High-speed driving vehicle cut-in intention prediction method and system, storage medium and vehicle

Abstract

The invention discloses a high-speed driving vehicle cut-in intention prediction method and system, a storage medium and a vehicle, and relates to the technical field of vehicle behavior prediction.The method comprises the steps that region division is conducted on a target road in front of the vehicle, and a straight moving region, a lane changing region and a lane changing buffer region are obtained; collecting vehicle dynamic data of at least one target vehicle in the straight moving area, the lane changing area and the lane changing buffer area in real time; constructing a vehicle cut-in intention prediction model based on a preset long short-term memory network, and training and verifying the vehicle cut-in intention prediction model; and importing the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model, and outputting vehicle intention data. By adopting the method disclosed by the invention, the adopted sensor equipment is simple, the cut-in intention of the high-speed vehicle can be predicted only through the existing road section speed detection and the analysis of related data acquired by the vehicle sensor, and the manufacturing cost of the vehicle can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle behavior prediction, and in particular to a method, system, storage medium and vehicle for predicting the cutting-in intention of a high-speed vehicle. Background Art

[0002] With the continuous development of autonomous driving technology, it is particularly important to judge the vehicle's cutting intention and behavior during high-speed driving. Most existing prediction methods are based on vehicle motion state, speed, acceleration and other parameters, but in complex traffic environments, the prediction accuracy and timeliness need to be improved.

[0003] Existing intelligent driving solutions rely on various sensors when facing the problem of vehicle cut-in. However, when faced with high-speed cut-in scenarios, the sensors have the problem of too late detection timing, which may not be enough to deal with vehicles that suddenly cut in, thereby increasing the risk of accidents. At the same time, due to the lack of intelligent processing mechanisms, the decision-making system is still unable to accurately analyze and predict the scene of a vehicle suddenly cutting in at high speed. This means that when dealing with emergencies such as high-speed cut-in, vehicles can often only take simple avoidance or braking measures, and cannot achieve higher levels of coordination and decision-making. Modern transportation technology uses technologies such as V2V (vehicle-to-vehicle communication) and V2I (vehicle-to-road collaboration) to allow vehicles to exchange and coordinate information with other vehicles and infrastructure around them, but there are still problems such as high equipment prices, huge initial investment, and the need to maintain software and hardware systems and network security.

[0004] Therefore, the current solution for detecting the cutting-in intention of a high-speed vehicle still has the problem of high cost, which significantly increases the manufacturing cost of the vehicle. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method, system, storage medium and vehicle for predicting the cutting-in intention of a high-speed vehicle, aiming to solve the problem that the solutions in the prior art for detecting the cutting-in intention of a high-speed vehicle are still costly and significantly increase the manufacturing cost of the vehicle.

[0006] A first aspect of the present invention is to provide a method for predicting a high-speed vehicle's cut-in intention, the method comprising:

[0007] During the driving process of the vehicle, the target road in front of the vehicle is divided into areas such as a straight-ahead area, a lane-changing area and a lane-changing buffer area;

[0008] The vehicle dynamic data of at least one target vehicle in the straight-ahead area, the lane-changing area and the lane-changing buffer area are collected in real time by using a speed sensor preset on the target road and a camera and a radar device preset on the vehicle;

[0009] Building a vehicle cut-in intention prediction model based on a preset long short-term memory network, and training and verifying the vehicle cut-in intention prediction model;

[0010] The vehicle dynamic data of the target vehicle is imported into the vehicle cut-in intention prediction model, and the vehicle intention data is output.

[0011] According to one aspect of the above technical solution, during the driving process of the vehicle, the target road in front of the vehicle is divided into regions to obtain a straight-ahead area, a lane-changing area and a lane-changing buffer area, including:

[0012] Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign;

[0013] Acquiring current traffic flow data of the target road and the current speed of the vehicle;

[0014] The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

[0015] According to one aspect of the above technical solution, the step of collecting vehicle dynamic data of at least one target vehicle located in a straight-ahead area, a lane-changing area, and a lane-changing buffer area in real time by means of a speed sensor preset on a target road, and a camera and a radar device preset on a vehicle includes:

[0016] The driving position, driving speed and acceleration of at least one target vehicle in the straight-ahead area, lane-changing area and lane-changing buffer area are collected in real time by using speed sensors preset on both sides of the vehicle road or above the road, and cameras and radar devices preset on the vehicle;

[0017] The driving position, driving speed and acceleration are marked according to a unified timestamp, and data cleaning and filtering are performed to obtain vehicle dynamic data of the target vehicle;

[0018] The acceleration includes longitudinal acceleration and lateral acceleration.

