Road abnormity early warning method and system, vehicle and computer readable storage medium

Abstract

The invention relates to a road abnormity early warning method and system, a vehicle and a computer readable storage medium. The method comprises the following steps: acquiring vehicle driving environment information and road surface information monitored by different types of vehicle-mounted sensors; determining a target fusion weight corresponding to each vehicle-mounted sensor according to the environment information; according to the target fusion weight, carrying out fusion processing on the multiple pieces of road surface information, and determining an identification result of the vehicle driving road surface; and when the identification result is that the driving road surface has the abnormal area, generating road surface early warning information related to the abnormal area, and uploading the road surface early warning information to a cloud end, so that the cloud end determines a target vehicle according to the road surface early warning information, and performs road surface abnormal early warning control on the target vehicle. By adopting the method, the timeliness and accuracy of road abnormity early warning can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a road anomaly warning method, system, vehicle, and computer-readable storage medium. Background Art

[0002] With the development of computer technology, intelligent transportation technology has emerged. Intelligent transportation technology provides intelligent management and control of transportation systems to improve transportation efficiency and ensure traffic safety. Therefore, road anomaly warnings are an indispensable component of intelligent transportation. When vehicles are traveling on open roads, road and environmental conditions can hinder drivers' ability to detect road hazards, leading to traffic accidents.

[0003] In related technologies, road abnormality warnings monitor road conditions through manual patrols and fixed sensors installed on both sides of the road. This method has problems such as large response delays and limited coverage, making it difficult to deliver warning information to all traffic participants in need in a timely and accurate manner. Summary of the Invention

[0004] Based on this, it is necessary to provide a road abnormality warning method, system, computer equipment, computer-readable storage medium and computer program product that can improve the timeliness and accuracy of road abnormality warning in response to the above technical problems.

[0005] In a first aspect, the present application provides a road anomaly warning method, comprising:

[0006] Obtain vehicle driving environment information and road surface information monitored by different types of vehicle-mounted sensors;

[0007] Determining the target fusion weight corresponding to each of the on-board sensors according to the environmental information;

[0008] fusing the plurality of road surface information according to the target fusion weight to determine an identification result of the road surface on which the vehicle is traveling;

[0009] When the recognition result indicates that there is an abnormal area on the driving road, road surface warning information related to the abnormal area is generated and uploaded to the cloud, so that the cloud can determine the target vehicle based on the road surface warning information and perform road surface abnormality warning control on the target vehicle.

[0010] In one embodiment, determining the target fusion weight corresponding to each of the vehicle-mounted sensors according to the environmental information includes:

[0011] Determine, from the on-board sensors, a first on-board sensor whose fusion weight is positively correlated with the environmental information, and a second on-board sensor whose fusion weight is negatively correlated with the environmental information;

[0012] adjusting the fusion weight of the first vehicle-mounted sensor according to the environmental information and the positive correlation to obtain a corresponding target fusion weight;

[0013] According to the environmental information and the negative correlation, the fusion weight of the second vehicle-mounted sensor is adjusted to obtain a corresponding target fusion weight.

[0014] In one embodiment, the fusing the road surface information according to the target fusion weight to determine the recognition result of the vehicle driving road surface includes:

[0015] Determining a road surface anomaly confidence level of each of the road surface information, and performing fusion processing based on the target fusion weight and the corresponding road surface anomaly confidence level to obtain a comprehensive confidence level;

[0016] The recognition result of the vehicle driving road surface is determined according to the comprehensive confidence level.

[0017] In one embodiment, when the recognition result indicates that there is an abnormal area on the driving road surface, generating road surface warning information related to the abnormal area and uploading the road surface warning information to the cloud includes:

[0018] If the recognition result indicates that an abnormal area exists on the driving road surface, determining a section feature of the driving road surface according to each of the road surface information;

[0019] If the road section feature does not exist in the preset road section feature database, determining that the abnormal area of ​​the driving road surface is not a preset false alarm point;

[0020] Determine the location information of the abnormal area, the danger level of the abnormal area, and a timestamp, generate road surface warning information related to the abnormal area, and upload the road surface warning information to the cloud.

[0021] In a second aspect, the present application provides a road anomaly warning method, comprising:

[0022] Obtaining road surface warning information sent by the vehicle; the road surface warning information is determined by any of the methods described above;

[0023] According to the road surface warning information, if it is detected that there is a target vehicle within the preset range of the vehicle, road surface abnormality warning control is performed on the target vehicle according to the road surface warning information to ensure safe driving of the target vehicle.

[0024] In an exemplary embodiment, performing road abnormality warning control on the target vehicle according to the road surface warning information to enable the target vehicle to travel safely includes:

[0025] Obtain road topology data of the driving road;

[0026] generating a strip fence extending along the road based on the position information of the abnormal area in the road warning information and the road topology data of the driving road;

[0027] Obtaining real-time location data of the target vehicle;

[0028] When the target vehicle is detected to have entered the strip fence of the road warning information according to the real-time position data, the warning strategy associated with the road warning information is pushed to the target vehicle, and the abnormal area is displayed on the display terminal of the target vehicle.

[0029] In an exemplary embodiment, the method further comprises:

[0030] If it is detected that the target vehicle stays at the strip fence for longer than a preset time, the target vehicle is controlled to play the warning strategy;

[0031] If it is monitored that the relative distance between the target vehicle and the abnormal area is not within the preset safety distance range, the target vehicle is controlled to travel at a preset safety speed and the double flash lights and alarm system of the target vehicle are triggered.

