WO2023093306A1 - 车辆换道的控制方法和装置、电子设备和存储介质 - Google Patents

车辆换道的控制方法和装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023093306A1
WO2023093306A1 PCT/CN2022/123369 CN2022123369W WO2023093306A1 WO 2023093306 A1 WO2023093306 A1 WO 2023093306A1 CN 2022123369 W CN2022123369 W CN 2022123369W WO 2023093306 A1 WO2023093306 A1 WO 2023093306A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
information
lane change
boundary data
drivable area
Prior art date
Application number
PCT/CN2022/123369
Other languages
English (en)
French (fr)
Inventor
曾路遥
高智
Original Assignee
上海安亭地平线智能交通技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海安亭地平线智能交通技术有限公司 filed Critical 上海安亭地平线智能交通技术有限公司
Priority to EP22897391.3A priority Critical patent/EP4438429A1/en
Publication of WO2023093306A1 publication Critical patent/WO2023093306A1/zh

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
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • 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
    • B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects

Definitions

  • the present disclosure relates to computer vision technology, in particular to a control method and device for vehicle lane change, electronic equipment and a storage medium.
  • the research on the automatic driving system of autonomous vehicles mainly focuses on the longitudinal control of the road, and less consideration is given to lateral motion such as lane changing.
  • the lateral movement of the vehicle is also an extremely frequent and critical part of the automatic driving process.
  • the automatic lane change function is one of the most basic functions of the automatic driving vehicle.
  • due to the long duration of the automatic lane change function and the variable parameters involved in the scene More, when the vehicle speed is high, once the automatic lane change function goes wrong, it will bring potential safety hazards.
  • image-based target detection is used to determine whether there are parallel vehicles.
  • image-based target detection is used to determine whether there are parallel vehicles.
  • there are large vehicles driving side by side due to the long body of the large vehicles and the high chassis, there will be cases where the parallel large vehicles are missed.
  • Time-changing lanes is very dangerous. Therefore, how to effectively identify parallel large vehicles and ensure the reliability and safety of the automatic lane-changing function of autonomous vehicles has become a technical problem that needs to be solved urgently.
  • Embodiments of the present disclosure provide a vehicle lane change control method and device, electronic equipment, and a storage medium.
  • a control method for vehicle lane change including: acquiring visual information of the surrounding environment; determining boundary data of the current vehicle's drivable area based on the visual information; Area boundary data, determining information of parallel vehicles on at least one side of the current vehicle; determining lane change information based on the information of parallel vehicles; controlling the driving state of the current vehicle according to the lane change information.
  • a vehicle lane change control device including: a first acquisition module, configured to acquire visual information of the surrounding environment; a first processing module, configured to, based on the visual information, Determine the drivable area boundary data of the current vehicle; the second processing module is used to determine the parallel vehicle information on at least one side of the current vehicle based on the drivable area boundary data; the first determination module is used to determine the parallel vehicle information based on the drivable area boundary data; The vehicle information is used to determine the lane change information; the control module is used to control the driving state of the current vehicle according to the lane change information.
  • a computer-readable storage medium stores a computer program, and the computer program is used to perform the control of vehicle lane change described in any of the above-mentioned embodiments of the present disclosure. method.
  • an electronic device includes: a processor; a memory for storing instructions executable by the processor; The executable instructions are read and executed to implement the vehicle lane change control method described in any one of the above-mentioned embodiments of the present disclosure.
  • the visual information of the vehicle's surrounding environment is collected through the vehicle's surrounding sensors, and the drivable area boundary data on both sides of the vehicle is determined based on the visual information. Then judge whether there are parallel vehicles on both sides of the vehicle based on the boundary data of the drivable area, and determine whether the lane change information can be changed based on the judgment result to control the driving state of the vehicle.
  • the accurate and effective detection of parallel vehicles Based on the drivable area, the accurate and effective detection of parallel vehicles The judgment provides accurate and reliable lane-changing information for vehicles to change lanes, thereby improving the reliability and safety of the vehicle's automatic lane-changing function, and solving the problem that the existing technology based on target detection cannot effectively identify parallel large vehicles.
  • FIG. 1 is an application scenario of a vehicle lane change control method provided by an exemplary embodiment of the present disclosure
  • Fig. 2 is a schematic flowchart of a control method for vehicle lane change provided by an exemplary embodiment of the present disclosure
  • Fig. 3 is a schematic flowchart of a control method for vehicle lane change provided by another exemplary embodiment of the present disclosure
  • FIG. 4 is a schematic flowchart of step 203 provided by an exemplary embodiment of the present disclosure.
  • Fig. 5 is an overall flowchart of a control method for vehicle lane change provided by an exemplary embodiment of the present disclosure
  • Fig. 6 is a schematic structural diagram of a vehicle lane-changing control device provided by an exemplary embodiment of the present disclosure
  • Fig. 7 is a schematic structural diagram of a vehicle lane change control device provided by another exemplary embodiment of the present disclosure.
  • Fig. 8 is a schematic structural diagram of a second processing module provided by an exemplary embodiment of the present disclosure.
  • Fig. 9 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure.
  • plural may refer to two or more than two, and “at least one” may refer to one, two or more than two.
  • the term "and/or" in the present disclosure is only an association relationship describing associated objects, indicating that there may be three relationships, for example, A and/or B may indicate: A exists alone, and A and B exist at the same time , there are three cases of B alone.
  • the character "/" in the present disclosure generally indicates that the contextual objects are an "or" relationship.
  • Embodiments of the present disclosure may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which may operate with numerous other general purpose or special purpose computing system environments or configurations.
  • Examples of well known terminal devices, computing systems, environments and/or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick client computers, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the foregoing, among others.
  • Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by the computer system.
  • program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types.
  • the computer system/server can be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network.
  • program modules may be located in both local and remote computing system storage media including storage devices.
  • the inventors found that when the self-driving vehicle needs to change lanes during driving, the target detection is used to identify whether there are vehicles driving side by side in the adjacent lane, and if not, the lane change can be automatically controlled.
  • the target detection is used to identify whether there are vehicles driving side by side in the adjacent lane, and if not, the lane change can be automatically controlled.
  • the target detection is used to identify whether there are vehicles driving side by side in the adjacent lane, and if not, the lane change can be automatically controlled.
  • the target detection is used to identify whether there are vehicles driving side by side in the adjacent lane, and if not, the lane change can be automatically controlled.
  • the target detection is used to identify whether there are vehicles driving side by side in the adjacent lane, and if not, the lane change can be automatically controlled.
  • the reliability and safety of the automatic lane changing function in the prior art are relatively poor.
  • Fig. 1 is an application scenario of a vehicle lane change control method provided by an exemplary embodiment of the present disclosure.
  • the visual information of the environment on both sides can be collected through the side-view camera of the vehicle, and the side-view camera can include The left front camera, the left rear camera, the right front camera and the right rear camera, wherein the left front camera is installed on the left front of the vehicle to collect the visual information of the left rear perspective of the current environment; the left rear camera is installed on the left rear of the vehicle for Collect the visual information of the left front angle of view of the current environment; the right front camera, installed in the right front of the vehicle, is used to collect the visual information of the right rear angle of view of the current environment; the right rear camera, installed in the right rear of the vehicle, is used to collect the right front angle of view of the current environment visual information.
  • the drivable area boundary data includes multiple coordinate points on the drivable area boundary.
  • Each coordinate point can be a coordinate in the vehicle coordinate system point, the vehicle coordinate system can be established according to actual needs.
  • the vehicle coordinate system takes the center of the rear axle of the vehicle as the coordinate origin, the vehicle length direction as the vertical axis (indicated by x), and the vehicle width direction as the horizontal axis (indicated by x y means).
  • Fig. 2 is a schematic flowchart of a method for controlling a vehicle lane change provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic equipment, specifically on a vehicle-mounted computing platform, as shown in Figure 2, including the following steps:
  • Step 201 acquiring visual information of the surrounding environment.
  • the surrounding environment can refer to the environment on the left side and the right side of the current vehicle
  • the visual information can include image information captured by the camera, and can also include information collected by other related sensors, such as point cloud data collected by laser radar, etc., according to Actual demand setting.
  • a left front camera, a left rear camera, a right front camera and a right rear camera can be installed on the vehicle, and based on these cameras, the visual information of the left rear perspective, left front perspective, right rear perspective and right front perspective can be collected.
  • Step 202 based on the visual information, determine the boundary data of the drivable area of the current vehicle.
  • the boundary data of the drivable area includes a plurality of coordinate points on the boundary of the area where the current vehicle can drive, and the boundary of the drivable area refers to the junction between the road area where the current vehicle can drive and obstacles.
  • the method of determining the boundary data of the drivable area can adopt any implementable method. According to different visual information, the method of determining the boundary data of the drivable area is different. For example, if the visual information is image data, obstacles in the image can be identified based on multi-target detection object area and road surface area, so as to obtain the boundary data of the drivable area based on the obstacle area and road surface area; The three-dimensional obstacle information and road surface information identified by the cloud data are used to determine the boundary data of the drivable area, which will not be described in detail.
  • the drivable area boundary data may only include the left drivable area boundary data, or only include the right drivable area boundary data, or include both the left side and the right side, which can be set according to actual needs.
  • the drivable area boundary data on one side may be determined based on the visual information on the side.
  • the visual information collected by the left front camera and the left rear camera is combined as the left visual information
