CN115571165A - Vehicle control method, device, electronic equipment and computer readable medium - Google Patents
Vehicle control method, device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN115571165A CN115571165A CN202211575828.0A CN202211575828A CN115571165A CN 115571165 A CN115571165 A CN 115571165A CN 202211575828 A CN202211575828 A CN 202211575828A CN 115571165 A CN115571165 A CN 115571165A
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- driver
- target
- lane change
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 148
- 230000004044 response Effects 0.000 claims abstract description 44
- 230000002452 interceptive effect Effects 0.000 claims abstract description 38
- 230000003993 interaction Effects 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000007613 environmental effect Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 description 40
- 230000006870 function Effects 0.000 description 32
- 230000008569 process Effects 0.000 description 15
- 230000008901 benefit Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 10
- 230000006399 behavior Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008450 motivation Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 239000000126 substance Substances 0.000 description 6
- 238000009499 grossing Methods 0.000 description 5
- 230000015654 memory Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 231100000817 safety factor Toxicity 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
- B60W60/00272—Planning or execution of driving tasks using trajectory prediction for other traffic participants relying on extrapolation of current movement
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4045—Intention, e.g. lane change or imminent movement
Abstract
The embodiment of the disclosure discloses a vehicle control method, a vehicle control device, an electronic device and a computer readable medium. One embodiment of the method comprises: controlling a vehicle-mounted sensor to acquire environmental information and interactive information of a target vehicle; identifying driver information of a target vehicle; in response to determining that the driver information corresponds to a driver being a target driver, determining driving style information of the target driver; recognizing lane change intention information of a target driver according to the environment information, the interaction information and the driving style information; generating vehicle control information according to the lane change intention information and the environment information; determining whether driving conflict exists between the vehicle control information and the interactive information; and controlling the vehicle-mounted system to perform lane change processing on the target vehicle according to the vehicle control information. The embodiment can take the influence of the driving style of the driver and the intention of changing lanes on the lane changing strategy into consideration, so as to improve the driving safety and the driving experience of the driver.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a vehicle control method and apparatus, an electronic device, and a computer-readable medium.
Background
Lane changing is a common driving behavior and one of the major dangerous behaviors that cause traffic accidents. The lane change behavior is one of the comprehensive decision behaviors that a driver adjusts the position of a vehicle in traffic by aiming at pursuing a certain interest motivation according to the surrounding road conditions and the surrounding vehicle information. For controlling the lane change of the vehicle, the following methods are generally adopted: based on an artificial intelligence model, a series of artificial intelligence algorithms are used for carrying out modeling analysis on the behavior of the lane to be changed; based on the model of the incentive, the maximum benefit is typically selected to decide whether to take a lane change.
However, the inventor has found that when the vehicle is controlled to change lanes in the above manner, the following technical problems often occur:
firstly, when the lane of the vehicle is changed, only the factors of the lane changing vehicle are considered, and the lane changing decision is not accurate due to the single data source, so that the safety of the lane changing vehicle and the experience of a driver are reduced.
Second, when changing lanes for a vehicle, the influence of the situation of communication with surrounding vehicles and the driving style on changing lanes is not considered, resulting in a reduction in the safety of changing lanes and a missing opportunity to change lanes.
Thirdly, for a driver with little driving data, it is difficult to determine the driving style information of the driver through the history data, so that the intention of changing lanes of the driver cannot be recognized, thereby reducing the safety of the vehicle in the driving process.
The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art in this country.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a vehicle control method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a vehicle control method, including: controlling a vehicle-mounted sensor to acquire environmental information and interactive information of a target vehicle, wherein the interactive information can be operation instruction information of a driver on the target vehicle; identifying driver information of the target vehicle; in response to determining that the driver information corresponds to a driver being a target driver, determining driving style information of the target driver; recognizing lane change intention information of the target driver according to the environment information, the interaction information and the driving style information; generating vehicle control information according to the lane change intention information and the environment information; in response to determining that the interactive information is not null information, determining whether a driving conflict exists between the vehicle operation information and the interactive information; and in response to determining that no driving conflict exists, controlling an on-board system to perform lane change processing on the target vehicle according to the vehicle control information.
In a second aspect, some embodiments of the present disclosure provide a vehicle control apparatus including: the control system comprises a first control unit, a second control unit and a control unit, wherein the first control unit is configured to control an on-board sensor to acquire environmental information and interaction information of a target vehicle, and the interaction information can be operation instruction information of a driver on the target vehicle; a first recognition unit configured to recognize driver information of the target vehicle; a first determination unit configured to determine driving style information of a target driver in response to determining that the driver information corresponds to the driver being the target driver; a second recognition unit configured to recognize lane change intention information of the target driver based on the environment information, the interaction information, and the driving style information; a generating unit configured to generate vehicle manipulation information according to the lane change intention information and the environment information; a second determination unit configured to determine whether there is a driving conflict between the vehicle manipulation information and the interactive information in response to determining that the interactive information is not null information; and a second control unit configured to control an in-vehicle system to perform lane change processing on the target vehicle according to the vehicle manipulation information in response to a determination that there is no driving conflict.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following beneficial effects: the vehicle control method of some embodiments of the present disclosure takes into account the influence of the driving style and lane change intention of the driver on the lane change strategy to improve the driving safety and driving experience of the driver. In particular, the reason for the lower driving safety and driving experience of the driver concerned is that: when the vehicle changes lanes, only the factors of the lane changing vehicle are considered, and the lane changing decision is not accurate due to the single data source. Based on this, the vehicle control method of some embodiments of the present disclosure may first control the vehicle-mounted sensor to acquire environmental information and interaction information of a target vehicle, where the interaction information may be operation instruction information of a driver on the target vehicle. The environmental information and the interaction information acquired by the vehicle-mounted sensor facilitate the determination of subsequent driving style information and vehicle control information. And secondly, identifying the driver information of the target vehicle, wherein the identification of the driver information is used for subsequently determining the identity of the driver of the target vehicle and determining the driving style of the driver. And thirdly, in response to the fact that the driver corresponding to the driver information is determined to be the target driver, determining the driving style information of the target driver. Here, the driving style of the target driver is determined for subsequent determination of the vehicle handling information. Next, lane change intention information of the target driver is recognized based on the environment information, the interaction information, and the driving style information. The resulting lane change intention information is used for the subsequent determination of the vehicle operating information. Then, vehicle control information is generated according to the lane change intention information and the environment information. The resulting control information is used to control a safe lane change of the vehicle. Then, in response to determining that the interactive information is not null information, it is determined whether there is a driving conflict between the vehicle operation information and the interactive information. Here, whether conflict exists between the vehicle control information and the interactive information is checked, and the driving experience and the driving safety of a driver driving the vehicle are improved. And finally, in response to determining that no driving conflict exists, controlling an on-board system to perform lane changing processing on the target vehicle according to the vehicle control information. Therefore, the vehicle control method can take the influence of the driving style of the driver and the intention of changing lanes on the lane changing strategy into consideration, so as to improve the driving safety and the driving experience of the driver.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.
