sensor parameter calibration method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the sensor parameter calibration method according to any one of claims 1-6.

Images