  • the visual information collected by the right front camera and the right rear camera is combined as the right visual information, and then based on the left visual information
  • the boundary data of the drivable area on the left is determined
  • the boundary data of the drivable area on the right is determined based on the visual information on the right.
  • Step 203 based on the drivable area boundary data, determine the parallel vehicle information on at least one side of the current vehicle.
  • the parallel vehicle information on one side of the current vehicle includes the judgment result of whether there is a parallel vehicle on this side. Since the drivable area boundary data is the coordinate point of the boundary between the drivable area and the obstacle, as long as there is a certain range on the current vehicle side If there is a point in the boundary data of the drivable area, it means that there is an obstacle in this range, that is, there are vehicles driving side by side on this side.
  • the parallel vehicle information of the side is determined based on the drivable area boundary data of the side.
  • Step 204 based on the parallel vehicle information, determine lane change information.
  • the lane change information may include judgment result information on whether lane change is possible.
  • the lane change information may include left lane change information and/or right lane change information, that is, whether the left side can change lanes, the right side lane change information, and the right lane change information. Is it possible to change lanes. For one side, if it is determined that there are side-by-side vehicles on this side, the side cannot change lanes. If there are no side-by-side vehicles on this side, then this side can change lanes.
  • the lane-changing information is the lane-changing control decision of the current vehicle Provide evidence.
  • Step 205 control the current driving state of the vehicle according to the lane change information.
  • the current vehicle is controlled to continue driving along the current driving lane; Change lanes on the left or right, if the determined lane change information is that the left side can change lanes and the right side can change lanes, then you can change lanes to the left or right according to the needs, and the vehicle travels
  • the specific control principle of the state is the prior art, and will not be repeated here.
  • the vehicle lane change control method determines the drivable area boundary data around the current vehicle based on the collected visual information of the surrounding environment of the current vehicle, and determines whether at least one side of the current vehicle exists based on the drivable area boundary data.
  • FIG. 3 is a schematic flowchart of a vehicle lane change control method provided by another exemplary embodiment of the present disclosure.
  • the parallel vehicle information on at least one side of the current vehicle includes at least The result information of whether there is a parallel vehicle on one side;
  • the method of the present disclosure before determining the lane change information based on the parallel vehicle information, the method of the present disclosure also includes:
  • Step 301 obtain the current speed of the current vehicle.
  • the current speed of the current vehicle may be obtained through a speed sensor, or may be obtained through any other practicable manner, and may be specifically set according to actual requirements, which is not limited in this embodiment.
  • the lane change information is determined based on the parallel vehicle information in step 204, specifically including:
  • Step 2041 based on the parallel vehicle information and the current speed of the current vehicle, determine lane change information, the lane change information includes the result information of whether the lane change is possible.
  • this disclosure combines the determined parallel vehicles Information and the current speed of the current vehicle to determine the lane change information to further improve the reliability and safety of automatic lane change.
  • a lane change control decision may be made according to the current vehicle speed to determine a specific lane change path. Different lane change paths may be set for different vehicle speeds, and may be specifically set according to actual needs.
  • the speed threshold when it is desired to change lanes, it is also possible to first determine whether the current speed of the current vehicle is less than the preset speed threshold, if it is less than the preset speed threshold, then determine whether there is a parallel vehicle, if it is greater than or equal to the preset speed threshold If the speed threshold is set, it can be directly determined that the lane cannot be changed, and there is no need to judge the situation of parallel vehicles.
  • the present disclosure determines whether a lane change is possible by combining the current speed of the vehicle and the conditions of vehicles traveling side by side on both sides of the vehicle, thereby further improving the reliability and safety of the automatic lane change function.
  • Fig. 4 is a schematic flowchart of step 203 provided by an exemplary embodiment of the present disclosure.
  • the drivable area boundary data includes coordinate points in the vehicle coordinate system, and the corresponding step 203 may specifically include:
  • Step 2031 determine the distance between each coordinate point in the drivable area boundary data and the center line of the vehicle.
  • Step 2032 if the distances of all coordinate points in the first drivable area boundary data corresponding to the first side of at least one side of the current vehicle from the vehicle centerline are greater than a preset threshold, determine that there is no parallel vehicle on the first side .
  • the preset threshold can be set according to the width of the lane and the lateral safety distance of the vehicle changing lanes. For example, it can be set to 10 meters or other values.
  • the center line of the vehicle is the line where the vertical axis of the above vehicle coordinate system is located. If the distance between all coordinate points in the data (taking the drivable area boundary data on the left as an example) and the centerline of the vehicle is greater than the preset threshold, it means that there are no obstacles within 10 meters to the left of the current vehicle, so there is no side-by-side moving vehicles.
  • step 203 also includes:
  • Step 2033 if there is a coordinate point whose distance from the center line of the vehicle is less than or equal to a preset threshold in the first drivable area boundary data corresponding to the first side of at least one side of the current vehicle, then based on the preset filtering rule A drivable area boundary data is screened to obtain a second drivable area boundary data.
  • the first side may be the left side, and the corresponding first drivable area boundary data is the left drivable area boundary data, and the first side may also be the right side, and correspondingly, the first drivable area boundary data is Right side drivable area boundary data.
  • the preset filtering rules can be set according to actual needs. The purpose is to filter out invalid data. For example, invalid data can be coordinate points whose distance from the center line of the vehicle is greater than the preset threshold, continuous horizontal coordinate points, and other noise points.
  • Step 2034 classify the boundary data of the second drivable area based on the support vector machine algorithm, and obtain a classification result.
  • the classification result includes the type to which the second drivable area boundary data belongs, for example, the types include 1 and -1. 1 is used to indicate that there is no parallel vehicle, and -1 is used to indicate that there is a parallel vehicle.
  • Support Vector Machine (SVM) algorithm is a kind of generalized linear classifier (generalized linear classifier) that performs binary classification on data according to supervised learning, and its decision boundary is solved for learning samples A maximum-margin hyperplane, which works well for classification problems. After SVM projects the characteristic parameters into a high-dimensional space, it looks for a hyperplane to divide the data. The goal of SVM is to maximize the interval width under the premise of correct classification, and transform the classification problem into an optimization problem.
  • the specific process of the support vector machine algorithm includes: training based on the training sample data and the preset loss function to obtain a classification model, the classification model includes the classification hyperplane and classification decision function obtained through training, and then based on the classification decision function to realize the classification object (this disclosure Middle is the classification of the second drivable area boundary data).
  • the classification process based on the classification decision function includes: performing a kernel product on the coordinate points in the boundary data of the second drivable area based on the kernel function, multiplying the inner product with the pre-obtained coefficients and summing them, and then summing them based on the signal function The results are categorized.
  • the preset loss function can adopt any implementable loss function, which can be set according to actual needs, and the kernel function can choose a linear kernel function according to actual needs polynomial kernel function Or a Gaussian function (exp(- ⁇ (X i -X j ) 2 )), which is not specifically limited.
  • X i and X j respectively represent the elements in the input vector, corresponding to the two coordinate points in the boundary data of the drivable area in this disclosure, and ⁇ , r, and d are related parameters, which can be set according to actual needs or obtained through learning.
  • the specific principle of the support vector machine algorithm is the prior art, and will not be repeated here.
  • the training sample data may include positive sample data, negative sample data, and corresponding label data.
  • the positive sample data is the drivable area boundary data in the absence of parallel vehicles
  • the negative sample data is the drivable area boundary data in the presence of parallel vehicles.
  • the model parameters are continuously adjusted based on the preset loss function, and finally a trained classification model is obtained. , the specific training process will not be repeated here.
  • the support vector machine algorithm may use a basic support vector machine algorithm or any implementable improved algorithm, which is not limited in this embodiment.
  • Step 2035 determine whether there is a parallel vehicle on the first side.
  • the specific type flag can be set according to actual needs, which is not limited in this disclosure.
  • the present disclosure further judges whether there is a parallel vehicle based on the distance from the center line to determine whether there is a parallel vehicle, which can further improve the reliability and safety of the automatic lane changing function.
  • two classification models based on the SVM algorithm can be used to judge the situation on the left side and the right side respectively, so as to improve the data processing speed .
  • the method of the present disclosure before classifying the second drivable area boundary data based on a support vector machine algorithm and obtaining the classification result, further includes: classifying the second drivable area boundary data Perform normalization processing to obtain the boundary data of the third drivable area; correspondingly, classify the boundary data of the second drivable area based on the support vector machine algorithm to obtain a classification result, including: classifying the data based on the support vector machine algorithm The boundary data of the third drivable area is classified to obtain a classification result.
  • the vertical coordinate since the parallel vehicle judgment problem is strongly dependent on the horizontal coordinate (y coordinate) of the drivable area boundary data, the vertical coordinate does not need to be considered too much, but when classifying based on the support vector machine algorithm, the vertical coordinate is required Coordinates, in order to reduce the impact of the ordinate on the classification results, this disclosure performs normalization processing on the boundary data of the second drivable area, normalizes the ordinates of the coordinate points in the boundary data of the second drivable area, and converts them The overall range is reduced, and the abscissa remains unchanged. For example, all ordinates are normalized to a range of 0-1, or a range smaller than the original range. The specific normalization degree can be set according to actual needs, and this embodiment does not limit it .
  • the classification is to classify the third drivable area boundary data obtained after normalization.
