Vehicle control method, device, equipment and medium

Abstract

The embodiment of the invention discloses a vehicle control method and device, equipment and a medium. The method comprises the steps of obtaining candidate verification data and candidate sensing data of a candidate sensing group in a current vehicle and backup sensing data of a backup sensing group, and performing data integrity verification according to the candidate verification data to obtain a data verification result; if the data verification result is that the data is not missing, determining candidate function data of the corresponding candidate controller according to the candidate sensing data and the backup sensing data, and determining reference function data according to the backup sensing data; determining candidate confidence of the corresponding candidate controller according to the candidate function data and the reference function data; and determining target function data of the current vehicle according to the candidate confidence and a preset confidence threshold, and controlling the current vehicle to run according to the target function data. The accuracy of controlling the vehicle operation based on the target function data is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle control method, device, equipment and medium. Background Technology

[0002] Currently, intelligent driving vehicles often only have one set of sensors, which cannot guarantee perception performance in the event of sensor failure. Furthermore, they only have two redundancies: a main controller and a secondary controller (i.e., a slave controller). If the secondary controller fails while monitoring the main controller, it can lead to abnormal vehicle control. Therefore, improving the accuracy of vehicle operation control is crucial. Summary of the Invention

[0003] This invention provides a vehicle control method, apparatus, device, and medium to improve the accuracy of vehicle operation control.

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

[0005] Acquire candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and perform data integrity verification based on the candidate verification data to obtain the data verification result.

[0006] If the data verification result is that the data is not missing, then the candidate function data of the corresponding candidate controller is determined according to the candidate sensor data and the backup sensor data, and the reference function data is determined according to the backup sensor data.

[0007] Based on the candidate function data and the reference function data, determine the candidate confidence level of the corresponding candidate controller;

[0008] Based on the candidate confidence level and the preset confidence threshold, the target function data of the current vehicle is determined, and the operation of the current vehicle is controlled according to the target function data.

[0009] According to another aspect of the present invention, a vehicle control device is provided, disposed in a vehicle controller, comprising:

[0010] The data verification result determination module is used to obtain candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and to perform data integrity verification based on the candidate verification data to obtain the data verification result.

[0011] The function data determination module is used to determine the candidate function data of the corresponding candidate controller based on the candidate sensor data and the backup sensor data if the data verification result is that the data is not missing, and to determine the reference function data based on the backup sensor data.

[0012] The candidate confidence level determination module is used to determine the candidate confidence level of the corresponding candidate controller based on the candidate function data and the reference function data.

[0013] The vehicle operation control module is used to determine the target function data of the current vehicle based on the candidate confidence level and the preset confidence threshold, and to control the operation of the current vehicle based on the target function data.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] One or more processors;

[0016] Memory, used to store one or more programs;

[0017] When one or more programs are executed by one or more processors, the one or more processors are able to execute any of the vehicle control methods provided in the embodiments of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement any of the vehicle control methods provided in the embodiments of the present invention.

[0019] This invention provides a vehicle control scheme. It acquires candidate verification data and candidate sensor data from candidate sensor groups, as well as backup sensor data from backup sensor groups, in the current vehicle. Data integrity is verified based on the candidate verification data to obtain a data verification result. If the data verification result indicates no missing data, candidate function data for the corresponding candidate controller is determined based on the candidate sensor data and backup sensor data. Reference function data is determined based on the backup sensor data. The candidate confidence level of the corresponding candidate controller is determined based on the candidate function data and reference function data. The target function data for the current vehicle is determined based on the candidate confidence level and a preset confidence threshold. The vehicle is then controlled to operate based on the target function data. This scheme improves the accuracy of the determined target function data by determining candidate function data for the corresponding candidate controller based on candidate sensor data from different candidate sensor groups, determining reference function data based on backup sensor data from backup sensor groups, determining candidate confidence levels for the corresponding candidate controller based on candidate function data and reference function data, and finally determining the target function data based on the candidate confidence level and a preset confidence threshold. This improves the accuracy of vehicle operation control based on the target function data.

[0020] 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

[0021] 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.

[0022] Figure 1 This is a flowchart of a vehicle control method provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a vehicle control method provided in Embodiment 2 of the present invention;

[0024] Figure 3A This is a structural diagram of a multi-redundancy architecture intelligent driving controller provided in Embodiment 3 of the present invention;

[0025] Figure 3B This is a smart driving control method based on a multi-redundancy architecture provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of a vehicle control device provided in Embodiment 4 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing a vehicle control method provided in Embodiment 5 of the present invention. Detailed Implementation

[0028] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a vehicle control method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a vehicle controller based on a multi-redundancy architecture controls vehicle operation. The method can be executed by a vehicle control device, which can be implemented in software and / or hardware and can be configured in an electronic device that carries vehicle control functions.

[0031] See Figure 1 The vehicle control method shown is applied to a vehicle controller and includes:

[0032] S110. Obtain candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and perform data integrity verification based on the candidate verification data to obtain the data verification result.

[0033] The vehicle controller is used to control the current operation of the vehicle. For example, the vehicle controller may include a main controller, slave controllers, and an auxiliary control module. The main controller is the core of the vehicle controller and is used to determine the control commands (i.e., main function data) for the current vehicle. The slave controller assists the main controller to reduce its workload and can also provide corresponding control commands (i.e., slave function data). The auxiliary control module performs safety checks on the main and slave controllers and provides relatively safe control commands (i.e., reference function data) for the current vehicle.

[0034] Here, "current vehicle" refers to the vehicle that needs to be controlled at the current moment. Specifically, the current vehicle can be an autonomous driving vehicle. "Candidate sensor group" refers to the group of sensors in the current vehicle connected to the candidate controller. The candidate sensor group includes a master sensor group and a slave sensor group. The master sensor group is the candidate sensor group connected to the master controller. The slave sensor group is the candidate sensor group connected to the slave controller. The backup sensor group refers to the combination of sensors connected to the auxiliary control module.

