Vehicle control method, data processing method and related equipment

Abstract

The embodiment of the invention provides a vehicle control method which comprises the steps that first road condition data and second road condition data of a preset road are obtained, the first road condition data are from a platform data source, and the second road condition data are from a vehicle-mounted data source; performing risk classification processing based on the first road condition data to obtain a target risk type of the preset road; determining a target risk level corresponding to the target risk type based on the second road condition data; based on the target risk type and the corresponding target risk level, determining a target driving strategy when driving on the preset road; and performing driving control on the vehicle based on the target driving strategy. Due to the fact that the first road condition data of the platform data source and the second road condition data of the vehicle-mounted data source are integrated, the road condition of an emergency can be obtained in advance, the corresponding driving strategy is determined, prospective vehicle control is achieved, and the response speed during vehicle control can be increased.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more particularly to a vehicle control method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the context of developing modern autonomous driving systems, ensuring the safety of autonomous driving has become an urgent need. Traditional autonomous driving vehicle control methods mainly rely on onboard sensors and advanced processing algorithms to understand and react to the vehicle's environment. However, the reaction speed of traditional methods in response to emergencies depends on the processing speed of the algorithms. However, after onboard sensors acquire lane images in real time, the processing time available for the algorithms is limited, resulting in a slow reaction speed to emergencies. Therefore, how to provide a vehicle control method that can improve the reaction speed in the face of emergencies has become a pressing problem to be solved. Summary of the Invention

[0003] This invention provides a vehicle control method aimed at addressing the slow response speed of existing vehicle control methods in the face of emergencies. By using first and second road condition data, the target risk type and target risk level of a preset road are determined. Based on the target risk type and target risk level, a target driving strategy is determined, and the vehicle is controlled according to the target driving strategy. Because it integrates the first road condition data from the platform data source and the second road condition data from the vehicle data source, it is possible to anticipate road conditions for emergencies and determine corresponding driving strategies, thereby achieving proactive vehicle control and improving the response speed during vehicle control.

[0004] In a first aspect, embodiments of the present invention provide a vehicle control method, the method comprising the following steps:

[0005] Acquire first and second road condition data for a preset road. The first road condition data comes from a platform data source, and the second road condition data comes from an in-vehicle data source.

[0006] Based on the first road condition data, risk classification processing is performed to obtain the target risk type of the preset road.

[0007] Based on the second road condition data, the target risk level corresponding to the target risk type is determined;

[0008] Based on the target risk type and the corresponding target risk level, determine the target driving strategy when driving on the preset road;

[0009] Based on the target driving strategy, the vehicle is controlled for driving.

[0010] Optionally, determining the target risk level corresponding to the target risk type based on the second road condition data includes:

[0011] In the second road condition data, the identification target corresponding to the target risk type is determined;

[0012] Based on the identified target, a risk assessment is performed to obtain the target risk level of the preset road.

[0013] Optionally, the identified target includes its corresponding size and coordinates, and the risk assessment process based on the identified target to obtain the target risk level of the preset road includes:

[0014] Based on the size and coordinates, the influence area of ​​the identified target is determined;

[0015] Based on the affected area, the target risk level of the preset road is determined.

[0016] Optionally, each risk type corresponds to a driving strategy, the driving strategy including at least one intervention action, and determining the target driving strategy for driving on the preset road based on the target risk type and the corresponding target risk level includes:

[0017] Based on the correspondence between the risk type and the driving strategy, determine the driving strategy corresponding to the target risk type;

[0018] Based on the correspondence between risk level and intervention action, the target intervention action corresponding to the target risk level is determined in the driving strategy corresponding to the target risk type.

[0019] Based on the target intervention action, a target driving strategy is determined when driving on the preset road.

[0020] Optionally, determining the target intervention action corresponding to the target risk level within the driving strategy corresponding to the target risk type based on the correspondence between risk levels and intervention actions includes:

[0021] Based on the first traffic data or the second traffic data, the road type of the preset road is determined;

[0022] Based on the correspondence between the risk level and the intervention action, the intervention action to be performed corresponding to the target risk level is determined in the driving strategy corresponding to the target risk type.

[0023] Based on the road type, the intervention actions to be performed are screened to obtain the target intervention actions corresponding to the target risk level.

[0024] Optionally, the target driving strategy includes at least one intervention action, and the driving control of the vehicle based on the target driving strategy includes:

[0025] A feasibility analysis was performed on the intervention action to obtain the analysis results.

[0026] When the vehicle is in autonomous driving mode and the analysis result is executable, the intervention action is executed;

[0027] When the vehicle is in manual driving mode, driving suggestions are determined based on the analysis results and then sent to the vehicle's user interface.

[0028] Secondly, embodiments of the present invention provide a data processing method, the method being applied to a data management platform, the data management platform being used to feed back first road condition data to a vehicle, so that the vehicle executes the vehicle control method provided by the embodiments of the present invention, the method comprising the following steps:

[0029] Acquire road visual data from at least one data source;

[0030] Based on the road visual data, road condition analysis and processing are performed to obtain road condition data for each road;

[0031] Upon receiving a data request from the vehicle, the first road condition data of the preset road is determined from the road condition data of each road according to the data request.

[0032] The first road condition data is fed back to the vehicle.

[0033] Thirdly, embodiments of the present invention also provide a vehicle control device, the vehicle control device comprising:

[0034] The first acquisition module is used to acquire first road condition data and second road condition data of a preset road. The first road condition data comes from a platform data source and the second road condition data comes from an in-vehicle data source.

