Calibration information processing method and device, equipment and storage medium

Abstract

The present disclosure provides a calibration information processing method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, and in particular to the technical field of automatic driving, vehicle control and intelligent traffic. The specific implementation scheme is: generating new calibration information of a vehicle according to a calibration mode and calibration data of the vehicle; controlling detection of the new calibration information according to a detection condition corresponding to the calibration mode; and controlling updating of original calibration information according to a detection result of the new calibration information and an updating condition corresponding to the calibration mode. In the embodiment of the present disclosure, the detection and updating of the calibration information are controlled according to the detection condition and the updating condition corresponding to the calibration mode, the calibration information of the vehicle can be updated in time, which is conducive to adapting to changes in more scenes, working conditions and the like, and improving the control accuracy of the vehicle.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to the fields of autonomous driving, vehicle control, and intelligent transportation. Background Technology

[0002] In scenarios such as autonomous driving, vehicles may use calibration tables to assist in vehicle control. For example, an autonomous driving longitudinal control calibration table could be a mapping table between speed, acceleration, and pedal opening. Pedal opening could include accelerator pedal opening and / or brake pedal opening. The current speed and desired acceleration can be mapped to the corresponding accelerator or brake pedal opening. Summary of the Invention

[0003] This disclosure provides a calibration information processing method, apparatus, device, and storage medium.

[0004] According to one aspect of this disclosure, a calibration information processing method is provided, the method comprising the following steps:

[0005] Based on the vehicle's calibration mode and calibration data, generate new calibration information for the vehicle;

[0006] The detection of the new calibration information is controlled according to the detection conditions corresponding to the calibration mode;

[0007] Based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode, the update of the original calibration information is controlled.

[0008] According to another aspect of this disclosure, a calibration information processing apparatus is provided, the apparatus comprising:

[0009] The generation module is used to generate new calibration information for the vehicle based on the vehicle's calibration mode and calibration data.

[0010] The first control module is used to control the detection of the new calibration information according to the detection conditions corresponding to the calibration mode;

[0011] The second control module is used to control the updating of the original calibration information based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode.

[0012] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

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

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods of any embodiment of the present disclosure.

[0016] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform a method according to any embodiment of this disclosure.

[0017] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements a method according to any embodiment of this disclosure.

[0018] In this embodiment of the disclosure, the vehicle's calibration information can be updated in a timely manner according to the detection and update conditions corresponding to the calibration mode, thereby controlling the detection and update of the calibration information. This is beneficial for adapting to more scenarios, operating conditions, and other changes, and improving the vehicle's control accuracy.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a schematic flowchart of a calibration information processing method according to an embodiment of the present disclosure;

[0022] Figure 2 This is a schematic flowchart of a calibration information processing method according to another embodiment of the present disclosure;

[0023] Figure 3 This is a schematic flowchart of a calibration information processing method according to another embodiment of the present disclosure;

[0024] Figure 4 This is a schematic flowchart of a calibration information processing method according to another embodiment of the present disclosure;

[0025] Figure 5 This is a schematic diagram of system components according to an embodiment of the present disclosure;

[0026] Figure 6 This is a flowchart illustrating the overall operation of a system according to an embodiment of the present disclosure;

[0027] Figure 7 This is a schematic diagram of the structure of a calibration information processing apparatus according to an embodiment of the present disclosure;

[0028] Figure 8 This is a schematic diagram of the structure of a calibration information processing apparatus according to another embodiment of the present disclosure;

[0029] Figure 9 This is a block diagram of an electronic device used to implement embodiments of the present disclosure. Detailed Implementation

[0030] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] Figure 1 This is a flowchart illustrating a calibration information processing method according to an embodiment of the present disclosure, which may include:

[0032] S101. Generate new calibration information for the vehicle based on its calibration mode and calibration data;

[0033] S102. Control the detection of the new calibration information according to the detection conditions corresponding to the calibration mode;

[0034] S103. Based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode, control the update of the original calibration information.

[0035] In some examples, vehicle calibration information may include calibration tables, such as longitudinal control calibration tables used in autonomous driving scenarios. In related technologies, longitudinal control calibration tables can be created from offline data acquisition. However, due to the limited availability of offline data and scenarios, and the stringent requirements for the data acquisition site, the calculated calibration tables can only adapt to a limited number of scenarios and operating conditions, leading to a deterioration in control performance using these tables in certain situations. Furthermore, as the vehicle's usage time increases, the vehicle's transmission performance changes, reducing the adaptability of offline calibration tables and consequently decreasing control accuracy.

