Autopilot Lane Change Method, Device, Electronic Device and Storage Medium

Abstract

The present invention relates to the field of autonomous driving technology, and discloses an autonomous driving lane-changing method, device, electronic device, and storage medium. The method includes: obtaining real-time road condition information and real-time vehicle condition information; collecting electroencephalogram of the driver to obtain real-time electroencephalogram information, where the electroencephalogram information represents the driving intention of the driver; based on the real-time road condition information and real-time vehicle condition information, using a trained lane-changing decision model to predict the driving route of the vehicle itself on the current road condition, and obtaining a route prediction result; comparing the route prediction result with the driving intention of the driver represented by the electroencephalogram information, and when the route prediction result is consistent with the driving intention of the driver, controlling the vehicle itself to perform a lane-changing driving action along the route prediction result. The embodiments of the present invention can improve the synchronization and safety during autonomous driving lane-changing.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular, to an autonomous driving lane-changing method, device, electronic device, and storage medium. Background Art

[0002] At present, road traffic injuries have become one of the important causes of death among the population. Approximately 95% of various motor vehicle accidents are caused by improper driver operation to a certain extent, and traffic accidents induced entirely by inappropriate driver behavior account for three-quarters of the total number of accidents. Therefore, it is very necessary to analyze driver behavior and driver state.

[0003] Currently, autonomous driving is mostly applied to specific scenarios. Under complex working conditions, it is still unable to compare with the decision-making and control capabilities of human drivers and is difficult to achieve full-condition application. Summary of the Invention

[0004] The purpose of the present invention is to provide an autonomous driving lane-changing method, device, electronic device, and storage medium, aiming to improve the synchronization and safety during autonomous driving lane-changing.

[0005] In a first aspect, an autonomous driving lane-changing method is provided, including:

[0006] Obtain real-time road condition information and real-time vehicle condition information. The road condition information includes the number of lanes, the lane where the vehicle is located, the driving vehicles, and the obstacle spacing representing the relative distance between the vehicle and the driving vehicle or obstacle. The vehicle condition information includes the vehicle speed and the vehicle positioning of the vehicle itself;

[0007] Collect electroencephalogram (EEG) of the driver to obtain real-time EEG information, which represents the driving intention of the driver;

[0008] Based on the real-time road condition information and real-time vehicle condition information, use the trained lane-changing decision model to predict the driving route of the vehicle itself under the current road conditions, and obtain the route prediction result;

[0009] Compare the route prediction result with the driving intention of the driver represented by the EEG information. When the route prediction result is consistent with the driving intention of the driver, Figure 1 Control the vehicle itself to perform a lane-changing driving action along the route prediction result.

[0010] In some embodiments, before obtaining the road condition information and vehicle condition information, it further includes:

[0011] Obtain offline training information, which includes offline road condition information and offline vehicle condition information;

[0012] Use the offline training information to construct a decision table;

[0013] Discretize the offline training information in the decision table, and use a preset neural network model to classify the discretized offline training information to obtain a discrete classification result;

[0014] Reduce the attributes of the decision table according to the discrete classification result, and determine the minimum set of conditional attributes for expressing the decision;

[0015] Integrate the minimum sets of conditional attributes with the same decision expression results, and calculate the coverage and confidence level of the integrated minimum set of conditional attributes to determine the offline decision rules;

[0016] Train the lane-changing decision model using the offline decision rules, and compare the route prediction results of the lane-changing decision model with the offline EEG information.

[0017] In some embodiments, the reducing the attributes of the decision table according to the discrete classification to determine the minimum set of conditional attributes for expressing the decision results includes:

[0018] Construct a training data set based on the offline training information, and randomly encode each type of offline training information in the training data set;

[0019] Calculate the dependence degree of the decision attribute on the offline training information required for the decision;

[0020] Determine whether the current dependence degree is equal to the minimum relative dependence value;

[0021] If so, when the optimal fitness of the training data set does not improve for several consecutive generations, output the minimum set of conditional attributes;

[0022] If not, iteratively perform random selection, crossover, and mutation processing on the training data set, copy the training data set with the optimal fitness to the next generation of training data set until the optimal fitness of the training data set does not improve for several consecutive generations and output the minimum set of conditional attributes.

[0023] In some embodiments, the collecting the EEG of the driver to obtain the EEG information characterizing the driving intention of the driver includes:

[0024] Collect the brain wave signals generated by the driver during driving to obtain the initial EEG information;

[0025] Preprocess the initial EEG information, and compare the preprocessed initial EEG information with a preset EEG analogy template to obtain an EEG analogy result;

[0026] Determine the error potentials existing in the preprocessed initial EEG information according to the EEG analogy result and perform rejection processing to obtain the EEG information characterizing the driving intention of the driver.

