Intelligent driving system control method and device, storage medium and electronic equipment

Abstract

The invention relates to the technical field of vehicles, and discloses an intelligent driving system control method and device, a storage medium and electronic equipment. The method comprises the following steps: screening invalid vehicle and road cloud data at least according to roadside sensing data, vehicle end sensing data, cloud acquisition data, sensing environment information, roadside equipment operation data, vehicle end equipment operation data and cloud delay information; calculating a current vehicle operation influence index and a future vehicle operation influence index at least according to the invalid vehicle and road cloud data, the current vehicle operation scene and the vehicle operation scene in a future preset time period; and executing vehicle gradient arbitration and function degradation operation based on the current vehicle operation influence index and the future vehicle operation influence index so as to realize seamless switching among a plurality of vehicle intelligent driving grades. The problems that switching of the intelligent driving function of the vehicle is lagged, misjudgment is prone to occurring, and repeated switching exists can be solved at least, and the safety, reliability and robustness of vehicle control can be improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, device, storage medium, and electronic device for controlling an intelligent driving system. Background Technology

[0002] Vehicle-road-cloud integrated driving assistance functions can integrate vehicle, road, and cloud elements through next-generation information and communication technologies. Based on system-wide collaborative perception, decision-making, and control, it can achieve safe, efficient, energy-saving, and comfortable operation of intelligent connected vehicles and transportation systems.

[0003] Current methods for switching, arbitrating, and downgrading intelligent driving functions in vehicle-road-cloud systems mostly focus on the vehicle-side system. The core issues include at least the following:

[0004] 1. Vehicle-side limitations: Relying on the local perception of on-board sensors, it is unable to obtain global information from the roadside or cloud, resulting in delayed function switching or misjudgment;

[0005] 2. Simple arbitration mechanisms: mostly based on fixed priorities (such as safety over comfort) or single fault detection (such as sensor failure), lacking multi-dimensional arbitration based on dynamic scene perception;

[0006] 3. The degradation strategy is simple: it only supports "full function degradation to manual takeover" or "partial function shutdown", and the function entry and exit are repeatedly executed. It does not combine vehicle-road-cloud collaboration with gradient degradation. Summary of the Invention

[0007] The purpose of this invention is to provide a control method, device, storage medium, and electronic device for an intelligent driving system, which at least solves problems such as delayed switching of intelligent driving functions, easy misjudgment, and repeated switching, thereby improving the safety, reliability, and robustness of vehicle control.

[0008] To address the aforementioned technical problems, in a first aspect, the present invention provides an intelligent driving system control method, comprising at least:

[0009] Failed vehicle-road-cloud data should be filtered based on at least the following: roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information.

[0010] The current vehicle operation impact index and the future vehicle operation impact index are calculated based at least on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period.

[0011] Based on the current vehicle operation impact index and the future vehicle operation impact index, vehicle gradient arbitration and function downgrade operations are performed to achieve seamless switching between multiple vehicle intelligent driving levels.

[0012] Optionally, before filtering out invalid vehicle-road-cloud data based at least on roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information, the method further includes at least:

[0013] The roadside sensing data and the roadside equipment operation data are acquired through the roadside unit;

[0014] The vehicle-side sensing module is used to acquire the vehicle-side perception data, and the vehicle-side device operation data is acquired at least based on the vehicle-mounted central control unit;

[0015] The cloud is invoked to obtain the cloud-collected data and the cloud latency information.

[0016] Optionally, the step of filtering out invalid vehicle-road-cloud data based at least on roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information includes at least:

[0017] At least based on the roadside equipment operation data, the sensing environment information, and each roadside sensing data point, a corresponding roadside data score is calculated.

[0018] At least the corresponding vehicle data score is calculated based on the vehicle-side device operation data, the perceived environment information, and each of the vehicle-side perception data.

[0019] At least based on the cloud latency information and each of the cloud-collected data, calculate the corresponding cloud data score;

[0020] Based on each of the roadside data scores, each of the vehicle-side data scores, and each of the cloud-based data scores, the failed vehicle-road-cloud data is selected from the dataset composed of the roadside perception data, the vehicle-side perception data, and the cloud-based collected data.

[0021] Optionally, the current vehicle operation scenario is determined at least based on the roadside perception data, the vehicle-side perception data, and the cloud-collected data at the current moment;

[0022] The vehicle operation scenario within the future preset time period is determined at least based on the roadside perception data, the vehicle-side perception data, and the cloud-collected data within the future preset time period.

