CN114780349A - Data processing method and device for automatic driving vehicle - Google Patents
Data processing method and device for automatic driving vehicle Download PDFInfo
- Publication number
- CN114780349A CN114780349A CN202210483017.1A CN202210483017A CN114780349A CN 114780349 A CN114780349 A CN 114780349A CN 202210483017 A CN202210483017 A CN 202210483017A CN 114780349 A CN114780349 A CN 114780349A
- Authority
- CN
- China
- Prior art keywords
- data
- target data
- target
- cloud server
- automatic driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
Abstract
The invention discloses a data processing method and device for an automatic driving vehicle. Wherein, the method comprises the following steps: acquiring first target data generated by an automatic driving vehicle in an automatic driving process; determining a first screening rule corresponding to the automatic driving vehicle based on the first target data; screening the first target data based on a first screening rule to obtain second target data; and uploading the second target data to a cloud server, wherein the second target data is processed by the cloud server. The invention solves the technical problem of low data transmission efficiency caused by large data transmission quantity in the related technology.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to a data processing method and device for an automatic driving vehicle.
Background
In recent years, the automatic driving technology has become a focus of controversy of various host factories, colleges and universities and research institutes, and the test is an important part in the automatic driving development process. On one hand, the automatic driving scene data collected by the real vehicle can generate a simulation scene through data recharging, on the other hand, the problem analysis in the real vehicle test process also needs to take the automatic driving data as the basis, and the data are an indispensable part in the simulation test and the real vehicle test. Big data technology has been widely used in the field of automatic driving, but the prior art does not relate to how to obtain useful data from a large amount of automatic driving data.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a data processing method and device for an automatic driving vehicle, which at least solve the technical problem of low data transmission efficiency caused by large data transmission amount in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a data processing method of an autonomous vehicle, including: acquiring first target data generated by an automatic driving vehicle in an automatic driving process; determining a first screening rule corresponding to the automatic driving vehicle based on the first target data; screening the first target data based on a first screening rule to obtain second target data; and uploading the second target data to a cloud server, wherein the second target data is processed by the cloud server.
Optionally, determining, based on the first target data, a first filtering rule corresponding to the autonomous vehicle includes: processing sensor data in the first target data to determine a target driving scene where the automatic driving vehicle is located currently; processing sensor data and vehicle control data in the first target data to determine a current target driving state of the automatic driving vehicle; based on the target driving scene and/or the target driving state, a first screening rule is determined.
Optionally, uploading the second target data to a cloud server, including: acquiring label information corresponding to the second target data, wherein the label information is used for representing a target driving scene and/or a target driving state where the automatic driving vehicle is located currently; and uploading the second target data and the tag information to a cloud server.
Optionally, uploading the second target data to a cloud server, including: acquiring the running state of a vehicle controller of the automatic driving vehicle and timestamp information of second target data, wherein the timestamp information is used for representing the generation time of the second target data; determining the uploading time of the second target data based on the running state and the timestamp information; and responding to the arrival of the uploading time, and uploading the second target data to the cloud server.
Optionally, the method further comprises: determining third target data except the second target data in the first target data; and deleting the third target data.
Optionally, obtaining first target data generated by the autonomous vehicle during autonomous driving comprises: acquiring initial data generated by an automatic driving vehicle in an automatic driving process; performing packet processing on the initial data based on a second preset rule to obtain first target data, wherein the second preset rule comprises at least one of the following rules: a preset time interval and a preset data size.
Optionally, the file name of the first target data includes: packetization time stamp information of the first target data.
Optionally, the second target data is processed by the cloud server, and the processing includes at least one of: the second target data is analyzed and played back by the cloud server; modifying the tag information corresponding to the second target data by the cloud server; retrieving the second target data by the cloud server based on the tag information; the second target data is downloaded by the cloud server and stored to the local of the cloud server; the second target data and the tag information corresponding to the second target data are counted by the cloud server to obtain a statistical result, and the statistical result is displayed by the cloud server according to a preset display mode; and marking the second target data by the cloud server.
