CN112706785B - Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium - Google Patents
Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium Download PDFInfo
- Publication number
- CN112706785B CN112706785B CN202110129398.9A CN202110129398A CN112706785B CN 112706785 B CN112706785 B CN 112706785B CN 202110129398 A CN202110129398 A CN 202110129398A CN 112706785 B CN112706785 B CN 112706785B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- boundary
- model
- lane line
- track
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a device and a machine-readable storage medium for selecting an environment cognitive target of an automatic driving vehicle, wherein the method comprises the following steps of 1, acquiring perception information and vehicle information from a vehicle perception interface; 2, establishing a boundary line model for the driving environment according to the perception information and the vehicle information; 3, establishing a boundary line arbitration module and selecting an optimal boundary line model of the current scene; and 4, sequentially placing the targets into the corresponding lanes according to the optimal boundary line model, and filtering the targets exceeding the boundary line. According to the method, a plurality of models are established for the running environment of the automatic driving vehicle by collecting information data of the sensor and the vehicle, targets in a running road are selected, accurate and effective information is provided for planning the track of the automatic driving vehicle, and the problems of robustness, adaptability and the like of target selection in the prior art are partially solved.
Description
Technical Field
The invention belongs to the field of intelligent driving of automobiles, and particularly relates to an environment cognitive target selection method.
Background
The automatic vehicle driving system mainly comprises an environment perception fusion module, an environment cognition module and a planning control module. The automatic vehicle driving system firstly needs to receive information from environment perception fusion, such as target information, lane line information, traffic sign information and the like; then, a series of processing is carried out on the environment perception information to obtain accurate information required by the planning control module, so that the planning control module can safely and effectively control the motion of the vehicle.
In the context awareness module, target selection is crucial, and the prior art adopts various methods to implement. For example, in "threat degree calculation method in autonomous driving, target selection method, and application" disclosed in chinese patent document CN201710420037.3, the target threat degree is calculated from the lateral and vertical position and speed of the target, and the target is selected. In the method and the device for selecting the forward target and the vehicle-mounted equipment disclosed in the chinese patent document CN201911111390.9, a forward target selection model is trained by an ensemble learning method, and the forward target is determined by combining real-time sensing data. In the actual application process of the automatic driving vehicle, the methods have more problems, such as inaccurate transverse and longitudinal positions and speed of the target directly influence the calculation result of the threat degree, and result in wrong target selection result; the ensemble learning method for training the forward target selection model is a method for classifying the forward targets, depends heavily on the quality of training data, and is easy to generate an overfitting phenomenon.
Disclosure of Invention
The invention provides a method, a device and a machine-readable storage medium for selecting an environment cognition target of an automatic driving vehicle, aiming at the defects in the prior art, and the method, the device and the machine-readable storage medium are used for at least partially solving the problems of robustness, adaptability and the like of target selection in an environment cognition module of the automatic driving vehicle in the background technology.
The technical scheme adopted by the invention for solving the technical problems is as follows:
an autonomous vehicle context aware target selection method comprising the steps of:
step 1: acquiring perception information and vehicle information from a vehicle perception interface;
step 2: establishing a boundary line model for the driving environment according to the perception information and the vehicle information;
and step 3: establishing a boundary line arbitration module and selecting an optimal boundary line model of the current scene;
and 4, step 4: and sequentially placing the targets into the corresponding lanes according to the optimal boundary line model, and filtering the targets exceeding the boundary line.
Further, the perception information comprises target information, lane line information and positioning information which are obtained by an automatic driving sensor; the vehicle information includes a vehicle yaw acceleration, a vehicle steering wheel angle, and a vehicle speed scalar.
The boundary line model includes a lane line boundary model, a vehicle trajectory prediction boundary model, and a vehicle track boundary model, the lane line boundary model is generated according to the lane line information, and a vehicle trajectory prediction cubic curve and a vehicle track cubic curve are calculated according to the vehicle yaw rate, the steering wheel angle, and the vehicle speed scalar, so that the vehicle trajectory prediction boundary model and the vehicle track boundary model are generated.