[0036] This longitudinal control calibration table can be generated manually by collecting data under specific scenarios, such as acceleration and deceleration tests on a long, straight, flat road under no-load conditions, with speeds covering maximum speeds and throttle and / or brake pedal openings covering maximum openings. The collected data is then filtered to obtain a table corresponding to speed, acceleration, and throttle and / or brake pedal openings. Some solutions also use an online calibration model to learn and update the table in real time. Offline generation of this longitudinal control calibration table involves a high degree of manual intervention, leading to lower data processing efficiency and stricter requirements for the data collection site and process. Furthermore, different vehicles of a particular model may only have one calibration table calibrated. For new vehicles, the same calibration table may be well-suited. However, for older vehicles, the matching degree of the calibration table varies significantly depending on the vehicle's age. Calibrating all vehicles would be labor-intensive and have a high error rate. Furthermore, due to the limited data collected offline, the generated calibration table is applicable to fewer scenarios and the system has weak anti-interference capabilities. For example, in scenarios such as uphill and downhill, empty and heavy load, wet and slippery road surfaces, and changes in vehicle operating conditions (increased wear), the accuracy of the table decreases, resulting in reduced robustness of the control system and worse control performance.

[0037] In this embodiment of the disclosure, the calibration data may include data collected for generating new calibration information, such as the actual speed, acceleration, and pedal opening during vehicle operation. Pedal opening may include the accelerator pedal opening and / or the brake pedal opening.

[0038] In this embodiment, the calibration mode can be flexibly set according to changes in scenarios and operating conditions. The detection and update conditions can be different for different calibration modes. The calibration mode is used to improve the adaptability of calibration information to changes in scenarios and operating conditions, so that the calibration information processing method can be applied to more scenarios and operating conditions. The calibration mode can also be called the control mode or calibration control mode, etc.

[0039] This embodiment of the disclosure can generate new calibration information for the vehicle based on the vehicle's calibration mode and calibration data, and then control the detection and updating of the calibration information according to the detection and update conditions corresponding to the calibration mode. This allows for timely updates to the vehicle's calibration information, which is beneficial for adapting to changes in more scenarios and operating conditions, and improving the vehicle's control accuracy.

[0040] Figure 2 This is a flowchart illustrating a calibration information processing method according to another embodiment of the present disclosure. The method may include one or more features of the calibration information processing method described in the above embodiments. In one implementation, the method further includes:

[0041] S201. Based on the vehicle's environmental data and / or status data, determine whether the vehicle's operating scenario matches the target scenario.

[0042] In this embodiment of the disclosure, the vehicle's environmental data may include external environmental data collected by the vehicle, as well as environmental data received by the vehicle from other devices such as other vehicles, roadside equipment, and cloud servers. The environmental data may include various types, which can be selected according to the different scenarios that need to be supported. For example, environmental data may include weather information, road surface information, etc.

[0043] In this embodiment of the disclosure, the vehicle's state data may include data such as gear position, gradient, and load during vehicle operation. The gradient can be obtained by measuring the pitch angle using an inertial measurement unit (IMU). The vehicle's state data may also include calibration data such as the actual speed, acceleration, and pedal opening mentioned above. The state data can also be selected according to the different scenarios it supports.

[0044] In this embodiment, several scenarios can be pre-set, such as uphill / downhill, heavy load, rain / snow weather, slippery road surface, and vehicle usage time. Vehicle usage time scenarios may include continuous vehicle operation for more than 3 hours or operation for more than 8 hours per day. Some scenarios can be determined based on vehicle environmental data, such as rain / snow weather scenarios. Some scenarios can be determined based on vehicle status data, such as heavy load scenarios. Some scenarios can be determined based on both vehicle environmental and status data, such as uphill / downhill scenarios.

[0045] In this embodiment of the disclosure, based on the vehicle's environmental data and / or status data, the vehicle can be adapted to more scenarios, facilitating flexible control of the detection and / or updating of calibration information for different target scenarios.

[0046] In some examples, the calibration mode may include a first calibration mode and a second calibration mode. The detection condition for the first calibration mode can be that new calibration information is generated after a scene change, while the detection condition for the second calibration mode can be that the generated new calibration information differs from the original calibration information. Based on the vehicle's environmental data and / or state data, it is determined whether the vehicle's operating scenario matches the target scenario.

[0047] like Figure 3As shown, the calibration information processing method in the first calibration mode may include the following processing steps. In one embodiment, in S101, new calibration information for the vehicle is generated based on the vehicle's calibration mode and calibration data, including: S301, in the first calibration mode, if the vehicle experiences a scene change, the new calibration information is generated based on the calibration data. For example, in the first calibration mode, if the vehicle changes from a normal driving scenario to an uphill or downhill scenario, new calibration information can be generated based on the collected calibration data. Similarly, in the first calibration mode, if the vehicle changes from a dry road surface scenario to a wet road surface scenario, new calibration information can be generated based on the collected calibration data. Specific methods for generating new calibration information may include multi-layer neural networks, deep learning, etc.