According to another aspect of the embodiments of the present invention, there is also provided a data processing apparatus of an autonomous vehicle, including: the data recording module is used for acquiring first target data generated by the automatic driving vehicle in the automatic driving process; the data determination module is used for determining a first screening rule corresponding to the automatic driving vehicle based on the first target data; the data screening module is used for screening the first target data based on a first screening rule to obtain second target data; and the data transmission module is used for uploading the second target data to the cloud server, wherein the second target data is processed by the cloud server.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform any of the above-described methods of data processing for an autonomous vehicle.
According to another aspect of the embodiments of the present invention, there is also provided a non-volatile storage medium including a stored program, wherein any one of the above-described data processing methods of an autonomous vehicle is executed in a processor controlling a device in which the program is executed when the program is executed.
In the embodiment of the invention, the method comprises the steps of acquiring first target data generated by an automatic driving vehicle in an automatic driving process; determining a first screening rule corresponding to the automatic driving vehicle based on the first target data; screening the first target data based on a first screening rule to obtain second target data; the second target data are uploaded to the cloud server, wherein the second target data are processed by the cloud server, it is easy to notice that a screening rule is determined through a target driving scene of a target driving vehicle and a target driving state, the data are screened based on the screening rule, and the purpose of screening a large amount of data is achieved, so that the technical effect of improving the data transmission efficiency is achieved, and the technical problem of low data transmission efficiency caused by large data transmission quantity in the related technology is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a data processing method for an autonomous vehicle according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an alternative autopilot data collection and processing system according to an embodiment of the present invention;
FIG. 3 is a flow chart of an alternative data processing method based on an automatic driving data collection and processing system according to an embodiment of the invention;
fig. 4 is a schematic structural diagram of a data processing device of an autonomous vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided an autonomous vehicle data processing method embodiment, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than presented herein.
Fig. 1 is a flow chart illustrating a data processing method of an autonomous vehicle according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, first target data generated by the automatic driving vehicle in the automatic driving process is acquired.
Optionally, obtaining first target data generated by the autonomous vehicle during autonomous driving comprises: acquiring initial data generated by an automatic driving vehicle in an automatic driving process; performing sub-packet processing on the initial data based on a second preset rule to obtain first target data, wherein the second preset rule comprises at least one of the following rules: a preset time interval and a preset data size.
Optionally, the file name of the first target data includes: packetization timestamp information of the first target data.
The automatic driving vehicle may be a hybrid vehicle or a new energy vehicle, which is not specifically limited in this embodiment and may be any vehicle capable of realizing automatic driving; the initial data is data generated by the autonomous vehicle during driving, and may include, but is not limited to: sensor data, vehicle state data, positioning state data, target identification and target trajectory prediction data, vehicle control data, and the like; the second preset rule may include, but is not limited to: dividing packets according to the same time interval, and dividing packets according to the initial data size; the first target data may be data obtained by packetizing the initial data; the preset time may be time set in advance by a user, and is used for performing sub-packaging on the initial data, a specific time value is not limited, in this embodiment, the same time interval may be used, for example, the initial data is sub-packaged and stored every 1 minute; the preset data size is data set in advance by a user and is used for performing sub-packaging on initial data, a specific data value is not limited, in this embodiment, an example in which the initial data amount reaches 100M is taken as an example, and the initial data amount reaches 100MB and then is subjected to sub-packaging and stored.
The time stamp may be data indicating a generation time of a piece of data, which may be accurate to milliseconds, and the packetization time stamp may be data indicating a packetization time of the first target data.
