WO2019233081A1 - 一种自动驾驶方法及装置 - Google Patents
一种自动驾驶方法及装置 Download PDFInfo
- Publication number
- WO2019233081A1 WO2019233081A1 PCT/CN2018/121833 CN2018121833W WO2019233081A1 WO 2019233081 A1 WO2019233081 A1 WO 2019233081A1 CN 2018121833 W CN2018121833 W CN 2018121833W WO 2019233081 A1 WO2019233081 A1 WO 2019233081A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- driving
- lane
- time
- current
- Prior art date
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
- 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
Definitions
- the present application relates to the technical field of automobiles, and in particular, to an automatic driving method and device.
- autonomous driving has shown great advantages in terms of safe travel, energy saving and environmental protection. Therefore, autonomous driving is considered to be an effective way to solve traffic congestion, reduce traffic accidents and improve environmental pollution.
- image information of a lane line in front of a current driving lane can be collected in real time, and then a clear image of a lane line is detected from an image collected at the current moment as an effective lane line image.
- the feature points of the lane lines on the left and right sides of the vehicle's current lane can be extracted separately, and then the mathematical expression of the lane line can be determined based on the extracted feature points of each lane line.
- Preset vehicle driving position information in the lane such as setting the vehicle to drive on the center of the lane, planning the driving route of the vehicle, and finally, determining the position to which the vehicle will drive at the next moment according to the planned driving route and a given driving distance , And drive the vehicle to this position.
- the lane line may be unclear or missing.
- the embodiments of the present application provide an automatic driving method and device, which are used to solve the problem that if there are multiple short-term lane lines missing or unclear in the driving lane in the prior art, the number of parking times of the automatic driving vehicle is relatively large, and the user experience is poor. The problem.
- an automatic driving method provided in an embodiment of the present application, which is applied to lane keeping, includes:
- For vehicles in an autonomous driving state collect real-time image information in front of the driving lane of the vehicle;
- the current time is the planned driving route of the vehicle based on the driving route planned for the vehicle at the previous time, the current time, and the pose information of the vehicle at the previous time.
- the pose information includes at least the vehicle's position information and heading angle information;
- image information of a lane line located in front of a driving lane of a vehicle is collected in real time, and a clear image of the lane line can be detected from the image information of the forward lane line collected at the current moment as a valid lane line image. Furthermore, based on these valid lane line image information, the vehicle's driving route is planned. If the lane line is missing or unclear, the driving route planned for the vehicle at the previous time, the current time and the vehicle position of the previous time can also be used.
- the vehicle therefore, can effectively reduce the number of vehicle parking times and improve the user experience.
- predicting the driving route planned for the vehicle at the current time includes:
- the vehicle driving route polynomial is fitted according to the coordinates of the discrete points after the conversion, and the fitted polynomial is determined as the mathematical expression of the driving route planned for the vehicle at the current moment.
- the above solution uses the travel route planned at the previous time to predict the travel route planned at the current time, and the error will not be too great.
- (x t , y t ) is the position coordinates of the vehicle at the current moment
- ⁇ t is the heading angle of the vehicle at the current moment
- (x t-1 , y t-1 ) is the position coordinates of the vehicle at the previous moment
- ⁇ t- 1 is the heading angle of the vehicle at the previous moment
- (x, y) is the coordinates of the discrete points before conversion
- (x ', y') is the coordinates of the discrete points after conversion.
- determining the driving route planned for the vehicle at the current moment includes:
- the feature points of the lane lines on the left and right sides of the current driving lane of the vehicle are separately extracted, and the mathematical expression of the lane line is determined according to the feature points of each lane line;
- the mathematical expressions of the left and right lane lines of the vehicle's current driving lane and the driving position information in the lane set for the vehicle are determined.
- the method further includes:
- an automatic driving device provided in an embodiment of the present application, which is applied to lane keeping, includes:
- An acquisition module configured to collect, in real time, image information of a vehicle in front of a driving lane of the vehicle in an autonomous driving state
- the planning module is configured to detect the forward image information that has been collected at the current moment, and determine the current moment according to the detected valid lane line image information and the driving position information set for the vehicle in the traveling lane.
- a prediction module configured to predict, if no valid lane line image information is detected at the current time, based on the driving route planned for the vehicle at the previous time, the current time, and the posture information of the vehicle at the previous time, predict the current planned driving of the vehicle Line, the pose information of the vehicle includes at least position information and heading angle information of the vehicle;
- the driving module is configured to calculate a position to which the vehicle travels at the next time according to the predicted driving route and a given distance from the current time to the next time, and drive the vehicle to the position.
- the prediction module is specifically configured to:
- the vehicle driving route polynomial is fitted according to the coordinates of the discrete points after the conversion, and the fitted polynomial is determined as the mathematical expression of the driving route planned for the vehicle at the current moment.
- the prediction module is specifically configured to transform the coordinates of each pair of discrete points according to the following formula:
- (x t , y t ) is the position coordinates of the vehicle at the current moment
- ⁇ t is the heading angle of the vehicle at the current moment
- (x t-1 , y t-1 ) is the position coordinates of the vehicle at the previous moment
- ⁇ t- 1 is the heading angle of the vehicle at the previous moment
- (x, y) is the coordinates of the discrete points before conversion
- (x ', y') is the coordinates of the discrete points after conversion.
- the planning module is specifically configured to:
- the feature points of the lane lines on the left and right sides of the current driving lane of the vehicle are separately extracted, and the mathematical expression of the lane line is determined according to the feature points of each lane line;
- the mathematical expressions of the left and right lane lines of the vehicle's current driving lane and the driving position information in the lane set for the vehicle are determined.
- the method further includes:
- the reminder module is configured to record the lane line extraction failure information once no valid lane line image information is detected at the current moment; if it is determined that the number of consecutive lane line extraction failures exceeds a preset number, the driver is reminded to take over the vehicle.
- a computer provided in an embodiment of the present application includes at least one processing unit and at least one storage unit, wherein the storage unit stores program code, and when the program code is executed by the processing unit, The computer is caused to perform the steps of the automatic driving method described above.
- a computer-readable storage medium provided by an embodiment of the present application includes program code, and when the program code is run on a computer, the computer is caused to execute the steps of the foregoing automatic driving method.
- FIG. 1 is a schematic diagram of an application scenario of an automatic driving method according to an embodiment of the present application
- FIG. 3 is a schematic structural diagram of a device for implementing an automatic driving method according to an embodiment of the present application
- FIG. 4 is a structural diagram of another automatic driving device according to an embodiment of the present application.
- embodiments of the present application provide an automatic driving method and device.