[0023] The vehicle operation scenario includes at least the type of road the vehicle travels on, the actions the vehicle performs, the weather type, and the number and location of intersections the vehicle passes through.

[0024] Optionally, the step of calculating the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period includes at least:

[0025] The current vehicle operation impact index shall be calculated based at least on the failed vehicle-road cloud data and the current vehicle operation scenario.

[0026] The future vehicle operation impact index is calculated based at least on the failed vehicle-road cloud data and the vehicle operation scenarios within the preset future time period.

[0027] Optionally, the step of performing vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index to achieve seamless switching between multiple vehicle intelligent driving levels includes at least:

[0028] Determine whether the current vehicle operation impact index is greater than a first index threshold, and whether the future vehicle operation impact index is greater than a second index threshold;

[0029] When the current vehicle operation impact index is not greater than the first index threshold and the future vehicle operation impact index is not greater than the second index threshold, it is determined that the vehicle meets the full-function operation requirements and the vehicle is controlled to perform full-function operation.

[0030] When the current vehicle operation impact index is greater than the first index threshold, it is determined that the vehicle meets the first degraded operation requirement, the vehicle is controlled to perform degraded operation, and the user is reminded to take over the vehicle.

[0031] When the current vehicle operation impact index is not greater than the first index threshold, but the future vehicle operation impact index is greater than the second index threshold, it is determined that the vehicle meets the second downgraded operation requirement, and the vehicle is controlled to perform downgraded operation for at least the future preset time period and the user is reminded to take over the vehicle.

[0032] After notifying the user to take over the vehicle, determine whether the vehicle has been taken over by the user;

[0033] The intelligent driving function is deactivated when the vehicle is taken over by the user.

[0034] Optionally, after determining whether the vehicle has been taken over by the user after reminding the user to take over the vehicle, the method further includes at least:

[0035] When the vehicle is not under user control, the system controls the vehicle to perform minimum-risk operations until the vehicle reaches a preset safety state and the intelligent driving function is deactivated.

[0036] Based on the same concept, in a second aspect, the present invention also provides an intelligent driving system control device for executing the intelligent driving system control method described in any one of the first aspects;

[0037] The intelligent driving system control device includes at least:

[0038] The data filtering module is used to filter out invalid vehicle-road-cloud data based on at least roadside sensing data, vehicle-side sensing data, cloud-collected data, sensing environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information.

[0039] The index calculation module is at least used to calculate the current vehicle operation impact index and the future vehicle operation impact index based on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period.

[0040] The operation execution module is used to perform vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index, so as to achieve seamless switching between multiple vehicle intelligent driving levels.

[0041] Based on the same concept, in a third aspect, the present invention also provides an electronic device, including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the program to implement the steps of the intelligent driving system control method of any one of the first aspects.

[0042] Based on the same concept, in a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the intelligent driving system control method according to any one of the first aspects.

[0043] The technical solution provided by this invention firstly filters out failed vehicle-road-cloud data based at least on roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information. Further, it calculates the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road-cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period. Finally, it performs vehicle gradient arbitration and function degradation operations based on the current and future vehicle operation impact indices to achieve seamless switching between multiple vehicle intelligent driving levels. Therefore, this invention can design an efficient, reliable, and secure intelligent driving system control and degradation arbitration mechanism in a complex cross-domain system that integrates multi-source heterogeneous perception information from vehicles, roadside, and the cloud. This addresses issues such as delayed intelligent driving function switching, susceptibility to misjudgment, and repeated switching, thereby improving the safety, reliability, and robustness of vehicle control. Attached Figure Description

[0044] Figure 1 This is a flowchart of an intelligent driving system control method provided in an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of the structure of an intelligent driving system control device provided in an embodiment of the present invention;

[0046] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0049] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0050] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0051] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0053] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0054] Figure 1 This is a flowchart of an intelligent driving system control method provided by an embodiment of the present invention. This embodiment is at least applicable to vehicle control scenarios such as intelligent connected vehicles with autonomous driving capabilities and vehicle-to-infrastructure and / or vehicle-to-cloud connectivity, connected vehicles without autonomous driving capabilities but with vehicle-to-infrastructure and / or vehicle-to-cloud connectivity, and non-connected vehicles. This intelligent driving system control method can be, but is not limited to, executed by the intelligent driving system control device in this embodiment of the present invention as the execution subject, and this execution subject can be implemented in software and / or hardware. Figure 1 As shown, the intelligent driving system control method includes at least the following steps:

[0055] S1. At least based on roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information, filter out invalid vehicle-road-cloud data.

