Safety monitoring method and safety monitoring system for intelligent driving, and vehicle for same

Abstract

The present application relates to the technical field of vehicles, and discloses a safety monitoring method and a safety monitoring system for intelligent driving, and a vehicle for same. The safety monitoring method comprises: determining the state of an intelligent driving function (S100); and when the intelligent driving function is in an activated state and it is identified that a safety risk behavior event of a vehicle exists, uploading current operation data of the vehicle to a cloud (S200).

Description

Intelligent driving safety monitoring method, safety monitoring system and vehicle thereof

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202410046122.8 and application date January 11, 2024, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present application relates to the field of vehicle technology, and in particular to a safety monitoring method, a safety monitoring system and a vehicle thereof for intelligent driving. Background Art

[0004] Intelligent driving technology applies artificial intelligence, computer vision, sensor technology, and communication technologies to achieve autonomous navigation, traffic planning, and safety control during vehicle operation and control. With advancements in hardware, software, and computing power, intelligent driving technology has made significant progress. In recent years, automakers have continuously advanced the automation and intelligence of their vehicles, and market acceptance of autonomous driving has continued to grow. Sales of vehicles with assisted or autonomous driving capabilities have grown rapidly. Together with electrification, automation has become a major force transforming the global automotive industry. Autonomous driving technology has gradually matured, with performance improving, costs decreasing, and market acceptance increasing, leading to rapid industry development.

[0005] With the increasing complexity of electronic and electrical systems and the emergence of autonomous driving features, there are numerous vehicle risks caused by inadequate triggering functions due to unknown scenario conditions during the design process. First, the new technologies of intelligent driving have not been extensively tested, and there is no guarantee that they are completely free of hidden dangers. Intelligent driving vehicles require complex decision-making, including speed, direction, and collision avoidance. However, the decision-making systems of intelligent driving vehicles may make errors, leading to safety issues. Secondly, some users may have concerns about the safety of intelligent driving technology, which may lead to a decrease in driver trust in the vehicle, indirectly affecting the driver's ability to control the vehicle and affecting driving safety. Therefore, it is particularly important to conduct reasonable safety monitoring of vehicles in autonomous driving. Currently, there are no comprehensive examples of the development of autonomous driving safety monitoring functions on the market.

[0006] Summary of the Invention

[0007] This application aims to solve, at least to some extent, one of the technical problems existing in the related art. To this end, this application proposes a safety monitoring method for intelligent driving, which can monitor the safety of autonomous driving and help improve the safety of autonomous driving.

[0008] This application also provides an intelligent driving safety monitoring system and a vehicle thereof.

[0009] The intelligent driving safety monitoring method according to the first aspect of the embodiment of the present application is applied to a vehicle with an intelligent driving function, and the safety monitoring method includes:

[0010] determining a status of the intelligent driving function;

[0011] When the intelligent driving function is activated and a safety risk behavior event is identified in the vehicle, the current operating data of the vehicle is uploaded to the cloud.

[0012] The intelligent driving safety monitoring method according to the embodiment of the present application has at least the following beneficial effects:

[0013] The safety monitoring method of the embodiment is applied to vehicles with intelligent driving functions. First, the status of the vehicle's intelligent driving function is judged to determine whether the intelligent driving function is in an activated state; when the intelligent driving function is in an activated state and a safety risk behavior event is identified in the vehicle, the vehicle's current operating data is uploaded to the cloud to facilitate the restoration, analysis and problem judgment of the problem scenario. For research and development, potential vehicle safety risk behavior events can be identified, a rapid analysis and response mechanism can be established, and product iteration and upgrading can be driven, which is conducive to improving the stability and safety of vehicle intelligent driving.

[0014] According to some embodiments of the present application, the vehicle includes an in-vehicle infotainment system, and the safety monitoring method further includes:

[0015] When the intelligent driving function is activated, the driver's operation is collected through the in-vehicle infotainment system;

[0016] When the in-vehicle infotainment system obtains the operation information of the driver's feedback of a safety risk behavior event, it is determined that a safety risk behavior event is identified in the vehicle.

[0017] According to some embodiments of the present application, the intelligent driving function includes an automatic driving function, and collecting the driver's operation through the in-vehicle infotainment system further includes:

[0018] Obtain the number of times drivers report safety risk behavior events;

[0019] When the in-vehicle infotainment system obtains the operation information of the driver's feedback on the safety risk behavior event, determining that the vehicle has identified the safety risk behavior event includes:

[0020] When the automatic driving function has been activated, operation information of the driver's feedback on a safety risk behavior event is obtained, and the number of operations is less than a preset number, it is determined that a safety risk behavior event has been identified for the vehicle.

[0021] According to some embodiments of the present application, the data includes partial bus data, sensory data, and audio and video data of the vehicle, and collecting the driver's operation through the in-vehicle infotainment system includes:

[0022] calling a data recording interface through the in-vehicle infotainment system to record and store the bus data, the perception data, and the audio and video data, and feeding back a data recording status;

[0023] The uploading of the current operating data of the vehicle to the cloud includes:

[0024] The bus data, the perception data, and the audio and video data are uploaded to the cloud and stored in a data lake.

[0025] According to some embodiments of the present application, the security monitoring method further includes:

[0026] collecting status data of the vehicle in real time, and determining whether the vehicle exceeds a functional safety boundary based on the status data;

[0027] When the vehicle has exceeded the functional safety boundary or there is a risk of exceeding the functional safety boundary, it is determined as the event of identifying that the vehicle has a safety risk behavior.