[0019] According to one aspect of the above technical solution, the step of importing the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and outputting the vehicle intention data includes:

[0020] Importing the driving position, driving speed and acceleration in the vehicle dynamic data into the vehicle cut-in intention prediction model in sequence;

[0021] The vehicle dynamic data is analyzed by the vehicle cut-in intention prediction model to output vehicle intention data.

[0022] According to one aspect of the above technical solution, the step of analyzing the vehicle dynamic data by the vehicle cut-in intention prediction model and outputting the vehicle intention data includes:

[0023] The driving position, driving speed and acceleration of the target vehicle collected in real time are sequentially imported into the pre-trained vehicle cut-in intention prediction model;

[0024] The probability distribution of various driving intentions of the target vehicle is calculated and output to obtain vehicle intention data.

[0025] According to one aspect of the above technical solution, the probability distribution of various driving intentions of the target vehicle includes cutting into the lane, maintaining straight driving, accelerating, and decelerating.

[0026] A second aspect of the present invention is to provide a high-speed vehicle cut-in intention prediction system, which is applied to the method described in the above technical solution, and the system comprises:

[0027] The area division module is used to divide the target road in front of the vehicle into areas during the vehicle's driving process, and obtain the straight-ahead area, the lane-changing area and the lane-changing buffer area;

[0028] A data acquisition module is used to collect vehicle dynamic data of at least one target vehicle located in a straight-ahead area, a lane-changing area, and a lane-changing buffer area in real time through a speed sensor preset on a target road, and a camera and a radar device preset on the vehicle;

[0029] A model building module, used to build a vehicle cut-in intention prediction model based on a preset long short-term memory network, and train and verify the vehicle cut-in intention prediction model;

[0030] The intention output module is used to import the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and output vehicle intention data.

[0031] According to one aspect of the above technical solution, the area division module is specifically used for:

[0032] Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign;

[0033] Acquiring current traffic flow data of the target road and the current speed of the vehicle;

[0034] The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

[0035] A third aspect of the present invention provides a readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method described in the above technical solution.

[0036] A fourth aspect of the present invention provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the above technical solution when executing the program.

[0037] Compared with the prior art, the method, system, storage medium and vehicle for predicting the cutting-in intention of a high-speed vehicle shown in the present invention have the following beneficial effects:

[0038] The present invention divides the target road in front of the vehicle into regions during the vehicle driving process, obtains the straight-through area, the lane change area and the lane change buffer area, can timely dynamically detect and track the vehicles cutting in at high speed in multiple regions, and then builds a prediction model of the surrounding vehicle driving area through a long short-term memory network (LSTM). The LSTM model can understand the interactive behavior of the vehicle-vehicle, respond to the changes in the traffic environment, so that the vehicle driving area can be predicted in real time in the actual scene, and the vehicle intention data of the target vehicle is output to the decision module of the automatic driving system, providing the vehicle with real-time and accurate driving area prediction information, and finally timely judging the cutting-in intention of the target vehicle. The method shown in the present invention is adopted, and the sensor equipment used is simple. Only by obtaining relevant data through the existing road section speed detection and the self-vehicle sensor for analysis, the cutting-in intention of the high-speed vehicle can be predicted, which can effectively reduce the vehicle cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0040] Figure 1 It is a flow chart of a method for predicting a high-speed vehicle's cut-in intention in one embodiment of the present invention;

[0041] Figure 2 The structure block diagram of a high-speed vehicle cut-in intention prediction system in one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. Several embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0044] Embodiment 1

[0045] See also Figure 1 The first embodiment of the present invention provides a method for predicting a high-speed vehicle's cut-in intention, the method comprising steps S10 to S40:

[0046] Step S10, during the driving process of the vehicle, the target road in front of the vehicle is divided into regions to obtain a straight-ahead region, a lane-changing region and a lane-changing buffer region.