- the driving position in the lane set for the vehicle in the embodiment of the present application refers to the relative position between the vehicle and the driving lane, rather than the actual geographical location.
- FIG. 1 shows an example provided by the embodiment of the present application.
- the schematic diagram of the application scenario of the automatic driving method is shown in FIG. 1.
- the driving position in the lane set for the vehicle in FIG. 1 is the lane center.
- the camera installed on the vehicle can collect the image information of the left and right lane lines in front of the current driving lane in real time, and detect the image information of the forward lane lines that have been collected at the current moment.
- the detected lanes will be A clear line image is used as a valid lane line image.
- the current driving route is determined for the vehicle at the current moment, and then according to the driving route and the given.
- the distance traveled by the vehicle from the current moment to the next moment calculates the position to which the vehicle will travel at the next moment and drives the vehicle to the corresponding position. In this way, even if the lane line is temporarily lost or unclear, it can still be achieved well. Lane keeping can effectively reduce the number of times the vehicle stops.
- a currently acquired lane line image in front of the current lane may be detected, and a clearer image of the detected lane line may be used as a valid lane line image.
- These effective lane line images and the relative position information of the lane center set for the vehicle determine the time t-1 as the planned vehicle driving route, and determine the time t according to the driving distance of the given vehicle from time t-1 to time t After the vehicle reaches the position, the vehicle can reach the position along the center of the lane, that is, the position where the vehicle is located at time t.
- the driver can also be reminded to take over the steering wheel in a certain way, so that it can provide a certain reaction time for the driver to take over the steering wheel, which is safe. It has better performance, and if it is determined that the driver has not taken over the steering wheel for a certain period of time, the vehicle can be decelerated to a stop, which further improves the safety of the vehicle during driving.
- a flowchart of an automatic driving method according to an embodiment of the present application includes the following steps:
- S201 For vehicles in an autonomous driving state, real-time collection of image information in front of the driving lane of the vehicle.
- S202 Detect the image information of the front that has been collected at the current moment, and determine that the current moment is planned for the vehicle according to the detected valid lane line image information and the driving position information set for the vehicle in the driving lane. Driving route.
- the feature points of the lane lines on the left and right sides of the current driving lane of the vehicle can be extracted separately, and then the side lane line is determined based on the feature points of each side lane line.
- y left a l0 + a l1 ⁇ x + a l2 ⁇ x 2 + a l3 ⁇ x 3 ;
- a l0 , a l1 , a l2, and a l3 are parameters to be determined.
- y right a r0 + a r1 ⁇ x + a r2 ⁇ x 2 + a r3 ⁇ x 3 ;
- a r0 , a r1 , a r2 and a r3 are parameters to be determined.
- the values of a l0 , a l1 , a l2, and a l3 are determined according to the characteristic points of the left lane line; for the above mathematical expression of the right lane line
- the values of a r0 , a r1 , a r2 and a r3 are determined according to the feature points of the right lane line.
- the planned travel route for the vehicle at the current moment is:
- the current time is the planned driving route of the vehicle according to the driving route planned for the vehicle at the previous time, the current time, and the posture information of the vehicle at the previous time.
- the pose information of the vehicle includes at least the position information and the heading angle information of the vehicle.
- the driving route planned for the vehicle, the current time, and the pose information of the vehicle at the previous time are used to predict the driving route planned for the vehicle at the current time.
- a predetermined number of discrete points falling on a driving route planned for the vehicle at the previous moment may be determined first, and then the coordinates of each discrete point are converted according to the pose information of the vehicle at the current moment and the previous moment, Further, the vehicle driving route polynomial is fitted according to the coordinates of the discrete points after the conversion, and the fitted polynomial is determined as the mathematical expression of the driving route planned by the vehicle at the current moment.
- the coordinates of each pair of discrete points can be transformed according to the following formula:
- (x t , y t ) is the position coordinates of the vehicle at the current moment
- ⁇ t is the heading angle of the vehicle at the current moment
- (x t-1 , y t-1 ) is the position coordinates of the vehicle at the previous moment
- ⁇ t- 1 is the heading angle of the vehicle at the previous moment
- (x, y) is the coordinates of the discrete points before conversion
- (x ', y') is the coordinates of the discrete points after conversion.
- the coordinate of the discrete points after the transformation can be used to polynomial the vehicle driving route:
- y a 0 + a 1 ⁇ x + a 2 ⁇ x 2 + a 3 ⁇ x 3 ;
- S204 Calculate the position to which the vehicle travels at the next time according to the predicted driving route and the distance traveled by the vehicle from the given current time to the next time, and drive the vehicle to the corresponding position.
- l is the distance traveled by the vehicle from a given current time to the next time, and l can be determined by a technician according to the vehicle's driving speed and heading angle, and will not be repeated here.
- the vehicle can be driven from the current position to (x t + 1 , y t + 1 ).
- step S202 if no valid lane line image information is detected at the current time, the lane line extraction failure information may be recorded once. If it is determined that the number of consecutive lane line extraction failures exceeds the preset number, It means that the lane line is missing or unclear for a long time. At this time, the planned driving route for the vehicle may not be accurate enough, so the driver can be reminded to take over the vehicle, and if it is determined that the driver has not taken over the vehicle within a certain period of time, Then, the vehicle can be decelerated to a stop, so that, in the case where the lane line is not clear enough, the number of times the vehicle can be reduced and stopped can be effectively reduced and the safety of the vehicle during driving can be guaranteed.
- the driving route planned for the vehicle at the last moment is:
- y b 0 + b 1 ⁇ x + b 2 ⁇ x 2 + b 3 ⁇ x 3 ;
- X 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, and 60, and then the value of each X is substituted into the three times of the driving line at the previous moment.
- Polynomial: y b 0 + b 1 ⁇ x + b 2 ⁇ x 2 + b 3 ⁇ x 3 to get the corresponding Y. In this way, 13 discrete points on the driving line determined at the previous moment can be obtained.
- (x t , y t ) is the position coordinates of the vehicle at the current moment
- ⁇ t is the heading angle of the vehicle at the current moment
- (x t-1 , y t-1 ) is the position coordinates of the vehicle at the previous moment
- ⁇ t- 1 is the heading angle of the vehicle at the previous moment
- (x, y) is the coordinates of the discrete points before conversion
- (x ', y') is the coordinates of the discrete points after conversion.