[0032] In an exemplary embodiment, before detecting that the target vehicle enters the strip fence of the road warning information, the method further includes:

[0033] Determine the relative distance between the target vehicle and the strip fence according to the real-time position data;

[0034] The reporting frequency of the position data of the target vehicle is adjusted according to the relative distance, and the reporting frequency and the relative distance satisfy a positive correlation relationship.

[0035] In a third aspect, the present application further provides a road anomaly warning system, including a vehicle, a cloud, and a target vehicle, wherein the vehicle includes a controller, wherein:

[0036] The controller is configured to obtain environmental information about the vehicle and road surface information monitored by different types of on-board sensors; determine target fusion weights corresponding to each of the on-board sensors based on the environmental information; fuse the plurality of road surface information based on the target fusion weights to determine an identification result of the road surface on which the vehicle is traveling; and, if the identification result indicates an abnormal area on the road surface, generate road surface warning information related to the abnormal area and upload the road surface warning information to the cloud;

[0037] The cloud is used to determine the target vehicle according to the road surface warning information and perform road surface abnormality warning control on the target vehicle.

[0038] In a fourth aspect, the present application further provides a vehicle comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described above when executing the computer program.

[0039] In a fifth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0040] In a sixth aspect, the present application also provides a computer program product, comprising a computer program, which implements the steps of any of the methods described above when executed by a processor.

[0041] The above-mentioned road abnormality warning method, system, computer equipment, computer-readable storage medium and computer program product obtain the environmental information of the vehicle's driving and the road surface information monitored by different types of on-board sensors, adaptively determine the target fusion weight of each on-board sensor according to the environmental information, fuse the multiple road surface information based on the target fusion weight, and determine the identification result of the road surface on which the vehicle is driving. This method can accurately determine the identification result of the vehicle's driving road surface based on environmental perception and on-board sensors and obtain the actual road conditions of the driving road surface in real time. In the case of abnormalities in the actual road conditions, the information can be uploaded to the cloud, and the cloud can perform road abnormality warning control on other target vehicles based on the reported road warning information, so that the target vehicle can obtain abnormal road conditions in a timely manner, thereby ensuring driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A diagram showing an application environment of a road anomaly warning method in one embodiment;

[0044] Figure 2 1 is a flow chart of a road abnormality warning method according to an embodiment;

[0045] Figure 3 204 is a flow chart of step 204 in one embodiment;

[0046] Figure 4 A schematic flow chart of a road abnormality warning method in another embodiment;

[0047] Figure 5 A schematic flow chart of a road abnormality warning method in another embodiment;

[0048] Figure 6 is a timing diagram of a road abnormality warning method in one embodiment;

[0049] Figure 7 is a structural block diagram of a road abnormality warning system in one embodiment;

[0050] Figure 8 FIG. 1 is a diagram of the internal structure of a vehicle in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0052] Conventional technologies primarily rely on manual inspections or fixed monitoring equipment to detect road anomalies, which can lead to significant response delays and limited coverage. While some onboard systems can detect road conditions, they lack inter-vehicle coordination mechanisms, preventing subsequent vehicles from timely monitoring of road conditions ahead, posing a significant safety hazard.

[0053] In view of this, in order to improve the timeliness and accuracy of road abnormality warning and ensure driving safety, a road abnormality warning method is proposed. The road abnormality warning method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, vehicle 102, cloud 104, and target vehicle 106 communicate via a network. A data storage system can store data to be processed by vehicle 102 and / or cloud 104. The data storage system can be integrated with vehicle 102 or cloud 104, or placed on another network server.

[0054] The vehicle-side 102 obtains environmental information about the vehicle and road surface information monitored by various types of onboard sensors; determines target fusion weights corresponding to each onboard sensor based on the environmental information; fuses multiple road surface information based on the target fusion weights to determine an identification result of the road surface on which the vehicle is traveling; and if the identification result indicates an abnormal area on the road surface, generates road surface warning information related to the abnormal area and uploads the road surface warning information to the cloud, so that the cloud can identify the target vehicle based on the road surface warning information and perform road surface abnormality warning control on the target vehicle. The vehicle-side 102 and the target vehicle-side 106 can be, but are not limited to, different types of vehicles.

[0055] In an exemplary embodiment, Figure 2 As shown, a road abnormality warning method is provided, which is applied to Figure 1 Taking the vehicle in FIG. 1 as an example, the method includes the following steps 202 to 208. Among them:

[0056] Step 202: Acquire vehicle driving environment information and road surface information monitored by different types of vehicle-mounted sensors.

[0057] The vehicle is equipped with various types of onboard sensors, including inertial measurement unit (IMU) sensors, visual sensors, and radar sensors. Radar sensors can be of different types, such as lidar and millimeter-wave radar. Visual sensors can be of different types of cameras. Optionally, the vehicle is equipped with an IMU, a camera, and a radar. Environmental information about the vehicle's driving environment can include brightness information and / or rainfall.

[0058] Furthermore, the inertial measurement unit (IMU) sensor can determine the degree of road bumps based on the vehicle body vibration intensity value. Visual sensors can identify road anomalies based on road imagery, such as "70% crack probability" or "pothole detected." Radar can determine road elevation changes based on detected data. For example, millimeter-wave radar can detect a sudden 10-centimeter drop in the road surface two meters ahead. Determining road surface information monitored by different types of on-board sensors can be accomplished using existing methods and will not be elaborated on here.

[0059] Step 204 : Determine the target fusion weight corresponding to each vehicle-mounted sensor according to the environmental information.

[0060] The detection performance of each onboard sensor varies in different environmental conditions. For example, when the brightness is below a preset level, the detection performance of the visual sensor will decrease, and the detection reliability will be lower than that of the radar. When the rainfall exceeds the preset level, such as during a downpour, the detection results of the inertial measurement unit sensor will be affected by the heavy rain, which will have a certain impact on the detection results. To ensure the reliability of the detection results, the target fusion weights corresponding to each onboard sensor can be adaptively adjusted based on environmental information.

[0061] For example, the target fusion weights corresponding to the vehicle-mounted sensors corresponding to the environmental information can be determined from a preset data table according to the environmental information. The preset data table includes the target fusion weights corresponding to the vehicle-mounted sensors under different environmental information.

[0062] Step 206 , fusing the multiple road surface information according to the target fusion weight to determine the recognition result of the vehicle driving road surface.

[0063] The sum of the target fusion weights is a preset value, which may be, but is not limited to, 1. In this embodiment, the preset value is 1. By fusing multiple road surface information, a road surface anomaly confidence level corresponding to each road surface information level can be determined. The road surface anomaly confidence level is used to characterize the degree of road surface anomaly.

[0064] For example, the road anomaly confidence level for each target fusion weight is determined. The road anomaly confidence levels are then fused based on the target fusion weights to generate a comprehensive confidence level. This comprehensive confidence level is then used to determine the road surface identification result for the vehicle. The identification results include the presence and absence of abnormal areas. If an abnormal area exists, further determination is required to determine whether a warning is required. An abnormal area can be a road surface where characteristics do not meet pre-defined normal road characteristics, such as bumps or collapses.

[0065] For example, if the comprehensive confidence after fusion processing is <0.4, the road surface is judged to be normal; if 0.4<comprehensive confidence<0.9, it is judged to be ordinary bumps (i.e., no warning is required); if the comprehensive confidence is >0.9, it is judged to be a dangerous collapse (i.e., a warning is required).

[0066] In step 208, when the identification result shows that there is an abnormal area on the driving road, road warning information related to the abnormal area is generated and uploaded to the cloud, so that the cloud can determine the target vehicle based on the road warning information and perform road abnormality warning control on the target vehicle.

[0067] The road surface warning information includes at least the coordinates of the abnormal area, an image of the abnormal area, the danger level, and a timestamp. The timestamp may be the time when the abnormal area was identified. Uploading the road surface warning information to the cloud may involve encrypting the road surface warning information and uploading the encrypted road surface warning information to the cloud. If the abnormal area is identified, further determination is made as to whether the alarm threshold is exceeded. If so, a dangerous collapse is determined, requiring an alert, and road surface warning information related to the abnormal area is generated.

[0068] For example, when the identification result shows that there is an abnormal area on the driving road and an early warning is required, road warning information related to the abnormal area is generated, and the road warning information is encrypted and uploaded to the cloud, so that the cloud can determine the target vehicle based on the road warning information and perform road abnormality early warning control on the target vehicle.

[0069] Furthermore, the cloud determines the target vehicle within a preset range based on the acquired road warning information and the position of the vehicle as a reference point. The target vehicle may be the vehicle behind the vehicle. The cloud generates a strip fence extending along the road based on the position information in the road warning information and the acquired road topology data of the driving road. The strip fence can be dynamically adjusted according to the real-time road network data, for example, to support temporary topology changes such as construction diversion.

[0070] When the cloud detects that the target vehicle enters the strip fence, the warning strategy associated with the road warning information will be pushed to the target vehicle, and the abnormal area will be displayed on the display terminal of the target vehicle; if the target vehicle is detected to stay in the strip fence for longer than the preset time, the target vehicle will be controlled to play the warning information; the warning information may include the location information of the abnormal area; if the relative distance between the target vehicle and the abnormal area is detected to be not within the preset safety distance range, the target vehicle will be controlled to travel at the preset safety speed and the target vehicle's hazard lights and alarm system will be triggered.

[0071] In the above-mentioned road abnormality warning method, by obtaining the environmental information of the vehicle and the road surface information monitored by different types of on-board sensors, the target fusion weight of each on-board sensor is adaptively determined according to the environmental information, and the multiple road surface information are fused based on the target fusion weight to determine the identification result of the vehicle's driving road surface. This method can accurately determine the identification result of the vehicle's driving road surface based on environmental perception and on-board sensors and obtain the actual road conditions of the driving road surface in real time. In the case of abnormalities in the actual road conditions, the information can be uploaded to the cloud, and the cloud can perform road abnormality warning control on other target vehicles based on the reported road warning information, so that the target vehicle can obtain abnormal road conditions in time to ensure driving safety.

[0072] The following provides an implementation method for adaptively adjusting the weight of the vehicle-mounted sensors according to the environmental information. In an exemplary embodiment, Figure 3 As shown, step 204 includes steps 302 to 306. Among them:

[0073] Step 302 : Determine, from the vehicle-mounted sensors, a first vehicle-mounted sensor whose fusion weight is positively correlated with the environmental information, and a second vehicle-mounted sensor whose fusion weight is negatively correlated with the environmental information.

[0074] The positive or negative correlation between environmental information and onboard sensors can be determined based on historical data or preset. For example, if environmental information includes brightness and rainfall information, for example, brightness greater than a preset brightness indicates daytime or sunny weather, brightness less than a preset brightness indicates nighttime, and rainfall greater than a preset rainfall indicates heavy rain. As the brightness transitions from nighttime to daytime, the fusion weights of onboard sensors with positive correlations can be increased by a preset value, while the fusion weights of onboard sensors with negative correlations can be decreased by a preset value.

[0075] The first and second vehicle-mounted sensors include at least one of an inertial measurement unit (IMU), a visual sensor, and a radar sensor. It should be noted that the first and second vehicle-mounted sensors may be different for the same environmental information. This example uses a camera as the visual sensor and a millimeter-wave radar as the radar sensor.

[0076] Step 304 : According to the environmental information and the positive correlation, the fusion weight of the first vehicle-mounted sensor is adjusted to obtain a corresponding target fusion weight.

[0077] Optionally, based on the environmental information and the positive correlation, the fusion weight of the first vehicle-mounted sensor is increased according to a first preset adjustment ratio to obtain a corresponding target fusion weight.

[0078] Step 306 : According to the environmental information and the negative correlation, the fusion weight of the second vehicle-mounted sensor is adjusted to obtain a corresponding target fusion weight.

[0079] Optionally, based on the environmental information and the negative correlation, the fusion weight of the second vehicle-mounted sensor is reduced according to a second preset adjustment ratio to obtain a corresponding target fusion weight. The absolute values ​​of the first preset adjustment ratio and the second preset adjustment ratio may be equal or unequal.

[0080] For example, the vehicle's IMU sensor monitors abnormal vehicle body vibrations, a camera captures road surface images, and a millimeter-wave radar detects changes in road height. Fusion weights are adaptively adjusted based on weather conditions. At night or in low light, if the first onboard sensor includes radar and the second onboard sensor includes a camera, the camera weight is reduced and the radar weight is increased. In heavy rain, if the first onboard sensor includes a camera and radar and the second onboard sensor includes an onboard IMU sensor, vibration detection is disabled, the radar and camera weights are increased, and radar + vision fusion is relied upon. In sunny / daytime conditions, the onboard IMU sensor remains unchanged, the first onboard sensor includes a camera and the second onboard sensor includes a radar, and the camera weight is increased and the radar weight is decreased.

[0081] For example, in nighttime / low-light conditions, the camera's weight is reduced to 20%, the radar's weight is increased to 50%, and the vehicle's IMU sensor remains unchanged at 30%. In sunny / daytime conditions, the vehicle's IMU sensor remains unchanged at 30%, the camera's weight is increased to 50%, and the radar's weight is reduced to 20%. In heavy rain, the vehicle's IMU sensor weight is reduced to 0, the radar's weight is increased to 60%, and the camera's weight is increased to 40%.

[0082] It is understood that different types of sensors have corresponding initial fusion weights, and the initial fusion weights can be equal, and the sum of the initial fusion weights can be 1. In addition, in nighttime / low light conditions, infrared fill light can be used to increase brightness.

[0083] In this embodiment, by adaptively adjusting the target fusion weights of each vehicle-mounted sensor according to environmental information, the accuracy and reliability of the recognition results of the road surface recognition can be ensured, and errors caused by changes in environmental information can be avoided.

[0084] In an exemplary embodiment, the road surface information is fused according to the target fusion weight to determine the recognition result of the vehicle driving road surface, including:

[0085] Determine the road anomaly confidence level of each acquired road surface information, perform fusion processing based on the target fusion weight and the corresponding road anomaly confidence level to obtain a comprehensive confidence level; and determine the identification result of the vehicle's driving road surface based on the comprehensive confidence level. The fusion processing method may be to first multiply each target fusion weight and the corresponding road anomaly confidence level to obtain a product, and then perform weighted processing on each product to obtain a comprehensive confidence level. It is understandable that the fusion processing can also be achieved through other existing methods, which will not be elaborated here. This weighted fusion method can refer to the road surface detection results under different modes, and adaptively adjust the target fusion weights of different sensors based on environmental information to ensure the accuracy and reliability of road surface detection.

[0086] It is understandable that since the road surface may have conditions similar to abnormal road surfaces, in order to avoid false detection of road surface abnormalities, before reporting road surface abnormality warning information, it is necessary to detect whether the abnormal area is a preset false alarm point.

[0087] In an exemplary embodiment, when the identification result indicates that an abnormal area exists on the driving road surface, generating road surface warning information related to the abnormal area and uploading the road surface warning information to the cloud includes:

[0088] When the recognition result shows that there is an abnormal area on the driving road surface, the road section characteristics of the driving road surface are determined based on the road surface information; if the road section characteristics do not exist in the preset road section characteristic database, it is determined that the abnormal area on the driving road surface is not a preset false alarm point; the location information of the abnormal area, the danger level of the abnormal area and the timestamp are determined, and road surface warning information related to the abnormal area is generated, and the road surface warning information is uploaded to the cloud.

[0089] The preset road section feature database can be stored in the cloud. Optionally, if the location information of the abnormal area does not exist in the preset road section feature database, and the road section features corresponding to the location information are different from the road section features of the driving road surface determined by each road surface information, then the abnormal area of ​​the driving road surface is determined not to be a preset false alarm point. If it is not a preset false alarm point, that is, if the identification result is that there is an abnormal area on the driving road surface, the location information of the abnormal area, the danger level of the abnormal area, and the timestamp are determined, and road surface warning information related to the abnormal area is generated and uploaded to the cloud. Furthermore, if it is determined based on the comprehensive confidence that it is greater than the alarm threshold and a warning is required, the road surface warning information is uploaded to the cloud, and the cloud generates a warning strategy based on the reported road surface warning information. The warning strategy includes at least the image and location information of the abnormal area and the planned avoidance path.

[0090] Furthermore, if it is determined that the abnormal area of ​​the driving road is not a preset false alarm point, a secondary verification can be performed through manual verification. If it is determined that the abnormal area of ​​the driving road is not a preset false alarm point, but is determined to be a newly added false alarm point, the preset road section feature database is updated. At this time, the vehicle can be controlled to reduce the detection sensitivity of the on-board sensor in the abnormal area, and the detection sensitivity of the on-board sensor can be restored when the vehicle travels out of the abnormal area. It should be noted that reducing the detection sensitivity of the on-board sensor can be achieved through existing methods and will not be elaborated here. Optionally, when the abnormal area of ​​the driving road is determined to be a preset false alarm point, the detection sensitivity of the false alarm location is reduced.

[0091] A road feature database is established for locations that frequently experience false alarms (such as speed bumps). During driving, the vehicle compares this information to the database. If a feature point is found in the database, it is identified as a prone false alarm point, and the sensor's detection sensitivity is proactively reduced, establishing self-learning capabilities to avoid false alarms. It should also be noted that after uploading road warning information to the cloud, the cloud can verify whether the uploaded abnormal area is a pre-set false alarm point based on the pre-set road feature database. The specific processing method is the same as that on the vehicle side and is not detailed here.

[0092] In the above method, the recognition result of the vehicle driving road surface is based on the preset road section feature database to detect whether it is a preset false alarm location, and the false alarm rate can be reduced through self-learning ability.

[0093] In the above-mentioned embodiment method, the road condition of the driving road is identified by the vehicle to determine the identification result of the driving road. When the identification result shows that there is an abnormal area on the driving road, road warning information related to the abnormal area is generated and the road warning information is uploaded to the cloud. The cloud can warn and control the vehicles coming from behind and within the preset range based on the reported road warning information to ensure the driving safety of the vehicles coming from behind and within the preset range.

[0094] In an exemplary embodiment, Figure 4 As shown, a road abnormality warning method is provided, which is applied to Figure 1 The cloud in FIG is taken as an example to illustrate, including the following steps 402 to 404. Among them:

[0095] Step 402: Obtain road warning information sent by the vehicle.

[0096] The road surface warning information may be determined based on any of the above-mentioned road abnormality warning methods.

[0097] Step 404: If a target vehicle is detected within the preset range of the vehicle according to the road warning information, road abnormality warning control is performed on the target vehicle according to the road warning information to ensure safe driving of the target vehicle.

[0098] It is understood that under normal circumstances, the vehicle reports its coordinates in real time through the GPS / Beidou positioning module, wherein the reporting frequency is a preset frequency, which is adjustable. For example, under normal circumstances, the preset frequency is once every 10 seconds.

[0099] For example, after receiving road warning information, the cloud generates a roadside fence based on the location of the abnormal area in the warning information and the acquired road topology data. It then monitors vehicles within a preset range. If a target vehicle is detected within the preset range, the cloud obtains the target vehicle's real-time coordinates. If the target vehicle enters the fence based on the real-time coordinates, the cloud pushes the warning strategy associated with the road warning information to the target vehicle and displays the abnormal area on the target vehicle's display terminal. The warning strategy includes image information of the abnormal area, the abnormal area's location information, and a driving path to avoid the abnormal area.

[0100] The above-mentioned road abnormality warning method obtains the environmental information of the vehicle's driving and the road surface information monitored by different types of on-board sensors, adaptively determines the target fusion weight of each on-board sensor according to the environmental information, and fuses the multiple road surface information based on the target fusion weight to determine the identification result of the road surface on which the vehicle is driving. This method can accurately determine the identification result of the vehicle's driving road surface based on environmental perception and on-board sensors and obtain the actual road conditions of the driving road surface in real time. In the case of abnormalities in the actual road conditions, it can be uploaded to the cloud, and the cloud can perform road abnormality warning control on other target vehicles based on the reported road warning information, so that the target vehicle can obtain abnormal road conditions in time, thereby ensuring driving safety.

[0101] It should be noted that under normal circumstances, the vehicle reports its coordinates in real time through the GPS / Beidou positioning module at a preset reporting frequency. However, in the event of abnormal differences, in order to better monitor the movements of the target vehicle, the reporting frequency is adjusted to better monitor the target vehicle.

[0102] In an exemplary embodiment, before detecting that the target vehicle enters the strip fence of the road warning information, the method further includes:

[0103] Acquire the real-time location data of the target vehicle; determine the relative distance between the target vehicle and the strip fence based on the real-time location data; and adjust the reporting frequency of the target vehicle's location data based on the relative distance, wherein the reporting frequency and the relative distance satisfy a positive correlation.

[0104] For example, if the target vehicle is within a certain range from the fence boundary (for example, 50 meters, and the distance can be adjusted according to actual needs), once the conditions are met, the vehicle will speed up reporting its position from every 10 seconds to every 2 seconds, ensuring that the cloud can track the vehicle's movements more accurately and push warning information in a timely manner.

[0105] Optionally, in an exemplary embodiment, performing road abnormality warning control on a target vehicle according to road surface warning information to ensure safe driving of the target vehicle includes:

[0106] Acquire road topology data for the road surface; generate a strip fence extending along the road based on the location of the abnormal area in the road warning information and the road topology data of the road surface; acquire the real-time location data of the target vehicle; and if the target vehicle enters the strip fence based on the real-time location data, push the warning strategy associated with the road warning information to the target vehicle and display the abnormal area on the target vehicle's display terminal. This method can promptly transmit the abnormal area information to the target vehicle, allowing the target vehicle to avoid it in time and ensure driving safety.

