A multi-dimensional cooperative vehicle lane change decision method based on user portrait

Abstract

The present invention relates to a multi-dimensional collaborative vehicle lane change decision method based on user profiles, and belongs to the field of mobile communication technology. In autonomous driving technology, the traditional method of using neural networks in vehicle lane change decisions mainly relies on single-vehicle data, resulting in poor accuracy and real-time performance. To solve the above problems, first, the vehicle generates a driving feature map and a vehicle trajectory flow map based on sensor data, and shares them with surrounding vehicles and roadside units to achieve data collaboration; secondly, the vehicle downloads the initial decision model from the roadside unit, and makes lane change decisions based on its own and surrounding vehicle data; then, the roadside unit uses a deep neural network to update the model based on these data and traffic factors and re-sends it to the vehicle to ensure the real-time and safety of the decision. The present invention generates a user profile by integrating historical driving characteristics and vehicle trajectory predictions, and then applies a deep neural network to achieve more accurate lane change decisions, thereby improving the safety and operational efficiency of the traffic system.

Description

Technical Field

[0001] The present invention belongs to the field of mobile communication technology and relates to a multi-dimensional collaborative vehicle lane change decision method based on user portraits. Background Art

[0002] With the development of connected vehicles and intelligent driving technologies, information sharing and collaborative decision-making have become crucial for improving traffic safety and efficiency. Existing lane-change decision-making systems primarily rely on single-vehicle data, which has limitations in providing environmental awareness and is unable to fully capture complex surrounding traffic conditions, thus restricting the accuracy and safety of decision-making.

[0003] Traditional lane change decision-making systems typically rely on the vehicle's own sensor data, such as speed, driving trajectory, and steering angle. However, this data is limited, providing only information about the vehicle's own motion and failing to fully understand other vehicles and dynamic changes in the surrounding environment. Especially on busy urban roads or highways, a single vehicle's perspective cannot guarantee comprehensive and safe lane change decisions.

[0004] In a connected vehicle environment, information sharing between vehicles is key to solving this problem. By sharing real-time information such as location, speed, and driving trajectory with surrounding vehicles, vehicles can obtain more comprehensive traffic data, enabling them to make more optimized lane-changing decisions. This information sharing requires efficient, low-latency communication technology, as well as reliable data processing and decision-making models.

[0005] Deep neural networks excel at processing complex data patterns and efficiently learning, and have been widely adopted in the field of autonomous driving. However, existing decision-making models often lack the ability to update in real time during lane change decisions, making them difficult to adapt to rapidly changing traffic conditions. In particular, when traffic conditions change suddenly, existing models are unable to adjust in a timely manner, potentially leading to safety hazards.

[0006] In addition, the user's driving style also has a significant impact on lane change decisions. Driving style includes the driver's behavioral characteristics such as acceleration, braking, and steering. These characteristics can be described by parameters such as vehicle speed, acceleration, and steering wheel angle. Different drivers' driving styles can lead to significant differences in the vehicle's decision-making behavior under similar traffic conditions. For example, some drivers may tend to drive more conservatively and choose to change lanes less frequently, while others may be more aggressive and change lanes frequently in pursuit of faster driving speeds. Differences in user profiles are not only reflected between individual drivers but are also affected by different traffic conditions, road conditions, and driving purposes. In order to improve the personalization and accuracy of lane change decisions, it is necessary to incorporate user profiles into the decision-making model.

[0007] The present invention aims to solve the above problems and proposes a prediction-collaboration-decision-making integrated vehicle lane change decision method based on user portraits. First, the user driving behavior characteristics in historical data are analyzed, and a personalized driving style model is constructed to perform user portraits. Based on different user portraits, the system makes lane change decisions that are more in line with the driver's expectations, thereby improving user experience and safety. Secondly, through vehicle-road collaboration, the vehicle's local data is shared with the real-time information of surrounding vehicles, and decision adjustments are made based on the traffic flow diagram predicted by the vehicle trajectory, so that the CAV can obtain a more comprehensive perception of the traffic environment, quickly adapt to changes in traffic conditions, and reduce potential safety risks. Finally, deep learning models (such as ResNet and Transformer) are used to process and extract complex environmental features, learn key patterns and features from large amounts of traffic data, and improve the accuracy of lane change decisions. Summary of the Invention