[0056] Among them, roadside perception data can refer to perception information identified by roadside radar and cameras, as well as traffic light information; vehicle-side perception data can refer to data perceived through vehicle-mounted cameras, LiDAR, millimeter-wave radar, etc.; cloud-collected data can refer to traffic situation information, real-time weather information, dynamically adjusted global path information, as well as map and location information, etc.; perception environment information can be used to characterize the actual environmental conditions of vehicle operation, such as whether there is congestion or rain; roadside equipment operation data can refer to the actual working time and service life of the aforementioned roadside radar and cameras; vehicle-side equipment operation data can refer to the actual working time and service life of the aforementioned vehicle-mounted cameras, LiDAR, millimeter-wave radar, etc.; cloud latency information can refer to the quality of vehicle-to-cloud data communication and data latency time, etc.

[0057] Based on this, in one specific implementation, optionally, before the aforementioned step S1, at least the following step is included:

[0058] (0-1) Obtain roadside sensing data and roadside equipment operation data through roadside units;

[0059] (0-2) Obtain vehicle-side perception data using vehicle-side sensing modules and at least obtain vehicle-side equipment operation data based on the vehicle-mounted central control unit;

[0060] (0-3) Call the cloud to obtain cloud-collected data and cloud delay information.

[0061] In another specific implementation, optionally, the aforementioned step S1 includes at least:

[0062] (1-1) At least the roadside data score should be calculated based on the roadside equipment operation data, the perceived environment information, and each roadside perception data.

[0063] (1-2) Calculate the corresponding vehicle-side data score based at least on the vehicle-side equipment operation data, the sensing environment information, and each vehicle-side sensing data;

[0064] (1-3) Calculate the corresponding cloud data score based at least on the cloud latency information and each cloud-collected data;

[0065] (1-4) Based on the scores of each roadside data, each vehicle-side data, and each cloud-based data, the failed vehicle-road-cloud data are selected from the dataset composed of roadside perception data, vehicle-side perception data, and cloud-based data.

[0066] Taking roadside data scoring as an example, the roadside data score for any roadside sensing data can be calculated in at least the following ways:

[0067] S = αA * βB * (1 / γC);

[0068] In the formula, S represents the roadside data score; α represents the perception data error weight; A represents the roadside perception data; β represents the perception environment weight; B represents the perception environment information; γ represents the operating span weight; and C represents the roadside equipment operating data. It is understood that the above weights can be determined at least through a table lookup. Furthermore, the calculation methods for vehicle-side data scores and cloud-based data scores are similar to those for roadside data scores, and will not be elaborated further.

[0069] It is known that the failed vehicle-road cloud data may include roadside perception data with a roadside data score lower than a first score threshold, and / or vehicle-side perception data with a vehicle-side data score lower than a second score threshold, and / or cloud-based data collected data with a cloud-based data score lower than a third score threshold.

[0070] S2. Calculate the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period.

[0071] The preset time period can be 1 minute, 5 minutes, etc.

[0072] In yet another specific implementation, the current vehicle operation scenario can be determined at least based on roadside perception data, vehicle-side perception data, and cloud-collected data at the current moment.

[0073] The vehicle operation scenario within the future preset time period can be determined based on roadside perception data, vehicle-side perception data, and cloud-collected data within the future preset time period.

[0074] The vehicle operation scenario includes at least the type of road the vehicle travels on, the actions the vehicle performs, the weather type, and the number and location of intersections the vehicle passes through.

[0075] In yet another specific implementation, step S2 may optionally include at least:

[0076] (2-1) The current vehicle operation impact index shall be calculated based at least on the failed vehicle-road cloud data and the current vehicle operation scenario (of course, in another specific implementation, the current vehicle operation impact index may be calculated based at least on the failed vehicle-road cloud data, the non-failed vehicle-road cloud data and the current vehicle operation scenario).

[0077] (2-2) Calculate the future vehicle operation impact index based at least on the failed vehicle-road cloud data and the vehicle operation scenarios within the future preset time period (of course, in another specific implementation, the future vehicle operation impact index can be calculated based at least on the failed vehicle-road cloud data, the non-failed vehicle-road cloud data and the vehicle operation scenarios within the future preset time period).