FIG. 1 is a flow chart of some embodiments of a vehicle control method according to the present disclosure;
FIG. 2 is a schematic structural diagram of some embodiments of a vehicle control apparatus according to the present disclosure;
FIG. 3 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Referring to fig. 1, a flow 100 of some embodiments of a vehicle control method according to the present disclosure is shown. The vehicle control method includes the steps of:
and step 101, controlling a vehicle-mounted sensor to acquire environmental information and interactive information of a target vehicle.
In some embodiments, the executing subject of the vehicle control method may control the vehicle-mounted sensor to acquire environmental information and interaction information of the target vehicle. The interactive information may be operation instruction information of the driver on the target vehicle. The environmental information may be surrounding vehicle information and road information. The above-mentioned on-board sensor may include at least one of: laser radar, camera and GPS sensor. The target vehicle may be a vehicle that collects environmental information and interactive information. For example, the target vehicle may be an unmanned vehicle.
In some embodiments, the execution subject may identify driver information of the target vehicle. Wherein, the driver information may include: the face information, name and identification number of the driver.
As an example, the execution body may control a camera mounted on the target vehicle to capture an image of a driver of the target vehicle, so as to obtain image data of the driver. Then, feature recognition is performed on the image data to obtain the driver information.
In some embodiments, the executing entity may determine the driving style information of the target driver in response to determining that the driver information corresponds to the driver being the target driver. The target driver may be a driver who has driven the target vehicle for the longest time among the drivers who drive the target vehicle. The driving style information may be driving behavior characteristic information representing that a driver habitually manipulates the vehicle during driving. The driving style information may be conservative driving style information, or stable driving style information. The driving style information may also be aggressive driving style information. The driver with conservative driving style information is characterized by relatively slow response to traffic conditions, relatively slow driving speed, less overtaking times, no risk motivation and tendency to drive at low speed. The driver with stable driving style information is characterized in that the operation of the vehicle is stable in the driving process of the vehicle, the vehicle speed is kept fluctuating within a normal range, and sudden acceleration and deceleration do not occur. The characteristics of drivers with aggressive driving style information are that the drivers often pursue faster vehicle speed, have higher risk motivation and strong overtaking motivation, and are easy to have rapid acceleration and rapid deceleration in the driving process.
As an example, the execution subject may first acquire the historical driving data of the target driver through the target driver information. Next, the historical driving data is input to a high-dimensional gaussian Hidden Markov Model (HMM) to obtain driving style information of the target driver.
In some optional implementations of some embodiments, the determining the driving style of the driver may include:
the method comprises the steps of firstly, controlling a driving simulator and an intelligent bracelet to respectively collect driving style characteristic data representing a driver. The driving style characteristic data may be data representing a driving style. The driving style characteristic data includes: longitudinal speed average value, longitudinal speed maximum value, longitudinal speed standard deviation, longitudinal speed minimum value, longitudinal acceleration average value, longitudinal acceleration maximum value, longitudinal acceleration minimum value, longitudinal acceleration standard deviation, transverse acceleration maximum value, transverse acceleration minimum value, minimum headway time, collision time parameter reciprocal and minimum headway.
And secondly, performing data dimension reduction processing on the driving style characteristic data matrix to obtain driving style characteristic data subjected to dimension reduction as first driving style characteristic data.
For example, the executing unit may perform data dimension reduction processing on the driving style characteristic data by using a principal component analysis method to obtain driving style characteristic data after dimension reduction as the first driving style characteristic data.
And thirdly, clustering the first driving style characteristic data to determine the driving style of the first driver.
As an example, the executing entity may perform clustering processing on the first driving style characteristic data by using a fuzzy mean algorithm to determine the driving style of the first driver.
Optionally, after determining the driving style information of the target driver in response to determining that the driver information corresponds to the driver being the target driver, the method may further include:
and the first step, in response to the fact that the driver corresponding to the driver information is determined to be a first driver, screening the driving data to obtain target driving data. The first driver may be a driver who has not driven the target vehicle before. The above-mentioned driving data may be driving data of each driver driving the target vehicle collected to drive the target vehicle. For example, the driving data may include: data characterizing the driving state of the vehicle, data relating to driver information, data relating to road traffic conditions. The target driving data may include at least one of: longitudinal speed of the vehicle, longitudinal acceleration of the vehicle, lateral acceleration of the vehicle, distance from the surrounding vehicle, time distance from the surrounding vehicle, vehicle number, time of collision, distance from the center of the vehicle to the edge of the road, etc.
As an example, the execution subject described above may screen out data representing the running state of the vehicle from the driving data as the target driving data.
And step two, smoothing the target driving data to generate smoothed target driving data serving as first target driving data. The first target driving data may be target driving data obtained by performing smoothing processing to remove noise data.
As an example, the executing body may perform smoothing processing on the target driving data by using a least square smoothing filter method to obtain driving characteristic data.