[0048] Utilizing scenario changes to trigger the generation of new calibration information allows for wider applicability to various scenarios and operating conditions, improving vehicle control accuracy and enhancing safety in scenarios such as autonomous driving. Furthermore, it facilitates flexible expansion to even more scenarios and operating conditions.

[0049] In one implementation, in S102, the detection of the new calibration information is controlled according to the detection conditions corresponding to the calibration mode, including: S302, in the first calibration mode, when the vehicle generates new calibration information, the availability of the new calibration information is detected. In this embodiment of the disclosure, scene changes can trigger the generation of new calibration information as well as the detection of new calibration information, which is beneficial for application to more scenarios, working conditions, and other actual situations. Detecting the availability of the new calibration information is beneficial for using new calibration information with better availability for vehicle control, thereby improving the control accuracy of the vehicle.

[0050] In one implementation, in S103, the update of the original calibration information is controlled according to the detection result of the new calibration information and the update conditions corresponding to the calibration mode, including: S303, in the first calibration mode, in response to the environmental data and / or status data of the vehicle conforming to the update rules, the original calibration information is updated using the new calibration information.

[0051] In this embodiment, the original calibration information may be offline-generated calibration information or the calibration information corresponding to the previous scenario or moment before the generation of the new calibration information. After generating new calibration information, it is not necessarily necessary to update the original calibration information to prevent frequent updates from affecting vehicle control accuracy. Therefore, some update rules can be pre-set. In the first mode, these update rules can be used to determine whether the original calibration information needs to be updated with the new calibration information. The specific content and number of update rules can be flexibly set according to actual needs, and this embodiment does not impose any limitations. For example, in the first calibration mode, if there is a significant change in the vehicle's load or the vehicle's operating time exceeds a certain period, an update to the original calibration information can be triggered. Based on whether the vehicle's environmental data and / or status data meet the update rules, it can be determined whether to use the new calibration information to update the original calibration information, thereby reasonably controlling the timing of calibration information updates and improving the stability and safety of vehicle control.

[0052] In this embodiment of the disclosure, rules similar to update rules can also be used to trigger the generation of new calibration information, and scenario changes can also be used to trigger availability detection of the new calibration information. Availability detection can also be understood as availability judgment, that is, judging whether the new calibration information, such as a new longitudinal control calibration table, is available.

[0053] like Figure 4 As shown, the calibration information processing method in the second calibration mode may include the following processing steps. In one embodiment, in S101, new calibration information for the vehicle is generated based on the vehicle's calibration mode and calibration data, including: S401, generating the new calibration information based on the calibration data in the second calibration mode. For example, in the second calibration mode, new calibration information can be generated at intervals such as 1 hour or 10 minutes. If the time interval is short, it can achieve the effect of generating new calibration information in real time. The time interval can be the same or varied. For example, the time interval for generating new calibration information can be different at different times of the day; the time interval before 7:00 AM can be longer than that after 7:00 AM. Similarly, the time interval for generating new calibration information from Monday to Friday can be different from that on Saturday and Sunday. In the second calibration mode, new calibration information can be generated in a timely manner based on the collected calibration data, which is beneficial for achieving a refined calibration effect and improving vehicle control accuracy.

[0054] In one implementation, in S102, the detection of the new calibration information is controlled according to the detection conditions corresponding to the calibration mode, including: S402, in the second calibration mode, if the absolute value of the difference between the vehicle speed in the new calibration information and the original calibration information is greater than a set threshold, the availability of the new calibration information is detected. Since the frequency of generating new calibration information is high in the second calibration mode, in order to reduce the computational load on the vehicle control system, availability detection can be triggered only when the difference between the new and old calibration information meets certain availability detection conditions. For example, if the absolute value of the difference between the vehicle speed in the new calibration information and the original calibration information is greater than a set threshold, availability detection of the new calibration information is triggered. The vehicle speed in the calibration information can be calculated based on acceleration and time over a period of time. Controlling the availability detection of the new calibration information by the difference in vehicle speed between the new and original calibration information can reasonably trigger availability detection, reduce the computational load on the vehicle control system, and prevent excessively frequent availability detection.