[0035] For example, the main sensor group may include a front-view camera 1, a rear-view camera, a front LiDAR, and a front millimeter-wave radar. The secondary sensor group may include a surround-view camera, a left front millimeter-wave radar, a left rear millimeter-wave radar, a left front-view camera, and a left rear-view camera. The backup sensor group may include a front-view camera 2, a right front-view camera, a right rear-view camera, a right front millimeter-wave radar, and a right rear millimeter-wave radar.

[0036] Candidate verification data refers to the road environment data determined by each sensor in the candidate sensor group based on its own collected perception data. Candidate verification data can include primary verification data and secondary verification data. Primary verification data refers to the road environment data determined by each sensor in the primary sensor group based on its own collected perception data. Secondary verification data refers to the road environment data determined by each sensor in the secondary sensor group based on its own collected perception data.

[0037] Candidate sensor data refers to the sensing data collected by each sensor in the candidate sensor group. Candidate sensor data can include master sensor data and slave sensor data. Master sensor data refers to the sensing data collected by each sensor in the master sensor group. Slave sensor data refers to the sensing data collected by each sensor in the slave sensor group. Backup sensor data refers to the sensing data collected by each sensor in the backup sensor group.

[0038] Among them, data integrity verification can be used to verify whether there are any missing candidate verification data in different candidate sensor groups. Specifically, the master verification data of the master sensor group and the slave verification data of the slave sensor group are compared. If they match completely, the data verification result indicates that no data is missing, meaning that none of the candidate verification data corresponding to the candidate controller is missing. If they do not match completely, it is determined that one side has missing data. That is, if the master verification data of the master sensor group is missing at least one master verification data compared to the slave verification data of the slave sensor group, the data verification result indicates that the candidate verification data corresponding to the master controller is missing, meaning that master verification data is missing. If the slave verification data of the slave sensor group is missing at least one slave verification data compared to the master verification data of the master sensor group, the data verification result indicates that the candidate verification data corresponding to the slave controller is missing, meaning that slave verification data is missing. If the master verification data of the master sensor group and the slave verification data of the slave sensor group are each missing at least one verification data, meaning that the master sensor group is missing at least one master verification data and the slave sensor group is missing at least one slave verification data, the data verification result indicates that both the candidate verification data corresponding to the candidate controller are missing, meaning that both master and slave verification data are missing.

[0039] Specifically, the main controller obtains master verification data and master sensor data from the connected master sensor group and sends them to the auxiliary control module; the slave controller obtains slave verification data and slave sensor data from the connected slave sensor group and sends them to the auxiliary control module; the auxiliary control module obtains backup sensor data from the connected backup sensor group; and the auxiliary control module performs data integrity verification on the master verification data sent by the main controller and the slave verification data sent by the slave controller to obtain the data verification result.

[0040] S120. If the data verification result shows that the data is not missing, then the candidate function data of the corresponding candidate controller is determined based on the candidate sensor data and the backup sensor data, and the reference function data is determined based on the backup sensor data.

[0041] In this context, "no missing data" means that no candidate verification data is missing for either the main controller or the slave controller. Candidate function data refers to the function data related to the current vehicle operation determined by the candidate controller. For example, candidate function data may include main function data and slave function data. Main function data refers to the function data related to the current vehicle operation determined by the main controller. Slave function data refers to the function data related to the current vehicle operation determined by the slave controller. Reference function data refers to the function data related to the current vehicle operation determined by the auxiliary control module.

[0042] Specifically, if the data verification result indicates that no data is missing, the main controller determines the main function data of the main controller based on the slave sensor data, backup sensor data, and the main controller's own main sensor data sent by the auxiliary control module; the slave controller determines the slave function data of the slave controller based on the main sensor data, backup sensor data, and the slave controller's own slave sensor data sent by the auxiliary control module; and the auxiliary control module determines the reference function data based on the backup sensor data.

[0043] S130. Based on the candidate function data and reference function data, determine the candidate confidence level of the corresponding candidate controller.

[0044] The candidate confidence score can be used to quantify the reliability of a candidate controller. For example, the candidate confidence score can include a master control confidence score and a slave control confidence score. The master control confidence score can be used to quantify the reliability of the master controller. The slave control confidence score can be used to quantify the reliability of the slave controller.

[0045] Specifically, the auxiliary control module determines the master control confidence level of the master controller based on the reference function data and the master function data of the master controller; the auxiliary control module determines the slave control confidence level of the slave controller based on the reference function data and the slave function data of the slave controller.

[0046] S140. Based on the candidate confidence level and the preset confidence threshold, determine the target function data of the current vehicle, and control the operation of the current vehicle according to the target function data.

[0047] The embodiments of the present invention do not impose any limitation on the size of the preset confidence threshold. It can be set by technicians based on experience or needs, or determined repeatedly through a large number of experiments.

[0048] Among them, target function data refers to the final function data determined by the vehicle controller for controlling the current operation of the vehicle.

[0049] Specifically, the auxiliary control module determines the target function data for the current vehicle from candidate function data and reference function data based on candidate confidence levels and preset confidence thresholds, and then determines the target control command based on the target function data. The target control command is then sent to the chassis actuators of the current vehicle, causing the chassis actuators to respond to the target control command and drive the current vehicle. The chassis actuators can be used to execute the target control command to drive the current vehicle. The target control command can be used to control the operation of the current vehicle.

[0050] In one optional embodiment, determining the target function data of the current vehicle based on the candidate confidence level and a preset confidence threshold includes: if the candidate confidence levels of all candidate controllers are less than the preset confidence threshold, then the reference function data is used as the target function data; if the candidate confidence levels of all candidate controllers are greater than or equal to the preset confidence threshold, then the candidate function data corresponding to the larger candidate confidence level is used as the target function data; if there exists a candidate confidence level of any candidate controller that is greater than or equal to the preset confidence threshold, and a candidate confidence level of another candidate controller that is less than the preset confidence threshold, then the candidate function data corresponding to the candidate controller whose candidate confidence level is greater than or equal to the preset confidence threshold is used as the target function data.