- the least-squares algorithm and the coordinates of the discrete points after the transformation can be used to polynomial the vehicle driving line:
- y a 0 + a 1 ⁇ x + a 2 ⁇ x 2 + a 3 ⁇ x 3 ;
- the fitting is performed to obtain the values of the parameters a 0 , a 1 , a 2, and a 3 in the polynomial. Substituting the values of a 0 , a 1 , a 2, and a 3 into the above formula, the predicted current time is the vehicle. Mathematical expressions of the planned driving route.
- l is the distance traveled by the vehicle from a given current time to the next time, and l can be determined by a technician according to the speed and heading angle of the vehicle.
- the vehicle can be driven from the current position to (x t + 1 , y t + 1 ).
- the driver can be reminded to take over the vehicle. If the driver has not taken over the vehicle within the set period of time, the driver can also take the The vehicle slowed to a stop.
- a preset time such as 5S
- FIG. 3 is a schematic structural diagram of a device for implementing an automatic driving method according to an embodiment of the present application.
- the device includes physical devices such as a transceiver 301 and a processor 302.
- the processor 302 may be a central processing unit. (central processing unit, CPU), microprocessor, application specific integrated circuit, programmable logic circuit, large scale integrated circuit, or digital processing unit, and so on.
- the transceiver 301 is configured to perform data transmission and reception with other devices.
- the device may further include a memory 303 configured to store software instructions executed by the processor 302, and of course, it may also store some other data required by the device, such as device identification information, device encrypted information, and / or user data.
- the memory 303 may be a volatile memory (for example, random-access memory (RAM); the memory 303 may also be a non-volatile memory (for example, read-only memory) only memory (ROM), flash memory (flash memory), hard disk (HDD) or solid-state drive (SSD), or memory 303 can be configured to carry or store instructions or data structures
- the desired program code is any other medium that can be accessed by a computer, but is not limited thereto, and the memory 303 may be a combination of the above memories.
- the specific connection medium between the processor 302, the memory 303, and the transceiver 301 is not limited in the embodiment of the present application.
- only the memory 303, the processor 302, and the transceiver 301 are connected by using a bus 304 as an example in FIG. 3, and the bus is indicated by a thick line in FIG. 3.
- the connection between other components is only It is for illustrative purposes and is not limited.
- the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only a thick line is used in FIG. 3, but it does not mean that there is only one bus or one type of bus.
- the processor 302 may be dedicated hardware or a processor running software. When the processor 302 can run software, the processor 302 reads software instructions stored in the memory 303, and executes the foregoing embodiments under the driving of the software instructions. Autonomous driving method.
- the device may include multiple functional modules, and each functional module may include software, hardware, or a combination thereof.
- FIG. 4 it is a schematic structural diagram of still another automatic driving device according to an embodiment of the present application.
- the device includes an acquisition module 401, a planning module 402, a prediction module 403, and a driving module 404, where:
- the acquisition module 401 is configured to collect, in real time, image information of a vehicle in a driving lane of a vehicle in an autonomous driving state;
- the planning module 402 is configured to detect the forward image information collected at the current time, and determine the current time as the vehicle based on the detected valid lane line image information and the driving position information in the driving lane set for the vehicle. Planned driving routes;
- the prediction module 403 is configured to predict, if valid lane line image information is not detected at the current time, based on the driving route planned for the vehicle at the previous time, the current time, and the posture information of the vehicle at the previous time, and predict the current time as the planned vehicle.
- a driving route, the pose information of the vehicle includes at least position information and heading angle information of the vehicle;
- the driving module 404 is configured to calculate a position to which the vehicle travels at the next time according to the predicted driving route and a given distance from the current time to the next time, and drive the vehicle to the position.
- the prediction module 403 is specifically configured to:
- the vehicle driving route polynomial is fitted according to the coordinates of the discrete points after the conversion, and the fitted polynomial is determined as the mathematical expression of the driving route planned for the vehicle at the current moment.
- the prediction module 403 is specifically configured to transform the coordinates of each pair of discrete points according to the following formula:
- (x t , y t ) is the position coordinates of the vehicle at the current moment
- ⁇ t is the heading angle of the vehicle at the current moment
- (x t-1 , y t-1 ) is the position coordinates of the vehicle at the previous moment
- ⁇ t- 1 is the heading angle of the vehicle at the previous moment
- (x, y) is the coordinates of the discrete points before conversion
- (x ', y') is the coordinates of the discrete points after conversion.
- the planning module 402 is specifically configured to:
- the feature points of the lane lines on the left and right sides of the current driving lane of the vehicle are separately extracted, and the mathematical expression of the lane line is determined according to the feature points of each lane line;
- the mathematical expressions of the left and right lane lines of the vehicle's current driving lane and the driving position information in the lane set for the vehicle are determined.
- the apparatus further includes:
- the reminder module 405 is configured to record the lane line extraction failure information once no valid lane line image information is detected at the current moment; if it is determined that the number of consecutive lane line extraction failures exceeds a preset number, the driver is reminded to take over the vehicle .
- a computer-readable storage medium provided in an embodiment of the present application includes program code, and when the program code is run on a computer, the computer is caused to execute the steps of the foregoing automatic driving method.
- this application may be provided as a method, a system, or a computer program product. Therefore, this application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, and / or optical storage, etc.) containing computer-usable program code.
- computer-usable storage media including but not limited to disk storage, CD-ROM, and / or optical storage, etc.
- These computer program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, so that the instructions generated by the processor of the computer or other programmable data processing device are used to generate instructions Means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, the instructions
- the device implements the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of steps can be performed on the computer or other programmable device to produce a computer-implemented process, which can be executed on the computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.
