Method, device and product for determining an assisted driving strategy

Abstract

The present disclosure provides a method and device for determining an assisted driving strategy, electronic equipment, storage medium and computer program product, relates to the technical field of computers, specifically to the technical field of intelligent driving, map navigation and the like, and can be applied to scenarios such as map navigation. The specific implementation scheme is as follows: in the navigation process, the fusion wind condition data of the subsequent navigation path is determined by combining the live wind condition data of the subsequent navigation path and the detected wind condition data of the current position of the vehicle; the influence degree of wind on the driving safety of the vehicle is determined according to the fusion wind condition data and the pose data of the vehicle in the subsequent navigation path; and the assisted driving strategy of the risk section in the subsequent navigation path is determined according to the influence degree. The present disclosure converts the wind condition from an uncontrollable factor into a variable that can be referenced in navigation to be integrated into the navigation process, determines the risk section and the assisted driving strategy for the risk section in real time, solves the crosswind interference problem in the driving process, and helps to improve the driving safety.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of intelligent driving and map navigation, and particularly to a method, device, electronic device, storage medium, and computer program product for determining an assisted driving strategy, which can be applied to scenarios such as map navigation. Background Technology

[0002] With the development of navigation technology, navigation methods that combine positioning systems with real-time traffic data have been widely used in navigation systems. However, crosswinds are frequent in high-altitude areas (such as mountainous areas and plateaus), often causing steering wheel vibrations, vehicle deviation, and even traffic accidents. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for determining an assisted driving strategy.

[0004] According to the first aspect, a method for determining an assisted driving strategy is provided, comprising: during navigation, combining real-time wind data of the subsequent navigation path with detected wind data of the vehicle's current location to determine fused wind data of the subsequent navigation path; determining the degree of wind's impact on the vehicle's driving safety based on the fused wind data and the vehicle's pose data in the subsequent navigation path; and determining the assisted driving strategy for risky road sections in the subsequent navigation path based on the degree of impact.

[0005] According to a second aspect, an apparatus for determining an assisted driving strategy is provided, comprising: a wind condition determination unit configured to, during navigation, combine real-time wind condition data of the subsequent navigation path with detected wind condition data of the vehicle's current position to determine fused wind condition data of the subsequent navigation path; a degree determination unit configured to determine the degree of wind impact on the vehicle's driving safety based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path; and a strategy determination unit configured to determine an assisted driving strategy for risky sections of the subsequent navigation path based on the degree of impact.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as described in any implementation of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing a computer to perform the method described in any implementation of the first aspect.

[0008] According to a fifth aspect, a computer program product is provided, comprising: a computer program that, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is an exemplary system architecture diagram that can be applied to an embodiment of this disclosure; Figure 2 This is a flowchart of one embodiment of the method for determining an assisted driving strategy according to the present disclosure; Figure 3 A schematic diagram illustrating an application scenario of the method for determining the assisted driving strategy according to this embodiment; Figure 4 This is a flowchart of yet another embodiment of the method for determining the assisted driving strategy according to the present disclosure; Figure 5 This is a structural diagram of one embodiment of the driver assistance strategy determination device according to the present disclosure; Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure. Detailed Implementation

[0011] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0012] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0013] Figure 1 An exemplary architecture 100 of a method and apparatus for determining assisted driving strategies that can be applied according to this disclosure is shown.

[0014] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The communication connections between terminal devices 101, 102, and 103 form a network topology. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0015] Terminal devices 101, 102, and 103 can be hardware or software that supports network connectivity for data interaction and processing. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices supporting network connectivity, information acquisition, interaction, display, and processing functions, including but not limited to in-vehicle computers, sensors, and other in-vehicle terminal devices, as well as computer terminal devices such as smartphones, tablets, e-book readers, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices. They can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are imposed here.

[0016] Server 105 can be a server that provides various services, such as a backend processing server that generates navigation routes based on navigation requests from terminal devices 101, 102, and 103, and determines risky road sections and implements assisted driving strategies for those sections by referring to wind data during navigation. As an example, server 105 could be a cloud server.

[0017] It should be noted that a server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules (such as software programs or software modules used to provide distributed services), or as a single software program or software module. No specific limitations are made here.

[0018] It should also be noted that the method for determining the assisted driving strategy provided in the embodiments of this disclosure is generally executed by a server, but the possibility of it being executed by a terminal device, or by the server and the terminal device cooperating with each other, is not excluded. Accordingly, the various parts (e.g., various units) included in the assisted driving strategy determination device can be all set in the server, all set in the terminal device, or set in the server and the terminal device respectively.

[0019] It should be understood that Figure 1The number of terminal devices, networks, and servers shown is merely illustrative. Any number of terminal devices, networks, and servers can be included depending on implementation needs. When the electronic devices on which the method for determining the driver assistance strategy runs do not require data transmission with other electronic devices, the system architecture may consist only of the electronic devices (e.g., terminal devices or servers) on which the method for determining the driver assistance strategy runs.

[0020] Please refer to Figure 2 , Figure 2 This is a schematic diagram of the data processing flow for a method of determining an assisted driving strategy provided in an embodiment of this disclosure. Flow 200 includes the following steps: Step 201: During the navigation process, combine the real-time wind data of the subsequent navigation path with the detected wind data of the vehicle's current location to determine the fused wind data of the subsequent navigation path.

[0021] In this embodiment, the execution entity of the method for determining the assisted driving strategy (e.g., Figure 1 The server can obtain real-time wind data and detected wind data remotely or locally via wired or wireless network connection. During navigation, it combines the real-time wind data of the subsequent navigation path with the detected wind data of the vehicle's current location to determine the fused wind data of the subsequent navigation path.

[0022] Real-time wind data refers to the actual wind conditions in the areas covered by the navigation path, including wind speed and direction. This data can be obtained through meteorological services, such as online weather services from meteorological bureaus and weather forecasting applications. For example, real-time wind data can be collected from weather forecasting applications via a meteorological service API (Application Programming Interface).

[0023] Wind condition data is obtained by detecting the wind conditions at the vehicle's current location, and can be obtained using wind sensors. Examples of wind sensors include mechanical anemometer-type wind direction sensors, photoelectric wind direction sensors, mechanical wind speed sensors, thermal wind speed sensors, and laser Doppler anemometers.

[0024] During navigation, real-time and detected wind data can be acquired or periodically. For example, wind data can be collected and detected every preset time interval (e.g., 5 minutes) to update the real-time wind data for the subsequent navigation path and the detected wind data for the vehicle's current location.

[0025] For real-time wind data, the aforementioned execution entity connects to the meteorological service API via a 4G / 5G network every 5 minutes to obtain wind data for the subsequent navigation path. This data is received in JSON (JavaScript Object Notation) format, containing latitude and longitude, wind speed (in meters per second), and wind direction (0-360°, with true north as 0°). The JSON data is decoded into a two-dimensional array, with array indices corresponding to grid coordinates. For example, array index [i,j] represents the grid cell located in row i and column j.