In an alternative embodiment, obtaining first target data generated by an autonomous vehicle during autonomous driving includes; initial data generated by the autonomous vehicle during autonomous driving is first obtained, which may include but is not limited to: sensor data, vehicle state data, positioning state data, target identification and target trajectory prediction data, vehicle control data, etc., and then packetizing the initial data based on a second preset rule, for example: the initial data is subpackaged once every 1 minute and stored or the initial data volume reaches 100MB and then is subpackaged and stored, so that the condition that the data occupies too large space in the same memory and the subpackaged data are continuous is avoided; finally, the first target data may be obtained by packetizing the initial data, and may be named by a packetizing timestamp.
And step S104, determining a first screening rule corresponding to the automatic driving vehicle based on the first target data.
Optionally, determining, based on the first target data, a first filtering rule corresponding to the autonomous vehicle includes: processing sensor data in the first target data to determine a target driving scene where the automatic driving vehicle is located currently; processing sensor data and vehicle control data in the first target data to determine a current target driving state of the automatic driving vehicle; based on the target driving scene and/or the target driving state, a first screening rule is determined.
The first filtering rule may include, but is not limited to: the method comprises the following steps that a target driving scene where an automatic driving vehicle is located at present and a target driving state where the automatic driving vehicle is located at present are obtained; the target driving scenario described above may be determined by processing the sensor data in the first target data, for example, by analyzing and processing the sensor data in the first target data, a target driving scenario in which the autonomous vehicle is currently located may be determined, such as a roundabout, an intersection, a narrowing of an approaching road, a cutting of other vehicles into a lane of the current autonomous vehicle, and the like; the target driving state may be obtained by processing the sensor data and the vehicle control data in the first target data, for example, by analyzing the sensor data and the vehicle control data in the first target data, the target driving state of the autonomously driven vehicle may be determined, such as a situation of collision, traffic incapability, and heavy control.
The first filtering rule may include, but is not limited to: only the current target driving scene of the automatic driving vehicle and the current target driving state of the automatic driving vehicle are considered, and the current target driving scene of the automatic driving vehicle and the current target driving state of the automatic driving vehicle are considered.
In an alternative embodiment, determining a corresponding first filter rule for the autonomous vehicle based on the first target data includes: analyzing and processing sensor data in the first target data to obtain a target driving scene where the automatic driving vehicle is located at present, such as a rotary island, a crossroad, a narrow arrival road, other vehicles cutting into a current automatic driving vehicle lane and the like; the sensor data and the vehicle control data in the first target data are analyzed, the current target driving state of the automatic driving vehicle can be obtained, such as collision, traffic incapability, too violent control and the like, and finally, the first screening rule can be determined based on the target driving scene and/or the target driving state.
And step S106, screening the first target data based on the first screening rule to obtain second target data.
In an optional embodiment, when the first filtering rule only considers a target driving scenario in which the autonomous vehicle is currently located, first the sensor data in the first target data may be analyzed and processed to obtain the target driving scenario, and then the data in the first target data that meets the target driving scenario is selected, so that the second target data may be obtained.
In another alternative embodiment, when the first filtering rule only considers the current target driving state of the autonomous vehicle, the sensor data and the vehicle control data in the first target data may be analyzed and processed to obtain the target driving state, and then the data satisfying the target driving state in the first target data may be selected to obtain the second target data.
In yet another alternative embodiment, when the first filtering rule considers both the target driving scenario and the target driving status, the sensor data in the first target data may be analyzed and processed to obtain the target driving scenario, the sensor data in the first target data and the vehicle control data may be analyzed and processed to obtain the target driving status, and the data including the target driving scenario and the target driving status in the first target data may be selected to obtain the second target data, for example, when the target driving scenario is determined to be "roundabout" by the sensor data in the first target data, and the target driving status is determined to be "collision" by the sensor data in the first target data and the vehicle control data, the data including the "roundabout" and "collision" information in the first target data may be selected, then the second target data, i.e. data containing "islands-in-the-loop" and "crashes" information, can be obtained.
Step S108, uploading the second target data to the cloud server, wherein the second target data is processed by the cloud server.