[0055] In one implementation, in S103, based on the detection result of the new calibration information and the update conditions corresponding to the calibration mode, the update of the original calibration information is controlled, including: S403, in the second calibration mode, in response to the vehicle's operating scenario conforming to the target scenario, the original calibration information is updated using the new calibration information. If the new calibration information is detected as available, it can be used for subsequent vehicle control. If, based on the vehicle's environmental data and / or state data, it is determined that the vehicle is in a target scenario, such as a long, straight, flat road surface scenario, when the new calibration information is generated, the new calibration information can be used to update the original calibration information. If the vehicle does not conform to any target scenario when the new calibration information is generated, only the new calibration information can be used for vehicle control, but the new calibration information is not used to update the original calibration information. Through the update conditions of the second calibration mode, the update of calibration information can be reasonably controlled, updating the original calibration information in certain scenarios, which is beneficial for application to more scenarios and operating conditions, improving the stability and safety of vehicle control.

[0056] In one embodiment, in S301 and / or S401, generating the new calibration information based on the calibration data includes: incrementally generating the new calibration information when the speed range of the calibration data covers at least a set proportion of the set vehicle speed range.

[0057] In this embodiment, the process of collecting calibration data can be a real-time process, and new calibration information can be incrementally generated under certain conditions. For example, the maximum vehicle speed range is set to 0-100 km / h, and the set ratio is 1 / 5. If the vehicle speed range in the collected calibration data is 10 km / h-50 km / h, covering 2 / 5 of the maximum vehicle speed range, which is more than 1 / 5, new calibration information can be generated. If the vehicle speed range in the collected calibration data is 10 km / h-20 km / h, covering 1 / 10 of the maximum vehicle speed range, which is less than 1 / 5, new calibration information cannot be generated. The method for generating new calibration information can be incremental generation. Incremental generation can be understood as modifying the information that needs to change based on the original calibration information. For example, modifying the pedal opening corresponding to a speed of 10 km / h-20 km / h and acceleration of a1 in the original calibration table. Modifying the pedal opening corresponding to a speed of 15 km / h-30 km / h and acceleration of a2 in the original calibration table. Incremental generation of new calibration information can reduce the system resources required to generate calibration information and improve information processing speed. Furthermore, determining whether to generate new calibration information based on the speed range of the calibration data allows control over the timing and / or conditions for generating new calibration information, thereby obtaining more suitable new calibration information.

[0058] In one embodiment, the method further includes performing a smoothing filter at the junction of the unchanged speed range and the changed speed range in the original calibration information. This smoothing filter reduces abrupt changes in relevant data, such as pedal opening abruptly, thereby improving the safety of vehicle control.

[0059] In one implementation, in S302 and / or S402, detecting the availability of the new calibration information includes detecting at least one of the surface smoothness, deviation, and incremental update degree of the new calibration information.

[0060] In one implementation, the surface smoothness includes a first difference between the accelerations corresponding to adjacent velocities and pedal openings in the new calibration information. The absolute value of this first difference being less than a first value indicates that the new calibration information is usable. For example, the velocity v1 and pedal opening p1 in the new calibration information correspond to acceleration a1, and the velocity v2 and pedal opening p2 in the new calibration information correspond to acceleration a2. |a1-a2| being less than a set threshold, i.e., the first value, indicates that the new calibration information is usable. |a1-a2| being greater than or equal to the first value indicates that the new calibration information is unusable.

[0061] In one implementation, the deviation includes a second difference between the accelerations corresponding to the speed and pedal opening of the new calibration information and the original calibration information, respectively. The absolute value of this second difference being less than a second value indicates that the new calibration information is usable. For example, if the speed v1 and pedal opening p1 of the new calibration information correspond to acceleration a1, and the speed v1 and pedal opening p1 of the old calibration information correspond to acceleration a3, then |a1-a3| represents the absolute value of the second difference in accelerations.

[0062] In this embodiment of the disclosure, if all the second differences corresponding to speed, pedal opening, and acceleration are less than the second value, it can be indicated that the new calibration information is available. Alternatively, at least one of the second differences, such as the second difference of speed, can be set to be less than the second value to indicate that the new calibration information is available. Correspondingly, if one or more second differences are greater than or equal to the second value, it can be indicated that the new calibration information is not available.

[0063] In one implementation, the incremental update degree includes the number of data changes of the new calibration information relative to the original calibration information. If the proportion of the number of data changes to the total amount of data in the original calibration information is greater than a third value, it indicates that the new calibration information is available.

[0064] For example, if a new calibration table is generated incrementally, the number of data changes in the new calibration table relative to the original calibration table can be calculated. For instance, if the original calibration table contains 1000 records and 150 records are incrementally updated, the number of data changes represents 15% of the total data in the original calibration table. If the set threshold, or third value, is 10%, then an incremental update rate of 15% indicates that the new calibration information is available. Conversely, if the incremental update rate is less than or equal to the third value, it indicates that the new calibration information is unavailable.