[0078] The above vehicle operation impact index can be calculated at least by looking up a table.

[0079] More specifically, by receiving location information, map information, global path planning information from the cloud, traffic situation information, weather condition information, and perception data information fused from multiple sources, the system can determine the actual environment in which the vehicle is operating at present and at a certain point in the future. It can then output the environment in which the vehicle will operate and the actions it will perform at present and for a certain distance or time in the future. These actions include, but are not limited to: the type of road currently being traveled (such as highways, urban roads, etc.), the actions the vehicle will perform in the future (such as going straight, changing lanes, turning, etc.), and whether there is an intersection ahead (i.e., corresponding straight road, ramp, etc.).

[0080] Furthermore, if a malfunction is detected in the vehicle's forward-facing LiDAR, but the forward-facing camera and millimeter-wave radar are functioning normally, the system can use data fusion from the forward-facing camera and millimeter-wave radar to output the perceived target. Based on location and map information, it can be determined that the vehicle is currently traveling on a highway. Analysis of the current operating scenario shows that the LiDAR malfunction has no impact on highway driving (this can be interpreted as the current vehicle's impact index being less than a certain threshold). LiDAR is primarily used for identifying small or irregularly shaped obstacles such as cones and guardrails on urban roads, situations rarely encountered on highways. Therefore, the system will not experience a failure or degradation and will continue to operate with full functionality. However, in the same abnormal situation, if the operating scenario is on urban roads and occurs during the vehicle's future travel period (this can be interpreted as the future vehicle's impact index being greater than a certain threshold), a LiDAR malfunction might lead to the inability to detect irregularly shaped obstacles on the road, resulting in a collision hazard. In this case, the LiDAR malfunction should be classified as a system failure, reminding the driver to remain attentive and ready to take over the vehicle at any time.

[0081] S3. Based on the current vehicle operation impact index and the future vehicle operation impact index, perform vehicle gradient arbitration and function downgrade operations to achieve seamless switching between multiple vehicle intelligent driving levels.

[0082] The vehicle's intelligent driving level can include full-function operation level, downgraded operation level, minimum risk operation level, and function exit level.

[0083] In yet another specific implementation, step S3 may optionally include at least:

[0084] (3-1) Determine whether the current vehicle operation impact index is greater than the first index threshold and whether the future vehicle operation impact index is greater than the second index threshold;

[0085] (3-2) When the current vehicle operation impact index is not greater than the first index threshold and the future vehicle operation impact index is not greater than the second index threshold, determine that the vehicle meets the full-function operation requirements and control the vehicle to perform full-function operation.

[0086] (3-3) When the current vehicle operation impact index is greater than the first index threshold, determine that the vehicle meets the first downgrade operation requirements, control the vehicle to perform downgrade operation, and remind the user to take over the vehicle;

[0087] (3-4) When the current vehicle operation impact index is not greater than the first index threshold, but the future vehicle operation impact index is greater than the second index threshold, determine that the vehicle meets the second downgrade operation requirement, control the vehicle to perform downgrade operation for at least the future preset period, and remind the user to take over the vehicle;

[0088] (3-5) After notifying the user to take over the vehicle, determine whether the vehicle has been taken over by the user;

[0089] (3-6) When the vehicle is taken over by the user, the intelligent driving function is deactivated.

[0090] In yet another specific implementation, step S3 may optionally include at least:

[0091] (3-7) When the vehicle is not taken over by the user, control the vehicle to perform the minimum risk operation until the vehicle reaches the preset safety state and the intelligent driving function is deactivated.

[0092] As can be seen, the threshold values ​​of each of the above indices can be configured according to the actual adaptability of the vehicle.

[0093] Specifically, the system can dynamically determine whether a current data failure affects normal vehicle operation by receiving the target data reliability flag after multi-source data fusion processing, the fault status of various sensors (roadside and vehicle-side), the current actual vehicle operating scenario, and the actions the vehicle will perform in the future. This is achieved through methods such as applying fixed conditions and directly degrading or shutting down the system without considering the current scenario. In other words, if a sensor or certain sensing data exhibits an abnormal state, the system can analyze whether this abnormal state affects the normal operation of the vehicle in the current and / or future scenarios based on the current vehicle operating scenario and the actions to be performed in the future. If it affects vehicle operation, the system further determines what safety measures to take, such as degrading operation, triggering a takeover alert, or implementing a minimum risk strategy. If the current anomaly does not affect the vehicle's operation in the current scenario or the normal operation of future actions, no degrading or takeover strategies will be adopted, and the system will continue to operate with full functionality. Clearly, this configuration effectively solves the problem that certain fault conditions can easily lead to frequent system function degradation or shutdown when the failure does not affect the normal operation of the vehicle, thus improving the user's subjective driving experience.