Further, the method for generating the boundary line model comprises the following steps:
step 2.1, obtaining an identifier whether the lane line is valid or not according to the comparison of the lengths of the left lane line and the right lane line with a threshold, namely, when the lengths of the left lane line and the right lane line are simultaneously larger than the threshold, the lane line is valid, otherwise, the lane line is invalid, and generating a lane line boundary model;
step 2.2, setting a low-speed threshold and a high-speed threshold of the speed of the vehicle, and calculating the turning radius R1 of the vehicle by using the yaw angular velocity of the vehicle and the speed of the vehicle when the speed of the vehicle is greater than the high-speed threshold; when the speed of the vehicle is lower than a low speed threshold value, the turning radius R3 of the vehicle is calculated by using the turning angle of a steering wheel; when the speed of the vehicle is between a low-speed threshold value and a high-speed threshold value, carrying out weighted average associated with the speed on the R1 and the R3 to obtain the turning radius R2 of the vehicle;
step 2.3, according to the current turning radius of the vehicle, namely the predicted track, taking more than 3 points on the track, and fitting to obtain a vehicle track predicted cubic curve, thereby generating a vehicle track predicted boundary model;
and 2.4, calculating historical track points of the running of the vehicle according to the speed and the yaw rate of the vehicle, fitting the historical track points into a cubic curve by using a least square method to obtain the cubic curve of the track of the vehicle, and generating a boundary model of the track of the vehicle.
Further, the step 3 comprises:
step 3.1, calculating whether the boundary model of the front lane line is effective, if so, using the boundary model of the front lane line as a boundary of target selection, and if not, using the vehicle track to predict cubic curve translation to generate curves (left, right, left, right lane lines) of 4 lane lines in front, wherein the finally formed lanes comprise a local lane, a left lane and a right lane;
step 3.2, calculating whether the boundary model of the lane line at the rear part is effective or not, wherein the calculation method is the same as that of the lane line at the front part; and finally, obtaining the front and rear boundary models of the vehicle.
Further, in the step 4, objects exceeding the boundary line are filtered, the boundary line comprises a left boundary line, a right boundary line, a left boundary line, a right boundary line and a right boundary line, the objects exceeding the boundary line are deleted, and the objects in the boundary line are selected into the correct lane.
Compared with the prior art, the method for selecting the environment cognitive target of the automatic driving vehicle has the following advantages:
1. according to the method, the information data of the sensor and the vehicle are collected, a plurality of models are established for the driving environment of the automatic driving vehicle, the target in the driving road is selected, and the provided information is more accurate and effective.
2. The method considers the prediction of the vehicle track and the historical track information, can select the target even when the lane line information is lost, and increases the system adaptability.
3. According to the method, the relative position relation between the boundary line and the target is calculated, and the target is placed in the corresponding lane, so that the transverse position fluctuation of the target has a certain influence on target selection, and the influence of the longitudinal position fluctuation on the target selection is reduced, so that the robustness of the system is improved.
Another object of the present invention is to propose a fusion device for environmental targets that at least partially solves the technical problems mentioned in the background.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
an autonomous vehicle context awareness target selection device, the device comprising a memory and a processor, the memory having stored therein instructions for enabling the processor to execute the aforementioned target selection method for autonomous vehicle context awareness.
Compared with the prior art, the environment cognition target selection device of the automatic driving vehicle and the target selection method for environment cognition of the automatic driving vehicle have the same advantages, and the description is omitted.
Accordingly, embodiments of the present invention also provide a machine-readable storage medium having instructions stored thereon for enabling a machine to perform the above-described target selection method for autonomous vehicle environment recognition.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 illustrates a flow diagram of a method of context aware target selection according to an embodiment of the present invention;
FIG. 2 illustrates a boundary line model generation flow diagram according to an embodiment of the invention;
FIG. 3 illustrates a borderline arbitration flow diagram according to an embodiment of the present invention;
FIG. 4 illustrates a target selection diagram according to an embodiment of the invention.
Detailed Description
The invention is further described with reference to the accompanying drawings in which:
the "sensor" mentioned in the embodiments of the present invention may refer to any type of device arranged on a vehicle for environmental awareness, and may be, for example, a camera, a laser radar, a millimeter wave radar, or the like. Reference to a "target" or "environmental target" in embodiments of the present invention may refer to any object, moving or stationary, in front of, behind, or to the side of a vehicle, such as a vehicle, a person, a building, or the like.