[0065] In this embodiment of the disclosure, the availability of new calibration information can be determined by comprehensively considering the conditions that the surface smoothness, deviation, and incremental update degree all meet the set thresholds, or the availability of new calibration information can be determined based on one or two conditions that meet the set thresholds.

[0066] The calibration information processing method provided in this disclosure can be used to update the vehicle calibration table. For example, it can incrementally update the calibration table online in real time according to changes in scenarios and operating conditions to improve control accuracy in various scenarios. In one example, the calibration information processing method provided in this disclosure can be used in a vehicle control system. This system can be divided into two modes: a simple mode and a fine mode. In the simple mode, the system can activate the online calibration function based on scenario changes and / or set rules, triggering the generation and updating of the calibration table. In the fine mode, the system is in operation, making decisions based on various data collected in real time, generating a new calibration table in real time, and determining the update status of the calibration table based on changes in the calibration table.

[0067] This disclosure may include an environmental variable determination system 501, a calibration data acquisition system 502, an incremental calibration generation system 503, and a calibration table availability determination system 504, such as... Figure 5 As shown, the functions of each part are as follows.

[0068] The environmental variable determination system 501 is used to detect changes in the external environment and / or vehicle operating scenarios. If changes are detected in the external environment and / or vehicle operating scenarios, the initial calibration table generated offline will be insufficiently adapted and needs to be updated. The vehicle will collect data in real time, including gear position, gradient (IMU pitch angle), load, etc., and obtain current weather information, such as rain and snow, which affect the road adhesion coefficient, through communication with the cloud for environmental data monitoring. The system presets certain rules and scenarios, such as: uphill and downhill slopes, heavy loads, rain and snow, slippery roads, vehicle usage time, etc., which affect the longitudinal transmission characteristics of the vehicle. The environmental data monitoring part will make judgments based on the collected data. If the load changes significantly or the vehicle operating time exceeds a certain period of time, etc., and meets the corresponding rules, the online calibration function is triggered to generate a new calibration table.

[0069] For example, multiple calibration modes can be provided. In simple mode, the detection and / or updating of a new calibration table can be triggered based on static rules. In fine mode, the detection and / or updating of a new calibration table can be triggered based on environmental changes that affect the calibration table.

[0070] If the system is preset to fine mode, the online calibration function will be enabled. The system will collect actual speed, acceleration, and accelerator / brake pedal opening in real time and generate at least one new calibration table. The update status of the calibration table will be determined by comparing the initial calibration table (the system's preset offline calibration table) with the newly generated calibration table. The determination method is as follows:

[0071] acc = f(speed, pedal)

[0072] acc' = f'(speed,pedal)

[0073] In the formula, speed is the current speed, pedal is the current accelerator / brake pedal opening, f() represents the mapping relationship corresponding to the initial calibration table, acc is the acceleration corresponding to the current speed and pedal opening in the initial calibration table, f'() represents the mapping relationship of the new table, and acc' is the acceleration corresponding to the current state in the new table. The offline system calculates the speed change corresponding to the two tables over a time period t using the following formula:

[0074] V=acc1×Δt+acc2×Δt+…+acc k ×Δt

[0075] V'=acc'1×Δt+acc'2×Δt+…+acc’ k ×Δt

[0076] If the absolute value of the difference between V and V' is greater than the threshold after time t, it is considered that the environmental variable has changed significantly, which may affect the actual speed control effect, and the calibration table needs to be updated.

[0077] In addition, if the environment is determined to be similar to the offline calibration table generation environment, such as being unloaded or having a long, straight, flat road surface, then the scenario will be marked for subsequent local storage of newly generated calibration tables.

[0078] The calibration data acquisition system 502 is used to collect the data required for updating the calibration table and to filter and process the data. The collected data includes the current steering wheel angle, actual speed, actual acceleration, and actual accelerator / brake pedal opening. During acquisition, only relevant data with steering wheel angles less than a certain value are collected, and then filtered and stored.

[0079] The incremental calibration generation system 503 employs methods such as multi-layer neural networks to generate new three-dimensional calibration tables for speed, acceleration, and throttle / brake pedal opening. The variation range of the new calibration table is determined based on the collected valid data. It is stipulated that the required data speed range must cover at least a certain proportion, such as 1 / 10 of the maximum vehicle speed range, before incremental updates can be performed on the original table. At the junction of the updated speed range and the unupdated speed range in the original table, smoothing filtering is performed to avoid large abrupt changes, ultimately generating the new calibration table.

