Vehicle intelligent driving control method, device, equipment and computer storage medium

Abstract

This invention relates to a vehicle intelligent driving control method, device, equipment, and computer storage medium, belonging to the field of intelligent driving technology. The method includes: acquiring the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario; acquiring the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length, and vehicle width of a target vehicle in the current driving scenario; calculating the longitudinal risk time when the current vehicle and the target vehicle collide longitudinally; calculating the lateral lane change time when the current vehicle and the target vehicle overlap laterally; and performing intelligent driving control on the current vehicle based on the longitudinal risk time and lateral lane change time. This invention avoids vehicle collisions by determining the longitudinal risk time and lateral lane change time during vehicle operation, thereby ensuring the accuracy and reliability of intelligent driving technology.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a vehicle intelligent driving control method, device, equipment, and computer storage medium. Background Technology

[0002] Intelligent driving, a product of the integration of the automotive industry and information technology, is gradually becoming an important development direction for the automotive sector. Intelligent driving systems mainly consist of three key components: network navigation, autonomous driving, and human intervention. Network navigation addresses issues such as vehicle positioning and route planning; autonomous driving, under the control of the intelligent system, performs driving behaviors such as lane keeping, overtaking, and traffic signal recognition; and human intervention refers to the driver's ability to take over vehicle control when necessary and react to actual road conditions. However, current intelligent driving technologies also face some challenges and limitations. For example, ensuring the accuracy and reliability of intelligent driving technology in complex and ever-changing road environments is a problem that urgently needs to be solved. Summary of the Invention

[0003] In view of this, it is necessary to provide a vehicle intelligent driving control method, device, equipment, and computer storage medium to ensure the accuracy and reliability of vehicle intelligent driving technology.

[0004] To address the aforementioned problems, in a first aspect, the present invention provides a vehicle intelligent driving control method, comprising:

[0005] The system obtains the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length, and vehicle width of the target vehicle in the same driving scenario.

[0006] Based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, calculate the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction.

[0007] Based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle, calculate the lateral lane change time when the current vehicle and the target vehicle overlap laterally.

[0008] Intelligent driving control of the current vehicle is performed based on the longitudinal risk time and the lateral lane change time.

[0009] In one possible implementation, calculating the longitudinal risk time when a collision occurs between the current vehicle and the target vehicle in the longitudinal direction, based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, includes:

[0010] Based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, calculate the collision time when the current vehicle and the target vehicle collide in the longitudinal direction.

[0011] Based on the current vehicle's longitudinal position, the target vehicle's longitudinal position, the target vehicle's length, and the current vehicle's longitudinal speed, calculate the time it takes for the current vehicle to reach the target vehicle's position.

[0012] Based on the collision time and the workshop time, the longitudinal risk time when the current vehicle collides with the target vehicle in the longitudinal direction is determined.

[0013] In one possible implementation, the collision time when the current vehicle and the target vehicle collide longitudinally is calculated based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal velocity of the current vehicle, and the longitudinal velocity of the target vehicle.

[0014]

[0015] In the formula, This indicates the time of collision when the current vehicle and the target vehicle collide longitudinally. Indicates the longitudinal position of the target vehicle; Indicates the current longitudinal position of the vehicle; Indicates the length of the target vehicle; The longitudinal speed of the target vehicle; The current longitudinal speed of the vehicle;

[0016] Based on the current vehicle's longitudinal position, the target vehicle's longitudinal position, the target vehicle's length, and the current vehicle's longitudinal speed, calculate the time it takes for the current vehicle to reach the target vehicle's position.

[0017]

[0018] In the formula, This indicates the time taken when the current vehicle reaches the target vehicle's location.

[0019] In one possible implementation, the lateral lane change time when the current vehicle and the target vehicle overlap laterally is calculated based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle.

[0020]

[0021] In the formula, This indicates the lateral lane change time when the current vehicle and the target vehicle overlap laterally. Indicates the current lateral position of the vehicle. Indicates the lateral position of the target vehicle. This indicates the width of the target vehicle. This represents the lateral velocity of the target vehicle. This indicates the current lateral speed of the vehicle.