One embodiment of the invention is shown in fig. 1, which shows a process of target selection in an environment awareness module, and an environment awareness target selection method includes:
firstly, acquiring sensor information including target information, lane line information, positioning information and the like from a sensing interface; and the vehicle state information including a vehicle yaw rate, a steering wheel angle, a vehicle speed scalar and the like.
And secondly, generating a lane line boundary model according to the lane line information, and calculating a vehicle track prediction cubic curve and a vehicle track cubic curve according to the yaw velocity of the vehicle, the steering wheel angle and the vehicle speed scalar so as to generate a vehicle track prediction boundary model and a vehicle track boundary model.
And thirdly, arbitrating the generated boundary model to select an optimal boundary model.
And fourthly, placing the target into the corresponding lane according to the boundary model, filtering out the target exceeding the range of the lane, and selecting the target in the boundary line into the correct lane.
And fifthly, writing the result of the target selection into a cognitive interface for planning control.
FIG. 2 illustrates a boundary line model generation flow according to an embodiment of the invention, as shown in FIG. 2: the boundary line model generation is to calculate whether the lane line is effective according to the lane line information, calculate the vehicle track prediction cubic curve and the vehicle track cubic curve according to the vehicle yaw velocity, the vehicle speed and the steering wheel information, and specifically comprises the following steps:
1) And comparing the lengths of the left lane line and the right lane line with a threshold (such as the threshold is 5 meters and 10 meters, and the threshold is an empirical value) to obtain an identifier whether the lane line is valid. That is, when the lengths of the left lane line and the right lane line are both greater than the threshold value, the lane line is valid, otherwise, the lane line is invalid.
2) Setting a low-speed threshold value and a high-speed threshold value of the speed of the vehicle, and calculating the turning radius R1 of the vehicle by using the yaw velocity and the speed of the vehicle when the speed of the vehicle is greater than the high-speed threshold value; when the speed of the vehicle is between a low-speed threshold value and a high-speed threshold value, calculating a turning radius R3 by using a steering wheel corner, and then carrying out weighted average associated with the speed on R1 and R3 to obtain a turning radius R2 of the vehicle; when the vehicle speed is lower than the low speed threshold, R3 is directly used.
3) And (3) predicting a track according to the current turning radius of the vehicle, namely R1, R2 or R3, taking more than 3 points on the track, and fitting a vehicle track prediction cubic curve.
4) And calculating the historical track points of the running of the vehicle according to the speed and the yaw rate of the vehicle, and fitting the historical track points into a cubic curve by using a least square method to obtain the cubic curve of the track of the vehicle.
FIG. 3 illustrates a borderline arbitration flow according to an embodiment of the invention, FIG. 3 illustrates:
firstly, calculating whether a front lane line boundary model is valid or not, if the front lane line boundary model is valid, using the front lane line boundary model as a boundary for target selection, and if the front lane line boundary model is invalid, using the vehicle track prediction cubic curve translation to generate curves (left, right, left, right lane lines) of front 4 lane lines, wherein finally formed lanes comprise a local lane, a left lane and a right lane.
And secondly, calculating whether the boundary model of the lane line at the rear part is effective or not, wherein the calculation method is the same as that of the lane line at the front part. And finally, obtaining the front and rear boundary models of the vehicle.
Namely the front: when the lane line is effective, a lane line boundary model is used, otherwise, a track prediction model is used. Rear: when the lane line boundary model is effective, the lane line boundary model is used, otherwise, the vehicle track boundary model is used.
Fig. 3 shows a target selection step according to an embodiment of the present invention, as shown in fig. 4, ego is the host vehicle, the vehicle targets around the host vehicle are input information of the sensors, and the target selection only considers the targets acting on the keys for the driving decision of the host vehicle, i.e. the targets in the host vehicle lane, the left lane and the right lane. The boundary lines comprise left, right, left, right and right boundary lines, the targets exceeding the boundary lines are deleted, and the targets in the boundary lines are selected into the correct lane.
Accordingly, embodiments of the present invention also provide a machine-readable storage medium having instructions stored thereon for enabling a machine to perform the above-described target selection method for autonomous vehicle environment awareness. The machine-readable storage medium may be, for example, a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or various other media capable of storing program codes.