Abstract
一种自动驾驶方法及装置，属于汽车技术领域，该方法包括：车辆处于自动驾驶状态时，实时采集行驶车道前方的图像信息，并对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像和为车辆设定的在车道中的行驶位置信息为车辆规划行驶线路，若当前时刻未检测出有效的车道线图像信息，则可根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息对当前时刻为车辆规划的行驶线路进行预测，进而根据预测的行驶线路和给定的行驶距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至相应位置，这样，即便车道线短暂丢失或不清晰仍可有效地实现保持车道，因此，可减少自动驾驶车辆的停车次数。
Description
相关申请的交叉引用
本申请要求于2018年06月05日提交中国专利局的申请号为CN201810570006.0、名称为“一种自动驾驶方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及汽车技术领域，尤其涉及一种自动驾驶方法及装置。
随着汽车技术的快速发展，自动驾驶在安全出行和节能环保等方面都显现出巨大优势，因此，自动驾驶被认为是解决交通拥堵、降低交通事故和改善环境污染的有效途径。
现有技术中，当车辆处于自动驾驶状态时，可实时采集当前行驶车道前方车道线的图像信息，之后，从当前时刻采集到的图像中检测出车道线清晰的图像作为有效的车道线图像，对每帧有效的车道线图像，可分别提取车辆当前行驶车道左右两侧车道线的特征点，进而根据提取的每侧车道线的特征点确定该侧车道线的数学表达式，之后，可根据预设的车辆在车道中的行驶位置信息，如设定车辆在车道中心上行驶，规划车辆的行驶线路，最后，根据规划的行驶线路和给定的行驶距离确定下一时刻车辆行驶至的位置，并驱动车辆行驶至该位置，采用这种方式，在车道线清晰时，可较好地驱动车辆自动驾驶，但在实际的交通环境种，车道线会出现不清晰或者丢失的情况，此时，就无法更新为车辆规划的行驶线路，准确地确定出下一时刻车辆行驶至的位置，所以针对这种情况，现有技术是直接将车辆减速至停，这样，如果行驶车道出现多处短暂的车道线丢失或不清晰的情况，车辆的停车次数就会比较多。
发明内容
本申请实施例提供一种自动驾驶方法及装置，用以解决现有技术中如果行驶车道出现多处短暂的车道线丢失或不清晰的情况，自动驾驶车辆的停车次数会比较多，用户体验差的问题。
第一方面，本申请实施例提供的一种自动驾驶方法，应用于车道保持，包括：
针对处于自动驾驶状态的车辆，实时采集位于车辆行驶车道前方的图像信息；
对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为车辆规划的行驶线路；
若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路，所述车辆的位姿信息至少包括车辆的位置信息和航向角信息；
根据预测的行驶线路和给定的当前时刻到下一时刻车辆行驶的距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至该位置。
本申请实施例中，实时采集位于车辆行驶车道前方的车道线的图像信息，并可从当前时刻已采集到的前方车道线的图像信息中检测出车道线清晰的图像作为有效的车道线图像，进而根据这些有效的车道线的图像信息为车辆规划行驶线路，若出现车道线丢失或者不清晰的情况，还可根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路，进而确定出下一时刻车辆行驶至的位置，并驱动车辆行驶至相应位置，这样，不必一出现短暂的车道线丢失或者不清晰的情况就减停车辆，因此，可有效减少车辆的停车次数，提升用户体验。
在一种可能的实施方式下，根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路，包括：
确定预设数量的落在上一时刻为车辆规划的行驶线路上的离散点；
根据当前时刻和上一时刻车辆的位姿信息对每个离散点的坐标进行转换；
根据转换后各离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的多项式确定为当前时刻为车辆规划的行驶线路的数学表达式。
因为一般车道线不会发生较大幅度的变化，所以上述方案利用上一时刻规划的行驶线路来预测当前时刻规划的行驶线路，误差也不会太大。
在一种可能的实施方式下，可根据以下公式对每一对离散点的坐标进行转换：
Δθ＝θ
t-θ
t-1；
其中，(x
t,y
t)为当前时刻车辆的位置坐标，θ
t为当前时刻车辆的航向角，(x
t-1,y
t-1)为上一时刻车辆的位置坐标，θ
t-1为上一时刻车辆的航向角，(x,y)为转换前离散点的坐标，(x',y')为转换后离散点的坐标。
在一种可能的实施方式下，根据检测出的有效的车道线图像信息和为车辆设定的在行 驶车道中的行驶位置信息，确定当前时刻为车辆规划的行驶线路，包括：
针对检测出的每一帧有效的车道线图像，分别提取该图像中车辆当前行驶车道左右两侧车道线的特征点，根据每侧车道线的特征点确定该侧车道线的数学表达式；
根据车辆当前行驶车道左右两侧车道线的数学表达式和为车辆设定的在车道中的行驶位置信息，确定为车辆规划的行驶线路的数学表达式。
在一种可能的实施方式下，若当前时刻未检测出有效的车道线图像信息，还包括：
记录一次车道线提取失败的信息；
若连续出现车道线提取失败的次数超过预设次数，则提醒驾驶员接管车辆。
采用上述方案，可避免长时间丢失车道线而造成的行驶线路规划不准确的问题，同时可提升自动驾驶的安全性。
第二方面，本申请实施例提供的一种自动驾驶装置，应用于车道保持，包括：
采集模块，配置成针对处于自动驾驶状态的车辆，实时采集位于车辆行驶车道前方的图像信息；
规划模块，配置成对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为车辆规划的行驶线路；
预测模块，配置成若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路，所述车辆的位姿信息至少包括车辆的位置信息和航向角信息；
驱动模块，配置成根据预测的行驶线路和给定的当前时刻到下一时刻车辆行驶的距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至所述位置。
在一种可能的实施方式下，预测模块具体配置成：
确定预设数量的落在上一时刻为车辆规划的行驶线路上的离散点；
根据当前时刻和上一时刻所述车辆的位姿信息对每个离散点的坐标进行转换；
根据转换后各离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的多项式确定为当前时刻为车辆规划的行驶线路的数学表达式。
在一种可能的实施方式下，预测模块具体配置成根据以下公式对每一对离散点的坐标进行转换：
Δθ＝θ
t-θ
t-1；
其中，(x
t,y
t)为当前时刻车辆的位置坐标，θ
t为当前时刻车辆的航向角，(x
t-1,y
t-1)为上一时刻车辆的位置坐标，θ
t-1为上一时刻车辆的航向角，(x,y)为转换前离散点的坐标，(x',y')为转换后离散点的坐标。
在一种可能的实施方式下，规划模块具体配置成：
针对检测出的每一帧有效的车道线图像，分别提取该图像中车辆当前行驶车道左右两侧车道线的特征点，根据每侧车道线的特征点确定该侧车道线的数学表达式；
根据车辆当前行驶车道左右两侧车道线的数学表达式和为车辆设定的在车道中的行驶位置信息，确定为车辆规划的行驶线路的数学表达式。
在一种可能的实施方式下，还包括：
提醒模块，配置成在当前时刻未检测出有效的车道线图像信息时，记录一次车道线提取失败的信息；若确定连续出现车道线提取失败的次数超过预设次数，则提醒驾驶员接管车辆。