[0047] In this embodiment, the vehicle is driving at high speed, that is, on urban expressways and highways. The intelligent driving sensor on the vehicle is used to detect the target road being driven, thereby obtaining video information, radar information, etc. The target road in front of the vehicle is then divided into regions based on the video information, radar information, etc. Specifically, the target road in front of the vehicle is divided into a straight-ahead area for the vehicle and a lane-changing area and a lane-changing buffer area for the target vehicle.

[0048] It should be noted that the lane change area and lane change buffer zone are road areas that are sequentially transitioned to the straight-ahead area. The lane change area refers to the road area in front of the lane and the adjacent lane, usually referring to the area on both sides of the lane line, while the lane change buffer zone mainly refers to the ramp area that merges into the injection ramp.

[0049] In this embodiment, the step of dividing the target road ahead of the vehicle into a straight-ahead area, a lane-changing area, and a lane-changing buffer area includes:

[0050] Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign;

[0051] Acquiring current traffic flow data of the target road and the current speed of the vehicle;

[0052] The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

[0053] Among them, the road signs on the target road include road guidance signs and speed limit signs. The road grade of the target road, such as expressways and urban expressways, is determined by the road guidance signs and speed limit signs, so that the road grade conditions of the target road can be determined, so as to ultimately determine the vehicle spacing, speed limit, etc. required for the target road.

[0054] Step S20, real-time vehicle dynamic data of at least one target vehicle in the straight-ahead area, the lane-changing area, and the lane-changing buffer area are collected through a speed sensor preset on the target road, and a camera and a radar device preset on the vehicle.

[0055] In this embodiment, the steps of collecting vehicle dynamic data of at least one target vehicle in the straight-ahead area, the lane-changing area, and the lane-changing buffer area in real time by using a speed sensor preset on the target road, and a camera and a radar device preset on the vehicle include:

[0056] The driving position, driving speed and acceleration of at least one target vehicle in the straight-ahead area, lane-changing area and lane-changing buffer area are collected in real time by using speed sensors preset on both sides of the vehicle road or above the road, and cameras and radar devices preset on the vehicle;

[0057] The driving position, driving speed and acceleration are marked according to a unified timestamp, and data cleaning and filtering are performed to obtain vehicle dynamic data of the target vehicle;

[0058] The acceleration includes longitudinal acceleration and lateral acceleration.

[0059] Specifically, by using speed sensors preset on both sides of the vehicle road or on the road, the driving speed and acceleration of at least one target vehicle located in the straight-ahead area or the lane-changing buffer area or the lane-changing area are obtained, and the acceleration includes longitudinal acceleration and lateral acceleration. In addition, by using cameras and radar devices preset on the vehicle, the driving position of the target vehicle located in the straight-ahead area or the lane-changing buffer area or the lane-changing area is obtained in real time, thereby determining the relative position and distance between the two based on the driving position of the target vehicle and the driving position of the own vehicle.

[0060] In addition, after obtaining the target vehicle's driving position, driving speed and acceleration, they will be marked according to a unified timestamp to facilitate subsequent time series analysis. The data format of driving position, driving speed and acceleration can be a structured table or JSON object of timestamp + position (x, y, z), speed, acceleration.

[0061] Step S30, constructing a vehicle cut-in intention prediction model based on a preset long short-term memory network, and training and verifying the vehicle cut-in intention prediction model.

[0062] In this embodiment, the steps of constructing a vehicle cut-in intention prediction model and performing training and verification include:

[0063] 1. Data preparation

[0064] Step 1.1: Data Collection

[0065] Collect dynamic data of many vehicles from vehicle sensors, Internet of Vehicles systems or historical trajectory data, including but not limited to driving position (GPS coordinates), speed, acceleration, etc.

[0066] Labeled data: For the training set, either human annotation or a rule-based algorithm is needed to determine which data points represent vehicle cut-in events.

[0067] Step 1.2: Data preprocessing

[0068] Clean data: remove outliers and fill in missing values.