  • the present disclosure normalizes the boundary data of the second drivable area and normalizes the vertical coordinates of its coordinate points to a smaller range, which can effectively reduce the influence of the vertical coordinates on the classification results of the SVM algorithm, thereby further improving the classification accuracy sex.
  • determining the parallel vehicle information on at least one side of the current vehicle based on the drivable area boundary data in step 203 may specifically include: based on the drivable area boundary data of consecutive K frames, determining the Information about parallel vehicles on at least one side of the current vehicle, where K is an integer greater than 1.
  • the setting principle is to ensure the validity of the accumulated data, that is, it should not be too long, and the impact on subsequent control decisions will be reduced if the time is too long , the judgment result may not be real-time enough.
  • this disclosure judges the situation of parallel vehicles based on continuous multi-frame drivable area boundary data.
  • the The drivable area boundary data of the K frames on the side are merged as the drivable area boundary data used to determine the situation of parallel vehicles on the side, and then the side is determined based on the merged drivable area boundary data according to the processing procedures in the foregoing embodiments or examples.
  • parallel vehicle information is a registered trademark of Lucent Technologies Inc.
  • the disclosure determines the parallel vehicle information on at least one side of the current vehicle based on the drivable area boundary data of consecutive K frames, avoids the situation that the data reliability of one frame is low, and further improves the reliability and safety of the automatic lane changing function.
  • determining lane change information based on the parallel vehicle information in step 204 includes: determining the lane change information based on M consecutive determined parallel vehicle information, where M is an integer greater than 1.
  • the value of M can be set according to actual needs.
  • the setting principle is similar to the aforementioned K. After obtaining the determined parallel vehicle information once, counting is performed, and the current parallel vehicle information is stored. After M consecutive acquisitions, the M Together with the results of the second time, it is determined whether the lane can be changed.
  • the specific determination rules can be set according to actual needs, for example, for one side, when there is a preset proportion of the results of M times, there is no parallel vehicle , then it can be determined that the lane change information on this side is capable of changing lanes; for another example, in order to further ensure the safety of lane changing, it is determined that only when the results of M times are that there are no parallel vehicles can change lanes, otherwise it is not possible to change lanes, Then in the
  • the disclosure further improves the reliability of the lane-changing information by determining the lane-changing information based on the parallel vehicle information determined consecutively for M times, thereby improving the reliability and safety of the automatic lane-changing function.
  • the parallel vehicle information determined for any one time may be determined based on one frame of drivable area boundary data, or based on the drivable area boundary of consecutive K frames The data is determined, and the details can be set according to actual needs.
  • FIG. 5 is an overall flowchart of a control method for lane changing of a vehicle provided by an exemplary embodiment of the present disclosure.
  • the left side is taken as an example, the right side is similar, and both sides are judged in parallel.
  • the control method for vehicle lane change specifically includes:
  • step 4 Determine whether there is a point within 10 meters. If there is a point, go to step 4, if there is no point, go to step 11.
  • Any control method for vehicle lane change provided in the embodiments of the present disclosure may be executed by any appropriate device with data processing capabilities, including but not limited to: terminal devices, servers, and the like.
  • any of the vehicle lane change control methods provided in the embodiments of the present disclosure may be executed by a processor, for example, the processor executes any of the vehicle lane change control methods mentioned in the embodiments of the present disclosure by calling corresponding instructions stored in the memory method. I won't go into details below.
  • Fig. 6 is a schematic structural diagram of a vehicle lane change control device provided by an exemplary embodiment of the present disclosure.
  • the device of this embodiment can be used to implement the corresponding method embodiment of the present disclosure.
  • the first acquisition module 501 is configured to acquire visual information of the surrounding environment.
  • the first processing module 502 is configured to determine the drivable region boundary data of the current vehicle based on the visual information obtained by the first obtaining module 501 .
  • the second processing module 503 is configured to determine the parallel vehicle information on at least one side of the current vehicle based on the drivable area boundary data determined by the first processing module 502 .
  • the first determination module 504 is configured to determine lane change information based on the parallel vehicle information determined by the second processing module 503 .
  • the control module 505 is configured to control the current driving state of the vehicle according to the lane change information determined by the first determination module 504 .
  • Fig. 7 is a schematic structural diagram of a vehicle lane change control device provided by another exemplary embodiment of the present disclosure.
  • the parallel vehicle information on at least one side of the current vehicle includes result information of whether there is a parallel vehicle on at least one side of the current vehicle; correspondingly, as shown in FIG. 7 , the device of the present disclosure further includes: The second acquiring module 506 .
  • the second obtaining module 506 is configured to obtain the current speed of the current vehicle; correspondingly, the first determining module 504 is specifically configured to obtain the current speed based on the parallel vehicle information determined by the second processing module 503 and the second obtaining module 506 , to determine the lane change information, where the lane change information includes result information on whether the lane change is possible.
  • Fig. 8 is a schematic structural diagram of a second processing module provided by an exemplary embodiment of the present disclosure.
  • the drivable area boundary data includes coordinate points in the vehicle coordinate system; as shown in FIG. 8 , the second processing module 503 includes: a first unit 5031 configured to, if the at least one If the distances of all coordinate points in the first drivable area boundary data corresponding to the first side from the vehicle centerline are greater than a preset threshold, it is determined that there is no parallel vehicle on the first side.
  • the second processing module 503 further includes: a second unit 5032 , a third unit 5033 and a fourth unit 5034 .
  • the second unit 5032 is configured to: if there are coordinate points in the boundary data of the first drivable area whose distance from the center line of the vehicle is less than or equal to the preset threshold, the first drivable area is selected based on a preset filtering rule.
  • the third unit 5033 is used to classify the boundary data of the second drivable area obtained by the second unit 5032 based on the support vector machine algorithm, and obtain the classification result;
  • the fourth unit 5034 is configured to determine whether there is a parallel vehicle on the first side according to the classification result obtained by the third unit 5033 .
  • the second processing module 503 further includes: a fifth unit 5035, configured to perform normalization processing on the second drivable area boundary data obtained by the second unit 5032 to obtain the third drivable area boundary data
  • the third unit 5033 is specifically configured to classify the third drivable area boundary data obtained by the fifth unit 5035 based on the support vector machine algorithm, and obtain a classification result.
  • the second processing module 503 is specifically configured to determine the parallel vehicle information on at least one side of the current vehicle based on continuous K frames of drivable area boundary data, where K is an integer greater than 1.
  • the first determining module 504 is specifically configured to determine the lane change information based on the parallel vehicle information determined for M consecutive times, where M is an integer greater than 1.
  • An embodiment of the present disclosure also provides an electronic device, including: a memory configured to store a computer program;
  • the processor is configured to execute the computer program stored in the memory, and when the computer program is executed, implement the vehicle lane change control method described in any one of the above-mentioned embodiments of the present disclosure.
  • Fig. 9 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure.
  • the electronic device 10 includes one or more processors 11 and memory 12 .
  • Processor 11 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in electronic device 10 to perform desired functions.
  • CPU central processing unit
  • Processor 11 may control other components in electronic device 10 to perform desired functions.
  • Memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache).
  • the non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like.
  • One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the vehicle lane-changing control method and the above-mentioned various embodiments of the present disclosure. / or other desired functionality.
  • Various contents such as input signal, signal component, noise component, etc. may also be stored in the computer-readable storage medium.
  • the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected through a bus system and/or other forms of connection mechanisms (not shown).
  • the input device 13 may be the above-mentioned microphone or microphone array, which is used to capture the input signal of the sound source.
  • the input device 13 may also include, for example, a keyboard, a mouse, and the like.
  • the output device 14 can output various information to the outside, including determined distance information, direction information, and the like.
  • the output device 14 may include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, and the like.
  • the electronic device 10 may also include any other suitable components.
  • embodiments of the present disclosure may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the above-mentioned "exemplary method" of this specification.
  • the steps in the control method for vehicle lane change according to various embodiments of the present disclosure described in the section.
  • the computer program product can be written in any combination of one or more programming languages to execute the program codes for performing the operations of the embodiments of the present disclosure, and the programming languages include object-oriented programming languages, such as Java, C++, etc. , also includes conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.
  • embodiments of the present disclosure may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, cause the processor to execute the above-mentioned "Exemplary Method" section of this specification.
  • the computer readable storage medium may employ any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • a readable storage medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof, for example. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • the methods and apparatus of the present disclosure may be implemented in many ways.
  • the methods and apparatuses of the present disclosure may be implemented by software, hardware, firmware or any combination of software, hardware, and firmware.
  • the above sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise.
  • the present disclosure can also be implemented as programs recorded in recording media, and these programs include machine-readable instructions for implementing the vehicle lane change control method according to the present disclosure.
  • the present disclosure also covers a recording medium storing a program for executing the control method for vehicle lane change according to the present disclosure.
  • each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种车辆换道的控制方法和装置、电子设备和存储介质，其中，方法包括：获取周围环境的视觉信息；基于视觉信息，确定当前车辆的可行驶区域边界数据；基于可行驶区域边界数据，确定当前车辆至少一侧的并行车辆信息；基于并行车辆信息，确定换道信息；根据换道信息控制当前车辆的行驶状态。该控制方法和装置可以为车辆的换道控制决策提供准确可靠的依据，避免因遗漏识别并排行驶的大型车辆而为换道带来安全隐患的情况发生，从而提高车辆自动换道功能的可靠性和安全性。