[0094] The technical solution provided in this embodiment firstly filters out failed vehicle-road-cloud data based at least on roadside perception data, vehicle-side perception data, cloud-collected data, perceived environmental information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information. Further, it calculates the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road-cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period. Finally, it performs vehicle gradient arbitration and function degradation operations based on the current and future vehicle operation impact indices to achieve seamless switching between multiple vehicle intelligent driving levels. Therefore, this embodiment can design an efficient, reliable, and secure intelligent driving system control and degradation arbitration mechanism in a complex cross-domain system that integrates multi-source heterogeneous perception information from vehicles, roadside, and the cloud. This addresses issues such as delayed intelligent driving function switching, susceptibility to misjudgment, and repeated switching, thereby improving the safety, reliability, and robustness of vehicle control.

[0095] It should be noted that the solutions of the embodiments or implementation methods of this application can be optimized in at least the following ways:

[0096] 1. Dynamic Arbitration of Multi-Source Data: Confidence levels are assigned to data from vehicle-side, roadside, and cloud-side sources, with different confidence levels applied based on different scenarios. For example: When vehicle-to-cloud data communication quality is poor and data latency is long, the confidence level of cloud-side data is adjusted to low, while the confidence level of vehicle-side data is adjusted to high; when the traffic light information perceived by the vehicle-side is inconsistent with the traffic light information provided by roadside equipment, roadside data uses high confidence, while vehicle-side data uses low confidence; when a vehicle passes through a congested section of road or when other vehicles obstruct a large blind spot, roadside data uses high confidence, while vehicle-side data uses low confidence; when current weather conditions are obtained from the cloud, such as in heavy fog or rain, the recognition capability of camera sensors decreases, so the confidence level of camera data is lowered, the confidence level of millimeter-wave radar is increased, and high confidence is applied to cloud-side data. These are just examples and are not limited to the scenarios described above. Dynamic arbitration of multi-source data can optimize the final data quality. When a problem occurs in the data from a certain data source, such as sensor failure or functional limitation, the function can be determined by combining data from other data sources to determine whether the function needs to be alerted for takeover or downgraded / exited.

[0097] 2. Dynamic Failure Arbitration: Traditional failure assessment typically only considers the current failure mode of the vehicle, such as a corresponding sensor malfunction, without taking into account the actions to be performed next. Judging solely based on the current conditions can lead to prompting the driver to take over or the function to exit even for temporary malfunctions. Dynamic failure arbitration not only identifies the current failure state but also comprehensively considers future actions. Actions the vehicle will perform over a future period or distance can be sent from the cloud. For example, if the vehicle is traveling straight for the next 2 kilometers, and a temporary failure of the side-sensor doesn't affect the subsequent actions since it only needs to travel straight and doesn't need to change lanes, then there's no need to prompt the driver to take over, and the function doesn't need to exit. When the cloud sends a message indicating a lane change or turn is needed, if the side-sensor still has a malfunction, the driver is prompted to take over. If the temporary side-sensor malfunction disappears during the 2-kilometer straight-ahead journey, the system automatically resumes full-function operation. Since most of the time on the road is spent traveling straight, this method significantly reduces the number of times the system prompts the driver to take over or exits the function due to temporary malfunctions.

[0098] 3. ODD Dynamic Arbitration: ODD (Operational Design Domain) refers to the specific set of environments and conditions under which an autonomous driving system is designed to operate safely, including multi-dimensional constraints such as road type, geographical scope, and weather conditions. Traditional intelligent driving functions have predefined ODDs. When the system exceeds the ODD's operating range, it will prompt the driver to take over, or the function will be downgraded / exited. Vehicle-road-cloud integrated intelligent driving systems have multiple data inputs, and different data sources may emphasize different application scenarios. For example, vehicle-side data focuses on near-field target information around the vehicle, roadside data focuses on traffic light information and target information within the vehicle's blind spots, while cloud data focuses on the global traffic situation, enabling coordinated control of vehicles across the entire system. Therefore, the failure of different data sources will correspond to different ODD operating ranges, and certain single faults or failures may not necessarily affect the normal execution of functions. For example, when both vehicle-road-cloud (VDD) and roadside data are normal, the ODD can be set to operate on urban roads or highways within the coverage area of ​​the VDD. When roadside data fails, the ODD may need to be set to operate on urban expressways or highways to avoid traffic congestion or intersections where a lack of roadside data could affect driving safety. This ensures that the function can be activated and run normally under different ODD conditions, and automatically switches to full-function operation when the conditions are met, improving the application efficiency of the function.