[0027] In some embodiments, controlling the host vehicle to perform a lane-changing driving action according to the route prediction result includes:

[0028] Finding a plurality of preview points based on the distance between the host vehicle and the obstacle, and drawing a lane-changing route using a Bezier curve constructed by the preview points;

[0029] Performing boundary dilation processing on the obstacle, and setting the dilation radius of the obstacle according to the current lane-changing route and the host vehicle environment information;

[0030] Judging whether the dilation radius of the obstacle is greater than the width of the obstacle;

[0031] If so, controlling the host vehicle to drive along the current lane-changing route;

[0032] If not, resetting the position of the preview point, redrawing the lane-changing route using a Bezier curve constructed by the reset preview point, the steering angle of the host vehicle corresponding to the redrawn lane-changing route being greater than the steering angle of the host vehicle corresponding to the previously drawn lane-changing route, and returning to the step of performing boundary dilation processing on the obstacle.

[0033] In some embodiments, controlling the host vehicle to drive along the current lane-changing route includes:

[0034] When no continuous obstacles appear within the detection range, controlling the host vehicle after lane change to drive past the obstacle and then change to the lane of the initial driving route; when continuous obstacles appear within the detection range, controlling the host vehicle after lane change to drive past the continuous obstacles and then change to the lane of the initial driving route;

[0035] The continuous obstacle is an obstacle whose distance from the previous obstacle in the same lane is less than a preset obstacle distance threshold.

[0036] In some embodiments, a simulated driving scenario is constructed based on real-time road condition information and real-time vehicle condition information, and the simulated driving scenario is displayed. The simulated driving scenario converts real-time road condition information into simulated road condition information and real-time vehicle condition information into simulated vehicle condition information.

[0037] In a second aspect, an automatic driving lane-changing device is provided, and the device includes:

[0038] An acquisition module, configured to acquire real-time road condition information and real-time vehicle condition information, where the road condition information includes the number of lanes, the lane where the host vehicle is located, driving vehicles, and an obstacle spacing characterizing the relative distance between the host vehicle and the driving vehicle or the obstacle, and the vehicle condition information includes the host vehicle speed and the host vehicle position;

[0039] A collection module, configured to perform electroencephalogram collection on the driver to obtain real-time electroencephalogram information, and the electroencephalogram information characterizes the driving intention of the driver;

[0040] The prediction module is used to predict the driving route of the vehicle under the current road conditions based on the real-time road condition information and the real-time vehicle condition information using the trained lane change decision model to obtain the route prediction result;

[0041] The control module is used to compare the route prediction result with the driver's driving intention represented by the EEG information, and Figure 1 When the vehicle is controlled to change lanes according to the route prediction result,

[0042] According to a third aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the automatic driving lane changing method according to the first aspect when executing the computer program.

[0043] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the automatic driving lane changing method described in the first aspect is implemented.

[0044] The beneficial effects of the present invention are as follows: based on a deep learning method, a lane change decision model is trained based on offline road condition information, vehicle condition information and EEG information representing the driver's driving intention, thereby promoting the realization of humanoid autonomous driving. The EEG-based driver intention recognition is objective and highly accurate, which improves the synchronization and safety of autonomous driving when changing lanes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flowchart of an automatic driving lane changing method shown in the first embodiment.

[0046] Figure 2 It is a flowchart of an automatic driving lane changing method shown in a second embodiment.

[0047] Figure 3 yes Figure 2 A first flow chart of step S204 in FIG.

[0048] Figure 4 yes Figure 1 A second flow chart of step S102 in FIG.

[0049] Figure 5 yes Figure 1 A third flow chart of step S104 in FIG.

[0050] Figure 6 It is a schematic diagram of the structure of the automatic driving lane changing device provided in an embodiment of the present application.

[0051] Figure 7 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application.

[0052] Figure 8 It is a schematic diagram of drawing a lane-changing route shown in the first embodiment.

[0053] Figure 9 It is a schematic diagram of drawing a lane-changing route shown in the second embodiment.

[0054] Figure 10 It is a schematic diagram of drawing a lane-changing route shown in the third embodiment. Detailed implementation manners

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the present invention will be further described below in conjunction with the embodiments and the drawings.

[0056] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0057] To make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the drawings and the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the description, the claims, and the above drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] First, several nouns involved in this application are analyzed:

[0061] 1) Artificial Intelligence (AI)

[0062] Artificial intelligence uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, a theory, method, technology, and application system that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines, enabling machines to have the functions of perception, reasoning, and decision-making.

[0063] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields involved, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0064] 2) Machine Learning (ML)

[0065] Machine learning is an interdisciplinary subject that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning from demonstration.

[0066] In related technologies, the algorithms for behavior decision-making mainly include rule-based behavior decision-making algorithms and learning-based behavior decision-making algorithms; rule-based decision-making methods have advantages in the breadth of scenario traversal, strong logical interpretability, and are easy to design according to scenarios in modules, and there are many decision-making system examples using finite state machines both at home and abroad. However, its system structure determines that there are certain bottlenecks in the depth of scenario traversal and decision-making accuracy, and it is difficult to handle complex working conditions; the advantage of the behavior decision-making system based on learning algorithms is that it has the advantage of the depth of scenario traversal. For a specific sub-scenario, it is easier to cover all working conditions through a big data system, but the learning algorithm does not have the advantage of the breadth of scenario traversal, and the learning models required for different scenarios may be completely different; machine learning requires a large amount of experimental data as learning samples; the decision-making effect depends on the data quality, and problems such as overlearning and underlearning will occur due to insufficient samples, poor data quality, and unreasonable network structure, and it is also unable to compare with the decision-making control ability of human drivers under complex working conditions, making it difficult to achieve full working condition applications.