The cloud server may be any server capable of processing target data, and is not specifically limited in this embodiment.
In an optional embodiment, after uploading the second target data to the cloud server, the second target data may be processed by the cloud server.
In the embodiment of the invention, first target data generated by an automatic driving vehicle in an automatic driving process is acquired; determining a first screening rule corresponding to the automatic driving vehicle based on the first target data; screening the first target data based on a first screening rule to obtain second target data; the second target data are uploaded to the cloud server, wherein the second target data are processed by the cloud server, it is easy to notice that a screening rule is determined through scene data screening logic and autopilot problem data screening logic, the data are screened based on the screening rule, and part of screened data are uploaded, so that the purpose of avoiding large data volume uploading through screening a large amount of data is achieved, the technical effect of improving the data transmission efficiency is achieved, and the technical problem of low data transmission efficiency caused by large data transmission volume in the related technology is solved.
Optionally, uploading the second target data to the cloud server, including: acquiring label information corresponding to the second target data, wherein the label information is used for representing a target driving scene and/or a target driving state where the automatic driving vehicle is located currently; and uploading the second target data and the tag information to a cloud server.
The tag information may be information including a target driving scene and/or a target driving state of the target driving vehicle, for example, if the target driving scene is "roundabout" and the target driving state is "collision", the tag information may be information including "roundabout" and/or "collision", and there may be a plurality of tag information for each second target data.
In an optional embodiment, uploading the second target data to the cloud server further includes: and acquiring the tag information of the second target data, and uploading the second target data and the tag information to a cloud server after the tag information is acquired.
Optionally, uploading the second target data to the cloud server, including: acquiring the running state of a vehicle controller of the automatic driving vehicle and timestamp information of second target data, wherein the timestamp information is used for representing the generation time of the second target data; determining the uploading time of the second target data based on the running state and the timestamp information; and responding to the arrival uploading time, and uploading the second target data to the cloud server.
The operating states of the above-described controller may include, but are not limited to: the controller is idle, normal and busy; the timestamp information of the second target data may be data that can represent the generation time of the second target data, and the uploading time may be the time when the controller is idle and uploads the second target data in the order of the generation timestamp information of the second target data.
In an optional embodiment, uploading the second target data to the cloud server further includes: the method comprises the steps of obtaining the state of a vehicle controller of the automatic driving vehicle and the generation time stamp information of second target data, determining the uploading time of the second target data based on the running state and the generation time stamp information of the controller, responding to the arrival of the uploading time, uploading the second target data to a cloud server, for example, after the running state of the controller and the generation time stamp information of the second target data are obtained, when the running state of the controller meets an idle state, uploading the second target data to the cloud server according to the sequence of the generation time stamp information of the second target data, and achieving the purpose of saving the computing power of the controller to guarantee the stability of the automatic driving function.
In another alternative embodiment, the target second data may be further tagged with a tag file, where the tag file includes file name information, generation time stamp information, and tag information of the second target data.
Optionally, the second target data is processed by the cloud server, and the processing includes at least one of: the second target data is analyzed and played back by the cloud server; modifying the tag information corresponding to the second target data by the cloud server; retrieving the second target data by the cloud server based on the tag information; the second target data is downloaded by the cloud server and stored to the local of the cloud server; the second target data and the tag information corresponding to the second target data are counted by the cloud server to obtain a statistical result, and the statistical result is displayed by the cloud server according to a preset display mode; and marking the second target data by the cloud server.
The preset display mode may be any mode capable of displaying the statistical result, and the specific form is not limited, and in this embodiment, an icon may be used as an example for description.