[0008] In view of this, the purpose of the present invention is to provide a multi-dimensional collaborative vehicle lane change decision method based on user portraits. This method deeply integrates the historical driving data of connected and autonomous vehicles (CAV) and surrounding vehicles (Surrounding vehicles, SVs), constructs a driving feature picture (DFP) and a trajectory flow diagram (TFD), and uses deep neural networks to provide more accurate and safe decision support for vehicle lane changes through data sharing of road side units (RSU). It aims to achieve more accurate and efficient lane change decisions through historical driving characteristics, vehicle trajectory prediction, and vehicle data sharing. This method combines the vehicle's local sensor data, the edge model trained by RSU, and the shared information of surrounding vehicles to form a closed-loop system of prediction-collaboration-decision-making, thereby improving the safety and operational efficiency of the overall traffic system.

[0009] In order to achieve the above object, the present invention provides the following technical solutions:

[0010] In a first aspect, an embodiment of the present invention provides a multi-dimensional collaborative vehicle lane change decision method based on user profiles according to the characteristics of a vehicle lane change scenario. The method includes the following steps:

[0011] S1: Data sharing model based on CAV-SVs-RSU

[0012] S2: CAV DFP generation solution based on user profile;

[0013] S3: Lane change decision scheme based on DFP and TFD of CAVs and SVs;

[0014] S4: TFD generation scheme for CAV based on lane-changing maneuvers;

[0015] S5: DFP and TFD sharing scheme for CAV;

[0016] S6: Transformer network model based on ResNet.

[0017] Secondly, in S1, a CAV-SV-RSU data sharing model is adopted. This model improves lane change safety by sharing data between CAVs, SVs, and RSUs. CAVs and SVs share the Distributed Feature Plane (DFP) and Transient Flow (TFD) to enhance CAV perception of the surrounding environment. Data sharing between CAVs and RSUs improves model update efficiency. As the accuracy of the new model improves, CAVs and RSUs share edge models to further enhance lane change decision accuracy.

[0018] On the third aspect, in S1 of the embodiment of the present invention, the CAV calculates the lane change incentive parameter by comprehensively considering multiple factors such as the current lane's achievable speed, the current vehicle speed, the distance to the preceding vehicle, and the time interval between preceding vehicles. When the parameter reaches the preset threshold, the system executes the lane change decision process, and the CAV generates a DFP representing the driving characteristics based on the sensor data. Specifically, the CAV collects L feature data from its own sensors and calculates M statistical functions thereof respectively. Based on the calculation results, a two-dimensional matrix is ​​generated, and a DFP reflecting the vehicle's spatiotemporal historical driving characteristics is generated through a sliding time window of S seconds in length. In this way, specific features can be extracted from historical driving information to implicitly describe the user's driving style, and the data used for decision-making will also contain more specific driving style information, thereby more accurately simulating the user's driving style.

[0019] Fourthly, in S2 of an embodiment of the present invention, the vehicle downloads the edge model from the RSU, receives the DFP and TFD of the SVs, and applies the edge decision model based on this data to make lane change decisions. The decision model is trained and updated using a deep neural network, and the SVs include the K vehicles closest to the CAV, including the leading vehicle in the current lane, the leading vehicle in the left adjacent lane, the leading vehicle in the right adjacent lane, the following vehicle in the left adjacent lane, the following vehicle in the right adjacent lane, the parallel vehicles in the left adjacent lane, and the parallel vehicles in the right adjacent lane. The method for generating TFD and DFP for SVs is the same as that for CAVs. The DFP and TFD of SVs can reflect the SVs' historical driving characteristics and predict their future trajectory, making the CAV's lane change decision safer and more accurate.

[0020] In the fifth aspect, in S3 of the embodiment of the present invention, the CAV generates a local TFD based on the output action of the lane change decision. The TFD is a two-dimensional grid matrix generated according to the lane change behavior of the vehicle. By encoding the spatiotemporal information of the grid matrix, the occupancy of obstacles and the change of the vehicle position over time (i.e., the future driving trajectory of the vehicle) are represented. Specifically, the grid positions occupied by obstacles are uniformly set to 1, the value of the vehicle position at time t is encoded as 1, and decreases linearly to 0 over time (i.e., at time t+T D The value of the position is 0, where T D is the time length of the trajectory). This provides a representation of the vehicle's demand for road rights. This encoding allows CAVs to make fine-grained reasoning decisions about the driving behavior of SVs.