[0028] According to some embodiments of the present application, the vehicle includes an intelligent vehicle control platform control unit, and determining whether the vehicle exceeds a functional safety boundary based on the status data includes:

[0029] Comparing the state data with preset security boundary rules;

[0030] When the status data matches the safety boundary rule, it is determined that the vehicle has exceeded the functional safety boundary or is at risk of exceeding the functional safety boundary, and the intelligent vehicle control platform control unit is triggered to execute the uploading of the vehicle's current operating data to the cloud.

[0031] According to some embodiments of the present application, the vehicle includes an intelligent vehicle control platform control unit, and uploading the current operating data of the vehicle to the cloud includes:

[0032] Storing the operating data of the vehicle through the intelligent vehicle control platform control unit;

[0033] When the amount of data to be stored reaches a preset value, the data stored in the control unit of the intelligent vehicle control platform is controlled to be uploaded.

[0034] According to some embodiments of the present application, the vehicle further includes an advanced autonomous driving controller, the data includes partial bus data, perception data, and audio and video data of the vehicle, and the safety monitoring method further includes:

[0035] Acquiring the bus data, the perception data, and the audio and video data through the advanced autonomous driving controller;

[0036] The uploading of the current operating data of the vehicle to the cloud includes:

[0037] The bus data, the perception data, and the audio and video data are uploaded to the cloud and stored in a data lake.

[0038] According to the second aspect of the embodiment of the present application, the intelligent driving safety monitoring system is applied to a vehicle with an intelligent driving function, and the safety monitoring system includes:

[0039] a judgment module, configured to determine a state of the intelligent driving function;

[0040] The execution module is configured to upload the current operating data of the vehicle to the cloud when the intelligent driving function is activated and a safety risk behavior event is identified in the vehicle.

[0041] The intelligent driving safety monitoring system according to the embodiment of the present application has at least the following beneficial effects:

[0042] The intelligent driving safety monitoring system uses a judgment module to determine the status of the vehicle's intelligent driving function and whether the intelligent driving function is in an activated state; when the intelligent driving function is in an activated state and a safety risk behavior event is identified in the vehicle, the execution module uploads the vehicle's current operating data to the cloud, facilitating the restoration, analysis and problem judgment of the problem scenario. For R&D, it can identify potential vehicle safety risk behavior events, establish a rapid analysis and response mechanism, drive product iteration and upgrades, and help improve the stability and safety of vehicle intelligent driving.

[0043] The vehicle according to the third aspect of the embodiment of the present application includes the intelligent driving safety monitoring system described in the second aspect of the above embodiment.

[0044] Since the vehicle adopts all the technical solutions of the intelligent driving safety monitoring system of the above-mentioned embodiment, it has at least all the beneficial effects brought by the technical solutions of the above-mentioned embodiment, which will not be repeated here.

[0045] Other features and advantages of the present application will be set forth in the following description, and in part will be apparent from the description, or may be learned by practicing the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] FIG1 is a data flow diagram of the autonomous driving principle architecture according to an embodiment of the present application;

[0047] FIG2 is a flow chart of a safety monitoring method for intelligent driving according to an embodiment of the present application;

[0048] FIG3 is a flowchart of a manual uploading step in a security monitoring method according to an embodiment of the present application;

[0049] FIG4 is a flowchart of a specific example of manual uploading of a security monitoring method according to an embodiment of the present application;

[0050] FIG5 is a schematic diagram of data flow of a security monitoring method according to an embodiment of the present application;

[0051] FIG6 is a flowchart of the automatic uploading step in the security monitoring method according to an embodiment of the present application;

[0052] FIG7 is a flowchart showing a specific example of automatic uploading of a security monitoring method according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0054] In the description of this application, it should be understood that the terms upper, lower, etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on this application.

[0055] In the description of this application, "above," "below," and "within" are understood to be exclusive of the number indicated, while "above," "below," and "within" are understood to be inclusive of the number indicated. The use of "first" and "second" is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly specifying the number or order of the indicated technical features.

[0056] In the description of this application, it should be noted that terms such as setting, installing, and connecting should be understood in a broad sense, and technical personnel in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0057] The technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described below are only part of the embodiments of the present application, not all of the embodiments.

[0058] Autonomous driving, also known as unmanned driving, computer-driven driving, or wheeled mobile robots, is a cutting-edge technology that relies on computers and artificial intelligence to achieve complete, safe, and efficient driving without human intervention. The fundamental principle of intelligent driving is to use sensors to perceive the vehicle and its surroundings in real time, then use intelligent systems to make planning decisions, and finally, control systems to execute driving operations. Autonomous vehicles rely on three key aspects: perception, decision-making, and control.

[0059] The perception layer primarily provides the autonomous driving system with data about the external road environment and assists with vehicle positioning. Representative sensors in current autonomous driving systems include cameras, lidar, millimeter-wave radar, ultrasonic radar, and GNSS / IMU, suitable for diverse scenarios. Most vehicles currently utilize a fusion of multiple sensors to address various scenarios and ensure optimal practical performance.

[0060] The decision-making layer requires the autonomous driving chip to smoothly process this data to ensure the system makes timely and accurate decisions, controlling the vehicle's autonomous driving and ensuring safety. The control layer primarily relies on wire control. This replaces mechanical, hydraulic, or pneumatic connections with wires (electrical signals) to achieve electronic control, eliminating the need for driver input of force or torque.