[0022] In one possible implementation, the intelligent driving control of the current vehicle based on the longitudinal risk time and the lateral lane change time includes:

[0023] Based on the longitudinal risk time and the lateral lane change time, calculate the risk index of the current vehicle and the target vehicle making contact in the current driving scenario;

[0024] Obtain a first risk index data set of the current vehicle changing over a preset time period and a second risk index data set established based on the current vehicle's successful risk avoidance scenarios at historical moments. Perform correlation analysis on the first risk index data set and the second risk index data set to obtain the risk correlation coefficient.

[0025] When the risk correlation coefficient is greater than a first preset threshold and the risk index is less than a second preset threshold, a risk avoidance planning trajectory for the current vehicle is generated, and intelligent driving control of the current vehicle is performed based on the risk avoidance planning trajectory.

[0026] In one possible implementation, generating the current vehicle's hazard avoidance planning trajectory includes:

[0027] Obtain the first historical trajectory information of the current vehicle and the second historical trajectory information of the target vehicle;

[0028] The first historical trajectory information and the second historical trajectory information are encoded using an encoding neural network to obtain the current vehicle hidden layer vector and the target vehicle hidden layer vector containing historical trajectory features.

[0029] The current vehicle hidden layer vector and the target vehicle hidden layer vector are used as vertex feature vectors, and the current vehicle and the target vehicle are used as vertices. After connecting the vertices, the edge feature vectors are obtained.

[0030] A graph structure is constructed based on the vertex feature vectors and the edge feature vectors, and the connection relationship between vertices in the graph structure is determined as an adjacency matrix.

[0031] Based on the adjacency matrix and the vertex feature vector, generate the trajectory interaction feature vector between the current vehicle and the target vehicle;

[0032] Based on the current vehicle's hidden layer vector and the target vehicle's hidden layer vector, the attention scores of the current vehicle and the target vehicle are calculated, and the attention scores are normalized to obtain the attention vectors of the current vehicle and the target vehicle.

[0033] The trajectory interaction feature vector and the attention vector are concatenated to generate the driving intention recognition vector of the current vehicle.

[0034] The trajectory interaction feature vector, the attention vector, and the current vehicle's driving intention recognition vector are input into a decoding neural network for decoding to predict the future trajectory probability distribution under different driving intentions, and the current vehicle's risk avoidance planning trajectory is generated based on the future trajectory probability distribution.

[0035] In one possible implementation, the current driving scenario includes a straight-line driving scenario and / or a lane-changing driving scenario, and the target vehicle includes vehicles within a preset distance range from the current vehicle.

[0036] In a second aspect, the present invention also provides a vehicle intelligent driving control device, comprising:

[0037] The data acquisition module is used to acquire the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length, and vehicle width of the target vehicle in the same driving scenario.

[0038] The first-time calculation module is used to calculate the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction, based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle.

[0039] The second time calculation module is used to calculate the lateral lane change time when the current vehicle and the target vehicle overlap laterally, based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle.

[0040] The intelligent driving control module is used to perform intelligent driving control on the current vehicle based on the longitudinal risk time and the lateral lane change time.

[0041] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the above-described intelligent driving control method for vehicles.

[0042] Fourthly, the present invention also provides a computer storage medium, which stores a computer program that, when executed by a processor, implements the steps of the vehicle intelligent driving control method described above.

[0043] The beneficial effects of this invention are:

[0044] This invention first obtains the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal speed, lateral speed, length, and width of the target vehicle in the same driving scenario. Then, based on the longitudinal position, target vehicle's longitudinal position, target vehicle's length, and the target vehicle's longitudinal speed, it calculates the longitudinal risk time when a collision occurs between the two vehicles. Simultaneously, based on the lateral position, target vehicle's lateral position, target vehicle's width, and the target vehicle's lateral speed, it calculates the lateral lane-change time when the two vehicles overlap laterally. Finally, based on the longitudinal risk time and lateral lane-change time, it performs intelligent driving control on the current vehicle to prevent contact between the current and target vehicles in the current driving scenario. This ensures the accuracy and reliability of the vehicle's intelligent driving technology. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating an embodiment of a vehicle intelligent driving control method provided by the present invention.

[0047] Figure 2 This is a schematic diagram of the driving of a current vehicle and a target vehicle in a certain driving scenario, provided in one embodiment of the present invention;

[0048] Figure 3 This is a flowchart of a method for intelligent driving control of a current vehicle according to an embodiment of the present invention;

[0049] Figure 4This is a flowchart illustrating a method for generating a current vehicle's hazard avoidance planning trajectory, as provided in an embodiment of the present invention.