And thirdly, screening the first target driving data to generate screened first target driving data serving as driving characteristic data. The driving characteristic data may be first target driving data obtained by removing first target driving data having a sub-portion that does not meet the requirement. For example, the unsatisfactory first target driving data may be the first target driving data having the lowest headway and the minimum headway of-1 of the vehicle. For example, the first target driving data may include data of the lowest headway and the minimum headway of-1 of the vehicle, and the data of the lowest headway and the minimum headway of-1 of the vehicle represents a no-driving vehicle ahead of the vehicle. And deleting data with the minimum headway time and the minimum headway distance of-1 from the first target driving data to obtain driving characteristic data.
And fourthly, performing dimension reduction on the driving characteristic data to obtain first driving characteristic data. Wherein the driving characteristic data may include at least one of: longitudinal velocity mean, longitudinal velocity maximum, longitudinal velocity minimum, longitudinal velocity standard deviation, longitudinal acceleration mean, longitudinal acceleration standard deviation, longitudinal acceleration maximum, longitudinal acceleration minimum, lateral acceleration mean, lateral acceleration standard deviation, lateral acceleration maximum, lateral acceleration minimum, minimum headway, and time to collision. The first driving characteristic data may be first driving characteristic data representing maximum speed, minimum speed and average speed, first driving characteristic data representing a standard deviation of lateral acceleration and a maximum value of lateral acceleration, first driving characteristic data representing a mean value of longitudinal acceleration and a maximum value of longitudinal acceleration, first driving characteristic data representing a standard deviation of longitudinal acceleration, first driving characteristic data representing minimum headway and minimum headway, and first driving characteristic data representing a mean value of lateral acceleration.
As an example, the executing body may perform dimension reduction on the first target driving data by using a principal component analysis method to obtain driving characteristic data.
And fifthly, performing cluster analysis on the driving characteristic data to obtain various driving style information. Wherein the plurality of driving style information comprises at least one of: conservative driving style information, stable driving style information, and aggressive driving style information. The driver with conservative driving style information is characterized by slow response to traffic conditions, slow driving speed, less overtaking times, no risk-taking motivation and tendency to drive at low speed. Drivers with stable driving style information are characterized by stable driving speed, normal range and no sudden acceleration or deceleration. The characteristics of drivers with aggressive driving style information are that the drivers seek faster driving speed, have higher risk causing motivation and strong overtaking motivation, and are easy to have the situations of rapid acceleration and rapid deceleration in the driving process. The driving style may be a characteristic of the driving behavior of the driver on the vehicle during driving.
As an example, the executing entity may perform cluster analysis on the driving characteristic data by using a K-means algorithm to obtain a plurality of driving style information.
And sixthly, performing statistical analysis on the number of drivers corresponding to each driving style information in the multiple driving style information to obtain a driver number set corresponding to each driving style.
And seventhly, determining the driving style information corresponding to the largest number of drivers in the driver data set as the driving style information of the first driver.
The technical scheme and the related content thereof are taken as an invention point of the embodiment of the disclosure, and the technical problems mentioned in the background art are solved, namely, for a driver with little driving data, the driving style information of the driver is difficult to determine through historical data, so that the lane changing intention of the driver cannot be identified, and the safety of the vehicle in the driving process is further reduced. The safety factors during the driving of the vehicle tend to be as follows: for a driver with little driving data, it is difficult to determine the driving style information of the driver from the history data, resulting in failure to recognize the intention of the driver to change lanes. If the factors are solved, the safety of the vehicle in the running process can be improved. In order to achieve the effect, the present disclosure first performs a screening process on the driving data to obtain target driving data in response to determining that the driver corresponding to the driver information is the first driver. Here, since the first driver is a person who has not driven the target vehicle before, the first driving data of the first driver is lacked, and the collected driving data of the other drivers who driven the target vehicle is taken as the driving data of the first driver, which is advantageous for determining the driving style information of the first driver. And then, smoothing the target driving data to obtain first target driving data. The target driving data is smoothed to remove noise data, and first target driving data is obtained, and the first target driving data is used for obtaining more accurate driving style information of the first driver. And thirdly, screening the first target driving data to generate the screened first target driving data as driving characteristic data. The first target driving data are screened to obtain more accurate driving characteristic data, and the driving characteristic data are used for obtaining more accurate driving style information of the first driver. Next, the dimension reduction is performed on the driving characteristic data to obtain first driving characteristic data. Here, the obtained first driving characteristic data removes redundant information between the driving characteristic data, reducing the load of the target vehicle. And then, carrying out cluster analysis on the driving characteristic data to obtain various driving style information. The obtained plurality of types of driving style information are used for subsequent determination of the driving style information for the first driver. And finally, performing statistical analysis on the number of drivers corresponding to each driving style information in the multiple driving style information to obtain a driver number set corresponding to each driving style. And determining the driving style information corresponding to the largest number of drivers in the driver data set as the driving style information of the first driver. Here, it is advantageous to recognize the intention of the first driver to change lanes and to improve the safety of the traveling vehicle by determining the driving style information corresponding to the largest number of drivers as the driving style information of the first driver. Therefore, the determination of the driving style information of the vehicle person who does not drive the target vehicle is completed, and the driving safety of the driver in the driving process is improved.
And 104, recognizing lane change intention information of the target driver according to the environment information, the interaction information and the driving style information.
In some embodiments, the execution body may recognize lane change intention information of the target driver based on the environment information, the interaction information, and the driving style information. The lane change intention information may be information indicating whether the target driver intends to change lanes.