[0026] As an example, based on fluid mechanics principles, a wind propagation model is constructed for different terrains and environments, considering factors such as terrain undulations and building obstruction. Real-time wind data is used as the initial field and boundary conditions of the propagation model, combined with geographical information along the navigation path, to perform spatiotemporal simulations of the wind conditions. The detected wind data at the current location is used as a real-time correction factor for the propagation model, adjusting the wind conditions of the subsequent navigation path predicted by the model. Finally, by combining the physical model simulation results and the real-time corrected data, the fused wind data for the subsequent navigation path is determined.

[0027] By modeling wind propagation patterns using physical models and integrating real-time wind data from meteorological services with wind sensor data, the accuracy and physical plausibility of wind forecasts are improved. In areas with complex terrain and limited meteorological data resolution, wind conditions for subsequent navigation paths can be more accurately predicted based on physical principles, reducing prediction biases caused by data sparsity or inaccuracy and providing more reliable wind condition warnings for vehicles.

[0028] Specifically, firstly, an intelligent terrain-wind field coupling model is constructed. Based on the principles of CFD (Computational Fluid Dynamics), an intelligent and adaptive wind field propagation model is built. This model not only considers the basic fluid dynamics equations but also incorporates the coupling effects of terrain and environmental factors. Deep learning algorithms are used to train the wind field propagation model, enabling it to automatically identify and adapt to the impact of different terrain and environmental features on the wind field. For example, in mountainous areas, the wind field propagation model can learn the blocking and guiding effects of mountains on the wind; in urban areas, it can identify the shading effect of buildings and the wind tunnel effect. The model training data includes historical meteorological data, geographic information data, and historical detection data from wind sensors, improving the model's accuracy and adaptability through a data-driven approach.

[0029] Then, spatiotemporal extrapolation and dynamic correction are performed based on real-time wind data and detected wind data. Real-time wind data is used as the initial field and boundary conditions of the model, combined with geographical information along the navigation path, to perform high-precision spatiotemporal extrapolation and predict wind conditions along the subsequent navigation path. Detected wind data from wind sensors is received in real-time and used as a real-time correction factor for the model. A dynamic weight adjustment algorithm automatically adjusts the weights of the detected wind data and the model's predicted data during the fusion process based on the difference. For example, when the deviation between the wind sensor data and the model's predicted data is large, the weight of the detected wind data is increased to quickly correct the model's prediction results. A correction mechanism based on the PSO (Particle Swarm Optimization) algorithm is introduced to optimize the wind field propagation model parameters in real time, ensuring that the wind field propagation model can quickly adapt to wind field changes and improve the accuracy and reliability of predictions.

[0030] As another example, firstly, real-time wind data along the subsequent navigation path is collected, including wind speed and direction at different times and locations, forming a meteorological service dataset. Secondly, wind condition data detected by the vehicle over a continuous period up to its current location is collected and compiled into a time series. Then, a data assimilation algorithm is used to fuse the wind condition data detected by the wind sensors with the real-time wind condition data from the meteorological service. The data assimilation algorithm, based on Bayesian estimation theory, aims to minimize the difference between the two to find the most likely true wind condition. During the assimilation process, the weights of the two data are dynamically adjusted according to their uncertainty and correlation. For detected wind condition data, higher weights are assigned if the sensor accuracy is high and the temporal and spatial matching with the meteorological service data is good; conversely, lower weights are assigned to data with greater uncertainty. Finally, after data assimilation, fused wind condition data for the subsequent navigation path is obtained, including more accurate wind speed, wind direction, and their changing trends.

[0031] It should be noted that, in order to improve the processing efficiency of the fused wind data and reduce the data processing pressure, the vehicle's current location can be used as the starting point to determine the fused wind data for a road segment of a preset length (e.g., 2000 meters) in the subsequent navigation path.

[0032] In some optional implementations of this embodiment, the execution entity can perform step 201 as follows: The first step is to adjust the original spatial resolution of the real-time wind data to the target spatial resolution required for the navigation process, thereby obtaining refined wind data.

[0033] Generally, the raw spatial resolution of real-time wind data is lower than the target spatial resolution required for navigation. For example, the unit area at the raw spatial resolution is a grid with a side length of 100 meters, while the unit area at the target spatial resolution is a grid with a side length of 10 meters. That is, the navigation process requires wind data for each grid with a side length of 10 meters in the subsequent navigation path.

[0034] As an example, a wind field model suitable for small scales (10-meter level corresponding to the target spatial resolution) is pre-constructed based on fluid dynamics principles. The flow characteristics of wind on different terrains and ground features are considered, such as the blocking effect of buildings and the weakening effect of ground roughness. Physical equations are established for each 10m × 10m grid cell to describe the variation of wind speed and direction with spatial location. A large amount of historical meteorological data and corresponding high-precision wind condition observation data (such as data sources from meteorological stations, lidar, etc., that can provide 10-meter level resolution) are prepared. A machine learning model is trained using this data. The model inputs the original 100-meter grid wind condition data along with terrain and ground feature information such as altitude, building density, and vegetation cover, and outputs refined wind condition data in 10-meter grids. A convolutional neural network (CNN) architecture from deep learning is employed to automatically extract spatial features and patterns from the data.

[0035] The second step is to combine refined wind condition data and detected wind condition data to determine the fused wind condition data.

[0036] In this implementation, the aforementioned executing entity can refer to the above-mentioned method of "combining the real-time wind data of the subsequent navigation path with the detected wind data of the vehicle's current location to determine the fused wind data of the subsequent navigation path" and combine refined wind data and detected wind data to determine the fused wind data, which will not be elaborated here.

[0037] In this implementation, the original spatial resolution of the real-time wind data is refined to the target resolution and fused with the detected wind data to obtain more accurate and detailed fused wind data, which helps to improve the accuracy of predicting risky road sections based on fused wind data.

[0038] In some optional implementations of this embodiment, the execution entity can perform the first step as follows: for the refined unit region in the original unit region, the refined unit region's refined wind condition data is determined based on the refined unit region's position in the original unit region, the actual wind condition data of the original unit region, and the actual wind condition data of the neighboring unit regions of the original unit region.

[0039] The original cell region is the cell region corresponding to the original spatial resolution, and the refined cell region is the cell region corresponding to the target spatial resolution.

[0040] As an example, the aforementioned execution entity can input the location of the refined unit region within the original unit region, the positional relationship between the original unit region and neighboring unit regions, the actual wind condition data of the original unit region, and the actual wind condition data of neighboring unit regions into a pre-trained wind condition calculation model. The wind condition calculation model outputs refined wind condition data for the refined unit region. The wind condition calculation model is used to characterize the location of the refined unit region within the original unit region, the positional relationship between the original unit region and neighboring unit regions, the actual wind condition data of the original unit region, and the correspondence between the actual wind condition data of neighboring unit regions and the refined wind condition data of the refined unit region.

[0041] Wind condition calculation models can be trained using neural network models such as recurrent neural networks and long short-term memory networks. First, a training sample set is obtained. This set includes the sample positions of refined unit regions within the original unit region, the positional relationships between the original unit region and neighboring unit regions, the actual wind condition data of the original unit region, the actual wind condition data of the neighboring unit regions, and the refined wind condition data labels for the refined unit regions. Then, a machine learning algorithm is used, taking the sample positions of refined unit regions within the original unit region, the positional relationships between the original unit region and neighboring unit regions, the actual wind condition data of the original unit region, and the actual wind condition data of the neighboring unit regions as input, and the refined wind condition data labels corresponding to the input data as the desired output, to train the wind condition calculation model.

[0042] In this embodiment, the real-time wind data of the original unit area and the real-time wind data of the neighboring unit areas of the original unit area are combined to determine the refined wind data of the refined unit area, which improves the spatial accuracy and makes the distribution of wind data on the navigation path more detailed.

[0043] In some optional implementations of this embodiment, the execution entity can determine the refined wind condition data of the refined unit region in the following way: First, based on the position of the refined unit region in the original unit region, determine the weights corresponding to the actual wind condition data of the original unit region and the actual wind condition data of the neighboring unit regions; then, based on the weights, combine the actual wind condition data of the original unit region and the actual wind condition data of the neighboring unit regions to determine the refined wind condition data of the refined unit region.

[0044] Continuing with the example of a large-scale grid with sides of 100 meters for the original unit region and a small-scale grid with sides of 10 meters for the refined unit region, for the large-scale grid ( , ), and the four surrounding large-scale grids (neighboring cell regions) are respectively ( , ), ( , ), ( , )and( , The wind speeds of the four large-scale grids are as follows: , , , The wind directions are respectively , , , .

[0045] Target point ( For points within a small-scale grid, the normalized distance is obtained by performing a normalized distance operation on them using the following formula:

[0046] in, , For large-scale grids ( , The coordinates of the lower left corner of ).

[0047] The weights of the actual wind conditions in the original unit region and the actual wind conditions in neighboring unit regions are determined based on the normalized distance parameter. Among them, ( , ), ( , ), ( , )and( , The weights of the real-time wind data in each grid are as follows: , , , .

[0048] The wind speed at the target point is calculated using the following formula. :

[0049] The wind direction at the target point is calculated using the following method. : First, convert the wind directions of the four large-scale grids into vector form: , , , ; Then, the vector is calculated using the following formula ( ):

[0050] Finally, the vector-to-angle conversion is performed using the following formula, with the angle range being 0-360°:

[0051] This implementation provides a specific method for adjusting the spatial resolution of real-time wind data. By utilizing the real-time wind data from four adjacent grids, the wind speed and direction at the target point are calculated, thereby refining the wind data from low spatial resolution (original spatial resolution) to high spatial resolution (target spatial resolution), further improving the accuracy of the refined wind data and helping to provide more accurate wind information for vehicles.

[0052] In some optional implementations of this embodiment, the above-mentioned execution entity can perform the second step described above to obtain the fused wind condition data in the following manner: by using a weighted Kalman filter, combining the refined wind condition data and the detected wind condition data, the fused wind condition data is determined.

[0053] As an example, first, the wind speed and wind direction Its trigonometric function components are used as the state vector This is to provide a comprehensive description of the wind conditions and facilitate subsequent calculations.

[0054] Then, the cosine and sine values ​​of wind speed and direction are obtained from the meteorological service API to form a real-time wind condition vector. And set its noise covariance matrix. 0.1 This is to reflect the uncertainty of real-time wind data.

[0055] By using the vehicle's wind condition sensors to measure the cosine and sine values ​​of wind speed and direction, a wind condition vector is obtained. Set its noise covariance matrix 0.05 , which represents the error characteristics of the wind condition data.

[0056] Then, assuming the wind remains stable in the short term, predict the state vector. Take the state vector directly from the previous time step. ,Right now = This is to prepare for future updates.

[0057] Then, calculate the Kalman gain. ,in, To predict the covariance matrix, which measures the uncertainty of the predicted state. To measure the noise covariance matrix.

[0058] Then, calculate the weighted measurement values. ,in, , These represent the weights of the real-time wind data and the detected wind data, respectively. =0.3, =0.7.

[0059] Then, update the state vector. By integrating real-time wind data and detected wind data, a more accurate wind condition estimate can be obtained.

[0060] Finally, from the updated state vector Extracting wind speed and wind direction This forms a wind condition vector representing the fused wind condition data. This provides high-precision wind condition information for subsequent modules.

[0061] This implementation provides a wind condition data fusion method based on a weighted Kalman filter, which balances the stability of real-time wind condition data with the real-time performance of detected wind condition data, thereby improving the accuracy of the fused wind condition data.

[0062] In some optional implementations of this embodiment, the execution entity can perform the second step as follows: First, determine the error between the timestamp of the refined wind condition data, the timestamp of the detected wind condition data, and the timestamp corresponding to the navigation process.

[0063] As an example, a first error is determined between the timestamp of the refined wind condition data and the timestamp corresponding to the navigation process, and a second error is determined between the timestamp of the detected wind condition data and the timestamp corresponding to the navigation process. The timestamp of the refined wind condition data is the same as the timestamp of the real-time wind condition data.

[0064] The timestamp corresponding to the navigation process is the current timestamp of the navigation system. When the first error and the second error are large, it indicates that the refined wind condition data and the detected wind condition data have not been updated within a certain period of time from the current time represented by the timestamp of the navigation system.

[0065] Then, in response to the error being within a preset error range, a weighted Kalman filter is used to combine refined wind condition data and detected wind condition data to determine the fused wind condition data.

[0066] Since both the first and second errors are within the preset error range, it indicates that the time interval between the update time of the refined wind condition data and the detected wind condition data is small. Therefore, a weighted Kalman filter is used to combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data.

[0067] In response to the first error exceeding the preset error range, it is necessary to re-collect real-time wind data in order to obtain refined wind data based on the real-time wind data; in response to the second error exceeding the preset error range, it is necessary to redetermine the detected wind data.

[0068] To improve the flexibility of data acquisition and meet the needs of different data acquisition characteristics, different preset error ranges can be set for refined wind condition data and detected wind condition data. For example, real-time wind condition data has higher stability, and its preset error range is larger than that of detected wind condition data.

[0069] In this implementation, the timing of updating the real-time wind data and the detected wind data needs to be determined based on the timestamp corresponding to the navigation process and the preset error range, so that the real-time wind data and the detected wind data are adapted to the current time, thereby improving the real-time performance and accuracy of the fused wind data.

[0070] In some optional implementations of this embodiment, the executing entity may perform the following operations before executing step 201: First, the propagation time difference between the two ultrasonic transducers in each ultrasonic transducer pair is determined by using two ultrasonic transducer pairs installed on the vehicle, wherein the two ultrasonic transducer pairs are arranged in a cross shape on the vehicle; then, the wind condition data is determined based on the propagation time difference.

[0071] An ultrasonic anemometer (example model: Gill WindSonic, measurement range 0-60 m / s, accuracy ±0.1 m / s, directional accuracy ±2°) is installed in the center of the vehicle roof. The anemometer consists of two pairs of ultrasonic transducers. In one pair, transducers A and B are positioned along a north-south axis, while in the other pair, transducers C and D are positioned along an east-west axis. The distance between the two transducers in each pair is L = 0.2 meters. The two transducer pairs are located in the center of the roof to avoid areas prone to airflow interference. Power is supplied by the vehicle's 12V power supply, and the signal is transmitted to the onboard processor via an RS-485 interface.

[0072] Then, the wind speed and direction are calculated using the time difference of ultrasonic wave propagation in the wind. Specifically, ultrasonic transducer A emits ultrasonic waves to ultrasonic transducer B, and the propagation time is recorded. Ultrasonic transducer B emits ultrasonic waves to ultrasonic transducer A, and the propagation time is recorded. Similarly, ultrasonic transducer C emits ultrasonic waves into ultrasonic transducer D, and the propagation time is recorded. Ultrasonic transducer D emits ultrasonic waves to ultrasonic transducer C, and the propagation time is recorded. .

[0073] Calculate the north-south wind speed components :

[0074] Similarly, calculate the east-west wind speed component. :

[0075] Based on the above wind speed components and Calculate the wind speed in the detected wind data. :

[0076] Based on the above wind speed components and Calculate the wind direction in the detected wind data. :

[0077] wind direction The angular range is 0-360°, with due north as 0°.

[0078] In this implementation, each pair of ultrasonic transducers emits 10 ultrasonic pulses per second (period 100ms), generating 10 sets of ( ) data. Then, 10 groups ( Take the average value, and calculate based on the average value. and .

[0079] In this implementation, zero-point calibration and outlier removal operations can also be performed on the detected wind condition data. During the zero-point calibration operation, with the vehicle stationary, data is continuously collected over a specified duration (e.g., 5 seconds), and the average value is obtained. and The above results minus After obtaining the calibrated wind speed data, the above-mentioned data will be used to... minus The calibrated wind direction data is obtained.

[0080] Because ultrasonic anemometers measure the relative wind speed of the vehicle to the surrounding air. When the vehicle is stationary, the ultrasonic anemometer is fixed to the roof, and there is no relative wind speed generated by the vehicle's movement. Therefore, theoretically, the ultrasonic anemometer measures the wind speed at rest. It should be 0, but the mean of the measurements in the static state was not found to be 0, indicating that there may be some error in the hardware. Based on this, the above non-static state was used... and Subtract offset and To correct the error.

[0081] In the anomaly removal operation, if a single measurement yields... and If the deviation from the mean of the previous multiple (e.g., 10) data is greater than the standard deviation of the preset speed (e.g., 3 times), it indicates that the data collected this time is abnormal. This abnormality may be caused by a sudden gust of wind or sensor vibration, and the data needs to be discarded.

[0082] Ultimately, based on the ultrasonic transducer pair, one wind condition data point is generated per second. , The accuracy is 0.1 m / s and 1° respectively.

[0083] This implementation provides a method for obtaining wind condition data based on ultrasonic transducer pairs. By combining two ultrasonic transducer pairs arranged in a cross shape, the accuracy and real-time performance of the wind condition data are improved.

[0084] Step 202: Based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path, determine the degree of impact of wind on the vehicle's driving safety.

[0085] In this embodiment, the aforementioned execution entity can determine the degree of impact of wind on the vehicle's driving safety based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path.

[0086] As an example, firstly, based on the subsequent navigation path, the vehicle's attitude data at each position along the path is determined, such as driving direction and pitch angle, i.e., pose data. Then, the combined wind condition data and the vehicle's pose data along the subsequent navigation path are input into the influence determination model to obtain the degree of wind's impact on the vehicle's driving safety. The influence determination model can be obtained by training a neural network model (e.g., a residual network or a long short-term memory network) using machine learning algorithms.

[0087] Specifically, first, a training sample set is obtained. This set includes sample wind condition data, sample pose data, and impact level labels. Then, a machine learning algorithm is used, with the sample wind condition data and sample pose data as input to the initial impact level determination model, and the impact level labels as the initial impact level determination model's expected output. This initial impact level determination model is then trained, resulting in the final impact level determination model.

[0088] As another example, firstly, based on the principles of vehicle dynamics, risk assessment indicators are designed, including lateral displacement, lateral acceleration, and vehicle stability. These indicators directly reflect the dynamic performance of the vehicle under wind conditions. Specifically, the lateral displacement trend of the vehicle is calculated by combining the angle between the vehicle's direction of travel and the wind direction with the wind speed. The lateral acceleration exerted on the vehicle by the wind is calculated based on the wind speed and vehicle speed. Finally, the vehicle's stability is assessed using parameters such as acceleration and attitude changes.

[0089] Then, during vehicle operation, the aforementioned risk assessment indicators are calculated in real time. The multiple indicators obtained in real time are normalized so that their values ​​are within the range of [0, 1]. Using a weighted comprehensive risk assessment formula, these three indicators are integrated into a single numerical value representing the degree of wind's impact on vehicle driving safety.

[0090] In some optional implementations of this embodiment, the execution entity can perform step 202 as follows: The first step is to determine the lateral wind speed experienced by the vehicle based on the fused wind condition data and position data.

[0091] Among them, lateral wind speed represents the component of wind speed in the direction perpendicular to the vehicle's direction of travel in the fused wind condition data.

[0092] As an example, for each location point of the vehicle in the candidate navigation path, perform the following operation: First, determine the fused wind condition vector obtained in step 201 ( ), and the direction of vehicle travel. Vehicle direction of travel The location is determined as follows: by continuously sampling the location using a GPS (Global Positioning System) module. )and( The time interval is 1 second. Calculate the vehicle's direction of travel. Its range is 0-360°.

[0093] Then, the lateral wind speed is calculated using the following formula:

[0094] in, This is the sine of the angle between the wind direction and the vehicle's direction of travel. This refers to the lateral wind speed (in meters per second). If | |>180°, adjust to = ± 360°, take and Calculate the minimum included angle between them to ensure the sine value is correct; finally calculate the... Keep two decimal places (e.g.) = 8.34 m / s).

[0095] The second step is to determine the extent of the impact based on the lateral wind speed.

[0096] As an example, the principle that lateral wind speed is positively correlated with the degree of impact is adopted, and the degree of impact is determined based on the lateral wind speed.

[0097] This implementation provides a method for determining the degree of impact based on lateral wind speed, which improves the accuracy of the degree of impact.

[0098] In some optional implementations of this embodiment, the execution entity can perform the second step described above to determine the degree of influence by determining the degree of influence based on the lateral wind speed and the vehicle's inertial dynamics parameters.

[0099] Vehicle inertial dynamics parameters describe the vehicle's inertial characteristics in resisting changes in its state of motion, as well as the set of parameters for external dynamic excitations (such as wind loads). These include parameters such as the vehicle's wind sensitivity coefficient and mass. Through user input or the OBD (On-Board Diagnostics) interface, the aforementioned actuator can obtain the vehicle's mass M (kg) and crosswind sensitivity coefficient k (unitless, default 1.0 for passenger cars, 1.5 for trucks).

[0100] As an example, the degree of influence can be calculated using the following formula:

[0101] The unit for the magnitude of influence is Newtons (N). For example, = 10 m / s, = 1500 kg, =1.0, then = 1.0 × 10 × 1500 = 15000 N.

[0102] In this implementation, in determining the degree of impact, in addition to referring to the lateral wind speed, the inertial dynamics parameters of the vehicle are also taken into account. This allows for the targeted determination of the degree of impact for different vehicles, thus improving the accuracy of the degree of impact.

[0103] Step 203: Determine the assisted driving strategy for the risky sections of the subsequent navigation path based on the degree of impact.

[0104] In this implementation, the aforementioned implementing entity can determine the risky road segments in the subsequent navigation path and the assisted driving strategies for the risky road segments based on the degree of impact.

[0105] As an example, based on a comparison of the degree of impact and the risk assessment threshold, it is determined whether each location in the subsequent navigation path is a risk point; the road segments represented by adjacent risk points are identified as risk road segments. Based on factors such as the length and terrain of the risk road segments, an assisted driving strategy is determined for these risk road segments.

[0106] Specifically, firstly, the high-risk road segment is divided into several sections based on its length, taking into account terrain changes (such as continuous curves on mountain roads, and the starting and ending points of bridges) as the basis for segmentation. Then, a risk index model is established by combining the segment length and terrain characteristics. For example, for long-distance mountain roads, the risk index is higher due to continuous curves and slope changes; while for short-distance bridge sections, the risk index is relatively lower, mainly considering the impact of crosswinds.

[0107] Then, based on the risk index, determine the assisted driving strategy, such as dynamically adjusting the vehicle speed according to the risk index. On long, high-risk road sections, gradually reduce the speed to a safe range and maintain a stable speed; on short, low-risk road sections, moderately reduce the speed to ensure safe passage. Activate the vehicle stability control system and adjust control parameters according to terrain and wind conditions. Increase stability support on curves in mountainous areas and enhance resistance to crosswinds on bridge sections. Provide risk warnings and assisted driving strategies to the driver through the in-vehicle infotainment system. On high-risk road sections, advise maintaining concentration and avoiding dangerous maneuvers such as sudden lane changes; on long, high-risk road sections, remind the driver to take breaks and avoid fatigue driving.

[0108] As another example, the numerical value of the impact level is input into the assisted driving strategy generation model, which then generates assisted driving strategies. The assisted driving strategy generation model is used to characterize the correspondence between the numerical impact level and the assisted driving strategies. For example, for a higher impact level, the assisted driving strategy might include stopping safely and replanning the subsequent navigation route; for a lower impact level, the assisted driving strategy might include providing a safe speed reminder, etc.

[0109] In some optional implementations of this embodiment, the execution entity can perform step 203 as follows: The first step is to determine the risk level of the affected road sections based on the degree of impact.

[0110] In this implementation, corresponding numerical ranges can be set for different risk levels, thereby determining the risk level based on the numerical range in which the degree of impact falls.

[0111] For example, R < 5000 N is low risk; 5000 ≤ R ≤ 15000 N is medium risk; and R > 15000 N is high risk.

[0112] In this implementation, a preset calculation frequency, such as once per second, can be used to determine the degree of influence; the average value of the degree of influence within the specified time period up to the present is taken as the current degree of influence.

[0113] The second step is to determine the assisted driving strategy for the high-risk road sections based on the risk level.

[0114] As an example, the assisted driving strategy corresponding to each risk level is determined in advance, so that after determining the risk level corresponding to the degree of impact, the assisted driving strategy corresponding to the risk level is determined.

[0115] For each risky road segment in the subsequent navigation path, in response to the vehicle's proximity to that road segment, such as when the distance between the vehicle and the risky road segment is less than a preset distance threshold, assisted driving suggestions for that risky road segment are displayed to the driver of the vehicle through voice, text, or other means.

[0116] Different preset distance thresholds apply to road sections with different risk levels. For example, the preset distance threshold is positively correlated with the risk level; that is, the higher the risk level, the larger the preset distance threshold.

[0117] In this implementation, the assisted driving strategy for the risky road section is determined based on the risk level of the risky road section. Through accurate risk assessment, the vehicle can take appropriate preventive measures in advance, which helps to reduce the probability of accidents and improve driving safety.

[0118] In some optional implementations of this embodiment, the execution entity may also perform the following operations: First, the lateral force borne by the vehicle is determined based on the lateral wind speed and the vehicle's aerodynamic geometry parameters.

[0119] Among them, lateral wind speed represents the component of wind speed in the direction perpendicular to the vehicle's travel direction from the fused wind data. Aerodynamic geometry parameters represent the geometric properties and efficiency parameters of the interaction between the vehicle body shape and airflow, such as side area and lateral drag coefficient.

[0120] As an example, the following formula is used to calculate the lateral force:

[0121] Where ρ represents air density. The standard air density is 1.225 kg / m³. In high-altitude areas, it can be adjusted according to air pressure. For example, the air density at an altitude of 5000 meters is ρ≈0.736 kg / m³. This represents the lateral drag coefficient of a vehicle and can be adjusted from a vehicle model database, such as for SUVs (Sport Utility Vehicles). It is 0.45; A represents the side area of ​​the vehicle, which is determined by user input or vehicle model matching, such as the side area of ​​a sedan A≈2.5 m²; This indicates the lateral wind speed.

[0122] Then, based on the lateral force and the vehicle's stiffness parameters, the degree of directional deviation of the vehicle under the influence of the lateral force is determined.

[0123] As an example, the degree of directional deviation of a vehicle under the influence of lateral forces can be determined by the following formula: The value indicates the degree of directional deviation, in degrees; K is the vehicle suspension stiffness, which can be determined according to the vehicle type. For example, K for a truck can be set to 15000, in N / degree.

[0124] The degree of directional offset is calculated using a preset calculation frequency, such as updating δ once per second, which is the same as the calculation frequency for the degree of influence.

[0125] For example, = 61.25 N, K = 10000 N / degree, δ = (61.25 / 10000) ≈ 0.35.

[0126] In this implementation, the aforementioned implementing entity can perform the process of determining the assisted driving strategy in the following way: based on the risk level and the degree of directional deviation, determine the assisted driving strategy for the risky road section.

[0127] Based on the combination of risk level and degree of directional deviation, develop corresponding driver assistance strategies. For example: When the risk level is low and the degree of directional deviation is small, only slight directional adjustment suggestions can be provided to assist the driver in keeping the vehicle within the lane.

[0128] When the risk level is low but the degree of directional deviation is large, in addition to providing directional adjustment suggestions, the sensitivity of the vehicle stability control system (ESC) can be appropriately increased to prevent the vehicle from becoming unstable due to directional deviation.

[0129] If the risk level is medium and the degree of directional deviation is small, a slight directional correction assist will be automatically activated, and the driver will be reminded to maintain the correct driving direction.

[0130] If the risk level is medium and the directional deviation is significant, the driver should be alerted to the risk and advised to slow down. At the same time, the steering correction assistance should be enhanced, and the vehicle's maximum speed limit may be appropriately reduced.

[0131] When the risk level is high and the degree of directional deviation is small, the system will automatically make appropriate directional corrections and remind the driver to stay focused. At the same time, it will activate functions such as forward collision warning to deal with possible emergencies.

[0132] When the risk level is high and the directional deviation is significant, an emergency warning is triggered, advising the driver to immediately slow down and avoid high-risk maneuvers such as lane changes. At the same time, it provides obvious directional correction assistance and can automatically activate the emergency braking assistance function to reduce the risk of accidents.

[0133] For example, if the impact level R > 15000 N and δ > 1°, a voice announcement will be made to the driver: "Crosswind X meters ahead." "meters per second, grip the steering wheel firmly, adjust δ° to the left", X is the distance from the starting point of the risk zone to the vehicle.

[0134] Before the vehicle enters a high-risk section of road, the system automatically executes or prompts the driver to implement appropriate driver assistance strategies based on a pre-assessed risk level and real-time calculated directional deviation. During the journey, the system continuously monitors changes in vehicle status, road conditions, and directional deviation, dynamically adjusting the driver assistance strategies based on the latest data to ensure their real-time performance and effectiveness. After the journey, the system collects driver feedback and actual vehicle driving data to evaluate and analyze the effectiveness of the driver assistance strategies, allowing for optimization and improvement.

[0135] In this implementation, the assisted driving strategy for risky road sections is determined by combining the risk level and the degree of directional deviation, which further improves the accuracy of the assisted driving strategy and its matching with risky scenarios.

[0136] In some optional implementations of this embodiment, the above-mentioned execution entity may also perform the following operations: during the navigation process, a preset display method is used to display the risky road segments and their risk levels on the navigation interface.

[0137] Among them, the preset display method is to display the risk section and the risk level of the risk section through text, such as through a floating layer or floating window.

[0138] In some implementations, semi-transparent polygons are overlaid on the navigation path in the navigation map using OpenGL (Open Graphics Library). The boundaries are connected by path points of the risky path, and the width is set to the lane width (default 3.5 meters). The polygons have different colors corresponding to different wind directions. For example, linear interpolation can be used to smooth the boundary transitions, achieving a color gradient effect between risky road segments of different risk levels.

[0139] In this implementation, a preset display method is used to display the risky road sections and their risk levels on the navigation interface, allowing users to intuitively understand the risky road sections and their risk levels, thereby improving user experience and information acquisition efficiency.

[0140] In some optional implementations of this embodiment, the above-mentioned execution entity may also perform the following operation: during the navigation process, a preset icon is used to display the degree of influence on the navigation interface.

[0141] Multiple preset icon styles can be set, and the icon style to be displayed to the user is determined based on the user's selection. Different indicators can be used to display different levels of influence among the preset icons.

[0142] As an example, a wind vane icon is added to the navigation interface of the navigation map. The icon color is determined according to the degree of impact R: green for R < 5000 N, yellow for 5000-15000 N, and red for R > 15000 N. Specifically, an RGB (Red, Green, Blue) gradient function is used to represent the degree of wind impact on driving safety. = 0 in, This represents the mean of the degree of influence, R.

[0143] In this implementation, preset icons are used to display the degree of impact on the navigation interface, allowing users to intuitively understand the degree of impact and further improving user experience and information acquisition efficiency.

[0144] See also Figure 3 , Figure 3This is a schematic diagram 300 illustrating an application scenario of the method for determining the assisted driving strategy according to this embodiment. User 301 requests a navigation route from the origin to the destination from a navigation application in terminal device 302, and drives the vehicle according to the navigation route. During navigation, server 302 combines real-time wind data of the subsequent navigation route obtained from a weather application and wind data detected at the vehicle's current position collected from an onboard wind sensor to determine fused wind data for the subsequent navigation route; based on the fused wind data and the vehicle's pose data in the subsequent navigation route, it determines the degree of wind's impact on the vehicle's driving safety; based on the degree of impact, it determines risky road sections 304 in the subsequent navigation route and assisted driving strategies 305 for these risky road sections, such as "50 meters ahead, crosswind of 18 m / s, grip the steering wheel tightly, adjust 2° to the left."

[0145] This embodiment provides a method for determining assisted driving strategies. During navigation, it combines real-time wind data of the subsequent navigation path with detected wind data of the vehicle's current location to determine fused wind data for the subsequent navigation path. Based on the fused wind data and the vehicle's pose data in the subsequent navigation path, it determines the degree of wind's impact on the vehicle's driving safety. Based on the degree of impact, it identifies risky road sections in the subsequent navigation path and corresponding assisted driving strategies for these risky sections. This transforms wind conditions from an uncontrollable factor into a navigation-referenceable variable integrated into the navigation process, enabling real-time determination of risky road sections and corresponding assisted driving strategies. This solves the problem of crosswind interference during driving and helps improve driving safety.

[0146] Continue to refer to Figure 4 The illustration shows a schematic flow 400 of yet another embodiment of the method for determining an assisted driving strategy according to the present disclosure. Flow 400 includes the following steps: Step 401: During the navigation process, the original spatial resolution of the real-time wind data of the subsequent navigation path is adjusted to the target spatial resolution required for the navigation process to obtain refined wind data.

[0147] Step 402: Determine the error between the timestamp of the refined wind condition data, the timestamp of the wind condition data detected at the current vehicle location, and the timestamp corresponding to the navigation process.

[0148] Step 403: In response to the error being within a preset error range, a weighted Kalman filter is used to combine refined wind condition data and detected wind condition data to determine the fused wind condition data.

[0149] Step 404: Determine the lateral wind speed experienced by the vehicle based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path.

[0150] Among them, lateral wind speed represents the component of wind speed in the direction perpendicular to the vehicle's direction of travel in the fused wind condition data.

[0151] Step 405: Determine the degree of wind's impact on vehicle driving safety based on lateral wind speed and vehicle inertial dynamics parameters.

[0152] Step 406: Determine the risk level of the risky road segments in the subsequent navigation path based on the degree of impact.

[0153] Step 407: Determine the lateral force borne by the vehicle based on the lateral wind speed and the vehicle's aerodynamic geometry parameters.

[0154] Step 408: Determine the degree of directional deviation of the vehicle under the influence of the lateral force based on the lateral force and the vehicle's stiffness parameters.

[0155] Step 409: Determine the assisted driving strategy for the risky road section based on the risk level and the degree of directional deviation.

[0156] The process 400 of the method for determining the assisted driving strategy in this embodiment, compared with the process 200 above, specifically describes the process of determining the fusion of wind condition data, the process of determining the degree of influence, and the process of determining the assisted driving strategy. It transforms wind conditions from an uncontrollable factor into a navigation-referenced variable to be integrated into the navigation process, and determines risky road sections and assisted driving strategies for risky road sections in real time. This solves the problem of crosswind interference during driving and helps to improve driving safety.

[0157] Continue to refer to Figure 5 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a device for determining an assisted driving strategy. This system embodiment is similar to... Figure 2 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0158] like Figure 5 As shown, the driver assistance strategy determination device 500 includes: a wind condition determination unit 501, configured to determine fused wind condition data for the subsequent navigation path by combining real-time wind condition data of the subsequent navigation path and detected wind condition data of the vehicle's current position during navigation; a degree determination unit 502, configured to determine the degree of wind impact on the vehicle's driving safety based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path; and a strategy determination unit 503, configured to determine the driver assistance strategy for risky sections in the subsequent navigation path based on the degree of impact.

[0159] In some optional implementations of this embodiment, the wind condition determination unit 501 is further configured to: adjust the original spatial resolution of the real-time wind condition data to the target spatial resolution required for the navigation process to obtain refined wind condition data; combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data, wherein the original spatial resolution is less than the target spatial resolution.

[0160] In some optional implementations of this embodiment, the wind condition determination unit 501 is further configured to: for a refined unit region in the original unit region, determine the refined wind condition data of the refined unit region based on the position of the refined unit region in the original unit region, the real-time wind condition data of the original unit region and the real-time wind condition data of the neighboring unit regions of the original unit region, wherein the original unit region is the unit region corresponding to the original spatial resolution and the refined unit region is the unit region corresponding to the target spatial resolution.

[0161] In some optional implementations of this embodiment, the wind condition determination unit 501 is further configured to: determine the weights corresponding to the real-time wind condition data of the original unit region and the real-time wind condition data of neighboring unit regions based on the position of the refined unit region in the original unit region; and determine the refined wind condition data of the refined unit region based on the weights and by combining the real-time wind condition data of the original unit region and the real-time wind condition data of neighboring unit regions.

[0162] In some optional implementations of this embodiment, the wind condition determination unit 501 is further configured to: use a weighted Kalman filter to combine refined wind condition data and detected wind condition data to determine fused wind condition data.

[0163] In some optional implementations of this embodiment, the wind condition determination unit 501 is further configured to: determine the error between the timestamp of the refined wind condition data, the timestamp of the detected wind condition data and the timestamp corresponding to the navigation process; and, in response to the error being within a preset error range, use a weighted Kalman filter to combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data.

[0164] In some optional implementations of this embodiment, the degree determination unit 502 is further configured to: determine the lateral wind speed experienced by the vehicle based on the fused wind condition data and pose data, wherein the lateral wind speed represents the component of the wind speed in the fused wind condition data in the direction perpendicular to the vehicle's driving direction; and determine the degree of influence based on the lateral wind speed.

[0165] In some optional implementations of this embodiment, the degree determination unit 502 is further configured to determine the degree of influence based on the lateral wind speed and the vehicle's inertial dynamics parameters.

[0166] In some optional implementations of this embodiment, the strategy determination unit 503 is further configured to: determine the risk level of the risky road segment based on the degree of impact; and determine an assisted driving strategy for the risky road segment based on the risk level.

[0167] In some optional implementations of this embodiment, the degree determination unit 502 is further configured to: determine the lateral force borne by the vehicle based on the lateral wind speed and the aerodynamic geometry parameters of the vehicle, wherein the lateral wind speed represents the component of the wind speed in the fused wind condition data in the direction perpendicular to the vehicle's driving direction; determine the degree of directional deviation of the vehicle under the influence of the lateral force based on the lateral force and the vehicle's stiffness parameters; and the strategy determination unit 503 is further configured to: determine an assisted driving strategy for the risky road section based on the risk level and the degree of directional deviation.

[0168] In some optional implementations of this embodiment, the device further includes a detection unit (not shown in the figure), configured to: determine the propagation time difference between the two ultrasonic transducers in each ultrasonic transducer pair using two ultrasonic transducer pairs installed on the vehicle, wherein the two ultrasonic transducer pairs are arranged in a cross shape on the vehicle; and determine the detected wind condition data based on the propagation time difference.

[0169] In some optional implementations of this embodiment, the above-mentioned device further includes: a display unit (not shown in the figure), configured to display risky road segments and their risk levels on the navigation interface using a preset display method during navigation.

[0170] In some optional implementations of this embodiment, the display unit (not shown in the figure) is also configured to display the degree of influence on the navigation interface using a preset icon during navigation.

[0171] This embodiment provides a device for determining assisted driving strategies. During navigation, it combines real-time wind data of the subsequent navigation path with detected wind data of the vehicle's current location to determine fused wind data for the subsequent navigation path. Based on the fused wind data and the vehicle's pose data in the subsequent navigation path, it determines the degree of wind's impact on the vehicle's driving safety. Based on the degree of impact, it identifies risky road sections in the subsequent navigation path and corresponding assisted driving strategies for these risky sections. This transforms wind conditions from an uncontrollable factor into a navigation-referenceable variable integrated into the navigation process, enabling real-time determination of risky road sections and corresponding assisted driving strategies. This solves the problem of crosswind interference during driving and helps improve driving safety.

[0172] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the method for determining the assisted driving strategy described in any of the above embodiments when executed.

[0173] According to embodiments of this disclosure, this disclosure also provides a readable storage medium storing computer instructions that, when executed by a computer, enable the determination method for the assisted driving strategy described in any of the above embodiments.

