Assisted driving warning method, device, vehicle and storage medium

Abstract

The embodiment of the present invention relates to the field of data processing technology, and discloses an assisted driving warning method, device, vehicle and storage medium, the method comprising: obtaining driving scene data and vehicle networking data of the vehicle in the target area; extracting the driving scene data to obtain the road condition data and vehicle intention data of the target area; analyzing the driving scene data and vehicle networking data to obtain abnormal scene data in the target area; planning the driving path of the vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain the target driving path; triggering the corresponding auxiliary warning function based on the target driving path and the current driving state of the vehicle. Applying the technical solution of the present invention can improve the accuracy and reliability of assisted driving warning.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and specifically to an assisted driving warning method, device, vehicle and storage medium. Background Art

[0002] The vision of autonomous driving technology is to improve road safety, ease traffic congestion, improve travel efficiency, and may completely change the way people travel in the future. Assisted driving warning involves continuous monitoring and analysis of the road environment in order to identify potential dangers or abnormal situations. This link is crucial for autonomous vehicles because it helps autonomous vehicles make safer and more reasonable driving decisions, thereby avoiding potential accidents. Therefore, the accuracy of assisted driving warning information plays a vital role in the safe operation of autonomous vehicles. Summary of the invention

[0003] In view of the above problems, an embodiment of the present invention provides an assisted driving warning method, device, vehicle and storage medium.

[0004] According to one aspect of an embodiment of the present invention, an assisted driving warning method is provided, which includes: acquiring driving scene data and vehicle networking data of an own vehicle in a target area; extracting data from the driving scene data to obtain road condition data and vehicle intention data of the target area; analyzing the driving scene data and vehicle networking data to obtain abnormal scene data in the target area; planning a driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain a target driving path; and triggering a corresponding auxiliary warning function based on the target driving path and the current driving status of the own vehicle.

[0005] In an optional implementation, obtaining driving scene data and Internet of Vehicles data of the vehicle in the target area includes:

[0006] Obtain sensor detection data of the vehicle and traffic data of the target area;

[0007] Analyze sensor detection data and traffic data to obtain driving scene data;

[0008] Obtain social media data and traffic broadcast data for target areas;

[0009] Traffic information is extracted based on social media data and traffic broadcast data to obtain Internet of Vehicles data.

[0010] In an optional implementation, data extraction is performed on the driving scene data to obtain road condition data and vehicle intention data of the target area, including:

[0011] Based on the driving action characteristics of the vehicle and the action characteristics of vehicles and pedestrians in the target area, dynamic features of the driving scene data are extracted to obtain dynamic scene data;

[0012] Based on the interactive behaviors of vehicles and pedestrians in dynamic scene data, the road condition data of the target area is obtained;

[0013] Based on the trajectory data of vehicles around the vehicle in the dynamic scene data, the vehicle intention data is obtained.

[0014] In an optional implementation, data analysis is performed on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area, including:

[0015] Based on the driving action characteristics of the vehicle and the action characteristics of vehicles and pedestrians in the target area, static features of the driving scene data are extracted to obtain static scene data;

[0016] Perform data analysis on static scene data to obtain abnormal road surfaces in the target area;

[0017] Analyze the Internet of Vehicles data to obtain accident sites and construction sections in the target area;

[0018] Based on abnormal road surfaces, accident sites and construction sections, determine abnormal scene data in the target area.

[0019] In an optional implementation, the driving path of the vehicle is planned based on the road condition data, the vehicle intention data, and the abnormal scene data to obtain the target driving path, including:

[0020] Based on the road condition data and abnormal scene data, the driving path of the vehicle in the target area is planned to obtain the initial driving path;

[0021] Determine an obstacle avoidance path corresponding to the current section in the initial driving path based on the vehicle intention data;

[0022] The initial driving path is updated based on the obstacle avoidance path to obtain the target driving path.

[0023] In an optional implementation, based on the target driving path and the current driving state of the vehicle, a corresponding auxiliary warning function is triggered, including:

[0024] Based on the deviation information between the current driving state of the vehicle and the target driving path, the auxiliary warning function of path deviation is triggered;

[0025] Based on the current driving status of the vehicle and the vehicle intention data, the auxiliary warning function of vehicle collision is triggered.

[0026] In an optional implementation, the above method further includes:

[0027] Receive user feedback based on auxiliary warning functions;

[0028] The auxiliary warning function is optimized based on feedback information.

[0029] According to another aspect of an embodiment of the present invention, an assisted driving warning device is provided, including: a data acquisition module, used to acquire driving scene data and vehicle networking data of the own vehicle in a target area; a data analysis module, used to extract data from the driving scene data to obtain road condition data and vehicle intention data of the target area; a data processing module, used to analyze the driving scene data and vehicle networking data to obtain abnormal scene data in the target area; a path determination module, used to plan the driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain a target driving path; an assisted driving module, used to trigger a corresponding auxiliary warning function based on the target driving path and the current driving status of the own vehicle.

[0030] According to another aspect of an embodiment of the present invention, a vehicle is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the aforementioned assisted driving warning method.

[0031] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a vehicle / device to perform the operation of the aforementioned assisted driving warning method.

[0032] The technical solution provided by the embodiment of the present invention improves the comprehensiveness and accuracy of assisted driving information acquisition by acquiring driving scene data and vehicle networking data of the own vehicle in the target area; obtains road condition data and vehicle intention data of the target area by extracting driving scene data, performs data analysis on driving scene data and vehicle networking data, obtains abnormal scene data in the target area, and plans the driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain the target driving path, thereby improving the adaptability of the assisted driving vehicle to highly dynamic and uncertain traffic environments; triggers the corresponding auxiliary warning function based on the target driving path and the current driving status of the own vehicle, thereby improving the accuracy and reliability of the assisted driving warning, and providing necessary guarantees for safe driving of the vehicle.