[0061] Refer to Figure 1, which shows the data flow diagram of the entire architecture and the upstream and downstream dependencies of each module. Perception is upstream of prediction; perception, prediction, positioning, and mapping are upstream of planning; control is downstream of planning; and the human machine interface (HMI) is downstream of the entire system. Each module relies on high-precision maps, which play a crucial role.

[0062] It is understandable that autonomous driving ranges from Level 1 to Level 5, with the higher the level, the higher the degree of automation. The key to Level 1 assisted driving is to control only one of the vehicle's lateral or longitudinal operations. Level 2, on the other hand, controls multiple lateral and longitudinal operations simultaneously. Level 2 to Level 3 is a big leap. When the L3 function is turned on, the system is fully responsible for control and environmental monitoring. The driver can take their hands off the steering wheel. When the system identifies a situation that it cannot handle, it will issue an early alarm and ask the driver to take over. At Level 4, all operations are performed by the unmanned driving system. Depending on the system requirements, humans may not provide appropriate responses, and road and environmental conditions are limited. At Level 5, all operations are performed by the unmanned driving system. Depending on the system requirements, humans may not provide appropriate responses, and road and environmental conditions are not limited.

[0063] Taking Level 2 and Level 3 as examples, Level 2 autonomous driving includes Super Cruise, Auto Parking Assist (APA), Traffic Jam Assistant (TJA), and Highway Assist (HWA). Level 3 autonomous driving includes Highway Pilot (HWP), Traffic Jam Pilot (TJP), Navigate on Autopilot (NOA), and Navigate on Pilot (NOP).

[0064] Among them, the Super Cruise system is the superposition of Adaptive Cruise Control (ACC) and Lane Keeping Assist (LKA), which enables automatic following or constant speed driving in the current lane.

[0065] APA uses sensors and system model calculations to identify the parking location. It then controls the vehicle through steering, acceleration, and deceleration, automatically completing parking at a low speed along the system-calculated parking trajectory. During parking, the vehicle also detects the vehicle and surrounding obstacles in real time, adjusting the parking trajectory to avoid collisions.

[0066] TJA is an assistance system for traffic jams that allows the driver to relax and let the vehicle follow the car. Based on the strategy, TJA maintains lanes, automatically follows the car, and uses sensors to detect surrounding obstacles in real time and make fine adjustments to the vehicle's steering.

[0067] HWA includes automatic lane changes based on driver instructions (such as turning on the turn signal) and driver status monitoring. HWA uses sensors to determine whether a lane change is possible and, based on the driver's instructions, enables safe automatic lane changes.

[0068] HWP includes features such as cruise control, automatic passing of slower-moving vehicles, automatic lane changing, automatic on- and off-ramp entry and exit, and automatic vehicle following on highways covered by high-precision maps. HWP activates when specific conditions are met. Using comprehensive sensors, HWP identifies the vehicle and its surroundings, systematically plans and determines the driving trajectory, and automatically controls vehicle movement. Compared to HWP, TJP provides Level 3 autonomous driving in congested traffic scenarios.

[0069] NOA enables vehicles to automatically change lanes and enter and exit ramps when traveling on certain closed sections of highways or elevated highways, using the onboard navigation route. On elevated highways, the system uses high-precision satellite navigation for navigation and various onboard sensors to detect surrounding conditions, enabling autonomous lane changes, steering, acceleration and deceleration, and lighting. This reduces driver workload and helps drivers avoid risks. The essence of NOA is the integration of "navigation" and "assisted driving." Building on existing Level 2 assisted driving features (such as lane keeping and automatic following), NOA adds navigation information from the vehicle's computer (such as mapping software) to enable automated lane changes, enabling autonomous driving from point A to point B. NOP deeply integrates the navigation system and high-precision maps, enabling a degree of fully autonomous point-to-point driving. This includes: automatically merging onto the main road; intelligently selecting the optimal lane while cruising on the main road; automatically switching to the next highway / elevated highway according to navigation guidance; and automatically exiting the main road.

[0070] Despite the rapid development of autonomous driving technology, the maturing market demand, and the booming industry, autonomous driving still faces serious safety challenges. With the increasing complexity of electronic and electrical systems and the emergence of autonomous driving features, numerous vehicle risks arise from inadequate functionality triggered by unknown scenarios during the design process. Therefore, proper safety monitoring of autonomous vehicles is crucial.

[0071] An embodiment of the present application provides a safety monitoring method for intelligent driving. When the intelligent driving function is activated, it will identify safety risk behavior events based on the vehicle-side monitoring rules, and automatically upload relevant information to the cloud, so as to facilitate the restoration, analysis and judgment of problem scenarios. For research and development, it can identify potential vehicle safety risk behavior events and establish a rapid analysis and response mechanism, which is conducive to improving the stability and safety of vehicle intelligent driving.

[0072] 2 to 7 , a safety monitoring method for intelligent driving according to an embodiment of the present application is described, which is applied to a vehicle with an intelligent driving function. The safety monitoring method is illustrated below with a specific example.

[0073] 2 , the intelligent driving safety monitoring method according to an embodiment of the present application includes but is not limited to the following steps:

[0074] Step S100, determining the state of the intelligent driving function;

[0075] Step S200: When the intelligent driving function is activated and a safety risk behavior event is identified in the vehicle, the current operation data of the vehicle is uploaded to the cloud.