[0035] The first classification module is used to perform risk classification processing based on the first road condition data to obtain the target risk type of the preset road.

[0036] The first determining module is used to determine the target risk level corresponding to the target risk type based on the second road condition data;

[0037] The second determining module is used to determine the target driving strategy when driving on the preset road based on the target risk type and the corresponding target risk level.

[0038] The first control module is used to control the vehicle's driving based on the target driving strategy.

[0039] Fourthly, embodiments of the present invention also provide a data processing apparatus, the data processing apparatus comprising:

[0040] The second acquisition module is used to acquire road visual data from at least one data source;

[0041] The road condition analysis module is used to perform road condition analysis and processing based on the road visual data to obtain road condition data for each road.

[0042] The third determining module is used to determine the first road condition data of the preset road from the road condition data of each road when the data request of the vehicle is received.

[0043] The feedback module is used to feed back the first road condition data to the vehicle.

[0044] Fifthly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the vehicle control method or data processing method provided in embodiments of the present invention.

[0045] In a sixth aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the vehicle control method or data processing method provided in the embodiments of the invention.

[0046] In this embodiment of the invention, first road condition data and second road condition data for a preset road are acquired. The first road condition data originates from a platform data source, and the second road condition data originates from an in-vehicle data source. Risk classification processing is performed based on the first road condition data to obtain the target risk type of the preset road. Based on the second road condition data, a target risk level corresponding to the target risk type is determined. Based on the target risk type and the corresponding target risk level, a target driving strategy for driving on the preset road is determined. Based on the target driving strategy, driving control is performed on the vehicle. By using the first and second road condition data, the target risk type and target risk level of the preset road are determined. Based on the target risk type and target risk level, a target driving strategy is determined, and driving control is performed on the vehicle according to the target driving strategy. Because the first road condition data from the platform data source and the second road condition data from the in-vehicle data source are integrated, road conditions for unexpected events can be obtained in advance, and corresponding driving strategies can be determined to achieve proactive vehicle control, thereby improving the reaction speed during vehicle control. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of the present invention;

[0049] Figure 2 This is a flowchart of another vehicle control method provided in an embodiment of the present invention;

[0050] Figure 3 This is a flowchart of a data processing method provided in an embodiment of the present invention;

[0051] Figure 4 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present invention;

[0053] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of the present invention, including:

[0056] 101. Obtain the first and second road condition data for the preset road.

[0057] In this embodiment of the invention, the vehicle control method described above can be applied to the on-board electronic equipment of any type of vehicle. The on-board electronic equipment can be an on-board computer or an on-board control device, and it can contain any type of processor to execute the vehicle control method. For example, the vehicles described above can be classified according to their purpose, such as passenger cars, trucks, buses, taxis, construction vehicles, ambulances, etc.

[0058] The first traffic data mentioned above originates from a platform data source, while the second traffic data originates from an in-vehicle data source. The platform data source can be a data management platform, which can integrate real-time visual data from different urban monitoring systems, such as visual data from urban traffic monitoring systems and visual data from urban governance centers. After acquiring the real-time visual data, the data management platform can perform traffic analysis to obtain the corresponding current road traffic data. This traffic data can be understood as road conditions; for example, when there is traffic congestion, road conditions may include congestion time, congestion length, number of lanes, and number of vehicles in congestion. Alternatively, when an obstacle occupies the road, road conditions may include the size of the obstacle, its coordinates, and the lane it is located in. This traffic analysis can be implemented using any image recognition algorithm capable of traffic analysis, such as YOLOv series algorithms or CNN series algorithms.

[0059] The aforementioned preset road can be the road that the vehicle needs to travel from the starting point to the destination. The preset road can be determined by the navigation system or navigation software deployed in the vehicle.

[0060] Specifically, when the vehicle implements the vehicle control method, it can send a data request to the data management platform to obtain the first road condition data of the preset road. At the same time, when the vehicle is traveling on the preset road, it collects road visual data of the preset road through on-board sensors deployed on the vehicle, and performs road condition analysis on the road visual data to obtain the second road condition data.

[0061] 102. Based on the first road condition data, perform risk classification processing to obtain the target risk type of the preset road.

[0062] In this embodiment of the invention, the target risk type of the preset road can be determined based on the first road condition data. For example, the risk type may include road occupancy risk, road damage risk, and facility damage risk. It should be noted that since the first road condition data is obtained through a data management platform, the target risk type can be determined before the vehicle travels on the preset road.

[0063] Specifically, the first road condition data can be matched with preset risk types to achieve the aforementioned risk classification process, thereby obtaining the target risk type. Then, in the second road condition data, the identification target corresponding to the target risk type is determined, and the target risk level is determined based on the identification target.

[0064] Specifically, the aforementioned preset risk types can include road occupancy risks, road defects risks, and facility defects risks. Road occupancy risks can specifically include road flooding, haphazard parking, large objects falling from vehicles, debris, and sudden obstruction of roads by landscaping features. Road defects risks can specifically include cracks, potholes, ruts, loose surfaces, subsidence, vehicle bumps at bridge or culvert tops, and surface damage. Facility defects risks can specifically include missing protective facilities, damaged guardrails, damaged streetlights, damaged traffic lights, abnormal / damaged road signs, and faded or damaged road markings.

[0065] For example, if the first road condition data includes the presence of obstacles on the road, it can be successfully matched with the road occupancy type risk. In this case, the target risk type for the preset road is road occupancy type risk. Alternatively, if the first road condition data includes cracks in the road, it can be successfully matched with the road damage risk. In this case, the target risk type for the preset road is road damage risk. Or, if the first road condition data includes damaged streetlights, it can be successfully matched with the facility damage risk. In this case, the target risk type for the preset road is facility damage risk.