[0050] Figure 5 This is a schematic diagram of an embodiment of a vehicle intelligent driving control device provided by the present invention.

[0051] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0052] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0053] In the description of the embodiments of the present invention, unless otherwise stated, "a plurality of" means two or more.

[0054] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0055] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0056] A specific embodiment of the present invention, such as Figure 1 As shown, Figure 1 A flowchart of an embodiment of a vehicle intelligent driving control method provided by the present invention includes:

[0057] S101: Obtain the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario, and obtain the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length, and vehicle width of the target vehicle in the current driving scenario;

[0058] S102: Based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, calculate the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction.

[0059] S103: Based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle, calculate the lateral lane change time when the current vehicle and the target vehicle overlap laterally.

[0060] S104: Intelligent driving control of the current vehicle is achieved by considering longitudinal risk time and lateral lane change time.

[0061] It is understood that the current driving scenario includes straight-line driving and / or lane-changing scenarios, and the target vehicle includes surrounding vehicles whose distance from the current vehicle is within a preset distance range. The current vehicle can be a manned or unmanned vehicle, and the target vehicle can be a manned or unmanned vehicle. For an example, please refer to [link to example]. Figure 2 , Figure 2 This is a schematic diagram of the current vehicle and the target vehicle in a certain driving scenario provided in one embodiment of the present invention.

[0062] This invention first obtains the longitudinal position, lateral position, longitudinal speed, and lateral speed of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal speed, lateral speed, length, and width of the target vehicle in the same driving scenario. Then, based on the longitudinal position, target vehicle's longitudinal position, target vehicle's length, and the target vehicle's longitudinal speed, it calculates the longitudinal risk time when a collision occurs between the two vehicles. Simultaneously, based on the lateral position, target vehicle's lateral position, target vehicle's width, and the target vehicle's lateral speed, it calculates the lateral lane-change time when the two vehicles overlap laterally. Finally, based on the longitudinal risk time and lateral lane-change time, it performs intelligent driving control on the current vehicle to prevent contact between the current and target vehicles in the current driving scenario. This ensures the accuracy and reliability of the vehicle's intelligent driving technology.

[0063] In one embodiment of the present invention, based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, the longitudinal risk time when a collision occurs between the current vehicle and the target vehicle in the longitudinal direction is calculated, including:

[0064] Based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, calculate the collision time when the current vehicle and the target vehicle collide in the longitudinal direction.

[0065] Based on the current vehicle's longitudinal position, the target vehicle's longitudinal position, the target vehicle's length, and the current vehicle's longitudinal speed, calculate the time it takes for the current vehicle to reach the target vehicle's position.

[0066] Based on the collision time and the workshop time, the longitudinal risk time when the current vehicle collides with the target vehicle in the longitudinal direction is determined.

[0067] Understandably, collision time and time-to-distance travel time serve as longitudinal risk indicators for the current vehicle's hazard avoidance decision. Collision time represents the time required for the two vehicles to collide, calculated as the relative distance between them divided by their relative speed; a smaller value indicates a greater collision risk. However, when the current vehicle's speed is less than the target vehicle's, collision time may not be sufficient for risk assessment. Therefore, time-to-distance travel time is introduced as a supplementary longitudinal risk indicator. Time-to-distance travel time is the time required for the current vehicle to reach the target vehicle's position; a smaller value indicates a greater collision risk. Specifically, based on the current vehicle's longitudinal position, the target vehicle's longitudinal position, the target vehicle's length, the current vehicle's longitudinal speed, and the target vehicle's longitudinal speed, the collision time when the current vehicle and target vehicle collide longitudinally is calculated.

[0068] ;

[0069] In the formula, This indicates the time of collision when the current vehicle and the target vehicle collide longitudinally. Indicates the longitudinal position of the target vehicle; Indicates the current longitudinal position of the vehicle; Indicates the length of the target vehicle; The longitudinal velocity of the target vehicle; The longitudinal speed of the current vehicle; in addition, based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, and the longitudinal speed of the current vehicle, calculate the time taken for the current vehicle to reach the position of the target vehicle.

[0070] ;

[0071] In the formula, This indicates the time taken when the current vehicle reaches the target vehicle's location.