[0076] It can be understood that the safety monitoring method of the embodiment of the present application monitors the vehicle status, behavior, environmental conditions and personnel use in intelligent driving. The prerequisite is that the intelligent driving function is in an activated state. Therefore, it is necessary to first judge the working status of the vehicle's intelligent driving to determine whether the intelligent driving function is in an activated state. The intelligent driving function can also be understood as the vehicle's automatic driving function.

[0077] Specifically, the activation status of intelligent driving functions can be determined by acquiring signals from the vehicle's controller. For example, when the driver activates NOA, the autonomous driving function is activated. In some embodiments, the vehicle has a Highly Automated Driving (HAD) controller that has functions such as determining function activation, exit, override, takeover, emergency events, faults, and request records. The HAD can provide feedback on whether autonomous driving is enabled, thereby determining the activation status of the autonomous driving function.

[0078] In some examples, HAD uses Infineon's high-end Aurix series TC297 as the main chip. The software adopts a multi-core parallel architecture, with independent CPUs handling policy calculation and message routing, while leaving one core for safety calculations to improve functional safety coverage. HAD receives information from the CAN network, processes and calculates it, and then sends execution commands to the control end. HAD integrates information from cameras, radar, and RF sensors, and performs logical strategy calculations to direct the vehicle to perform lane keeping, automatic parking, adaptive cruise control, and active braking functions.

[0079] When the intelligent driving function is activated, the vehicle can implement the aforementioned autonomous driving functions. For example, in Level 2 autonomous driving mode, functions such as APA, ACC, and LKA can be implemented, and in Level 3 autonomous driving mode, functions such as TJP, NOA, and NOP can be implemented. It should be noted that if the intelligent driving function is not activated, the driver is in control of the vehicle's movement, and the aforementioned autonomous driving function does not intervene, and the safety monitoring method of the embodiment is not executed.

[0080] It can be understood that in the above step S200, when the automatic driving function is activated, the operating status of the automatic driving is monitored in real time, specifically the vehicle status, behavior, environmental conditions and personnel use are monitored. When a safety risk behavior event is identified in the vehicle during the monitoring process, the current operating data of the vehicle is uploaded to the cloud to store the above operating data through the cloud.

[0081] In one embodiment, safety risk behavior events include collision-related events, safety distance events, safety behavior events, traffic rule events, human misuse events, system failures, and abnormal events. For example, the identification of airbag collision signals, vehicle lateral and longitudinal acceleration, and vehicle malfunction information can be determined as safety risk behavior events. As can be understood from Figure 5 , when the vehicle-based monitoring mechanism identifies the presence of such safety risk behavior events during the autonomous driving process, the relevant operational data containing the triggering safety risk behavior events is uploaded to the cloud, specifically a cloud monitoring platform. Data upload can be performed through a telematics service provider (TSP). By analyzing the uploaded data, problem scenarios can be restored, analyzed, and identified, and emergency response mechanisms can be activated.

[0082] For example, in autonomous driving mode, HAD will integrate information from devices such as cameras, radars, and radio frequency sensors, and perform logical strategy calculations to direct the vehicle to perform lane keeping, automatic parking, adaptive cruise control, active braking and other functions. If improper following or unreasonable speed setting occurs during the adaptive cruise process, HAD will initiate information on the safety risk behavior event and record it to facilitate uploading of the recorded data to the cloud.

[0083] It can be understood that the safety monitoring method of the embodiment judges the status of the vehicle's intelligent driving function. When the intelligent driving function is in an activated state and a safety risk behavior event is identified in the vehicle, the vehicle's current operating data is uploaded to the cloud, thereby achieving the purpose of recording and storing safety risk behavior event data, facilitating the restoration, analysis and problem judgment of problem scenarios, and initiating emergency response mechanisms, which will have great benefits for R&D, customers, liability and insurance.

[0084] It should be noted that the security monitoring method in the embodiment of the present application is divided into two parts: manual uploading and automatic uploading, which are described below with specific examples.

[0085] 3 , in some embodiments, the specific steps of manually uploading in the security monitoring method include:

[0086] Step S210, when the intelligent driving function is activated, the driver's operation is collected through the in-vehicle infotainment system;

[0087] Step S220 : When the in-vehicle infotainment system obtains the driver's operational information regarding the safety risk behavior event, it is determined that a safety risk behavior event has been identified in the vehicle.

[0088] It's understood that vehicles include an in-vehicle infotainment (IVI) system. IVI utilizes a dedicated onboard central processing unit (CPU) and is based on a vehicle bus system and internet services, forming a comprehensive in-vehicle information processing system. IVI enables a range of applications, including 3D navigation, real-time traffic conditions, IPTV, assisted driving, fault detection, vehicle information, body control, mobile office, wireless communications, online entertainment, and TSP services, significantly enhancing the vehicle's electronic, networked, and intelligent capabilities. IVI integrates a variety of in-vehicle services, such as car phone, navigation, and music playback, and can be operated through voice commands and touch controls, greatly facilitating the driving experience for both drivers and passengers. It also supports online services, such as news, weather forecasts, and online shopping, allowing people to access external information at any time while in the vehicle. Furthermore, IVI can provide intelligent driving assistance features to help drivers better manage driving safety.