Further, an embodiment of the present invention further provides a target selection apparatus for environment awareness of an autonomous vehicle, where the apparatus may include a memory and a processor, and the memory may store instructions that enable the processor to execute a target selection method for environment awareness of an autonomous vehicle according to any of the embodiments of the present invention.
The processor may be a Central Processing Unit (CPU), but may also be other general purpose processors, digital signal processors (dsps), application specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like.
The memory may be used to store the computer program instructions and the processor may implement the various functions of the data fusion device for vehicle sensors by executing or executing the computer program instructions stored in the memory and invoking the data stored in the memory. The memory may include high speed random access memory and may also include non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) card, a flash memory card, at least one magnetic disk storage device, a flash memory device, or other volatile solid state storage device.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.
Claims (5)
1. An autonomous vehicle environmental awareness target selection method, comprising the steps of:
step 1: acquiring perception information and vehicle information from a vehicle perception interface; the perception information comprises target information, lane line information and positioning information which are obtained by an automatic driving sensor; the vehicle information comprises vehicle yaw acceleration, vehicle steering wheel turning angle and vehicle speed scalar;
step 2: establishing a boundary line model for the driving environment according to the perception information and the vehicle information; the boundary line model comprises a lane line boundary model, a vehicle track prediction boundary model and a vehicle track boundary model, the lane line boundary model is generated according to lane line information, and a vehicle track prediction cubic curve and a vehicle track cubic curve are calculated according to the yaw velocity, the steering wheel corner and the vehicle speed scalar, so that the vehicle track prediction boundary model and the vehicle track boundary model are generated;
the method for generating the boundary line model comprises the following steps:
step 2.1, obtaining an identifier whether the lane line is valid or not according to the comparison of the lengths of the left lane line and the right lane line with a threshold, namely, when the lengths of the left lane line and the right lane line are simultaneously larger than the threshold, the lane line is valid, otherwise, the lane line is invalid, and generating a lane line boundary model;
step 2.2, setting a low-speed threshold and a high-speed threshold of the speed of the vehicle, and calculating the turning radius R1 of the vehicle by using the yaw angular velocity of the vehicle and the speed of the vehicle when the speed of the vehicle is greater than the high-speed threshold; when the speed of the vehicle is lower than a low-speed threshold value, calculating the turning radius R3 of the vehicle by using the turning angle of a steering wheel; when the speed of the vehicle is between a low-speed threshold value and a high-speed threshold value, carrying out weighted average associated with the speed on the R1 and the R3 to obtain the turning radius R2 of the vehicle;
step 2.3, predicting a track according to the current turning radius of the vehicle, taking more than 3 points on the track, and fitting to obtain a vehicle track prediction cubic curve, thereby generating a vehicle track prediction boundary model;
step 2.4, calculating historical track points of the running of the vehicle according to the speed and the yaw angular velocity of the vehicle, fitting the historical track points into a cubic curve by using a least square method to obtain a cubic curve of the track of the vehicle, and generating a boundary model of the track of the vehicle;
and step 3: establishing a boundary line arbitration module and selecting an optimal boundary line model of the current scene; the method comprises the following steps:
step 3.1, calculating whether the boundary model of the front lane line is effective, if so, using the boundary model of the front lane line as a boundary of target selection, and if not, using the vehicle track to predict cubic curve translation to generate a curve of the front lane line, wherein the finally formed lane comprises a local lane, a left lane and a right lane;
step 3.2, calculating whether the boundary model of the rear lane line is effective or not, wherein the calculation method is the same as that of the front lane line; finally, obtaining a front boundary model and a rear boundary model of the vehicle;
and 4, step 4: and sequentially placing the targets into the corresponding lanes according to the optimal boundary line model, and filtering the targets exceeding the boundary line.
2. The method according to claim 1, wherein in step 3.1, the curve of the front 4 lane lines is generated by predicting three times curve translation by the vehicle trajectory, and the curve comprises left, right, left, right lane lines.
3. The method as claimed in claim 1, wherein the step 4 filters the targets beyond the boundary lines, the boundary lines include left, right, left, right and right boundary lines, the targets beyond the boundary lines are deleted, and the targets within the boundary lines are selected to be in the right lane.