[0067] Based on this, the embodiments of the present application provide an automatic driving lane-changing method, device, electronic device and storage medium, aiming to improve the synchronization and safety during automatic driving lane-changing.

[0068] The automatic driving lane-changing method, device, electronic device and storage medium provided by the embodiments of the present application are specifically described through the following embodiments. First, the recommendation method in the embodiments of the present application is described.

[0069] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0070] The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The automatic driving lane-changing method provided by the embodiments of the present application relates to the field of artificial intelligence technology. The automatic driving lane-changing method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can also be software running on the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application for implementing the table information extraction method, etc., but is not limited to the above forms.

[0072] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0073] It should be noted that in each specific embodiment of this application, when it comes to performing relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when this application embodiment needs to obtain the user's sensitive personal information, it will obtain the user's separate permission or separate consent through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of this application embodiment will be obtained.

[0074] Figure 1 It is a schematic flowchart of an automatic driving lane-changing method shown in the first embodiment. Figure 1 The method in [it] may include but is not limited to steps S101 to S104.

[0075] Step S101, obtain real-time road condition information and real-time vehicle condition information.

[0076] The road condition information includes the number of lanes, the lane where the vehicle itself is located, the moving vehicles, and the obstacle spacing characterizing the relative distance between the vehicle itself and the moving vehicles or obstacles. The vehicle condition information includes the vehicle speed and the vehicle positioning of the vehicle itself.

[0077] In a possible implementation manner, the road condition information and the vehicle condition information are the vehicle environment information and vehicle state information of the vehicle collected by a device with a sensing module. The sensing module includes lidar, cameras, a navigation system, and a car machine system, etc.

[0078] In a possible implementation, the road condition information may refer to all data related to vehicle driving safety in the environment where the vehicle is located collected by sensing modules such as lidar or cameras. For example, the vehicle environment information may be the driving states of all vehicles in the environment where the vehicle is located, or it may be the driving environment in the environment where the vehicle is located (such as lane line data, obstacle data, real-time positioning data, and map data). The embodiments of the present application do not make special limitations on this.

[0079] In a possible implementation, the vehicle condition information may refer to all data related to the vehicle's own driving state during the vehicle's driving collected by sensing modules such as the in-vehicle system. For example, the vehicle state information, actual vehicle speed data, sensing data on the steering wheel, brake pedal, accelerator pedal, and clutch. The embodiments of the present application do not make special limitations on this.

[0080] Step S102: Perform electroencephalogram (EEG) acquisition on the driver to obtain real-time EEG information, where the EEG information represents the driving intention of the driver.

[0081] It can be understood that when brain nerve cells react, corresponding electric waves will be generated. These electric waves are called brain waves. Collecting the brain waves and expressing them in the form of signals is the EEG information. By analyzing the waveform of the EEG information, the driving intention of the driver can be determined.

[0082] In a possible implementation, the EEG information may be the EEG information of the driver collected by a device with a brain-computer interface. The brain-computer interface has at least two electrodes. During the process of signal acquisition of the driver through the brain-computer interface, the two electrodes are located in different regions of the driver's head to collect the EEG information generated in different regions of the driver.

[0083] More specifically, a cosine similarity matrix is constructed according to the calculated cosine similarity. The type to which the cosine similarity matrix belongs is predicted through a trained convolutional neural network to obtain the type of driving intention to which the brain wave signal belongs. For example, if the feature vectors of the EEG information are all 128, then 128 cosine similarities can be calculated. At this time, a cosine similarity matrix can be constructed based on these 128 cosine similarities, and then the type to which the cosine similarity matrix belongs is predicted through a trained convolutional neural network to obtain the type of driving intention to which the EEG information belongs.

[0084] Step S103: Based on the real-time road condition information and real-time vehicle condition information, use the trained lane-changing decision model to predict the driving route of the host vehicle when driving in the current road conditions, and obtain a route prediction result.

[0085] Input the real-time road condition information and vehicle condition information into the trained lane-changing decision model, and the lane-changing decision model predicts the driving route. The route prediction result can include a lane-keeping mode, a lane-changing driving mode, or an intersection turning mode. It can be understood that the lane-keeping mode, the lane-changing driving mode, and the intersection turning mode are all preset driving modes. The route prediction result is based on the road condition information, vehicle condition information, and EEG information to judge the current road condition of the vehicle itself and the driving intention of the driver. When the driving space in the real-time driving area meets the preset conditions of the corresponding driving mode, the driving intention of the driver is executed on the basis of ensuring safety, so as to obtain the route prediction result.

[0086] In this embodiment, the lane-keeping mode can be understood as a driving mode in which the vehicle itself maintains driving along the current lane. The lane-changing driving mode can be understood as a driving mode in which the vehicle itself switches from the current driving lane to other lanes. The intersection turning can be understood as a driving mode in which the vehicle itself turns according to the initial driving route or the real-time driving route when it reaches the intersection.

[0087] Step S104, compare the route prediction result with the driving intention of the driver represented by the EEG information. When the route prediction result is consistent with the driving intention of the driver Figure 1 control the vehicle itself to perform a lane-changing driving action along the route prediction result.