[0051] Specifically, if the master controller's master control confidence is less than a preset confidence threshold, and the slave controller's slave control confidence is less than a preset confidence threshold, then the reference function data determined by the auxiliary control module is used as the target function data. If the master controller's master control confidence is greater than or equal to a preset confidence threshold, and the slave controller's slave control confidence is greater than or equal to a preset confidence threshold, then the master control confidence and slave control confidence are compared. If the master control confidence is greater than or equal to the slave control confidence, then the master function data of the master controller is used as the target function data. If the master control confidence is less than the slave control confidence, then the slave function data of the slave controller is used as the target function data. If the master control confidence is greater than or equal to a preset confidence threshold, and the slave control confidence is less than a preset confidence threshold, then the master function data of the master controller is used as the target function data. If the slave control confidence is greater than or equal to a preset confidence threshold, and the master control confidence is less than a preset confidence threshold, then the slave function data of the slave controller is used as the target function data.

[0052] Understandably, by comparing the candidate confidence scores of candidate controllers with preset confidence thresholds, and determining the target function data based on the comparison results, the accuracy of the determined target function data is improved.

[0053] This invention provides a vehicle control scheme. It acquires candidate verification data and candidate sensor data from candidate sensor groups, as well as backup sensor data from backup sensor groups, in the current vehicle. Data integrity is verified based on the candidate verification data to obtain a data verification result. If the data verification result indicates no missing data, candidate function data for the corresponding candidate controller is determined based on the candidate sensor data and backup sensor data. Reference function data is determined based on the backup sensor data. The candidate confidence level of the corresponding candidate controller is determined based on the candidate function data and reference function data. The target function data for the current vehicle is determined based on the candidate confidence level and a preset confidence threshold. The vehicle is then controlled to operate based on the target function data. This scheme improves the accuracy of the determined target function data by determining candidate function data for the corresponding candidate controller based on candidate sensor data from different candidate sensor groups, determining reference function data based on backup sensor data from backup sensor groups, determining candidate confidence levels for the corresponding candidate controller based on candidate function data and reference function data, and finally determining the target function data based on the candidate confidence level and a preset confidence threshold. This improves the accuracy of vehicle operation control based on the target function data.

[0054] Based on the above technical solutions, embodiments of the present invention also provide a method for determining target functional data when the data verification result indicates that data is missing. In an optional embodiment, if the candidate controller includes a master controller and a slave controller, after performing data integrity verification based on the candidate verification data and obtaining the data verification result, the method further includes: if the data verification result indicates that the candidate verification data corresponding to the master controller is missing, then the reference functional data is used as the target functional data; if the data verification result indicates that the candidate verification data corresponding to the slave controller is missing, then the candidate functional data corresponding to the master controller is used as the target functional data; if the data verification result indicates that all candidate verification data corresponding to the candidate controllers are missing, then the reference functional data is used as the target functional data.

[0055] Specifically, the auxiliary control module determines whether the main verification data of the main controller is missing. If the main verification data is not missing, the main function data of the main controller is used as the target function data; if the main verification data is missing, the reference function data is used as the target function data.

[0056] Understandably, by determining the target function data from the reference function data and candidate function data based on different data verification results, the accuracy of the determined target function data is improved.

[0057] Example 2

[0058] Figure 2This is a flowchart of a vehicle control method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further refines the operation of "determining the candidate confidence level of the corresponding candidate controller based on candidate function data and reference function data" into "determining the perception confidence level of the corresponding candidate controller based on candidate perception data and reference perception data; determining the planning confidence level of the corresponding candidate controller based on candidate planning data and reference planning data; determining the control confidence level of the corresponding candidate controller based on candidate control data and reference control data; and determining the candidate confidence level of the corresponding candidate controller based on the perception confidence level, planning confidence level, and control confidence level," thereby improving the candidate confidence level determination mechanism. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments.

[0059] See Figure 2 The vehicle control method shown includes:

[0060] S210. Obtain candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and perform data integrity verification based on the candidate verification data to obtain the data verification result.

[0061] S220. If the data verification result shows that the data is not missing, then the candidate function data of the corresponding candidate controller is determined based on the candidate sensor data and the backup sensor data, and the reference function data is determined based on the backup sensor data.

[0062] S230. Determine the perception confidence of the corresponding candidate controller based on the candidate perception data and the reference perception data.

[0063] The candidate function data in this embodiment of the invention includes candidate perception data, candidate planning data, and candidate control data. Candidate perception data refers to the perception data of the current vehicle determined by the candidate controller. For example, candidate perception data may include candidate lane line data, candidate vehicle data, and candidate obstacle data. Candidate lane line data may include all lane line information on the road. Candidate vehicle data refers to data related to vehicles on the road. Candidate vehicle data may include the current vehicle's position and speed, as well as the positions and speeds of other vehicles on the road. Candidate obstacle data refers to data associated with obstacles on the road. Candidate obstacle data may include obstacle position and obstacle speed.

[0064] Here, candidate planning data refers to the planning data of the current vehicle determined by the candidate controller. For example, candidate planning data can be the candidate desired trajectory determined by the candidate controller. The candidate desired trajectory refers to the trajectory that the candidate controller expects the current vehicle to travel.

[0065] Here, candidate control data refers to the control data of the current vehicle determined by the candidate controller. For example, candidate control data may include candidate steering angle and candidate acceleration. Candidate steering angle refers to the steering wheel angle data of the current vehicle determined by the candidate controller. Candidate acceleration refers to the acceleration of the current vehicle determined by the candidate controller.

[0066] It should be noted that the candidate function data includes main function data and slave function data. The main function data includes candidate perception data, candidate planning data and candidate control data corresponding to the main controller. Similarly, the slave function data includes candidate perception data, candidate planning data and candidate control data corresponding to the slave controller.

[0067] Among them, the perception confidence score can be used to quantify the reliability of the perception performance of a candidate controller.

[0068] Specifically, for any candidate controller, the auxiliary control module determines the perception confidence of the candidate controller based on the reference perception data and the candidate perception data of the candidate controller.