4. An autonomous vehicle environmental awareness target selection apparatus, comprising a memory and a processor, the memory having stored therein instructions for enabling the processor to perform a target selection method for autonomous vehicle environmental awareness in accordance with any of claims 1 to 3.
5. A machine-readable storage medium having stored thereon instructions for enabling a machine to perform the method of target selection for autonomous vehicle context awareness of any of claims 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110129398.9A CN112706785B (en) | 2021-01-29 | 2021-01-29 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110129398.9A CN112706785B (en) | 2021-01-29 | 2021-01-29 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112706785A CN112706785A (en) | 2021-04-27 |
CN112706785B true CN112706785B (en) | 2023-03-28 |
Family
ID=75549846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110129398.9A Active CN112706785B (en) | 2021-01-29 | 2021-01-29 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112706785B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113587940A (en) * | 2021-07-30 | 2021-11-02 | 重庆长安汽车股份有限公司 | Lane line checking method and system based on vehicle turning radius and vehicle |
CN113619606B (en) * | 2021-09-17 | 2024-06-14 | 中国第一汽车股份有限公司 | Obstacle determination method, device, equipment and storage medium |
WO2023092451A1 (en) * | 2021-11-26 | 2023-06-01 | 华为技术有限公司 | Method and apparatus for predicting drivable lane |
CN114475614A (en) * | 2022-03-21 | 2022-05-13 | 中国第一汽车股份有限公司 | Method, device, medium and equipment for screening dangerous targets |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018063517A (en) * | 2016-10-12 | 2018-04-19 | 日産自動車株式会社 | Lane boundary monitoring method and lane boundary monitoring device |
CN109552327A (en) * | 2018-12-18 | 2019-04-02 | 重庆长安汽车股份有限公司 | Promote the system and method for self-adaption cruise system bend performance |
Family Cites Families (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140083723A (en) * | 2012-12-26 | 2014-07-04 | 현대모비스 주식회사 | SCC device and method determining lane of target vehicle applying the same |
US9045144B2 (en) * | 2013-05-09 | 2015-06-02 | Robert Bosch Gmbh | Third-order polynomial-based course prediction for driver assistance functions |
JP6492469B2 (en) * | 2014-09-08 | 2019-04-03 | 株式会社豊田中央研究所 | Own vehicle travel lane estimation device and program |
CN105260699B (en) * | 2015-09-10 | 2018-06-26 | 百度在线网络技术(北京)有限公司 | A kind of processing method and processing device of lane line data |
CN105631217B (en) * | 2015-12-30 | 2018-12-21 | 苏州安智汽车零部件有限公司 | Front effective target selection method based on the adaptive virtual lane of this vehicle |
JP6592423B2 (en) * | 2016-11-25 | 2019-10-16 | 株式会社デンソー | Vehicle control device |
CN106681318A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Vehicle safety control system and method for lane line detection temporary loss in automatic drive |
CN107415951A (en) * | 2017-02-28 | 2017-12-01 | 苏州安智汽车零部件有限公司 | A kind of road curvature method of estimation based on this car motion state and environmental information |
US11127297B2 (en) * | 2017-07-17 | 2021-09-21 | Veoneer Us, Inc. | Traffic environment adaptive thresholds |
US10649458B2 (en) * | 2017-09-07 | 2020-05-12 | Tusimple, Inc. | Data-driven prediction-based system and method for trajectory planning of autonomous vehicles |
JP6643370B2 (en) * | 2018-01-23 | 2020-02-12 | 本田技研工業株式会社 | Driving reference line determination device and automatic driving device |
CN108801286B (en) * | 2018-08-01 | 2021-11-30 | 奇瑞汽车股份有限公司 | Method and device for determining a driving trajectory |
CN109460739A (en) * | 2018-11-13 | 2019-03-12 | 广州小鹏汽车科技有限公司 | Method for detecting lane lines and device |
CN109543636B (en) * | 2018-11-29 | 2020-12-15 | 连尚(新昌)网络科技有限公司 | Method and equipment for detecting sharp curve of road |
KR102540842B1 (en) * | 2018-12-17 | 2023-06-08 | 현대자동차주식회사 | Vehicle, and control method for the same |
US11150664B2 (en) * | 2019-02-01 | 2021-10-19 | Tesla, Inc. | Predicting three-dimensional features for autonomous driving |