As an example, the execution subject may first acquire the interaction information of the target driver through the target vehicle CAN bus. Next, environmental information and the driving style information are acquired by an equipment sensor mounted on the subject vehicle. The equipment sensor may include at least one of: acceleration sensor, velocity sensor, infrared sensor, laser rangefinder sensor, ultrasonic sensor and camera. Then, the relevant operation characteristic parameters are extracted from the mutual information, the relevant driving characteristic parameters are extracted from the driving style information, and the relevant traffic characteristic parameters are extracted from the environment information. Wherein the operating characteristic parameters include, but are not limited to: the haptic information includes steering wheel angle, steering wheel angular acceleration, steering wheel rest time, brake pedal position, accelerator pedal position, clutch pedal position, and transmission gear position. The driving characteristic parameters include, but are not limited to: the vehicle speed, position, acceleration, yaw rate, speed, distance, and acceleration of the vehicle with respect to the surrounding vehicles in the target vehicle travel information. The traffic environment characteristic parameters include, but are not limited to: the surrounding vehicle speed, position, acceleration, road curvature, road width, traffic sign, road sign, and traffic light state in the traffic environment information. And finally, classifying the operation characteristic parameters, the driving characteristic parameters and the traffic characteristic parameters in a preset classifier, and identifying the lane change intention information of the target driver corresponding to the relevant characteristics according to the classification result in the classifier. The establishing of the preset classifier specifically comprises the following steps: the method comprises the steps of collecting driving training information including interaction information, driving style information and environment information within preset time. Extracting training characteristic parameters from the driving training information, wherein the training characteristic parameters include operation characteristic parameters corresponding to interactive information, driving characteristic parameters corresponding to driving style information and traffic characteristic parameters corresponding to environment information, and the training characteristic parameters include but are not limited to: vehicle speed, vehicle acceleration, steering wheel angle, lateral distance from lane center line, yaw rate, and brake pedal force. Labeling labels of different training characteristic parameters to mark lane change intention information of corresponding target drivers. And learning and training the training operation characteristics under different labels based on a preset classification algorithm to form a preset classifier.
In some optional implementations of some embodiments, the recognizing lane change intention information of the target driver according to the environment information, the interaction information, and the driving style information may include:
in response to determining that the interactive information is null information, inputting the environmental information and the driving style information to a lane change intention recognition model to generate lane change intention information. The lane change intention recognition model may be a neural network model that recognizes whether the driver changes lanes. The neural network model may be a Bi-LSTM (Bi-directional Long Short Term Memory neural network). The above-mentioned lane change intention information may be information representing whether the target driver intends to change lanes. The lane change intention information may include: a lane change intent type and a sequence of probability values corresponding to the lane change intent type. The lane change intention recognition model is obtained by training the following steps:
and a substep 1, obtaining a sample set, wherein the samples in the sample set comprise sample characteristic sequence data and sample transformation lane intention types and probability values corresponding to the sample characteristic sequence data. The sample feature sequence data may include, but is not limited to: the driving style information of the driver is obtained by the following steps of driving the target vehicle to the surrounding vehicle, the headway distance of the target vehicle to the surrounding vehicle, the time of collision of the target vehicle to the surrounding vehicle, the longitudinal speed of the target vehicle, the lateral speed of the target vehicle, the longitudinal acceleration of the target vehicle, the lateral acceleration of the target vehicle, the forward looking distance of the target vehicle to the surrounding vehicle, the backward looking distance of the target vehicle to the surrounding vehicle, and the driving style information of the driver. The lane change intent types may include, but are not limited to: a lane left change intention, a lane right change intention, a lane keeping intention.
Substep 2, performing the following training steps based on the sample set:
the first substep is that sample feature sequence data of at least one sample in the sample set are respectively input into an initial lane change intention recognition model, and a lane change intention type and a probability value corresponding to each sample in the at least one sample are obtained. The initial lane change intention recognition model may be an initial neural network model that takes the feature sequence data as input and takes the lane change intention type and the probability value as output. The initial neural network may be a neural network to be trained.
And a second substep of comparing the corresponding intention type and probability value of the lane change corresponding to each sample in the at least one sample with the corresponding intention type and probability value of the lane change corresponding to the sample. Here, first, whether the lane change intention type corresponding to each of the above-described at least one sample and the corresponding sample lane change intention type are the same lane change intention type is compared. Then, in the case that the lane change intention types are the same, the comparison may be a comparison of a probability value of the lane change intention type corresponding to each of the at least one sample with a magnitude of the probability value of the corresponding sample lane change intention type.
And a third substep of determining whether the initial lane change intention recognition model reaches a preset optimization target according to the comparison result. Here, the optimization target may be whether the loss function value of the initial lane change intention recognition model reaches a preset loss threshold value when the predicted lane change intention types are the same. Here, the above-mentioned loss function value may be a cross-entropy loss function value. The preset loss threshold may be 0.1.
A fourth substep of determining the initial lane change intention recognition model as a trained lane change intention recognition model in response to determining that the initial lane change intention recognition model achieves the optimization objective.
Optionally, the method may further include the steps of:
and in response to determining that the initial lane change intention recognition model does not reach the optimization target, adjusting relevant parameters of the initial lane change intention recognition model, re-selecting samples from the sample set, taking the adjusted initial lane change intention recognition model as a lane change intention recognition model, and executing the training step again.
As an example, a Back propagation Algorithm (BP Algorithm) and a gradient descent method (e.g., a small batch gradient descent Algorithm) may be used to adjust the network parameters of the initial log fault information prediction model.
And 105, generating vehicle control information according to the lane change intention information and the environment information.
In some embodiments, the execution subject may generate the vehicle manipulation information according to the lane change intention information and the environment information. The vehicle operation information may be command information for controlling the target vehicle to change lanes.
As an example, the executing body may first determine whether the lane change intention information of the target driver is to make a lane change. Next, in response to determining that the lane change intention information is to make a lane change, ambient environment information is acquired by a sensor mounted on the target vehicle. Wherein the ambient environment information includes: speed, acceleration, relative distance to surrounding vehicles of the target vehicle. And then, determining the relationship between the surrounding environment information and the lane change decision of the target vehicle by using the kinematic relationship in the typical free lane change scene. And finally, constructing a vehicle lane change decision model by using the Bayesian network to obtain vehicle control information.
