CN110789522B - Lane keeping assist control method, device, system, vehicle and storage medium - Google Patents
Lane keeping assist control method, device, system, vehicle and storage medium Download PDFInfo
- Publication number
- CN110789522B CN110789522B CN201910875691.2A CN201910875691A CN110789522B CN 110789522 B CN110789522 B CN 110789522B CN 201910875691 A CN201910875691 A CN 201910875691A CN 110789522 B CN110789522 B CN 110789522B
- Authority
- CN
- China
- Prior art keywords
- steering
- lane
- behavior
- steering wheel
- information
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims description 30
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 100
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000007476 Maximum Likelihood Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 5
- 101100382321 Caenorhabditis elegans cal-1 gene Proteins 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013139 quantization Methods 0.000 description 3
- 230000028838 turning behavior Effects 0.000 description 3
- 101100096319 Drosophila melanogaster Spc25 gene Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013179 statistical model Methods 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
- B60W2050/0052—Filtering, filters
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention discloses a lane keeping auxiliary control method, which comprises the following steps: acquiring lane environment information and steering wheel information detected by a sensor in real time; identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time; judging the steering preference of the driver according to the recognition result of the steering behavior category within the preset time length; determining lane keeping control parameters of the vehicle according to the steering preference and the lane environment information; and controlling the vehicle to automatically keep the lane according to the lane keeping control parameter. The invention also discloses a lane keeping auxiliary control device, a lane keeping auxiliary control system, a vehicle and a storage medium. The invention has the advantages of ensuring the active safety performance and the comfort performance of vehicle movement, particularly transverse movement.
Description
Technical Field
The invention relates to the field of intelligent driving, in particular to a lane keeping auxiliary control method, a lane keeping auxiliary control device, a lane keeping auxiliary control system, a vehicle and a storage medium.
Background
The current vehicle technology is undergoing a deep revolution of intellectualization, and learning and effective identification of driver characteristics are indispensable in the process of transition from intelligent assisted driving to unmanned driving. As an important driver characteristic, driver steering behavior directly affects vehicle lateral motion, so effective monitoring and accurate identification of driver steering behavior is beneficial for improving vehicle lateral active safety performance. The accurately identified steering behavior characteristics of the driver are applied to the auxiliary driving system, so that the use experience of the user can be further improved. However, in the prior art, it is difficult to ensure the accuracy of behavior recognition, and it is difficult to achieve consistency between the driving process when the lane keeping function is activated and the autonomous driving of the driver because the driver's steering behavior is not deeply identified.
Disclosure of Invention
In a first aspect, the present invention discloses a lane keeping assist control method including:
acquiring lane environment information and steering wheel information detected by a sensor in real time;
identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time;
judging the steering preference of the driver according to the recognition result of the steering behavior category within the preset time length;
determining lane keeping control parameters of the vehicle according to the steering preference and the lane environment information;
and controlling the vehicle to automatically keep the lane according to the lane keeping control parameter.
Further, the identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time includes:
obtaining steering behavior data of the driver off line;
taking the steering behavior data acquired offline as an original training set, and correspondingly dividing the original training set into a plurality of behavior training sets according to the steering behavior category;
self-learning is carried out on each behavior training set through a self-learning model to obtain a behavior self-learning library; the behavior self-learning library comprises steering characteristic vectors corresponding to the behavior training sets;
and comparing and judging the steering wheel information acquired in real time with the behavior self-learning library, and identifying to obtain the current steering behavior category of the driver.
Further, the steering behavior category is divided according to steering wheel angle data, steering wheel rotating speed data and steering wheel torque data in the steering behavior data.
Further, the steering wheel information acquired in real time is compared and judged with the self-learning library through an estimation method, so that the steering behavior category with the highest probability is used as the recognition result of the current steering behavior of the driver.
Further, the determining the steering preference of the driver according to the recognition result of the steering behavior category within the preset time period includes:
counting the proportion of each steering category according to the recognition result in a preset time length;
and judging the steering preference of the driver according to the proportion of each steering category.
Further, the identification result of the steering behavior category within a preset time length is dynamically stored through a steering behavior time window.
Further, the lane keeping assist control method further includes:
and carrying out preprocessing of abnormal value elimination, filtering and rotation speed signal calculation on the lane environment information and the steering wheel information.