[0089] IVI has a central control screen that can collect the driver's operation information through touch. When the driver identifies that the autonomous driving function has a safety risk behavior event, the operation information of the safety risk behavior event is fed back through manual operation of IVI. This indicates that a safety risk behavior event has been identified in the autonomous driving function, which means that the potential vehicle accident risk can be identified.

[0090] Specifically, after the driver agrees to turn on the data collection function and activates the automatic driving function, the IVI will pop up a "Problem Feedback" button in the lower left corner of the central control screen. At this time, the automatic driving function will intervene. If the driver or co-driver believes that the vehicle's automatic driving intervention is inappropriate, they can click the "Problem Feedback" button to upload the relevant data to the cloud for the R&D team to conduct technical analysis, labeling and training. At the same time, it can also enhance user participation, reduce user complaints, and accurately resolve user doubts.

[0091] In some embodiments, step S220 of the security monitoring method further includes:

[0092] Step S221, obtaining the number of times the driver reports a safety risk behavior event;

[0093] Step S222: When the automatic driving function has been activated, the driver's feedback on the safety risk behavior event is obtained, and the number of operations is less than the preset number, it is determined that a safety risk behavior event has been identified in the vehicle.

[0094] It is understood that manual upload operations in the safety monitoring method are applicable only when the data recording function is not disabled, the autonomous driving function is activated, the number of operations does not exceed the preset limit, and the user believes that the autonomous driving function has intervened inappropriately. It should be noted that by increasing the limit on the number of operations, it is intended to prevent users from frequently uploading data and consuming data bandwidth. Specifically, the number of user uploads is limited to a reasonable range of 10-15 times per day.

[0095] It should be noted that participants who manually upload data can be users, including drivers and co-drivers, or the vehicle R&D team. Users can provide real-time feedback on vehicle autonomous driving issues, increasing user participation and ensuring that user feedback is accurately addressed.

[0096] 4 , the following is a specific example of a security monitoring method based on manual uploading, which includes the following steps:

[0097] Step S101: The user presses the "Problem Feedback" button;

[0098] Step S102, actively calling the data recording interface through IVI to record and store the operating data;

[0099] Step S103, issuing an indication of the vehicle's data recording status, including "data recording in progress", "data recording successful", and "data recording failed";

[0100] Step S104: The cloud actively pulls the recorded data and stores it in the data lake;

[0101] Step S105: The security monitoring cloud platform displays and replays the data;

[0102] In step S106, the R&D team obtains user feedback through the security monitoring cloud platform and performs problem analysis.

[0103] In conjunction with Figure 5, it can be understood that the data includes part of the vehicle's bus data, perception data, and audio and video data, wherein the perception data includes perception raw data and perception intermediate data, and the audio and video data includes recorded audio data and video data. If the driver or co-driver believes that the vehicle intervention is inappropriate, when clicking the "Problem Feedback" button, the above data will be recorded and uploaded. For example, when NOP intervenes, it will control the vehicle's driving. If there is an obstacle and there is no emergency avoidance, the driver controls it, but the driver feels that the NOP function is not good, he can click this button; for example, when NOP controls the vehicle to turn, the acceleration may not be set well, or the speed may be too fast or too slow, causing the driver to be nervous and uncomfortable, and the user can also click this button.

[0104] Since the "Manual Upload" function requires user consent for data collection, a corresponding "Data Collection" switch has been added to the system settings. If the "Data Collection" function status is on, the security monitoring function is enabled by default; if the "Data Collection" function status is off, the security monitoring function is disabled by default.

[0105] If the "manual upload" function can be turned on, the input is the on / off status of the automatic driving function, the pressing status of the "problem feedback" button on the IVI, and the number of operations of the "problem feedback" button on the IVI; when the automatic driving function is turned on, a "problem feedback" button pops up at a certain position of the IVI vehicle computer (lower left corner). When the user (driver or co-driver) thinks that the current automatic driving function is inappropriate, click the "problem feedback" button on the IVI; when data recording is successful, that is, when the IVI receives the successful return value of the data upload interface, the "problem feedback" button on the IVI displays the "data recording upload successful" status information and automatically returns to normal after 5 seconds; if data recording fails, that is, the interface returns timeout or the IVI receives the failure return value of the data upload interface, the "problem feedback" button on the IVI displays the "data recording failed" status information and automatically returns to normal after 5 seconds.

[0106] The following is a detailed description of the central control function, focusing on the soft switch setting interface related to the NOP function, the NOP function alarm and reminder, etc. Its function configuration soft switch settings include:

[0107] a) After the vehicle is started, the NOP function is in the off state by default. The central control should have a NOP function configuration switch setting interface to enable the NOP function to be turned on and off and related settings.

[0108] b) The function activation setting interface must have a text description and icon display of the corresponding function, and a corresponding toggle switch must be set to enable and disable the function.

[0109] c) When the central control detects that the current user ID has not been started through the NOP function, when the user operates the NOP function switch to turn it on, the NOP function must be kept off and the NOP function start interface will pop up.

[0110] d) The aforementioned NOP function and its sub-functions shall include the following: NOP function on and off; automatic lane change function on and off; autonomous driving style setting options, including aggressive, normal, and conservative styles; smart deviation function on and off; lever lane change function on and off; NOP voice prompt on and off; and other reserved functions.