[0066] 103. Based on the second road condition data, determine the target risk level corresponding to the target risk type.

[0067] In this embodiment of the invention, the target risk level corresponding to the target risk type can be determined from the second road condition data.

[0068] Each risk type corresponds to at least one risk level. For example, when the risk type is the road occupancy risk mentioned above, the risk level is directly proportional to the size of the obstacle occupying the road; the larger the obstacle, the higher the risk level, and vice versa. Alternatively, the risk level can be inversely proportional to the distance between the lane where the obstacle is located and the vehicle's current lane; the farther the lane where the obstacle is located from the current lane, the lower the risk level, and vice versa.

[0069] It should be noted that since the aforementioned second road condition data is obtained by the aforementioned vehicle through onboard sensors and other equipment, the aforementioned second road condition data can only be obtained when the aforementioned vehicle is traveling on the aforementioned preset road, and the target risk level corresponding to the aforementioned target risk type can be determined through the aforementioned second road condition data.

[0070] The target risk type can be determined before the vehicle travels on the preset road. When traveling on the preset road, it is only necessary to determine the target risk level corresponding to the target risk type based on the second road condition data. This reduces the processing steps when traveling on the preset road, enables proactive judgment, and thus greatly improves the response speed to emergencies.

[0071] In one possible embodiment, before the vehicle travels on the preset road, it can determine the target risk type through the first road condition data. While traveling on the preset road, it collects road visual data through onboard sensors and analyzes the collected data to obtain second road condition data. In the second road condition data, it identifies the target corresponding to the target risk level and determines the target risk level based on the size, coordinates, damage condition, etc. of the target.

[0072] 104. Based on the target risk type and the corresponding target risk level, determine the target driving strategy on the preset road.

[0073] In this embodiment of the invention, the target driving strategy includes at least one intervention action. For example, the intervention action may be lane changing, deceleration, or stopping. Each risk type corresponds to at least one risk level, and each risk type also corresponds to a driving strategy. Each driving strategy includes an intervention action corresponding to the risk level.

[0074] The aforementioned vehicle may store a strategy dataset, which includes driving strategies corresponding to different risk types, as well as intervention actions corresponding to different risk levels for different risk types.

[0075] After obtaining the target risk type and corresponding target risk level of the preset road, a driving strategy corresponding to the target risk type can be matched in the above strategy dataset. After matching the driving strategy corresponding to the target risk type, an intervention action corresponding to the target risk level can be matched in the driving strategy corresponding to the target risk type.

[0076] 105. Based on the target driving strategy, control the vehicle's driving.

[0077] In this embodiment of the invention, driving control of the vehicle can be performed based on at least one intervention action in the above-mentioned target driving strategy to deal with road risks.

[0078] Specifically, in addition to physical intervention actions on the vehicle such as lane changing and deceleration (or understood as active intervention actions), the above-mentioned intervention actions may also include delivering driving suggestions (which can be understood as passive intervention actions). The above-mentioned driving suggestions can be determined according to the above-mentioned target driving strategy. For example, when the above-mentioned target driving strategy contains only one intervention action "lane changing", the above-mentioned driving suggestions may be a suggested lane change, as well as the direction of the lane change, the coordinates of the lane change, etc.

[0079] More specifically, the vehicle can be controlled based on its current state and the target driving strategy. The current state includes both automated driving and manual driving modes.

[0080] When the vehicle is currently in autonomous driving mode, physical driving control can be achieved through intervention actions in the aforementioned target driving strategy. When the vehicle is currently in manual driving mode, driving suggestions can be sent to the vehicle's user interface to achieve non-physical driving control.

[0081] In this embodiment of the invention, first road condition data and second road condition data for a preset road are acquired. The first road condition data originates from a platform data source, and the second road condition data originates from an in-vehicle data source. Risk classification processing is performed based on the first road condition data to obtain the target risk type of the preset road. Based on the second road condition data, a target risk level corresponding to the target risk type is determined. Based on the target risk type and the corresponding target risk level, a target driving strategy for driving on the preset road is determined. Based on the target driving strategy, driving control is performed on the vehicle. By using the first and second road condition data, the target risk type and target risk level of the preset road are determined. Based on the target risk type and target risk level, a target driving strategy is determined, and driving control is performed on the vehicle according to the target driving strategy. Because the first road condition data from the platform data source and the second road condition data from the in-vehicle data source are integrated, road conditions for unexpected events can be obtained in advance, and corresponding driving strategies can be determined to achieve proactive vehicle control, thereby improving the reaction speed during vehicle control.

[0082] It is understood that in the specific implementation of this application, data such as first road condition data, second road condition data, and road vision data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0083] It should be noted that the vehicle control method provided in this embodiment of the invention can be applied to in-vehicle electronic devices capable of vehicle control.

[0084] Optionally, in the step of determining the target risk level corresponding to the target risk type based on the second road condition data, the identification target corresponding to the target risk type can also be determined from the second road condition data; risk assessment processing can be performed based on the identification target to obtain the target risk level of the preset road.

[0085] In this embodiment of the invention, the aforementioned identification target may include a corresponding size and coordinates. The size may be any area unit, such as square centimeters or square meters. The coordinates may be coordinates of any geographic coordinate system, such as latitude and longitude in a latitude and longitude coordinate system, UTM (Universal Transverse Mercator) coordinate system, MGRS (Military Grid Reference System), NAD83 coordinate system, ECEF (Earth-Centered, Earth-Fixed) coordinate system, etc.