[0021] Sixth, in S4, the embodiments of the present invention upload the DFP and TFD of the CAV and SVs to the RSU experience replay pool for RSU edge model updates. Simultaneously, the CAV's DFP and TFD are shared with the SVs for use in their lane change decisions. By sharing driving intent and lane change information with the SVs, the CAV promotes inter-vehicle collaboration and improves the safety of the lane change decision model.

[0022] Seventh, in embodiment S5 of the present invention, the RSU uses the DFP and TFD sampled from the experience replay pool, combined with the ResNet network of the attention mechanism, to extract the CAV's historical driving feature information, convert it into a vector, connect it with the 10-dimensional risk assessment vector obtained based on traffic factors in the RSU, and input it into the decision network. The model accuracy is calculated based on the actual lane change decision action, and when the edge model accuracy improves, the model is updated. The vehicle downloads the updated edge model from the RSU for local lane change decision-making, and uploads the new data generated by the decision to the RSU experience replay pool.

[0023] The beneficial effects of the present invention are:

[0024] (1) Improve lane change decision accuracy:

[0025] By analyzing historical driving data and building a personalized driving style model, we can more accurately simulate real users' driving behavior, make lane change decisions more in line with drivers' expectations and habits, and improve user experience.

[0026] The integration of local vehicle sensor data, edge models trained by roadside units, and shared information from surrounding vehicles provides the vehicle with more comprehensive environmental perception, reducing the risk of misjudgment and collision.

[0027] Deep learning models are used to process and extract complex environmental features, learn key patterns and features from large amounts of traffic data, and improve the accuracy of lane change decisions.

[0028] (2) Enhanced lane change decision safety:

[0029] Through vehicle-road collaboration, vehicles share real-time data, including driving characteristic maps, trajectory flow maps, etc., to achieve information sharing and collaborative decision-making, enhance perception of the surrounding environment, and reduce safety hazards.

[0030] The roadside unit uses a deep learning model to continuously update the edge model based on the data in the experience replay pool and sends it to the vehicle to ensure the real-time and adaptability of the decision-making model.

[0031] The vehicle generates a trajectory flow graph based on lane change decisions, predicts future driving trajectories, and characterizes road right requirements, helping the vehicle to more accurately judge the driving intentions of surrounding vehicles and avoid potential conflicts.

[0032] (3) Improve the efficiency of the transportation system:

[0033] Through more accurate and safer lane change decisions, traffic congestion can be reduced, traffic flow can be optimized, and road traffic efficiency can be improved.

[0034] Reduce traffic accidents caused by improper lane changing operations, improve traffic system safety, and reduce social costs.

[0035] Optimizing traffic flow can reduce vehicle fuel consumption and emissions, promote energy conservation and emission reduction, and protect the environment.

[0036] (4) Good scalability:

[0037] More types of data sources can be connected as needed, such as weather information, traffic event information, etc., to further improve the accuracy and adaptability of the decision-making model.

[0038] The model architecture and parameters can be adjusted according to different application scenarios and needs to make it more suitable for different traffic environments and driving styles.

[0039] Other advantages, objects, and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art upon examination of the following description or may be learned from practice of the present invention. The objects and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below with reference to the accompanying drawings, in which:

[0041] Figure 1 This is a system architecture diagram of the multi-dimensional collaborative vehicle lane change decision method based on user portrait;

[0042] Figure 2 Generate a flow chart for DFP of CAV based on historical driving data;

[0043] Figure 3 Schematic diagram of the Transformer network based on ResNet;

[0044] Figure 4 Flowchart for the execution of a multi-dimensional collaborative vehicle lane change decision method based on user profile. DETAILED DESCRIPTION

[0045] The following describes the embodiments of the present invention by means of specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0046] Among them, the accompanying drawings are only for illustrative purposes and represent only schematic diagrams rather than actual pictures, and should not be understood as limiting the present invention. In order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the dimensions of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions may be omitted in the accompanying drawings.

[0047] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "front", "back", etc. indicating directions or positional relationships, they are based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0048] Figure 1 The schematic diagram shows the whole process of vehicle data collection, data processing, model download, lane change decision, generation and sharing of traffic snapshots, data upload, risk assessment and model update. Figure 1As shown in the figure, the network considers historical driving data on vehicle driving characteristics and generates a trajectory flow graph for vehicle trajectory prediction. Vehicles share this real-time information to improve lane change safety based on the CAV's decision-making model. This information is uploaded to the RSU experience replay pool and used as new data to update the lane change model. This data takes into account three traffic factors: safety, incentives, and tolerance.