[0111] e) Once the NOP function is activated, it cannot be exited via the NOP function switch. If the user presses the configuration switch while NOP is activated, the text next to the NOP configuration switch will read "NOP is activated, please exit and close" and the instrument will sound a warning (TBD). This function is only available for the NOP function main switch.

[0112] f) After the user turns on the NOP function switch, other switches in the central control settings that affect autonomous driving related functions (such as positioning, AEB, BSD, rearview mirror folding, suspension, driving mode, etc.) are automatically switched to the on state. If the user operates the switch to try to turn off the corresponding function when the NOP function is turned on / activated, the central control should give a text prompt "NOP function is turned on, please turn off NOP function first and then turn off this function", and the instrument should give a prompt sound.

[0113] 6 , in some embodiments, the specific steps of automatically uploading in the security monitoring method include:

[0114] Step S230: collecting vehicle status data in real time and determining whether the vehicle exceeds the functional safety boundary based on the status data;

[0115] In step S240 , when the vehicle has exceeded the functional safety boundary or is at risk of exceeding the functional safety boundary, it is determined that a safety risk behavior event of the vehicle has been identified.

[0116] While the user is driving, the safety monitoring function collects real-time vehicle status data and determines whether the vehicle has exceeded the functional safety boundary. If it detects that the vehicle has exceeded or is at risk of exceeding the functional safety boundary, the data recording and upload function is activated, uploading partial bus data, raw and intermediate sensor data, and audio and video data to the cloud. This function can identify potential vehicle accident risks.

[0117] It should be noted that the functional safety boundary can be understood as the triggering of safety risk behavior events including the aforementioned safety risk behavior events by the autonomous driving function. The vehicle's monitoring mechanism is able to identify safety risk behavior events that occur during the autonomous driving process. For example, since HAD has the functions of function activation, exit, override, takeover, emergency event, fault and request recording, HAD can accurately determine whether the vehicle exceeds the functional safety boundary through the vehicle's real-time status data and trigger data recording by HAD. In addition, the risk of exceeding the functional safety boundary can be understood as the vehicle's operating state is close to or has triggered a safety risk behavior event. Specifically, the operating data can be analyzed based on HAD to determine whether the corresponding parameters exceed the threshold.

[0118] It is understandable that the safety monitoring method, in automatic uploading mode, uploads relevant operating data to the cloud after identifying a safety risk behavior event in the vehicle.

[0119] The safety monitoring function of the embodiment of the present application will monitor the vehicle status, behavior, environmental conditions and personnel use, identify functional behavior risks based on the vehicle-side monitoring mechanism, and automatically or manually upload relevant information to the cloud monitoring platform to achieve restoration, analysis and judgment of problem scenarios, and activate emergency response mechanisms, which will have great benefits for R&D, customers, liability and insurance.

[0120] For R&D, it can identify potential vehicle safety risk behavior events, establish a rapid analysis and response mechanism, drive product iteration and upgrades, and continuously enhance product safety and stability; it can accumulate scenario data to support forward development and continuous improvement of safety; it can save companies huge testing and verification costs and effectively deal with the long-tail effect.

[0121] For customers, it allows them to manually report problems, accurately resolve customer queries, reduce online complaints, and improve product satisfaction and image; it can also monitor accidents and proactively care for customers at the first opportunity.

[0122] For liability and insurance, it can realistically restore the accident scene and clarify the responsibilities of all parties; based on the above-mentioned safety monitoring methods and subsequent data analysis, it can also support the determination of vehicle insurance premiums and define innovative vehicle insurance policies.

[0123] In some embodiments, in step S230, determining whether the vehicle exceeds the functional safety boundary based on the status data specifically includes:

[0124] Step S231, comparing the status data with the preset security boundary rules;

[0125] In step S232, when the status data matches the safety boundary rule, it is determined that the vehicle has exceeded the functional safety boundary or there is a risk of exceeding the functional safety boundary, and the intelligent vehicle control platform control unit is triggered to upload the vehicle's current operating data to the cloud.

[0126] In some embodiments, the vehicle features an intelligent vehicle domain computer (VDC). The VDC collects driver control information, vehicle driving information, engine, motor, battery, transmission data, and feedback from various subsystems. After calculation, it sends control commands to each subsystem, thereby enabling VDC control of the entire vehicle. The VDC, with the electronic control unit (VCU) at its core, directs key assembly components, such as the energy storage system and motor system, via the CAN bus to execute corresponding power-up and power-down actions and torque commands, ultimately completing vehicle operation. The VDC's strategy is to combine the motor, battery, and engine to drive the vehicle under different operating conditions for optimal efficiency.

[0127] It should be noted that VDC has a trigger and an automatic upload function. This function collects vehicle information, such as the collision signal of the airbag, the vehicle's lateral and longitudinal acceleration, vehicle fault information, etc., and then enters the matching library of the safety boundary rules to determine whether the vehicle violates the defined safety boundary rules through comparison; for example, if the vehicle collides, the rule is triggered. At this time, the trigger of the vehicle's VDC recognizes the event and then uploads the entire vehicle data 15 seconds before and after this moment to the cloud backend; specific examples of safety boundary rules are, which can be kinematics-related, for example, the vehicle's lateral acceleration exceeds 0.13g and lasts for 200ms; or it can be fault-related, for example, a serious fault in the steering system, etc.