[0086] Specifically, based on the size and coordinates of the identified target, the influence area of ​​the target on a preset road can be determined. Based on this influence area, the number of lanes on the preset road affected by the influence area, and the influence area of ​​each lane, can be determined. The risk level of the target is then determined based on the number of lanes and the influence area. The number of lanes and the influence area are directly proportional to the target's risk level; the more lanes and the larger the influence area, the higher the target's risk level. Conversely, the fewer lanes and the smaller the influence area, the lower the target's risk level.

[0087] Alternatively, the target risk level can be determined directly based on the aforementioned size and coordinates. For example, the larger the size, the closer the target's coordinates are to the vehicle's current coordinates, and the higher the target risk level. Conversely, the smaller the size, the farther the target's coordinates are from the vehicle's current coordinates, and the lower the target risk level.

[0088] Optionally, in the step of performing risk assessment based on the identified target to obtain the target risk level of the preset road, the influence area of ​​the identified target can also be determined based on its size and coordinates; and the target risk level of the preset road can be determined based on the influence area.

[0089] In this embodiment of the invention, when the target risk type is a road occupancy risk, specifically when there is an obstacle on the road, road visual data of the preset road can be collected by onboard sensors while the vehicle is traveling on the preset road. This road visual data is then processed for identification (with a focus on identifying the presence of obstacles) to obtain second road condition data. This second road condition data may include the obstacle size and coordinates. Based on the second road condition data, the identified target (i.e., obstacle) corresponding to the target risk type in the preset road is determined. The target risk level is determined based on the obstacle's size and coordinates. A higher target risk level is achieved when the obstacle is larger and closer to the vehicle. Conversely, a lower target risk level is achieved when the obstacle is smaller and farther from the vehicle.

[0090] It should be noted that the distance between the obstacle and the vehicle can be determined by analyzing the obstacle's coordinates and determining its lane. If the obstacle is in the same lane as the vehicle, the distance is considered close; if it's in an adjacent lane, the distance is relatively close; and if it's in neither an adjacent nor the same lane, the distance is relatively far. Alternatively, the distance between the obstacle and the vehicle can be determined by comparing the obstacle's current coordinates. Another approach is to combine the distances between the obstacle's current coordinates and the vehicle's current coordinates, as well as the distances between the obstacle's current lane and the vehicle's current lane, to calculate the distance between them. In other words, comparing the obstacle's current lane coordinates with the current lane coordinates provides a lateral distance comparison, while comparing the obstacle's current lane coordinates provides a vertical distance comparison.

[0091] When the target risk type is road defect risk, specifically cracks, road visual data of the preset road can be collected by onboard sensors while the vehicle is traveling on the preset road. This road visual data is then processed for identification (with a focus on identifying the presence of cracks) to obtain second road condition data. This second road condition data may include crack size and crack coordinates. Based on this second road condition data, the identification target (i.e., road crack) corresponding to the target risk type in the preset road is determined. The target risk level is determined based on the crack's size and coordinates. A higher target risk level is achieved when the crack is larger and closer to the vehicle. Conversely, a lower target risk level is achieved when the crack is smaller and farther from the vehicle. It should be noted that the distance between the crack's coordinates and the vehicle is determined in the same way as the distance between an obstacle and the vehicle, and with the same effect. To avoid redundancy, this will not be elaborated further.

[0092] When the target risk type is facility damage risk, specifically street light damage, road visual data of the preset road can be collected by onboard sensors while the vehicle is traveling on the preset road. This road visual data is then processed (with a focus on identifying damaged street lights) to obtain second road condition data. This second road condition data may include the street light damage status and street light coordinates. Based on this second road condition data, the identification target (i.e., street light) corresponding to the target risk type in the preset road is determined. The affected area caused by the street light damage is predicted based on the street light damage status. The target risk level is determined based on the coordinates and the affected area. A higher target risk level is achieved when the affected area of ​​the street light is larger and its coordinates are closer to the vehicle. Conversely, a lower target risk level is achieved when the affected area of ​​the street light is smaller and its coordinates are farther from the vehicle.

[0093] It should be noted that, generally speaking, if the damage to the streetlights is less than a preset threshold, the more severe the damage, the larger the affected area; conversely, the less severe the damage, the smaller the affected area. The preset threshold can be determined based on the material of the streetlight. For example, in extreme cases, when the streetlight is made of plastic, the preset threshold can be set relatively low; when the streetlight is made of alloy, the preset threshold can be set relatively high.

[0094] When the damage exceeds the preset threshold, it can be simply understood as the streetlight turning to dust. Normally, when a streetlight turns to dust, it will not affect vehicle safety. Therefore, the direct proportionality between the damage and the affected area only applies when the damage is less than the threshold. However, when the damage exceeds the preset threshold, since it does not affect driving safety, the target risk level can be directly set to the lowest risk level.

[0095] Similarly, the method for determining the coordinates of the streetlights and their distance from the vehicle is the same as the method for determining the distance between the obstacle and the vehicle, and the effect is the same. To avoid repetition and redundancy, it will not be repeated here.

[0096] Optionally, in the step of determining the target driving strategy when driving on the preset road based on the target risk type and the corresponding target risk level, the driving strategy corresponding to the target risk type can also be determined based on the correspondence between the risk type and the driving strategy; the target intervention action corresponding to the target risk level can be determined in the driving strategy corresponding to the target risk type based on the correspondence between the risk level and the intervention action; and the target driving strategy when driving on the preset road can be determined based on the target intervention action.