Description

车辆换道的控制方法和装置、电子设备和存储介质
本公开要求在2021年11月24日提交的、申请号为202111409699.3、发明名称为“车辆换道的控制方法和装置、电子设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及计算机视觉技术，尤其是一种车辆换道的控制方法和装置、电子设备和存储介质。
背景技术
目前，对自动驾驶车辆的自动驾驶系统的研究主要集中于道路纵向的控制，而对于换道这样的横向运动考虑较少。车辆的横向运动也是自动驾驶过程中极为频繁且关键的部分，自动换道功能是自动驾驶车辆最基本的功能之一，但由于自动换道功能持续时间较长，且涉及到的场景可变参数较多，在车速较高时，自动换道功能一旦出错将带来安全隐患。
现有技术中，基于图像的目标检测来确定是否有并行车辆，当存在并排行驶的大型车辆时，由于大型车辆车身较长、底盘较高，会存在遗漏识别到并行的大型车辆的情况，此时换道是十分危险的，因此，如何能够有效识别并行的大型车辆，保证自动驾驶车辆的自动换道功能的可靠性和安全性成为亟需解决的技术问题。
发明内容
为了解决上述技术问题，提出了本公开。本公开的实施例提供了一种车辆换道的控制方法和装置、电子设备和存储介质。
根据本公开实施例的一个方面，提供了一种车辆换道的控制方法，包括：获取周围环境的视觉信息；基于所述视觉信息，确定当前车辆的可行驶区域边界数据；基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息；基于所述并行车辆信息，确定换道信息；根据所述换道信息控制所述当前车辆的行驶状态。
根据本公开实施例的另一个方面，提供了一种车辆换道的控制装置，包括：第一获取模块，用于获取周围环境的视觉信息；第一处理模块，用于基于所述视觉信息，确定当前车辆的可行驶区域边界数据；第二处理模块，用于基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息；第一确定模块，用于基于所述并行车辆信息，确定换道信息；控制模块，用于根据所述换道信息控制所述当前车辆的行驶状态。
根据本公开实施例的再一方面，提供一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行本公开上述任一实施例所述的车辆换道的控制方法。
根据本公开实施例的又一方面，提供一种电子设备，所述电子设备包括：处理器；用于存储所述处理器可执行指令的存储器；所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现本公开上述任一实施例所述的车辆换道的控制方法。
基于本公开上述实施例提供的车辆换道的控制方法和装置、电子设备和存储介质，通过车辆周围传感器采集车辆周围环境的视觉信息，基于视觉信息确定车辆的两侧的可行驶区域边界数据，进而基于可行驶区域边界数据来判断车辆两侧是否存在并行车辆，并基于判断结果确定是否能换道的换道信息，以控制车辆的行驶状态，基于可行驶区域实现了对并行车辆的准确有效的判断，为车辆换道提供准确可靠的换道信息，进而提高车辆自动换道功能的可靠性和安全性，解决了现有技术基于目标检测无法有效识别并行大型车辆的问题。
下面通过附图和实施例，对本公开的技术方案做进一步的详细描述。
附图说明
通过结合附图对本公开实施例进行更详细的描述，本公开的上述以及其他目的、特征和优势将变得更加明显。附图用来提供对本公开实施例的进一步理解，并且构成说明书的一部分，与本公开实施例一起用于解释本公开，并不构成对本公开的限制。在附图中，相同的参考标号通常代表相同部件或步骤。
图1是本公开一示例性实施例提供的车辆换道的控制方法的应用场景；
图2是本公开一示例性实施例提供的车辆换道的控制方法的流程示意图；
图3是本公开另一个示例性实施例提供的车辆换道的控制方法的流程示意图；
图4是本公开一个示例性实施例提供的步骤203的流程示意图；
图5是本公开一示例性实施例提供的车辆换道的控制方法的一种整体流程框图；
图6是本公开一示例性实施例提供的车辆换道的控制装置的结构示意图；
图7是本公开另一示例性实施例提供的车辆换道的控制装置的结构示意图；
图8是本公开一示例性实施例提供的第二处理模块的结构示意图；
图9是本公开一示例性实施例提供的电子设备的结构示意图。
具体实施方式
下面，将参考附图详细地描述根据本公开的示例实施例。显然，所描述的实施例仅仅是本公开的一部分实施例，而不是本公开的全部实施例，应理解，本公开不受这里描述的示例实施例的限制。
应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。
本领域技术人员可以理解，本公开实施例中的“第一”、“第二”等术语仅用于区别不同步骤、设备或模块等，既不代表任何特定技术含义，也不表示它们之间的必然逻辑顺序。
还应理解，在本公开实施例中，“多个”可以指两个或两个以上，“至少一个”可以指一个、两个或两个以上。
还应理解，对于本公开实施例中提及的任一部件、数据或结构，在没有明确限定或者在前后文给出相反启示的情况下，一般可以理解为一个或多个。
另外，本公开中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本公开中字符“/”，一般表示前后关联对象是一种“或”的关系。
还应理解，本公开对各个实施例的描述着重强调各个实施例之间的不同之处，其相同或相似之处可以相互参考，为了简洁，不再一一赘述。
同时，应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
本公开实施例可以应用于终端设备、计算机系统、服务器等电子设备，其可与众多其它通用或专用计算系统环境或配置一起操作。适于与终端设备、计算机系统、服务器等电子设备一起使用的众所周知的终端设备、计算系统、环境和/或配置的例子包括但不限于：个人计算机系统、服务器计算机系统、瘦客户机、厚客户机、手持或膝上设备、基于微处理器的系统、机顶盒、可编程消费电子产品、网络个人电脑、小型计算机系统、大型计算机系统和包括上述任何系统的分布式云计算技术环境，等等。
终端设备、计算机系统、服务器等电子设备可以在由计算机系统执行的计算机系统可执行指令(诸如程序模块)的一般语境下描述。通常，程序模块可以包括例程、程序、目标程序、组件、逻辑、数据结构等等，它们执行特定的任务或者实现特定的抽象数据类型。计算机系统/服务器可以在分布式云计算环境中实施，分布式云计算环境中，任务是由通过通信网络链接的远程处理设备执行的。在分布式云计算环境中，程序模块可以位于包括存储设备的本地或远程计算系统存储介质上。
本公开概述
在实现本公开的过程中，发明人发现，自动驾驶车辆在行驶过程中需要换道时，通过目标检测来识别相邻车道是否有并排行驶的车辆，若没有则可以自动控制换道，但是，当存在并排行驶的大型车辆时，由于大型车辆车身较长、底盘较高，会存在遗漏识别并行的大型车辆的情况，此时换道是十分危险的。可见现有技术自动换道功能可靠性和安全性较差。
示例性概述
图1是本公开一示例性实施例提供的车辆换道的控制方法的应用场景。
如图1所示，针对并排行驶车辆的情况，为了能够保证换道的安全性，利用本公开提供的技术方案，可以通过车辆的侧视摄像头采集两侧环境的视觉信息，侧视摄像头可以包括左前摄像头、左后摄像头、右前摄像头和右后摄像头，其中，左前摄像头，安装于车辆左前方，用于采集当前环境的左后视角的视觉信息；左后摄像头，安装于车辆左后方，用于采集当前环境的左前视角的视觉信息；右前摄像头，安装于车辆右前方，用于采集当前环境的右后视角的视觉信息；右后摄像头，安装于车辆右后方，用于采集当前环 境的右前视角的视觉信息。基于各摄像头采集的视觉信息确定车辆两侧的可行驶区域(free space)边界数据，可行驶区域边界数据包括可行驶区域边界上的多个坐标点，各坐标点可以是车辆坐标系下的坐标点，车辆坐标系可以根据实际需求建立，本公开实施例中车辆坐标系以车辆后轴中心为坐标原点，以车辆长度方向为纵轴(用x表示)，以车辆宽度方向为横轴(用y表示)。基于车辆两侧的可行驶区域边界数据来判断车辆两侧车道是否存在并排行驶的车辆，从而为车辆的换道控制提供更可靠的依据，避免遗漏识别并行的大型车辆的情况发生，从而提高自动换道功能的可靠性和安全性。