[0088] In a possible implementation manner, compare the route prediction result with the driving intention of the driver represented by the EEG information. When the route prediction result is consistent with the driving intention of the driver Figure 1 control the vehicle itself to perform a lane-changing driving action along the route prediction result. By interacting with the control system of the vehicle itself, send the route prediction result to the control system of the vehicle. The control system of the vehicle converts the driving mode indicated by the received route prediction result into a control command for the vehicle, and controls the vehicle to drive according to the driving mode indicated by the route prediction result. When the route prediction result is a lane change, control the vehicle itself to perform a lane-changing driving action; otherwise, perform the driving action corresponding to the driving intention of the driver.

[0089] Figure 2 is a schematic flowchart of an automatic driving lane-changing method shown in the second embodiment. On the basis of Figure 1 the embodiment, Figure 2 the method in

[0090] Step S201, obtain offline training information.

[0091] The offline training information includes offline road condition information and offline vehicle condition information.

[0092] It can be understood that the offline training information is historical information that is saved, namely historical data road conditions information and historical vehicle conditions information. The historical data road conditions information and the historical vehicle conditions information are matched according to the generation time and form a training set.

[0093] Step S202, construct a decision table using the offline training information.

[0094] Among them, the decision table, also known as the judgment table, is a tabular graphical tool suitable for describing situations where there are many processing judgment conditions, the conditions are combined with each other, and there are multiple decision-making schemes. It is an accurate and concise way to describe complex logic, corresponding multiple conditions to the actions to be executed after these conditions are met. However, different from the control statements in traditional programming languages, the decision table can clearly show the direct connection between multiple independent conditions and multiple actions.

[0095] In a possible implementation, the offline training information is preprocessed to match the offline road conditions information and the offline vehicle conditions information according to time. For incomplete matching results, the rough neural network algorithm is used to eliminate the incomplete offline training information, thereby forming a decision table.

[0096] Step S203, perform discretization processing on the offline training information in the decision table, and use a preset neural network model to classify the discretized offline training information to obtain a discrete classification result.

[0097] In a possible implementation, the discretized offline training information is input into a preset neural network model. The preset neural network model is pre-set with probability parameters of a classification distribution, and it can be a classification distribution that obeys the preset probability parameters. The specific probability values of the preset probability parameters can be initially set in advance. Each group of data in the offline training information is numbered in turn. After obtaining the preset probability parameters, the data with the same label as the distribution selection parameter is obtained, and the selected data is classified into the corresponding category to obtain a discrete classification result.

[0098] Step S204, perform attribute reduction on the decision table according to the discrete classification result to determine the minimum set of conditional attributes for expressing decisions.

[0099] It can be understood that attribute reduction is to delete the offline training information in the decision table that has little effect on the decision, reducing the data volume of the decision table. This is because the discretized offline training information has the characteristics of a large data sample, diverse data, and relatively high data sample quality. Deleting the offline training information will not affect the expression of the object. By deleting these redundant data, the conditional attributes of the decision are simplified.

[0100] Step S205: Integrate the minimal conditional attribute sets with the same expression decision results, and calculate the coverage and confidence level of the integrated minimal conditional attribute sets to determine the offline decision rules.

[0101] In a possible implementation, summarize the minimal conditional attribute sets with the same expression decision results to extract the decision rules. Specifically, rule extraction is a process of summarizing the previous work. Simplify the decision table again according to the attribute reduction situation, merge the conditional attribute intervals and decision attributes that have been discretized and reduced, and calculate the coverage of the rule. The coverage is the proportion of this rule among all the rules with the same decision attribute.

[0102] Step S206: Use the offline decision rules to train the lane-changing decision model, and compare the route prediction result of the lane-changing decision model with the offline EEG information.

[0103] In a possible implementation, during the training process, iteratively adjust the parameters of the lane-changing decision model. When the degree of coincidence between the route prediction result of the lane-changing decision model and the offline EEG information reaches the preset accuracy rate, end the training.

[0104] Please refer to Figure 3 , in some embodiments, step S204 may include but is not limited to steps S301 to S305.

[0105] Step S301: Construct a training data set based on the offline training information, and randomly encode each type of offline training information in the training data set.

[0106] In a possible implementation, encoding each type of offline training information in the training data set may be to represent each data with a binary string of a fixed length, using random binary numbers, where each bit represents an attribute. For example, 1 represents selecting the decision attribute as the required data, and 0 represents not selecting the decision attribute as the required data.

[0107] Exemplarily, for a typical lane-changing scenario, the training data set constructed from the offline training information is {x i , y i , v i , x i环境 , y i环境 , v i环境}, where v i is the speed of the host vehicle, (x i , y i ) are the horizontal and vertical coordinates of the GPS position of the host vehicle, (x i环境 , y i环境 ) are the position coordinates of the surrounding vehicles or obstacles relative to the host vehicle, vi The environment is the speed of surrounding vehicles relative to the host vehicle. Randomly encode the training data set to obtain the binary string {0, 0, 1, 1, 0, 0}.

[0108] Step S302: Calculate the degree of dependence of the decision attribute on the offline training information required for decision-making.