[0069] In an optional embodiment, if the candidate perception data includes candidate vehicle data, candidate obstacle data, and candidate lane line data, and the reference perception data includes reference vehicle data, reference obstacle data, and reference lane line data, then determining the perception confidence of the corresponding candidate controller based on the candidate perception data and the reference perception data includes: determining the number of reference vehicles based on the reference vehicle data, and determining the number of candidate vehicles based on the reference vehicle data and the candidate vehicle data; determining the number of reference obstacles based on the reference obstacle data, and determining the number of candidate obstacles based on the reference obstacle data and the candidate obstacle data; determining the lane line distance data of the corresponding candidate controller based on the candidate lane line data and the reference lane line data; and determining the perception confidence of the corresponding candidate controller based on the number of reference vehicles, the number of candidate vehicles, the number of reference obstacles, the number of candidate obstacles, the lane line distance data, and a preset lane line distance threshold.

[0070] Among them, reference perception data refers to the perception data of the current vehicle determined by the auxiliary control module. Reference planning data refers to the planning data of the current vehicle determined by the auxiliary control module. Reference control data refers to the control data of the current vehicle determined by the auxiliary control module.

[0071] The reference vehicle count refers to the number of vehicles on the road as determined by the auxiliary control module. The candidate vehicle count refers to the number of vehicles whose determination by the candidate controller overlaps with the number of vehicles determined by the auxiliary control module.

[0072] The reference obstacle count refers to the number of obstacles on the road determined by the auxiliary control module. The candidate obstacle count refers to the number of obstacles that overlap with those determined by the candidate controller and the auxiliary control module.

[0073] The lane distance data can be used to quantify the difference between candidate lane line data and reference lane line data. For example, the lane distance data can be the vertical distance between a candidate lane line determined by the candidate lane line data and a reference lane line determined by the reference lane line data. This embodiment of the invention does not limit the size of the preset lane distance threshold; it can be set by a technician based on experience or needs, or determined repeatedly through numerous experiments.

[0074] For example, the perception confidence of the main controller can be determined based on the following formula:

[0075]

[0076] Among them, P 1_percept y1 represents the perception confidence of the main controller; z1 represents the number of candidate vehicles corresponding to the main controller; m represents the number of reference vehicles; n represents the number of reference obstacles; X represents the preset lane line distance threshold; L1 represents the lane line distance data corresponding to the main controller.

[0077] For example, the perceived confidence from the controller can be determined based on the following formula:

[0078]

[0079] Among them, P 2_percept y1 represents the perception confidence from the controller; y2 represents the number of candidate vehicles corresponding to the controller; z2 represents the number of candidate obstacles corresponding to the controller; L2 represents the lane line distance data corresponding to the controller.

[0080] Understandably, by determining the perception confidence of the corresponding candidate controller based on the number of reference vehicles, the number of candidate vehicles, the number of reference obstacles, the number of candidate obstacles, lane line distance data, and the preset lane line distance threshold, the perception confidence is determined from multiple dimensions, thus improving the accuracy of the determined perception confidence.

[0081] S240. Based on the candidate planning data and the reference planning data, determine the planning confidence level of the corresponding candidate controller.

[0082] Among them, the planning confidence score can be used to quantify the reliability of the planning performance of candidate controllers.

[0083] Specifically, for any candidate controller, the auxiliary control module determines the planning confidence level of the candidate controller based on the reference planning data and the candidate planning data of the candidate controller.

[0084] In an optional embodiment, determining the planning confidence of the corresponding candidate controller based on candidate planning data and reference planning data includes: determining the planning distance data of the corresponding candidate controller based on the candidate planning data and reference planning data, and determining the planning confidence of the corresponding candidate controller based on the planning distance data and a preset planning distance threshold.

[0085] The planned distance data can be used to quantify the difference between candidate planned data and reference planned data. For example, the planned distance data can be the vertical distance between the candidate desired trajectory and the reference desired trajectory. The reference desired trajectory refers to the trajectory that the auxiliary control module expects the current vehicle to travel. This embodiment of the invention does not limit the size of the preset planned distance threshold; it can be set by technicians based on experience or needs, or determined repeatedly through numerous experiments.

[0086] Specifically, the auxiliary control module determines the planning distance data of the corresponding candidate controller based on the candidate expected trajectory and the reference expected trajectory, and determines the planning confidence of the corresponding candidate controller based on the planning distance data and the preset planning distance threshold.

[0087] For example, the planning confidence of the master controller can be determined using the following formula:

[0088]

[0089] Among them, P 1_plan Indicates the planning confidence level of the main controller; Dis max This indicates the preset planning distance threshold; Distance1 indicates the planning distance data of the main controller.

[0090] For example, the planning confidence from the controller can be determined using the following formula:

[0091]

[0092] Among them, P 2_plan Distance1 represents the planning confidence from the controller; Distance2 represents the planning distance data from the controller.

[0093] Understandably, by determining the planning confidence of the corresponding candidate controller based on the planning distance data and the preset planning distance threshold, the accuracy of the determined planning confidence is improved.

[0094] S250. Based on the candidate control data and the reference control data, determine the control confidence level of the corresponding candidate controller.

[0095] Among them, control confidence can be used to quantify the reliability of the control performance of candidate controllers.

[0096] Specifically, for any candidate controller, the auxiliary control module determines the control confidence level of the candidate controller based on the reference control data and the candidate control data of the candidate controller.

[0097] In an optional embodiment, determining the control confidence of the corresponding candidate controller based on candidate control data and reference control data includes: determining the control confidence of the corresponding candidate controller based on the candidate steering angle and candidate acceleration in the candidate control data, and the reference steering angle and reference acceleration in the reference control data.

[0098] The reference steering angle refers to the steering wheel angle data of the current vehicle determined by the auxiliary control module. The reference acceleration refers to the acceleration of the current vehicle determined by the auxiliary control module.

[0099] For example, the control confidence of the main controller can be determined based on the following formula:

[0100]

[0101] Among them, P 1_control Indicates the control confidence level of the main controller; δ 1_steer Indicates the candidate steering angle of the main controller; δ steer Indicates the reference steering angle; a 1_expect Indicates the candidate acceleration of the main controller; a expect This represents the reference acceleration.

[0102] For example, the control confidence from the controller can be determined based on the following formula:

[0103]

[0104] Among them, P 2_control Indicates the control confidence level from the controller; δ 2_steer Indicates the candidate steering angle from the controller; a 2_expect This represents the candidate acceleration from the controller.

[0105] Understandably, by determining the control confidence of the corresponding candidate controller based on the candidate steering angle, candidate acceleration, reference steering angle, and reference acceleration, the accuracy of the determined control confidence is improved.