[0049] 1. CAV DFP generation solution based on historical driving data

[0050] This method generates a two-dimensional matrix by calculating M statistical functions of vehicle driving characteristics and converts the data into a DFP using time window extraction. This allows specific features to be extracted from historical driving information to implicitly describe the user profile of driving characteristics, with the goal of performing lane change decision tasks and including more specific driving style information. Figure 2 As shown in the figure, the specific process of CAV converting historical data into DFP is as follows:

[0051] (1) Data collection: The current vehicle j collects the relative position y through sensors j , relative position x j , lateral speed Longitudinal speed lateral acceleration Longitudinal acceleration Headway d jk 、Headway h jk L historical driving features, etc., where k∈{B,P,PL,FL,FR,ASL,ASR}. B, P, PL, FL, FR, ASL, and ASR represent the following vehicle in the current lane, the preceding vehicle in the current lane, the preceding vehicle in the left adjacent lane, the preceding vehicle in the right adjacent lane, the following vehicle in the left adjacent lane, the following vehicle in the right adjacent lane, the parallel vehicles in the left adjacent lane, and the parallel vehicles in the right adjacent lane, respectively.

[0052] (2) Statistical function calculation: For each of the L driving characteristics, M statistical functions, including the mean, standard deviation, median, 25% percentile, 75% percentile, minimum value, and maximum value, are calculated for each second. Based on the obtained results, a column of a two-dimensional matrix is ​​generated, that is, a column vector of size L·M×1 (L driving characteristics×M statistical functions) is generated every second.

[0053] (3) Time Window Setting: As time accumulates, the two-dimensional matrix gradually becomes larger, reflecting the long-term driving characteristics of the CAV. Since the lane change time is very short, the focus is on short-term driving characteristics. Therefore, a time window of length S seconds is set to frame the two-dimensional matrix S seconds before the lane change. This means that the size of each DFP is L·M×S.

[0054] (4) Normalization: All data in the two-dimensional matrix are normalized to eliminate the influence of different feature dimensions on DFP.

[0055] (5) DFP generation: All data in the two-dimensional matrix are represented as different colors. The depth of the color reflects the size of the data, and the type of color represents the category of the driving feature, thereby generating a driving feature map and implicitly representing the driving feature as an image.

[0056] 2. Trajectory flow graph TFD generation process

[0057] The trajectory flow graph is a two-dimensional grid matrix with CAV trajectories and SVs positions, such as Figure 1 As shown in the figure, the grids occupied by obstacles are uniformly set to 1. For grids occupied by vehicles, their values ​​are set to 1; otherwise, their values ​​are 0. At the same time, the vehicle's driving intention is represented by the predicted trajectory. There are two main reasons: first, any driving intention will eventually be reflected in the driving trajectory, that is, the predicted trajectory has the general characteristics of all types of driving intentions (such as acceleration, deceleration, lane change, etc.); second, the change behavior will essentially lead to right-of-way conflicts between vehicles, and the predicted trajectory directly reflects the vehicle's next right-of-way demand. The use of trajectory flow graphs can promote the neural network to learn the ability to negotiate right of way similar to that of the driver.

[0058] Specifically, in order to encode the spatiotemporal information of the predicted trajectory into a two-dimensional grid matrix, the value of the vehicle's position at time t is encoded as 1 and decreases linearly to 0 over time, that is, at time t+T D The value of the position is 0, where T D is the time length of the trajectory. This encoding allows the vehicle to make more fine-grained reasoning about the driving behavior of surrounding vehicles, thereby making more accurate decisions.

[0059] 3. Transformer network based on ResNet

[0060] Compared with convolutional neural networks (CNNs), residual networks (ResNets) have deeper models. They solve the vanishing gradient problem in deep network training through residual connections, allowing for the training of very deep networks, thereby capturing features at more levels. Transformers have powerful global feature modeling capabilities and can capture more complex dependencies and long-distance information. When dealing with complex tasks such as lane change decisions, Transformer networks combined with ResNets can better capture the complex relationships between historical data such as vehicle speed, trajectory, and steering angles, thereby improving the model's decision-making performance. Figure 3 As shown, the main steps of the algorithm are as follows:

[0061] (1) DFP feature extraction: After the RSU receives the DFP of CAV and SVs, the image is resized by bilinear interpolation to fit the input of ResNet-50. The resized image first passes through the initial convolution layer of ResNet-50 for feature extraction, then is normalized by the batch normalization layer, and the ReLU activation function is applied to introduce nonlinear characteristics and enhance feature representation capabilities. Next, the image enters the residual block stacking part. Each residual block contains multiple convolution layers, batch normalization layers, and ReLU activation functions. The input features are retained through jump connections and training is accelerated. High-level features are gradually extracted through multiple residual blocks. After passing through the global average pooling layer, the feature map is flattened into a one-dimensional vector.