[0107] Furthermore, to ensure the safety of the target vehicle, if it is detected that the target vehicle has been inside the fence for longer than a preset time, the target vehicle will be controlled to play a warning strategy. The duration exceeding the preset time can be a threshold (for example, 5 minutes) where the warning level is upgraded and the vehicle's computer voice broadcasts the warning information, i.e., the warning strategy. In this approach, if the target vehicle stays inside the fence for longer than the preset time, the vehicle's computer voice broadcasts the warning strategy to alert the driver.

[0108] Optionally, if the relative distance between the target vehicle and the abnormal area is detected to be outside a preset safe distance range, the target vehicle is controlled to travel at a preset safe speed, and the target vehicle's hazard lights and alarm system are triggered. The preset safe speed limit can include limiting the vehicle's speed to 50% of the current road speed limit, while also triggering the vehicle-side hazard lights and alarm system to alert vehicles behind. This approach ensures the driving safety of the target vehicle and other vehicles through active speed limiting.

[0109] In an exemplary embodiment, a flowchart based on the above-mentioned road abnormality warning method is provided, such as Figure 5 As shown, including:

[0110] The vehicle is equipped with various sensors, which are controlled to monitor road conditions and obtain environmental information. The sensors' cameras detect road collapse, radar scans detect road elevation differences, and the IMU monitors vehicle vibrations. This information is then used to generate road surface information from each sensor. Multi-sensor fusion is then performed based on this information. To further ensure the reliability of the results, the target fusion weights of each sensor are adaptively adjusted based on the acquired environmental information. For example, the target fusion weights of each sensor are adaptively assigned based on the current weather conditions. For example, if the weather is sunny, the weight of the IMU sensor is adjusted to 30%, the weight of the camera to 50%, and the weight of the radar to 20%. If the weather is nighttime or low light, the weight of the IMU sensor is adjusted to 30%, the weight of the camera to 50%, and the weight of the radar to 20%. If the weather is rainy, the weight of the IMU sensor is turned off, with the weight of the camera to 0 and the weight of the camera to 60%. The multiple road surface information is fused according to the target fusion weight to determine the recognition result of the vehicle driving road surface.

[0111] If the identification result indicates an abnormal area on the road surface, the system determines the road section characteristics based on the road surface information. It then queries the preset road section characteristics database to determine whether the road section characteristics exist. If not, it determines that the abnormal area on the road surface is not a preset false alarm point. The system then determines whether the alarm threshold is exceeded based on the comprehensive confidence level. If the alarm threshold is exceeded, the system determines the location information, danger level, and timestamp of the abnormal area, generates road surface warning information related to the abnormal area, and uploads the road surface warning information to the cloud. If the calculated comprehensive confidence level does not exceed the alarm threshold, the on-board sensors are controlled to continue detection.

[0112] If so, the abnormal area of ​​the road surface is determined to be a preset false alarm point, and the detection sensitivity of the vehicle-mounted sensor at the preset false alarm point is reduced.

[0113] It should be noted that the specific implementation of this embodiment can be achieved through the above-mentioned limited methods, which will not be elaborated here.

[0114] In the above embodiment, on-board sensors acquire road information. By dynamically adjusting the fusion weights of each on-board sensor based on environmental information, any abnormal road information detected is uploaded to the cloud. The cloud then identifies the target vehicle based on the road warning information and initiates road anomaly warning control for the target vehicle, preventing other vehicles from being unaware of the road conditions ahead and reducing driving risks. This approach, through the technical process of environmental perception → data fusion → dynamic fencing → closed-loop optimization, addresses the technical issues of high false alarm rates, inaccurate warning coverage, and a lack of self-learning capabilities.

[0115] In an exemplary embodiment, a timing diagram based on the above-mentioned road abnormality warning method is provided, such as Figure 6 As shown, the sequence diagram includes the vehicle terminal, the cloud, and other vehicles. The target vehicle is determined based on other vehicles, and the vehicle terminal is mounted on the vehicle. Specifically, it includes the following:

[0116] The vehicle obtains driving environment information and road surface information monitored by different types of on-board sensors; determines the target fusion weight corresponding to each on-board sensor based on the environmental information; fuses multiple road surface information based on the target fusion weight to determine the identification result of the vehicle's driving road surface; if the identification result is that there is an abnormal area on the driving road surface, generates road surface warning information related to the abnormal area and uploads the road surface warning information to the cloud, where the warning information may include location information and image information of the abnormal area.

[0117] After receiving the reported road warning information, the cloud generates a strip fence, also known as a strip electronic fence, based on the location information of the abnormal area. Other vehicles normally report their real-time location information at a preset reporting frequency. The cloud uses this real-time location information to identify the target vehicle within the preset range. As the target vehicle approaches the strip fence, the reporting frequency is adjusted to increase. For example, under normal driving conditions, the reporting frequency is once every 10 seconds. When the relative distance between the target vehicle and the strip fence is within the preset distance, that is, when the target vehicle is close to the strip fence, the reporting frequency is reduced to once every 2 seconds.

[0118] When a target vehicle is detected entering a strip fence, the warning strategy associated with the road warning information will be pushed to the target vehicle, and the abnormal area will be displayed on the target vehicle's display terminal. For example, when entering a strip fence for the first time, the cloud will push a warning strategy including the image, location, and recommended detour route of the abnormal area to the target vehicle.