[0097] In this embodiment of the invention, each of the above-mentioned risk types corresponds to at least one of the above-mentioned risk levels, each of the above-mentioned risk types corresponds to one of the above-mentioned driving strategies, the driving strategies include intervention actions corresponding to the above-mentioned risk levels, and the target driving strategies include at least one of the above-mentioned target intervention actions.

[0098] Once the target risk type and target risk level are determined, the driving strategy corresponding to the target risk type can be determined based on the correspondence between risk types and driving strategies. It should be noted that the driving strategy corresponding to the target risk type includes intervention actions corresponding to different risk levels. Therefore, based on the correspondence between risk levels and intervention actions, the target intervention action corresponding to the target risk level can be determined within the driving strategy corresponding to the target risk type.

[0099] For example, when the target risk type is road occupancy risk, the corresponding risk level can include a first risk level, a second risk level, and a third risk level. The corresponding driving strategies could be: at the first risk level, intervention could involve sending a warning message to the driver to inform them of obstacles ahead. At the second risk level, intervention could involve assessing the safety of other lanes; if safe, activating the automatic lane change function and switching to a safe lane if it is safe to do so. At the third risk level, intervention could involve reducing speed, activating the anti-skid system when wading through water to maintain vehicle stability, and safely stopping if necessary.

[0100] It should be noted that when the target risk level is Level 1, it means the obstacle is very small and does not affect the normal driving of the vehicle. Therefore, only an alarm message needs to be sent to avoid false alarms, and the target intervention action is to send an alarm message. When the target risk level is Level 2, it means the obstacle's coordinates are located in the vehicle's current lane and its size is large enough to affect the normal driving of the current lane. Therefore, a lane change is required, and the target intervention action is to change lanes. When the target risk level is Level 3, it means the obstacle's coordinates are located in the vehicle's current lane and its size is large enough to affect the normal driving of all lanes on the current road. Therefore, it is necessary to slow down and, if necessary, stop. The target intervention actions include slowing down and stopping.

[0101] Alternatively, when the target risk type is road defect risk, the risk level corresponding to the target risk type may include a first risk level, a second risk level, and a third risk level. The corresponding driving strategy may be: at the first risk level, a warning message is sent to the driver to inform them in advance of the road defect situation ahead; at the second risk level, the intervention action may be to reduce the vehicle speed and adjust the suspension settings appropriately to ensure a smooth passage; at the third risk level, the intervention action may be to assess whether there are road defects in other lanes and automatically change lanes; if there are also road defects in other lanes, emergency deceleration is initiated and preparations are made to detour (i.e., detour away from the currently traveled preset road).

[0102] It should be noted that when the target risk level is Level 1, it means the road defect is very small and does not affect normal vehicle operation. Therefore, only a warning message needs to be sent to avoid misjudgment, and the target intervention action is to send a warning message. When the target risk level is Level 2, it means the road defect is located in the vehicle's current lane and its size is sufficient to affect normal driving in the current lane. Therefore, it is necessary to slow down and adjust the suspension. The target intervention action includes slowing down and adjusting the suspension. When the target risk level is Level 3, it means the road defect is located in the vehicle's current lane and its size seriously affects normal driving in the current lane. Therefore, it is necessary to change lanes, and if all lanes are seriously affected, it is necessary to slow down and detour. The target intervention action includes assessment, lane change, slowing down, and detour.

[0103] Alternatively, when the target risk type is facility failure risk, the risk level corresponding to the target risk type can include a first risk level and a second risk level. The corresponding driving strategy could be: at the first risk level, reduce vehicle speed, activate the enhanced vision system, and replace the solution calculated by the system when it is safe to do so; at the second risk level, adjust the route and move away from the facility failure based on temporary traffic signals or bypass navigation suggestions.

[0104] It should be noted that when the target risk level is Level 1, it indicates that the facility's damage risk is not severe, and the pre-designed road is still passable. However, to avoid emergencies, it is still necessary to reduce vehicle speed and activate the enhanced vision system. Alternative solutions should be calculated and implemented while ensuring safety. In this case, the intervention actions include slowing down, activating the enhanced vision system, and calculating alternative solutions. When the target risk level is Level 2, it indicates that the facility's damage risk is severe, and the pre-designed road is impassable. If there are temporary traffic signals or bypass navigation suggestions, the route should be adjusted according to these signals or suggestions to move away from the facility's damage. In this case, the intervention actions include recognizing traffic signals or bypass navigation suggestions and adjusting the route accordingly.

[0105] After obtaining the aforementioned target intervention actions, if there is only one target intervention action, it can be directly identified as the target driving strategy. If there are multiple target intervention actions, the execution order of these actions can be determined, and the target driving strategy can be determined based on the execution order and the multiple target intervention actions. The execution order can be set based on historical driving experience.

[0106] Optionally, in the step of determining the target intervention action corresponding to the target risk level in the driving strategy corresponding to the target risk type based on the correspondence between risk level and intervention action, the road type of the preset road can also be determined based on the first road condition data or the second road condition data; the intervention action to be executed corresponding to the target risk level can be determined in the driving strategy corresponding to the target risk type based on the correspondence between risk level and intervention action; and the intervention action to be executed can be filtered based on the road type to obtain the target intervention action corresponding to the target risk level.

[0107] In this embodiment of the invention, the road type of the preset road can be a highway, tunnel section, bridge section, railway crossing section, etc., and the road type of the preset road can be determined based on the first road condition data or the second road condition data. Based on the correspondence between risk level and intervention action, the intervention action to be executed corresponding to the target risk level is determined in the driving strategy corresponding to the target risk type. The intervention actions to be executed are then filtered according to the road type to obtain the target intervention action.