[0106] S260. Based on the perception confidence, planning confidence, and control confidence, determine the candidate confidence of the corresponding candidate controller. For example, the candidate confidence of the main controller (i.e., the main control confidence) can be determined based on the following formula:

[0107] P1 = P 1_percept ×P 1_plan ×P 1_control ;

[0108] Where P1 represents the main control confidence level, that is, the candidate confidence level corresponding to the main controller.

[0109] For example, candidate confidence from the controller (i.e., confidence from the controller) can be determined based on the following formula:

[0110] P2 = P 2_percept ×P 2_plan ×P 2_control ;

[0111] Where P2 represents the control confidence, that is, the candidate confidence corresponding to the controller.

[0112] S270. Based on the candidate confidence level and the preset confidence threshold, determine the target function data of the current vehicle, and control the operation of the current vehicle according to the target function data.

[0113] This invention provides a vehicle control scheme that refines the process of determining the candidate confidence level of a candidate controller based on candidate function data and reference function data into determining the perception confidence level of the candidate controller based on candidate perception data and reference perception data; determining the planning confidence level of the candidate controller based on candidate planning data and reference planning data; determining the control confidence level of the candidate controller based on candidate control data and reference control data; and determining the candidate confidence level of the candidate controller based on the perception confidence level, planning confidence level, and control confidence level. This improves the candidate confidence level determination mechanism. The above scheme, by determining the candidate confidence level of the candidate controller from the separately determined perception confidence level, planning confidence level, and control confidence level, achieves multi-dimensional determination of candidate confidence level, improving the accuracy of the determined candidate confidence level.

[0114] Example 3

[0115] This invention provides an optional example based on the above embodiments. It should be noted that for parts not described in detail in this invention's embodiments, please refer to the descriptions in other embodiments.

[0116] Currently, intelligent driving vehicles often only have one set of sensors, which cannot guarantee perception performance in the event of sensor failure. Furthermore, they only have dual redundancy (main controller and secondary controller), and the secondary controller's monitoring of the main controller can fail, compromising absolute safety. Additionally, there is a lack of process supervision strategies for the perception, planning, and control stages. Level 4 and even Level 3 autonomous driving vehicles must achieve sensor redundancy, controller redundancy, and ensure the computation process is free from abnormal failures. Existing technologies suffer from the following problems: Currently, intelligent driving vehicles often only have one set of sensors, which cannot guarantee perception performance in the event of sensor failure; using two sets of sensors would significantly increase costs; the dual redundancy (main controller and secondary controller) means the secondary controller's monitoring of the main controller can fail, compromising absolute safety; and there is a lack of process supervision strategies for the perception, planning, and control stages.

[0117] This invention proposes an intelligent driving control method based on a multi-redundancy architecture, which has the following advantages: By rationally configuring the architecture, the safety arbitration module (i.e., auxiliary control module) of the two controllers (i.e., the master controller and the slave controller) is connected to different sensors, realizing sensor grouping and reducing the cost of full sensor redundancy; the invention introduces a safety arbitration module and establishes a switching strategy, realizing third-party supervision of the master controller or slave controller (i.e., the slave controller), significantly improving the safety level; and establishing reasonable verification logic ensures that abnormal failures of the controller during perception, planning, and control processes can be detected, guaranteeing absolute safety of intelligent driving and increasing its safety.

[0118] This invention proposes an intelligent driving control method based on a multi-redundancy architecture. Specifically, an overall hardware architecture is established, namely a vehicle controller, including controller 1 (i.e., the main controller), controller 2 (i.e., the slave controller), and a safety arbitration module. By connecting different sensors to the two controllers and the safety arbitration module respectively, sensor grouping is achieved, reducing the cost of full sensor redundancy. The introduction of the safety arbitration module and the establishment of a switching strategy enable third-party supervision of the main or slave controller, and a reasonable verification logic is established to ensure that abnormal failures of the controller during perception, planning, and control processes can be detected, guaranteeing the absolute safety of intelligent driving. Based on the above key inventive points, the method achieves the advantages of low cost, high redundancy, and high reliability in intelligent driving control.

[0119] This invention proposes an intelligent driving control method based on a multi-redundancy architecture. The overall system includes sensing devices, an intelligent driving controller (i.e., a vehicle controller), and chassis actuators.

[0120] For example, an embodiment of the present invention provides a hardware structure diagram of an intelligent driving controller with a multi-redundancy architecture, such as... Figure 3AAs shown, the intelligent driving controller (i.e., vehicle controller) mainly includes controller 1, controller 2 and safety arbitration module.

[0121] For example, controller 1 receives perception data (i.e., main sensor data) from the main sensor group (front-view camera 1 + rear-view camera + front LiDAR + front millimeter-wave radar), deserializes the image data collected by front-view camera 1 and rear-view camera, reads Ethernet messages from the data collected by the front LiDAR, and reads CAN (Controller Area Network) messages from the data collected by the front millimeter-wave radar. Simultaneously, it sends all perception data to the safety arbitration module. Additionally, controller 1 also receives perception data from controller 2 and the backup group (i.e., receives slave sensor data and backup sensor data) sent by the safety arbitration module. It fuses the received perception data with its own perception data and then performs a three-step process: perception, planning, and control. The perception program outputs lane line, vehicle, and obstacle information (i.e., candidate sensor data for the main controller) processed by controller 1; the planning program outputs the desired trajectory information (i.e., candidate planning data for the main controller) processed by controller 1; and the control program outputs the desired acceleration and steering wheel angle information (i.e., candidate control data for the main controller) processed by controller 1. Controller 1 needs to send the intermediate output information of the three-step procedure to the safety arbitration module for verification. It should be noted that the perception procedure determines candidate perception data based on the main sensor data, the planning procedure determines candidate planning data based on the candidate perception data, and the control procedure determines candidate control data based on the candidate planning data.