[0080] The calibration table availability assessment system 504 is used to evaluate newly generated calibration tables to determine their usability. For example, evaluation metrics may include three: surface smoothness, deviation, and incremental update rate. Surface smoothness is calculated as follows: for a newly generated table, calculate the difference in acceleration corresponding to the preceding and following velocities and pedal openings. If the absolute value of this difference is greater than a certain value, the table is considered to have significant fluctuations and is deemed unusable. Deviation is calculated as follows: the difference between the new calibration table and the initial table. Subtract the acceleration corresponding to the same velocity and pedal opening from the two tables. If the absolute value of the difference is greater than a certain value, the new table is considered to have low reliability and will not be updated. Incremental update rate is calculated as follows: the number of changed cells in the new table compared to the original table. If the proportion of changed cells to the total number of cells is less than a certain value, the table is considered unusable. In these cases, the previous calibration table will still be used; otherwise, the available calibration table will be used directly online. In addition, if a new table is generated in a scenario marked by the environment variable determination system, it will be stored locally, replacing the original offline table, and used as the initial table for comparison by the subsequent environment variable determination system.

[0081] The overall system operation flowchart is as follows: Figure 6As shown.

[0082] S601, The environmental variable determination system collects environmental data in real time and performs rule and scene recognition.

[0083] S602. The environment variable determination system checks whether the system mode is fine-grained. If so, proceed to S606; otherwise, it is in simple mode, and proceed to S603.

[0084] S603. In simple mode, determine whether the vehicle's operating scenario matches the scenario in the preset update calibration table. If yes, proceed to S604. Alternatively, determine whether the rule matches the rule in the preset update calibration table; if yes, proceed to S604. Otherwise, subsequent operations can be skipped.

[0085] S604. The calibration data acquisition system collects the data required to update the calibration table in real time and performs post-processing.

[0086] S605: The calibration data acquisition system determines whether the calibration data meets the requirements for incrementally generating a new calibration table based on factors such as the speed range of the calibration data. If the data meets the requirements, a new calibration table is generated incrementally. Then, S609 is executed.

[0087] S606. In fine mode, the calibration data acquisition system collects the data required to update the calibration table in real time and performs post-processing.

[0088] S607. The calibration data acquisition system determines whether the requirements for incrementally generating a new calibration table are met based on factors such as the speed range of the calibration data. If the data meets the requirements, a new calibration table is generated incrementally.

[0089] S608. The environment variable determination system determines whether an update is needed based on the changes between the old and new tables. If so, proceed to S609; otherwise, stop executing subsequent steps or return to S601 or S602 to begin the next loop.

[0090] S609. The calibration table availability determination system assesses whether the new calibration table is available. If it is available, S610 can be executed. Otherwise, if the new calibration table is unavailable, it will not be used for vehicle control, nor will the old calibration table (or original calibration table, initial calibration table, etc.) be updated.

[0091] S610: The calibration table availability determination system determines whether the scenario is one marked by the environment variable determination system. If so, S611 can be executed to use the new calibration table online and store it locally to replace the old calibration table (e.g., the initial calibration table). Otherwise, S612 can be executed to use the new calibration table online without replacing the original calibration table.

[0092] The solution of this disclosure can update the calibration table for longitudinal control in autonomous driving in real time, so that the calibration table can adapt to different environments and vehicle conditions, thereby improving the control accuracy of autonomous driving and increasing the reliability of autonomous driving.

[0093] Figure 7 This is a schematic diagram of a calibration information processing apparatus according to an embodiment of the present disclosure, the apparatus including:

[0094] The generation module 701 is used to generate new calibration information for the vehicle based on the vehicle's calibration mode and calibration data.

[0095] The first control module 702 is used to control the detection of the new calibration information according to the detection conditions corresponding to the calibration mode;

[0096] The second control module 703 is used to control the update of the original calibration information based on the detection result of the new calibration information and the update conditions corresponding to the calibration mode.

[0097] Figure 8 This is a schematic flowchart of a calibration information processing apparatus according to another embodiment of the present disclosure. The apparatus may include one or more features of the calibration information processing apparatus of the above embodiments. In one embodiment, the apparatus further includes:

[0098] The determination module 801 is used to determine whether the vehicle's operating scenario matches the target scenario based on the vehicle's environmental data and / or status data.

[0099] In one possible implementation, such as Figure 8 As shown, the generation module 701 includes:

[0100] The first generation submodule 7011 is used to generate the new calibration information based on the calibration data in the first calibration mode when the vehicle's scenario changes.

[0101] In one possible implementation, such as Figure 8 As shown, the first control module 702 includes:

[0102] The first detection submodule 7021 is used to detect the availability of the new calibration information when the vehicle generates new calibration information in the first calibration mode.