[0072] If the relative distance between the current vehicle and the target vehicle is short and the relative speed is low, and the target vehicle brakes suddenly, the current distance may be insufficient for braking and evasive action. However, due to the low relative speed, the collision time is insufficient to characterize the risk. In this case, the inter-vehicle time is smaller and can characterize a higher risk, thus compensating for the shortcomings of the collision time. Therefore, the longitudinal risk time when a collision occurs between the current vehicle and the target vehicle can be selected based on the collision time and the inter-vehicle time. Specifically, ,in, Indicates the time frame of longitudinal risk; and It is a constant. and The settings can be adjusted according to the actual situation; no specific numerical limit is set in this embodiment.

[0073] In one embodiment of the present invention, the lateral collision risk between the current vehicle and the target vehicle mainly comes from vehicles on the lateral side. Therefore, the lateral lane change time is set as a lateral risk indicator for the current vehicle's risk avoidance decision. Specifically, based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle, the lateral lane change time when the current vehicle and the target vehicle overlap laterally is calculated.

[0074] ;

[0075] In the formula, This indicates the lateral lane change time when the current vehicle and the target vehicle overlap laterally. Indicates the current lateral position of the vehicle. Indicates the lateral position of the target vehicle. This indicates the width of the target vehicle. This represents the lateral velocity of the target vehicle. This indicates the current lateral speed of the vehicle.

[0076] In one embodiment of the present invention, such as Figure 3 As shown, Figure 3 This is a flowchart of a method for intelligent driving control of a current vehicle, provided as an embodiment of the present invention.

[0077] S301: Calculate the risk index of contact between the current vehicle and the target vehicle in the current driving scenario based on the longitudinal risk time and the lateral lane change time;

[0078] S302: Obtain the first risk index data set of the current vehicle changing over a preset time period and the second risk index data set established by the current vehicle's successful risk avoidance scenarios at historical moments, and perform correlation analysis on the first risk index data set and the second risk index data set to obtain the risk correlation coefficient;

[0079] S303: When the risk correlation coefficient is greater than the first preset threshold and the risk index is less than the second preset threshold, generate the current vehicle's risk avoidance planning trajectory based on the current vehicle's first historical trajectory information and the target vehicle's second historical trajectory information, and perform intelligent driving control on the current vehicle based on the risk avoidance planning trajectory.

[0080] It is understandable that when other vehicles change lanes to enter the lane currently occupied by the vehicle, the longitudinal risk time can be obtained. With lateral lane change time ,like This indicates that other vehicles had already changed lanes laterally before the longitudinal positions of the two vehicles overlapped; in this case, only longitudinal risk needs to be considered. This indicates that when the two vehicles overlap longitudinally, other vehicles to the side have not yet completed their lane changes, resulting in a higher risk of collision. The timing of the lateral lane change must also be considered. To increase risk considerations, the risk index of contact between the current vehicle and the target vehicle in the current driving scenario is defined by longitudinal risk time and lateral lane change time.

[0081] ;

[0082] In the formula, This indicates the risk index of potential contact between the current vehicle and the target vehicle in the current driving scenario.

[0083] Indicates the time frame of longitudinal risk; This represents a pre-set or real-time error coefficient; in this embodiment or other embodiments, the error coefficient... Specific numerical limits can be set according to actual circumstances to prevent calculation errors. For potential collision risks, a risk indicator database of successful avoidance scenarios is established based on the dataset. During driving, the correlation between current risk indicators and the database of successful avoidance scenarios is compared to reflect the likelihood of future collision risks. When the correlation is high, avoidance planning is triggered to avoid potential collision risks. Therefore, by introducing a risk correlation coefficient to reflect the closeness of the relationship between two sets of variables and to measure their linear relationship, we have:

[0084]

[0085] In the formula, This represents the risk correlation coefficient, with a value range of [value range missing]. between, The closer the absolute value is to 0, the weaker the correlation; the closer it is to 1, the stronger the correlation. A dataset representing how the risk index of a vehicle changes over a preset time period; This represents a dataset established based on the risk index corresponding to successful vehicle hazard avoidance scenarios at historical moments. This represents the covariance of the risk index; express Standard deviation; express Standard deviation;

[0086] Record the risk index of the vehicle during its current driving process and perform correlation analysis with historical data sets; Greater than the first threshold and When the distance is less than the second threshold, an avoidance planning trajectory for the current vehicle is generated based on the first historical trajectory information of the current vehicle and the second historical trajectory information of the target vehicle. Intelligent driving control of the current vehicle is then performed according to this trajectory. Furthermore, to avoid overly aggressive evaluation based solely on time-domain indicators, a spatial domain safe distance can be used as a prerequisite for avoidance decisions. Specifically, when the distance between the two vehicles is less than the safe distance at the current speed, a decision is triggered to determine whether to generate an avoidance planning trajectory for the current vehicle.