[0108] For example, when the aforementioned road types are tunnel sections, bridge sections, or railway crossing sections, lane changes are not permitted to avoid safety risks. Therefore, intervention actions related to lane changes (such as lane changing, overtaking, etc.) cannot be performed. Thus, lane-change related intervention actions can be removed from the list of pending intervention actions. For example, if the pending intervention actions include reducing speed and changing lanes, lane changing can be removed, and only reducing speed can be performed. Alternatively, if all pending intervention actions are related to lane changing, a preset alternative can be activated, such as reducing speed while reminding the user to switch to manual driving mode.

[0109] For example, if the road type mentioned above is a school zone, honking is usually not allowed on school zones. Therefore, intervention actions related to honking cannot be executed. Thus, intervention actions related to honking can be removed from the pending actions.

[0110] For example, if the target risk type is road defect risk and the target risk level is the third risk level, it means that there are serious road defects in the current driving lane. In this case, the intervention action of the target driving strategy can be to require switching to manual driving mode in advance.

[0111] Optionally, in the step of driving control of the vehicle based on the target driving strategy, a feasibility analysis of the intervention action can be performed to obtain the analysis results of the intervention action; when the vehicle is in an autonomous driving state and the analysis result is executable, the intervention action is executed; when the vehicle is in a manual driving state, driving suggestions are determined based on the analysis results and the driving suggestions are sent to the user interface of the vehicle.

[0112] In this embodiment of the invention, the target driving strategy includes at least one intervention action, and the feasibility analysis can be implemented by any algorithm capable of performing feasibility analysis, such as Kalman Filter, FiniteState Machine (FSM), Deep Q-Learning (DQN), Constant Velocity Model, etc.

[0113] When the vehicle is in autonomous driving mode, each intervention action can be analyzed for feasibility. The analysis results for each intervention action are obtained. If the analysis result is executable, the intervention action is executed. If the analysis result is not executable, the intervention action is not executed, and the analysis results are sent to the aforementioned user interface.

[0114] Alternatively, when the vehicle is in manual driving mode, driving suggestions can be determined based on the above analysis results. For example, if the analysis result indicates that lane changing is permitted, the corresponding driving suggestion could be to suggest changing lanes, while providing information such as the timing and direction of the lane change. This driving suggestion would then be sent to the aforementioned user interface. The user interface could be the vehicle's central control screen, instrument panel, or HUD device, etc.

[0115] like Figure 2 As shown, Figure 2 This is a flowchart of another vehicle control method provided by an embodiment of the present invention. It includes a data integration layer (i.e., a data management platform) and a vehicle terminal. The data integration layer can integrate road visual data collected by different image acquisition systems and perform preliminary analysis on the road visual data to obtain first road condition data. The data integration layer determines the target risk type based on the first road condition data, or directly sends the first road condition data to the vehicle terminal, where the vehicle terminal determines the target risk type based on the first road condition data. Based on the target risk type, a target risk level is determined. Based on the target risk level, interventions and prompts (i.e., intervention actions, where intervention can be understood as active intervention actions and prompts as passive intervention actions) are determined in the target driving strategy. Vehicle control is then performed based on the interventions and prompts.

[0116] like Figure 3 As shown, Figure 3This is a flowchart of a data processing method provided in an embodiment of the present invention, applied to a data management platform. The data management platform is used to feed back first road condition data to the vehicle, so that the vehicle executes the vehicle control method provided in this embodiment of the present invention, including:

[0117] 301. Obtain road visual data from at least one data source.

[0118] In this embodiment of the invention, the above-described data processing method can be applied to a data management platform. This platform can be constructed using a server or server cluster, which can be any electronic device with functions such as data processing, data analysis, data storage, and data transmission. The road visual data from at least one data source can be road visual data collected by an urban traffic monitoring system, road visual data collected by an urban governance center, or road visual data collected by other platforms capable of collecting road visual data.

[0119] The aforementioned data management platform can integrate and store road vision data from different image acquisition systems through the aforementioned data transmission function.

[0120] 302. Based on road visual data, perform road condition analysis and processing to obtain road condition data for each road.

[0121] In this embodiment of the invention, the aforementioned road condition analysis can be implemented using any image recognition algorithm capable of road condition analysis, such as the YOLOv series algorithms, CNN series algorithms, etc. A road condition analysis model can be constructed and trained using the aforementioned image recognition algorithm. This model is then deployed on the aforementioned data management platform. Upon receiving the aforementioned road visual data, the data management platform inputs the road visual data into the aforementioned road condition analysis model for road condition analysis processing, thereby obtaining road condition data for each road.

[0122] 303. Upon receiving a data request from a vehicle, determine the first road condition data for the preset road from the road condition data of each road according to the data request.

[0123] In this embodiment of the invention, the traffic condition data of each of the aforementioned roads can be stored in the storage medium of the aforementioned data management platform. The data request from the vehicle can be a request for traffic condition data of a preset road. Before driving on the preset road, the vehicle can send the data request to the aforementioned data management platform. After receiving the data request, the data management platform determines the first traffic condition data of the preset road from the traffic condition data of each road according to the data request.

[0124] 304. Feed back the first road condition data to the vehicle.

[0125] In this embodiment of the invention, after determining the first road condition data of the preset road, the data management platform feeds back the first road condition data to the vehicle through the data transmission function, so that the vehicle executes any of the vehicle control methods provided in this embodiment of the invention.