CN109583151B (en) * | 2019-02-20 | 2023-07-21 | 阿波罗智能技术(北京)有限公司 | Method and device for predicting running track of vehicle |
CN110162037B (en) * | 2019-04-30 | 2022-07-26 | 惠州市德赛西威智能交通技术研究院有限公司 | Method for predicting track of vehicle |
CN110293970B (en) * | 2019-05-22 | 2020-10-16 | 重庆长安汽车股份有限公司 | Driving control method and device for automatic driving automobile and automobile |
CN110906940B (en) * | 2019-10-26 | 2021-05-18 | 武汉中海庭数据技术有限公司 | Lane sideline aggregation method based on track direction |
CN111209361B (en) * | 2019-12-31 | 2023-06-30 | 深圳安智杰科技有限公司 | Method and device for selecting following target, electronic equipment and readable storage medium |
CN111258323B (en) * | 2020-03-30 | 2021-10-26 | 华南理工大学 | Intelligent vehicle trajectory planning and tracking combined control method |
CN111797701B (en) * | 2020-06-10 | 2024-05-24 | 广东正扬传感科技股份有限公司 | Road obstacle sensing method and system for vehicle multi-sensor fusion system |
-
2021
- 2021-01-29 CN CN202110129398.9A patent/CN112706785B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018063517A (en) * | 2016-10-12 | 2018-04-19 | 日産自動車株式会社 | Lane boundary monitoring method and lane boundary monitoring device |
CN109552327A (en) * | 2018-12-18 | 2019-04-02 | 重庆长安汽车股份有限公司 | Promote the system and method for self-adaption cruise system bend performance |
Non-Patent Citations (1)
Title |
---|
张润生 ; 黄小云 ; 刘晶 ; 马雷 ; 韩睿 ; 赵玉勤 ; 杨新红 ; .基于视觉复杂环境下车辆行驶轨迹预测方法.机械工程学报.2011,(第02期),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN112706785A (en) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112706785B (en) | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium | |
CN112133089B (en) | Vehicle track prediction method, system and device based on surrounding environment and behavior intention | |
CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
CN113267199B (en) | Method and device for planning driving track | |
CN112069944B (en) | Road congestion level determining method | |
US11003928B2 (en) | Using captured video data to identify active turn signals on a vehicle | |
CN108133484B (en) | Automatic driving processing method and device based on scene segmentation and computing equipment | |
CN112967283B (en) | Target identification method, system, equipment and storage medium based on binocular camera | |
CN110929655B (en) | Lane line identification method in driving process, terminal device and storage medium | |
US11436815B2 (en) | Method for limiting object detection area in a mobile system equipped with a rotation sensor or a position sensor with an image sensor, and apparatus for performing the same | |
CN109427191B (en) | Driving detection method and device | |
CN111582189A (en) | Traffic signal lamp identification method and device, vehicle-mounted control terminal and motor vehicle | |
Chao et al. | Multi-lane detection based on deep convolutional neural network | |
CN114419098A (en) | Moving target trajectory prediction method and device based on visual transformation | |
CN114705121B (en) | Vehicle pose measurement method and device, electronic equipment and storage medium | |
CN114802261A (en) | Parking control method, obstacle recognition model training method and device | |
CN114620059B (en) | Automatic driving method, system thereof and computer readable storage medium | |
CN106408593A (en) | Video-based vehicle tracking method and device | |
WO2022006777A1 (en) | Method and system for performing lane-change classification on surrounding moving objects, and computer device and storage medium | |
CN113954836A (en) | Segmented navigation lane changing method and system, computer equipment and storage medium | |
CN115123291B (en) | Behavior prediction method and device based on obstacle recognition | |
CN107452230A (en) | A kind of obstacle detection method, device, terminal device and storage medium | |
CN112465076A (en) | Multi-feature fusion method, device, system and storage medium | |
CN118015047B (en) | Multi-target tracking method, device, equipment and storage medium | |
CN117576926B (en) | Method, device and storage medium for detecting vehicle violations |
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 |