In some optional implementations of some embodiments, the generating the vehicle handling information according to the lane change intention information and the environment information may include:
in a first step, a revenue matrix of the target vehicle and the vehicles in the target lane is constructed. Wherein the revenue matrix may be expressed as:
the revenue matrix is generated by the target vehicle and the vehicles in the target vehicle when different strategies are selected. The gain function is composed of the impact degree, the safe distance gain and the safe vehicle speed gain. The target vehicle selection lane changing strategy, the target vehicle selection lane keeping strategy, the vehicle selection lane changing acceptance strategy in the target lane and the vehicle selection lane changing non-acceptance strategy in the target lane form four strategy combinations.The revenue function for the vehicle in the target lane is expressed as a selection of the vehicle in the target lane to receive a lane change strategy and a selection of the lane change strategy by the target vehicle.The revenue function of the vehicle in the target lane is expressed as a received lane change policy for the vehicle in the target lane and a selected lane keeping policy for the target vehicle.Expressed as a revenue function of the vehicle in the target lane not receiving the lane change policy and the target vehicle selecting the lane change policy.Expressed as a revenue function of the vehicle in the target lane not receiving the lane change policy and the target vehicle selecting the lane keeping policy.Receiving a lane change policy for selection of a vehicle in the target lane and selecting a lane change policy for the target vehicle are shown to be a revenue function for the target vehicle.The receive lane change strategy and the target vehicle select lane keeping strategy expressed as vehicles in the target lane are revenue functions of the target vehicle.Expressed as a revenue function for the target vehicle within the target lane without receiving a lane change policy and the target vehicle selecting a lane change policy.Expressed as a revenue function for the target vehicle in the target lane not receiving the lane change policy and the target vehicle selecting the lane keeping policy.
And secondly, determining the impact degree of the target vehicle according to the running speed of the target vehicle. Wherein the impact represents an identification coefficient of the driving style information. The above-mentioned impact degree can be expressed as:
wherein, the first and the second end of the pipe are connected with each other,is shown asStandard deviation of (d).Expressed as the average value of the driver's impact at the current operating conditions. The average value of the impact degree under the crowded working condition is. The average value of the impact degree under the urban working condition is. The average value of the impact degree under suburb working conditions is. The average value of the impact under the high-speed working condition is. Wherein the content of the first and second substances,
wherein the content of the first and second substances,expressed as the rate of change of the acceleration of the target vehicle.Indicated as target vehicle atThe running speed at the time.
As an example, the execution subject described above may first acquire the travel speed of the target vehicle within a preset time by a sensor of the target vehicle. And then, determining the standard deviation of the impact degree of the target vehicle within the preset time according to the running speed of the target vehicle. And finally, determining the impact degree according to the standard deviation of the impact degree. Wherein the threshold value of the degree of impact of the driver of the stable driving style information is 0.5. The threshold value of the degree of impact of the driver of the aggressive driving style information is 1. And if the impact degree is smaller than the impact degree threshold value corresponding to the driver with stable driving style information, determining that the driving style information of the driver corresponding to the impact degree is conservative. And if the impact degree is greater than the impact degree threshold value corresponding to the driver of the aggressive driving style information, determining that the driving style information of the driver corresponding to the impact degree is aggressive. And if the impact degree is greater than the impact degree threshold corresponding to the driver with the stable driving style information and is less than the impact degree threshold corresponding to the driver with the aggressive driving style information, determining that the driving style information of the driver corresponding to the impact degree is conservative.
And thirdly, determining the safe distance benefit of the target vehicle according to the running distance between the target vehicle and the surrounding vehicles. The driving distance represents the safe distance between the target vehicle and the vehicle on the target lane in the process of changing lanes of the target vehicle. Wherein the safe distance gain may be expressed as:
wherein the content of the first and second substances,expressed as the distance between the target vehicle and the vehicle within the target lane.Represented as the speed of the vehicle in the target lane.Expressed as the speed of the target vehicle.Expressed as the time at which the target vehicle changes lanes.Expressed as the longitudinal acceleration of the vehicle in the target lane.Expressed as the longitudinal acceleration of the target vehicle.Is the heading angle of the target vehicle.Expressed as the length of the target vehicle.Indicated as the width of the target vehicle.
As an example, the executing body described above may first acquire the speed of the target vehicle, the longitudinal acceleration of the target vehicle, the time to lane change, the speed of the vehicle in the target lane, the longitudinal acceleration of the vehicle in the target lane, by communicating with V2X (vehicle to accelerating) through the sensor of the target vehicle. Then, the length and width of the target vehicle are acquired. Finally, a safe distance is determined between the target vehicle and the vehicle in the target lane when changing lanes.
And fourthly, determining the safe vehicle speed benefit of the target vehicle according to the speed relation between the target vehicle and the surrounding vehicles. And the speed relation represents the speed relation between the target vehicle and the vehicle on the target lane in the lane changing process. Wherein the above-mentioned safe vehicle speed yield may be expressed as
Wherein the content of the first and second substances,expressed as the speed of the vehicle in the target lane.Expressed as the speed of a vehicle in the same lane as the target vehicle.Expressed as the speed of the target vehicle.
And fifthly, determining a profit function of the target vehicle according to the safe distance profit, the safe speed profit and the impact degree. Wherein the revenue function of the target vehicle may be expressed as:
wherein the content of the first and second substances,expressed as the degree of impact of the target vehicle.Expressed as the degree of impact of the vehicle in the target lane.Expressed as a safe distance gain.Expressed as a safe vehicle speed benefit.、The weight coefficient is used because drivers corresponding to different driving style information have different requirements on safety benefits and speed benefits.、The value range of (0,1).