[0174] This disclosure provides a computer program product that, when executed by a processor, can implement the method for determining the assisted driving strategy described in any of the above embodiments.

[0175] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0176] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0177] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0178] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for determining an assisted driving strategy. For example, in some embodiments, the method for determining an assisted driving strategy may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method for determining an assisted driving strategy described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method for determining an assisted driving strategy by any other suitable means (e.g., by means of firmware).

[0179] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0180] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other device for determining a programmable driver assistance strategy, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0181] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0182] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0183] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0184] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are hosting products within the cloud computing service system to address the management difficulties and weak business scalability inherent in traditional physical hosts and Virtual Private Servers (VPS) services; they can also be servers for distributed systems or servers incorporating blockchain technology.

[0185] According to the technical solution of this disclosure, a method and apparatus for determining assisted driving strategies are provided. During navigation, by combining real-time wind data of the subsequent navigation path with detected wind data of the vehicle's current location, fused wind data for the subsequent navigation path is determined. Based on the fused wind data and the vehicle's pose data in the subsequent navigation path, the degree of wind's impact on the vehicle's driving safety is determined. Based on the degree of impact, risky road sections in the subsequent navigation path and assisted driving strategies for these risky road sections are determined. This transforms wind conditions from an uncontrollable factor into a navigation-referenceable variable to be integrated into the navigation process, enabling real-time determination of risky road sections and assisted driving strategies for them. This solves the problem of crosswind interference during driving and helps improve driving safety.

[0186] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution provided in this disclosure can be achieved, and this is not limited herein.

[0187] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining an assisted driving strategy, comprising: During navigation, for a refined unit region within the original unit region on the subsequent navigation path, the refined wind condition data of the refined unit region is determined based on the position of the refined unit region within the original unit region, the real-time wind condition data of the original unit region, and the real-time wind condition data of the neighboring unit regions of the original unit region. Here, the original unit region is the unit region corresponding to the original spatial resolution of the real-time wind condition data, and the refined unit region is the unit region corresponding to the target spatial resolution required for the navigation process. The original spatial resolution is smaller than the target spatial resolution. By combining the refined wind condition data and the wind condition data detected at the vehicle's current location, the fused wind condition data for the subsequent navigation path is determined. Based on the fused wind data and the vehicle's pose data in the subsequent navigation path, the degree of wind's impact on the vehicle's driving safety is determined. Based on the degree of impact, determine the assisted driving strategy for the risky sections of the subsequent navigation path.

2. The method according to claim 1, wherein, The step of determining the refined wind condition data of the refined unit region based on the position of the refined unit region in the original unit region, the real-time wind condition data of the original unit region, and the real-time wind condition data of the neighboring unit regions of the original unit region includes: Based on the position of the refined unit region in the original unit region, determine the weights corresponding to the real-time wind data of the original unit region and the real-time wind data of the neighboring unit regions. Based on the weights, and combining the real-time wind data of the original unit area with the real-time wind data of the neighboring unit areas, the refined wind data of the refined unit area is determined.

3. The method according to claim 1, wherein, The process of combining the refined wind data and the wind data detected at the vehicle's current location to determine the fused wind data includes: The weighted Kalman filter is used to combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data.

4. The method according to claim 3, wherein, The process of using a weighted Kalman filter to combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data includes: Determine the errors between the timestamp of the refined wind condition data, the timestamp of the detected wind condition data, and the timestamp corresponding to the navigation process; In response to the error being within a preset error range, a weighted Kalman filter is used to combine the refined wind condition data and the detected wind condition data to determine the fused wind condition data.

5. The method according to claim 1, wherein, The step of determining the degree of wind's impact on the vehicle's driving safety based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path includes: Based on the fused wind data and the pose data, the lateral wind speed experienced by the vehicle is determined, wherein the lateral wind speed represents the component of the wind speed in the fused wind data in the direction perpendicular to the vehicle's direction of travel. The degree of impact is determined based on the lateral wind speed.

6. The method according to claim 5, wherein, Determining the degree of influence based on the lateral wind speed includes: The degree of influence is determined based on the lateral wind speed and the vehicle's inertial dynamics parameters.

7. The method according to claim 1, wherein, The step of determining the assisted driving strategy for the risky road segments in the subsequent navigation path based on the degree of impact includes: Based on the degree of impact, the risk level of the risky road segment is determined; Based on the risk level, determine the assisted driving strategy for the risky road section.

8. The method according to claim 7, wherein, This also includes: The lateral force borne by the vehicle is determined based on the lateral wind speed and the aerodynamic geometry parameters of the vehicle, wherein the lateral wind speed represents the component of the wind speed in the fused wind data in the direction perpendicular to the vehicle's direction of travel. Based on the lateral force and the vehicle's stiffness parameters, determine the degree of directional deviation of the vehicle under the influence of the lateral force; and The step of determining the assisted driving strategy for the risky road segment based on the risk level includes: Based on the risk level and the degree of directional deviation, an assisted driving strategy is determined for the risky road segment.

9. The method according to claim 1, wherein, Before determining the fused wind data for the subsequent navigation path by combining real-time wind data of the subsequent navigation path and wind data detected at the vehicle's current location during the navigation process, the method further includes: The propagation time difference of ultrasonic waves between the two ultrasonic transducers in each ultrasonic transducer pair is determined by using two ultrasonic transducer pairs installed on the vehicle, wherein the two ultrasonic transducer pairs are arranged in a cross shape on the vehicle. The wind condition data is determined based on the propagation time difference.

10. The method according to any one of claims 1-9, wherein, Also includes: During the navigation process, a preset display method is used to display the risky road segment and its risk level on the navigation interface.

11. The method according to any one of claims 1-9, wherein, Also includes: During the navigation process, preset icons are used to display the degree of influence on the navigation interface.

12. A device for determining an assisted driving strategy, comprising: A wind condition determination unit is configured to, during navigation, determine refined wind condition data for a refined unit region within an original unit region on a subsequent navigation path, based on the refined unit region's position within the original unit region, the real-time wind condition data of the original unit region, and the real-time wind condition data of neighboring unit regions. The original unit region is the unit region corresponding to the original spatial resolution of the real-time wind condition data, and the refined unit region is the unit region corresponding to the target spatial resolution required for the navigation process, where the original spatial resolution is smaller than the target spatial resolution. The unit then combines the refined wind condition data with wind condition data detected at the vehicle's current location to determine fused wind condition data for the subsequent navigation path. The degree determination unit is configured to determine the degree of impact of wind on the driving safety of the vehicle based on the fused wind condition data and the vehicle's pose data in the subsequent navigation path. The strategy determination unit is configured to determine the assisted driving strategy for the risky road segments in the subsequent navigation path based on the degree of impact.

13. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

14. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

15. A computer program product comprising: A computer program that, when executed by a processor, implements the method according to any one of claims 1-11.

Images