[0087] In one embodiment of the present invention, such as Figure 4 As shown, Figure 4 A flowchart of a method for generating a current vehicle's hazard avoidance planning trajectory, provided as an embodiment of the present invention, includes:

[0088] S401: Encode the first historical trajectory information and the second historical trajectory information using an encoding neural network to obtain the current vehicle hidden layer vector and the target vehicle hidden layer vector containing historical trajectory features.

[0089] S402: Use the current vehicle's hidden layer vector and the target vehicle's hidden layer vector as vertex feature vectors, and use the current vehicle and the target vehicle as vertices. Connect the vertices to obtain the edge feature vectors.

[0090] S403: Construct a graph structure based on vertex feature vectors and edge feature vectors, and determine the connection relationship between vertices in the graph structure as an adjacency matrix;

[0091] S404: Generate trajectory interaction feature vectors between the current vehicle and the target vehicle based on the adjacency matrix and vertex feature vectors;

[0092] S405: Based on the current vehicle's hidden layer vector and the target vehicle's hidden layer vector, calculate the attention scores of the current vehicle and the target vehicle, and normalize the attention scores to obtain the attention vectors of the current vehicle and the target vehicle.

[0093] S406: Concatenate the trajectory interaction feature vector and the attention vector to generate the current vehicle's driving intention recognition vector;

[0094] S407: Input the trajectory interaction feature vector, attention vector and the current vehicle's driving intention recognition vector into the decoding neural network for decoding, predict the future trajectory probability distribution under different driving intentions, and generate the current vehicle's risk avoidance planning trajectory based on the future trajectory probability distribution.

[0095] Understandably, obtaining the time... The current vehicle's historical trajectory information and the target vehicle's historical trajectory information are displayed. Specifically, In the formula, Indicates the current time of the vehicle The horizontal position coordinates below Indicates the current time of the vehicle The vertical position coordinates below, Indicates the first The target vehicle at time The lateral relative distance between the vehicle and the current vehicle. Indicates the first The target vehicle at time The longitudinal relative distance to the current vehicle is set below. If there is no vehicle at the corresponding position, the corresponding lateral and longitudinal relative distances are set to positive infinity.

[0096] An encoding neural network constructed using a Long Short-Term Memory (LSTM) neural network is used to encode the first historical trajectory information of the current vehicle and the second historical trajectory information of the target vehicle, resulting in hidden layer vectors for the current vehicle and the target vehicle that contain historical trajectory features, respectively. Specifically: In the formula, Indicates time The hidden layer state containing historical trajectory features is given below, and the corresponding hidden layer vector of the current vehicle containing historical trajectory features is given below. The corresponding hidden layer vector of the target vehicle containing historical trajectory features is , This represents the weights of the encoded neural network.

[0097] The obtained hidden layer vectors of the current vehicle and the target vehicle are used as vertex feature vectors, and the current vehicle and the target vehicle are used as vertices. Edge feature vectors are obtained by connecting the vertices. Furthermore, a graph structure is constructed based on the vertex feature vectors and edge feature vectors, and the connection relationships between vertices in the graph structure are represented as an adjacency matrix. Specifically, at time... The current vehicle and the target vehicle are considered as a graph structure. In The current vehicle hidden layer vector is obtained by encoding the vertices of the Long Short-Term Memory Neural Network (LSTM). and the hidden layer vector of the target vehicle As vertex feature vectors, i.e. Edge features are obtained by connecting vertices. Then, the connection relationships between vertices are represented as an adjacency matrix. .

[0098] By using the adjacency matrix and vertex feature vectors, trajectory interaction feature vectors between the current vehicle and the target vehicle are generated. Specifically, by employing a two-layer graph convolutional neural network, the time-series data is output. Trajectory interaction feature vector containing its own features : In the formula, This represents the activation function. These are the weights of the first layer of the graph convolutional neural network. These are the weights of the second layer of the graph convolutional neural network.