In an alternative embodiment, the second target data is processed by the cloud server, which may include but is not limited to: the second target data can be analyzed and played back by the cloud server, so that research and development management personnel can know the actual data condition conveniently; the tag information corresponding to the second target data can be modified, deleted or added by the cloud server; the second target data can be retrieved by the cloud server based on the tag information and the generation timestamp information; the second target data can be downloaded by the cloud server and stored to the local cloud server; the second target data and the tag information corresponding to the second target data may be counted by the cloud server to obtain a statistical result, and the statistical result may be displayed in a graph manner, where the display item may include but is not limited to: counting the number of each label, counting the generation time of data and labels, and the like; the second target data may be tagged by the cloud server, for example, information such as the number, the location, the orientation, and the size of the obstacle targets appearing in the second target data may be tagged.
Optionally, the method further comprises: determining third target data except the second target data in the first target data; and deleting the third target data.
The third target data may be data that is not selected from the first target data based on the first filtering rule.
In an alternative embodiment, after the third target data is determined, the third target data may be deleted based on the user requirement.
The system presented by the present invention is deployed on an autonomous vehicle, but is equally applicable to non-autonomous vehicles that require data acquisition and management. According to the invention, data screening rules can be set as required, one-step data screening operation is carried out at the vehicle end, the screened data is uploaded to the cloud end, the data which is not screened can be cleared or reserved as required, the data uploading amount is reduced while the useful data is ensured to be obtained, and the storage space requirement of the vehicle end data is reduced.
Fig. 2 is a schematic diagram of an alternative automatic driving data collecting and processing system according to an embodiment of the present invention, as shown in fig. 2, the system includes the following components: the system comprises an automatic driving module 21, a data recording module 22, a data screening module 23, a data transmission module 24 and a cloud management module 25. The automatic driving module 21, the data recording module 22, the data screening module 23 and the data transmission module 24 are arranged on the vehicle-end controller, the cloud management module 25 is arranged on the cloud server, and the vehicle-end controller and the cloud controller perform data interaction through a 4G/5G network.
Fig. 3 is a flowchart of an alternative data processing method based on an automatic driving data collecting and processing system according to an embodiment of the present invention, where the method specifically includes the following steps:
step S301: the automatic driving function module generates automatic driving data;
step S302: the data recording module records the automatic driving data in real time;
step S303: the data screening module screens data, marks timestamps and labels for the data, stores label files and processes unseltered data;
step S304: the data transmission module uploads data to the cloud according to the tag file;
step S305: and the cloud management module manages the data.
Optionally, the autopilot module, while providing autopilot functionality for the autopilot vehicle, also generates data related to autopilot, including but not limited to sensor data, vehicle status data, positioning status data, target identification and target trajectory prediction data, vehicle control data, and the like.
Optionally, the data recording module can record the data generated by the automatic driving module in real time and store the recorded data in the vehicle-end controller.
Optionally, the data recording module can save the data subpackage record according to a certain rule, and name the subpackaged data according to a certain rule, and the subpackage rule of the data recording module includes, but is not limited to, the following modes: dividing packets according to the same time interval (for example, performing sub-packet storage every 1 minute), and dividing packets according to the file size (for example, performing sub-packet after the data volume reaches 100 MB); the data record subpackage naming rule includes but is not limited to the following modes: named with a packetization timestamp.
Optionally, the data screening module can screen the data of the data recording module according to a certain rule to obtain the data of the automatic driving concern. The rules of the data filtering module can be set as required, and can include but are not limited to scene data filtering logic and automatic driving problem data filtering logic. The scene data screening logic of the data screening module can be implemented by, but not limited to, the following ways: the data screening module obtains the actual driving scene of the sensor through analysis and processing of the sensor data, such as rotary island, crossroad, narrow arrival path, cut-in of the target vehicle into the lane of the vehicle, and the like. The autopilot problem screening logic of the data screening module may be implemented by, but is not limited to: the data screening module judges whether the automatic driving vehicle is in a wrong automatic driving state, such as collision, traffic incapability, over-violent control and the like, through the sensor data and the vehicle control data.
Optionally, the data filtering module may tag the filtered data according to the data filtering logic, obtain a saved file name and a generated timestamp of the data, and store timestamp information, file name information, and tag information in a tag file. And after the screening is completed, the data screening module can operate on the unselected data to determine whether the data is deleted or reserved, wherein the operation of the data screening module on the unselected data can be configured through a program.