[0128] It should be noted that the data recorded in the automatic upload process of the autonomous driving function includes some necessary bus data, perception raw / intermediate data and audio and video data. In some embodiments, the above data is stored in the VDC. When the cumulative amount of data to be stored reaches a preset value, the big data team triggers the "data upload" interface to upload the relevant data to the cloud backend and store it in the data lake; the security monitoring cloud platform pulls data from the data lake for display, and supports data download, data-based scene restoration, video playback restoration and download and other functions; R&D engineers analyze and solve problems based on the data of the security monitoring platform, actively iterate and upgrade, and improve product performance and user experience.

[0129] When a safety risk behavior event is identified, the data is not uploaded immediately. Instead, it is uploaded together after the accumulated data volume reaches a preset value. The purpose is to maximize the conservation of data resources such as data traffic. Since automatic upload does not have a strict timeliness requirement, it can be uploaded using the above method. Manual upload, on the other hand, is manually uploaded by the user, and the autonomous driving data can be analyzed by analyzing the driving situation at the time of upload. This process has a strong timeliness requirement, so it needs to be uploaded in real time.

[0130] 7 , the process of the security monitoring method based on automatic uploading is described in detail below with a specific example, which specifically includes the following steps:

[0131] Step S201: The IVI actively identifies and records security risk behavior events based on the vehicle-side monitoring component;

[0132] Step S202: The cloud actively pulls the recorded data and stores it in the data lake;

[0133] Step S203: The security monitoring cloud platform displays and replays the data;

[0134] In step S204, the R&D team obtains automatic monitoring data through the security monitoring cloud platform and performs problem analysis.

[0135] Among them, the vehicle-side monitoring component can be an advanced autonomous driving controller or other autonomous driving control systems. It should be noted that since the HAD initiation record cannot cover the HAD's own failure scenario, if it is the HAD's own failure scenario, it needs to be initiated by the VDC / gateway.

[0136] As can be understood, the safety monitoring method of the present embodiment combines the aforementioned manual and automatic upload functions to monitor vehicle status, functional behavior, environmental conditions, and user usage on the vehicle side. It then identifies safety risk behavior events based on vehicle-side monitoring rules and automatically uploads the relevant data to the cloud. Alternatively, the vehicle side can collect user problem data for reporting purposes, manually uploading the relevant data to the cloud upon receiving user problem feedback signals.

[0137] The cloud is responsible for implementing functions such as data storage, scheduling, restoration of problem scenarios, restoration of video playback, and data download. By continuously collecting and analyzing large amounts of data generated during the driving process and related data that users believe are unreasonable for autonomous driving intervention, the cloud can continuously optimize the autonomous driving algorithm to make it more accurate and stable. In addition, the manual monitoring and automatic monitoring methods used in this application can also be extended to models with intelligent driving functions. While meeting relevant laws and regulations, it also greatly enhances the safety of intelligent driving. It has strong adaptability and portability, and the core logic can be reused, which greatly reduces the development cost of subsequent similar safety monitoring functions. Therefore, the safety monitoring method used in intelligent driving used in the embodiment of this application has certain promotion and versatility for subsequent autonomous driving vehicles.

[0138] As can be seen from Figure 5, safety engineers analyze issues based on data from the security monitoring platform and evaluate the collected data to determine whether the risk is still reasonable. If necessary, they activate emergency response mechanisms and, in the short term, implement OTA upgrades to partially or completely suppress functions to avoid significant loss of life, property, and corporate reputation. In the long term, they add new Safety of the Intended Functionality (SOTIF) measures and upgrade the system to enhance product safety, meet regulatory requirements, and improve the user experience.

[0139] Intended functional safety refers to an approach that ensures the proper functioning of electrical and electronic systems by effectively identifying and evaluating triggering events for algorithms, sensors, or actuators. It aims to eliminate unreasonable risks posed by hazards arising from abnormal behavior of electrical and electronic systems and ensure that vehicles can achieve a certifiable functional safety state in complex environments shared with other older vehicles that may have less or no automation. It also considers factors such as system or component performance limitations and foreseeable misuse.

[0140] An embodiment of the present application also provides a safety monitoring system for intelligent driving, which can execute the safety monitoring method for intelligent driving provided in the above embodiment. Specifically, the safety monitoring system for intelligent driving includes a judgment module and an execution module.

[0141] Among them, the judgment module is used to determine the status of the intelligent driving function; the execution module is used to upload the vehicle's current operating data to the cloud when the intelligent driving function is activated and a safety risk behavior event is identified in the vehicle.

[0142] As shown in Figure 2, the safety monitoring system of this embodiment monitors vehicle status, behavior, environmental conditions, and human use during intelligent driving. First, a judgment module acquires vehicle operating data and uses this data to determine whether the vehicle's intelligent driving function is active. If a vehicle safety risk behavior event is identified during the monitoring process, the execution module uploads the vehicle's current operating data to the cloud. This uploaded data is analyzed to restore, analyze, and determine the problematic scenario, and initiate emergency response mechanisms.

[0143] It should be noted that the intelligent driving safety monitoring system of the embodiment of the present application has a processor and a memory, and the memory is used to store instructions. When the instructions are executed by the processor, the intelligent driving safety monitoring method of the above embodiment is executed.

[0144] Take the example of a processor and memory in a safety monitoring system for intelligent driving that can be connected via a bus. Memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk memory, a flash memory device, or other non-transient solid-state memory device. In some embodiments, the memory includes a memory remotely located relative to the control processor, and these remote memories may be connected to the controller via a network.