[0103] In one possible implementation, such as Figure 8 As shown, the second control module 703 includes:

[0104] The first update submodule 7031 is used in the first calibration mode to update the original calibration information using the new calibration information in response to the vehicle's environmental data and / or status data conforming to the update rules.

[0105] In one possible implementation, such as Figure 8 As shown, the generation module 701 includes:

[0106] The second generation submodule 7012 is used to generate the new calibration information based on the calibration data in the second calibration mode.

[0107] In one possible implementation, such as Figure 8 As shown, the first control module 702 includes:

[0108] The second detection submodule 7022 is used in the second calibration mode to detect the availability of the new calibration information when the absolute value of the difference between the vehicle speed in the new calibration information and the original calibration information is greater than a set threshold.

[0109] In one possible implementation, such as Figure 8 As shown, the second control module 703 includes:

[0110] The second update submodule 7032 is used to update the original calibration information using the new calibration information in the second calibration mode in response to the vehicle's operating scenario matching the target scenario.

[0111] In one possible implementation, the first detection submodule 7021 or the second detection submodule 7022 detects the availability of the new calibration information by detecting at least one of the surface smoothness, deviation, and incremental update degree of the new calibration information;

[0112] The surface smoothness includes the first difference between the accelerations corresponding to adjacent velocities and pedal openings in the new calibration information. The absolute value of the first difference being less than the first value indicates that the new calibration information is usable.

[0113] The deviation includes a second difference between the acceleration corresponding to the speed and pedal opening of the new calibration information and the original calibration information, respectively. If the absolute value of the second difference is less than the second value, it indicates that the new calibration information is usable.

[0114] The incremental update rate includes the number of data changes of the new calibration information relative to the original calibration information. If the proportion of the number of data changes to the total amount of data in the original calibration information is greater than the third value, it indicates that the new calibration information is available.

[0115] In one possible implementation, the first generation submodule 7011 or the second generation submodule 7012 generates the new calibration information based on the calibration data, including: incrementally generating the new calibration information when the speed range of the calibration data covers at least a set proportion of the set vehicle speed range.

[0116] In one possible implementation, such as Figure 8 As shown, the device also includes:

[0117] The processing module 802 is used to perform smoothing filtering at the junction of the unchanged speed range and the changed speed range in the original calibration information.

[0118] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0119] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0120] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0121] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure 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 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, 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 present disclosure described and / or claimed herein.

[0122] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0123] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0124] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 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 computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as calibration information processing methods. For example, in some embodiments, the calibration information processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the calibration information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform calibration information processing methods by any other suitable means (e.g., by means of firmware).

[0125] 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.

[0126] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may 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.

[0127] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. 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).

[0129] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments 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., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0130] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0131] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0132] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A calibration information processing method, comprising: Based on the vehicle's calibration mode and calibration data, new calibration information for the vehicle is generated; The detection of the new calibration information is controlled according to the detection conditions corresponding to the calibration mode; wherein, the calibration mode includes a first calibration mode and a second calibration mode, the detection condition corresponding to the first calibration mode is that the new calibration information is generated after the scene changes, and the detection condition corresponding to the second calibration mode is that the generated new calibration information has a difference from the original calibration information; Based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode, the update of the original calibration information is controlled.

2. The method according to claim 1, further comprising: Based on the vehicle's environmental data and / or status data, determine whether the vehicle's operating scenario matches the target scenario.

3. The method according to claim 1, wherein, Based on the vehicle's calibration mode and calibration data, new calibration information for the vehicle is generated, including: In the first calibration mode, when the vehicle's scenario changes, the new calibration information is generated based on the calibration data.

4. The method according to claim 3, wherein, Controlling the detection of the new calibration information according to the detection conditions corresponding to the calibration mode includes: In the first calibration mode, when the vehicle generates new calibration information, the availability of the new calibration information is detected.

5. The method according to claim 3 or 4, wherein, Based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode, the update of the original calibration information is controlled, including: In the first calibration mode, in response to the vehicle's environmental data and / or status data conforming to the update rules, the original calibration information is updated using the new calibration information.

6. The method according to claim 1, wherein, Based on the vehicle's calibration mode and calibration data, new calibration information for the vehicle is generated, including: In the second calibration mode, the new calibration information is generated based on the calibration data.

7. The method according to claim 6, wherein, Controlling the detection of the new calibration information according to the detection conditions corresponding to the calibration mode includes: In the second calibration mode, if the absolute value of the difference between the vehicle speed in the new calibration information and the original calibration information is greater than a set threshold, the availability of the new calibration information is detected.