示例性方法
图2是本公开一示例性实施例提供的车辆换道的控制方法的流程示意图。本实施例可应用在电子设备上，具体比如车载计算平台上，如图2所示，包括如下步骤：
步骤201，获取周围环境的视觉信息。
其中，周围环境可以是指当前车辆左侧环境和右侧环境，视觉信息可以包括摄像头拍摄的图像信息，还可以包括其他相关传感器采集的信息，比如激光雷达等采集的点云数据，具体可以根据实际需求设置。以摄像头为例，可以在车辆上安装左前摄像头、左后摄像头、右前摄像头和右后摄像头，基于这些摄像头采集左后视角、左前视角、右后视角和右前视角的视觉信息。
步骤202，基于视觉信息，确定当前车辆的可行驶区域边界数据。
其中，可行驶区域边界数据包括当前车辆可行驶的区域边界上的多个坐标点，可行驶区域边界是指当前车辆可行驶道路区域与障碍物的交界。
可行驶区域边界数据的确定方式可以采用任意可实施的方式，根据视觉信息的不同，确定可行驶区域边界数据的方式不同，比如视觉信息为图像数据，则可以基于多目标检测识别图像中的障碍物区域和路面区域，从而基于障碍物区域和路面区域来获得可行驶区域边界数据；若视觉信息包括图像数据和点云数据，则可以结合基于图像数据识别的障碍物区域、路面区域，基于点云数据识别出的三维障碍物信息和路面信息来确定可行驶区域边界数据，具体不再赘述。
可行驶区域边界数据可以是只包括左侧可行驶区域边界数据，也可以是只包括右侧可行驶区域边界数据，还可以是既包括左侧又包括右侧，具体可以根据实际需求设置。其中，对于一侧的可行驶区域边界数据，可以基于该侧的视觉信息来确定。
示例性的，对左前摄像头和左后摄像头采集的视觉信息进行合并，作为左侧视觉信息，对于右前摄像头和右后摄像头采集的视觉信息进行合并，作为右侧视觉信息，进而基于左侧视觉信息确定左侧可行驶区域边界数据，基于右侧视觉信息确定右侧可行驶区域边界数据。
步骤203，基于可行驶区域边界数据，确定当前车辆至少一侧的并行车辆信息。
其中，当前车辆的一侧的并行车辆信息包括该侧是否存在并行车辆的判断结果，由于可行驶区域边界数据是可行驶区域与障碍物的交界的坐标点，因此只要在当前车辆一侧一定范围内存在可行驶区域边界数据中的点，则表示在该范围内存在障碍物，即认为该侧存在并排行驶的车辆。
在实际应用中，可以根据实际需求设置需要确定当前车辆的哪一侧是否有并排行驶的车辆，比如可以只判断左侧，也可以只判断右侧，还可以同时判断左侧和右侧，本实施例不做限定。针对一侧，基于该侧的可行驶区域边界数据来确定该侧的并行车辆信息。
步骤204，基于并行车辆信息，确定换道信息。
其中，换道信息可以包括是否能换道的判断结果信息，与前面步骤相应，换道信息可以包括左侧换道信息和/或右侧换道信息，即左侧是否能换道、右侧是否能换道。对于一侧来说，若确定该侧有并排行驶的车辆，则该侧不能换道，若该侧没有并排行驶的车辆，则该侧可以换道，换道信息为当前车辆的换道控制决策提供依据。
步骤205，根据换道信息控制当前车辆的行驶状态。
具体的，若确定的换道信息为不能换道，则控制当前车辆继续沿当前行驶车道行驶，若确定的换道信息为左侧能换道或右侧能换道，则可以控制当前车辆向左侧换道或向右侧换道，若确定的换道信息为左侧能换道右侧也能换道，则可以根据需求既可以向左换道，也可以向右换道，车辆行驶状态的具体控制原理为现有技术，在此不再赘述。
本实施例提供的车辆换道的控制方法，基于采集的当前车辆的周围环境的视觉信息确定当前车辆周围的可行驶区域边界数据，基于可行驶区域边界数据来判断当前车辆的至少一侧是否存在并排行驶的车辆，进而基于并行车辆情况来确定当前是否能换道，为车辆的换道控制决策提供准确可靠的依据，避免因遗漏识别并排行驶的大型车辆而为换道带来安全隐患的情况发生，从而提高车辆自动换道功能的可靠性和安全性。
在一个可选示例中，图3是本公开另一个示例性实施例提供的车辆换道的控制方法的流程示意图，本示例中，当前车辆的至少一侧的并行车辆信息包括该当前车辆的至少一侧是否存在并行车辆的结果信息； 如图3所示，在基于并行车辆信息，确定换道信息之前，本公开的方法还包括：
步骤301，获取当前车辆的当前速度。
其中，当前车辆的当前速度可以通过速度传感器获得，也可以通过其他任意可实施的方式获得，具体可以根据实际需求设置，本实施例不做限定。
相应的，步骤204的基于并行车辆信息，确定换道信息，具体包括：
步骤2041，基于并行车辆信息及当前车辆的当前速度，确定换道信息，换道信息包括是否能换道的结果信息。
为了保证车辆行驶的安全性，车辆的横向运动会受到当前车速的限制，当车速太大时不适合换道，车速级别不同时，换道采取的路径也不同，因此，本公开结合确定的并行车辆信息和当前车辆的当前速度来确定换道信息，以进一步提高自动换道的可靠性和安全性。
示例性的，对于一侧来说，若该侧没有并行车辆，但是当前车辆的当前速度大于预设速度阈值，则确定该侧不能换道。
在一个可选示例中，当确定能够换道时，还可以根据当前车速进行换道控制决策，来确定具体的换道路径，不同车速可以设置不同的换道路径，具体可以根据实际需求设置。
在一个可选示例中，在想要换道时，也可以是先判断当前车辆的当前速度是否小于预设速度阈值，若小于预设速度阈值，再判断是否有并行车辆，若大于或等于预设速度阈值，则可以直接确定不能换道，无需再进行并行车辆情况判断。
本公开通过结合车辆当前速度及车辆两侧并排行驶车辆的情况来确定是否能换道，进一步提高自动换道功能的可靠性和安全性。
图4是本公开一个示例性实施例提供的步骤203的流程示意图。
在一个可选示例中，如图4所示，可行驶区域边界数据包括车辆坐标系下的坐标点，相应的步骤203具体可以包括：
步骤2031，确定可行驶区域边界数据中各坐标点与车辆中心线的距离。
步骤2032，若当前车辆至少一侧中的第一侧对应的第一可行驶区域边界数据中的所有坐标点距车辆中心线的距离均大于预设阈值，则确定所述第一侧没有并行车辆。
其中，预设阈值可以根据车道宽度情况及车辆换道横向安全距离进行设置，比如可以设置为10米或其他值，车辆中心线是上述车辆坐标系中纵轴所在的线，当可行驶区域边界数据(以左侧可行驶区域边界数据为例)中所有坐标点距车辆中心线的距离均大于预设阈值，则表示在当前车辆的左侧10米范围内不存在障碍物，因此不存在并排行驶的车辆。
在一个可选示例中，步骤203还包括：
步骤2033，若当前车辆至少一侧中的第一侧对应的第一可行驶区域边界数据中，存在距车辆中心线的距离小于或等于预设阈值的坐标点，则基于预设筛选规则对第一可行驶区域边界数据进行筛选，获得第二可行驶区域边界数据。
其中，第一侧可以是左侧，相应的第一可行驶区域边界数据即为左侧可行驶区域边界数据，第一侧也可以是右侧，相应的，第一可行驶区域边界数据即为右侧可行驶区域边界数据。预设筛选规则可以根据实际需求设置，目的是筛选出无效数据，无效数据比如可以是距车辆中心线的距离大于预设阈值的坐标点、连续横向的坐标点及其他噪点等。当第一可行驶区域边界数据中存在距车辆中心线的距离小于预设阈值的坐标点时，表示在当前车辆第一侧预设阈值距离的范围内存在障碍物，可能会对当前车辆换道带来安全隐患，因此需要进一步确认是否能够换道。
步骤2034，基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果。
其中，分类结果包括第二可行驶区域边界数据所属类型，类型比如包括1和-1两种。1用于表示没有并行车辆，-1用于表示有并行车辆。
支持向量机(Support Vector Machine，简称：SVM)算法是一类按监督学习(supervised learning)方式对数据进行二元分类的广义线性分类器(generalized linear classifier)，其决策边界是对学习样本求解的最大边距超平面，可以很好地解决分类问题。SVM将特征参数投影到高维空间后，寻找超平面对数据进行划分。SVM的目标是在正确分类的前提下，最大化间隔宽度，将分类问题转化为最优化问题。
支持向量机算法的具体流程包括：基于训练样本数据及预设损失函数进行训练获得分类模型，分类模型包括训练获得的分类超平面和分类决策函数，进而基于分类决策函数实现对待分类对象(本公开中即第二可行驶区域边界数据)的分类。基于分类决策函数的分类过程包括：基于核函数对第二可行驶区域边界数据中的坐标点进行核内积，内积后与预先获得的系数相乘并求和，进而基于signal函数对求和结果进行分类。其中，预设损失函数可以采用任意可实施的损失函数，具体可以根据实际需求设置，核函数可以根据实际需求选择线性核函数
Figure PCTCN2022123369-appb-000001
多项式核函数
Figure PCTCN2022123369-appb-000002
或高斯函数(exp(-γ(X i-X j) 2))，具体不做限定。其中，X i，X j分别表示输入向量中的元素，对应本公开中可行驶区 域边界数据中的两个坐标点，γ、r、d为相关参数，可以根据实际需求设置或通过学习获得。支持向量机算法的具体原理为现有技术，在此不再赘述。在训练过程中，训练样本数据可以包括正样本数据和负样本数据，及对应的标签数据。正样本数据为不存在并行车辆情况下的可行驶区域边界数据，负样本数据为存在并行车辆情况下的可行驶区域边界数据，基于预设损失函数不断调整模型参数，最终获得训练好的分类模型，具体训练过程不再赘述。
在实际应用中，支持向量机算法可以采用支持向量机的基本算法或任意可实施的改进算法，本实施例不做限定。
步骤2035，根据所述分类结果，确定所述第一侧是否存在并行车辆。
具体的，可以根据分类结果的类型标志及类型标志与含义的对应关系确定第一侧是否存在并行车辆，比如类型标志为1，则确定不存在并行车辆，类型标志为-1则确定存在并行车辆，具体类型标志可以根据实际需求设置，本公开不做限定。
本公开基于支持向量机算法对无法根据与中心线距离判断是否存在并行车辆的情况进一步进行判断，来确定是否存在并行车辆，可以进一步提高自动换道功能的可靠性和安全性。
在一个可选示例中，对于需要判断当前车辆左右两侧是否有并排行驶车辆的情况，可以采用两个基于SVM算法的分类模型，分别对左侧和右侧情况进行判断，以提高数据处理速度。两模型综合输出包括左侧和右侧分类结果的二维向量，比如(L，R)＝(1，-1)，或者(L，R)＝(1，0)，其中1表示没有并行车辆，-1、0表示有并行车辆，具体表示方式不做限定。
在一个可选示例中，在所述基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果之前，本公开的方法还包括：对所述第二可行驶区域边界数据进行归一化处理，获得第三可行驶区域边界数据；相应的，所述基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果，包括：基于支持向量机算法对所述第三可行驶区域边界数据进行分类，获得分类结果。
具体的，由于并行车辆判断问题对可行驶区域边界数据的横向坐标(y坐标)依赖较强，而对纵坐标不需要太多考虑，但是在基于支持向量机算法进行分类时，需要用到纵坐标，为了降低纵坐标对分类结果的影响，本公开对第二可行驶区域边界数据进行归一化处理，将第二可行驶区域边界数据中的坐标点的纵坐标进行归一化，将其整体范围缩小，横坐标保持不变，比如将所有纵坐标归一化到0-1范围，或者比原来范围较小的范围，具体归一化程度可以根据实际需求设置，本实施例不做限定。相应地，分类时是对归一化后获得的第三可行驶区域边界数据进行分类。
可以理解地，在对支持向量机分类模型进行训练时，相应地，同样需要对训练样本数据进行归一化。
本公开通过对第二可行驶区域边界数据进行归一化，将其坐标点的纵坐标归一化到更小的范围，可以有效降低纵坐标对SVM算法分类结果的影响，从而进一步提高分类准确性。
在一个可选示例中，步骤203的基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，具体可以包括：基于连续K帧的可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，其中，K为大于1的整数。
其中，K可以根据实际需求设置，比如可以设置为K＝2或K＝3，设置原则为保证累积数据的有效性，也即不能时间过长，时间过长其对后续控制决策的影响减小，导致判断结果可能不够实时，为了进一步提高并行车辆情况判断的准确性，本公开基于连续多帧的可行驶区域边界数据来判断并行车辆情况，具体来说，针对一侧的情况，可以将该侧的K帧的可行驶区域边界数据合并，作为用于确定该侧并行车辆情况的可行驶区域边界数据，进而基于合并的可行驶区域边界数据按照前述实施例或示例中的处理过程确定该侧的并行车辆信息。
本公开通过基于连续K帧的可行驶区域边界数据，确定当前车辆至少一侧的并行车辆信息，避免一帧的数据可靠性较低的情况，进一步提高自动换道功能的可靠性和安全性。
在一个可选示例中，步骤204的基于所述并行车辆信息，确定换道信息，包括：基于连续M次确定的并行车辆信息，确定所述换道信息，其中，M为大于1的整数。
其中，M的值可以根据实际需求设置，设置原则与前述的K类似，当获得一次确定的并行车辆信息后进行计数，将本次的并行车辆信息进行存储，连续获得M次后，综合这M次的结果一起确定是否能换道。
示例性的，以左右两侧均判断为例，获得了M＝3次的车辆并行信息(L，R)分别为(1，0)、(1，0)、(1，0)，其中，L表示左侧，R表示右侧，1表示没有并行车辆(也可以认为表示本次确定的结果是能换道)，0表示有并行车辆(也即表示本次判断的结果是不能换道)，综合这3次的结果做出最终是否能换道的决策，具体确定规则可以根据实际需求设置，比如对于一侧来说，当M次的结果中有预设比例的结果为没有并行车辆时，则可以确定该侧的换道信息为能换道；再比如，为了进一步保证换道的安全性，确定当M次的结果均为没有并行车辆时才可以换道，否则不可以换道，那么上述3次结果中左侧3次都是1，因此左侧能换道，右侧3次都是0，因此右侧不可以换道，最终的换道信息即包括左侧能换道，右侧不能换道。
本公开通过基于连续M次确定的并行车辆信息，确定换道信息，进一步提高换道信息的可靠性，从而 提高自动换道功能的可靠性和安全性。
在一个可选示例中，连续M次确定的并行车辆信息中，其中任一次确定的并行车辆信息可以是基于一帧可行驶区域边界数据确定的，也可以是基于连续K帧的可行驶区域边界数据确定的，具体可以根据实际需求设置。
示例性的，第1次，基于累积的连续3帧的可行驶区域边界数据，确定当前车辆左右两侧的并行车辆信息，即为一次确定的并行车辆信息，之后第2次，又累积了3帧的可行驶区域边界数据，再确定当前车辆左右两侧的并行车辆信息，则有了两次确定的并行车辆信息，以此类推，累积连续M次(比如3次)确定的并行车辆信息，综合用于确定最终的换道信息。
在一个可选示例中，图5是本公开一示例性实施例提供的车辆换道的控制方法的一种整体流程框图。本示例中，如图5所示，以左侧为例，右侧类似，两侧则并行判断，车辆换道的控制方法具体包括：
1、获取周围环境的视觉信息。
2、基于视觉信息确定当前车辆的左侧可行驶区域边界数据。
3、判断10米范围内是否有点。若有点则转步骤4，若无点则转步骤11。
即判断距车辆中心线的横向距离10米范围内是否存在可行驶区域边界数据中的点。
4、从左侧可行驶区域边界数据中剔除10米范围外的点，获得第二可行驶区域边界数据。
5、对第二可行驶区域边界数据进行归一化，获得第三可行驶区域边界数据。
6、累积K帧的第三可行驶区域边界数据，获得第四可行驶区域边界数据。
7、基于支持向量机算法对第四可行驶区域边界数据进行分类，获得分类结果。
8、根据分类结果确定左侧是否存在并行车辆，获得并行车辆信息。
9、基于连续M次确定的并行车辆信息，确定左侧最终的换道信息。
10、根据换道信息控制当前车辆的行驶状态。
11、确定换道信息为左侧能换道，转步骤10。
本公开实施例提供的任一种车辆换道的控制方法可以由任意适当的具有数据处理能力的设备执行，包括但不限于：终端设备和服务器等。或者，本公开实施例提供的任一种车辆换道的控制方法可以由处理器执行，如处理器通过调用存储器存储的相应指令来执行本公开实施例提及的任一种车辆换道的控制方法。下文不再赘述。
示例性装置
图6是本公开一示例性实施例提供的车辆换道的控制装置的结构示意图。该实施例的装置可用于实现本公开相应的方法实施例，如图6所示的装置包括：第一获取模块501、第一处理模块502、第二处理模块503、第一确定模块504和控制模块505。
第一获取模块501，用于获取周围环境的视觉信息。
第一处理模块502，用于基于第一获取模块501获取的视觉信息，确定当前车辆的可行驶区域边界数据。
第二处理模块503，用于基于第一处理模块502确定的可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息。
第一确定模块504，用于基于第二处理模块503确定的并行车辆信息，确定换道信息。
控制模块505，用于根据第一确定模块504确定的换道信息控制所述当前车辆的行驶状态。
图7是本公开另一示例性实施例提供的车辆换道的控制装置的结构示意图。
在一个可选示例中，所述当前车辆的至少一侧的并行车辆信息包括当前车辆的至少一侧是否存在并行车辆的结果信息；相应的，如图7所示，本公开的装置还包括：第二获取模块506。第二获取模块506，用于获取所述当前车辆的当前速度；相应的，第一确定模块504，具体用于基于第二处理模块503确定的并行车辆信息及第二获取模块506获取的当前速度，确定所述换道信息，所述换道信息包括是否能换道的结果信息。
图8是本公开一示例性实施例提供的第二处理模块的结构示意图。
在一个可选示例中，所述可行驶区域边界数据包括车辆坐标系下的坐标点；如图8所示，所述第二处理模块503包括：第一单元5031，用于若所述至少一侧中的第一侧对应的第一可行驶区域边界数据中的所有坐标点距车辆中心线的距离均大于预设阈值，则确定所述第一侧没有并行车辆。
在一个可选示例中，所述第二处理模块503还包括：第二单元5032、第三单元5033和第四单元5034。第二单元5032，用于若所述第一可行驶区域边界数据中，存在距车辆中心线的距离小于或等于所述预设阈值的坐标点，则基于预设筛选规则对所述第一可行驶区域边界数据进行筛选，获得第二可行驶区域边界数据；第三单元5033，用于基于支持向量机算法对第二单元5032获得的第二可行驶区域边界数据进行分类，获得分类结果；第四单元5034，用于根据第三单元5033获得的分类结果，确定所述第一侧是否存在并行 车辆。
在一个可选示例中，第二处理模块503还包括：第五单元5035，用于对第二单元5032获得的第二可行驶区域边界数据进行归一化处理，获得第三可行驶区域边界数据；相应的，第三单元5033，具体用于基于支持向量机算法对第五单元5035获得的第三可行驶区域边界数据进行分类，获得分类结果。
在一个可选示例中，第二处理模块503，具体用于基于连续K帧的可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，其中，K为大于1的整数。
在一个可选示例中，第一确定模块504具体用于基于连续M次确定的并行车辆信息，确定所述换道信息，其中，M为大于1的整数。
示例性电子设备
本公开实施例还提供了一种电子设备，包括：存储器，用于存储计算机程序；
处理器，用于执行所述存储器中存储的计算机程序，且所述计算机程序被执行时，实现本公开上述任一实施例所述的车辆换道的控制方法。
图9是本公开一示例性实施例提供的电子设备的结构示意图。本实施例中，如图9所示，该电子设备10包括一个或多个处理器11和存储器12。
处理器11可以是中央处理单元(CPU)或者具有数据处理能力和/或指令执行能力的其他形式的处理单元，并且可以控制电子设备10中的其他组件以执行期望的功能。
存储器12可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。在所述计算机可读存储介质上可以存储一个或多个计算机程序指令，处理器11可以运行所述程序指令，以实现上文所述的本公开的各个实施例的车辆换道的控制方法以及/或者其他期望的功能。在所述计算机可读存储介质中还可以存储诸如输入信号、信号分量、噪声分量等各种内容。
在一个示例中，电子设备10还可以包括：输入装置13和输出装置14，这些组件通过总线系统和/或其他形式的连接机构(未示出)互连。
例如，该输入装置13可以是上述的麦克风或麦克风阵列，用于捕捉声源的输入信号。
此外，该输入装置13还可以包括例如键盘、鼠标等等。
该输出装置14可以向外部输出各种信息，包括确定出的距离信息、方向信息等。该输出装置14可以包括例如显示器、扬声器、打印机、以及通信网络及其所连接的远程输出设备等等。
当然，为了简化，图9中仅示出了该电子设备10中与本公开有关的组件中的一些，省略了诸如总线、输入/输出接口等等的组件。除此之外，根据具体应用情况，电子设备10还可以包括任何其他适当的组件。
示例性计算机程序产品和计算机可读存储介质
除了上述方法和设备以外，本公开的实施例还可以是计算机程序产品，其包括计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本公开各种实施例的车辆换道的控制方法中的步骤。
所述计算机程序产品可以以一种或多种程序设计语言的任意组合来编写用于执行本公开实施例操作的程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、C++等，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。
此外，本公开的实施例还可以是计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本公开各种实施例的车辆换道的控制方法中的步骤。
所述计算机可读存储介质可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以包括但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
以上结合具体实施例描述了本公开的基本原理，但是，需要指出的是，在本公开中提及的优点、优势、效果等仅是示例而非限制，不能认为这些优点、优势、效果等是本公开的各个实施例必须具备的。另外，上述公开的具体细节仅是为了示例的作用和便于理解的作用，而非限制，上述细节并不限制本公开为必须 采用上述具体的细节来实现。
本说明书中各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似的部分相互参见即可。对于系统实施例而言，由于其与方法实施例基本对应，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
本公开中涉及的器件、装置、设备、系统的方框图仅作为例示性的例子并且不意图要求或暗示必须按照方框图示出的方式进行连接、布置、配置。如本领域技术人员将认识到的，可以按任意方式连接、布置、配置这些器件、装置、设备、系统。诸如“包括”、“包含”、“具有”等等的词语是开放性词汇，指“包括但不限于”，且可与其互换使用。这里所使用的词汇“或”和“和”指词汇“和/或”，且可与其互换使用，除非上下文明确指示不是如此。这里所使用的词汇“诸如”指词组“诸如但不限于”，且可与其互换使用。
可能以许多方式来实现本公开的方法和装置。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本公开的方法和装置。用于所述方法的步骤的上述顺序仅是为了进行说明，本公开的方法的步骤不限于以上具体描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本公开实施为记录在记录介质中的程序，这些程序包括用于实现根据本公开的车辆换道的控制方法的机器可读指令。因而，本公开还覆盖存储用于执行根据本公开的车辆换道的控制方法的程序的记录介质。
还需要指出的是，在本公开的装置、设备和方法中，各部件或各步骤是可以分解和/或重新组合的。这些分解和/或重新组合应视为本公开的等效方案。
提供所公开的方面的以上描述以使本领域的任何技术人员能够做出或者使用本公开。对这些方面的各种修改对于本领域技术人员而言是非常显而易见的，并且在此定义的一般原理可以应用于其他方面而不脱离本公开的范围。因此，本公开不意图被限制到在此示出的方面，而是按照与在此公开的原理和新颖的特征一致的最宽范围。
为了例示和描述的目的已经给出了以上描述。此外，此描述不意图将本公开的实施例限制到在此公开的形式。尽管以上已经讨论了多个示例方面和实施例，但是本领域技术人员将认识到其某些变型、修改、改变、添加和子组合。