第三方面，本申请实施例提供的一种计算机，包括至少一个处理单元、以及至少一个存储单元，其中，所述存储单元存储有程序代码，当所述程序代码被所述处理单元执行时，使得所述计算机执行上述自动驾驶方法的步骤。
第四方面，本申请实施例提供的一种计算机可读存储介质，包括程序代码，当所述程序代码在计算机上运行时，使所述计算机执行上述自动驾驶方法的步骤。
另外，第二方面至第四方面中任一种设计方式所带来的技术效果可参见第一方面中不同实现方式所带来的技术效果，此处不再赘述。
本申请的这些方面或其它方面在以下实施例的描述中会更加简明易懂。
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1为本申请实施例提供的自动驾驶方法的应用场景示意图；
图2为本申请实施例提供的自动驾驶方法的流程图；
图3为本申请实施例提供的实现自动驾驶方法的装置的结构示意图；
图4为本申请实施例提供的又一自动驾驶装置的结构图。
为了在行驶车道出现多处短暂的车道线丢失或不清晰的情况时，减少自动驾驶车辆的停车次数，提升用户体验，本申请实施例提供了一种自动驾驶方法及装置。
以下结合说明书附图对本申请的优选实施例进行说明，应当理解，此处所描述的优选实施例仅用于说明和解释本申请，并不用于限定本申请，并且在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
在本申请实施例中为车辆设定的在车道中的行驶位置是指车辆与行驶车道之间的相对位置，而非实际的地理位置，参见图1，图1示出了本申请实施例提供的自动驾驶方法的应用场景示意图，图1中为车辆设定的在车道中的行驶位置为车道中心。
实际应用中，安装在车辆上的摄像头可实时采集位于当前行驶车道前方的左右两侧车道线的图像信息，并对当前时刻已采集到的前方车道线的图像信息进行检测，将检测出的车道线清晰的图像作为有效的车道线图像，之后，根据有效的车道线图像和为车辆设定的车道中心的相对位置信息，确定当前时刻为车辆规划行驶线路，进而根据该行驶线路和给定的当前时刻到下一时刻车辆行驶的距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至相应位置，这样，即便在车道线短暂地丢失或者不清晰的情况下，仍然能够较好地实现车道保持，有效减少车辆减停的次数。
具体地，参见图1，t-1时刻，可对当前已采集到的位于当前车道前方的车道线图像进行检测，将检测出的车道线比较清晰的图像作为有效的车道线图像，之后，根据这些有效的车道线图像和为车辆设定的车道中心的相对位置信息，确定t-1时刻为车辆规划行驶线路，并根据给定的车辆从t-1时刻到t时刻的行驶距离确定t时刻车辆达到的位置，之后，车辆即可沿着车道中心到达该位置，即t时刻车辆所在的位置。
假设从t-1时刻到t时刻某侧车道线的图像不清晰或者车道线丢失，那么，在t时刻就无法从已采集到的前方车道线的图像中再检测出新的有效的车道线图像，即，t时刻就无法为车辆规划行驶线路，考虑到一般情况下，车道线不会出现较大幅度的改变，所以可以根据t-1时刻为车辆规划的行驶线路、t时刻和t-1时刻车辆的位姿信息，预测t时刻为车辆规划的行驶线路，进而根据预测的t时刻为车辆规划的行驶线路和给定的车辆从t时刻到t+1时刻的行驶距离计算t+1时刻车辆行驶至的位置，并驱动车辆行驶至该位置。
这样，若只是短暂的车道线丢失或者不清晰，则可以利用已有的行驶线路来预测后续的行驶线路，而不必一遇到车道线丢失或者不清晰的情况就将车辆减速至停，因此，可减少车辆减停的次数，大大提高客户体验。
此外，具体实施时，若确定车道线持续丢失的时间超过设定时间，如5s时，还可通过一定的方式提醒驾驶员接管方向盘，这样，可为驾驶员接管方向盘提供一定的反应时间，安全性更好，并且，若确定超过一定时间驾驶员仍未接管方向盘则可将车辆减速至停，进 一步提高车辆行驶过程中的安全性。
如图2所示，为本申请实施例提供的自动驾驶方法的流程图，包括以下步骤：
S201：针对处于自动驾驶状态的车辆，实时采集位于车辆行驶车道前方的图像信息。
S202：对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为车辆规划的行驶线路。
具体地，针对检测出的每一帧有效的车道线图像，可分别提取该图像中车辆当前行驶车道左右两侧车道线的特征点，之后，根据每侧车道线的特征点确定该侧车道线的数学表达式。
比如，对每一车道，设定的左侧车道线的数学表达式为：
y
left＝a
l0+a
l1·x+a
l2·x
2+a
l3·x
3；
其中，a
l0、a
l1、a
l2和a
l3为待确定的参数。
设定的右侧车道线的数学表达式为：
y
right＝a
r0+a
r1·x+a
r2·x
2+a
r3·x
3；
其中，a
r0、a
r1、a
r2和a
r3为待确定的参数。
则，对于上述左侧车道线的数学表达式而言，即根据左侧车道线的特征点确定a
l0、a
l1、a
l2和a
l3的取值；对于上述右侧车道线的数学表达式而言，即根据右侧车道线的特征点确定a
r0、a
r1、a
r2和a
r3的取值。
进一步地，假设为车辆设定的在车道中的行驶位置为车道中心，则当前时刻为车辆规划的行驶线路为：
S203：若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路。
其中，车辆的位姿信息至少包括车辆的位置信息和航向角信息。
实际应用中，如果出现车道线丢失或者不清晰的情况，则当前时刻可能就无法检测出有效的车道线图像信息，因此，就无法为车辆规划行驶线路，为了解决该问题，可根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，对当前时刻为车辆规划的行驶线路进行预测。
具体地，可先确定预设数量的落在上一时刻为车辆规划的行驶线路上的离散点，之后，根据当前时刻和上一时刻车辆的位姿信息对每个离散点的坐标进行转换，进而根据转换后各离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的多项式确定为当前时刻为车辆规划的行驶线路的数学表达式。
比如，可以根据以下公式对每一对离散点的坐标进行转换：
Δθ＝θ
t-θ
t-1；
其中，(x
t,y
t)为当前时刻车辆的位置坐标，θ
t为当前时刻车辆的航向角，(x
t-1,y
t-1)为上一时刻车辆的位置坐标，θ
t-1为上一时刻车辆的航向角，(x,y)为转换前离散点的坐标，(x',y')为转换后离散点的坐标。
进一步地，可利用转换后各离散点的坐标对车辆行驶线路多项式：
y＝a
0+a
1·x+a
2·x
2+a
3·x
3；
进行拟合，确定多项式中参数a
0、a
1、a
2和a
3的取值，将a
0、a
1、a
2和a
3的取值代入上式即可得到预测的当前时刻为车辆规划的行驶线路的数学表达式。
S204：根据预测的行驶线路和给定的当前时刻到下一时刻车辆行驶的距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至相应位置。
具体地，求解如下方程组即可得到下一时刻车辆行驶至位置的坐标(x
t+1,y
t+1)：
其中，l为给定的当前时刻到下一时刻车辆行驶的距离，l可由技术人员根据车辆的行驶速度和航向角确定，在此不再赘述。
进一步地，驱动车辆从当前位置行驶至(x
t+1,y
t+1)即可。
此外，具体实施时，在步骤S202中，若当前时刻未检测出有效的车道线图像信息，还可以记录一次车道线提取失败的信息，若确定连续出现车道线提取失败的次数超过预设次数，则说明车道线丢失或者不清晰的时间较久，此时，为车辆规划的行驶线路可能已不够准确，所以可提醒驾驶员接管车辆，并且，若确定在一定时间段内驾驶员未接管车辆，则 可将车辆减速至停，这样，针对车道线不够清晰的情况，即可有效减少车辆减停的次数又可保证车辆行驶过程中的安全性。