[0119] If the target vehicle is detected to have stayed within the strip fence for longer than a preset time, the target vehicle will be controlled to play a warning strategy. For example, if the stay time exceeds five minutes, the vehicle will play a voice warning strategy. If the relative distance between the target vehicle and the abnormal area is detected to be outside the preset safe distance range, the target vehicle will be controlled to travel at a preset safe speed and trigger the target vehicle's hazard lights and alarm system. For example, when the target vehicle approaches the abnormal area, the target vehicle's speed is reduced to 50% of the current road speed limit, and the target vehicle's hazard lights and alarm system are triggered. The reporting frequency of the target vehicle within the strip fence can remain unchanged.

[0120] In the above embodiment, on-board sensors are used to obtain road surface information, and the identification result of the vehicle's driving road surface is determined by dynamically adjusting the fusion weights of each on-board sensor according to environmental information. When abnormal road surface information is detected, road surface warning information is uploaded to the cloud. The cloud determines the target vehicle based on the road surface warning information and monitors the target vehicle in a timely manner. The distance between the target vehicle and the strip fence is monitored to determine different road surface abnormality warning control methods. The target vehicle is controlled in a progressive manner to provide sufficient time for the target vehicle to avoid the abnormal area, ensuring driving safety. This method can avoid the current vehicle from identifying abnormal road conditions ahead, and can notify other vehicles in a timely manner so that other vehicles can know the road conditions ahead in a timely manner, reducing driving risks.

[0121] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0122] Based on the same inventive concept, embodiments of the present application also provide a road anomaly warning system for implementing the aforementioned road anomaly warning method. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more road anomaly warning system embodiments provided below can be found in the aforementioned limitations of the road anomaly warning method and will not be further elaborated here.

[0123] In an exemplary embodiment, Figure 7 As shown, a road abnormality warning system is provided, which includes a vehicle, a cloud and a target vehicle, and the vehicle includes a controller, wherein:

[0124] The controller is configured to obtain information about the vehicle's driving environment and road surface information monitored by various types of on-board sensors; determine target fusion weights corresponding to each on-board sensor based on the environmental information; fuse multiple road surface information based on the target fusion weights to determine an identification result of the vehicle's driving road surface; and, if the identification result indicates an abnormal area on the driving road surface, generate road surface warning information related to the abnormal area and upload the road surface warning information to the cloud;

[0125] The cloud is used to identify the target vehicle based on road warning information and to perform road abnormality warning control on the target vehicle.

[0126] The above-mentioned road abnormality warning system obtains the environmental information of the vehicle's driving and the road surface information monitored by different types of on-board sensors, adaptively determines the target fusion weight of each on-board sensor according to the environmental information, and fuses the multiple road surface information based on the target fusion weight to determine the identification result of the road surface on which the vehicle is driving. This method can accurately determine the identification result of the vehicle's driving road surface based on environmental perception and on-board sensors and obtain the actual road conditions of the driving road surface in real time. In the case of abnormalities in the actual road conditions, it can be uploaded to the cloud, and the cloud can perform road abnormality warning control on other target vehicles based on the reported road warning information, so that the target vehicle can obtain abnormal road conditions in time, thereby ensuring driving safety.

[0127] In an exemplary embodiment, the controller is further configured to determine, from the vehicle-mounted sensors, a first vehicle-mounted sensor whose fusion weight is positively correlated with the environmental information, and a second vehicle-mounted sensor whose fusion weight is negatively correlated with the environmental information;

[0128] According to the environmental information and the positive correlation, the fusion weight of the first vehicle-mounted sensor is adjusted to obtain the corresponding target fusion weight;

[0129] According to the environmental information and the negative correlation, the fusion weight of the second vehicle-mounted sensor is adjusted to obtain the corresponding target fusion weight.

[0130] In an exemplary embodiment, the controller is further configured to determine a road surface anomaly confidence level of each road surface information acquired, and perform fusion processing based on a target fusion weight and a corresponding road surface anomaly confidence level to obtain a comprehensive confidence level;

[0131] The recognition result of the vehicle driving road is determined based on the comprehensive confidence level.

[0132] In an exemplary embodiment, the controller is further configured to determine a road section feature of the driving road according to each road surface information;

[0133] If the road section feature does not exist in the preset road section feature database, determining that the abnormal area of ​​the driving road surface is not a preset false alarm point;

[0134] When the recognition result shows that there is an abnormal area on the driving road, the location information, danger level and timestamp of the abnormal area are determined, road surface warning information related to the abnormal area is generated, and the road surface warning information is uploaded to the cloud.

[0135] In an exemplary embodiment, the cloud is further used to obtain road topology data of the driving road surface; based on the location information of the abnormal area in the road warning information and the road topology data of the driving road surface, a strip fence extending along the road surface is generated;

[0136] Obtain real-time location data of the target vehicle;

[0137] When the target vehicle is detected to have entered the strip fence based on the real-time location data, the warning strategy associated with the road warning information will be pushed to the target vehicle, and the abnormal area will be displayed on the display terminal of the target vehicle.

[0138] In an exemplary embodiment, the cloud is further configured to control the target vehicle to play a warning strategy if it is detected that the target vehicle has stayed at the strip fence for longer than a preset time;

[0139] If the relative distance between the target vehicle and the abnormal area is detected to be outside the preset safety distance range, the target vehicle will be controlled to travel at a preset safety speed and the hazard lights and alarm system of the target vehicle will be triggered.