[0099] 4. Gradual Degradation: After determining the corresponding failure mode through dynamic arbitration, the system comprehensively assesses the operational status of the function based on different failure modes, selecting from operating modes such as maintaining full functionality, degraded operation, prompting the driver to take over, or function exit. For example: when cloud data fails, since there is no global traffic situation information from the cloud, it may only affect traffic efficiency, and full functionality can be maintained using roadside unit data + vehicle-side perception data; when roadside data fails, especially when passing through intersections, there are large blind spots in the vehicle's perception range, and the system can remind the driver to maintain attention and take over the vehicle in an emergency. Under normal circumstances, full functionality can be maintained in speed-limited mode using cloud data + vehicle-side perception; when vehicle-side data is abnormal, the system reminds the driver to take over the vehicle, and the function exits after the driver takes over. If the driver does not take over the vehicle, the minimum risk strategy is executed to ensure the vehicle comes to a safe stop, minimizing the risk.

[0100] Figure 2 This is a schematic diagram of the structure of an intelligent driving system control device provided in an embodiment of the present invention. This embodiment is at least applicable to vehicle control scenarios such as intelligent connected vehicles with autonomous driving capabilities and vehicle-to-infrastructure and / or vehicle-to-cloud connectivity, connected vehicles without autonomous driving capabilities but with vehicle-to-infrastructure and / or vehicle-to-cloud connectivity, and non-connected vehicles. The intelligent driving system control device can be implemented using software and / or hardware. Figure 2 As shown, the intelligent driving system control device is used to execute the intelligent driving system control method of any of the foregoing embodiments or implementations.

[0101] The intelligent driving system control device includes at least:

[0102] The data filtering module 110 is used at least to filter out invalid vehicle-road-cloud data based on roadside perception data, vehicle-end perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-end equipment operation data, and cloud delay information.

[0103] The index calculation module 120 is used at least to calculate the current vehicle operation impact index and the future vehicle operation impact index based on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period.

[0104] The operation execution module 130 is used to perform vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index, so as to achieve seamless switching between multiple vehicle intelligent driving levels.

[0105] Optionally, it may also include at least a data acquisition module 140;

[0106] The data acquisition module 140 is specifically used for:

[0107] Roadside sensing data and roadside equipment operation data are acquired through roadside units;

[0108] Vehicle-side sensing modules are used to acquire vehicle-side perception data, and vehicle-side equipment operation data are acquired at least based on the vehicle-mounted central control unit;

[0109] Access cloud-based data collection and latency information.

[0110] Optionally, the data filtering module 110 is specifically used for at least:

[0111] At least the corresponding roadside data score should be calculated based on the roadside equipment operation data, the perceived environment information, and each roadside perception data.

[0112] At least the corresponding vehicle data score should be calculated based on the vehicle-side equipment operation data, the perceived environment information, and each vehicle-side perception data.

[0113] At least calculate the corresponding cloud data score based on cloud latency information and each piece of cloud-collected data;

[0114] Based on the scores of each roadside data, each vehicle-side data, and each cloud-based data, failed vehicle-road-cloud data are filtered out from the dataset composed of roadside perception data, vehicle-side perception data, and cloud-based data.

[0115] Optionally, the current vehicle operation scenario can be determined based at least on roadside perception data, vehicle-side perception data, and cloud-collected data at the current moment;

[0116] The vehicle operation scenario within the future preset time period can be determined based on roadside perception data, vehicle-side perception data, and cloud-collected data within the future preset time period.

[0117] The vehicle operation scenario includes at least the type of road the vehicle travels on, the actions the vehicle performs, the weather type, and the number and location of intersections the vehicle passes through.