下面结合具体的实施例对上述过程进行说明。
假设上一时刻车辆的位姿信息为：(x
t-1,y
t-1,θ
t-1)；
上一时刻为车辆规划的行驶线路为：
y＝b
0+b
1·x+b
2·x
2+b
3·x
3；
其中，b
0、b
1、b
2和b
3的取值已确定。
若当前时刻未检测出有效的车道线图像信息，则可按照以下步骤执行：
1)将上一时刻确定的行驶线路的三次多项式离散为一系列点。
具体地，可取X＝0、5、10、15、20、25、30、35、40、45、50、55和60，之后，将每个X的取值代入上一时刻的行驶线路的三次多项式：y＝b
0+b
1·x+b
2·x
2+b
3·x
3，得到对应的Y，这样就可得到13个位于上一时刻确定的行驶线路上的离散点。
2)根据以下公式对每一对离散点的坐标进行转换。
Δθ＝θ
t-θ
t-1；
其中，(x
t,y
t)为当前时刻车辆的位置坐标，θ
t为当前时刻车辆的航向角，(x
t-1,y
t-1)为上一时刻车辆的位置坐标，θ
t-1为上一时刻车辆的航向角，(x,y)为转换前离散点的坐标，(x',y')为转换后离散点的坐标。
3)将经过坐标转换的离散点对车辆行驶线路多项式进行拟合，将拟合的多项式确定为当前时刻为车辆规划的行驶线路的数学表达式。
具体地，可以利用最小二乘算法和变换后各离散点的坐标对车辆行驶线路多项式：
y＝a
0+a
1·x+a
2·x
2+a
3·x
3；
进行拟合，从而得到多项式中参数a
0、a
1、a
2和a
3的取值，将a
0、a
1、a
2和a
3的取值代入上式即得到预测的当前时刻为车辆规划的行驶线路的数学表达式。
之后，求解如下方程组即可得到下一时刻车辆行驶至位置的坐标(x
t+1,y
t+1)：
其中，l为给定的当前时刻到下一时刻车辆行驶的距离，l可由技术人员根据车辆的行驶速度和航向角确定。
最后，驱动车辆从当前位置行驶至(x
t+1,y
t+1)即可。
此外，在具体实施时，若确定车道线丢失或者不清晰的时间连续超过预设时间，如5S，则可提醒驾驶员接管车辆，若在设定时间段内驾驶员未接管车辆，还可将车辆减速至停。
参见图3，图3为本申请实施例提供的一种实现自动驾驶方法的装置的结构示意图，该装置包括收发器301以及处理器302等物理器件，其中，处理器302可以是一个中央处理单元(central processing unit，CPU)、微处理器、专用集成电路、可编程逻辑电路、大规模集成电路、或者为数字处理单元等等。收发器301配置成与其他设备进行数据收发。
该装置还可以包括存储器303，配置成存储处理器302执行的软件指令，当然还可以存储装置需要的一些其他数据，如装置的标识信息、装置的加密信息和/或用户数据等。存储器303可以是易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；存储器303也可以是非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)、或者存储器303是能够配置成携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此，存储器303可以是上述存储器的组合。
本申请实施例中不限定上述处理器302、存储器303以及收发器301之间的具体连接介质。本申请实施例在图3中仅以存储器303、处理器302以及收发器301之间通过总线304连接为例进行说明，总线在图3中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。所述总线可以分为地址总线、数据总线和控制总线等。为便于表示，图3中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
处理器302可以是专用硬件或运行软件的处理器，当处理器302可以运行软件时，处理器302读取存储器303存储的软件指令，并在所述软件指令的驱动下，执行前述实施例中的自动驾驶方法。
当本申请实施例中提供的方法以软件或硬件或软硬件结合实现的时候，装置中可以包括多个功能模块，每个功能模块可以包括软件、硬件或其结合。具体的，参见图4，为本申请实施例提供的又一种自动驾驶装置的结构示意图，该装置包括采集模块401、规划模块402、预测模块403和驱动模块404，其中：
采集模块401，配置成针对处于自动驾驶状态的车辆，实时采集位于车辆行驶车道前方 的图像信息；
规划模块402，配置成对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为车辆设定的在行驶车道中的行驶位置信息，确定当前时刻为车辆规划的行驶线路；
预测模块403，配置成若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为车辆规划的行驶线路、当前时刻和上一时刻车辆的位姿信息，预测当前时刻为车辆规划的行驶线路，所述车辆的位姿信息至少包括车辆的位置信息和航向角信息；
驱动模块404，配置成根据预测的行驶线路和给定的当前时刻到下一时刻车辆行驶的距离计算下一时刻车辆行驶至的位置，并驱动车辆行驶至所述位置。
在一种可能的实施方式下，预测模块403具体配置成：
确定预设数量的落在上一时刻为车辆规划的行驶线路上的离散点；
根据当前时刻和上一时刻所述车辆的位姿信息对每个离散点的坐标进行转换；
根据转换后各离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的多项式确定为当前时刻为车辆规划的行驶线路的数学表达式。
在一种可能的实施方式下，预测模块403具体配置成根据以下公式对每一对离散点的坐标进行转换：
Δθ＝θ
t-θ
t-1；
其中，(x
t,y
t)为当前时刻车辆的位置坐标，θ
t为当前时刻车辆的航向角，(x
t-1,y
t-1)为上一时刻车辆的位置坐标，θ
t-1为上一时刻车辆的航向角，(x,y)为转换前离散点的坐标，(x',y')为转换后离散点的坐标。
在一种可能的实施方式下，规划模块402具体配置成：
针对检测出的每一帧有效的车道线图像，分别提取该图像中车辆当前行驶车道左右两侧车道线的特征点，根据每侧车道线的特征点确定该侧车道线的数学表达式；
根据车辆当前行驶车道左右两侧车道线的数学表达式和为车辆设定的在车道中的行驶位置信息，确定为车辆规划的行驶线路的数学表达式。
在一种可能的实施方式下，该装置还包括：
提醒模块405，配置成在当前时刻未检测出有效的车道线图像信息时，记录一次车道线提取失败的信息；若确定连续出现车道线提取失败的次数超过预设次数，则提醒驾驶员接管车辆。
本申请实施例提供的一种计算机可读存储介质，包括程序代码，当所述程序代码在计算机上运行时，使计算机执行上述自动驾驶方法的步骤。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM和/或光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、装置(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。
Claims (10)
- 一种自动驾驶方法，其特征在于，包括：针对处于自动驾驶状态的车辆，实时采集位于所述车辆行驶车道前方的图像信息；对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为所述车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为所述车辆规划的行驶线路；若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为所述车辆规划的行驶线路、当前时刻和上一时刻所述车辆的位姿信息，预测当前时刻为所述车辆规划的行驶线路，所述车辆的位姿信息至少包括所述车辆的位置信息和航向角信息；根据预测的行驶线路和给定的当前时刻到下一时刻所述车辆行驶的距离计算下一时刻所述车辆行驶至的位置，并驱动所述车辆行驶至所述位置。