[0069] Feature engineering: Extract and construct features that are useful for prediction, such as speed change rate, acceleration change rate, lane information, surrounding vehicle information, etc.

[0070] Data normalization: Scale feature values ​​to a suitable range to speed up model training and improve performance.

[0071] Time series partitioning: Divide the continuous data points into time series segments, each segment contains a fixed number of time steps, which are used as input for the LSTM model.

[0072] 2. LSTM model construction

[0073] Step 2.1: Select a framework

[0074] Use a deep learning framework such as TensorFlow, PyTorch, or Keras to build an LSTM model.

[0075] Step 2.2: Define the model structure

[0076] Input layer: accepts preprocessed time series data.

[0077] LSTM layers: One or more LSTM layers are used to capture long-term dependencies in time series.

[0078] Fully connected layer (Dense layer): converts the output of the LSTM layer into the final intent prediction.

[0079] Output layer: Usually uses the softmax activation function to output the probability distribution of each intent.

[0080] Step 2.3: Set hyperparameters

[0081] The number of units and layers of the LSTM layer.

[0082] Optimizers (such as Adam, RMSprop).

[0083] Loss function (such as cross entropy loss).

[0084] Learning rate, batch size, number of iterations, etc.

[0085] 3. Model training

[0086] Step 3.1: Divide the dataset

[0087] Divide the dataset into training, validation, and test sets (usually in a ratio of 70%, 15%, and 15%).

[0088] Step 3.2: Train the model

[0089] The LSTM model is trained using the training set data, and the model parameters are optimized using the back propagation algorithm.

[0090] Monitor the loss and accuracy during training to assess the model's learning progress.

[0091] Step 3.3: Early stopping (optional)

[0092] If the performance on the validation set does not improve after several consecutive iterations, training is stopped to avoid overfitting.

[0093] 4. Model Validation and Evaluation

[0094] Step 4.1: Validate the model

[0095] Use the validation set data to evaluate the performance of the model and calculate indicators such as accuracy, recall, and F1 score.

[0096] Confusion Matrix: Analyze the prediction accuracy of the model on different intents.

[0097] Step 4.2: Adjust the model

[0098] Adjust the model structure, hyperparameters, or feature selection based on the validation results to improve performance.

[0099] Repeat the training and validation steps until the model performance reaches a satisfactory level.

[0100] 5. Model testing and deployment

[0101] Step 5.1: Test the model

[0102] Use the test set data to evaluate the final performance of the model to ensure that the model performs well on unseen data.

[0103] Step 5.2: Model deployment

[0104] Integrate the trained model into the vehicle control system or Internet of Vehicles platform to achieve real-time vehicle cut-in intention prediction.

[0105] Monitor the performance of your model in real-world applications and fine-tune or update it as needed.

[0106] 6. Continuous Optimization

[0107] Collect more data, especially data with more cutting events and complex scenarios, to further train and optimize the model.

[0108] Explore other deep learning techniques such as attention mechanism, Transformer, etc. to improve the predictive power of the model.

[0109] Evaluate the computational efficiency and resource requirements of the model, and optimize the model to suit different hardware platforms.

[0110] Step S40, importing the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model, and outputting vehicle intention data.

[0111] In this embodiment, the step of importing the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and outputting the vehicle intention data includes:

[0112] Importing the driving position, driving speed and acceleration in the vehicle dynamic data into the vehicle cut-in intention prediction model in sequence;

[0113] The vehicle dynamic data is analyzed by the vehicle cut-in intention prediction model to output vehicle intention data.

[0114] The step of analyzing the vehicle dynamic data by the vehicle cut-in intention prediction model and outputting the vehicle intention data comprises:

[0115] The driving position, driving speed and acceleration of the target vehicle collected in real time are sequentially imported into the pre-trained vehicle cut-in intention prediction model;

[0116] The probability distribution of various driving intentions of the target vehicle is calculated and output to obtain vehicle intention data.

[0117] Among them, the probability distribution of various driving intentions of the target vehicle, various driving intentions include cutting into the lane, maintaining straight driving, accelerating, and decelerating.