[0140] In an exemplary embodiment, the cloud is further configured to determine a relative distance between the target vehicle and the strip fence based on the real-time location data;

[0141] The reporting frequency of the target vehicle's location data is adjusted according to the relative distance, and the reporting frequency and the relative distance satisfy a positive correlation.

[0142] Each module in the aforementioned road anomaly warning system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0143] In an exemplary embodiment, a vehicle is provided. The vehicle may be a terminal, and its internal structure may be as shown in FIG. Figure 8As shown. The vehicle includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input system. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input system are connected to the system bus via the input / output interface. The vehicle's processor is used to provide computing and control capabilities. The vehicle's memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The vehicle's communication interface is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a road anomaly warning method. The vehicle's display unit is used to form a visually visible image and can be a display screen, a projection system, or a virtual reality imaging system. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input system of the vehicle can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0144] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific vehicle may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0147] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0150] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A road abnormality warning method, characterized in that: The method comprises: Obtain vehicle driving environment information and road surface information monitored by different types of vehicle-mounted sensors; Determining the target fusion weight corresponding to each of the on-board sensors according to the environmental information; fusing the plurality of road surface information according to the target fusion weight to determine an identification result of the road surface on which the vehicle is traveling; When the recognition result indicates that there is an abnormal area on the driving road, road surface warning information related to the abnormal area is generated and uploaded to the cloud, so that the cloud can determine the target vehicle based on the road surface warning information and perform road surface abnormality warning control on the target vehicle.

2. The method according to claim 1, characterized in that The determining, according to the environmental information, the target fusion weight corresponding to each of the vehicle-mounted sensors includes: Determine, from the on-board sensors, a first on-board sensor whose fusion weight is positively correlated with the environmental information, and a second on-board sensor whose fusion weight is negatively correlated with the environmental information; adjusting the fusion weight of the first vehicle-mounted sensor according to the environmental information and the positive correlation to obtain a corresponding target fusion weight; According to the environmental information and the negative correlation, the fusion weight of the second vehicle-mounted sensor is adjusted to obtain a corresponding target fusion weight.

3. The method according to claim 1, characterized in that The fusing the road surface information according to the target fusion weight to determine the recognition result of the vehicle driving road surface includes: Determining a road surface anomaly confidence level of each of the road surface information, and performing fusion processing based on the target fusion weight and the corresponding road surface anomaly confidence level to obtain a comprehensive confidence level; The recognition result of the vehicle driving road surface is determined according to the comprehensive confidence level.

4. The method according to claim 1, wherein When the recognition result indicates that an abnormal area exists on the driving road surface, generating road surface warning information related to the abnormal area and uploading the road surface warning information to the cloud includes: If the recognition result indicates that an abnormal area exists on the driving road surface, determining a section feature of the driving road surface according to each of the road surface information; If the road section feature does not exist in the preset road section feature database, determining that the abnormal area of ​​the driving road surface is not a preset false alarm point; Determine the location information of the abnormal area, the danger level of the abnormal area, and a timestamp, generate road surface warning information related to the abnormal area, and upload the road surface warning information to the cloud.

5. A road abnormality warning method, characterized in that: The method comprises: Obtaining road surface warning information sent by the vehicle; the road surface warning information is determined according to the method according to any one of claims 1 to 4; According to the road surface warning information, if it is detected that there is a target vehicle within the preset range of the vehicle, road surface abnormality warning control is performed on the target vehicle according to the road surface warning information to ensure safe driving of the target vehicle.

6. The method according to claim 5, characterized in that The performing road abnormality warning control on the target vehicle according to the road surface warning information so as to enable the target vehicle to travel safely includes: Obtain road topology data of the driving road; generating a strip fence extending along the road based on the position information of the abnormal area in the road warning information and the road topology data of the driving road; Obtaining real-time location data of the target vehicle; When it is detected according to the real-time position data that the target vehicle enters the strip fence, the warning strategy associated with the road warning information is pushed to the target vehicle, and the abnormal area is displayed on the display terminal of the target vehicle.

7. The method according to claim 6, characterized in that The method further comprises: If it is detected that the target vehicle stays at the strip fence for longer than a preset time, the target vehicle is controlled to play the warning strategy; If it is monitored that the relative distance between the target vehicle and the abnormal area is not within the preset safety distance range, the target vehicle is controlled to travel at a preset safety speed and the double flash lights and alarm system of the target vehicle are triggered.

8. The method according to claim 6, characterized in that Before detecting that the target vehicle enters the strip fence of the road warning information, the method further includes: Determine the relative distance between the target vehicle and the strip fence according to the real-time position data; The reporting frequency of the position data of the target vehicle is adjusted according to the relative distance, and the reporting frequency and the relative distance satisfy a positive correlation relationship.

9. A road abnormality warning system, characterized in that: The system includes a vehicle, a cloud, and a target vehicle, wherein the vehicle includes a controller, wherein: The controller is used to obtain environmental information of the vehicle and road surface information monitored by different types of vehicle-mounted sensors; Determining the target fusion weight corresponding to each of the on-board sensors according to the environmental information; fusing the plurality of road surface information according to the target fusion weight to determine an identification result of the vehicle's road surface; if the identification result indicates that an abnormal area exists on the road surface, generating road surface warning information related to the abnormal area, and uploading the road surface warning information to the cloud; The cloud is used to determine the target vehicle according to the road surface warning information and perform road surface abnormality warning control on the target vehicle.

10. A vehicle comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images