- 如权利要求1所述的方法，其特征在于，根据上一时刻为所述车辆规划的行驶线路、当前时刻和上一时刻所述车辆的位姿信息，预测当前时刻为所述车辆规划的行驶线路，包括：确定预设数量的落在上一时刻为所述车辆规划的行驶线路上的离散点；根据当前时刻和上一时刻所述车辆的位姿信息对每个所述离散点的坐标进行转换；根据转换后各所述离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的所述多项式确定为当前时刻为所述车辆规划的行驶线路的数学表达式。
- 如权利要求2所述的方法，其特征在于，根据以下公式对每一对所述离散点的坐标进行转换：
Δθ＝θ t-θ t-1；其中，(x t,y t)为当前时刻所述车辆的位置坐标，θ t为当前时刻所述车辆的航向角，(x t-1,y t-1)为上一时刻所述车辆的位置坐标，θ t-1为上一时刻所述车辆的航向角，(x,y)为转换前所述离散点的坐标，(x',y')为转换后所述离散点的坐标。 - 如权利要求1所述的方法，其特征在于，根据检测出的有效的车道线图像信息和为所述车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为所述车辆规划的行驶线路，包括：针对检测出的每一帧有效的车道线图像，分别提取所述图像中所述车辆当前行驶车道左右两侧车道线的特征点，根据每侧车道线的特征点确定所述侧车道线的数学表达式；根据所述车辆当前行驶车道左右两侧车道线的数学表达式和为所述车辆设定的在车道中的行驶位置信息，确定为所述车辆规划的行驶线路的数学表达式。
- 如权利要求1～4任一所述的方法，其特征在于，若当前时刻未检测出有效的车道线图像信息，还包括：记录一次车道线提取失败的信息；若连续出现车道线提取失败的次数超过预设次数，则提醒驾驶员接管所述车辆。
- 一种自动驾驶装置，其特征在于，包括：采集模块，配置成针对处于自动驾驶状态的车辆，实时采集位于所述车辆行驶车道前方的图像信息；规划模块，配置成对当前时刻已采集到的前方的图像信息进行检测，根据检测出的有效的车道线图像信息和为所述车辆设定的在所述行驶车道中的行驶位置信息，确定当前时刻为所述车辆规划的行驶线路；预测模块，配置成若当前时刻未检测出有效的车道线图像信息，则根据上一时刻为所述车辆规划的行驶线路、当前时刻和上一时刻所述车辆的位姿信息，预测当前时刻为所述车辆规划的行驶线路，所述车辆的位姿信息至少包括所述车辆的位置信息和航向角信息；驱动模块，配置成根据预测的行驶线路和给定的当前时刻到下一时刻所述车辆行驶的距离计算下一时刻所述车辆行驶至的位置，并驱动所述车辆行驶至所述位置。
- 如权利要求6所述的装置，其特征在于，所述预测模块具体配置成：确定预设数量的落在上一时刻为所述车辆规划的行驶线路上的离散点；根据当前时刻和上一时刻所述车辆的位姿信息对每个所述离散点的坐标进行转换；根据转换后各所述离散点的坐标对车辆行驶线路多项式进行拟合，将拟合的所述多项式确定为当前时刻为所述车辆规划的行驶线路的数学表达式。
- 如权利要求7所述的装置，其特征在于，预测模块具体配置成根据以下公式对每一对所述离散点的坐标进行转换：
Δθ＝θ t-θ t-1；其中，(x t,y t)为当前时刻所述车辆的位置坐标，θ t为当前时刻所述车辆的航向角，(x t-1,y t-1)为上一时刻所述车辆的位置坐标，θ t-1为上一时刻所述车辆的航向角，(x,y)为转换前所述离散点的坐标，(x',y')为转换后所述离散点的坐标。 - 如权利要求6所述的装置，其特征在于，所述规划模块具体配置成：针对检测出的每一帧有效的车道线图像，分别提取所述图像中所述车辆当前行驶车道左右两侧车道线的特征点，根据每侧车道线的特征点确定所述侧车道线的数学表达式；根据所述车辆当前行驶车道左右两侧车道线的数学表达式和为所述车辆设定的在车道中的行驶位置信息，确定为所述车辆规划的行驶线路的数学表达式。
- 如权利要求6～9任一所述的装置，其特征在于，还包括：提醒模块，配置成在当前时刻未检测出有效的车道线图像信息时，记录一次车道线提取失败的信息；若确定连续出现车道线提取失败的次数超过预设次数，则提醒驾驶员接管所述车辆。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810570006.0 | 2018-06-05 | ||
| CN201810570006.0A CN110562251A (zh) | 2018-06-05 | 2018-06-05 | 一种自动驾驶方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019233081A1 true WO2019233081A1 (zh) | 2019-12-12 |
Family
ID=68770776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/121833 WO2019233081A1 (zh) | 2018-06-05 | 2018-12-18 | 一种自动驾驶方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110562251A (zh) |
| WO (1) | WO2019233081A1 (zh) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738057A (zh) * | 2020-04-30 | 2020-10-02 | 上海智目科技有限公司 | 一种基于路边特征的车道线校正方法和装置 |
| CN111703422B (zh) * | 2020-06-24 | 2021-06-29 | 北京经纬恒润科技股份有限公司 | 智能驾驶车辆的目标跟踪路径选择方法及装置 |
| CN112329564A (zh) * | 2020-10-24 | 2021-02-05 | 武汉光庭信息技术股份有限公司 | 车道保持功能失效分析方法、系统、电子设备及存储介质 |
| JP7396308B2 (ja) * | 2021-01-28 | 2023-12-12 | トヨタ自動車株式会社 | 走行軌跡推定システム、走行軌跡推定プログラム、及び走行軌跡推定方法 |
| CN113525368A (zh) * | 2021-06-23 | 2021-10-22 | 清华大学 | 车辆的车道保持紧急控制策略与安全控制方法及装置 |
| CN114715272B (zh) * | 2022-03-16 | 2023-05-12 | 东风汽车集团股份有限公司 | 车道线修补方法及车辆主动转向控制装置 |
| CN116101327A (zh) * | 2023-04-14 | 2023-05-12 | 北京集度科技有限公司 | 行驶路径规划方法、装置、车辆及存储介质 |
| CN116834729B (zh) * | 2023-08-28 | 2023-11-17 | 常州星宇车灯股份有限公司 | 车辆辅助驾驶的横纵向联合控制系统及控制方法 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090296987A1 (en) * | 2008-05-27 | 2009-12-03 | Toyota Jidosha Kabushiki Kaisha | Road lane boundary detection system and road lane boundary detecting method |
| CN106467105A (zh) * | 2015-08-10 | 2017-03-01 | 富士重工业株式会社 | 车道线识别装置 |