[0118] Specifically, the target vehicle's dynamic data (the target vehicle's driving position, driving speed and acceleration) collected in real time is imported into the trained vehicle cut-in intention prediction model, which will perform logical reasoning and analysis based on the input data and output vehicle intention data. The vehicle intention data usually includes whether the target vehicle intends to cut into the adjacent lane, the timing of the cut-in and the cut-in speed.

[0119] Then, based on the vehicle intention data output by the model, the vehicle control system can make corresponding responses, such as slowing down in advance, adjusting lanes, etc.

[0120] At the same time, the prediction results will be fed back to the driver or the Internet of Vehicles system to improve driving safety and efficiency.

[0121] In summary, compared with the prior art, the method for predicting the cutting-in intention of a high-speed vehicle shown in this embodiment has the following beneficial effects:

[0122] This embodiment divides the target road in front of the vehicle into regions during the vehicle's driving process, obtains a straight-through area, a lane-changing area, and a lane-changing buffer area, and can timely dynamically detect and track vehicles that cut in at high speed in multiple areas, and then builds a prediction model of the surrounding vehicle driving area through a long short-term memory network (LSTM). The LSTM model can understand the interactive behavior of the vehicle-vehicle interface and respond to changes in the traffic environment, so that the vehicle driving area can be predicted in real time in the actual scene, and the vehicle intention data of the target vehicle is output to the decision module of the automatic driving system, providing the vehicle with real-time and accurate driving area prediction information, and finally timely judging the target vehicle's cutting-in intention. Using the method shown in this embodiment, the sensor equipment used is simple, and the cutting-in intention of high-speed vehicles can be predicted only by analyzing the existing road section speed detection and the relevant data obtained by the vehicle sensor, which can effectively reduce the vehicle cost.

[0123] Embodiment 2

[0124] See also Figure 2 The second embodiment of the present invention provides a high-speed vehicle cut-in intention prediction system, which is applied to the method described in the above embodiment, and the system comprises:

[0125] The area division module 10 is used to divide the target road in front of the vehicle into areas during the vehicle's driving process to obtain a straight-ahead area, a lane-changing area, and a lane-changing buffer area;

[0126] The data acquisition module 20 is used to collect the vehicle dynamic data of at least one target vehicle in the straight-ahead area, the lane-changing area and the lane-changing buffer area in real time through a speed sensor preset on the target road, and a camera and a radar device preset on the vehicle;

[0127] A model building module 30, for building a vehicle cut-in intention prediction model based on a preset long short-term memory network, and training and verifying the vehicle cut-in intention prediction model;

[0128] The intention output module 40 is used to import the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and output vehicle intention data.

[0129] The area division module 10 is specifically used for:

[0130] Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign;

[0131] Acquiring current traffic flow data of the target road and the current speed of the vehicle;

[0132] The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

[0133] Compared with the prior art, the high-speed vehicle cut-in intention prediction system shown in this embodiment has the following beneficial effects:

[0134] This embodiment divides the target road in front of the vehicle into regions during the vehicle's driving process, and obtains a straight-through area, a lane change area, and a lane change buffer area, so that the vehicles cutting in at high speed in multiple areas can be dynamically detected and tracked in a timely manner. Then, a prediction model of the surrounding vehicle driving area is constructed through a long short-term memory network (LSTM). The LSTM model can understand the interactive behavior between vehicles and vehicles, respond to changes in the traffic environment, and make it possible to predict the vehicle driving area in real time in actual scenarios, and output the vehicle intention data of the target vehicle to the decision module of the automatic driving system, so as to provide the vehicle with real-time and accurate driving area prediction information, and finally judge the target vehicle's cutting-in intention in a timely manner. The system shown in this embodiment uses simple sensor equipment, and only through the existing road section speed detection and the relevant data obtained by the vehicle sensor for analysis, the high-speed vehicle's cutting-in intention can be predicted, which can effectively reduce the vehicle cost.

[0135] Embodiment 3

[0136] A third embodiment of the present invention provides a readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the method described in the above embodiment is implemented.

[0137] Embodiment 4

[0138] A fourth aspect of the present invention is to provide a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the above embodiment when executing the program.