[0126] In one possible embodiment, any vehicle can register its vehicle information in the aforementioned data management platform. At the same time, the vehicle's location can be shared with the aforementioned data management platform. After determining the first road condition data based on the road visual data, the aforementioned data management platform can broadcast the first road condition data to all vehicles on the road corresponding to the first road condition data, based on the vehicle's location.

[0127] like Figure 4 As shown, embodiments of the present invention also provide a vehicle control device, comprising:

[0128] The first acquisition module 401 is used to acquire first road condition data and second road condition data of a preset road. The first road condition data comes from a platform data source and the second road condition data comes from a vehicle data source.

[0129] The first classification module 402 is used to perform risk classification processing based on the first road condition data to obtain the target risk type of the preset road.

[0130] The first determining module 403 is used to determine the target risk level corresponding to the target risk type based on the second road condition data;

[0131] The second determining module 404 is used to determine the target driving strategy when driving on the preset road based on the target risk type and the corresponding target risk level.

[0132] The first control module 405 is used to control the vehicle's driving based on the target driving strategy.

[0133] Optionally, the first determining module 403 includes:

[0134] The first determining submodule is used to determine the identification target corresponding to the target risk type in the second road condition data;

[0135] The first assessment submodule is used to perform risk assessment processing based on the identified target to obtain the target risk level of the preset road.

[0136] Optionally, the identified target includes its corresponding size and coordinates, and the first evaluation submodule includes:

[0137] The first determining unit is configured to determine the influence area of ​​the identified target based on the size and the coordinates.

[0138] The second determining unit is used to determine the target risk level of the preset road based on the affected area.

[0139] Optionally, each of the risk types corresponds to a driving strategy, the driving strategy including at least one intervention action, and the second determining module 404 includes:

[0140] The second determining submodule is used to determine the driving strategy corresponding to the target risk type based on the correspondence between the risk type and the driving strategy;

[0141] The third determination submodule is used to determine the target intervention action corresponding to the target risk level in the driving strategy corresponding to the target risk type based on the correspondence between risk level and intervention action.

[0142] The fourth determining submodule is used to determine the target driving strategy when driving on the preset road based on the target intervention action.

[0143] Optionally, the third determining submodule includes:

[0144] The third determining unit is used to determine the road type of the preset road based on the first road condition data or the second road condition data;

[0145] The fourth determining unit is used to determine the intervention action to be executed corresponding to the target risk level in the driving strategy corresponding to the target risk type based on the correspondence between the risk level and the intervention action;

[0146] The first screening unit is used to screen the intervention actions to be performed based on the road type to obtain the target intervention actions corresponding to the target risk level.

[0147] Optionally, the target driving strategy includes at least one intervention action, and the first control module 405 includes:

[0148] The first analysis submodule is used to perform a feasibility analysis on the intervention action and obtain the analysis results of the intervention action;

[0149] The first execution submodule is used to execute the intervention action when the vehicle is in an autonomous driving state and the analysis result is executable.

[0150] The first delivery submodule is used to determine driving suggestions based on the analysis results when the vehicle is in manual driving mode, and to deliver the driving suggestions to the user interface of the vehicle.

[0151] like Figure 5As shown, embodiments of the present invention also provide a data processing apparatus, including:

[0152] The second acquisition module 501 is used to acquire road visual data from at least one data source;

[0153] The road condition analysis module 502 is used to perform road condition analysis processing based on the road visual data to obtain road condition data for each road.

[0154] The third determining module 503 is used to determine the first road condition data of the preset road from the road condition data of each road when the data request of the vehicle is received.

[0155] Feedback module 504 is used to feed back the first road condition data to the vehicle.

[0156] like Figure 6 As shown, an embodiment of the present invention also provides an electronic device, characterized in that it includes a processor, which can execute any of the above-described vehicle control methods or data processing methods.

[0157] Specifically, it includes a processor 601 and a memory 602, as well as a computer program stored in the memory 602 and capable of running on the processor 601 to execute vehicle control methods or data processing methods, wherein:

[0158] The processor 601 executes the calculator program for the vehicle control method stored in the memory 602, performing the following steps:

[0159] Acquire first and second road condition data for a preset road. The first road condition data comes from a platform data source, and the second road condition data comes from an in-vehicle data source.

[0160] Based on the first road condition data, risk classification processing is performed to obtain the target risk type of the preset road.

[0161] Based on the second road condition data, the target risk level corresponding to the target risk type is determined;

[0162] Based on the target risk type and the corresponding target risk level, determine the target driving strategy when driving on the preset road;

[0163] Based on the target driving strategy, the vehicle is controlled for driving.

[0164] Optionally, the step of determining the target risk level corresponding to the target risk type based on the second road condition data, executed by the processor 601, includes:

[0165] In the second road condition data, the identification target corresponding to the target risk type is determined;

[0166] Based on the identified target, a risk assessment is performed to obtain the target risk level of the preset road.

[0167] Optionally, the identified target includes its corresponding size and coordinates, and the risk assessment processing based on the identified target performed by the processor 601 to obtain the target risk level of the preset road includes:

[0168] Based on the size and coordinates, the influence area of ​​the identified target is determined;

[0169] Based on the affected area, the target risk level of the preset road is determined.

[0170] Optionally, each risk type corresponds to a driving strategy, the driving strategy including at least one intervention action, and the processor 601 executing the determination of the target driving strategy for driving on the preset road based on the target risk type and the corresponding target risk level includes:

[0171] Based on the correspondence between the risk type and the driving strategy, determine the driving strategy corresponding to the target risk type;

[0172] Based on the correspondence between risk level and intervention action, the target intervention action corresponding to the target risk level is determined in the driving strategy corresponding to the target risk type.