8. The method according to claim 6 or 7, wherein, Based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode, the update of the original calibration information is controlled, including: In the second calibration mode, in response to the vehicle's operating scenario matching the target scenario, the original calibration information is updated using the new calibration information.

9. The method according to claim 4 or 7, wherein, Detecting the availability of the new calibration information includes: Detect at least one of the following: surface smoothness, deviation, and incremental update degree of the newly calibrated information; The surface smoothness includes the first difference between the accelerations corresponding to adjacent velocities and pedal openings in the new calibration information. The absolute value of the first difference being less than the first value indicates that the new calibration information is usable. The deviation includes a second difference between the acceleration corresponding to the speed and pedal opening of the new calibration information and the original calibration information, respectively. If the absolute value of the second difference is less than the second value, it indicates that the new calibration information is usable. The incremental update degree includes the number of data changes of the new calibration information relative to the original calibration information. If the proportion of the number of data changes to the total amount of data in the original calibration information is greater than a third value, it indicates that the new calibration information is available.

10. The method according to claim 3, 4, 6 or 7, wherein generating the new calibration information based on the calibration data comprises: The new calibration information is generated incrementally, provided that the speed range of the calibration data covers at least a set proportion of the set vehicle speed range.

11. The method of claim 10, further comprising: At the junction of the unchanged speed range and the changed speed range in the original calibration information, a smoothing filter is applied.

12. A calibration information processing device, comprising: The generation module is used to generate new calibration information for the vehicle based on the vehicle's calibration mode and calibration data. The first control module is used to control the detection of the new calibration information according to the detection conditions corresponding to the calibration mode; wherein, the calibration mode includes a first calibration mode and a second calibration mode, the detection condition corresponding to the first calibration mode is that the new calibration information is generated after the scene changes, and the detection condition corresponding to the second calibration mode is that the generated new calibration information has a difference from the original calibration information; The second control module is used to control the updating of the original calibration information based on the detection results of the new calibration information and the update conditions corresponding to the calibration mode.

13. The apparatus of claim 12, further comprising: The determination module is used to determine whether the vehicle's operating scenario matches the target scenario based on the vehicle's environmental data and / or status data.

14. The apparatus according to claim 12, wherein, The generation module includes: The first generation submodule is used to generate the new calibration information based on the calibration data when the vehicle scene changes in the first calibration mode.

15. The apparatus according to claim 14, wherein, The first control module includes: The first detection submodule is used to detect the availability of the new calibration information when the vehicle generates new calibration information in the first calibration mode.

16. The apparatus according to claim 14 or 15, wherein, The second control module includes: The first update submodule is used to update the original calibration information using the new calibration information in the first calibration mode, in response to the vehicle's environmental data and / or status data conforming to the update rules.

17. The apparatus according to claim 12, wherein, The generation module includes: The second generation submodule is used to generate the new calibration information based on the calibration data in the second calibration mode.

18. The apparatus according to claim 17, wherein, The first control module includes: The second detection submodule is used to detect the availability of the new calibration information when the absolute value of the difference between the vehicle speed in the new calibration information and the original calibration information is greater than a set threshold in the second calibration mode.

19. The apparatus according to claim 17 or 18, wherein, The second control module includes: The second update submodule is used to update the original calibration information using the new calibration information in the second calibration mode, in response to the vehicle's operating scenario conforming to the target scenario.

20. The apparatus according to claim 15 or 18, wherein, Detecting the availability of the new calibration information includes: detecting at least one of the surface smoothness, deviation, and incremental update degree of the new calibration information; The surface smoothness includes the first difference between the accelerations corresponding to adjacent velocities and pedal openings in the new calibration information. The absolute value of the first difference being less than the first value indicates that the new calibration information is usable. The deviation includes a second difference between the acceleration corresponding to the speed and pedal opening of the new calibration information and the original calibration information, respectively. If the absolute value of the second difference is less than the second value, it indicates that the new calibration information is usable. The incremental update degree includes the number of data changes of the new calibration information relative to the original calibration information. If the proportion of the number of data changes to the total amount of data in the original calibration information is greater than a third value, it indicates that the new calibration information is available.

21. The apparatus according to claim 14, 15, 17 or 18, wherein generating the new calibration information based on the calibration data comprises: The new calibration information is generated incrementally, provided that the speed range of the calibration data covers at least a set proportion of the set vehicle speed range.

22. The apparatus of claim 21, further comprising: The processing module is used to perform smoothing filtering at the junction of the unchanged speed range and the changed speed range in the original calibration information.

23. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

25. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-11.

26. An autonomous vehicle, comprising: The electronic device according to claim 23.

Images