And sixthly, performing hybrid Nash equilibrium solving of the non-cooperative game under complete information on the income matrix to obtain vehicle control information. Wherein the revenue matrix may be expressed as:
wherein the content of the first and second substances,represented as the probability of receiving a lane change strategy for selection of a vehicle in the target lane.Expressed as the probability that the selection of a vehicle within the target lane does not receive a lane change strategy.Representing the probability of selecting a lane change strategy for the target vehicle.Expressed as the probability of selecting a lane-keeping strategy for the target vehicle.The revenue function for the vehicle in the target lane is expressed as a selection of the vehicle in the target lane to receive a lane change strategy and a selection of the lane change strategy by the target vehicle.Receiving change lane policy expressed as vehicles in target laneThe target vehicle selects a revenue function for vehicles in the target lane of the lane keeping strategy.Expressed as a revenue function for the vehicle in the target lane not receiving the change lane strategy and the target vehicle selecting the change lane strategy.Expressed as a revenue function of the vehicle in the target lane not receiving the lane change policy and the target vehicle selecting the lane keeping policy.Receiving a lane change policy for selection of a vehicle in the target lane and selecting a lane change policy for the target vehicle are shown to be a revenue function for the target vehicle.The receive lane change strategy and the target vehicle select lane keeping strategy expressed as vehicles in the target lane are revenue functions of the target vehicle.Expressed as a revenue function for the target vehicle within the target lane without receiving a lane change policy and the target vehicle selecting a lane change policy.Expressed as a revenue function for the target vehicle in the target lane not receiving the lane change policy and the target vehicle selecting the lane keeping policy. According to the characteristics of the lane changing game of the vehicles in the intelligent internet traffic environment and the basic elements of the game theory, the lane changing strategy is determined to be a non-cooperative game based on complete information. In the lane changing game process of the vehicle, when the lane changing intention information of the target vehicle is the lane changing intention, the target driver determines the safety of the surrounding traffic environment and then operates the vehicle to change the lane, and at the moment, the vehicle in the target laneThe driver of the vehicle may choose to accelerate, decelerate, or move at a constant speed to treat the driving behavior of the target vehicle, so the nash balance studied by the invention is a hybrid nash balance in a non-cooperative game under limited complete information. So that at least one nash equalization exists.
As an example, the executing agent may solve the revenue matrix by using a hybrid nash balance of a non-cooperative game under complete information to obtain the vehicle operation information.
The above technical solution and its related contents are an inventive point of the embodiments of the present disclosure, and solve the technical problem mentioned in the background art that "when a vehicle changes lanes, the influence of the communication with surrounding vehicles and the driving style on lane changing is not considered, which results in the reduction of the lane changing safety and the missing of the time for lane changing. ". Factors that cause lane changes to be a low safety of the vehicle and miss the timing of lane changes are often as follows: the influence of the communication of the vehicle with surrounding vehicles and the driving style on lane changing is not considered when the vehicle makes a lane change. If the above factors are solved, the improvement of the safety of the vehicle can be achieved. To achieve this effect, the generating of the vehicle maneuver information according to the lane change intention information and the environment information may include: first, a revenue matrix is constructed for the target vehicle and the vehicles within the target lane. In the process of constructing the income matrix, the driving style of a driver and communication between vehicles are considered, and the vehicle operation and control information which is more suitable for the vehicles is constructed. Next, the impact degree of the target vehicle is determined from the traveling speed of the target vehicle. The impact degree can have different values according to different driving style information of the driver, and the driving style information of the driver is fully considered, so that the vehicle can obtain more accurate control information. And thirdly, determining the safe distance benefit of the target vehicle according to the running distance between the target vehicle and the surrounding vehicles. Then, a safe vehicle speed benefit of the target vehicle is determined from a speed relationship between the target vehicle and surrounding vehicles. And determining a lane change profit function of the target vehicle according to the safe distance profit, the safe speed profit and the impact degree. And finally, performing mixed Nash equilibrium solving of the non-cooperative game under complete information on the income matrix to obtain vehicle control information. Therefore, the technical scheme can obtain information such as vehicle running states and road traffic conditions, and uncertainty of game benefits in the lane changing game process is reduced. In the non-cooperative game under complete information, the vehicles can acquire information such as running characteristics, strategy sets and revenue functions of surrounding vehicles in real time, and the decision strategies of the surrounding vehicles are acquired through communication between the vehicles, so that the decision strategies according with self conditions are selected. The method is favorable for improving the driving safety of the vehicle and accurately grasping the time for changing lanes of the vehicle.
And step 106, responding to the fact that the interactive information is not empty information, and determining whether the vehicle operation information and the interactive information have driving conflict or not.
In some embodiments, the execution subject may determine whether there is a driving conflict between the vehicle manipulation information and the interactive information in response to determining that the interactive information is not null information. And the interactive information is not empty information and represents that a target driver performs corresponding operation on the target vehicle. For example, the above-mentioned mutual information may be that the control target vehicle changes lanes to the left. For example, when the target driver's mutual information with respect to the target vehicle is to change lanes to the left, however, the vehicle manipulation information determined by the target vehicle based on the surrounding environment information is to change lanes to the right, there is a driving conflict between the vehicle manipulation information and the mutual information.
And step 107, in response to determining that the driving conflict does not exist, controlling the vehicle-mounted system to perform lane changing processing on the target vehicle according to the vehicle control information.
In some embodiments, the executing body may control an in-vehicle system to perform lane change processing on the target vehicle according to the vehicle manipulation information in response to a determination that there is no driving conflict. The vehicle-mounted system may be a terminal system of a control target vehicle.
As an example, the execution subject may transmit the vehicle manipulation information to the in-vehicle system. And the vehicle-mounted system receives the instruction information and controls the vehicle to change lanes.
In some optional implementations of some embodiments, the method may further include:
the execution subject may control an in-vehicle system to perform lane change processing on the target vehicle according to the interaction information in response to determining that the driving conflict exists.
As an example, the executing body may respond to a determination that the interaction information sent by the target driver conflicts with the vehicle manipulation information, i.e., the target driver has an intention to change lanes to the right, whereas the vehicle manipulation information is to change lanes to the left. And sending the interactive information to a vehicle-mounted system of the target vehicle to control the target vehicle to carry out lane changing processing.
