CN112758107B - Automatic lane changing method for vehicle, control device, electronic equipment and automobile - Google Patents
Automatic lane changing method for vehicle, control device, electronic equipment and automobile Download PDFInfo
- Publication number
- CN112758107B CN112758107B CN202110167997.XA CN202110167997A CN112758107B CN 112758107 B CN112758107 B CN 112758107B CN 202110167997 A CN202110167997 A CN 202110167997A CN 112758107 B CN112758107 B CN 112758107B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- target vehicle
- surrounding environment
- judging
- 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
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
-
- 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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- 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
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
- B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic lane changing method for a vehicle, a control device, electronic equipment and the vehicle, wherein the method comprises the following steps: acquiring current surrounding environment information of a target vehicle; judging the lane changing intention of the target vehicle; if the target vehicle intends to change the lane, judging the type of a parallel lane line when the target vehicle needs to change the lane by adopting a first recognition model according to the information of the current surrounding environment; if the type of the parallel lane line is a solid line, stopping automatic lane changing; if the type of the parallel lane line is a dotted line, judging whether unsafe factors exist near the target vehicle or not by adopting a second identification model according to the information of the current surrounding environment; if no unsafe factors exist near the target vehicle, automatically changing lanes; and if unsafe factors exist near the target vehicle, stopping automatically changing the lane. The method and the system can accurately identify the state change of objects around the vehicle, can safely and reliably realize autonomous lane change under the condition of complex scene, and avoid unnecessary accidents.
Description
Technical Field
The invention relates to the field of automatic driving control of vehicles, in particular to an automatic lane changing method of a vehicle, a control device, electronic equipment and an automobile.
Background
The automobile has become a tool for ordinary people to walk instead of walk at present, in the development process of automobile technology, safe, convenient and intelligent design is always a key research work, in the high-tech development era, the convenience and the intelligence are really important, but the safety is a more important work. At present, many automobile manufacturers are researching and developing technologies such as unmanned driving and safe driving assistance, but the difficulty of really realizing unmanned driving with extremely high safety is higher.
The safety and the unmanned driving technology are mutually exclusive, common drivers highly concentrate on thinking in the driving process, and thus the safety is higher, but along with the social progress and the continuous development of the artificial intelligence technology, high technology is required to be slowly integrated into the driving process to really realize easy driving, so the safety in the driving process is an especially important consideration, and the unmanned driving technology can be better applied and popularized only if the safety is really improved.
Aiming at the characteristic that the current safety is not high in unmanned technology application, a plurality of research directions exist at present, for example, the fluency of a line is judged by counting the flow of a vehicle, so that a driver is reminded to pay attention to avoidance, a traffic signal lamp is intelligently detected, SLAM positioning is used, and the like. However, the safety factor is too much, so that the safety factor is difficult to be realized at all, and the potential safety hazard can be only slowly and technically explored and eliminated. The current vehicle auxiliary technical scheme that turns into the lane can be through detecting vehicle indicator on some high-end cars at present, then realizes safe lane changing under the condition of artificial direct intervention, and the lower end is compared to the technical aspect, really realizes complete automatic lane changing, still hardly accomplishes at present, does not have better realization yet.
At present, the development of the artificial intelligence technology has been impressive, and from the development of the artificial intelligence technology, the artificial intelligence technology has infinite potential, and particularly, a deep learning perception algorithm is considered by researchers to be an artificial intelligence method closer to a human sensory thinking mode, so that the deep learning perception algorithm is used for solving practical problems in reality, and a feasible research foundation is provided.
With the development of artificial intelligence technology, the artificial intelligence technology can be naturally combined with automobile technology, and most of the current artificial intelligence technology falls on the ground in automobiles based on human-vehicle interaction scenes, such as intelligent voice control of vehicle general control, realization of auxiliary driving and the like. The combination of the artificial intelligence technology and the depth of the automobile is gradually improved and gradually matured.
At present, a main vehicle main control system with an automatic lane changing function on some high-end brand cars detects the turning function of a vehicle and turns on, automatic lane changing is realized under the condition that a parallel lane is relatively open, only convenient auxiliary lane changing can be realized, the scheme of the automatic lane changing has certain feasibility, but the scheme has high stress requirement aiming at a complex scene, timely prejudgment on the safety problem is difficult to realize, and major accidents and traffic illegal behaviors happen carelessly.
In addition, some existing automatic lane change solutions mainly adopt digital image processing technology to extract RGB and CMY color spaces and remove irrelevant areas to detect whether other vehicles and some behavior state changes of the vehicles exist on the concerned area recognition parallel lane, and the realization idea is traditional, simple and large in error.
Disclosure of Invention
In order to solve the problems, the invention provides an automatic lane changing method for a vehicle, a control device, electronic equipment and an automobile.
To achieve the above object, in one aspect, the present invention provides an automatic lane change method for a vehicle, comprising the steps of:
acquiring current surrounding environment information of a target vehicle;
judging the lane changing intention of the target vehicle;
if the target vehicle intends to change lanes, judging the type of a parallel lane line when the target vehicle needs to change lanes by adopting a first recognition model according to the information of the current surrounding environment; the first recognition model is obtained by training according to the surrounding environment information of the historical vehicle and the type of the parallel lane line during the historical lane change;
if the type of the parallel lane line is a solid line, stopping automatic lane changing; if the type of the parallel lane line is a dotted line, judging whether unsafe factors exist near the target vehicle or not by adopting a second identification model according to the information of the current surrounding environment; the second recognition model is obtained by training according to the surrounding environment information of the historical vehicle and whether unsafe factors exist near the historical vehicle;
if no unsafe factors exist near the target vehicle, automatically changing lanes;
and if unsafe factors exist near the target vehicle, stopping automatically changing the lane.
Further, the first recognition model is obtained by the following steps:
acquiring the ambient environment information of the historical vehicle and the type of the parallel lane line during the historical lane change as training data, training a learning model and optimizing to obtain the first recognition model;
the second recognition model is obtained by the following steps:
acquiring surrounding environment information of the historical vehicle and whether unsafe factors exist near the historical vehicle as training data, training a learning model, and optimizing to obtain a second recognition model;
the specific steps of obtaining the ambient environment information of the historical vehicle and the type of the parallel lane line during the historical lane change as training data are as follows:
acquiring picture data of a plurality of actual roads, wherein the picture data comprises a single solid line, a single yellow line, double yellow lines, a dotted line, a left dotted line right solid line and a left solid line right dotted line, and the picture data is used as first sample data for judging the type of the parallel lane line;
and the first sample data is processed according to the following steps of 6:2:2, sequentially dividing the ratio into a training set, a test set and a verification set as training data of the first recognition model;
the second recognition model is obtained by the following steps:
acquiring surrounding environment information of the historical vehicle and whether unsafe factors exist near the historical vehicle as training data, training a learning model, and optimizing to obtain a second recognition model;
the specific steps of acquiring the surrounding environment information of the historical vehicle and the existence of unsafe factors near the historical vehicle as training data are as follows:
acquiring a plurality of pieces of video data with moving objects, and acquiring a plurality of pieces of single-frame picture data from the video data as second sample data for judging whether the moving objects exist or not;
collecting a plurality of pictures containing signal lamps of the front vehicle as third sample data for judging the movement behavior intention of the front vehicle;
collecting a plurality of pictures containing rear vehicle signal lamps as fourth sample data for judging the intention of the rear vehicle to move;
and the second sample data, the third sample data and the fourth sample data are processed according to the following steps of 6:2: and 2, sequentially dividing the ratio into a training set, a test set and a verification set as training data of the second recognition model.
Further, the specific steps of the vehicle general control system for judging the current lane change intention of the vehicle are as follows:
determining that the target vehicle has a tendency to lane change if the target vehicle turns on the turn signal switch;
judging whether an included angle alpha between the vehicle body and a lane line on the right side of the vehicle is in accordance with 0 degree < alpha <90 degrees or not, and if the alpha is in accordance with 0 degree < alpha <90 degrees, judging that the target vehicle has a tendency of changing lanes to the right;
judging whether the lane changing tendency of the target vehicle is consistent with that of the steering lamp, and stopping automatic lane changing if the lane changing tendency of the target vehicle is inconsistent with that of the steering lamp; if the steering direction of the lane change of the target vehicle is consistent with the steering lamp, determining that the target vehicle intends to change the lane;
if the alpha is not in accordance with 0 degrees < alpha <90 degrees, judging whether the included angle between the vehicle body and the lane line on the left side of the vehicle is beta in accordance with 0 degrees < beta <90 degrees, and if the beta in accordance with 0 degrees < beta <90 degrees, judging that the target vehicle has the tendency of changing lanes to the left;
judging whether the lane changing tendency of the target vehicle is consistent with that of the steering lamp, and stopping automatic lane changing if the lane changing tendency of the target vehicle is inconsistent with that of the steering lamp; if the steering direction of the lane change of the target vehicle is consistent with the steering lamp, determining that the target vehicle intends to change the lane;
if β does not meet 0 ° < β <90 °, it is determined that the target vehicle does not have a tendency to lane change, and automatic lane change is stopped.
Further, the specific steps of judging the type of the parallel lane line when the target vehicle needs to change lanes are as follows:
shooting parallel lane line pictures by cameras on two sides of a vehicle body to obtain current surrounding environment information of the target vehicle;
inputting the current surrounding environment information of the target vehicle into the first recognition model to obtain the type of the parallel lane line;
the solid lines are white solid lines, single yellow lines and double yellow lines, and the dotted lines are single dotted lines, left dotted line right solid lines and left solid line right dotted lines.
Further, the specific steps of judging whether unsafe factors exist near the target vehicle are as follows:
obtaining current surrounding environment information of the target vehicle by using single-frame pictures shot by cameras on two sides of a vehicle body;
inputting the current surrounding environment information of the target vehicle into the second recognition model, judging whether moving objects exist around the target vehicle, if so, entering the next step, and if not, starting automatic lane changing;
judging whether the distance between the moving object and the target vehicle is beyond the collision distance, if so, entering the next step, and if not, stopping automatic lane changing;
if the vehicle is arranged on the lane on the side where the lane change requirement exists, acquiring the vehicle speed information of the target vehicle, detecting the relative speed between the vehicle on the lane on the side where the lane change requirement exists and the target vehicle, and if the relative speed exceeds the threshold range, judging that the lane change is unsafe, and stopping automatic lane change; if the relative speed is within the threshold range, automatically changing the lane;
and when the lane change is finished, the vehicle continues to run on the road.
Further, the collision distance is 20 meters, and the threshold range of the relative speed is 0-20km/h.
In another aspect, the present invention provides a control apparatus for automatically changing lanes of a vehicle, including:
the acquisition unit is used for acquiring the ambient environment information of the historical vehicle and the type of the parallel lane line during the historical lane change;
an acquisition unit configured to acquire current surrounding environment information of a target vehicle;
the analysis unit is used for dividing the first sample data or the combined sample data comprising the second sample data, the third sample data and the fourth sample data into a training set, a test set and a verification set respectively;
the model training unit is used for training and optimizing the first recognition model and the second recognition model;
the identification unit is used for identifying the current surrounding environment information of the target vehicle and outputting a lane change instruction of the target vehicle;
and the control unit is used for controlling the target vehicle to carry out lane changing operation according to the lane changing instruction.
Furthermore, the identification unit comprises a first identification model and a second identification model and is arranged in the vehicle general control system.
In yet another aspect, the present invention also provides an electronic device comprising a memory and a processor, the memory storing a computer program for executing the above method, the computer program being executed by the processor.
In still another aspect, the invention further provides an automobile, and the automobile comprises the electronic device.
Compared with the prior art, the invention has the beneficial effects that:
the method can accurately identify the state change of objects around the vehicle, can safely and reliably realize autonomous lane change under the condition of complex scene, and avoids unnecessary accidents, but has no absolute safety in all the cases.
The invention utilizes the capability of deep learning perception algorithm, continuously adds various sample data, continuously optimizes the algorithm model, picks out the optimal algorithm model from the algorithm model, presets the model in the vehicle master control system, predicts the state change of objects around the vehicle by the master control system in the actual scene, judges whether unsafe hidden dangers exist in the automatic lane changing process, immediately cancels the automatic lane changing if the unsafe hidden dangers exist, and can realize the timely prevention of safety.
Drawings
FIG. 1 is a flow chart of a method for training a first recognition model according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for training a second recognition model according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for determining a lane change intention of a vehicle according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for determining whether an unsafe factor exists near a current vehicle according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a control device in an embodiment of the present invention.
In the figure: 100. a collection unit; 200. an acquisition unit; 300. an analysis unit; 400. a model training unit; 500. an identification unit; 600. a control unit.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, the training method for a first recognition model provided in the embodiment of the present invention includes the following steps S101 to S103:
s101: acquiring picture data of a plurality of actual roads including a single solid line, a single yellow line, double yellow lines, a dotted line, a left dotted line right solid line and a left solid line right dotted line as first sample data for judging the type of the parallel lane line;
s102: and the first sample data is processed according to the following steps of 6:2:2, sequentially dividing the ratio into a training set, a test set and a verification set as training data of the first recognition model;
s103: training a learning model and optimizing to obtain the first recognition model, and presetting the first recognition model in a vehicle master control system.
Referring to fig. 2, the method for training the second recognition model according to the embodiment of the present invention includes the following steps S201 to S204:
s201: acquiring a plurality of pieces of video data with moving objects, and acquiring a plurality of pieces of single-frame picture data from the video data as second sample data for judging whether the moving objects exist or not;
s202: collecting a plurality of pictures containing signal lamps of the front vehicle as third sample data for judging the movement behavior intention of the front vehicle;
s203: collecting a plurality of pictures containing rear vehicle signal lamps as fourth sample data for judging the intention of the rear vehicle to move;
s204: and the second sample data, the third sample data and the fourth sample data are processed according to the following steps of 6:2: and 2, sequentially dividing the ratio into a training set, a testing set and a verification set as training data of the second recognition model, and presetting the second recognition model in the vehicle master control system.
Referring to fig. 3, which is a flowchart of a method for determining a current lane change intention of a vehicle according to an embodiment of the present invention, the method includes the following steps S301 to S304:
s301: determining that the target vehicle has a tendency to lane change if the target vehicle turns on the turn signal switch;
s302: judging whether an included angle alpha between the vehicle body and a lane line on the right side of the vehicle is in accordance with 0 degree < alpha <90 degrees or not, and if the alpha is in accordance with 0 degree < alpha <90 degrees, judging that the target vehicle has a tendency of changing lanes to the right;
judging whether the lane changing tendency of the target vehicle is consistent with that of the steering lamp, and stopping automatic lane changing if the lane changing tendency of the target vehicle is inconsistent with that of the steering lamp; if the steering direction of the lane change of the target vehicle is consistent with the steering lamp, determining the lane change intention of the target vehicle;
s303: if the alpha is not in accordance with 0 degrees < alpha <90 degrees, judging whether the included angle between the vehicle body and the lane line on the left side of the vehicle is beta in accordance with 0 degrees < beta <90 degrees, and if the beta in accordance with 0 degrees < beta <90 degrees, judging that the target vehicle has the tendency of changing lanes to the left;
s304: judging whether the lane changing tendency of the target vehicle is consistent with that of the steering lamp, and stopping automatic lane changing if the lane changing tendency of the target vehicle is inconsistent with that of the steering lamp; if the steering direction of the lane change of the target vehicle is consistent with that of the steering lamp, determining that the target vehicle intends to change the lane;
if β does not meet 0 ° < β <90 °, it is determined that the target vehicle does not have a tendency to lane change, and automatic lane change is stopped.
Referring to fig. 4, which is a flowchart of a method for determining whether there is an unsafe factor in the vicinity of a current vehicle according to an embodiment of the present invention, the method includes the following steps S401 to S404:
s401: obtaining current surrounding environment information of the target vehicle by using single-frame pictures shot by cameras on two sides of a vehicle body;
s402: inputting the current surrounding environment information of the target vehicle into the second identification model, judging whether moving objects exist around the target vehicle, if so, entering the next step, and if not, starting automatic lane changing;
s403: judging whether the distance between the moving object and the target vehicle is beyond the collision distance, if so, entering the next step, and if not, stopping automatic lane changing;
if the vehicle is arranged on the lane on the side where the lane change requirement exists, acquiring the vehicle speed information of the target vehicle, detecting the relative speed between the vehicle on the lane on the side where the lane change requirement exists and the target vehicle, if the relative speed exceeds the threshold range, judging that the lane change condition is unsafe, and stopping automatic lane change; if the relative speed is within the threshold range, automatically changing the lane;
s404: and when the lane change is finished, the vehicle continues to run on the road.
In the present embodiment, the collision distance is 20 meters, and the threshold range of the relative speed is 0-20km/h.
The present invention provides a control device for automatic lane change of a vehicle, referring to fig. 5, comprising:
the acquisition unit 100 is used for acquiring the surrounding environment information of historical vehicles and the types of parallel lane lines during the historical lane change;
an acquisition unit 200 for acquiring current surrounding environment information of a target vehicle;
an analyzing unit 300, configured to divide the first sample data or the combined sample data including the second sample data, the third sample data, and the fourth sample data into a training set, a test set, and a verification set, respectively;
the model training unit 400 is used for training and optimizing the first recognition model and the second recognition model;
an identifying unit 500 for identifying current surrounding environment information of a target vehicle and outputting a lane change instruction of the target vehicle;
and a control unit 600 for controlling the target vehicle to perform a lane change operation according to the lane change instruction.
Based on the automatic lane changing method and the control device provided by the above embodiments, the invention further provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program for executing the above method, and the computer program is executed by the processor.
The embodiment of the invention also provides an automobile comprising the electronic equipment.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (6)
1. An automatic lane changing method for a vehicle is characterized by comprising the following steps:
acquiring current surrounding environment information of a target vehicle;
judging the lane changing intention of the target vehicle;
if the target vehicle intends to change lanes, judging the type of a parallel lane line when the target vehicle needs to change lanes by adopting a first recognition model according to the information of the current surrounding environment; the first recognition model is obtained by training according to the surrounding environment information of the historical vehicle and the type of the parallel lane line during the historical lane change;
if the type of the parallel lane line is a solid line, stopping automatic lane changing; if the type of the parallel lane line is a dotted line, judging whether unsafe factors exist near the target vehicle or not by adopting a second identification model according to the information of the current surrounding environment; the second recognition model is obtained by training according to the surrounding environment information of the historical vehicle and whether unsafe factors exist near the historical vehicle;
if no unsafe factors exist near the target vehicle, automatically changing lanes;
if unsafe factors exist near the target vehicle, stopping automatic lane changing;
the first recognition model is obtained by the following steps:
acquiring the ambient environment information of the historical vehicle and the type of the parallel lane line during the historical lane change as training data, training a learning model and optimizing to obtain the first recognition model;
the specific steps of obtaining the surrounding environment information of the historical vehicles and the type of the parallel lane lines during the historical lane change as training data are as follows:
acquiring picture data of a plurality of actual roads, wherein the picture data comprises a single solid line, a single yellow line, double yellow lines, a dotted line, a left dotted line right solid line and a left solid line right dotted line, and the picture data is used as first sample data for judging the type of the parallel lane line;
and the first sample data is processed according to the following steps of 6:2:2, sequentially dividing the ratio into a training set, a test set and a verification set as training data of the first recognition model;
the second recognition model is obtained by the following steps:
acquiring surrounding environment information of the historical vehicle and whether unsafe factors exist near the historical vehicle as training data, training a learning model, and optimizing to obtain a second recognition model;
the specific steps of acquiring the surrounding environment information of the historical vehicle and the existence of unsafe factors near the historical vehicle as training data are as follows:
acquiring a plurality of pieces of video data with moving objects, and acquiring a plurality of pieces of single-frame picture data from the video data as second sample data for judging whether the moving objects exist or not;
collecting a plurality of pictures containing signal lamps of the front vehicle as third sample data for judging the movement behavior intention of the front vehicle;
collecting a plurality of pictures containing rear vehicle signal lamps as fourth sample data for judging the intention of the rear vehicle to move;
and combining the second sample data, the third sample data and the fourth sample data according to 6:2:2, sequentially dividing the training set, the test set and the verification set as training data of the second recognition model;
the method for judging the current lane change intention of the vehicle main control system comprises the following specific steps:
determining that the target vehicle has a tendency to lane change if the target vehicle turns on the turn signal switch;
judging whether an included angle alpha between the vehicle body and a lane line on the right side of the vehicle is in accordance with 0 degree < alpha <90 degrees or not, and if the alpha is in accordance with 0 degree < alpha <90 degrees, judging that the target vehicle has a tendency of changing lanes to the right;
judging whether the lane changing tendency of the target vehicle is consistent with that of the steering lamp, and stopping automatic lane changing if the lane changing tendency of the target vehicle is inconsistent with that of the steering lamp; if the steering direction of the lane change of the target vehicle is consistent with the steering lamp, determining that the target vehicle intends to change the lane;
if the alpha is not in accordance with 0 degrees < alpha <90 degrees, judging whether the included angle between the vehicle body and the lane line on the left side of the vehicle is beta in accordance with 0 degrees < beta <90 degrees, and if the beta in accordance with 0 degrees < beta <90 degrees, judging that the target vehicle has the tendency of changing lanes to the left;
if beta does not meet the condition of 0 degrees < beta <90 degrees, judging that the target vehicle does not have the tendency of lane changing, and stopping automatic lane changing;
the specific steps for judging the type of the parallel lane line when the target vehicle needs to change lane are as follows:
shooting parallel lane line pictures by cameras on two sides of a vehicle body to obtain current surrounding environment information of the target vehicle;
inputting the current surrounding environment information of the target vehicle into the first recognition model to obtain the type of the parallel lane line;
the solid lines are white solid lines, single yellow lines and double yellow lines, and the dotted lines are single dotted lines, left dotted line right solid lines and left solid line right dotted lines;
the specific steps for judging whether unsafe factors exist near the target vehicle are as follows:
obtaining current surrounding environment information of the target vehicle by using single-frame pictures shot by cameras on two sides of a vehicle body;
inputting the current surrounding environment information of the target vehicle into the second recognition model, judging whether moving objects exist around the target vehicle, if so, entering the next step, and if not, starting automatic lane changing;
judging whether the distance between the moving object and the target vehicle is beyond the collision distance, if so, entering the next step, and if not, stopping automatic lane changing;
if the vehicle is arranged on the lane on the side where the lane change requirement exists, acquiring the vehicle speed information of the target vehicle, detecting the relative speed between the vehicle on the lane on the side where the lane change requirement exists and the target vehicle, if the relative speed exceeds the threshold range, judging that the lane change condition is unsafe, and stopping automatic lane change; if the relative speed is within the threshold range, automatically changing the lane;
and when the lane change is finished, the vehicle continues to run on the road.
2. The automatic lane change method for a vehicle according to claim 1, characterized in that: the collision distance is 20 meters, and the threshold range of the relative speed is 0-20km/h.
3. A control apparatus for automatic lane change of a vehicle, for implementing the automatic lane change method of a vehicle according to any one of claims 1 or 2, comprising:
the acquisition unit is used for acquiring the surrounding environment information of the historical vehicle and the type of the parallel lane line during the historical lane change;
an acquisition unit configured to acquire current surrounding environment information of a target vehicle;
the analysis unit is used for dividing the first sample data or the combined sample data comprising the second sample data, the third sample data and the fourth sample data into a training set, a test set and a verification set respectively;
the model training unit is used for training and optimizing the first recognition model and the second recognition model;
the identification unit is used for identifying the current surrounding environment information of the target vehicle and outputting a lane change instruction of the target vehicle;
and the control unit is used for controlling the target vehicle to perform lane changing operation according to the lane changing instruction.
4. The control device for vehicle automatic lane change according to claim 3, characterized in that: the recognition unit comprises a first recognition model and a second recognition model and is arranged in the vehicle main control system.
5. An electronic device, characterized in that: comprising a memory and a processor, the memory storing a computer program for implementing the method of any of claims 1-2, the computer program being executable by the processor.
6. An automobile, characterized in that: the automobile comprising the electronic device of claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110167997.XA CN112758107B (en) | 2021-02-07 | 2021-02-07 | Automatic lane changing method for vehicle, control device, electronic equipment and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110167997.XA CN112758107B (en) | 2021-02-07 | 2021-02-07 | Automatic lane changing method for vehicle, control device, electronic equipment and automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112758107A CN112758107A (en) | 2021-05-07 |
| CN112758107B true CN112758107B (en) | 2023-01-03 |
Family
ID=75705286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110167997.XA Active CN112758107B (en) | 2021-02-07 | 2021-02-07 | Automatic lane changing method for vehicle, control device, electronic equipment and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112758107B (en) |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102910126B (en) * | 2012-10-30 | 2015-03-04 | 浙江吉利汽车研究院有限公司杭州分公司 | Method and system for safe lane change of auxiliary vehicle |
| CN106741148B (en) * | 2017-01-04 | 2019-06-11 | 北京新能源汽车股份有限公司 | A kind of auto steering control method, device and automobile |
| CN108009524B (en) * | 2017-12-25 | 2021-07-09 | 西北工业大学 | Lane line detection method based on full convolution network |
| CN109344704B (en) * | 2018-08-24 | 2021-09-14 | 南京邮电大学 | Vehicle lane change behavior detection method based on included angle between driving direction and lane line |
| CN108961839A (en) * | 2018-09-05 | 2018-12-07 | 奇瑞汽车股份有限公司 | Driving lane change method and device |
| CN111661057A (en) * | 2019-03-07 | 2020-09-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle equipment and vehicle lane changing road condition prompting method |
| CN111746383A (en) * | 2019-03-26 | 2020-10-09 | 长城汽车股份有限公司 | Vehicle steering safety control system and vehicle |
| CN110222591B (en) * | 2019-05-16 | 2023-04-07 | 天津大学 | Lane line detection method based on deep neural network |
| CN110745136B (en) * | 2019-09-20 | 2021-05-07 | 中国科学技术大学 | Driving self-adaptive control method |
| CN111382686B (en) * | 2020-03-04 | 2023-03-24 | 上海海事大学 | Lane line detection method based on semi-supervised generation confrontation network |
| CN111516597A (en) * | 2020-03-23 | 2020-08-11 | 一汽奔腾轿车有限公司 | Novel intelligent external rearview mirror and control method thereof |
| CN111310737B (en) * | 2020-03-26 | 2023-10-13 | 山东极视角科技股份有限公司 | Lane line detection method and device |
| CN111703424B (en) * | 2020-05-26 | 2021-12-24 | 武汉理工大学 | Intelligent networking automobile multi-sensor fusion auxiliary lane changing method and system |
| CN111717197A (en) * | 2020-06-23 | 2020-09-29 | 中国第一汽车股份有限公司 | Rear collision prevention method and device and vehicle |
| CN111775938B (en) * | 2020-06-24 | 2021-11-16 | 福瑞泰克智能系统有限公司 | Lane change path planning method, device and system |
-
2021
- 2021-02-07 CN CN202110167997.XA patent/CN112758107B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112758107A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111212772B (en) | Method and device for determining a driving strategy of a vehicle | |
| CN110430401B (en) | Vehicle blind area early warning method, early warning device, MEC platform and storage medium | |
| EP3533681A2 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| US8626427B2 (en) | User interface method for terminal for vehicle and apparatus thereof | |
| CN111002984A (en) | Automatic driving method and device, vehicle and automatic driving equipment | |
| JP7156394B2 (en) | Other Vehicle Motion Prediction Method and Other Vehicle Motion Prediction Device | |
| CN105620489A (en) | Driving assistance system and real-time warning and prompting method for vehicle | |
| CN109859509A (en) | Lane state based reminding method and equipment | |
| CN104424487A (en) | vehicle environment recognition apparatus | |
| US10600323B2 (en) | Vehicle external notification device | |
| JP2024023319A (en) | Emergency vehicle detection | |
| CN113022441B (en) | Detection method and device for dead zone of vehicle, electronic equipment and storage medium | |
| CN112606831A (en) | Anti-collision warning information external interaction method and system for passenger car | |
| CN115877343A (en) | Man-vehicle matching method and device based on radar target tracking and electronic equipment | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| JP4986070B2 (en) | Ambient monitoring device for vehicles | |
| CN114407928A (en) | Vehicle avoidance control method and vehicle avoidance control device | |
| CN112758107B (en) | Automatic lane changing method for vehicle, control device, electronic equipment and automobile | |
| CN110727269B (en) | Vehicle control method and related product | |
| CN115082894A (en) | Distance detection method, vehicle high beam control method, device, medium and vehicle | |
| CN115402322A (en) | Intersection driving assistance method and system, electronic device and storage medium | |
| CN114771510A (en) | Parking method, parking system and electronic device based on route map | |
| CN114604269A (en) | Method and apparatus for controlling turning operation of vehicle | |
| Balcerek et al. | Mobile applications for driver and pedestrian assistance |
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 |