[0033] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0035] Figure 1 A schematic diagram of a process flow of an assisted driving warning method provided by the present invention is shown;

[0036] Figure 2 Another schematic diagram of a process of an assisted driving warning method provided by the present invention is shown;

[0037] Figure 3 A schematic structural diagram of a driver assistance warning device provided by the present invention is shown;

[0038] Figure 4 A schematic structural diagram of an assisted driving warning system provided by the present invention is shown;

[0039] Figure 5 A structural schematic diagram of a vehicle provided by the present invention is shown. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] Figure 1 FIG. 1 is a flow chart showing a first embodiment of an assisted driving warning method of the present invention, which is applicable to a vehicle. Figure 1 As shown, the method comprises the following steps:

[0042] Step 110, obtaining driving scene data and Internet of Vehicles data of the vehicle in the target area.

[0043] Among them, driving scene data includes but is not limited to the vehicle's real-time position, speed, acceleration, steering angle and other information. Internet of Vehicles data includes real-time information from other vehicles or transportation infrastructure, such as traffic flow, road conditions, weather conditions, accident reports, etc.

[0044] In an optional way, when obtaining the driving scene data and Internet of Vehicles data of the vehicle in the target area, the sensor detection data of the vehicle and the traffic data of the target area can be obtained first; the sensor detection data can be obtained by using various sensors carried by the vehicle, such as cameras, lidar, millimeter radar, laser scanner, etc., to detect the surrounding environment of the vehicle in real time, including other vehicles, pedestrians, obstacles, etc.; the traffic data can be obtained through the traffic monitoring system and GPS, including traffic flow, vehicle speed and congestion index. Then, the sensor detection data and traffic data are analyzed to obtain driving scene data; social media data and traffic broadcast data for the target area are obtained; traffic information is extracted based on social media data and traffic broadcast data to obtain Internet of Vehicles data.

[0045] In actual operation, when analyzing the sensor detection data and traffic data to obtain driving scene data, in order to improve the accuracy of obtaining the driving scene data, the sensor detection data and traffic data need to be integrated and processed.

[0046] Specifically, in the process of integrating and processing sensor detection data, the raw data from the laser radar, camera and millimeter wave radar are obtained respectively. These data are presented in the form of point cloud (laser radar), image frame (camera) and distance-speed information (millimeter wave radar). First, these data are preprocessed, including timestamp synchronization, coordinate system one (i.e., converting all data to vehicle coordinate system or global coordinate system), and denoising (filtering invalid points or noise points in the laser radar). Next, feature extraction is performed on the preprocessed data to extract the position and shape of the object from the laser radar data, image features (such as edges, textures) from the camera data, and distance and speed information of the object from the millimeter wave radar data. A state space model is constructed for each sensor, and the state vector and observation vector are clarified, where the state vector contains position and speed, and the observation vector is the data directly measured by the sensor. The Kalman filter algorithm is applied for state prediction, which iteratively predicts the state through a prediction-update cycle, where the prediction step uses a dynamic model to predict the state at the next moment, and the update step uses the observation data to correct the prediction result. Then, the state estimation results of multiple sensors are fused to obtain a full-range, high-precision road environment perception result. The fusion method can be a simple weighted average or a more complex covariance cross method. Analyze the noise characteristics of the fusion results, including system noise and measurement noise. Further apply filtering techniques (such as smoothing filtering and median filtering) to eliminate noise and improve the accuracy of the results. Finally, output the processed data for subsequent vehicle path planning and decision control.

[0047] Specifically, in the process of integrating and processing traffic data, historical traffic data should be collected first, covering traffic flow, vehicle speed, and congestion index. Subsequently, these historical data are preprocessed, including data cleaning (removing outliers and processing missing values), data normalization (converting traffic data into relative values ​​that are convenient for model training), and time series construction (organizing data into sequences by time points as LSTM input). Next, an LSTM neural network model is constructed. As a type of recurrent neural network RNN, this model is good at capturing long-term dependencies in time series data. In the model, we define the input layer, LSTM layer (including hidden states h and memory cells c), and output layer. Based on the preprocessed historical traffic data, a training data set and a validation data set are constructed, where the training data set is used for model training and the validation data set is used to evaluate model performance. The neural network model LSTM is trained using the training data set, and the model parameters are optimized through the back propagation algorithm to accurately predict future traffic flow and congestion trends. During the training process, the loss function and accuracy of the model are monitored, and the model structure (such as increasing the number of LSTM layers and hidden units) and training parameters (such as learning rate and batch size) are adjusted to improve model performance. Finally, the preprocessed real-time traffic data is input into the trained LSTM neural network model to predict future traffic flow and congestion trends. The prediction results are post-processed, including converting the predicted relative values ​​back to actual values ​​and generating traffic congestion warning information based on the prediction results. Finally, the prediction results and warning information are output for vehicle path planning and traffic information release.

[0048] Specifically, when using social media data and traffic broadcast data to extract traffic information to construct vehicle network data, text and voice information can be collected from social media and traffic broadcasts in the form of text messages and voice broadcasts. The collected data first needs to be preprocessed, which includes text cleaning (removing special characters and punctuation) and speech-to-text (using speech recognition technology to convert voice information into text). The preprocessed data will undergo natural language processing steps such as word segmentation and part-of-speech tagging to prepare for the input of the subsequent deep learning model. Next, a deep learning model based on the Transformer architecture is built, which uses a sequence-to-sequence model driven by a self-attention mechanism. In order to train this model, a training dataset containing labeled traffic-related information (such as accidents, congestion) and non-traffic-related information is created. By using this training dataset, we train the deep learning model and optimize its parameters to improve its efficiency in parsing traffic conditions in text and voice information. The preprocessed text and voice information are input into the trained deep learning model for information parsing. Finally, the model output extracts immediate information that has a direct impact on traffic conditions, such as accident locations, congestion levels, and road closures. This extracted information will be output in a structured form for subsequent vehicles to use in traffic information release and route planning.

[0049] Step 120 , extracting the driving scene data to obtain the road condition data and vehicle intention data of the target area.

[0050] As described above, the driving scene data of the target area is extracted so as to plan and warn the driving path of the vehicle based on the obtained road condition data and vehicle intention data.

[0051] In an optional manner, when extracting driving scene data to obtain road condition data and vehicle intention data of a target area, dynamic feature extraction can be performed on the driving scene data based on the driving action characteristics of the vehicle and the action characteristics of vehicles and pedestrians in the target area to obtain dynamic scene data; road condition data of the target area can be obtained based on the interaction behavior of vehicles and pedestrians in the dynamic scene data; and vehicle intention data can be obtained based on the trajectory data of vehicles around the vehicle in the dynamic scene data.

[0052] Specifically, when extracting driving scene data to obtain road condition information in the target area, pedestrian behavior data can be collected. These data include the trajectory, speed and direction of pedestrians, which are derived from camera monitoring and lidar sensors. Next, these pedestrian behavior data are preprocessed, including data cleaning, coordinate conversion (converting the trajectory of pedestrians into the vehicle coordinate system), and feature extraction (extracting the speed and direction change features of pedestrians). Then, a generative adversarial network model GAN ​​is constructed, which consists of two parts: a generator and a discriminator. The generator is responsible for generating realistic pedestrian behavior samples, while the discriminator is used to distinguish between real samples and generated samples. Create a training dataset that contains real pedestrian behavior samples and fake samples generated by the generator. Use this training dataset to train the adversarial network model GAN. By optimizing the loss functions of the generator and the discriminator, the generator can generate realistic pedestrian behavior samples, while the discriminator can accurately distinguish between real samples and fake samples. During the training process, the loss function of the model and the quality of the generated samples are monitored, and the model structure (such as increasing the number of layers and hidden units of the generator and discriminator) and training parameters (such as learning rate and batch size) are adjusted to improve the model performance. The preprocessed real-time pedestrian behavior data is input into the trained adversarial network model GA type to predict the pedestrian walking path and interaction with the vehicle. The prediction results are post-processed, including converting the generated pedestrian trajectory back to the global coordinate system to obtain the road condition data of the target area, and pedestrian collision warning information is generated based on this data. Finally, the prediction results and warning information are output for subsequent vehicles to use in traffic information release and path planning to improve the ability to respond to uncertain pedestrian behavior.

[0053] Specifically, when extracting driving scene data to obtain vehicle intention data, the vehicle's driving trajectory data should be collected first, covering position, speed and direction information. Subsequently, these trajectory data are constructed into a graph structure, in which each vehicle represents a node, and the relative position and speed relationship between vehicles constitute the edges of the graph. Next, a graph convolutional network model GCN is constructed, which is a deep learning model designed for processing graph structure data and can effectively capture the spatial relationship between nodes. Prepare training and validation data sets, the former for model training, and the latter for evaluating model performance. The graph convolutional network model GCN is trained using the training data set, and the model parameters are optimized through the back propagation algorithm to accurately predict the future movements of surrounding vehicles. During the training process, the loss function and accuracy are monitored, and the model structure (such as increasing the number of graph convolution layers and adjusting the convolution kernel size) and training parameters (such as learning rate and batch size) are adjusted to improve model performance. The vehicle driving trajectory data collected in real time is input into the trained graph convolutional network model to predict future movements. According to the model output, the future position, speed and direction of surrounding vehicles are determined to provide decision support for collaborative driving. The prediction results are output for subsequent vehicles to use in traffic information release and path planning to enhance collaborative driving capabilities and reduce collision risks.

[0054] In addition, vehicle dynamic data can also be collected, including vehicle speed, acceleration, steering wheel angle, and brake pressure. These data are preprocessed, including data cleaning and normalization, to ensure compatibility with the hidden Markov model HMM. A hidden Markov model HMM is constructed. As a statistical model, the model is used to describe Markov processes with implicit unknown parameters. In driver intention analysis, the hidden state of the hidden Markov model HMM represents the driver's intention (such as changing lanes, braking), while the observed state represents the dynamic data of the vehicle. A training data set containing vehicle dynamic data and corresponding driver intention labels is prepared. The hidden Markov model HMM is trained using the training data set, and the model parameters are estimated by the EM algorithm (expectation maximization algorithm) to accurately analyze the driver's intention. Then, the vehicle dynamic data collected in real time is input into the trained hidden Markov model HMM for driver intention analysis. According to the model output, the driver's current intention, including changing lanes and braking, is determined, thereby obtaining vehicle intention data. Based on the analysis results, the corresponding response strategies are output, such as adjusting vehicle speed and maintaining vehicle distance, for subsequent vehicles to use when publishing traffic information and planning routes, in order to achieve more accurate responses.

[0055] Through the above steps, accurate interpretation of vehicle intentions is achieved, providing key support for the decision-making and control of the autonomous driving system, thereby improving driving safety and comfort.

[0056] Step 130, performing data analysis on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area.

[0057] In an optional manner, when data analysis is performed on driving scene data and Internet of Vehicles data to obtain abnormal scene data in the target area, static features can be extracted from the driving scene data based on the driving action characteristics of the vehicle itself and the action characteristics of vehicles and pedestrians in the target area to obtain static scene data; data analysis is performed on the static scene data to obtain abnormal road surfaces in the target area; data analysis is performed on the Internet of Vehicles data to obtain accident sections and construction sections in the target area; and based on the abnormal road surfaces, accident sections and construction sections, the abnormal scene data in the target area is determined.

[0058] Specifically, by conducting in-depth analysis of static scene data, road image data can be extracted. These data cover a variety of situations such as normal roads, potholes, water accumulation, and obstacles, and are collected through vehicle-mounted cameras and drone aerial photography technology. The acquired road image data is preprocessed, including image cropping, scaling, and normalization operations to ensure the consistency of image size and pixel value, so as to facilitate subsequent model training. Subsequently, these preprocessed road images are annotated in detail, and abnormal areas such as potholes, water accumulation, and obstacles are clearly marked to provide necessary supervision information for model training. Next, a convolutional neural network model CNN consisting of a convolutional layer, a pooling layer, and a fully connected layer is constructed. A training data set and a validation data set are prepared, where the training data set is used for model training, and the validation data set is used to evaluate model performance. The convolutional neural network model CNN is trained using the training data set, and the model parameters are optimized using the back propagation algorithm to ensure that the model can accurately identify abnormal areas in road images. During the training process, the loss function and accuracy of the model are monitored in real time, and the model structure (such as increasing the number of convolution layers, adjusting the convolution kernel size) and training parameters (such as learning rate, batch size) are adjusted as needed to improve the overall performance of the model. Finally, the road image after real-time preprocessing is input into the CNN of the trained convolutional neural network model to identify abnormal areas. Based on the results output by the model, we can determine the type and location of the road anomaly and adjust the driving strategy accordingly, such as avoiding obstacles or slowing down to pass through waterlogged areas. Finally, the abnormality identification results and driving strategy adjustment suggestions are output to provide a reference for the subsequent vehicle path planning and decision control.

[0059] Furthermore, through in-depth analysis of the Internet of Vehicles data, accident-prone areas and construction sections in the target area can be identified. First, a geographic information system (GIS) is constructed to integrate multiple data sources such as map data, traffic data, and accident data. Subsequently, these integrated data are spatially analyzed, covering accident hotspot analysis and the identification of construction areas, laying a solid foundation for traffic monitoring. Using on-board sensors and traffic monitoring systems, traffic data such as vehicle speed, traffic volume, and accident information can be obtained in real time. These real-time data will be continuously updated to the GIS system to achieve dynamic monitoring of accident-prone areas and construction areas. Further analysis of real-time data will help us identify potential accident risks and construction impacts, and provide a scientific basis for issuing warnings. Based on the analysis results of the GIS system, warning information is issued in a timely manner to remind drivers to pay attention to potential dangerous areas. Finally, according to the warning information, corresponding response strategies are formulated, such as detours or speed reduction recommendations. These warning information and response strategy recommendations will be output for subsequent path planning and decision control of vehicles.

[0060] In addition, when identifying abnormal scene data in the target area, the data provided by the weather station can be integrated, covering real-time monitoring information of weather conditions such as rain, snow, fog and haze; these meteorological data are preprocessed, including data cleaning and format conversion, to ensure their compatibility with the machine learning model; at the same time, historical traffic data are collected, involving information such as traffic flow, vehicle speed, accident rate under different weather conditions, to provide necessary supervision data for model training; machine learning models, such as decision trees, random forests, support vector machines, etc., are constructed to evaluate the impact of weather conditions on driving behavior; training data sets are prepared, combining meteorological data and corresponding traffic data; machine learning models are trained using training data sets, and model parameters are adjusted through optimization algorithms (such as gradient descent, stochastic gradient descent) to improve the accuracy of the model's assessment of the impact of weather on driving; real-time meteorological data are input into the trained machine learning model to evaluate the impact of current weather conditions on driving; based on the model output, the specific impact of weather conditions on driving is clarified, such as recommendations to reduce vehicle speed and increase vehicle distance; finally, early warning information is issued in a timely manner based on the evaluation results to remind drivers to drive safely.

[0061] Step 140, based on the road condition data, the vehicle intention data, and the abnormal scene data, the driving path of the vehicle is planned to obtain the target driving path.

[0062] In actual operation, by integrating road condition data, vehicle intention data and abnormal scene data, high-precision map information can be obtained, covering key information such as road networks, intersections, and traffic signals. At the same time, road condition data such as traffic volume, vehicle speed, accidents and construction conditions are collected in real time to dynamically display the current traffic status. Since the A algorithm is a heuristic search algorithm, it can be used to find the shortest path from the starting point to the end point in a weighted graph. In this graph, the nodes represent road intersections, and the weights of the edges represent the driving costs (time, distance). The A* algorithm dynamically adjusts the weights of sections according to real-time road conditions. For example, the weights of sections with heavy traffic volume are increased, and the weights of sections with fast speeds are reduced to reflect the impact of current traffic conditions on path selection. Using the adjusted weights, the A* algorithm can quickly and accurately calculate the optimal path from the current location to the destination. The calculation results include the sequence of sections and turn instructions for use by subsequent modules such as navigation and decision control. Continuously monitor road condition information, and update the path planning in a timely manner once changes occur, to ensure that the vehicle can flexibly respond to traffic changes. In addition, based on the vehicle intention data, it can identify emergency situations, such as obstacles ahead or sudden braking of the vehicle, and quickly generate obstacle avoidance paths. In emergency situations, vehicle state data, including position, speed, acceleration, and environmental perception data, such as the position and size of obstacles, are collected. A reinforcement learning model is constructed, including a deep Q network (DQN) and a policy gradient, in which the strategy is continuously optimized through trial and error learning to maximize the cumulative reward. The state space, action space, and reward function are defined, where the state space includes the vehicle state and environmental perception data, the action space includes obstacle avoidance actions (such as steering and braking), and the reward function is designed based on factors such as the success or failure of obstacle avoidance, path length, and time consumption. The reinforcement learning model is trained using historical emergency data, and through continuous trial and error and policy adjustment, the model learns to quickly generate safe and effective obstacle avoidance paths in emergency situations. When an emergency occurs, the current vehicle state and environmental perception data are input into the trained model to generate an obstacle avoidance path. According to the generated obstacle avoidance path, the corresponding control instructions, including steering angle and braking force, are output for the vehicle to perform subsequent decision control. We continuously monitor vehicle status and environmental changes. Once the emergency is resolved or the path needs to be adjusted, we will promptly update the obstacle avoidance path to obtain the target driving path to ensure vehicle safety.

[0063] Step 150, triggering a corresponding auxiliary warning function based on the target driving path and the current driving state of the vehicle.

[0064] In an optional manner, when the corresponding auxiliary warning function is triggered based on the target driving path and the current driving status of the vehicle, the auxiliary warning function of path deviation can be triggered based on the deviation information between the current driving status of the vehicle and the target driving path; the auxiliary warning function of vehicle collision can be triggered based on the current driving status of the vehicle and the vehicle intention data.

[0065] In actual operation, the augmented reality system is first constructed, covering hardware devices such as AR glasses or in-vehicle AR display screens, as well as supporting software platforms; sensors (such as radar, camera, lidar) are used to collect real-time data of surrounding vehicles, pedestrians, and obstacles, and the accuracy and completeness of the information are ensured through data fusion technology; AR technology is used to accurately superimpose the information of surrounding vehicles, pedestrians, and obstacles into the driver's field of view, and image processing and computer vision algorithms, such as image registration and depth estimation, are used to ensure the correct alignment and display of information; the style and layout of the AR display, including the transparency, color, and size of the information, are adjusted according to the driver's needs and preferences to provide the best visual experience; through AR display, the driver can more intuitively perceive the dynamic changes of the surrounding environment, such as approaching vehicles and pedestrians crossing, thereby enhancing the perception ability during driving; combined with other assisted driving systems (such as automatic emergency braking and lane keeping assist), AR technology further provides accurate assisted driving information, such as lane departure warning and collision warning, to improve driving safety; natural language processing (NLP) technology is used to generate concise warning information. Construct a natural language processing (NLP) model, including a recurrent neural network (RNN), a long short-term memory network model LSTM or a Transformer model, to process and understand natural language text and generate concise and clear warning information. In addition, prepare a training data set, which includes text samples of warning information and its context labels, and train the NLP model through supervised learning so that it can generate appropriate warning information based on the context; input the vehicle status, environmental perception data and driver behavior information collected in real time into the trained NLP model to generate concise and clear warning information; optimize the generated warning information, adjust the sentence structure, select appropriate vocabulary and tone, and ensure that the information is accurately and clearly conveyed to the driver.

[0066] In an optional manner, feedback information from users based on the auxiliary warning function may also be received; and the auxiliary warning function may be optimized based on the feedback information.

[0067] In actual operation, the generated warning information can be accurately conveyed to the driver through speech synthesis technology or on-board display screen. Speech synthesis technology converts text information into speech output, while the on-board display screen displays the warning information in the form of text or icons. At the same time, the driver's feedback and response data are collected to evaluate the effectiveness and accuracy of the warning information. According to the feedback results, the NLP model and the warning information generation strategy are further optimized to improve the performance of the warning system and the driver's satisfaction.

[0068] Through the above steps, human-computer interaction and accurate warning are achieved, enhancing the driver's perception and reaction speed, thereby reducing the incidence of traffic accidents and improving driving safety.

[0069] The assisted driving warning method of the embodiment of the present invention improves the comprehensiveness and accuracy of assisted driving information acquisition by acquiring driving scene data and vehicle network data of the own vehicle in the target area; obtains road condition data and vehicle intention data of the target area by extracting driving scene data, performs data analysis on driving scene data and vehicle network data, obtains abnormal scene data in the target area, and plans the driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain the target driving path, thereby improving the adaptability of the assisted driving vehicle to highly dynamic and uncertain traffic environments; triggers the corresponding assisted warning function based on the target driving path and the current driving status of the own vehicle, thereby improving the accuracy and reliability of assisted driving warnings, and providing necessary guarantees for safe driving of the vehicle.

[0070] Figure 2 FIG. 1 is a flow chart showing another embodiment of the assisted driving warning method of the present invention, which is executed by a vehicle. Figure 2 As shown, the method comprises the following steps:

[0071] Step 210, obtaining driving scene data and Internet of Vehicles data of the vehicle in the target area.

[0072] For details, please see Figure 1 Step 110 of the illustrated embodiment will not be described in detail here.

[0073] Step 220 , extracting the driving scene data to obtain the road condition data and vehicle intention data of the target area.

[0074] For details, please see Figure 1 Step 120 of the illustrated embodiment will not be described in detail here.

[0075] Step 230, performing data analysis on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area.

[0076] For details, please see Figure 1 Step 130 of the illustrated embodiment will not be described in detail here.

[0077] Step 240, based on the road condition data, the vehicle intention data, and the abnormal scene data, the driving path of the vehicle is planned to obtain the target driving path.

[0078] Specifically, the above step 240 includes:

[0079] Step 2401, based on the road condition data and abnormal scene data, the driving path of the vehicle in the target area is planned to obtain an initial driving path.

[0080] As mentioned above, the vehicle's driving path in a specific area is planned by using road condition data and abnormal scenario data to obtain an initial driving route. The "self-vehicle" here refers to the vehicle itself that needs to plan the path, the "target area" refers to the specific geographical range where the vehicle needs to travel, and the "initial driving path" is the preliminary driving route calculated based on the existing data.

[0081] Step 2402, determining an obstacle avoidance path corresponding to the current section in the initial driving path based on the vehicle intention data.

[0082] As mentioned above, by utilizing the vehicle's intention data (which may be data collected through sensors, navigation systems, etc.) to determine the vehicle's driving route that should avoid obstacles for the current driving section during driving, it is possible to plan a path that can safely avoid obstacles by analyzing the vehicle's driving intention and the surrounding environment.

[0083] Step 2403: Update the initial driving path based on the obstacle avoidance path to obtain a target driving path.

[0084] Specifically, after obtaining the obstacle avoidance path, the path can be compared and integrated with the initial driving path to generate the final target driving path. This process involves the priority evaluation of the obstacle avoidance path to ensure that the driving distance and time are reduced as much as possible under the premise of safety. At the same time, the system will also monitor the dynamic state of the vehicle in real time, such as speed, acceleration, steering angle, etc., to ensure the real-time and accuracy of path planning.

[0085] In addition, the generation of the target driving path also takes into account the dynamic performance limitations of the vehicle, such as maximum steering angle, maximum acceleration and braking capacity, to avoid generating a path that exceeds the actual operating capabilities of the vehicle. When necessary, the system will also dynamically adjust the target driving path in combination with real-time traffic information, such as traffic congestion, construction areas, temporary speed limits, etc., to provide a safer and more efficient driving experience.

[0086] Ultimately, the target driving path will be presented to the driver through the on-board navigation system, or directly used for path control of the autonomous vehicle. In practical applications, this path planning method can significantly improve the driving safety and comfort of the vehicle in complex traffic environments, while reducing the additional driving costs caused by obstacle avoidance.

[0087] Step 250, triggering a corresponding auxiliary warning function based on the target driving path and the current driving state of the vehicle.

[0088] For details, please see Figure 1 Step 150 of the illustrated embodiment will not be described in detail here.

[0089] The assisted driving warning method of the embodiment of the present invention improves the comprehensiveness and accuracy of assisted driving information acquisition by acquiring driving scene data and vehicle network data of the own vehicle in the target area; obtains road condition data and vehicle intention data of the target area by extracting driving scene data, performs data analysis on driving scene data and vehicle network data, obtains abnormal scene data in the target area, and plans the driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain the target driving path, thereby improving the adaptability of the assisted driving vehicle to highly dynamic and uncertain traffic environments; triggers the corresponding assisted warning function based on the target driving path and the current driving status of the own vehicle, thereby improving the accuracy and reliability of assisted driving warnings, and providing necessary guarantees for safe driving of the vehicle.

[0090] Figure 3 FIG. 2 is a schematic diagram showing a structural diagram of an embodiment of an auxiliary driving warning device of the present invention. Figure 3 As shown, the device comprises:

[0091] The data acquisition module 310 is used to acquire the driving scene data and vehicle networking data of the vehicle in the target area;

[0092] The data analysis module 320 is used to extract the driving scene data to obtain the road condition data and vehicle intention data of the target area;

[0093] The data processing module 330 is used to analyze the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area;

[0094] The path determination module 340 is used to plan the driving path of the vehicle based on the road condition data, the vehicle intention data, and the abnormal scene data to obtain the target driving path;

[0095] The auxiliary driving module 350 is used to trigger the corresponding auxiliary warning function based on the target driving path and the current driving status of the vehicle.

[0096] In an optional implementation, the data acquisition module 310 includes:

[0097] The first data acquisition submodule is used to acquire the sensor detection data of the vehicle and the traffic data of the target area;

[0098] The data analysis submodule is used to analyze the sensor detection data and traffic data to obtain driving scene data;

[0099] A second data acquisition submodule is used to acquire social media data and traffic broadcast data for a target area;

[0100] The information extraction submodule is used to extract traffic information based on social media data and traffic broadcast data to obtain Internet of Vehicles data.

[0101] In an optional implementation, the data analysis module 320 includes:

[0102] The static feature extraction submodule is used to extract dynamic features of the driving scene data based on the driving action features of the vehicle and the action features of vehicles and pedestrians in the target area to obtain dynamic scene data;

[0103] The third data acquisition submodule is used to obtain the road condition data of the target area based on the interaction behavior of vehicles and pedestrians in the dynamic scene data;

[0104] The intention data acquisition submodule is used to obtain vehicle intention data based on the trajectory data of vehicles around the vehicle in the dynamic scene data.

[0105] In an optional implementation, the data processing module 330 includes:

[0106] The dynamic feature acquisition submodule is used to extract static features of the driving scene data based on the driving action features of the vehicle and the action features of vehicles and pedestrians in the target area to obtain static scene data;

[0107] The scene analysis submodule is used to analyze the static scene data and obtain the abnormal road surface in the target area;

[0108] The road section information acquisition submodule is used to analyze the Internet of Vehicles data and obtain the accident sections and construction sections in the target area;

[0109] The scene data determination submodule is used to determine abnormal scene data in the target area based on abnormal road surfaces, accident areas and construction sections.

[0110] In some optional implementations, the path determination module 340 includes:

[0111] The path planning submodule is used to plan the driving path of the vehicle in the target area based on the road condition data and abnormal scene data to obtain the initial driving path;

[0112] A path generation submodule, used to determine the obstacle avoidance path corresponding to the current section in the initial driving path based on the vehicle intention data;

[0113] The path updating submodule is used to update the initial driving path based on the obstacle avoidance path to obtain the target driving path.

[0114] In some optional embodiments, the auxiliary driving module 350 includes:

[0115] The first warning submodule is used to trigger the auxiliary warning function of the path deviation based on the deviation information between the current driving state of the vehicle and the target driving path;

[0116] The second warning submodule is used to trigger the auxiliary warning function of vehicle collision based on the current driving state of the vehicle and the vehicle intention data.

[0117] In some optional implementations, the assisted driving module 350 is further configured to receive user feedback information based on the assisted warning function; and optimize the assisted warning function based on the feedback information.

[0118] The further functional description of each of the above modules and units is the same as that of the above corresponding method embodiments and will not be repeated here.

[0119] Through the above device and its components, the technical solution provided by the embodiment of the present invention has the following advantages:

[0120] The assisted driving warning device of the embodiment of the present invention improves the comprehensiveness and accuracy of assisted driving information acquisition by acquiring driving scene data and vehicle networking data of the own vehicle in the target area; obtains road condition data and vehicle intention data of the target area by extracting driving scene data, and obtains abnormal scene data in the target area by performing data analysis on the driving scene data and vehicle networking data, so as to plan the driving path of the own vehicle based on the road condition data, vehicle intention data, and abnormal scene data to obtain the target driving path, thereby improving the adaptability of the assisted driving vehicle to highly dynamic and uncertain traffic environments; and triggers the corresponding assisted warning function based on the target driving path and the current driving status of the own vehicle, thereby improving the accuracy and reliability of the assisted driving warning, and providing necessary guarantees for safe driving of the vehicle.

[0121] Figure 4 FIG. 2 shows a schematic diagram of the structure of an embodiment of an auxiliary driving warning system of the present invention. Figure 4 As shown, the system includes: a multi-source data fusion module, a real-time road condition prediction module, an anomaly detection module, a risk area warning module, a vehicle intention recognition module, a dynamic path planning module, a human-computer interaction module, and an adaptive optimization module.

[0122] Among them, it should be noted that the multi-source data fusion module of this system is used for sensor data integration and unstructured data processing, the real-time road condition prediction module of this system is used for dynamic traffic flow prediction and pedestrian behavior prediction, the anomaly detection module of this system is used for road anomaly identification and weather condition assessment, the risk area warning module of this system is used for accident-prone areas identification and construction area monitoring, the vehicle intention recognition module of this system is used for surrounding vehicle trajectory prediction and driver intention analysis, the dynamic path planning module of this system is used for real-time optimal path calculation and emergency obstacle avoidance path generation, the human-computer interaction module of this system is used for driving status visualization and warning information push, and the adaptive optimization module of this system is used for online model update and system performance self-evaluation.

[0123] In this embodiment, it should also be noted that the multi-source data fusion module of the system also includes a sensor data integration unit and an unstructured data processing unit. The sensor data integration unit integrates multi-source sensor data of laser radar, camera, and millimeter wave radar through the Kalman filter algorithm to reduce noise and improve data accuracy, which is used to achieve all-round and high-precision road environment perception. The unstructured data processing unit uses a deep learning model (including Transformer) to process unstructured data from social media and traffic broadcasts, extract useful information, and is used to capture the real-time traffic dynamics of emergencies and road closures. In this embodiment, it should also be noted that the real-time road condition prediction module of the system also includes a dynamic traffic flow prediction unit and a pedestrian behavior prediction unit. The dynamic traffic flow prediction unit uses the long short-term memory network model LSTM to analyze historical traffic data and predict future traffic flow and congestion trends, which is used to plan congestion avoidance routes in advance and optimize driving strategies. The pedestrian behavior prediction unit uses the generative adversarial network model GAN ​​to simulate the possible action paths of pedestrians and predict the interaction between pedestrians and vehicles, which is used to enhance the ability to respond to the uncertain behavior of pedestrians crossing the road.

[0124] In this embodiment, it should also be noted that the anomaly detection module of the system also includes a road anomaly recognition unit and a weather condition evaluation unit. The road anomaly recognition unit uses a convolutional neural network model CNN combined with image recognition technology to detect road potholes, water accumulation, and obstacle anomalies, and is used to instantly adjust driving strategies to avoid accidents. The weather condition evaluation unit integrates meteorological station data and machine learning models to evaluate the impact of rain, snow, and haze on driving, and is used to adjust vehicle control system parameters according to weather changes to ensure safe driving.

[0125] In this embodiment, it should also be noted that the risk area warning module of the system also includes an accident-prone area identification unit and a construction area monitoring unit. The accident-prone area identification unit uses a clustering algorithm (including DBSCAN) to analyze historical accident data and identify high-risk sections and time periods for slowing down or detouring in advance to reduce accident risks. The construction area monitoring unit monitors road construction information through a geographic information system (GIS) and real-time data updates to dynamically adjust the path and avoid construction delays.

[0126] In this embodiment, it should also be noted that the vehicle intention recognition module of the system also includes a surrounding vehicle trajectory prediction unit and a driver intention analysis unit. The surrounding vehicle trajectory prediction unit adopts the graph convolutional network model GCN to analyze the driving trajectories of surrounding vehicles and predict their future movements, which is used to improve collaborative driving capabilities and reduce collision risks. The driver intention analysis unit uses the hidden Markov model HMM combined with vehicle dynamic data to analyze the driver's intention (including lane changing and braking), which is used to respond to the behavior of other vehicles more accurately and improve driving safety.

[0127] In this embodiment, it should also be noted that the dynamic path planning module of the system also includes a real-time optimal path calculation unit and an emergency obstacle avoidance path generation unit. The real-time optimal path calculation unit applies the A* algorithm combined with dynamic weight adjustment to quickly calculate the optimal path according to the real-time road conditions, so as to quickly respond to traffic changes and optimize the driving route. The emergency obstacle avoidance path generation unit uses a reinforcement learning algorithm to generate an obstacle avoidance path in an emergency situation, so as to ensure safe avoidance in emergency situations.

[0128] In this embodiment, it should also be noted that the human-computer interaction module of the system also includes a driving status visualization unit and a warning information push unit. The driving status visualization unit uses augmented reality technology to display information about surrounding vehicles, pedestrians, and obstacles to enhance the driver's perception of complex environments. The warning information push unit uses natural language processing (NLP) technology to generate concise warning information through voice or screen prompts to effectively convey emergency or important information and reduce the driver's reaction time.

[0129] In this embodiment, it should also be noted that the adaptive optimization module of the system also includes an online model updating unit and a system performance self-evaluation unit. The online model updating unit uses an online learning algorithm (including Online Learning with Bandit Feedback) to continuously optimize the prediction model to continuously improve the system's adaptability to new traffic patterns. The system performance self-evaluation unit uses Bayesian optimization to regularly evaluate and adjust the system performance to find the optimal parameter configuration to ensure that the system always maintains the best working state and improves the overall prediction and response capabilities.

[0130] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a vehicle provided by an optional embodiment of the present invention, such as Figure 5 As shown, the vehicle includes: one or more processors 510, a memory 520, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the vehicle, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple vehicles can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 510 is taken as an example.

[0131] The processor 510 may be a central processing unit, a network processor or a combination thereof. The processor 510 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0132] The memory 520 stores instructions executable by at least one processor 510, so that at least one processor 510 executes the method shown in the above embodiment.

[0133] The memory 520 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a vehicle displayed on a small program landing page, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 520 may optionally include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the vehicle via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a server cluster, a mobile communication network, and a combination thereof.

[0134] The memory 520 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 520 may also include a combination of the above types of memory.

[0135] The vehicle also includes a communication interface 530 for the vehicle to communicate with other devices or communication networks.

[0136] An embodiment of the present invention also provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is run on a vehicle / assisted driving warning device, the vehicle / assisted driving warning device executes the assisted driving warning method in any of the above method embodiments.

[0137] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0138] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0139] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0140] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. An assisted driving warning method, characterized in that: Applied to a vehicle, the method comprises: Acquire driving scene data and Internet of Vehicles data of the vehicle in the target area; Extracting the driving scene data to obtain the road condition data and vehicle intention data of the target area; Performing data analysis on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area; Based on the road condition data, the vehicle intention data, and the abnormal scenario data, a driving path of the vehicle is planned to obtain a target driving path; Based on the target driving path and the current driving state of the vehicle, a corresponding auxiliary warning function is triggered.

2. The method according to claim 1, characterized in that: The obtaining of driving scene data and Internet of Vehicles data of the vehicle in the target area includes: Acquiring sensor detection data of the vehicle and traffic data of the target area; Performing data analysis on the sensor detection data and the traffic data to obtain the driving scene data; Acquire social media data and traffic broadcast data for the target area; Traffic information is extracted based on the social media data and the traffic broadcast data to obtain the Internet of Vehicles data.

3. The method according to claim 1, characterized in that The extracting the driving scene data to obtain the road condition data and vehicle intention data of the target area includes: Based on the driving action characteristics of the vehicle and the action characteristics of vehicles and pedestrians in the target area, extracting dynamic features from the driving scene data to obtain dynamic scene data; Based on the interactive behaviors of the vehicles and pedestrians in the dynamic scene data, obtaining the road condition data of the target area; The vehicle intention data is obtained based on the trajectory data of the vehicles around the vehicle in the dynamic scene data.

4. The method according to claim 1, characterized in that The performing data analysis on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area includes: Based on the driving action characteristics of the vehicle and the action characteristics of vehicles and pedestrians in the target area, static feature extraction is performed on the driving scene data to obtain static scene data; Performing data analysis on the static scene data to obtain abnormal road surfaces in the target area; Performing data analysis on the Internet of Vehicles data to obtain accident sites and construction sections within the target area; Based on the abnormal road surface, the accident section and the construction section, abnormal scene data in the target area is determined.

5. The method according to claim 1, characterized in that The planning of the driving path of the vehicle based on the road condition data, the vehicle intention data, and the abnormal scene data to obtain a target driving path includes: Based on the road condition data and the abnormal scene data, planning a driving path of the vehicle in the target area to obtain an initial driving path; Determining an obstacle avoidance path corresponding to a current section in the initial driving path based on the vehicle intention data; The initial driving path is updated based on the obstacle avoidance path to obtain the target driving path.

6. The method according to any one of claims 1 to 5, characterized in that: The triggering of a corresponding auxiliary warning function based on the target driving path and the current driving state of the vehicle includes: Based on the deviation information between the current driving state of the vehicle and the target driving path, triggering the auxiliary warning function of path deviation; Based on the current driving state of the vehicle and the vehicle intention data, the auxiliary warning function of vehicle collision is triggered.

7. The method according to claim 6, characterized in that The method further comprises: Receiving feedback information from users based on the auxiliary warning function; The auxiliary warning function is optimized based on the feedback information.

8. An auxiliary driving warning device, characterized in that: Applied to a vehicle, the device comprises: A data acquisition module, used to acquire driving scene data and Internet of Vehicles data of the vehicle in the target area; A data analysis module, used to extract the driving scene data to obtain the road condition data and vehicle intention data of the target area; A data processing module, used for performing data analysis on the driving scene data and the Internet of Vehicles data to obtain abnormal scene data in the target area; A path determination module, used to plan the driving path of the vehicle based on the road condition data, the vehicle intention data, and the abnormal scene data to obtain a target driving path; The auxiliary driving module is used to trigger the corresponding auxiliary warning function based on the target driving path and the current driving state of the vehicle.

9. A vehicle, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the assisted driving warning method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction, and when the executable instruction is executed on the vehicle, the vehicle executes the operation of the assisted driving warning method as described in any one of claims 1 to 7.

Images