[0145] The non-transient software programs and instructions required to implement the security monitoring method of the above embodiment are stored in the memory. When executed by the processor, the security monitoring method of the above embodiment is executed, for example, the method steps S100 to S300 in Figure 1, the method steps S110 to S311 in Figure 3, the method steps S120 to S312 in Figure 4, etc. described above are executed.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0147] The present application also provides a vehicle comprising the intelligent driving safety monitoring system of the above-described embodiment. The vehicle can be a private vehicle, such as a sedan, SUV, MPV, or pickup truck. The vehicle can also be a commercial vehicle, such as a van, bus, small truck, or large trailer. The vehicle can be a gasoline vehicle or a new energy vehicle. When the vehicle is a new energy vehicle, it can be a hybrid vehicle or a pure electric vehicle.

[0148] The vehicle uses an intelligent driving safety monitoring system to execute safety monitoring methods. When the vehicle identifies a safety risk behavior event, the vehicle's current operating data is uploaded to the cloud through the execution module, facilitating the restoration, analysis, and judgment of the problem scenario. For R&D, it can identify potential vehicle safety risk behavior events, establish a rapid analysis and response mechanism, drive product iteration and upgrades, and help improve the stability and safety of vehicle intelligent driving.

[0149] Since the vehicle adopts all the technical solutions of the intelligent driving safety monitoring system of the above-mentioned embodiment, it has at least all the beneficial effects brought by the technical solutions of the above-mentioned embodiment, which will not be repeated here.

[0150] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the knowledge of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A safety monitoring method for intelligent driving, which is applied to a vehicle with intelligent driving function. The safety monitoring method includes: Determine the state of the intelligent driving function; When the intelligent driving function is in an activated state and a safety risk behavior event of the vehicle is recognized, upload the current operation data of the vehicle to the cloud.

2. The safety monitoring method for intelligent driving according to claim 1, wherein, The vehicle includes an in-vehicle infotainment system. The safety monitoring method further includes: When activating the intelligent driving function, collect the driver's operations through the in-vehicle infotainment system; When the in-vehicle infotainment system obtains the operation information of the driver's feedback on the safety risk behavior event, it is determined that the vehicle has a safety risk behavior event.

3. The safety monitoring method for intelligent driving according to claim 2, wherein, The intelligent driving function includes an autonomous driving function. The collection of the driver's operations through the in-vehicle infotainment system further includes: Obtain the number of operations of the driver's feedback on the safety risk behavior event; The step of when the in-vehicle infotainment system obtains the operation information of the driver's feedback on the safety risk behavior event and determines that the vehicle has a safety risk behavior event includes: When the autonomous driving function is activated, the operation information of the driver's feedback on the safety risk behavior event is obtained, and the number of operations is less than the preset number, it is determined that the vehicle has a safety risk behavior event.

4. The safety monitoring method for intelligent driving according to claim 2, wherein, The data includes partial bus data, perception data, and audio-video data of the vehicle. The collection of the driver's operations through the in-vehicle infotainment system includes: Call the data recording interface through the in-vehicle infotainment system to record and store the bus data, the perception data, and the audio-video data, and feedback the data recording status; The step of uploading the current operation data of the vehicle to the cloud includes: Upload the bus data, the perception data, and the audio-video data to the cloud and store them in the data lake.

5. The safety monitoring method for intelligent driving according to claim 1 further includes: Real-time collect the state data of the vehicle and judge whether the vehicle exceeds the functional safety boundary according to the state data; When the vehicle has exceeded the functional safety boundary or there is a risk of exceeding the functional safety boundary, it is determined that the vehicle has a safety risk behavior event.

6. The safety monitoring method for intelligent driving according to claim 5, wherein, The vehicle includes an intelligent vehicle control platform control unit. The judgment of whether the vehicle exceeds the functional safety boundary according to the state data includes: Compare the state data with the preset safety boundary rules; When the state data matches the safety boundary rules, it is determined that the vehicle has exceeded the functional safety boundary or there is a risk of exceeding the functional safety boundary, and trigger the intelligent vehicle control platform control unit to execute the upload of the current operation data of the vehicle to the cloud.

7. The safety monitoring method for intelligent driving according to claim 6, wherein, The vehicle includes an intelligent vehicle control platform control unit. The step of uploading the current operation data of the vehicle to the cloud includes: Store the operation data of the vehicle through the intelligent vehicle control platform control unit; When the accumulated amount of data to be stored reaches the preset value, control the upload of the data stored by the intelligent vehicle control platform control unit.

8. The safety monitoring method for intelligent driving according to any one of claims 5 to 7, wherein, The vehicle further includes an advanced autonomous driving controller, and the data includes partial bus data, perception data, and audio-visual data of the vehicle. The safety monitoring method further includes: Obtaining the bus data, the perception data, and the audio-visual data through the advanced autonomous driving controller; The uploading the current operation data of the vehicle to the cloud includes: Uploading the bus data, the perception data, and the audio-visual data to the cloud and storing them in a data lake.

9. A safety monitoring system for intelligent driving, which is applied to a vehicle with intelligent driving function. The safety monitoring system includes: A judgment module configured to determine the state of the intelligent driving function; An execution module configured to upload the current operation data of the vehicle to the cloud when the intelligent driving function is in an activated state and a safety risk behavior event of the vehicle is identified.

10. A vehicle includes the safety monitoring system for intelligent driving according to claim 9.

Images