| CN106627575A (zh) * | 2016-12-30 | 2017-05-10 | 吉林大学 | 一种车辆偏航预警方法及系统 |
| CN107364443A (zh) * | 2016-05-13 | 2017-11-21 | 德尔福技术有限公司 | 用于自动化车辆的车道保持系统 |
| CN107499309A (zh) * | 2016-06-14 | 2017-12-22 | 德尔福技术有限公司 | 用于自主车辆在相机漏失期间的车道保持系统 |
| CN107628028A (zh) * | 2016-07-19 | 2018-01-26 | 株式会社万都 | 车辆辅助驾驶装置 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120022739A1 (en) * | 2010-07-20 | 2012-01-26 | Gm Global Technology Operations, Inc. | Robust vehicular lateral control with front and rear cameras |
| JP6536340B2 (ja) * | 2014-12-01 | 2019-07-03 | 株式会社デンソー | 画像処理装置 |
| JP6270888B2 (ja) * | 2016-03-15 | 2018-01-31 | 本田技研工業株式会社 | 車両制御システム、車両制御方法、および車両制御プログラム |
| JP6788425B2 (ja) * | 2016-08-10 | 2020-11-25 | 株式会社Ｓｕｂａｒｕ | 車両の走行制御装置 |
| JP6637400B2 (ja) * | 2016-10-12 | 2020-01-29 | 本田技研工業株式会社 | 車両制御装置 |
| CN106681318A (zh) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | 自动驾驶中车道线检测短暂丢失的车辆安全控制系统及方法 |
-
2018
- 2018-06-05 CN CN201810570006.0A patent/CN110562251A/zh active Pending
- 2018-12-18 WO PCT/CN2018/121833 patent/WO2019233081A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090296987A1 (en) * | 2008-05-27 | 2009-12-03 | Toyota Jidosha Kabushiki Kaisha | Road lane boundary detection system and road lane boundary detecting method |
| CN106467105A (zh) * | 2015-08-10 | 2017-03-01 | 富士重工业株式会社 | 车道线识别装置 |
| CN107364443A (zh) * | 2016-05-13 | 2017-11-21 | 德尔福技术有限公司 | 用于自动化车辆的车道保持系统 |
| CN107499309A (zh) * | 2016-06-14 | 2017-12-22 | 德尔福技术有限公司 | 用于自主车辆在相机漏失期间的车道保持系统 |
| CN107628028A (zh) * | 2016-07-19 | 2018-01-26 | 株式会社万都 | 车辆辅助驾驶装置 |
| CN106627575A (zh) * | 2016-12-30 | 2017-05-10 | 吉林大学 | 一种车辆偏航预警方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110562251A (zh) | 2019-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019233081A1 (zh) | 一种自动驾驶方法及装置 | |
| US20200265710A1 (en) | Travelling track prediction method and device for vehicle | |
| US11718318B2 (en) | Method and apparatus for planning speed of autonomous vehicle, and storage medium | |
| JP6322268B2 (ja) | 車両用のマップデータを確定するためのシステム及び方法 | |
| CN105539586B (zh) | 用于自主驾驶的车辆躲避移动障碍物的统一的运动规划 | |
| US9227632B1 (en) | Method of path planning for evasive steering maneuver | |
| CN105270410B (zh) | 用于自主驾驶车辆的路径规划的精确曲率估计算法 | |
| JP6005055B2 (ja) | 車両のパーキングアシストシステムにおける駐車軌道を継続的に計算する、検査するおよび／または適応させる方法、コンピュータプログラムおよびパーキングアシストシステム | |
| CN113267199B (zh) | 行驶轨迹规划方法及装置 | |
| JP6809531B2 (ja) | 車両判定方法、走行経路補正方法、車両判定装置、及び走行経路補正装置 | |
| EP3694756B1 (en) | Spiral curve based vertical parking planner system for autonomous driving vehicles | |
| CN110803163B (zh) | 车辆行驶轨迹的预测、车辆跟随目标的选择方法及设备 | |
| US10909377B2 (en) | Tracking objects with multiple cues | |
| JP6941178B2 (ja) | 自動運転制御装置及び方法 | |
| GB2550485A (en) | Enhanced vehicle operation | |
| CN112249014A (zh) | 车辆横向控制方法、车辆以及计算机可读存储介质 | |
| CN114684111A (zh) | 一种车头先入的泊车方法、装置和系统 | |
| CN115127576A (zh) | 路径规划方法、装置、芯片、终端、电子设备及存储介质 | |
| US20220256082A1 (en) | Traveling environment recognition apparatus | |
| JP2019066445A (ja) | 位置補正方法、車両制御方法及び位置補正装置 | |
| CN114228703A (zh) | 一种自动泊车方法、系统、车辆及存储介质 | |
| JP6776842B2 (ja) | 駐車支援方法及び駐車支援装置 | |
| CN116476840A (zh) | 变道行驶方法、装置、设备及存储介质 | |
| JP6243319B2 (ja) | 逸脱判定装置 | |
| JP6306429B2 (ja) | 操舵制御システム |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18921876 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18921876 Country of ref document: EP Kind code of ref document: A1 |