The above embodiments of the present disclosure have the following beneficial effects: the vehicle control method of some embodiments of the present disclosure takes into account the influence of the driving style and lane change intention of the driver on the lane change strategy to improve the driving safety and driving experience of the driver. Specifically, the reason why the driving safety and the driving experience of the driver concerned are low is that: when the vehicle changes lanes, only the factors of the lane changing vehicle are considered, and the lane changing decision is not accurate due to the single data source. Based on this, the vehicle control method of some embodiments of the present disclosure may first control the vehicle-mounted sensor to acquire environmental information and interaction information of a target vehicle, where the interaction information may be operation instruction information of a driver on the target vehicle. The environmental information and the interaction information acquired by the vehicle-mounted sensor facilitate the determination of subsequent driving style information and vehicle control information. And secondly, identifying the driver information of the target vehicle, wherein the identification of the driver information is used for subsequently determining the identity of the driver of the target vehicle and determining the driving style of the driver. And thirdly, in response to the fact that the driver corresponding to the driver information is determined to be the target driver, determining the driving style information of the target driver. Here, the driving style of the target driver is determined for subsequent determination of the vehicle handling information. Next, lane change intention information of the target driver is recognized based on the environment information, the interaction information, and the driving style information. Here, the resulting lane change intention information is used for the subsequent determination of the vehicle handling information. And then, generating vehicle control information according to the lane change intention information and the environment information. The resulting control information is used to control the safe lane change of the vehicle. Then, in response to determining that the interactive information is not null information, it is determined whether there is a driving conflict between the vehicle operation information and the interactive information. Herein, whether the conflict exists between the vehicle operation information and the interactive information is checked, and the driving experience and the driving safety of a driver driving the vehicle are improved. And finally, in response to determining that no driving conflict exists, controlling an on-board system to perform lane changing processing on the target vehicle according to the vehicle control information. Therefore, the vehicle control method can take the influence of the driving style and the lane changing intention of the driver on the lane changing strategy into consideration, so that the driving safety and the driving experience of the driver are improved.
With further reference to fig. 2, as an implementation of the methods illustrated in the above figures, the present disclosure provides some embodiments of a vehicle control apparatus, which correspond to those illustrated in fig. 1, and which may be particularly applicable in various electronic devices.
As shown in fig. 2, a vehicle control apparatus 200 includes: a first control unit 201, a first recognition unit 202, a first determination unit 203, a second recognition unit 204, a generation unit 205, a second determination unit 206, and a second control unit 207. Wherein the first control unit 201 is configured to: and controlling the vehicle-mounted sensor to acquire environmental information and interactive information of the target vehicle, wherein the interactive information can be operation instruction information of a driver on the target vehicle. The first identification unit 202 is configured to: and identifying the driver information of the target vehicle. The first determination unit 203 is configured to: and determining the driving style information of the target driver in response to determining that the driver corresponding to the driver information is the target driver. The second identification unit 204 is configured to: and recognizing the lane change intention information of the target driver according to the environment information, the interaction information and the driving style information. The generation unit 205 is configured to: and generating vehicle control information according to the lane change intention information and the environment information. The second determination unit 206 is configured to: and in response to determining that the interactive information is not null information, determining whether a driving conflict exists between the vehicle operation information and the interactive information. The second control unit 207 is configured to: and in response to determining that no driving conflict exists, controlling an on-board system to perform lane change processing on the target vehicle according to the vehicle control information.
It is to be understood that the units recited in the vehicle control device 200 correspond to the respective steps in the method described with reference to fig. 1. Thus, the operations, features and resulting benefits described above with respect to the method are equally applicable to the vehicle control device 200 and the units included therein, and are not described in detail herein.
Referring now to fig. 3, a block diagram of an electronic device (e.g., electronic device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, or the like; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 3 may represent one device or may represent multiple devices, as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. The computer program, when executed by the processing apparatus 301, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described above in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (Hyper Text Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: controlling a vehicle-mounted sensor to acquire environmental information and interactive information of a target vehicle, wherein the interactive information can be operation instruction information of a driver on the target vehicle; identifying driver information of the target vehicle; in response to determining that the driver information corresponds to a driver being a target driver, determining driving style information of the target driver; recognizing lane change intention information of the target driver according to the environment information, the interaction information and the driving style information; generating vehicle control information according to the lane change intention information and the environment information; in response to determining that the interactive information is not null information, determining whether a driving conflict exists between the vehicle operation information and the interactive information; and in response to determining that no driving conflict exists, controlling an on-board system to perform lane change processing on the target vehicle according to the vehicle control information.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first control unit, a first recognition unit, a first determination unit, a second recognition unit, a generation unit, a second determination unit, and a second control unit. The names of these units do not in some cases constitute a limitation on the units themselves, and for example, the first control unit may also be described as a "unit that controls the in-vehicle sensors to acquire environmental information and interaction information of the target vehicle".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (8)
1. A vehicle control method comprising:
controlling a vehicle-mounted sensor to acquire environmental information and interactive information of a target vehicle, wherein the interactive information is operation instruction information of a driver on the target vehicle;
identifying driver information for the target vehicle;
in response to determining that the driver information corresponds to a driver being a target driver, determining driving style information of the target driver;
recognizing lane change intention information of the target driver according to the environment information, the interaction information and the driving style information;
generating vehicle control information according to the lane change intention information and the environment information;
in response to determining that the interactive information is not null information, determining whether there is a driving conflict between the vehicle handling information and the interactive information;
in response to determining that there is no driving conflict, controlling an in-vehicle system to perform lane change processing on the target vehicle according to the vehicle manipulation information.
2. The method of claim 1, wherein the method further comprises:
and in response to determining that the driving conflict exists, controlling an on-board system to perform lane change processing on the target vehicle according to the interactive information.
3. The method of claim 1, wherein the identifying lane change intention information of the target driver from the environmental information, interaction information, and driving style information comprises:
in response to determining that the interaction information is null information, inputting the environmental information and the driving style information to a lane change intention recognition model, and generating lane change intention information, wherein the lane change intention recognition model is trained by the following steps:
acquiring a sample set, wherein samples in the sample set comprise sample feature sequence data, and a sample change lane intention type and a probability value corresponding to the sample feature sequence data;
performing the following training steps based on the sample set:
respectively inputting sample feature sequence data of at least one sample in a sample set into an initial lane change intention recognition model to obtain a lane change intention type and a probability value corresponding to each sample in the at least one sample;
comparing the type of intention of changing lanes and the probability value corresponding to each sample in the at least one sample with the type of intention of changing lanes and the probability value corresponding to the sample;
determining whether the initial lane change intention recognition model reaches a preset optimization target or not according to the comparison result;
in response to determining that the initial lane change intent recognition model meets the optimization objective, determining the initial lane change intent recognition model as a trained lane change intent recognition model.