[0139] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0140] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for predicting a high-speed vehicle's cutting-in intention, characterized in that: The method comprises: During the driving process of the vehicle, the target road in front of the vehicle is divided into areas such as a straight-ahead area, a lane-changing area and a lane-changing buffer area; The vehicle dynamic data of at least one target vehicle in the straight-ahead area, the lane-changing area and the lane-changing buffer area are collected in real time by using a speed sensor preset on the target road and a camera and a radar device preset on the vehicle; Building a vehicle cut-in intention prediction model based on a preset long short-term memory network, and training and verifying the vehicle cut-in intention prediction model; The vehicle dynamic data of the target vehicle is imported into the vehicle cut-in intention prediction model, and the vehicle intention data is output.

2. The method for predicting the cutting-in intention of a high-speed vehicle according to claim 1, characterized in that: During the driving process of the vehicle, the target road ahead of the vehicle is divided into regions to obtain a straight-ahead region, a lane-changing region and a lane-changing buffer region, including: Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign; Acquiring current traffic flow data of the target road and the current speed of the vehicle; The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

3. The method for predicting the cutting-in intention of a high-speed vehicle according to claim 1, characterized in that: The step of collecting vehicle dynamic data of at least one target vehicle in a straight-ahead area, a lane-changing area, and a lane-changing buffer area in real time by using a speed sensor preset on a target road, and a camera and a radar device preset on a vehicle includes: The driving position, driving speed and acceleration of at least one target vehicle in the straight-ahead area, lane-changing area and lane-changing buffer area are collected in real time by using speed sensors preset on both sides of the vehicle road or above the road, and cameras and radar devices preset on the vehicle; The driving position, driving speed and acceleration are marked according to a unified timestamp, and data cleaning and filtering are performed to obtain vehicle dynamic data of the target vehicle; The acceleration includes longitudinal acceleration and lateral acceleration.

4. The method for predicting the cutting-in intention of a high-speed vehicle according to claim 3, characterized in that: The step of importing the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and outputting the vehicle intention data comprises: Importing the driving position, driving speed and acceleration in the vehicle dynamic data into the vehicle cut-in intention prediction model in sequence; The vehicle dynamic data is analyzed by the vehicle cut-in intention prediction model to output vehicle intention data.

5. The method for predicting the cutting-in intention of a high-speed vehicle according to claim 4, characterized in that: The step of analyzing the vehicle dynamic data by using the vehicle cut-in intention prediction model and outputting vehicle intention data comprises: The driving position, driving speed and acceleration of the target vehicle collected in real time are sequentially imported into the pre-trained vehicle cut-in intention prediction model; The probability distribution of various driving intentions of the target vehicle is calculated and output to obtain vehicle intention data.

6. The method for predicting the cutting-in intention of a high-speed vehicle according to claim 5, characterized in that: The probability distribution of various driving intentions of the target vehicle, wherein the various driving intentions include cutting into the lane, maintaining straight driving, accelerating, and decelerating.

7. A high-speed vehicle cut-in intention prediction system, characterized in that: The method applied to any one of claims 1 to 6, wherein the system comprises: The area division module is used to divide the target road in front of the vehicle into areas during the vehicle's driving process, and obtain the straight-ahead area, the lane-changing area and the lane-changing buffer area; A data acquisition module is used to collect vehicle dynamic data of at least one target vehicle located in a straight-ahead area, a lane-changing area, and a lane-changing buffer area in real time through a speed sensor preset on a target road, and a camera and a radar device preset on the vehicle; A model building module, used to build a vehicle cut-in intention prediction model based on a preset long short-term memory network, and train and verify the vehicle cut-in intention prediction model; The intention output module is used to import the vehicle dynamic data of the target vehicle into the vehicle cut-in intention prediction model and output vehicle intention data.

8. The high-speed vehicle cut-in intention prediction system according to claim 7, characterized in that: The area division module is specifically used for: Acquire a road sign of a target road on which the vehicle is traveling, and determine a road grade condition of the target road according to the road sign; Acquiring current traffic flow data of the target road and the current speed of the vehicle; The target road in front of the vehicle is divided into a straight-ahead area located directly in front of the vehicle, and a lane-changing area and a lane-changing buffer area which are sequentially transitionally connected to the straight-ahead area.

9. A readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images