[0099] Based on the current vehicle's hidden layer vector and the target vehicle's hidden layer vector, the attention scores for the current vehicle and the target vehicle are calculated, and the attention scores are normalized to obtain the attention vectors for the current vehicle and the target vehicle. Specifically, the attention vectors for the current vehicle and the target vehicle are... The hidden layer vector of the target vehicle after being encoded by a Long Short-Term Memory (LSTM) neural network. Consider K and V, and the current vehicle hidden layer vector Considered as Q, the degree of interaction between the target vehicle and the current vehicle is explained by calculating the correlation between K and Q. Because and Since the dimensions are the same, cosine similarity is selected as the function for calculating the attention score, and the resulting attention score is... The interaction weights are obtained after normalization using the softmax function. The final attention vector is obtained by weighted summation of this vector with V. The calculation expression is as follows: , , .

[0100] The trajectory interaction feature vector and attention vector are concatenated to generate a driving intention recognition vector. The trajectory interaction feature vector, attention vector, and driving intention recognition vector are then input into a decoding neural network for decoding to predict the future trajectory probability distribution under different driving intentions. Based on this future trajectory probability distribution, a hazard avoidance planning trajectory for the current vehicle is generated. Specifically, the trajectory interaction feature vector after graph convolution... With attention vector The concatenated vector is used as the input vector for driver intent prediction, and after normalization by the softmax function, the output is the driver intent recognition vector. ,in , and These represent the probabilities of changing lanes to the left, going straight, and changing lanes to the right, respectively; that is, the output of the intent recognition layer is... Finally, the trajectory interaction feature vector after graph convolution is... Attention vector and intent category vector After concatenation, the data is input into a decoding neural network composed of a Long Short-Term Memory (LSTM) neural network to predict the probability distribution of future trajectories under different intentions. In the formula, This represents the future trajectory predicted using the sliding window method; Predict the parameters of the binary Gaussian distribution for each frame in the future. , and These are the mean values ​​for the horizontal and vertical positions, respectively. and These are the variances of the horizontal and vertical positions, respectively. The correlation coefficient.

[0101] Therefore, this method determines the risk index of longitudinal and lateral collisions between the current vehicle and the target vehicle based on multiple vehicle parameters, providing a basis for judgment in the current vehicle's hazard avoidance planning. Simultaneously, by real-time monitoring of the driving risk index and performing correlation analysis with a database of successful hazard avoidance scenarios, the potential collision risk between the current vehicle and the target vehicle can be determined, thereby generating the current vehicle's hazard avoidance planning trajectory in advance. Then, based on the generated hazard avoidance planning trajectory, intelligent driving control is implemented to help the current vehicle avoid collision risks. Furthermore, in generating the hazard avoidance planning trajectory, a trajectory prediction model can be established by combining graph convolutional neural networks and long short-term memory networks, and incorporating an attention mechanism, to predict the probability distribution of future trajectories under different driving intentions, thus generating the current vehicle's hazard avoidance planning trajectory.

[0102] To better implement the vehicle intelligent driving control method in the embodiments of the present invention, based on the vehicle intelligent driving control method, correspondingly, as follows: Figure 5 As shown, Figure 5 A schematic diagram of an embodiment of a vehicle intelligent driving control device provided by the present invention includes:

[0103] The data acquisition module 501 is used to acquire the longitudinal position, lateral position, longitudinal speed and lateral speed of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length and vehicle width of the target vehicle in the current driving scenario;

[0104] The first-time calculation module 502 is used to calculate the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle.

[0105] The second time calculation module 503 is used to calculate the lateral lane change time when the current vehicle and the target vehicle overlap laterally, based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle.

[0106] The intelligent driving control module 504 is used to perform intelligent driving control on the current vehicle based on longitudinal risk time and lateral lane change time.

[0107] The vehicle intelligent driving control device 500 provided in the above embodiments can realize the technical solutions described in the above vehicle intelligent driving control method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above vehicle intelligent driving control method embodiments, and will not be repeated here.

[0108] like Figure 6 As shown, the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0109] In some embodiments, processor 601 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as the vehicle intelligent driving control method of the present invention.

[0110] In some embodiments, processor 601 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 601 may be local or remote. In some embodiments, processor 601 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0111] In some embodiments, memory 602 may be an internal storage unit of electronic device 600, such as a hard disk or memory of electronic device 600. In other embodiments, memory 602 may also be an external storage device of electronic device 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 600.