[0062] In the Transformer network, the feature vector extracted by ResNet-50 is first mapped to the feature dimension required by the Transformer through a linear transformation. At the same time, position encoding is added to incorporate the position information of the sequence. Specifically, the position is encoded using the following formula:

[0063]

[0064]

[0065] Where pos represents the position index of each element after flattening the DFP, i represents the dimension index of each element, and d mod Represents the dimension of the model. Subsequently, these feature vectors enter the multi-head self-attention mechanism to generate the query vector Q, key vector K and value vector V with dimension, and calculate the similarity between them to capture the relationship between features:

[0066]

[0067] By weighted summing these value vectors, we get the output of each attention head, and then we transform the output of all heads linearly to generate the final multi-head self-attention output. Next, we input it into the Feedforward Neural Network (FFN), which consists of two linear transformation layers and one nonlinear activation function, which can be expressed as:

[0068] FFN(X)=W2σ(W1X) (4)

[0069] Among them, W1 and W2 are the two parameter matrices of the two linear transformation layers, and σ represents the nonlinear activation function. Then the training is stabilized by layer normalization, and the final output is:

[0070] LayerNorm(X+Attention(X))(5)

[0071] Here, X is the input to the self-attention layer, and the query, key, and value matrices Q, K, and V are all derived from the same input matrix X. Finally, the output feature vector of the Transformer network is concatenated with the feature vector extracted by ResNet-50 and then fed into the fully connected layer for fusion with other features.

[0072] (2) TFD feature extraction: When the RSU receives the TFD of CAV and SVs, it inputs it into the CNN. First, it passes through a convolution layer containing 16 3×3 convolution kernels to perform a convolution operation on the input image to extract low-dimensional features. Then it passes through a 2×2 maximum pooling layer to reduce the size of the feature map while retaining the most important information. Next, it passes through a convolution layer containing 32 3×3 convolution kernels to further perform a convolution operation on the pooled feature map to extract high-dimensional features. It passes through a 2×2 maximum pooling layer again to further reduce the size of the feature map. Subsequently, the output of the pooling layer is flattened into a one-dimensional vector and input to a fully connected layer containing 64 neurons. It is processed by the ReLU activation function and finally outputs a feature vector containing 32 neurons. This feature vector is input into the fully connected layer and connected with the vector of the DFP processed by the neural network, and finally acts on the lane change decision.

[0073] (3) Traffic factor setting: The motivation of CAV lane change is to obtain faster speed and better driving conditions. At the same time, safety is the premise of lane change decision. These factors are jointly determined by adjacent vehicles. Therefore, the traffic factor is set as the weighted sum of incentive factors, safety factors and tolerance factors. j ,v k Expressed as the speed of CAVs and SVs, d jk It is represented as the distance from vehicle j to the surrounding vehicle k. If there is no such vehicle around vehicle j, that is, Then v k and d jk Will be set to 0. Where k∈{B,P,PL,FL,FR,ASL,ASR}, d max is the maximum safe distance on the current road. B, P, PL, FL, FR, ASL, and ASR represent the following vehicle in the current lane, the preceding vehicle in the current lane, the preceding vehicle in the left adjacent lane, the preceding vehicle in the right adjacent lane, the following vehicle in the left adjacent lane, the following vehicle in the right adjacent lane, the parallel vehicle in the left adjacent lane, and the parallel vehicle in the right adjacent lane, respectively.