[0122] For example, controller 2 receives perception data (i.e., slave sensor data) from the sensor group (surround view camera + left front millimeter wave radar + left rear millimeter wave radar + left front view camera + left rear view camera), deserializes the image data collected by the surround view camera, left front view camera, and left rear view camera, and reads the data collected by the left front millimeter wave radar and left rear millimeter wave radar using CAN messages. Simultaneously, it sends all perception data to the safety arbitration module. Additionally, controller 2 also receives perception data from controller 1 and the backup group (i.e., receives main sensor data and backup sensor data) sent by the safety arbitration module. It fuses the received perception data with the perception data from controller 2, and then performs a three-step process: perception, planning, and control. The perception program outputs lane lines, vehicle, and obstacle information processed by controller 2 (i.e., candidate sensor data from slave controllers); the planning program outputs the desired trajectory information processed by controller 2 (i.e., candidate planning data from the main controller); and the control program outputs the desired acceleration and steering wheel angle information processed by controller 2 (i.e., candidate control data from the main controller). Controller 2 needs to send the intermediate output information of the three-step process to the safety arbitration module for verification.

[0123] For example, the security arbitration module receives the sensing data (i.e., backup sensor data) from the backup sensor group (front-view camera 2 + right front-view camera + right rear-view camera + right front millimeter-wave radar + right rear millimeter-wave radar), deserializes the image data collected by the front-view camera 2, right front-view camera, and right rear-view camera, and reads the data collected by the right front millimeter-wave radar and right rear millimeter-wave radar using CAN messages. Simultaneously, the security arbitration module receives and verifies the sensing data sent by controller 1 and controller 2 (i.e., receives master sensor data, slave sensor data, master verification data, and slave verification data, and performs data integrity verification on the master and slave verification data). Additionally, the security arbitration module sends the sensing data of controller 2 and the backup group to controller 1, and sends the sensing data of controller 1 and the backup group to controller 2. The security arbitration module receives intermediate output information from controller 1, controller 2, and the minimum security strategy module for detailed verification of the sensing, planning, and control steps. Finally, the safety judgment is made using the three-level verification results. The expected control command is determined from the output commands of controller 1, controller 2 and safety judgment module and output to the chassis actuator. That is, the target function data is determined and the target control command is determined based on the target function data, and the target control command is sent to the chassis actuator.

[0124] For example, embodiments of the present invention provide an intelligent driving control method based on a multi-redundancy architecture, such as... Figure 3B As shown. Controller 1 receives data from the primary sensor group and forwards it, while controller 2 receives data from the secondary sensor group and forwards it. The security arbitration module receives data from the backup sensor group and simultaneously receives data from both controller 1 and controller 2, performing data integrity verification.

[0125] For example, the data integrity verification result has three scenarios: 1) Only controller 1 data is lost, or both controller 1 and controller 2 data are lost. The safety arbitration module executes the minimum safety strategy, directly outputting the desired control command to the chassis actuator, that is, determining the target control command based on the reference function data and sending the target control command to the chassis actuator. 2) Only controller 2 data is lost. Controller 1's function is degraded, the vehicle speed is reduced, and the safety arbitration part outputs real-time monitoring data of controller 1; 2.1) If controller 1 data is lost, the safety arbitration module executes the minimum safety strategy, directly outputting the desired control command to the chassis actuator, that is, determining the target control command based on the reference function data and sending the target control command to the chassis actuator; 2.2) If controller 1 data is not lost, controller 1 outputs control commands to the safety judgment module, that is, determining the target control command based on the main function data and sending the target control command to the chassis actuator. (3) Data from both controller 1 and controller 2 is intact and functions normally. The detailed verification section in the safety arbitration module verifies the intermediate output information of the perception, planning, and control steps of controller 1, controller 2, and the minimum safety strategy module. The specific verification method is described below. At the same time, the minimum safety strategy module runs. The safety judgment module selects the optimal control command from the output commands of controller 1, controller 2, and the minimum safety strategy module based on the three-level verification results and sends it to the chassis actuator. That is, the safety judgment module determines the candidate confidence level of the corresponding candidate controller based on the perception confidence level, planning confidence level, and control confidence level, and determines the target function data based on the candidate confidence level and the preset confidence threshold, and determines the target control command based on the target function data.

[0126] For example, the specific verification method of the detailed verification part in the aforementioned safety arbitration module is explained. Perception Verification: Controller 1 and Controller 2 respectively use algorithms to identify surrounding vehicles and obstacles, including vehicle position (Vehicle_position), vehicle speed (Vehicle_speed), obstacle position (Obstacle_position), obstacle speed (Obstacle_speed), and the coefficient matrix A of the cubic equation of the lane lines (i.e., candidate lane lines). Then, the detailed verification part calculates the perception confidence based on the results sent by Controller 1 and Controller 2 and the perception results of the minimum safety strategy module. For any controller i (controller 1 when i=1; controller 2 when i=2), if the minimum safety strategy module identifies m vehicles (i.e., the number of reference vehicles) and n obstacles (i.e., the number of reference obstacles), a reasonable deviation is set to obtain the number y of vehicles overlapping with m in the identification result of controller 1. i (i.e., the number of candidate vehicles in controller i), and the number of obstacles z that overlap with n. i(i.e., the number of candidate obstacles for controller i); then calculate the distance L between the cubic lane equation identified by controller i and the lane equation identified by the minimum safety strategy module. i (i.e., lane distance data of controller i), set the maximum distance X (i.e., preset lane distance threshold); the perception confidence P of controller i is finally obtained through the following formula. i_percept :

[0127]

[0128] For example, the planning verification process involves controllers 1 and 2 each planning the desired trajectory using an algorithm. Then, the detailed verification section calculates the planning confidence based on the desired trajectories sent by controllers 1 and 2, and the desired trajectory from the minimum safety policy module. For any controller i, the distance between the desired trajectory output by the minimum safety policy module and the desired trajectory of controller i is Distance. i (i.e., the planned distance data of controller i), set the maximum distance to Dis. max (i.e., the preset planning distance threshold) is used to finally obtain the planning confidence level P of controller i through the following formula. i_plan :

[0129]

[0130] For example, control verification: Controller 1 and Controller 2 will each use an algorithm to calculate the current desired steering angle δ steer and expected acceleration a expect Then, the detailed verification section calculates the control confidence level based on the control commands sent by controllers 1 and 2, and the control commands from the minimum safety policy module. For any controller i, the planning confidence level P of controller i is finally obtained using the following formula. i_control :

[0131]

[0132] Finally, the candidate confidence level P of controller i is obtained by comprehensively calculating the results of the three steps of perception verification, planning verification, and control verification. i :

[0133] P i =P i_percept ×P i_plan ×P i_control ;

[0134] For example, when both P1 and P2 are less than the minimum confidence threshold (i.e., the preset confidence threshold), it is considered that both controller 1 and controller 2 are faulty, and the safety judgment module outputs the control command of the minimum safety strategy module as the expected control command (i.e. the target control command) to the current vehicle; otherwise, the safety judgment module will take the controller output control command with higher confidence as the expected control command and output it to the current vehicle.