[0112] Furthermore, the memory 602 may include both internal storage units of the electronic device 600 and external storage devices. The memory 602 is used to store application software and various types of data installed on the electronic device 600.

[0113] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display information from electronic device 600 and to display a visual user interface. Components 601-603 of electronic device 600 communicate with each other via a system bus.

[0114] In some embodiments, when the processor 601 executes the vehicle intelligent driving control program in the memory 602, the following steps may be implemented:

[0115] The system obtains the longitudinal position, lateral position, longitudinal velocity, and lateral velocity of the current vehicle in the current driving scenario, as well as the longitudinal position, lateral position, longitudinal velocity, lateral velocity, vehicle length, and vehicle width of the target vehicle in the current driving scenario.

[0116] Based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle, calculate the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction.

[0117] Based on the lateral position of the current vehicle, the lateral position of the target vehicle, the width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle, calculate the lateral lane change time when the current vehicle and the target vehicle overlap laterally.

[0118] Intelligent driving control of the current vehicle is achieved by using longitudinal risk time and lateral lane change time.

[0119] It should be understood that when the processor 601 executes the vehicle intelligent driving control program in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0120] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 600 mentioned. Electronic device 600 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 600 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0121] In another exemplary embodiment of the present invention, this embodiment also provides a vehicle, which includes a vehicle intelligent driving control device as described in the above embodiments, or includes an electronic device as described in the above embodiments. It should be noted that since the specific methods by which the vehicle intelligent driving control device and the electronic device perform operations have been described in detail in the embodiments, the technical functions and effects of the vehicle provided in this embodiment can be referred to in the above embodiments, and will not be repeated here.

[0122] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the vehicle intelligent driving control methods provided in the above-described method embodiments.

[0123] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0124] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle intelligent driving control method, characterized in that, The method comprises: obtaining the longitudinal position, lateral position, longitudinal speed and lateral speed of the current vehicle in the current driving scene, and obtaining the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length and vehicle width of the target vehicle in the current driving scene; based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle, the longitudinal speed of the current vehicle and the longitudinal speed of the target vehicle, calculating the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction; based on the lateral position of the current vehicle, the lateral position of the target vehicle, the vehicle width of the target vehicle, the lateral speed of the current vehicle and the lateral speed of the target vehicle, calculating the lateral lane changing time when the current vehicle and the target vehicle overlap in the lateral direction; by the longitudinal risk time and the lateral lane changing time, the intelligent driving control of the current vehicle, including: based on the longitudinal risk time and the lateral lane changing time, calculating the risk index of the current vehicle and the target vehicle in the current driving scene; obtaining the first risk index data set of the current vehicle changing with time in a preset time period and the second risk index data set established by the current vehicle in a historical time when the current vehicle successfully avoids risk, and performing correlation analysis on the first risk index data set and the second risk index data set to obtain a risk correlation coefficient; when the risk correlation coefficient is greater than a first preset threshold and the risk index is less than a second preset threshold, generating an avoidance planning trajectory of the current vehicle based on the first historical trajectory information of the current vehicle and the second historical trajectory information of the target vehicle, and performing intelligent driving control on the current vehicle based on the avoidance planning trajectory. 2.The vehicle intelligent driving control method of claim 1, wherein, The method comprises: based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle, the longitudinal speed of the current vehicle and the longitudinal speed of the target vehicle, calculating the collision time when the current vehicle and the target vehicle collide in the longitudinal direction; based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle and the longitudinal speed of the current vehicle, calculating the headway time when the current vehicle travels to the position of the target vehicle; determining the longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction according to the collision time and the headway time. 3.The vehicle intelligent driving control method of claim 2, wherein The method comprises: In the formula, represents the collision time when the current vehicle and the target vehicle appear to collide in the longitudinal direction, represents the longitudinal position of the target vehicle; represents the longitudinal position of the current vehicle; represents the vehicle length of the target vehicle; the longitudinal speed of the target vehicle; the longitudinal speed of the current vehicle; based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle, the longitudinal speed of the current vehicle and the longitudinal speed of the target vehicle, calculating the collision time when the current vehicle and the target vehicle collide in the longitudinal direction; based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle and the longitudinal speed of the current vehicle, calculating the headway time when the current vehicle travels to the position of the target vehicle; In the formula, represents the corresponding headway time when the current vehicle travels to the target vehicle position.