[0074] Incentive factors: Incentive factors include speed gain and headway gain. The speed gain achieved by the vehicle can be expressed as the difference between the maximum achievable speed of the current lane and the maximum achievable speed of the target lane relative to the current speed. Similarly, headway gain can be expressed as the difference between the current headway and the headway in the target lane. Since the target lane can be the left adjacent lane, the right adjacent lane, or the current lane, the incentive factor can be expressed as:

[0075] F i =f I ((v j -v P ),(v PL -v P ),(v PR -v P ),(d jPL -d jP ),(d jPR -d jP )) (6)

[0076] Safety Factor: To ensure lane change safety, the collision risk with the following vehicle in the target lane must be assessed. This risk depends on the distance and speed difference between the current vehicle and the following vehicle. When the distance to the following vehicle in the target lane is large enough for the current vehicle to complete the lane change, and the vehicle's speed is faster than the following vehicle, the collision risk is low. Therefore, the safety factor can be expressed as:

[0077] F s =f S ((d jFL ,d jFR ,(v j -v jFL ),(v j -v jFR )) (7)

[0078] Tolerance factor: The tolerance factor is a criterion used to determine whether the current lane is suitable for continued driving. It takes into account the distance between vehicle j and the vehicle in front and the safety time interval t h Different roads have different speed limits, and the safe distance between vehicles varies. Although there is a minimum safe distance requirement, many drivers still choose to maintain a longer distance to ensure they have more reaction time and drive more comfortably and safely. The tolerance factor helps the vehicle decide whether to continue driving in the current lane or change to a more appropriate lane. It can be expressed as:

[0079] F r =f R (d jP -v j ·t h) (8)

[0080] (4) Decision model: To formulate the lane change decision model, the lane change motivation factors, safety factors, tolerance factors, historical driving features extracted from DFP, and trajectory prediction information extracted from TFD are considered as follows:

[0081]

[0082] where y is a lane change decision vector containing three elements, corresponding to the probabilities of lane keeping, left lane change, and right lane change, and f DS (D) is the driving style extracted from DFP, f DT (T) is the trajectory information extracted from TFD, f θ The role of is to find the solution of the decision model. Since lane change decision is a multi-parameter, nonlinear problem that is difficult to solve using traditional mathematical methods, this invention uses a deep learning model to solve this problem. Through the trajectory dataset, the vehicle can extract input variables frame by frame to make decisions, and then model it as a supervised learning problem. The learning goal is to find f θ (·) Minimize the long-term average loss, defined as follows:

[0083]

[0084] Where N is the number of input-output pairs used for training, is the true decision vector of vehicle j obtained from the dataset, and the cross entropy function is used as the loss function L. If the actual decision is c, then otherwise

[0085] 4. System Process

[0086] Figure 4 The following is a flowchart of the multi-dimensional collaborative vehicle lane change decision execution based on user portraits. The specific steps are as follows:

[0087] Steps 401-404: initialization phase;

[0088] Step 401: Algorithm initialization;

[0089] Step 402: CAV downloads the edge decision model from RSU;

[0090] Step 403: The CAV collects local sensor data and generates a DFP;

[0091] Step 404: The CAV receives the DFP and TFP of the SVs;

[0092] Steps 405-408: CAV local driving decision stage;

[0093] Step 405: The CAV uses its own DFP and SVs data to make a lane change decision based on the edge model;

[0094] Step 406: The CAV generates its own TFP based on the decision action made;

[0095] Step 407: CAV shares its own DFP and TFP with SVs;

[0096] Step 408: The CAV makes a lane change decision and uploads the DFP and TFP to the experience replay pool;

[0097] Steps 409-412: edge model update phase;

[0098] Step 409: RSU performs experience replay pool sampling;

[0099] Step 410: The RSU processes the DFP and TFP into vectors through different networks and sends them to the fully connected layer;

[0100] Step 411: Update the model by combining the 10-dimensional vector of traffic factors;