[0135] This invention proposes a hardware scheme for a multi-redundant architecture intelligent driving controller and interaction signals between modules; this invention proposes a switching strategy for the safety arbitration module in the event of failure of controller 1 or controller 2; this invention proposes calculation formulas for perception verification, planning verification, and control verification of the safety arbitration module.

[0136] This invention proposes an intelligent driving control method based on a multi-redundancy architecture. By using two controllers plus a safety arbitration module, sensor grouping is achieved, reducing the cost of full sensor redundancy. The introduction of a safety arbitration module and the establishment of a switching strategy enable third-party supervision of the main controller or the secondary controller. Furthermore, a reasonable verification logic is established to detect abnormal failures of the controller during the perception, planning, and control processes, ensuring the absolute safety of intelligent driving.

[0137] Example 4

[0138] Figure 4 This is a schematic diagram of a vehicle control device provided in Embodiment 4 of the present invention. This embodiment is applicable to situations where a vehicle controller based on a multi-redundancy architecture controls vehicle operation. The method can be executed by a vehicle control device, which can be implemented in software and / or hardware and can be configured in an electronic device that carries vehicle control functions.

[0139] like Figure 4 As shown, the device is configured in the vehicle controller and includes: a data verification result determination module 410, a functional data determination module 420, a candidate confidence level determination module 430, and a vehicle operation control module 440. Among them,

[0140] The data verification result determination module 410 is used to obtain candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and to perform data integrity verification based on the candidate verification data to obtain the data verification result.

[0141] The function data determination module 420 is used to determine the candidate function data of the corresponding candidate controller based on the candidate sensor data and the backup sensor data if the data verification result is that the data is not missing, and to determine the reference function data based on the backup sensor data.

[0142] The candidate confidence level determination module 430 is used to determine the candidate confidence level of the corresponding candidate controller based on the candidate function data and the reference function data.

[0143] The vehicle operation control module 440 is used to determine the target function data of the current vehicle based on the candidate confidence level and the preset confidence threshold, and to control the operation of the current vehicle based on the target function data.

[0144] This invention provides a vehicle control scheme. It acquires candidate verification data and candidate sensor data from candidate sensor groups, as well as backup sensor data from backup sensor groups, in the current vehicle. Data integrity is verified based on the candidate verification data to obtain a data verification result. If the data verification result indicates no missing data, candidate function data for the corresponding candidate controller is determined based on the candidate sensor data and backup sensor data. Reference function data is determined based on the backup sensor data. The candidate confidence level of the corresponding candidate controller is determined based on the candidate function data and reference function data. The target function data for the current vehicle is determined based on the candidate confidence level and a preset confidence threshold. The vehicle is then controlled to operate based on the target function data. This scheme improves the accuracy of the determined target function data by determining candidate function data for the corresponding candidate controller based on candidate sensor data from different candidate sensor groups, determining reference function data based on backup sensor data from backup sensor groups, determining candidate confidence levels for the corresponding candidate controller based on candidate function data and reference function data, and finally determining the target function data based on the candidate confidence level and a preset confidence threshold. This improves the accuracy of vehicle operation control based on the target function data.

[0145] Optionally, if the candidate function data includes candidate perception data, candidate planning data, and candidate control data, and the reference function data includes reference perception data, reference planning data, and reference control data, then the candidate confidence determination module 430 includes:

[0146] A perception confidence determination unit is used to determine the perception confidence of the corresponding candidate controller based on the candidate perception data and the reference perception data.

[0147] The planning confidence determination unit is used to determine the planning confidence of the corresponding candidate controller based on the candidate planning data and the reference planning data.

[0148] A control confidence determination unit is used to determine the control confidence of a corresponding candidate controller based on the candidate control data and the reference control data.

[0149] The candidate confidence determination unit is used to determine the candidate confidence of the corresponding candidate controller based on the perception confidence, the planning confidence, and the control confidence.

[0150] Optionally, if the candidate perception data includes candidate vehicle data, candidate obstacle data, and candidate lane line data, and the reference perception data includes reference vehicle data, reference obstacle data, and reference lane line data, then the perception confidence determination unit is specifically used for:

[0151] Based on the reference vehicle data, determine the number of reference vehicles, and based on the reference vehicle data and the candidate vehicle data, determine the number of candidate vehicles.

[0152] Based on the reference obstacle data, determine the number of reference obstacles, and based on the reference obstacle data and the candidate obstacle data, determine the number of candidate obstacles;

[0153] Based on the candidate lane line data and the reference lane line data, determine the lane line distance data of the corresponding candidate controller;

[0154] The perception confidence of the corresponding candidate controller is determined based on the number of reference vehicles, the number of candidate vehicles, the number of reference obstacles, the number of candidate obstacles, the lane line distance data, and the preset lane line distance threshold.

[0155] Optionally, the planning confidence determination unit is specifically used for:

[0156] Based on the candidate planning data and the reference planning data, the planning distance data of the corresponding candidate controller is determined, and based on the planning distance data and the preset planning distance threshold, the planning confidence of the corresponding candidate controller is determined.

[0157] Optionally, the control confidence determination unit is specifically used for:

[0158] The control confidence of the corresponding candidate controller is determined based on the candidate steering angle and candidate acceleration in the candidate control data, and the reference steering angle and reference acceleration in the reference control data.

[0159] Optionally, the vehicle operation control module 440 includes:

[0160] The first target function data determination unit is used to determine the reference function data as the target function data if the candidate confidence scores of the candidate controllers are all less than a preset confidence threshold.