Optionally, the data transmission module sends the screened data to the cloud end through a 4G/5G network according to the tag file generated by the data screening module. The data transmission module can transmit the screened files and also can transmit the label attributes of the screened files, and the label files store the file names of the screened files and the timestamps generated by the files, so that the files can be retrieved by the data transmission module at any time as long as the files exist, the data transmission module can comprehensively select uploading time without uploading in real time according to the current running condition of the vehicle-end controller, and the computing power of the vehicle-end controller is saved to the maximum extent to ensure the stability of the automatic driving function.
Optionally, the cloud management system may manage data uploaded by the data transmission module, and the specific management method and management content include, but are not limited to, the following items:
the cloud management system supports the analysis and playback of data, so that research and development management personnel can know the actual data condition conveniently;
the cloud management module supports addition, modification and deletion of data tags according to playback results;
the cloud management module is used for retrieving data according to information such as data generation time and data labels;
the cloud management module supports the function of downloading data to a local server;
the cloud management module supports the function of counting data and tags, and can display the counting result in a chart mode, wherein the counting result includes but is not limited to the number counting of each tag, the generation time counting of the data and the tags and the like.
Optionally, some cloud management modules further support a function of labeling data, such as information of the number, the position, the orientation, the size, and the like of obstacle targets appearing in the labeled data.
Example 2
According to another aspect of the embodiments of the present invention, there is further provided a data processing apparatus for an autonomous vehicle, where the apparatus may perform the data processing method for an autonomous vehicle provided in embodiment 1, and a specific implementation manner and a preferred application scenario are the same as those in embodiment 1, and are not described herein again.
Fig. 4 is a schematic configuration diagram of a data processing apparatus of an autonomous vehicle according to an embodiment of the present invention, as shown in fig. 4, the apparatus including: the data recording module 40 is used for acquiring first target data generated by the automatic driving vehicle in the automatic driving process; a first data determination module 42, configured to determine a first filtering rule corresponding to the autonomous vehicle based on the first target data; the data screening module 44 is configured to screen the first target data based on a first screening rule to obtain second target data; the data transmission module 46 is configured to upload the second target data to the cloud server, where the second target data is processed by the cloud server.
Optionally, the data determining module comprises: the first determining unit is used for processing the sensor data in the first target data and determining a target driving scene where the automatic driving vehicle is located currently; the second determining unit is used for processing the sensor data and the vehicle control data in the first target data and determining the current target running state of the automatic driving vehicle; and the third determination unit is used for determining the first screening rule based on the target driving scene and/or the target driving state.
Optionally, the data filtering module comprises: the first acquisition unit is used for acquiring label information corresponding to the second target data, wherein the label information is used for representing a target driving scene and/or a target driving state where the automatic driving vehicle is currently located; and the first transportation unit is used for uploading the second target data and the tag information to the cloud server.
Optionally, the data filtering module further comprises: a second acquisition unit for acquiring an operation state of a vehicle controller of the autonomous vehicle and time stamp information of the second target data, wherein the time stamp information is used for representing a generation time of the second target data; the determining unit is used for determining the uploading time of the second target data based on the running state and the timestamp information; and the second transportation unit is used for responding to the uploading time and uploading the second target data to the cloud server.
Optionally, the apparatus further comprises: the second data determination module is used for determining third target data except the second target data in the first target data; and the deleting module is used for deleting the third target data.
Optionally, the data recording module includes: an acquisition unit for acquiring initial data generated by an autonomous vehicle during autonomous driving; the processing unit is configured to perform packet processing on the initial data based on a second preset rule to obtain first target data, where the second preset rule includes at least one of the following rules: a preset time interval and a preset file size.
Optionally, the processing unit is further configured to name a file of the first target data, where a file name of the first data includes: packetization timestamp information of the first target data.