4. The method of claim 3, wherein the method further comprises:
and in response to determining that the initial lane change intention recognition model does not meet the optimization goal, adjusting relevant parameters of the initial lane change intention recognition model, reselecting samples from the sample set, taking the adjusted initial lane change intention recognition model as a lane change intention recognition model, and executing the training step again.
5. The method of claim 1, wherein the determining the driving style information of the target driver comprises:
controlling a driving simulator and an intelligent bracelet to respectively collect driving style characteristic data representing a driver;
carrying out data dimension reduction processing on the driving style characteristic data to obtain the driving style characteristic data subjected to dimension reduction as first driving style characteristic data;
and clustering the first driving style characteristic data to determine the driving style information of the first driver.
6. A vehicle control apparatus comprising:
the control system comprises a first control unit, a second control unit and a third control unit, wherein the first control unit is configured to control a vehicle-mounted sensor to acquire environmental information and interaction information of a target vehicle, and the interaction information is operation instruction information of a driver on the target vehicle;
a first recognition unit configured to recognize driver information of the target vehicle;
a first determination unit configured to determine driving style information of a target driver in response to determining that the driver information corresponds to the driver being the target driver;
a second recognition unit configured to recognize lane change intention information of the target driver according to the environment information, the interaction information, and the driving style information;
a generating unit configured to generate vehicle manipulation information according to the lane change intention information and the environment information;
a second determination unit configured to determine whether there is a driving conflict between the vehicle manipulation information and the mutual information in response to determining that the mutual information is not null information;
a second control unit configured to control an in-vehicle system to perform lane change processing on the target vehicle according to the vehicle manipulation information in response to a determination that there is no driving conflict.
7. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-5.
8. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211575828.0A CN115571165B (en) | 2022-12-09 | 2022-12-09 | Vehicle control method, device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211575828.0A CN115571165B (en) | 2022-12-09 | 2022-12-09 | Vehicle control method, device, electronic equipment and computer readable medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115571165A true CN115571165A (en) | 2023-01-06 |
CN115571165B CN115571165B (en) | 2023-03-31 |
Family
ID=84590043
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211575828.0A Active CN115571165B (en) | 2022-12-09 | 2022-12-09 | Vehicle control method, device, electronic equipment and computer readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115571165B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106043313A (en) * | 2016-07-28 | 2016-10-26 | 南昌大学 | Automobile driving lane-changing intelligent guiding device |
CN106681319A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Automatic lane-changing system and method |
CN113291324A (en) * | 2021-06-25 | 2021-08-24 | 的卢技术有限公司 | Intelligent automobile personalized lane change decision-making method, system and medium |
CN113722835A (en) * | 2021-09-14 | 2021-11-30 | 吉林大学 | Modeling method for anthropomorphic random lane change driving behavior |
US20220105961A1 (en) * | 2019-10-16 | 2022-04-07 | Tencent Technology (Shenzhen) Company Limited | Method for automatic control of vehicle and method for training lane change intention prediction network |
CN114566065A (en) * | 2022-03-04 | 2022-05-31 | 中智行(苏州)科技有限公司 | Multi-vehicle cooperative lane changing method based on vehicle-road cooperation |
-
2022
- 2022-12-09 CN CN202211575828.0A patent/CN115571165B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106043313A (en) * | 2016-07-28 | 2016-10-26 | 南昌大学 | Automobile driving lane-changing intelligent guiding device |
CN106681319A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Automatic lane-changing system and method |
US20220105961A1 (en) * | 2019-10-16 | 2022-04-07 | Tencent Technology (Shenzhen) Company Limited | Method for automatic control of vehicle and method for training lane change intention prediction network |
CN113291324A (en) * | 2021-06-25 | 2021-08-24 | 的卢技术有限公司 | Intelligent automobile personalized lane change decision-making method, system and medium |
CN113722835A (en) * | 2021-09-14 | 2021-11-30 | 吉林大学 | Modeling method for anthropomorphic random lane change driving behavior |
CN114566065A (en) * | 2022-03-04 | 2022-05-31 | 中智行(苏州)科技有限公司 | Multi-vehicle cooperative lane changing method based on vehicle-road cooperation |
Also Published As
Publication number | Publication date |
---|---|
CN115571165B (en) | 2023-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11899411B2 (en) | Hybrid reinforcement learning for autonomous driving | |
CN110796856B (en) | Vehicle lane change intention prediction method and training method of lane change intention prediction network | |
CN107491072B (en) | Vehicle obstacle avoidance method and device | |
CN109109863B (en) | Intelligent device and control method and device thereof | |
CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
US11364899B2 (en) | Driving assistance method and system | |
CN113366497A (en) | Agent prioritization for autonomous vehicles | |
CN113261035A (en) | Trajectory prediction method and related equipment | |
Jia et al. | Long short‐term memory and convolutional neural network for abnormal driving behaviour recognition | |
CN113439247A (en) | Agent prioritization for autonomous vehicles | |
US20220242448A1 (en) | Method, apparatus and device for determining behavioral driving habit and controlling vehicle driving | |
US20200391738A1 (en) | Autonomous vehicle interactive decision making | |
EP4316935A1 (en) | Method and apparatus for obtaining lane change area | |
CN115578876A (en) | Automatic driving method, system, equipment and storage medium of vehicle | |
Cui et al. | Receive, reason, and react: Drive as you say with large language models in autonomous vehicles | |
CN114932918A (en) | Behavior decision method and system for intelligent internet vehicle to drive under various road conditions | |
CN111830962A (en) | Interpretation data for reinforcement learning agent controller | |
Sharma et al. | Highway lane-changing prediction using a hierarchical software architecture based on support vector machine and continuous hidden markov model | |
CN116653957A (en) | Speed changing and lane changing method, device, equipment and storage medium | |
CN115571165B (en) | Vehicle control method, device, electronic equipment and computer readable medium | |
CN115083175B (en) | Signal management and control method based on vehicle-road cooperation, related device and program product | |
CN113968242A (en) | Automatic driving scene generation method, device and system | |
CN114926823B (en) | WGCN-based vehicle driving behavior prediction method | |
CN116461507A (en) | Vehicle driving decision method, device, equipment and storage medium | |
US11794780B2 (en) | Reward function for vehicles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |