CN112172810A - Lane keeping device, method and system and automobile - Google Patents
Lane keeping device, method and system and automobile Download PDFInfo
- Publication number
- CN112172810A CN112172810A CN201910524356.8A CN201910524356A CN112172810A CN 112172810 A CN112172810 A CN 112172810A CN 201910524356 A CN201910524356 A CN 201910524356A CN 112172810 A CN112172810 A CN 112172810A
- Authority
- CN
- China
- Prior art keywords
- lane line
- lane
- vehicle
- confidence
- lka
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 78
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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
- B60W30/10—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
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo or light sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
Abstract
The application relates to a lane keeping device, a lane keeping method, a lane keeping system and an automobile, wherein the lane keeping device comprises a lane detection unit and an LKA (lane-to-lane analysis) electric control unit; the lane detection unit outputs a first lane line confidence degree and first lane line information, and outputs a second lane line confidence degree and second lane line information; the LKA electric control unit selects the first lane line information or the second lane line information to process based on the first lane line confidence coefficient and the second lane line confidence coefficient to obtain steering data; and transmits the steering data to the electric power steering system for lateral control of the vehicle. The problem of traditional lane keeping auxiliary system (LKA) scene limited is solved in this application, the camera probably can't detect the lane line when perhaps not clear night or lane line, leads to the triggering fault of LKA function and frequently withdraws from and get into, and then enlarges LKA's in-service use scene and flexibility.
Description
Technical Field
The application relates to the technical field of intelligent driving of automobiles, in particular to a lane keeping device, a lane keeping method, a lane keeping system and an automobile.
Background
At present, a Lane Keeping Assistance system (LKA) completes detection of a Lane through a camera, the LKA gives an alarm and intervenes and controls Lane departure according to Lane information provided by the camera, so that a vehicle runs in the Lane, and the camera continuously monitors the condition of a road ahead in the process.
In the implementation process, the inventor finds that at least the following problems exist in the conventional technology: during traditional camera detected, when special illumination such as sleet haze weather, sunset backlight, door window fogging frosted and night illumination are not good, the detection to lane line all can be influenced, and then influence LKA's performance, for example, can't trigger LKA.
Disclosure of Invention
In view of the above, it is necessary to provide a lane keeping device, a lane keeping method, a lane keeping system, and an automobile.
In order to achieve the above object, in one aspect, an embodiment of the present invention provides a lane keeping apparatus, including a lane detection unit and an LKA electronic control unit;
when the LKA is started by the vehicle, the lane detection unit acquires the current geographic position of the vehicle, outputs lane information at the current geographic position of the vehicle in the high-precision map as first lane line information, performs reliability detection on the first lane line information, and outputs first lane line confidence;
the lane detection unit receives image data acquired by the vehicle camera, performs lane recognition on the image data, outputs second lane line information, performs reliability inspection on the second lane line information, and outputs second lane line confidence;
the LKA electric control unit selects the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmits the steering data to the electric power steering system to perform transverse control on the vehicle.
In one embodiment, the LKA electronic control unit comprises a connection processing module and an LKA control module;
the processing module compares the confidence of the first lane line with the confidence of the second lane line; the processing module determines steering data according to the current power data of the vehicle and the second lane line information when the confidence coefficient of the first lane line is smaller than or equal to the confidence coefficient of the second lane line; when the confidence coefficient of the first lane line is larger than that of the second lane line, determining steering data according to the current power data of the vehicle and the information of the first lane line; the vehicle current power data includes wheel speeds;
the processing module transmits the steering data to the LKA control module;
and the LKA control module transmits the steering data to the electric power steering system.
In one embodiment, the lane detection unit comprises a high-precision map module and a camera detection module;
the high-precision map module is used for positioning the vehicle to obtain the current geographic position of the vehicle, and inquiring in the high-precision map according to the current geographic position of the vehicle to obtain first lane line information; the high-precision map module carries out lane line definition and continuity detection on the first lane line information and outputs a first lane line confidence coefficient;
the camera detection module receives image data; the camera detection module processes the image data by adopting a corresponding lane line detection algorithm and outputs second lane line information; the camera detection module detects the definition and continuity of the lane line of the second lane line information and outputs a confidence coefficient of the second lane line.
In one embodiment, the LKA electronic control unit instructs the vehicle to close the LKA when the first lane line confidence and the second lane line confidence both fall into the preset failure interval.
On the other hand, the embodiment of the invention also provides a lane keeping method, which comprises the following steps:
receiving first lane line information and first lane line confidence transmitted by a lane detection unit; the first lane line information is obtained by processing the current geographic position of the vehicle according to a high-precision map by a lane detection unit; the first lane line confidence coefficient is obtained by checking the reliability of the first lane line information through a lane detection unit;
receiving second lane line information and second lane line confidence transmitted by a lane detection unit; the second lane line information is obtained by carrying out lane identification on image data acquired by a vehicle camera through a lane detection unit; the second lane line confidence coefficient is obtained by the reliability inspection of the second lane line information through a lane detection unit;
selecting the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmitting the steering data to the electric power steering system; the steering data is used to instruct the electric power steering system to perform lateral control of the vehicle.
In one embodiment, the step of selecting the first lane line information or the second lane line information to determine the steering data based on the first lane line confidence and the second lane line confidence includes:
comparing the confidence of the first lane line with the confidence of the second lane line;
when the confidence coefficient of the first lane line is greater than that of the second lane line, determining steering data according to the current power data of the vehicle and the information of the first lane line; the vehicle current power data includes wheel speeds;
and when the confidence coefficient of the first lane line is smaller than or equal to the confidence coefficient of the second lane line, determining steering data according to the current dynamic data of the vehicle and the information of the second lane line.
In one embodiment, the steering data is a turn angle; further comprising the steps of: acquiring current power data of a vehicle; the vehicle current power data includes wheel speeds;
the step of selecting the first lane line information or the second lane line information to determine the steering data comprises the following steps:
analyzing and processing the current dynamic data of the vehicle and the information of a first lane line or the current dynamic data of the vehicle and the information of a second lane line to obtain a track of the vehicle lane line, a distance of a lane line deviated from and a yaw rate of the vehicle;
and outputting the size of the turning angle according to the lane line track of the vehicle, the distance of the lane line to be deviated and the yaw rate of the vehicle.
In one embodiment, the method further comprises the following steps:
outputting an LKA exiting instruction when the first lane line confidence coefficient and the second lane line confidence coefficient both fall into a preset failure interval; the exit LKA command is used to instruct the vehicle to shut down the LKA.
A lane keeping system comprises a vehicle camera, an electric power steering system and any one lane keeping device;
the lane keeping device is connected between the vehicle camera and the electric power steering system.
An automobile comprises the lane keeping system.
One of the above technical solutions has the following advantages and beneficial effects:
the method and the device fuse the current positioning position and the lane line information provided by the camera, and acquire the lane line information according to the positioning position of the vehicle when the camera cannot provide the lane line information; when the vehicle cannot provide lane line information according to the positioning information, the lane keeping device can provide the lane line information by using the camera for control; when the positioning position and the camera can provide lane line information, the lane keeping device is controlled according to the lane line information with higher confidence coefficient, and the LKA function can be quitted only when the lane line information can not be provided according to the positioning position and the camera; the problem of traditional lane keeping auxiliary system (LKA) scene limited is solved in this application, the camera probably can't detect the lane line when perhaps not clear night or lane line, leads to the triggering fault of LKA function and frequently withdraws from and get into, and then enlarges LKA's in-service use scene and flexibility.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular description of preferred embodiments of the application, as illustrated in the accompanying drawings. Like reference numerals refer to like parts throughout the drawings, and the drawings are not intended to be drawn to scale in actual dimensions, emphasis instead being placed upon illustrating the subject matter of the present application.
FIG. 1 is a first schematic configuration block diagram of a lane keeping apparatus in one embodiment;
FIG. 2 is a second schematic configuration block diagram of a lane keeping apparatus in one embodiment;
FIG. 3 is a third schematic configuration block diagram of a lane keeping apparatus according to an embodiment;
FIG. 4 is a schematic view illustrating the operation of the lane keeping apparatus according to one embodiment;
FIG. 5 is a flow diagram illustrating a lane keeping method according to one embodiment;
FIG. 6 is an internal block diagram of a lane keeping system in one embodiment;
FIG. 7 is a schematic diagram of an automobile with a lane keeping system in one embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present application are shown in the drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element and be integral therewith, or intervening elements may also be present. The terms "connected," "one end," "the other end," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
At present, the LKA in the market is controlled by detecting the relevant information of the lane line through the camera, but the applicable scenes of the LKA based on the lane line detected by the camera are limited, the performance is limited under the conditions of extreme weather, extreme illumination and the like, the LKA cannot be started when the camera is shielded and the camera is overheated, and the driving comfort level and the driving experience are reduced. The method and the device can fuse the camera and provide lane line data according to the self positioning of the automobile, can cover more scenes encountered on a road, and expand the scenes used by the LKA.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The application provides a lane keeping device can be applied to intelligent driving assistance system. In one embodiment, as shown in fig. 1, there is provided a lane keeping apparatus including a lane detecting unit 110 and a LKA electric control unit 120;
the lane detection unit 110 acquires the current geographic position of the vehicle when the LKA of the vehicle is started, outputs lane information at the current geographic position of the vehicle in the high-precision map as first lane line information, performs reliability check on the first lane line information, and outputs a first lane line confidence;
the lane detection unit 110 receives image data acquired by a vehicle camera, performs lane recognition on the image data, outputs second lane line information, performs reliability inspection on the second lane line information, and outputs second lane line confidence;
the LKA electronic control unit 120 selects the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmits the steering data to the electric power steering system to perform lateral control of the vehicle.
The vehicle camera in the application can refer to a front camera of an automobile; in one specific example, the mounting position of the front camera may be near the rearview position at the center of the front windshield.
Specifically, the lane detection system comprises a lane detection unit and an LKA electric control unit; the lane detection unit may be used to connect to a vehicle camera, and the LKA electronic control unit may be used to connect to an Electric Power Steering (EPS).
In practical applications, when the LKA function is turned on by the vehicle, for example, after the LKA function is turned on by a driver through a hard switch (physical button switch) or a software switch (touch screen switch) on the vehicle, an icon indicating that the function is turned on is displayed on the meter; the lane detection unit obtains the current geographic position of the vehicle through positioning, obtains first lane line information and first lane line confidence coefficient according to the geographic position, and transmits the first lane line information and the first lane line confidence coefficient to the LKA electric control unit. In one specific example, the lane detection unit may implement the above-described functions using a high-precision map.
The high-precision map in the present application may refer to a high-precision map, that is, a map generated by scanning and processing road information with higher precision. In a specific example, the high-precision map of the present application may refer to an independent electronic control unit on a whole vehicle, and the high-precision map can accurately position the vehicle after receiving information such as a GPS (Global Positioning System), an RTK (Real Time Kinematic) and a camera, and the high-precision map (which collects and stores all information of a road) outputs information such as a lane line according to a geographic position of the vehicle; meanwhile, the high-precision map can comprise the following two aspects: accurate positioning and accurate road information; compared with a common navigation map, the high-precision map is more accurate in positioning and can output information such as road gradient, curvature of each lane line, traffic identification and the like.
Further, the lane detection unit receives image data acquired by a vehicle camera, and processes the image data to obtain second lane line information and a second lane line confidence; and the lane detection unit transmits the second lane line information and the second lane line confidence to the LKA electric control unit.
Specifically, the lane detection unit receives image data acquired by a vehicle camera, performs lane recognition on the image data, and outputs second lane line information; for example, based on the gradient and color features of the image, the position of the lane line is located, and the whole line is tracked and the lane mark on the image is connected; the lane detection unit can accurately position the position of the lane line by adopting a related lane line recognition algorithm, for example, lane feature matching is carried out, a lane is identified by adopting a variable lane model, identification is carried out based on the lane model, specifically, various model parameters are established according to the length, the curvature and the slope of the lane, and then the lane line is established in the image correspondingly.
In one specific example, the lane detection unit may perform confidence checks, such as contrast, width, distance, etc., based on the potential markers in the image.
If lane line information provided by the lane detection unit (e.g., using a high-precision map) is used only for accurate positioning, the lane line information may not be output in some places due to the factors of positioning accuracy and map updating frequency. The lane detection unit further acquires image information acquired by the camera, and transmits second lane line information and second lane line confidence obtained by processing image data (for example, performing lane line recognition on an image acquired by the camera) to the LKA electronic control unit.
The LKA electronic control unit selects corresponding lane line information (first lane line information or second lane line information) to process on the basis of the acquired first lane line confidence degree and second lane line confidence degree, and further obtains steering data; the LKA electronic control unit transmits Steering data to an Electric Power Steering (EPS) to perform lateral control of the vehicle.
The confidence degree can refer to the credibility of the collected lane line, the credibility is high if the lane line is clear and continuous, and the credibility of the lane line collected by the camera can be reduced if the lane line is not clear or the visual field of the camera is blocked by rain and fog weather.
Specifically, the LKA electronic control unit may output the lane line confidence level through a comparison between the high-precision map and the camera, and finally, calculate the required steering data (for example, the magnitude of the turning angle or the torque) in real time according to the lane line track of the vehicle, the distance deviating from the lane line (i.e., the distance between the vehicle and the lane line), the yaw rate of the vehicle, and other information by using the lane line information with the high confidence level; and then the steering data to be controlled is sent to an Electric Power Steering (EPS) system for transverse control. The Distance between the vehicle and the lane line may refer to a Distance between a wheel and the lane line, that is, a Distance to lane crossing (DLC) Distance or a Distance to a lane, and may be obtained by processing an algorithm described in an existing standard.
According to the lane line information that the automatically controlled unit of LKA fuses current location position and camera and provides in this application, solve traditional lane keeping auxiliary system (LKA) scene and restrict the problem, the camera probably can't detect the lane line when perhaps not clear night or lane line, lead to triggering failure, and frequent withdraw from and get into of LKA function, and then enlarge LKA's in-service use scene and flexibility.
For example, when the camera cannot provide lane line information (that is, the confidence of the second lane line is too low, or the camera fails), the LKA electronic control unit may acquire the lane line information according to the positioning position of the vehicle; when the vehicle cannot provide lane line information according to the positioning information (namely the confidence coefficient of the first lane line is too low, or a high-precision map, a local positioning device and the like fail), the LKA electric control unit uses the camera to provide the lane line information for control; when the positioning position and the camera can provide lane line information, the LKA is controlled according to the lane line information with high confidence coefficient.
In a specific embodiment, the LKA electronic control unit instructs the vehicle to close the LKA when the first lane line confidence and the second lane line confidence both fall into the preset failure interval.
Specifically, the LKA electric control unit can arrange to quit the LKA function when the positioning position and the camera cannot provide lane line information; the lane keeping auxiliary system (LKA) does not need to be limited to the sensing performance of a certain sensor, and the problem that the LKA function frequently exits and enters can be solved even if the lane line possibly cannot be detected when a camera is encountered at night or the lane line is unclear.
In the above way, the problem of limited scenes caused by lane lines output based on the traditional technology is solved, and the lane lines can be well detected under the conditions of unclear lane lines, special illumination conditions, fog and frost on vehicle windows and camera fault conditions by fusing the cameras and local positioning, so that the scenes used by the LKA are enlarged; the method and the device can cover more scenes and improve the usable range of the LKA.
In one embodiment, as shown in fig. 2, there is provided a lane keeping apparatus including a lane detecting unit 210 and a LKA electric control unit 220;
the lane detection unit 210 acquires the current geographic position of the vehicle when the LKA of the vehicle is started, outputs lane information at the current geographic position of the vehicle in the high-precision map as first lane line information, performs reliability check on the first lane line information, and outputs a first lane line confidence;
the lane detection unit 210 receives image data acquired by a vehicle camera, performs lane recognition on the image data, outputs second lane line information, performs reliability inspection on the second lane line information, and outputs second lane line confidence;
the LKA electronic control unit 220 selects the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmits the steering data to the electric power steering system to perform lateral control of the vehicle.
In one particular embodiment, LKA electronic control unit 220 includes a processing module 222 and a LKA control module 224;
the processing module 222 compares the first lane line confidence level and the second lane line confidence level; the processing module determines steering data according to the current power data of the vehicle and the second lane line information when the confidence coefficient of the first lane line is smaller than or equal to the confidence coefficient of the second lane line; when the confidence coefficient of the first lane line is larger than that of the second lane line, determining steering data according to the current power data of the vehicle and the information of the first lane line; the vehicle current power data includes wheel speeds;
the processing module 222 transmits the steering data to the LKA control module 224;
the LKA control module 224 transmits the steering data to the electric power steering system.
Specifically, the LKA electronic control unit may include a processing module (for implementing a real-time computing function) and an LKA control module; the LKA control module can perform information interaction with the electric power steering system, and further perform transverse control. The LKA electric control unit may be an independent electric control unit in the vehicle, or may be a control unit having a corresponding function extended based on the existing LKA system.
The processing module of the present application may compare the first lane line confidence a1 with the second lane line confidence a2, and adopt the first lane line information when a1> a2, adopt the second lane line information output by the camera when a1 < a2, and adopt the second lane line information output by the camera when a1 is a 2. Further, the processing module obtains data such as a lane line track, a lane line deviation distance, a vehicle yaw rate and the like of the vehicle according to the positioned vehicle position or information (namely lane line information) such as a current lane line deviation distance and a finished vehicle attitude acquired by the camera, and then obtains the size of a required corner or torque (namely steering data) through real-time calculation. In a specific example, the processing module may further obtain current dynamic data of the vehicle, for example, vehicle dynamic information transmitted by wheel speed sensors such as vehicle wheel rotation speed, wheel acceleration, and the like; then, data such as steering wheel turning angle, current steering torque of a driver and the like are obtained; and further obtains steering data (steering angle or torque) based on the current power data of the vehicle and the lane line information.
As shown in fig. 3, in a specific embodiment, the lane detection unit may include a high-precision map module and a camera detection module;
the high-precision map module is used for positioning the vehicle to obtain the current geographic position of the vehicle, and inquiring in the high-precision map according to the current geographic position of the vehicle to obtain first lane line information; the high-precision map module carries out lane line definition and continuity detection on the first lane line information and outputs a first lane line confidence coefficient;
the camera detection module receives image data; the camera detection module processes the image data by adopting a corresponding lane line detection algorithm and outputs second lane line information; the camera detection module detects the definition and continuity of the lane line of the second lane line information and outputs a confidence coefficient of the second lane line.
Specifically, the lane detection unit may include a high-precision map module and a camera detection module, that is, the application of the present application to a high-precision map and a camera is taken as an example; the processing module of the application can compare the first lane line confidence a1 with the second lane line confidence a2, and adopt the lane line information output by a high-precision map when a1> a2, adopt the lane line information output by a camera when a1 < a2, and adopt the lane line information output by a camera when a1 is a 2.
Further, when the high-precision map module fails, making the lane line confidence a1 equal to 0; when the camera is blind, making the confidence coefficient a2 be 0; in a specific example, the value ranges of a1 and a2 can be (0, 1). The preset failure interval in the application can be set according to actual conditions.
It should be noted that the failure of the high-precision map module indicates that the high-precision map has a fault, and the lane line information output by the high-precision map module may be wrong, so that the reference significance is not great. Similarly, when the camera is blind, the lane line information output by the camera may be wrong. For the confidence, the confidence can be defined as three levels of low, medium and high, and in practical application, when the confidence reaches the corresponding level, the corresponding lane line information is adopted to calculate the steering data. Meanwhile, the image data can be processed by adopting the existing lane line detection algorithm, so that lane lines can be identified and classified.
The following description is provided with reference to a specific example, the present application may include 3 modules, a lane detection module (i.e., a lane detection unit), a real-time calculation module (i.e., a processing module), and an LKA control module, and a workflow of the present application may be as shown in fig. 4:
a) starting LKA by the vehicle;
b) a lane detection module: the high-precision map outputs lane line and lane line confidence a1 information according to the accurate geographic position of the vehicle, and the camera acquires the lane line and confidence a2 information;
c) the real-time calculation module outputs the lane line confidence degree through comparing a high-precision map and a camera, and finally calculates the required turn angle or torque in real time according to the lane line track of the vehicle, the distance of the lane line deviated, the yaw rate of the vehicle and other information by adopting the lane line information with the high confidence degree;
d) and the LKA control module sends the rotation angle or the torque required to be controlled to an Electric Power Steering (EPS) for transverse control.
Wherein, the lane detection module can contain two parts: and detecting a high-precision map and a camera, wherein the high-precision map is an independent electric control unit, and the camera is used for detecting. The real-time calculation module and the LKA control module can belong to an LKA electric control unit.
Further, in step b), when the high-precision map module fails, the lane line confidence a1 is 0, when the camera is blind, the confidence a2 is 0, and the value ranges of a1 and a2 may be (0, 1).
And in step c), the lane line information output by the high-precision map is adopted when a1> a2, the lane line information output by the camera is adopted when a1 < a2, and the lane line information output by the camera is adopted when a1 is equal to a 2.
The improvement of the method is that the lane lines are output by using a high-precision map, the road surface is shot by using a camera, the lane lines are identified, the confidence degrees of the lane lines are output respectively, and then the final lane line is selected according to the relation between the confidence degrees of the lane lines and the confidence degrees of the lane lines so as to be used for lane keeping.
It should be noted that all or part of the modules in the lane keeping device may be implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent of a processor in an automobile or corresponding equipment, and can also be stored in a memory in the corresponding equipment in a software form, so that the processor can call and execute the corresponding operation of each module.
In the above way, the method and the device fuse the current positioning position and the lane line information provided by the camera, and when the camera cannot provide the lane line information, the lane line information is obtained according to the positioning position of the vehicle; when the vehicle cannot provide lane line information according to the positioning information, the LKA using the lane keeping device can provide the lane line information through the camera for control; when the positioning position and the camera can provide lane line information, the LKA using the lane keeping device is controlled according to the lane line information with high confidence coefficient, and the LKA function can exit only when the lane line information cannot be provided according to the positioning position and the camera; the problem of traditional lane keeping auxiliary system (LKA) scene limited is solved in this application, the camera probably can't detect the lane line when perhaps not clear night or lane line, leads to the triggering fault of LKA function and frequently withdraws from and get into, and then enlarges LKA's in-service use scene and flexibility.
In one embodiment, as shown in fig. 5, a lane keeping method is provided, which is applied to an intelligent driving assistance system, and in particular, an LKA electronic control unit applied to a lane keeping device as an example, and may include the following steps:
step S510, receiving first lane line information and first lane line confidence transmitted by a lane detection unit; the first lane line information is obtained by processing the current geographic position of the vehicle according to a high-precision map by a lane detection unit; the first lane line confidence coefficient is obtained by checking the reliability of the first lane line information through a lane detection unit;
step S520, receiving second lane line information and second lane line confidence transmitted by the lane detection unit; the second lane line information is obtained by carrying out lane identification on image data acquired by a vehicle camera through a lane detection unit; the second lane line confidence coefficient is obtained by the reliability inspection of the second lane line information through a lane detection unit;
step S530, based on the first lane line confidence degree and the second lane line confidence degree, selecting the first lane line information or the second lane line information to determine steering data, and transmitting the steering data to the electric power steering system; the steering data is used to instruct the electric power steering system to perform lateral control of the vehicle.
In one embodiment, the step of selecting the first lane line information or the second lane line information to determine the steering data based on the first lane line confidence and the second lane line confidence includes:
comparing the confidence of the first lane line with the confidence of the second lane line;
when the confidence coefficient of the first lane line is greater than that of the second lane line, determining steering data according to the current power data of the vehicle and the information of the first lane line;
and when the confidence coefficient of the first lane line is smaller than or equal to the confidence coefficient of the second lane line, determining steering data according to the current dynamic data of the vehicle and the information of the second lane line.
In one particular embodiment, the steering data is a turn angle; further comprising the steps of: acquiring current power data of a vehicle;
the step of selecting the first lane line information or the second lane line information to determine the steering data comprises the following steps:
analyzing and processing the current dynamic data of the vehicle and the information of a first lane line or the current dynamic data of the vehicle and the information of a second lane line to obtain a track of the vehicle lane line, a distance of a lane line deviated from and a yaw rate of the vehicle;
and outputting the size of the turning angle according to the lane line track of the vehicle, the distance of the lane line to be deviated and the yaw rate of the vehicle.
In one embodiment, the method further comprises the steps of:
outputting an LKA exiting instruction when the first lane line confidence coefficient and the second lane line confidence coefficient both fall into a preset failure interval; the exit LKA command is used to instruct the vehicle to shut down the LKA.
It should be noted that, for the specific definition of the lane keeping method, reference may be made to the definition of the lane keeping device in the above, and details are not described here.
According to the lane keeping method, the current positioning position and the lane line information provided by the camera can be fused, and when the camera cannot provide the lane line information, the lane line information is obtained according to the positioning position of the vehicle; when the vehicle cannot provide lane line information according to the positioning information, the LKA provides the lane line information by using the camera for control; when the positioning position and the camera can provide lane line information, the LKA is controlled according to the lane line information with higher confidence coefficient, and the LKA function can be quitted only when the positioning position and the camera cannot provide the lane line information; the problem of traditional lane keeping auxiliary system (LKA) scene limited is solved in this application, the camera probably can't detect the lane line when perhaps not clear night or lane line, leads to the triggering fault of LKA function and frequently withdraws from and get into, and then enlarges LKA's in-service use scene and flexibility.
It should be understood that, although the steps in the flowcharts of fig. 4 and 5 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 4 and 5 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, a lane keeping system is provided, the internal structure of which can be shown in fig. 6, and comprises a vehicle camera, an electric power steering system, and any one of the lane keeping devices;
the lane keeping device is connected between the vehicle camera and the electric power steering system.
Specifically, the lane keeping apparatus may include a lane detection unit and an LKA electronic control unit; the lane detection unit is used for being connected with a vehicle camera, and the LKA electric control unit is used for being connected with the electric power steering system.
Those skilled in the art will appreciate that the configuration shown in fig. 6 is a block diagram of only a portion of the configuration associated with the subject application and is not intended to limit the devices or products to which the subject application may be applied, and that a particular device or product may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Further, as shown in fig. 7, in one embodiment, the present application provides an automobile including the lane keeping system described above.
The lane keeping system comprises a vehicle camera, an electric power steering system and a lane keeping device connected between the vehicle camera and the electric power steering system.
Specifically, the lane keeping apparatus may include a lane detection unit and an LKA electronic control unit; the lane detection unit is used for being connected with a vehicle camera, and the LKA electric control unit is used for being connected with the electric power steering system.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A lane keeping device is characterized by comprising a lane detection unit and an LKA electric control unit;
the lane detection unit acquires the current geographic position of the vehicle when the LKA is started by the vehicle, outputs lane information at the current geographic position of the vehicle in a high-precision map as first lane line information, performs reliability detection on the first lane line information, and outputs first lane line confidence;
the lane detection unit receives image data acquired by a vehicle camera, performs lane recognition on the image data, outputs second lane line information, performs reliability inspection on the second lane line information, and outputs second lane line confidence;
and the LKA electric control unit selects the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmits the steering data to an electric power steering system to perform transverse control on the vehicle.
2. The lane keeping apparatus of claim 1, wherein the LKA electronic control unit comprises a processing module and an LKA control module;
the processing module compares the first lane line confidence level and the second lane line confidence level; the processing module determines the steering data according to current vehicle power data and the second lane line information when the first lane line confidence is less than or equal to the second lane line confidence; when the confidence coefficient of the first lane line is larger than that of the second lane line, determining the steering data according to the current dynamic data of the vehicle and the information of the first lane line; the vehicle current power data comprises wheel speeds;
the processing module transmits the steering data to the LKA control module;
and the LKA control module transmits the steering data to the electric power steering system.
3. The lane keeping apparatus of claim 1, wherein the lane detection unit includes a high-precision map module and a camera detection module;
the high-precision map module is used for positioning a vehicle to obtain the current geographic position of the vehicle, and inquiring in the high-precision map according to the current geographic position of the vehicle to obtain the first lane line information; the high-precision map module carries out lane line definition and continuity detection on the first lane line information and outputs a first lane line confidence coefficient;
the camera detection module receives the image data; the camera detection module processes the image data by adopting a corresponding lane line detection algorithm and outputs second lane line information; and the camera detection module detects the definition and continuity of the lane line of the second lane line information and outputs the confidence of the second lane line.
4. Lane keeping apparatus according to any one of claims 1 to 3,
and the LKA electric control unit indicates the vehicle to close the LKA when the first lane line confidence coefficient and the second lane line confidence coefficient both fall into a preset failure interval.
5. A lane keeping method, characterized by comprising the steps of:
receiving first lane line information and first lane line confidence transmitted by a lane detection unit; the first lane line information is obtained by processing the current geographic position of a vehicle through the lane detection unit according to a high-precision map; the first lane line confidence is obtained by performing confidence test on the first lane line information through the lane detection unit;
receiving second lane line information and second lane line confidence transmitted by the lane detection unit; the second lane line information is obtained by carrying out lane identification on image data acquired by a vehicle camera through the lane detection unit; the second lane line confidence coefficient is obtained by performing confidence test on the second lane line information through the lane detection unit;
selecting the first lane line information or the second lane line information to determine steering data based on the first lane line confidence degree and the second lane line confidence degree, and transmitting the steering data to an electric power steering system; the steering data is used to instruct the electric power steering system to perform lateral control of the vehicle.
6. The lane keeping method of claim 5, wherein the step of selecting the first lane line information or the second lane line information to determine steering data based on the first lane line confidence and the second lane line confidence comprises:
comparing the first lane line confidence level with the second lane line confidence level;
when the confidence coefficient of the first lane line is larger than that of the second lane line, determining the steering data according to the current dynamic data of the vehicle and the information of the first lane line; the vehicle current power data comprises wheel speeds;
and when the confidence coefficient of the first lane line is smaller than or equal to the confidence coefficient of the second lane line, determining the steering data according to the current dynamic data of the vehicle and the information of the second lane line.
7. The lane keeping method according to claim 5, wherein the steering data is a turning angle; further comprising the steps of: acquiring current power data of a vehicle; the vehicle current power data comprises wheel speeds;
the step of selecting the first lane line information or the second lane line information to determine steering data comprises the following steps:
analyzing and processing the current dynamic data of the vehicle and the first lane line information or the current dynamic data of the vehicle and the second lane line information to obtain a vehicle lane line track, a lane line deviation distance and a vehicle yaw rate;
and outputting the size of the corner according to the vehicle lane line track, the lane line deviation distance and the vehicle yaw rate.
8. The lane keeping method according to any one of claims 5 to 7, further comprising the steps of:
outputting an LKA exiting instruction when the first lane line confidence coefficient and the second lane line confidence coefficient both fall into a preset failure interval; the LKA exit instruction is used to instruct the vehicle to shut down the LKA.
9. A lane keeping system comprising a vehicle camera, an electric power steering system, and a lane keeping apparatus according to any one of claims 1 to 4;
the lane keeping device is connected between the vehicle camera and the electric power steering system.