[0161] The second target function data determination unit is used to determine the target function data if the candidate confidence scores of the candidate controllers are all greater than or equal to a preset confidence threshold.

[0162] Optionally, if the candidate controller includes a master controller and a slave controller, then after performing data integrity verification based on the candidate verification data and obtaining the data verification result, the device further includes:

[0163] The first target function data determination module is used to take the reference function data as the target function data if the data verification result shows that the candidate verification data corresponding to the main controller is missing.

[0164] The second target function data determination module is used to take the candidate function data corresponding to the main controller as the target function data if the data verification result shows that the candidate verification data corresponding to the controller is missing.

[0165] The third target function data determination module is used to take the reference function data as the target function data if the data verification result shows that all candidate verification data corresponding to the candidate controller are missing.

[0166] The vehicle control device provided in the embodiments of the present invention can execute the vehicle control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each vehicle control method.

[0167] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision and disclosure of candidate verification data, candidate sensing data and backup sensing data, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0168] Example 5

[0169] Figure 5 This is a schematic diagram of an electronic device for implementing a vehicle control method according to Embodiment 5 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 can 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.

[0170] like Figure 5As 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.

[0171] 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.

[0172] 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 vehicle control methods.

[0173] In some embodiments, the vehicle control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 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 vehicle control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle control method by any other suitable means (e.g., by means of firmware).

[0174] 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.

[0175] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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.

[0180] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0181] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle control method, characterized in that, Applied to vehicle controllers, including: Acquire candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and perform data integrity verification based on the candidate verification data to obtain the data verification result. If the data verification result is that the data is not missing, then the candidate function data of the corresponding candidate controller is determined according to the candidate sensor data and the backup sensor data, and the reference function data is determined according to the backup sensor data. Based on the candidate function data and the reference function data, determine the candidate confidence level of the corresponding candidate controller; Based on the candidate confidence level and the preset confidence threshold, the target function data of the current vehicle is determined, and the operation of the current vehicle is controlled according to the target function data.

2. The method according to claim 1, characterized in that, If the candidate function data includes candidate sensing data, candidate planning data, and candidate control data, and the reference function data includes reference sensing data, reference planning data, and reference control data, then determining the candidate confidence level of the corresponding candidate controller based on the candidate function data and the reference function data includes: Based on the candidate sensing data and the reference sensing data, the sensing confidence of the corresponding candidate controller is determined; Based on the candidate planning data and the reference planning data, determine the planning confidence level of the corresponding candidate controller; Based on the candidate control data and the reference control data, the control confidence level of the corresponding candidate controller is determined; Based on the perception confidence, the planning confidence, and the control confidence, the candidate confidence of the corresponding candidate controller is determined.

3. The method according to claim 2, characterized in that, If the candidate perception data includes candidate vehicle data, candidate obstacle data, and candidate lane line data, and the reference perception data includes reference vehicle data, reference obstacle data, and reference lane line data, then determining the perception confidence of the corresponding candidate controller based on the candidate perception data and the reference perception data includes: Based on the reference vehicle data, determine the number of reference vehicles, and based on the reference vehicle data and the candidate vehicle data, determine the number of candidate vehicles. Based on the reference obstacle data, determine the number of reference obstacles, and based on the reference obstacle data and the candidate obstacle data, determine the number of candidate obstacles; Based on the candidate lane line data and the reference lane line data, determine the lane line distance data of the corresponding candidate controller; The perception confidence of the corresponding candidate controller is determined based on the number of reference vehicles, the number of candidate vehicles, the number of reference obstacles, the number of candidate obstacles, the lane line distance data, and the preset lane line distance threshold.

4. The method according to claim 2, characterized in that, The step of determining the planning confidence level of the corresponding candidate controller based on the candidate planning data and the reference planning data includes: Based on the candidate planning data and the reference planning data, the planning distance data of the corresponding candidate controller is determined, and based on the planning distance data and the preset planning distance threshold, the planning confidence of the corresponding candidate controller is determined.

5. The method according to claim 2, characterized in that, The step of determining the control confidence level of the corresponding candidate controller based on the candidate control data and the reference control data includes: The control confidence of the corresponding candidate controller is determined based on the candidate steering angle and candidate acceleration in the candidate control data, and the reference steering angle and reference acceleration in the reference control data.

6. The method according to claim 1, characterized in that, The step of determining the target function data of the current vehicle based on the candidate confidence level and the preset confidence threshold includes: If the confidence scores of all candidate controllers are less than a preset confidence threshold, then the reference function data will be used as the target function data. If the candidate confidence scores of all candidate controllers are greater than or equal to a preset confidence threshold, then the candidate function data corresponding to the larger candidate confidence score will be used as the target function data.

7. The method according to any one of claims 1-6, characterized in that, If the candidate controller includes a master controller and a slave controller, then after performing data integrity verification based on the candidate verification data and obtaining the data verification result, the method further includes: If the data verification result shows that the candidate verification data corresponding to the main controller is missing, then the reference function data will be used as the target function data. If the data verification result indicates that the candidate verification data corresponding to the controller is missing, then the candidate function data corresponding to the main controller will be used as the target function data. If the data verification result shows that all candidate verification data corresponding to the candidate controller are missing, then the reference function data will be used as the target function data.

8. A vehicle control device, characterized in that, Configured in the vehicle controller, including: The data verification result determination module is used to obtain candidate verification data and candidate sensor data of the candidate sensor group in the current vehicle, as well as backup sensor data of the backup sensor group, and to perform data integrity verification based on the candidate verification data to obtain the data verification result. The function data determination module is used to determine the candidate function data of the corresponding candidate controller based on the candidate sensor data and the backup sensor data if the data verification result is that the data is not missing, and to determine the reference function data based on the backup sensor data. The candidate confidence level determination module is used to determine the candidate confidence level of the corresponding candidate controller based on the candidate function data and the reference function data. The vehicle operation control module is used to determine the target function data of the current vehicle based on the candidate confidence level and the preset confidence threshold, and to control the operation of the current vehicle based on the target function data.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a vehicle control method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements a vehicle control method as described in any one of claims 1-7.

Images