Claims (10)

  1. 一种车辆换道的控制方法，包括：
    获取周围环境的视觉信息；
    基于所述视觉信息，确定当前车辆的可行驶区域边界数据；
    基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息；
    基于所述并行车辆信息，确定换道信息；
    根据所述换道信息控制所述当前车辆的行驶状态。
  2. 根据权利要求1所述的方法，其中，所述当前车辆的至少一侧的并行车辆信息包括所述当前车辆的至少一侧是否存在并行车辆的结果信息；在所述基于所述并行车辆信息，确定换道信息之前，还包括：
    获取所述当前车辆的当前速度；
    所述基于所述并行车辆信息，确定换道信息，包括：
    基于所述并行车辆信息及所述当前车辆的当前速度，确定所述换道信息，所述换道信息包括是否能换道的结果信息。
  3. 根据权利要求2所述的方法，其中，所述可行驶区域边界数据包括车辆坐标系下的坐标点；所述基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，包括：
    若所述至少一侧中的第一侧对应的第一可行驶区域边界数据中的所有所述坐标点距车辆中心线的距离均大于预设阈值，则确定所述第一侧没有并行车辆。
  4. 根据权利要求3所述的方法，其中，所述基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，还包括：
    若所述第一可行驶区域边界数据中，存在距车辆中心线的距离小于或等于所述预设阈值的坐标点，则基于预设筛选规则对所述第一可行驶区域边界数据进行筛选，获得第二可行驶区域边界数据；
    基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果；
    根据所述分类结果，确定所述第一侧是否存在并行车辆。
  5. 根据权利要求4所述的方法，其中，在所述基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果之前，还包括：
    对所述第二可行驶区域边界数据进行归一化处理，获得第三可行驶区域边界数据；
    所述基于支持向量机算法对所述第二可行驶区域边界数据进行分类，获得分类结果，包括：
    基于支持向量机算法对所述第三可行驶区域边界数据进行分类，获得分类结果。
  6. 根据权利要求1所述的方法，其中，所述基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，包括：
    基于连续K帧的可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息，其中，K为大于1的整数。
  7. 根据权利要求1-6任一所述的方法，其中，所述基于所述并行车辆信息，确定换道信息，包括：
    基于连续M次确定的并行车辆信息，确定所述换道信息，其中，M为大于1的整数。
  8. 一种车辆换道的控制装置，包括：
    第一获取模块，用于获取周围环境的视觉信息；
    第一处理模块，用于基于所述视觉信息，确定当前车辆的可行驶区域边界数据；
    第二处理模块，用于基于所述可行驶区域边界数据，确定所述当前车辆至少一侧的并行车辆信息；
    第一确定模块，用于基于所述并行车辆信息，确定换道信息；
    控制模块，用于根据所述换道信息控制所述当前车辆的行驶状态。
  9. 一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-7任一所述的车辆换道的控制方法。
  10. 一种电子设备，所述电子设备包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现上述权利要求1-7任一所述的车辆换道的控制方法。
PCT/CN2022/123369 2021-11-24 2022-09-30 车辆换道的控制方法和装置、电子设备和存储介质 WO2023093306A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP22897391.3A EP4438429A1 (en) 2021-11-24 2022-09-30 Vehicle lane change control method and apparatus, electronic device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111409699.3 2021-11-24
CN202111409699.3A CN113954838B (zh) 2021-11-24 2021-11-24 车辆换道的控制方法和装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2023093306A1 true WO2023093306A1 (zh) 2023-06-01

Family

ID=79471914

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/123369 WO2023093306A1 (zh) 2021-11-24 2022-09-30 车辆换道的控制方法和装置、电子设备和存储介质

Country Status (3)

Country Link
EP (1) EP4438429A1 (zh)
CN (1) CN113954838B (zh)
WO (1) WO2023093306A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118135797A (zh) * 2024-04-30 2024-06-04 吉林大学 基于卫星数据多源融合的车路空间从属关系确定方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113954838B (zh) * 2021-11-24 2023-04-07 上海安亭地平线智能交通技术有限公司 车辆换道的控制方法和装置、电子设备和存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103386975A (zh) * 2013-08-02 2013-11-13 重庆市科学技术研究院 一种基于机器视觉的车辆避障方法及系统
CN109249930A (zh) * 2018-08-10 2019-01-22 重庆大数据研究院有限公司 一种智能车碰撞安全预测方法
CN110362096A (zh) * 2019-08-13 2019-10-22 东北大学 一种基于局部最优性的无人驾驶车辆动态轨迹规划方法
CN110834630A (zh) * 2019-10-22 2020-02-25 中国第一汽车股份有限公司 一种车辆的驾驶控制方法、装置、车辆及存储介质
US20200361489A1 (en) * 2019-05-15 2020-11-19 Rideflux Inc. Method and apparatus for controlling a vehicle's driving operation using advance information
WO2021000800A1 (zh) * 2019-06-29 2021-01-07 华为技术有限公司 道路可行驶区域推理方法及装置
CN113689718A (zh) * 2021-08-13 2021-11-23 吉林大学 智能信号灯与车道匹配系统及匹配方法
CN113954838A (zh) * 2021-11-24 2022-01-21 上海安亭地平线智能交通技术有限公司 车辆换道的控制方法和装置、电子设备和存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200148261A1 (en) * 2018-11-14 2020-05-14 Steering Solutions Ip Holding Corporation Lane change and collision avoidance system
CN110737266B (zh) * 2019-09-17 2022-11-18 中国第一汽车股份有限公司 一种自动驾驶控制方法、装置、车辆和存储介质
CN110562258B (zh) * 2019-09-30 2022-04-29 驭势科技（北京）有限公司 一种车辆自动换道决策的方法、车载设备和存储介质
CN110745140B (zh) * 2019-10-28 2021-01-01 清华大学 一种基于连续图像约束位姿估计的车辆换道预警方法
CN111238520B (zh) * 2020-02-06 2022-10-14 阿波罗智能技术(北京)有限公司 自动驾驶变道路径规划方法、装置和电子设备
CN112455445A (zh) * 2020-12-04 2021-03-09 苏州挚途科技有限公司 自动驾驶的变道决策方法、装置和车辆

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103386975A (zh) * 2013-08-02 2013-11-13 重庆市科学技术研究院 一种基于机器视觉的车辆避障方法及系统
CN109249930A (zh) * 2018-08-10 2019-01-22 重庆大数据研究院有限公司 一种智能车碰撞安全预测方法
US20200361489A1 (en) * 2019-05-15 2020-11-19 Rideflux Inc. Method and apparatus for controlling a vehicle's driving operation using advance information
WO2021000800A1 (zh) * 2019-06-29 2021-01-07 华为技术有限公司 道路可行驶区域推理方法及装置
CN110362096A (zh) * 2019-08-13 2019-10-22 东北大学 一种基于局部最优性的无人驾驶车辆动态轨迹规划方法
CN110834630A (zh) * 2019-10-22 2020-02-25 中国第一汽车股份有限公司 一种车辆的驾驶控制方法、装置、车辆及存储介质
CN113689718A (zh) * 2021-08-13 2021-11-23 吉林大学 智能信号灯与车道匹配系统及匹配方法
CN113954838A (zh) * 2021-11-24 2022-01-21 上海安亭地平线智能交通技术有限公司 车辆换道的控制方法和装置、电子设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118135797A (zh) * 2024-04-30 2024-06-04 吉林大学 基于卫星数据多源融合的车路空间从属关系确定方法
CN118135797B (zh) * 2024-04-30 2024-06-25 吉林大学 基于卫星数据多源融合的车路空间从属关系确定方法

Also Published As

Publication number Publication date
CN113954838A (zh) 2022-01-21
CN113954838B (zh) 2023-04-07
EP4438429A1 (en) 2024-10-02

Similar Documents

Publication Publication Date Title
WO2023093306A1 (zh) 车辆换道的控制方法和装置、电子设备和存储介质
US11643076B2 (en) Forward collision control method and apparatus, electronic device, program, and medium
WO2019228211A1 (zh) 基于车道线的智能驾驶控制方法和装置、电子设备
WO2019179464A1 (zh) 用于预测目标对象运动朝向的方法、车辆控制方法及装置
US20200082560A1 (en) Estimating two-dimensional object bounding box information based on bird's-eye view point cloud
CN112818778B (zh) 车道线拟合方法、装置、介质以及电子设备
US10685263B2 (en) System and method for object labeling
US11094080B2 (en) Method and device for determining whether a hand cooperates with a manual steering element of a vehicle
CN113095228B (zh) 图像中的目标检测方法、装置及计算机可读存储介质
EP3654276B1 (en) Analysis device, analysis method, and program
CN112406884B (zh) 车辆行驶状态的识别方法和装置、存储介质、电子设备
KR101821242B1 (ko) 영상 인식에 기반하여 차량을 계수하는 방법 및 이를 이용한 장치
CN114092913A (zh) 车道线的确定方法和装置、电子设备和存储介质
CN115147683A (zh) 位姿估计网络模型的训练方法、位姿估计方法及装置
US11080562B1 (en) Key point recognition with uncertainty measurement
CN114708578A (zh) 唇部动作检测方法、装置、可读存储介质和电子设备
Shiba et al. A fast geometric regularizer to mitigate event collapse in the contrast maximization framework
CN113160322A (zh) 摄像装置标定方法和设备、介质以及电子设备
CN112304293B (zh) 道路高度检测方法、装置、可读存储介质和电子设备
EP4047566A1 (en) Prevention of low-speed sideswipe collisions with non-moving objects
CN115830715A (zh) 基于手势识别的无人车控制方法、装置和设备
US12043286B2 (en) Method and system for detecting and alerting collision by autonomous robot based on multi-sensor LSTM
CN118135542B (zh) 一种障碍物动静态判定方法及其相关设备
CN116774590B (zh) 一种影响干扰用自适应调控方法及系统
CN113129330B (zh) 一种可移动设备的轨迹预测方法及装置

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: 22897391

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022897391

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022897391

Country of ref document: EP

Effective date: 20240624