10. An automobile comprising the lane keeping system of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910524356.8A CN112172810A (en) | 2019-06-18 | 2019-06-18 | Lane keeping device, method and system and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910524356.8A CN112172810A (en) | 2019-06-18 | 2019-06-18 | Lane keeping device, method and system and automobile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112172810A true CN112172810A (en) | 2021-01-05 |
Family
ID=73914381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910524356.8A Pending CN112172810A (en) | 2019-06-18 | 2019-06-18 | Lane keeping device, method and system and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112172810A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114347991A (en) * | 2022-02-07 | 2022-04-15 | 中国第一汽车股份有限公司 | Automatic lane changing method and device for vehicle, storage medium and vehicle |
| CN114379552A (en) * | 2021-11-11 | 2022-04-22 | 重庆大学 | Self-adaptive lane keeping control system and method based on high-precision map and vehicle-mounted sensor |
| CN115352455A (en) * | 2022-10-19 | 2022-11-18 | 福思(杭州)智能科技有限公司 | Road characteristic prediction method and device, storage medium and electronic device |
| WO2023017625A1 (en) * | 2021-08-11 | 2023-02-16 | Hitachi Astemo, Ltd. | Drive device, vehicle, and method for automated driving and/or assisted driving |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577682A (en) * | 2012-07-30 | 2014-02-12 | 通用汽车环球科技运作有限责任公司 | Anchor lane selection method using navigation input in road change scenarios |
| CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
| CN104240536A (en) * | 2013-06-20 | 2014-12-24 | 福特全球技术公司 | Lane monitoring method with electronic horizon |
| CN106476883A (en) * | 2015-09-02 | 2017-03-08 | 富士重工业株式会社 | The travel controlling system of vehicle |
| GB2556427A (en) * | 2016-10-06 | 2018-05-30 | Ford Global Tech Llc | Vehicle with environmental context analysis |
| CN108303103A (en) * | 2017-02-07 | 2018-07-20 | 腾讯科技（深圳）有限公司 | The determination method and apparatus in target track |
| CN109724615A (en) * | 2019-02-28 | 2019-05-07 | 北京经纬恒润科技有限公司 | A kind of method of calibration and system of Lane detection result |
-
2019
- 2019-06-18 CN CN201910524356.8A patent/CN112172810A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577682A (en) * | 2012-07-30 | 2014-02-12 | 通用汽车环球科技运作有限责任公司 | Anchor lane selection method using navigation input in road change scenarios |
| CN104240536A (en) * | 2013-06-20 | 2014-12-24 | 福特全球技术公司 | Lane monitoring method with electronic horizon |
| CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
| CN106476883A (en) * | 2015-09-02 | 2017-03-08 | 富士重工业株式会社 | The travel controlling system of vehicle |
| GB2556427A (en) * | 2016-10-06 | 2018-05-30 | Ford Global Tech Llc | Vehicle with environmental context analysis |
| CN108303103A (en) * | 2017-02-07 | 2018-07-20 | 腾讯科技（深圳）有限公司 | The determination method and apparatus in target track |
| CN109724615A (en) * | 2019-02-28 | 2019-05-07 | 北京经纬恒润科技有限公司 | A kind of method of calibration and system of Lane detection result |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023017625A1 (en) * | 2021-08-11 | 2023-02-16 | Hitachi Astemo, Ltd. | Drive device, vehicle, and method for automated driving and/or assisted driving |
| CN114379552A (en) * | 2021-11-11 | 2022-04-22 | 重庆大学 | Self-adaptive lane keeping control system and method based on high-precision map and vehicle-mounted sensor |
| CN114379552B (en) * | 2021-11-11 | 2024-03-26 | 重庆大学 | Self-adaptive lane keeping control system and method based on high-precision map and vehicle-mounted sensor |
| CN114347991A (en) * | 2022-02-07 | 2022-04-15 | 中国第一汽车股份有限公司 | Automatic lane changing method and device for vehicle, storage medium and vehicle |
| CN115352455A (en) * | 2022-10-19 | 2022-11-18 | 福思(杭州)智能科技有限公司 | Road characteristic prediction method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112172810A (en) | Lane keeping device, method and system and automobile | |
| Goldbeck et al. | Lane detection and tracking by video sensors | |
| CN107567412B (en) | Object position measurement using vehicle motion data with automotive camera | |
| KR102026685B1 (en) | Apparatus and server for providing dangerous road information using image data and vibration | |
| EP1383099B1 (en) | Image navigation device | |
| US11740093B2 (en) | Lane marking localization and fusion | |
| US20190347808A1 (en) | Monocular Visual Odometry: Speed And Yaw Rate Of Vehicle From Rear-View Camera | |
| CN112349144B (en) | Monocular vision-based vehicle collision early warning method and system | |
| EP1256784A2 (en) | Car navigation apparatus capable of determining entry into parking area | |
| KR20160051993A (en) | Apparatus for driver assistance | |
| US20180037162A1 (en) | Driver assistance system | |
| EP3530521B1 (en) | Driver assistance method and apparatus | |
| US10351144B2 (en) | Sightline estimation system and sightline estimation method | |
| US10996469B2 (en) | Method and apparatus for providing driving information of vehicle, and recording medium | |
| US20210394782A1 (en) | In-vehicle processing apparatus | |
| CN104990558A (en) | Vehicle navigation method and system | |
| CN112092809A (en) | Auxiliary reversing method, device and system and vehicle | |
| CN108107897A (en) | Real time sensor control method and device | |
| CN111152792A (en) | Device and method for determining the level of attention demand of a vehicle driver | |
| KR102552712B1 (en) | System for estimating a vehicle location and method for estimating the vehicle location using the system | |
| CN112833889A (en) | Vehicle positioning method and device | |
| WO2023108364A1 (en) | Method and apparatus for detecting driver state, and storage medium | |
| KR20190125012A (en) | Traffic sign recognition system and method reflecting conditional speed limit | |
| CN111824170B (en) | Method, system, device and electronic equipment for obtaining vehicle performance information | |
| KR101578434B1 (en) | Apparatus for detecting lane and method thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210105 |