In a second aspect, the present invention also discloses a lane keeping assist control apparatus including:
the data acquisition unit is used for acquiring lane environment information and steering wheel information detected by the sensor in real time;
the category identification unit is used for identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time;
the preference judging unit is used for judging the steering preference of the driver according to the recognition result of the steering behavior category within the preset time length;
a control parameter determination unit for determining a lane keeping control parameter of the vehicle according to the steering preference and the lane environment information;
and the lane keeping control unit is used for controlling the vehicle to automatically keep a lane according to the lane keeping control parameters.
In a third aspect, the invention also discloses a lane keeping assist control system, which comprises the lane keeping assist control device,
the lane keeping auxiliary control system further comprises a sensing unit, wherein the sensing unit comprises a front camera, a corner sensor and a torque sensor;
the front camera is used for acquiring lane environment information, the corner sensor is used for acquiring steering wheel corner information, and the torque sensor is used for acquiring steering wheel torque information.
In a fourth aspect, the invention further discloses a vehicle, which comprises the lane keeping auxiliary control device or the lane keeping auxiliary control system.
In a fifth aspect, the present invention also discloses a computer storage medium having at least one instruction, at least one program, code set, or set of instructions stored therein, the at least one instruction, at least one program, code set, or set of instructions being loaded by a processor and executing the lane keeping assist control method as any one of the above.
In a sixth aspect, the present invention also discloses an apparatus comprising a processor and a memory, the memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by the processor to implement the lane keeping assist control method according to any one of the preceding claims.
By adopting the technical scheme, the invention has the following beneficial effects: the method can evaluate the driving behavior by using the quantization grade, judge the steering preference of the driver in real time, finish the self-adaptive control of the lane keeping function through the self-learning of the preference of the driver, keep the driving feeling of the auxiliary driving when the lane keeping function is activated consistent with the driving feeling of the driver when the driver drives autonomously, and further ensure the active safety performance and the comfortable performance of the vehicle movement, particularly the transverse movement.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a lane keeping assist control method according to an embodiment of the present invention;
fig. 2 is a method for identifying a category of a turning behavior according to an embodiment of the present invention;
FIG. 3 is a specific process for identifying a category of real-time steering behavior according to an embodiment of the present invention;
fig. 4 is a method for determining steering preference according to an embodiment of the present invention;
FIG. 5 is a process for steering preference determination according to an embodiment of the present invention;
FIG. 6 is a process of adaptive parameter adjustment according to an embodiment of the present invention;
fig. 7 is a diagram illustrating a lane keeping assist control apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a lane keeping assist control system according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic may be included in at least one implementation of the invention. In the description of the present invention, it is to be understood that the terms "upper", "lower", "top", "bottom", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Moreover, the terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
Example (b):
an embodiment of the present invention provides a lane keeping assist control method, which includes, as shown in fig. 1:
s100: and acquiring the lane environment information and the steering wheel information detected by the sensor in real time.
In some possible embodiments, the sensors may include a camera of the vehicle, a rotation angle sensor in the EPS system, and a torque sensor.
Specifically, the camera may be a front camera of the vehicle, the front camera may acquire lane environment information, and a sensor in the EPS system may acquire steering wheel information, and specifically, the steering wheel information may include steering wheel angle information and steering wheel torque information, and may further include steering wheel rotation speed information.
In some possible embodiments, the lane environment information and the steering wheel information may also be preprocessed. Specifically, the preprocessing may include preprocessing such as outlier rejection, filtering, and rotation speed signal calculation.
It can be understood that the interference of the abnormal value can be removed by removing the abnormal value from the lane environment information and the steering wheel information; filtering can remove burrs; and the rotating speed information can be obtained through the steering wheel angle signal difference, so that the steering angle information and the rotating speed information of the steering wheel can be obtained through the steering angle sensor.
S200: and identifying the current steering behavior type of the driver according to the steering wheel information acquired in real time.
In some possible embodiments, the steering wheel angle data, steering wheel speed data and steering wheel torque data in the steering behavior data may be used as characteristic parameters for describing the steering behavior of the driver, so as to classify the steering behavior of the driver.
It is understood that the steering behavior of the driver may be divided into a plurality of categories according to specific requirements, for example, the categories of the steering behavior may include aggressive steering behavior, sporty steering behavior, normal steering behavior, gentle steering behavior, and micro-steering behavior.
In some possible embodiments, as shown in fig. 2, the step S200 may include:
s210: and obtaining the steering behavior data of the driver off line.
Further, the steering behavior data acquired offline may be behavior data during the driver's historical driving.
S220: and taking the steering behavior data acquired offline as an original training set, and correspondingly dividing the original training set into a plurality of behavior training sets according to the steering behavior category.
It can be understood that, by using the steering behavior data acquired offline as the original training set and training the original training set, the threshold value between different steering behavior categories can be determined based on the driving habits of the driver, so that the lane in the embodiment of the invention is kept in accordance with the driving habits of the driver. The steering behavior data may be historical steering behavior data of the driver.
And if the steering behavior categories include aggressive steering behavior, sporty steering behavior, normal steering behavior, soft steering behavior, and micro steering behavior, the original training set may be divided into an aggressive steering training set, a sporty steering training set, a normal steering training set, a soft steering training set, and a micro steering training set.
S230: self-learning is carried out on each behavior training set through a self-learning model to obtain a behavior self-learning library; and the behavior self-learning library comprises steering characteristic vectors corresponding to the behavior training sets.
In some possible embodiments, the self-learning model may be a hidden markov model, by which a time series of unobservable state quantities may be identified by a time series of observables. In the embodiment of the invention, the time sequence of observable steering behavior signals (steering wheel angle, rotating speed and moment) of a driver can be used for identifying the time sequence of unobservable quantity (steering behavior) through a state transition matrix and a probability matrix by using a hidden Markov model, so that the subjective concept of quantitatively representing the steering behavior of the driver is realized. Therefore, the hidden Markov model is used for self-learning each behavior training set to obtain the characteristic vector lambda of each steering behavior category, and a self-learning library for identifying the real-time steering wheel information is formed.
It can be understood that, in the above process, the torque and the estimated value of the rotation angle can be used as identification parameters, and by a mode identification method of a hidden markov statistical model, the real-time identification of the steering behavior of the driver can be completed and a quantization index can be output.
S240: and comparing and judging the steering wheel information acquired in real time with the behavior self-learning library, and identifying to obtain the current steering behavior category of the driver.
In some possible embodiments, the steering wheel information acquired in real time may be compared and judged with the self-learning library through an estimation method, so that the steering behavior category with the highest probability is used as the recognition result of the current steering behavior of the driver.
Furthermore, the steering wheel information and the self-learning library can be compared and judged through a maximum likelihood estimation method, and the steering behavior category with the maximum likelihood probability is used as the recognition result of the current steering behavior of the driver.
It can be understood that the likelihood probability of the input sequence generated by each steering behavior self-learning library can be compared through a maximum likelihood estimation method, which is different from the fact that in the prior art, the single likelihood is compared with a threshold value to obtain the corresponding steering category, the maximum likelihood estimation method does not need to preset a fixed threshold value, but transmits the real-time sequence to each feature learning library to judge which state the current sequence belongs to, so that the probability is higher, and the matching and calibration work for determining the threshold value can be reduced.
As shown in fig. 3, a specific process of identifying a category of real-time steering behavior is presented. The data acquisition unit transmits data to an offline data set and a real-time data sequence, the offline data set is used as an original training set, and feature extraction is carried out on the original training set to carry out behavior category classification on steering behavior data in the original training set so as to obtain a corresponding behavior training set; and self-learning the behavior training set through a hidden Markov model to obtain a behavior self-learning library. And transmitting the real-time data sequence to a behavior self-learning library, and acquiring and outputting a steering behavior identification result by a maximum likelihood estimation method. The behavior recognition result is applied to the lane keeping and other transverse driving auxiliary functions, so that the driving feeling of the auxiliary driving is consistent with the feeling of the driver when the driver drives actively, and the use experience of the user is improved.
S300: and judging the steering preference of the driver according to the recognition result of the steering behavior category within the preset time length.
In some possible embodiments, as shown in fig. 4, the step S300 may include:
s310: and counting the proportion of each steering category according to the recognition result in the preset time length.
S320: and judging the steering preference of the driver according to the proportion of each steering category.
It will be appreciated that steering preference may be understood as a driver's preference for the style of steering wheel operation while steering. For example, under the same working condition, some drivers feel aggressive in steering the steering wheel, and some drivers feel conservative in steering the steering wheel.
In some possible implementations, the steering preferences of the driver may be divided into a classification of the steering preferences as sporty, robust, and conservative. Accordingly, each type of steering preference corresponds to a different behavior proportion threshold. And comparing the actual proportion with the proportion threshold value to obtain and output the current steering preference judgment result.
Wherein, the action proportion can be understood as: the proportion of different steering actions within the time window. For example, N steering actions are totally included in the time window, and the number of occurrences corresponding to the five steering actions is N1,n2,n3,n4And n5That respective steering behavior ratio is n1/N,n2/N,n3/N,n4N and N5and/N. The behavior proportion threshold value can be understood as a preset proportion threshold value.
Further, the steering preference of the driver can be judged according to the proportion of a single steering category, the steering preference of the driver can also be judged by overlapping the proportions of a plurality of steering categories, and the steering preference of the driver can also be judged by combining the proportions of the plurality of steering categories and the proportion of the single steering category.
In some possible embodiments, the recognition result of the category of the turning behavior within a preset time period may be dynamically stored through a turning behavior time window. When the steering preference is determined, the identification result of the steering behavior category stored in the time window can be read dynamically.
Specifically, the length of the time window may be Tpref sec.
As shown in fig. 5, a process of steering preference determination provided by the present invention is provided. The method reads the recognition result in the preset time length from the time window, and counts the proportion of the recognition result of each steering category. For example, the occurrence ratios of aggressive steering behavior, sportive steering behavior, normal steering behavior, gentle steering behavior, and micro-steering behavior are λ1、λ2、λ3、λ4And λ5. In the process of making the steering preference determination, the determination may be made according to the proportion of occurrence of each steering behavior.
Specifically, the division of the steering preference of the driver into a sporty type, a robust type, and a conservative type is taken as an example;
the ratio lambda which can occur by aggressive steering behavior1And the proportion lambda at which the sporty steering behavior occurs2Judging whether the driver belongs to the sport steering preference:
if λ1And λ2The sum is greater than a first threshold lambdath1If yes, determining that the driver is the sport steering preference;
if not, the lambda is judged2Whether or not it is greater than a second threshold value lambdath2If yes, judging that the driver is a sports steering preference;
if said lambda is2Is not greater than a second threshold lambdath2Then the ratio lambda appearing by the gentle steering behavior4And the proportion lambda at which micro-steering behavior occurs5Judging whether the driver belongs to conservative steering preference:
if λ4And λ5The sum is greater than a third threshold lambdath3If so, judging that the driver is conservative steering preference;
if λ4And λ5The sum of which is not greater than the third threshold value lambdath3Then the ratio lambda appearing through normal steering behavior2And the proportion lambda at which the sporty steering behavior occurs3Judging whether the driver belongs to a steady steering preference or a conservative steering preference;
if λ2And λ3The sum is greater than a third threshold lambdath4Then, determine λ3Whether or not it is greater than lambdath5；
If λ3Greater than λth5If so, determining that the driver is in a steady steering preference;
if λ3Is not more than lambdath5If so, judging that the driver is conservative steering preference;
and, if λ2And λ3The sum of which is not greater than the third threshold value lambdath4And judging the driver to be conservative steering preference.
S400: and determining lane keeping control parameters of the vehicle according to the steering preference and the lane environment information.
In some possible embodiments, a parameter adaptive strategy can be preset in the interior, and a control parameter sequence corresponding to the current steering preference can be acquired during control.
Further, a parameter adaptive strategy is preset internally, which may be a driving parameter set according to the driver's historical driving habits.
In addition, the self-adaptive reference module obtains the control parameter sequence according to different steering preferences of the driver, so that lane keeping control capable of self-adapting to the steering preferences of the driver is realized, and subjective feelings of intelligent auxiliary driving and autonomous driving of the driver are more consistent.
As shown in fig. 6, a process of adaptive parameter adjustment is presented. Which determines the corresponding control parameter sequence output by reading the driver's steering preference.
Among them, the diagram is { Cal1, Cal 2.. Caln }Exercise of sports，{Cal1,Cal2,...Caln}Conservative，{Cal1,Cal2,...Caln}RobustThe n calibration quantities contained in the control strategy are illustrated for the three steering preferences, { Cal1, Cal 2.. Caln }, respectively.
In some possible embodiments, the control parameter sequence may be obtained by a table lookup.
S500: and controlling the vehicle to automatically keep the lane according to the lane keeping control parameter.
The embodiment of the invention can identify the behavior characteristics of the driver and control the vehicle based on the driving characteristic self-learning of the driver. Specifically, the lane keeping auxiliary control method can evaluate driving behaviors by using quantization levels, judge the steering preference of a driver in real time, complete self-adaptive control of the lane keeping function by self-learning of the preference of the driver, enable the output of the active steering torque to be consistent with that of the driver during autonomous driving when the lane keeping function is activated, and further guarantee the active safety performance and the comfort performance of the lateral movement of the vehicle.
Accordingly, an embodiment of the present invention further provides a lane keeping assist control device, as shown in fig. 7, including:
the data acquisition unit 101 is used for acquiring lane environment information and steering wheel information detected by the sensor in real time;
the category identification unit 102 is configured to identify a current steering behavior category of the driver according to the steering wheel information acquired in real time;
a preference determination unit 103, configured to determine steering preference of the driver according to a recognition result of the category of the steering behavior within a preset time period;
a control parameter determination unit 104 for determining a lane keeping control parameter of the vehicle according to the steering preference and the lane environment information;
a lane keeping control unit 105 for controlling the vehicle to automatically perform lane keeping according to the lane keeping control parameter.
In some possible embodiments, the lane keeping assist control apparatus further includes an information preprocessing unit 106 for preprocessing the lane environment information and the steering wheel information. Specifically, the preprocessing may include preprocessing such as outlier rejection, filtering, and rotation speed signal calculation.
In some possible embodiments, the lane keeping assist control apparatus further includes a parameter storage unit 107 for storing a recognition result for a preset time period.
Further, the data stored in the parameter storage unit 107 can be updated in the form of a time window after the full content, so that the requirement on the storage capacity can be reduced; meanwhile, the driver can manually clear all data in the space through the human-computer interface button.
Further, the preference determination unit 103 can determine the steering preference of the driver by using the recognition result of the preset time period in the parameter storage unit as an input.
In some possible embodiments, the lane keeping assist control apparatus further includes a target trajectory planning unit 108, and the target trajectory planning unit 108 is configured to determine a target driving trajectory of the vehicle when the lane keeping function is activated, so as to reasonably adjust the body posture to avoid the vehicle rushing out of the lane line.
In some possible embodiments, the lane-keeping control unit 105 may enable the vehicle to safely travel according to the target trajectory during the activation of the lane-keeping function, thereby completing the lane-keeping function of the vehicle. Specifically, it may be that steering control of the vehicle is completed.
Further, the relevant control parameters of the lane keeping control unit are from a control parameter determination unit.
In some possible embodiments, the control parameter determination unit 104 can determine the optimal lane keeping function control parameter sequence at the current steering preference by a built-in adaptive parameter strategy.
Correspondingly, the embodiment of the invention also provides a lane keeping auxiliary control system, which comprises any one of the lane keeping auxiliary control devices.
Further, the lane keeping auxiliary control system further comprises a sensing unit 2, wherein the sensing unit 2 comprises a front camera, a corner sensor and a torque sensor;
the front camera is used for acquiring lane environment information, the corner sensor is used for acquiring steering wheel corner information, and the torque sensor is used for acquiring steering wheel torque information.
Further, the lane keeping assist control system further includes a steering actuator 3 for executing control parameters of the lane keeping control unit to cause the vehicle to perform a lane keeping function.
In some possible embodiments, the steering actuator 3 may be an EPS system capable of receiving an active steering torque or steering angle request from a control decision layer output of a lane keeping control unit to perform corresponding operations.
As shown in fig. 8, a schematic diagram of the structure of the lane keeping assist control system is provided.
Correspondingly, the embodiment of the invention also provides a vehicle, which comprises the lane keeping auxiliary control device or the lane keeping auxiliary control system.
Accordingly, embodiments of the present invention also provide a computer storage medium having at least one instruction, at least one program, a set of codes, or a set of instructions stored therein, which is loaded by a processor and executes any one of the lane keeping assist control methods described above.
Accordingly, embodiments of the present invention also provide an apparatus, which includes a processor and a memory, where at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the lane keeping assist control method according to any one of the above items.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, system and server embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A lane keep assist control method characterized by comprising:
acquiring lane environment information and steering wheel information detected by a sensor in real time, wherein the steering wheel information comprises steering wheel corner information, steering wheel moment information and steering wheel rotating speed information;
identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time;
dynamically reading the recognition result of the steering behavior category in the preset time length stored in the time window, and judging the steering preference of the driver according to the recognition result of the steering behavior category in the preset time length, wherein the steps comprise: counting the proportion of each steering behavior category according to the recognition result in a preset time length, and comparing the proportion with a proportion threshold value to obtain a current steering preference judgment result, wherein the proportion threshold value corresponds to the steering preference;
determining lane keeping control parameters of the vehicle according to the steering preference and the lane environment information;
and controlling the vehicle to automatically keep the lane according to the lane keeping control parameter.
2. The lane keep assist control method according to claim 1, wherein the identifying a driver's current category of steering behavior from the steering wheel information acquired in real time includes:
obtaining steering behavior data of the driver off line;
taking the steering behavior data acquired offline as an original training set, and correspondingly dividing the original training set into a plurality of behavior training sets according to the steering behavior category;
self-learning is carried out on each behavior training set through a self-learning model to obtain a behavior self-learning library; the behavior self-learning library comprises steering characteristic vectors corresponding to the behavior training sets;
and comparing and judging the steering wheel information acquired in real time with the behavior self-learning library, and identifying to obtain the current steering behavior category of the driver.
3. The lane keep assist control method according to claim 2,
and dividing the steering behavior type according to steering wheel angle data, steering wheel rotating speed data and steering wheel torque data in the steering behavior data.
4. The lane keep assist control method according to claim 2,
and comparing and judging the steering wheel information acquired in real time with the self-learning library by an estimation method, so that the steering behavior category with the highest probability is used as the identification result of the current steering behavior of the driver.
5. The lane keep assist control method according to claim 1, wherein the determining of the steering preference of the driver according to the recognition result of the category of the steering behavior within a preset time period includes:
and dynamically storing the identification result of the steering behavior category within a preset time length through a steering behavior time window.
6. The lane keep assist control method according to claim 1, characterized by further comprising:
and carrying out preprocessing of abnormal value elimination, filtering and rotation speed signal calculation on the lane environment information and the steering wheel information.
7. A lane keep assist control device characterized by comprising:
the data acquisition unit is used for acquiring lane environment information and steering wheel information detected by the sensor in real time, wherein the steering wheel information comprises steering wheel corner information, steering wheel moment information and steering wheel rotating speed information;
the category identification unit is used for identifying the current steering behavior category of the driver according to the steering wheel information acquired in real time;
the preference determination unit is used for dynamically reading the identification result of the steering behavior category in the preset time length stored in the time window, and determining the steering preference of the driver according to the identification result of the steering behavior category in the preset time length, and comprises the following steps: counting the proportion of each steering behavior category according to the recognition result in a preset time length, and comparing the proportion with a proportion threshold value to obtain a current steering preference judgment result, wherein the proportion threshold value corresponds to the steering preference;
a control parameter determination unit for determining a lane keeping control parameter of the vehicle according to the steering preference and the lane environment information;
and the lane keeping control unit is used for controlling the vehicle to automatically keep a lane according to the lane keeping control parameters.
8. A lane keep assist control system characterized by comprising the lane keep assist control apparatus of claim 7,
the lane keeping auxiliary control system further comprises a sensing unit, wherein the sensing unit comprises a front camera, a corner sensor and a torque sensor;
the front camera is used for acquiring lane environment information, the corner sensor is used for acquiring steering wheel corner information, and the torque sensor is used for acquiring steering wheel torque information.
9. A vehicle characterized by comprising the lane keep assist control apparatus of claim 7 or comprising the lane keep assist control system of claim 8.
10. A computer storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions that is loaded by a processor and which performs the lane keeping assist control method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910875691.2A CN110789522B (en) | 2019-09-17 | 2019-09-17 | Lane keeping assist control method, device, system, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910875691.2A CN110789522B (en) | 2019-09-17 | 2019-09-17 | Lane keeping assist control method, device, system, vehicle and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110789522A CN110789522A (en) | 2020-02-14 |
| CN110789522B true CN110789522B (en) | 2021-03-05 |
Family
ID=69427272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910875691.2A Active CN110789522B (en) | 2019-09-17 | 2019-09-17 | Lane keeping assist control method, device, system, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110789522B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106184223A (en) * | 2016-09-28 | 2016-12-07 | 北京新能源汽车股份有限公司 | Automatic driving control method and device and automobile |
| KR20170140625A (en) * | 2016-06-13 | 2017-12-21 | 현대자동차주식회사 | System and Method for recognizing driving pattern of driver |
| CN108137090A (en) * | 2015-10-05 | 2018-06-08 | 德尔福技术有限公司 | For the hommization steering model of automated vehicle |
| CN108995653A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver's driving style recognition methods and system |
| CN109177982A (en) * | 2018-10-31 | 2019-01-11 | 吉林大学 | Consider the vehicle driving Hazard degree assessment method of driving style |
-
2019
- 2019-09-17 CN CN201910875691.2A patent/CN110789522B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108137090A (en) * | 2015-10-05 | 2018-06-08 | 德尔福技术有限公司 | For the hommization steering model of automated vehicle |
| KR20170140625A (en) * | 2016-06-13 | 2017-12-21 | 현대자동차주식회사 | System and Method for recognizing driving pattern of driver |
| CN106184223A (en) * | 2016-09-28 | 2016-12-07 | 北京新能源汽车股份有限公司 | Automatic driving control method and device and automobile |
| CN108995653A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver's driving style recognition methods and system |
| CN109177982A (en) * | 2018-10-31 | 2019-01-11 | 吉林大学 | Consider the vehicle driving Hazard degree assessment method of driving style |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110789522A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403426B (en) | Target object detection method and device | |
| CN107521501B (en) | Game theory-based driver assistance system decision method, system and others | |
| WO2019005547A1 (en) | Moving body control apparatus, moving body control method, and training method | |
| CN110789517A (en) | Automatic driving lateral control method, device, equipment and storage medium | |
| JP2020110911A (en) | Depth perception modeling for grasping object | |
| CN112689587B (en) | Method for classifying non-driving task activities taking account of the interruptibility of the non-driving task activities of a driver when the taking over of driving tasks is required, and method for re-releasing the non-driving task activities after interrupting the non-driving task activities due to the taking over of driving tasks is required | |
| US20200156649A1 (en) | Method and Device for Evaluating a Degree of Fatigue of a Vehicle Occupant in a Vehicle | |
| CN113602284A (en) | Man-machine common driving mode decision method, device, equipment and storage medium | |
| CN110341710B (en) | Self-adaptive cruise control method, device and equipment | |
| KR20190135394A (en) | Method and apparatus for executing cleaning operation | |
| CN114802293A (en) | Vehicle lateral control system with adjustable parameters | |
| CN113905938A (en) | System and method for improving interaction between a plurality of autonomous vehicles and their driving environment | |
| CN110789522B (en) | Lane keeping assist control method, device, system, vehicle and storage medium | |
| CN109910798A (en) | A kind of device and method adjusting vehicle-state | |
| CN114329306A (en) | Method and device for calculating braking distance, automobile and medium | |
| CN113743603A (en) | Control method, control device, storage medium and electronic equipment | |
| Amadori et al. | Decision anticipation for driving assistance systems | |
| CN113353066B (en) | Obstacle touch recognition method, device, equipment and storage medium | |
| CN115384539A (en) | Method and device for generating intelligent driving strategy of vehicle, vehicle and storage medium | |
| Okuno et al. | Body posture and face orientation estimation by convolutional network with heterogeneous learning | |
| CN114287008A (en) | Method for compressing neural networks | |
| Chi et al. | Deep Reinforcement Learning with Intervention Module for Autonomous Driving | |
| CN114800530B (en) | Control method, equipment and storage medium for vision-based robot | |
| JP7325687B2 (en) | Sleepiness estimation device and sleepiness estimation system | |
| KR102603423B1 (en) | Apparatus and method for classifying an event of an image using a neural network model |
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 |