[0109] In a possible implementation, first define a fitness function, and the fitness function is as follows:

[0110]

[0111] Use the dependence formula to calculate the degree of dependence of the decision attribute on the offline training information required for decision-making. The dependence formula is as follows:

[0112]

[0113] Where f(x) is the fitness function, h(x) is the number of 1s in a binary string, that is, the number of selected offline training information data, n is the total number of characters in this binary string, that is, the number of all offline training information data, m is the degree of dependence of the decision attribute on the conditional attribute represented by 1 in this binary string. The larger the m value, the stronger the dependence of the decision attribute on the conditional attribute. The goal is to make h(x) as small as possible while ensuring that the overall dependence degree of the decision attribute remains unchanged. V C (D) represents the degree of dependence of decision attribute D, c is the data of offline training information, and U is the universe of discourse.

[0114] Step S303: Determine whether the current degree of dependence is equal to the minimum relative dependence value. If so, execute Step S304; if not, execute Step S305.

[0115] Step S304: When the training data set with the optimal fitness does not improve for several consecutive generations, output the minimum conditional attribute set.

[0116] Step S305: Iteratively perform random selection, crossover, and mutation processing on the training data set, copy the training data set with the optimal fitness to the training data set of the next generation until the training data set with the optimal fitness does not improve for several consecutive generations and output the minimum conditional attribute set.

[0117] Please refer to Figure 4 , in some embodiments, Step S102 may include but is not limited to Step S401 to Step S403.

[0118] Step S401: Collect the electroencephalogram signals generated by the driver during driving to obtain the initial electroencephalogram information.

[0119] Step S402: Preprocess the initial EEG information, and compare the preprocessed initial EEG information with a preset EEG analogy template to obtain an EEG analogy result.

[0120] Step S403: Determine the error potentials existing in the preprocessed initial EEG information according to the EEG analogy result and perform rejection processing to obtain the EEG information representing the driving intention of the driver.

[0121] In a possible implementation manner, based on the Biopac actiCHAmp 64-channel EEG acquisition and analysis system, EEG signals are collected from 32 EEG channels from FP1 to O2; according to the position of the host vehicle, it is divided into six regions: front left, front center, front right, rear left, rear center, and rear right, and the position and speed information of the host vehicle and the position and speed information of other vehicles in the six regions are collected. The EEG signals of the FP1, F3, F7, FC5, FC1, FP2, F7, F4, F8, FC6, and FC2 channels are spatially filtered using the Common Average Reference (CAR) to eliminate noise; band-pass filtering is performed using a 1 - 10 hz band-pass filter; the EEG signal features are enhanced through canonical correlation analysis (CCA), and finally, template matching is implemented based on the analogy template for classification, and if incorrect correlation potentials are generated, they are rejected.

[0122] Please refer to Figure 5 , in some embodiments, step S104 may include but is not limited to steps S501 to S505.

[0123] Step S501: Find several preview points based on the distance between the host vehicle and the obstacle, and draw a lane-changing route using the Bézier curve constructed by the preview points.

[0124] The Bézier curve, also known as the Bezier curve or Bezier curve, is a mathematical curve applied to two-dimensional graphic applications. The Bézier curve creates and edits graphics by controlling four points on the curve (the starting point, the ending point, and two separate intermediate points), and the control line located in the center of the curve plays an important role. This line is virtual, crosses the Bézier curve in the middle, and the two ends are control endpoints. When moving the endpoints at both ends, the Bézier curve changes the curvature (the degree of bending) of the curve; when moving the intermediate points (that is, moving the virtual control line), the Bézier curve makes a uniform movement under the condition that the starting point and the ending point are locked.

[0125] The Bézier curve has the advantages of continuous curvature, easy tracking, and meeting vehicle dynamics constraints. Therefore, in the embodiments of the present invention, a fifth-order Bézier curve is selected to draw the lane-changing route.

[0126] The fifth-order Bessel curve can be expressed as:

[0127]

[0128] It can be expressed as:

[0129]

[0130] where B(t) represents the Bessel curve, and P 0 , P 1 , P 2 , P 3 , P 4 and P 5 are all preview points, t ∈ [0, 1], n ∈ [0, 5], i ∈ [0, 5].

[0131] Finding several preview points based on the distance between the host vehicle and the obstacle can be carried out by selecting within the real-time driving area, and connecting the selected preview points to obtain a Bessel curve as the lane-changing route. As Figure 8 shown, the coordinates P i = (X i , Y i ) of the 6 preview points in the fifth-order Bessel curve are determined according to the distance between the selected autonomous driving vehicle and the obstacle. Specifically:

[0132] First, determine the coordinates of preview points P 0 and P 5 :

[0133] P 0 = (X 0 , Y 0 );

[0134] P 5 = (X 5 , Y 5 ) = (L, w r );

[0135] Divide the distance between the host vehicle and the obstacle into 4 parts to obtain the coordinates of P 1 , P 2 , P 3 and P 4 :

[0136] P 1 = (X 1 , Y 1 ) = (X 5 / 4, Y 0 );

[0137] P 2 = (X2 , Y 2 ) = (X 5 / 2, Y 0 );

[0138] P 3 = (X 3 , Y 3 ) = (X 5 / 2, Y 5 );

[0139] P 4 = (X 4 , Y 4 ) = (3X 5 / 4, Y 5 );

[0140] Among them, L is the distance between the host vehicle and the obstacle in the frenet coordinate system detected by the perception system; w r is the lane width information provided by the lane line detection in the perception system.

[0141] Step S502: Perform boundary dilation processing on the obstacle, and set the dilation radius of the obstacle according to the current lane change route and the host vehicle environment information.

[0142] When using a Bezier curve to draw the lane change route, since the vehicle is regarded as a particle and the vehicle's own width is ignored, there is a possibility of collision with the obstacle when the host vehicle travels along the lane change route. By performing boundary dilation processing on the obstacle, the distance between the host vehicle and the obstacle when traveling along the lane change route is compared with the collision radius of the dilated obstacle for collision assessment. The formula for collision assessment can be expressed as:

[0143]

[0144] Among them, r is the dilation radius of the obstacle, is the vehicle's own width, d min is the desired minimum safety distance between the obstacle and the host vehicle, y ob is the projection distance between the center of the obstacle and the lane line in the frenet coordinate system, w c1 is the width of the obstacle detected by the perception system.

[0145] Step S503: Determine whether the dilation radius of the obstacle is greater than the width of the obstacle. If so, execute Step S504; if not, execute Step S505.

[0146] When determining whether the dilation radius of the obstacle is greater than the width of the obstacle, that is:

[0147]

[0148] Step S404, control the host vehicle to drive along the current lane-changing route.

[0149] Step S505, reset the position of the preview point, redraw the lane-changing route using the Bezier curve constructed with the reset preview point, and the steering angle of the host vehicle corresponding to the redrawn lane-changing route is greater than the steering angle of the host vehicle corresponding to the previously drawn lane-changing route. Return to step S502.

[0150] Re-select the preview point within the real-time driving area. First, re-determine the coordinates of the preview point P 5 , by shortening the distance between P 0 and P 5 to increase the steering angle of the host vehicle, so that the steering angle of the host vehicle corresponding to the redrawn lane-changing route is greater than the steering angle of the host vehicle corresponding to the previously drawn lane-changing route, reducing the collision risk between the host vehicle and the obstacle. In this embodiment, the coordinates of the preview point P 5 are changed according to the following formula:

[0151] P 5 = (X 5 , Y 5 ) = (4L / 5, w r ).

[0152] As Figure 9 shown, after the host vehicle drives along the current lane-changing route and bypasses the obstacle, control the host vehicle to return to the lane of the initial driving route. It can be to draw the route on the lane of the initial driving route using the mirrored Bezier curve, so as to return to the lane of the initial driving route after bypassing the obstacle.

[0153] In some embodiments, as Figure 10 shown, controlling the host vehicle to drive along the current lane-changing route can be when there are no continuous obstacles within the detection range, control the lane-changed host vehicle to drive past the obstacle and then change to the lane of the initial driving route; when there are continuous obstacles within the detection range, control the lane-changed host vehicle to drive past the continuous obstacles and then change to the lane of the initial driving route. Among them, continuous obstacles are obstacles whose distance from the previous obstacle in the same lane is less than the preset obstacle distance threshold.

[0154] In the above embodiments, the control of the host vehicle includes lateral control and longitudinal control.

[0155] The lateral control adopts the LQR algorithm. The steps of the LQR algorithm in the discrete case are as follows:

[0156] 1. Determine the iteration range N;

[0157] 2. Set the initial iteration value, let P N = Q f , where Q f = Q;

[0158] 3. Loop iteratively from t = N to 1 in reverse order:

[0159] P t-1 = Q + A T P t A - A T P t B(R + B T P t B) -1 B T P t A;

[0160] 4. Calculate the feedback coefficient iteratively from t = 0 to N - 1:

[0161] K t = (R + B T P t+1 B) -1 B T P t+1 A;

[0162] 5. Finally, obtain the optimized control quantity:

[0163]

[0164] The longitudinal control is based on the PID algorithm, specifically:

[0165] Construct a control quantity output model based on the target speed. The control quantity output model is:

[0166]

[0167] where U t represents the control output quantity, e(t) = v d - v a v d represents the target speed, v a represents the current speed, K P represents the proportional amplification coefficient, K I represents the integral time constant, K D represents the differential time constant;

[0168] Discretize the control quantity output model to obtain a discrete control quantity output model. The discrete control quantity output model is:

[0169]

[0170] where T is the command period of the controller, e j represents the speed deviation at the j-th moment, e k represents the speed deviation at the k-th moment, ek-1 represents the speed deviation at time k-1;

[0171] Calculate the control output quantity using the discrete control quantity output model, and perform assisted driving control on the vehicle through the calculated control output quantity.

[0172] In some embodiments, a simulated driving scenario is constructed based on real-time road condition information and real-time vehicle condition information, and the simulated driving scenario is displayed. The simulated driving scenario converts real-time road condition information into simulated road condition information and real-time vehicle condition information into simulated vehicle condition information.

[0173] As can be seen from the above, in the automatic driving lane-changing method provided in the embodiments of the present application, based on the deep learning method, the lane-changing decision-making model is trained based on offline road condition information, vehicle condition information, and electroencephalogram information representing the driver's driving intention, promoting the realization of human-like automatic driving. The driver intention recognition based on electroencephalogram is objective and has a high accuracy rate, improving the synchronization and safety during automatic driving lane-changing.

[0174] To better implement the above method, an embodiment of the present invention further provides an assisted driving device, which can be specifically integrated in electronic devices such as a server or a terminal.

[0175] Please refer to Figure 6 , an embodiment of the present application further provides an automatic driving lane-changing device, which can implement the automatic driving lane-changing method mentioned in the above embodiments. The device includes:

[0176] An acquisition module 601, configured to acquire real-time road condition information and real-time vehicle condition information. The road condition information includes the number of lanes, the lane where the vehicle is located, the driving vehicles, and the obstacle spacing representing the relative distance between the vehicle and the driving vehicles or obstacles. The vehicle condition information includes the vehicle speed and the vehicle positioning of the vehicle itself;

[0177] An acquisition module 602, configured to perform electroencephalogram acquisition on the driver to obtain real-time electroencephalogram information, and the electroencephalogram information represents the driver's driving intention;

[0178] A prediction module 603, configured to predict the driving route of the vehicle itself under the current road conditions using the trained lane-changing decision-making model based on the real-time road condition information and real-time vehicle condition information, and obtain a route prediction result;

[0179] A control module 604, configured to compare the route prediction result with the driver's driving intention represented by the electroencephalogram information. When the route prediction result is consistent with the driver's driving intention Figure 1 , control the vehicle itself to perform a lane-changing driving action along the route prediction result.

[0180] The specific implementation of the automatic driving lane-changing device is basically the same as the specific embodiment of the above-mentioned automatic driving lane-changing method, and will not be elaborated here.

[0181] An embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned automatic driving lane-changing method is implemented. The electronic device can be any intelligent terminal including a tablet computer, an in-vehicle computer, etc.

[0182] Please refer to Figure 7 , Figure 7 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes:

[0183] A processor 701, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0184] A memory 702, which can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 702, and the processor 701 is called to execute the automatic driving lane-changing method of the embodiments of the present application;

[0185] An input / output interface 703, which is used to implement information input and output;

[0186] A communication interface 704, which is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0187] A bus 705, which transmits information between various components of the device (such as the processor 701, the memory 702, the input / output interface 703, and the communication interface 704);

[0188] Among them, the processor 701, the memory 702, the input / output interface 703, and the communication interface 704 are communicatively connected to each other inside the device through the bus 705.

[0189] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned automatic driving lane-changing method is implemented.

[0190] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0191] The automatic driving lane-changing method, device, electronic device, and storage medium provided by the embodiments of the present application are based on a deep learning method, and train a lane-changing decision model based on offline road condition information, vehicle condition information, and electroencephalogram information characterizing the driver's driving intention, promoting the realization of human-like automatic driving. The driver intention recognition based on electroencephalogram is objective and has a high accuracy rate, improving the synchronization and safety during automatic driving lane-changing.

[0192] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0193] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or combine certain steps, or different steps.

[0194] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0196] In the description of the present application and the above-mentioned drawings, terms such as "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0197] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0198] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0199] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0201] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The foregoing storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0202] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings. However, this does not limit the scope of the rights of the embodiments of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall fall within the scope of the rights of the embodiments of the present application.

Claims

1. An automatic driving lane change method, characterized in that, it includes: Obtain real-time road condition information and real-time vehicle condition information. The road condition information includes the number of lanes, the lane where the vehicle is located, the driving vehicles, and the obstacle distance representing the relative distance between the vehicle and the driving vehicle or obstacle. The vehicle condition information includes the vehicle speed and the vehicle positioning; Collect the electroencephalogram of the driver to obtain real-time electroencephalogram information. The electroencephalogram information represents the driving intention of the driver. Among them, a cosine similarity matrix is constructed according to the calculated cosine similarity, and the type of the cosine similarity matrix is predicted through a trained convolutional neural network to obtain the driving intention type to which the electroencephalogram signal belongs; Based on the real-time road condition information and real-time vehicle condition information, use the trained lane change decision model to predict the driving route of the vehicle under the current road conditions, and obtain the route prediction result; Compare the route prediction result with the driving intention of the driver represented by the electroencephalogram information. When the route prediction result is consistent with the driving intention of the driver, control the vehicle to perform a lane change driving action along the route prediction result; Before obtaining the road condition information and vehicle condition information, it further includes: Obtain offline training information, where the offline training information includes offline road condition information and offline vehicle condition information; Use the offline training information to construct a decision table; Discretize the offline training information in the decision table, and use a preset neural network model to classify the discretized offline training information to obtain a discrete classification result; Reduce the attributes of the decision table according to the discrete classification result, and determine the minimum condition attribute set for expressing the decision; Integrate the minimum condition attribute sets with the same decision results, and calculate the coverage and confidence level of the integrated minimum condition attribute set to determine the offline decision rule; Use the offline decision rule to train the lane change decision model, and compare the route prediction result of the lane change decision model with the offline electroencephalogram information.

2. The automatic driving lane change method according to claim 1, characterized in that, The reducing the attributes of the decision table according to the discrete classification to determine the minimum condition attribute set for expressing the decision result includes: Construct a training data set based on the offline training information, and randomly encode the offline training information of each type in the training data set; Calculate the dependence degree of the decision attribute on the offline training information required for the decision; Judge whether the current dependence degree is equal to the minimum relative dependence value; If so, when the training data set with the optimal fitness no longer improves for several consecutive generations, output the minimum condition attribute set; If not, iteratively perform random selection, crossover, and mutation processing on the training data set, copy the training data set with the optimal fitness to the next generation of training data set until the training data set with the optimal fitness no longer improves for several consecutive generations and output the minimum condition attribute set.

3. The automatic driving lane change method according to claim 1, characterized in that, The collecting the electroencephalogram of the driver to obtain the electroencephalogram information representing the driving intention of the driver includes: Collect the electroencephalogram signal generated when the driver is driving to obtain the initial electroencephalogram information; Preprocess the initial EEG information, and compare the preprocessed initial EEG information with a preset EEG analogy template to obtain an EEG analogy result; Determine the incorrect potentials existing in the preprocessed initial EEG information according to the EEG analogy result and perform rejection processing to obtain the EEG information characterizing the driver's driving intention.

4. The automatic driving lane-changing method according to claim 1, characterized in that the controlling the host vehicle to perform a lane-changing driving action along the route prediction result includes: Search for a plurality of preview points based on the distance between the host vehicle and the obstacle, and draw a lane-changing route using a Bezier curve constructed by the preview points; Perform boundary dilation processing on the obstacle, and set the dilation radius of the obstacle according to the current lane-changing route and the host vehicle environment information; Judge whether the dilation radius of the obstacle is greater than the width of the obstacle; If so, control the host vehicle to drive along the current lane-changing route; If not, reset the position of the preview points, redraw the lane-changing route using the Bezier curve constructed by the reset preview points, and the steering angle of the host vehicle corresponding to the redrawn lane-changing route is greater than the steering angle of the host vehicle corresponding to the previously drawn lane-changing route, and return to the step of performing boundary dilation processing on the obstacle.

5. The automatic driving lane-changing method according to claim 4, characterized in that the controlling the host vehicle to drive along the current lane-changing route includes: When there are no continuous obstacles within the detection range, control the lane-changed host vehicle to drive past the obstacle and then change to the lane of the initial driving route; when there are continuous obstacles within the detection range, control the lane-changed host vehicle to drive past the continuous obstacles and then change to the lane of the initial driving route; The continuous obstacle is an obstacle whose distance from the previous obstacle in the same lane is less than a preset obstacle distance threshold.

6. The automatic driving lane-changing method according to claim 1, characterized in that further comprising: Construct a simulated driving scenario based on real-time road condition information and real-time vehicle condition information, and display the simulated driving scenario, where the simulated driving scenario converts real-time road condition information into simulated road condition information and converts real-time vehicle condition information into simulated vehicle condition information.

7. An automatic driving lane-changing device, characterized in that the device includes: An acquisition module for acquiring real-time road condition information and real-time vehicle condition information, where the road condition information includes the number of lanes, the lane where the host vehicle is located, the driving vehicles, and the obstacle spacing characterizing the relative distance between the host vehicle and the driving vehicles or obstacles, and the vehicle condition information includes the host vehicle speed and the host vehicle positioning; A collection module for collecting EEG of the driver to obtain real-time EEG information, where the EEG information characterizes the driver's driving intention. Among them, a cosine similarity matrix is constructed according to the calculated cosine similarity, and the type of the cosine similarity matrix is predicted by a trained convolutional neural network to obtain the driving intention type to which the EEG signal belongs; A prediction module for predicting the driving route of the host vehicle under the current road conditions based on real-time road condition information and real-time vehicle condition information by using a trained lane-changing decision model to obtain a route prediction result; A control module, configured to compare the route prediction result with the driving intention of the driver represented by the electroencephalogram information, and when the route prediction result is consistent with the driving intention of the driver, control the host vehicle to perform a lane change driving action along the route prediction result; Before obtaining the road condition information and the vehicle condition information, it further includes: Obtaining offline training information, where the offline training information includes offline road condition information and offline vehicle condition information; Constructing a decision table using the offline training information; Performing discretization processing on the offline training information in the decision table, and using a preset neural network model to classify the discretized offline training information to obtain a discrete classification result; Performing attribute reduction on the decision table according to the discrete classification result to determine the minimum condition attribute set for expressing the decision; Integrating the minimum condition attribute sets with the same decision results, calculating the coverage and confidence level of the integrated minimum condition attribute set to determine the offline decision rule; Training the lane change decision model using the offline decision rule, and comparing the route prediction result of the lane change decision model with the offline electroencephalogram information.

8. An electronic device, Characterized in that, The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the automatic driving lane change method according to any one of claims 1 to 6.

9. A computer-readable storage medium, the computer-readable storage medium stores a computer program, Characterized in that, When the computer program is executed by a processor, it implements the automatic driving lane change method according to any one of claims 1 to 6.

Images