[0101] Step 412: The algorithm ends.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-dimensional collaborative vehicle lane change decision method based on user profile, characterized by: The method comprises the following steps: S1: Establish a data sharing model based on CAV-SVs-RSU; SVs refer to surrounding vehicles; S2: CAV generates DFP based on historical driving data; DFP refers to driving feature map; S3: Lane change decision based on DFP and TFD of CAVs and SVs; TFD refers to trajectory flow diagram; S4: TFD generation of CAV based on lane-changing maneuvers; S5: DFP and TFD sharing of CAV; S6: Model training based on ResNet and Transformer; the steps for combining the ResNet and Transformer networks are as follows: (1) DFP feature extraction: After the RSU receives the DFP of CAV and SVs, the image is resized by bilinear interpolation to fit the input of ResNet-50. The resized image first passes through the initial convolution layer of ResNet-50 for feature extraction, and then is normalized by the batch normalization layer. The ReLU activation function is applied to introduce nonlinear characteristics and enhance the feature representation capability. Then, the image enters the residual block stacking part. Each residual block contains multiple convolution layers, batch normalization layers and ReLU activation functions. The input features are retained through jump connections and training is accelerated. High-level features are gradually extracted through multiple residual blocks. After passing through the global average pooling layer, the feature map is flattened into a one-dimensional vector. In the Transformer network, the feature vector extracted by ResNet-50 is first mapped to the feature dimension required by the Transformer through a linear transformation. At the same time, position encoding is added to incorporate the position information of the sequence. The position is encoded using the following formula: Where pos represents the position index of each element after flattening the DFP, i represents the dimension index of each element, and d mod Represents the dimension of the model; the feature vector enters the multi-head self-attention mechanism to generate a query vector Q, a key vector K, and a value vector V with dimensions, and calculates the similarity between them to capture the relationship between features: By weighted summing these value vectors, we get the output of each attention head, and then we transform the output of all heads linearly to generate the final multi-head self-attention output. Then, we input it into the feedforward neural network FFN, which consists of two linear transformation layers and one nonlinear activation function, expressed as: FFN(X)=W2σ(W1X) (4) Among them, W1 and W2 are the two parameter matrices of the two linear transformation layers, and σ represents the nonlinear activation function; the training is stabilized by layer normalization, and the final output is: LayerNorm(X+Attention(X))(5) Here, X is the input to the self-attention layer, and the query, key, and value matrices Q, K, and V are all derived from the same input matrix X. Finally, the output feature vector of the Transformer network is concatenated with the feature vector extracted by ResNet-50 and then fed into the fully connected layer for fusion with other features. (2) TFD feature extraction: When the RSU receives the TFD of CAV and SVs, it inputs it into the CNN. First, it passes through a convolution layer containing 16 3×3 convolution kernels to perform a convolution operation on the input image to extract low-dimensional features; then it passes through a 2×2 maximum pooling layer to reduce the size of the feature map while retaining the most important information; next, it passes through a convolution layer containing 32 3×3 convolution kernels to perform a further convolution operation on the pooled feature map to extract high-dimensional features; it passes through a 2×2 maximum pooling layer again to further reduce the size of the feature map; then, the output of the pooling layer is flattened into a one-dimensional vector and input to a fully connected layer containing 64 neurons, processed by the ReLU activation function, and finally outputs a feature vector containing 32 neurons; this feature vector is input into the fully connected layer and connected with the vector of the DFP processed by the neural network, and finally acts on the lane change decision; (3) Traffic factor setting: The motivation of CAV lane change is to obtain faster speed and better driving conditions. At the same time, safety is the premise of lane change decision. These factors are jointly determined by adjacent vehicles. The traffic factor is set as the weighted sum of incentive factors, safety factors and tolerance factors. j ,v k are the speeds of CAV and SVs, respectively, d jk It is represented as the distance from vehicle j to the surrounding vehicle k. If there is no such vehicle around vehicle j, that is, Then v k and d jk will be set to 0; where k∈{B,P,PL,PR,FL,FR,ASL,ASR}, d max is the maximum safe distance on the current road; B, P, PL, PR, FL, FR, ASL, and ASR represent the following vehicle in the current lane, the preceding vehicle in the current lane, the preceding vehicle in the left adjacent lane, the preceding vehicle in the right adjacent lane, the following vehicle in the left adjacent lane, the following vehicle in the right adjacent lane, the parallel vehicle in the left adjacent lane, and the parallel vehicle in the right adjacent lane, respectively. Incentive factors: Incentive factors include speed gain factors and headway gain factors. The speed gain obtained by the vehicle is represented by the difference between the maximum achievable speed of the current lane and the maximum achievable speed of the target lane relative to the current speed. The headway gain is represented by the difference between the current headway and the headway in the target lane. The target lane is the left adjacent lane, the right adjacent lane, or the current lane. The incentive factors are expressed as: F i =f I ((v j -v P ),(v PL -v P ),(v PR -v P ),(d jPL -d jP ),(d jPR -d jP )) (6) Safety factor: Assess the risk of collision with the following vehicle in the target lane. It depends on the distance and speed difference between the current vehicle and the following vehicle. When the distance to the following vehicle in the target lane is large enough for the current vehicle to complete the lane change, and the speed of vehicle j is faster than that of the following vehicle, the collision risk will be low. The safety factor is expressed as: F s =f S ((d jFL ,d jFR ,(v j -v FL ),(v j -v FR )) (7) Tolerance factor: The tolerance factor is a criterion used to determine whether the current lane is suitable for continued driving; it takes into account the distance between vehicle j and the vehicle in front and the safety time interval t h The tolerance factor helps the vehicle decide whether it should continue driving in the current lane or change to a more suitable lane, expressed as: F r =f R (d jP -v j ·t h ) (8) (4) Decision model: To formulate the lane change decision model, the lane change motivation factors, safety factors, tolerance factors, historical driving features extracted from DFP, and trajectory prediction information extracted from TFD are considered as follows: where y is a lane change decision vector containing three elements, corresponding to the probabilities of lane keeping, left lane change, and right lane change, and f DS (D) is the driving style extracted from DFP, f DT (T) is the trajectory information extracted from TFD, f θ The role of is to find the solution of the decision model; through the trajectory data set, the vehicle extracts input variables frame by frame to make decisions, and then models it as a supervised learning problem; the learning goal is to find f θ (·) Minimize the long-term average loss, defined as follows: Where N is the number of input-output pairs used for training, is the true decision vector of vehicle j obtained from the dataset, and the cross entropy function is used as the loss function L; where, if the actual decision is c, then otherwise 2. The multi-dimensional collaborative vehicle lane change decision method based on user profile according to claim 1 is characterized by: In S1, a data sharing model based on CAV, SVs, and RSU is adopted to improve the safety of lane change decisions by sharing data among CAV, SVs, and RSUs; CAV and SVs share DFP and TFD to improve CAV's perception of the surrounding environment.

3. The multi-dimensional collaborative vehicle lane change decision method based on user profile according to claim 2 is characterized by: In S2, a two-dimensional matrix is ​​generated by calculating M statistical functions of the vehicle's driving characteristics. Time window extraction is used to convert the data into a DFP. Features are extracted from historical driving information to implicitly describe the user profile of driving characteristics. The purpose is to perform lane change decision-making tasks and include more specific driving style information. The specific process of converting historical data into a DFP by the CAV is as follows: (1) Data collection: The current vehicle j collects the relative position y through sensors j , relative position x j , lateral speed Longitudinal speed lateral acceleration Longitudinal acceleration Headway d jk Distance between the front and rear wheels h jk L historical driving features; where k∈{B,P,PL,PR,FL,FR,ASL,ASR}; B, P, PL, PR, FL, FR, ASL, and ASR represent the following vehicle in the current lane, the preceding vehicle in the current lane, the preceding vehicle in the left adjacent lane, the preceding vehicle in the right adjacent lane, the following vehicle in the left adjacent lane, the following vehicle in the right adjacent lane, the parallel vehicles in the left adjacent lane, and the parallel vehicles in the right adjacent lane, respectively; (2) Statistical function calculation: For each of the L historical driving features, calculate the mean, standard deviation, median, 25% percentile, 75% percentile, minimum value, and maximum value of M statistical functions for each second. Generate a column of a two-dimensional matrix based on the obtained results, that is, generate a column vector of size L·M×1 for each second, L historical driving features × M statistical functions; (3) Time window setting: As time accumulates, the two-dimensional matrix gradually becomes larger, reflecting the long-term driving characteristics of the CAV. Since the lane change time is very short, we focus on short-term driving characteristics. We set a time window of length S seconds and frame the two-dimensional matrix S seconds before the lane change. The size of each DFP is L·M×S. (4) Normalization: Normalize all data in the two-dimensional matrix to eliminate the influence of different feature dimensions on DFP; (5) DFP generation: All data in the two-dimensional matrix are represented as different colors. The depth of the color reflects the size of the data, and the type of color represents the category of the driving feature. A driving feature map is generated, and the driving features are implicitly represented as an image.

4. The multi-dimensional collaborative vehicle lane change decision method based on user profile according to claim 3 is characterized by: In the said S4, the trajectory flow graph is a two-dimensional grid matrix with CAV trajectories and SVs positions, and the values ​​of grids occupied by obstacles are uniformly set to 1; Otherwise, its value is 0; at the same time, the vehicle's driving intention is represented by the predicted trajectory; In order to encode the spatiotemporal information of the predicted trajectory into a two-dimensional grid matrix, the value of the vehicle's position at time t is encoded as 1 and decreases linearly to 0 over time, that is, at time t+T D The value of the position is 0, where T D is the time length of the trajectory.

Images