[0118] Optionally, the index calculation module 120 is specifically used for at least:

[0119] At least the current vehicle operation impact index should be calculated based on failed vehicle-road cloud data and the current vehicle operation scenario;

[0120] The future vehicle operation impact index should be calculated based at least on failed vehicle-road cloud data and vehicle operation scenarios within a preset future time period.

[0121] Optionally, the operation execution module 130 is specifically used for at least:

[0122] Determine whether the current vehicle operation impact index is greater than the first index threshold, and whether the future vehicle operation impact index is greater than the second index threshold;

[0123] When the current vehicle operation impact index is not greater than the first index threshold and the future vehicle operation impact index is not greater than the second index threshold, it is determined that the vehicle meets the full-function operation requirements and the vehicle is controlled to perform full-function operation.

[0124] When the current vehicle operation impact index is greater than the first index threshold, it is determined that the vehicle meets the first degraded operation requirement, the vehicle is controlled to perform degraded operation, and the user is reminded to take over the vehicle.

[0125] When the current vehicle operation impact index is not greater than the first index threshold, but the future vehicle operation impact index is greater than the second index threshold, the vehicle is determined to meet the second downgrade operation requirement, and the vehicle is controlled to perform downgrade operation for at least the future preset period of time and the user is reminded to take over the vehicle.

[0126] After notifying the user to take over the vehicle, determine whether the vehicle has been taken over by the user;

[0127] The intelligent driving function is deactivated when the vehicle is taken over by the user.

[0128] Optionally, the operation execution module 130 is further specifically used for at least:

[0129] When the vehicle is not under user control, the system controls the vehicle to perform minimum-risk operations until the vehicle reaches a preset safety state and the intelligent driving function is deactivated.

[0130] The technical solution provided in this embodiment firstly filters out failed vehicle-road-cloud data based on at least roadside perception data, vehicle-side perception data, cloud-collected data, perceived environmental information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information through a data filtering module. Further, it calculates the current vehicle operation impact index and the future vehicle operation impact index based on the failed vehicle-road-cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period. Finally, it performs vehicle gradient arbitration and function degradation operations based on the current and future vehicle operation impact indices through an operation execution module, thereby achieving seamless switching between multiple vehicle intelligent driving levels. Therefore, this embodiment can design an efficient, reliable, and secure intelligent driving system control and degradation arbitration mechanism in a complex cross-domain system that integrates multi-source heterogeneous perception information from vehicles, roadside, and the cloud. This addresses issues such as delayed intelligent driving function switching, susceptibility to misjudgment, and repeated switching, thereby improving the safety, reliability, and robustness of vehicle control.

[0131] This embodiment provides an electronic device. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. See also: Figure 3The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above-mentioned intelligent driving system control methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanism (not shown). The memory 1002 stores a computer program that can be executed by the processor. When the electronic device 1000 is running, the processor 1001 executes the computer program to execute the intelligent driving system control method in any optional implementation of the above embodiments, so as to achieve at least the following functions: at least filtering failed vehicle-road-cloud data based on roadside perception data, vehicle-end perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-end equipment operation data and cloud delay information; at least calculating the current vehicle operation impact index and the future vehicle operation impact index based on the failed vehicle-road-cloud data, the current vehicle operation scenario and the vehicle operation scenario in the future preset time period; and performing vehicle gradient arbitration and function downgrade operation based on the current vehicle operation impact index and the future vehicle operation impact index to achieve seamless switching between multiple vehicle intelligent driving levels.

[0132] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the intelligent driving system control method provided in all embodiments of this application: filtering failed vehicle-road-cloud data based at least on roadside perception data, vehicle-end perception data, cloud-collected data, perceived environmental information, roadside equipment operation data, vehicle-end equipment operation data, and cloud latency information; calculating the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road-cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period; and performing vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index to achieve seamless switching between multiple vehicle intelligent driving levels.

[0133] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0135] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0136] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for an intelligent driving system, characterized in that, At least including: Failed vehicle-road-cloud data should be filtered based on at least the following: roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information. The current vehicle operation impact index and the future vehicle operation impact index are calculated based at least on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period. Based on the current vehicle operation impact index and the future vehicle operation impact index, vehicle gradient arbitration and function downgrade operations are performed to achieve seamless switching between multiple vehicle intelligent driving levels.