[0173] Based on the target intervention action, a target driving strategy is determined when driving on the preset road.

[0174] Optionally, the processor 601 executes the correspondence between risk level and intervention action, determining the target intervention action corresponding to the target risk level in the driving strategy corresponding to the target risk type, including:

[0175] Based on the first traffic data or the second traffic data, the road type of the preset road is determined;

[0176] Based on the correspondence between the risk level and the intervention action, the intervention action to be performed corresponding to the target risk level is determined in the driving strategy corresponding to the target risk type.

[0177] Based on the road type, the intervention actions to be performed are screened to obtain the target intervention actions corresponding to the target risk level.

[0178] Optionally, the target driving strategy includes at least one intervention action, and the driving control of the vehicle based on the target driving strategy executed by the processor 601 includes:

[0179] A feasibility analysis was performed on the intervention action to obtain the analysis results.

[0180] When the vehicle is in autonomous driving mode and the analysis result is executable, the intervention action is executed;

[0181] When the vehicle is in manual driving mode, driving suggestions are determined based on the analysis results and then sent to the vehicle's user interface.

[0182] The processor 601 executes the calculator program containing the data processing method stored in the memory 602, performing the following steps:

[0183] Acquire road visual data from at least one data source;

[0184] Based on the road visual data, road condition analysis and processing are performed to obtain road condition data for each road;

[0185] Upon receiving a data request from the vehicle, the first road condition data of the preset road is determined from the road condition data of each road according to the data request.

[0186] The first road condition data is fed back to the vehicle.

[0187] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the vehicle control method, data processing method, or application-side vehicle control method and data processing method provided in this invention, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0188] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The computer-readable storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0189] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A vehicle control method characterized by, The method comprises the following steps: obtaining first road condition data and second road condition data of a preset road, wherein the first road condition data is derived from a platform data source, and the second road condition data is derived from a vehicle-mounted data source; performing risk classification processing based on the first road condition data to obtain a target risk type of the preset road; based on the second road condition data, determining a target risk level corresponding to the target risk type; based on the target risk type and the corresponding target risk level, determining a target driving strategy when driving on the preset road; based on the target driving strategy, performing driving control on the vehicle.

2. The vehicle control method according to claim 1, characterized by, The method comprises the following steps: in the second road condition data, determining an identification target corresponding to the target risk type; based on the identification target, performing risk assessment processing to obtain a target risk level of the preset road.

3. The vehicle control method according to claim 2, characterized by, The identification target comprises a corresponding size and coordinates, and the risk assessment processing based on the identification target to obtain the target risk level of the preset road comprises: based on the size and the coordinates, determining an influence area of the identification target; based on the influence area, determining the target risk level of the preset road.

4. The vehicle control method according to claim 1, characterized by, Each risk type corresponds to a driving strategy, and the driving strategy comprises at least one intervention action. Based on the target risk type and the corresponding target risk level, the target driving strategy when driving on the preset road is determined, which comprises: based on the corresponding relationship between the risk type and the driving strategy, determining the driving strategy corresponding to the target risk type; based on the corresponding relationship between the risk level and the intervention action, determining the target intervention action corresponding to the target risk level in the driving strategy corresponding to the target risk type; based on the target intervention action, determining the target driving strategy when driving on the preset road.

5. The vehicle control method according to claim 4, characterized by, The method comprises the following steps: based on the first road condition data or the second road condition data, determining the road type of the preset road; based on the corresponding relationship between the risk level and the intervention action, determining the to-be-executed intervention action corresponding to the target risk level in the driving strategy corresponding to the target risk type; based on the road type, performing screening processing on the to-be-executed intervention action to obtain the target intervention action corresponding to the target risk level.

6. The vehicle control method according to claim 1, characterized by, The target driving strategy comprises at least one intervention action, and the driving control on the vehicle based on the target driving strategy comprises: performing feasibility analysis on the intervention action to obtain an analysis result of the intervention action; when the vehicle is in an autonomous driving state and the analysis result is executable, executing the intervention action; when the vehicle is in a manual driving state, determining a driving suggestion based on the analysis result and sending the driving suggestion to a user interaction interface of the vehicle.

7. A data processing method, characterized by, The method is applied to a data management platform for feeding back first road condition data to a vehicle to make the vehicle perform the vehicle control method as claimed in any one of claims 1 to 6, and the method comprises the following steps: acquiring road visual data of at least one data source; performing road condition analysis processing based on the road visual data to obtain road condition data of each road; when receiving a data request of the vehicle, determining the first road condition data of the preset road from the road condition data of each road according to the data request; feeding back the first road condition data to the vehicle.

8. A vehicle control device characterized by comprising: The vehicle control device comprises: a first acquisition module for acquiring first road condition data and second road condition data of a preset road, wherein the first road condition data is from a platform data source, and the second road condition data is from a vehicle-mounted data source; a first classification module for performing risk classification processing based on the first road condition data to obtain a target risk type of the preset road; a first determination module for determining a target risk level corresponding to the target risk type based on the second road condition data; a second determination module for determining a target driving strategy when driving on the preset road based on the target risk type and the corresponding target risk level; a first control module for performing driving control on the vehicle based on the target driving strategy.

9. An electronic device, comprising: comprise: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the vehicle control method as claimed in any one of claims 1 to 6 or the data processing method as claimed in claim 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the vehicle control method as claimed in any one of claims 1 to 7 or the data processing method as claimed in claim 7.

Images