4. The vehicle intelligent driving control method of claim 3, wherein, The lateral lane-changing time when the current vehicle and the target vehicle overlap in the lateral direction is calculated based on the lateral position of the current vehicle, the lateral position of the target vehicle, the vehicle width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle; In the formula, represents the lateral lane change time when the current vehicle and the target vehicle overlap in the lateral direction, represents the lateral position of the current vehicle, represents the lateral position of the target vehicle, represents the vehicle width of the target vehicle, represents the lateral speed of the target vehicle, represents the lateral speed of the current vehicle.

5. The vehicle intelligent drive control method according to claim 1, characterized by, The risk planning trajectory of the current vehicle is generated based on the first historical trajectory information of the current vehicle and the second historical trajectory information of the target vehicle, including: The first historical trajectory information and the second historical trajectory information are encoded by using an encoding neural network to obtain a current vehicle hidden layer vector and a target vehicle hidden layer vector containing historical trajectory features; The current vehicle hidden layer vector and the target vehicle hidden layer vector are taken as vertex feature vectors, and the current vehicle and the target vehicle are taken as vertices to connect the vertices to obtain edge feature vectors; A graph structure is constructed based on the vertex feature vectors and the edge feature vectors, and the connection relationship of the vertices in the graph structure is determined as an adjacency matrix; A trajectory interaction feature vector of the current vehicle and the target vehicle is generated based on the adjacency matrix and the vertex feature vectors; An attention score of the current vehicle and the target vehicle is calculated according to the current vehicle hidden layer vector and the target vehicle hidden layer vector, and the attention score is normalized to obtain an attention vector of the current vehicle and the target vehicle; The trajectory interaction feature vector and the attention vector are spliced to generate a driving intention recognition vector of the current vehicle; The trajectory interaction feature vector, the attention vector, and the driving intention recognition vector of the current vehicle are input into a decoding neural network for decoding to predict a future trajectory probability distribution under different driving intentions, and a risk planning trajectory of the current vehicle is generated based on the future trajectory probability distribution. 6.The vehicle intelligent driving control method of claim 1, wherein, The current driving scene includes a straight driving scene and / or a lane-changing driving scene, and the target vehicle is a vehicle whose distance from the current vehicle is within a preset distance range.

7. A vehicle intelligent driving control device, characterized by comprising: It includes: A data acquisition module is configured to acquire the longitudinal position, lateral position, longitudinal speed and lateral speed of the current vehicle in the current driving scene, and acquire the longitudinal position, lateral position, longitudinal speed, lateral speed, vehicle length and vehicle width of the target vehicle in the current driving scene; A first time calculation module is configured to calculate a longitudinal risk time when the current vehicle and the target vehicle collide in the longitudinal direction based on the longitudinal position of the current vehicle, the longitudinal position of the target vehicle, the vehicle length of the target vehicle, the longitudinal speed of the current vehicle, and the longitudinal speed of the target vehicle; A second time calculation module is configured to calculate a lateral lane-changing time when the current vehicle and the target vehicle overlap in the lateral direction based on the lateral position of the current vehicle, the lateral position of the target vehicle, the vehicle width of the target vehicle, the lateral speed of the current vehicle, and the lateral speed of the target vehicle; The intelligent driving control module is configured to perform intelligent driving control on the current vehicle based on the longitudinal risk time and the lateral lane-changing time, including: calculating a risk index of contact between the current vehicle and the target vehicle in the current driving scenario based on the longitudinal risk time and the lateral lane-changing time; obtaining a first risk index data set of the current vehicle changing over time in a preset time period and a second risk index data set of the current vehicle successfully avoiding risk in a historical time, and performing correlation analysis on the first risk index data set and the second risk index data set to obtain a risk correlation coefficient; when the risk correlation coefficient is greater than a first preset threshold and the risk index is less than a second preset threshold, generating an avoidance planning trajectory of the current vehicle based on first historical trajectory information of the current vehicle and second historical trajectory information of the target vehicle, and performing intelligent driving control on the current vehicle based on the avoidance planning trajectory.

8. An electronic device, comprising: comprising a memory and a processor, wherein the memory is configured to store a program; the processor, coupled with the memory, is configured to execute the program stored in the memory to implement the steps of the vehicle intelligent driving control method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, a computer readable program or instruction for storing, which can implement the steps of the vehicle intelligent driving control method in any one of claims 1 to 6 when executed by a processor.

Images