2. The intelligent driving system control method according to claim 1, characterized in that, Before filtering out invalid vehicle-road-cloud data based at least on roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information, the method further includes at least the following: The roadside sensing data and the roadside equipment operation data are acquired through the roadside unit; The vehicle-side sensing module is used to acquire the vehicle-side perception data, and the vehicle-side device operation data is acquired at least based on the vehicle-mounted central control unit; The cloud is invoked to obtain the cloud-collected data and the cloud latency information.

3. The intelligent driving system control method according to claim 1, characterized in that, The filtering of invalid vehicle-road-cloud data based on at least roadside perception data, vehicle-side perception data, cloud-collected data, perception environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information includes at least: At least based on the roadside equipment operation data, the sensing environment information, and each roadside sensing data point, a corresponding roadside data score is calculated. At least the corresponding vehicle data score is calculated based on the vehicle-side device operation data, the perceived environment information, and each of the vehicle-side perception data. At least based on the cloud latency information and each of the cloud-collected data, calculate the corresponding cloud data score; Based on each of the roadside data scores, each of the vehicle-side data scores, and each of the cloud-based data scores, the failed vehicle-road-cloud data is selected from the dataset composed of the roadside perception data, the vehicle-side perception data, and the cloud-based collected data.

4. The intelligent driving system control method according to claim 1, characterized in that, The current vehicle operation scenario is determined at least based on the roadside perception data, the vehicle-side perception data, and the cloud-collected data at the current moment. The vehicle operation scenario within the future preset time period is determined at least based on the roadside perception data, the vehicle-side perception data, and the cloud-collected data within the future preset time period. The vehicle operation scenario includes at least the type of road the vehicle travels on, the actions the vehicle performs, the weather type, and the number and location of intersections the vehicle passes through.

5. The intelligent driving system control method according to claim 1, characterized in that, The calculation of the current vehicle operation impact index and the future vehicle operation impact index based at least on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period includes at least: The current vehicle operation impact index shall be calculated based at least on the failed vehicle-road cloud data and the current vehicle operation scenario. The future vehicle operation impact index is calculated based at least on the failed vehicle-road cloud data and the vehicle operation scenarios within the preset future time period.

6. The intelligent driving system control method according to claim 1, characterized in that, The process of performing vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index to achieve seamless switching between multiple vehicle intelligent driving levels includes at least the following: Determine whether the current vehicle operation impact index is greater than a first index threshold, and whether the future vehicle operation impact index is greater than a second index threshold; When the current vehicle operation impact index is not greater than the first index threshold and the future vehicle operation impact index is not greater than the second index threshold, it is determined that the vehicle meets the full-function operation requirements and the vehicle is controlled to perform full-function operation. When the current vehicle operation impact index is greater than the first index threshold, it is determined that the vehicle meets the first degraded operation requirement, the vehicle is controlled to perform degraded operation, and the user is reminded to take over the vehicle. When the current vehicle operation impact index is not greater than the first index threshold, but the future vehicle operation impact index is greater than the second index threshold, it is determined that the vehicle meets the second downgraded operation requirement, and the vehicle is controlled to perform downgraded operation for at least the future preset time period and the user is reminded to take over the vehicle. After notifying the user to take over the vehicle, determine whether the vehicle has been taken over by the user; The intelligent driving function is deactivated when the vehicle is taken over by the user.

7. The intelligent driving system control method according to claim 6, characterized in that, After notifying the user to take over the vehicle and determining whether the vehicle has been taken over by the user, the process shall at least include: When the vehicle is not under user control, the system controls the vehicle to perform minimum-risk operations until the vehicle reaches a preset safety state and the intelligent driving function is deactivated.

8. A control device for an intelligent driving system, characterized in that, Used to perform the intelligent driving system control method according to any one of claims 1-7; The intelligent driving system control device includes at least: The data filtering module is used to filter out invalid vehicle-road-cloud data based on at least roadside sensing data, vehicle-side sensing data, cloud-collected data, sensing environment information, roadside equipment operation data, vehicle-side equipment operation data, and cloud latency information. The index calculation module is at least used to calculate the current vehicle operation impact index and the future vehicle operation impact index based on the failed vehicle-road cloud data, the current vehicle operation scenario, and the vehicle operation scenario within a preset future time period. The operation execution module is used to perform vehicle gradient arbitration and function downgrade operations based on the current vehicle operation impact index and the future vehicle operation impact index, so as to achieve seamless switching between multiple vehicle intelligent driving levels.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the intelligent driving system control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the intelligent driving system control method according to any one of claims 1 to 7.

Images