Optionally, the data transmission module includes: the processing unit is used for analyzing and playing back the second target data by the cloud server; the modifying unit is used for modifying the tag information corresponding to the second target data by the cloud server; the retrieval unit is used for retrieving the second target data from the cloud server based on the tag information; the downloading unit is used for downloading the second target data from the cloud server and storing the second target data to the local part of the cloud server; the statistical unit is used for carrying out statistics on the second target data and the label information corresponding to the second target data by the cloud server to obtain a statistical result, and the statistical result is displayed by the cloud server according to a preset display mode; and the marking unit is used for marking the second target data by the cloud server.
Example 3
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the data processing method of the autonomous vehicle of any of embodiments 1.
Example 4
According to another aspect of the embodiments of the present invention, there is also provided a nonvolatile storage medium including a stored program, wherein the data processing method of the autonomous vehicle in embodiment 1 is executed in a processor that controls a device in which the program runs.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described in detail in a certain embodiment.
In the embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A data processing method of an autonomous vehicle, comprising:
acquiring first target data generated by an automatic driving vehicle in an automatic driving process;
determining a first screening rule corresponding to the automatic driving vehicle based on the first target data;
screening the first target data based on the first screening rule to obtain second target data;
uploading the second target data to a cloud server, wherein the second target data is processed by the cloud server.
2. The method of claim 1, wherein determining a corresponding first screening rule for the autonomous vehicle based on the first target data comprises:
processing sensor data in the first target data to determine a target driving scene where the automatic driving vehicle is located currently;
processing the sensor data and vehicle control data in the first target data to determine a current target driving state of the automatic driving vehicle;
determining the first screening rule based on the target driving scene and/or the target driving state.
3. The method of claim 1 or 2, wherein uploading the second target data to a cloud server comprises:
acquiring label information corresponding to the second target data, wherein the label information is used for representing a target driving scene and/or a target driving state where the automatic driving vehicle is located currently;
and uploading the second target data and the tag information to the cloud server.
4. The method of claim 1 or 2, wherein uploading the second target data to a cloud server comprises:
acquiring an operating state of a vehicle controller of the autonomous vehicle and timestamp information of the second target data, wherein the timestamp information is used for representing the generation time of the second target data;
determining an uploading time of the second target data based on the operating state and the timestamp information;
and responding to the uploading time, and uploading the second target data to the cloud server.
5. The method of claim 1, further comprising:
determining third target data in the first target data except the second target data;
and deleting the third target data.
6. The method of claim 1, wherein obtaining first target data generated by the autonomous vehicle during autonomous driving comprises:
acquiring initial data generated by the automatic driving vehicle in an automatic driving process;
performing packet processing on the initial data based on a second preset rule to obtain the first target data, wherein the second preset rule includes at least one of the following rules: a preset time interval and a preset data size.
7. The method of claim 6, wherein the file name of the first target data comprises: packetization timestamp information of the first target data.
8. The method of claim 1, wherein the second target data is processed by the cloud server, and wherein the second target data comprises at least one of:
the second target data is analyzed and played back by the cloud server;
modifying the tag information corresponding to the second target data by the cloud server;
retrieving, by the cloud server, the second target data based on the tag information;
the second target data is downloaded by the cloud server and stored to the local cloud server;
the second target data and the tag information corresponding to the second target data are counted by the cloud server to obtain a statistical result, and the statistical result is displayed by the cloud server according to a preset display mode;
and marking the second target data by the cloud server.
9. A data processing apparatus of an autonomous vehicle, characterized by comprising:
the data recording module is used for acquiring first target data generated by the automatic driving vehicle in the automatic driving process;
the data determination module is used for determining a first screening rule corresponding to the automatic driving vehicle based on the first target data;
the data screening module is used for screening the first target data based on the first screening rule to obtain second target data;
and the data transmission module is used for uploading the second target data to a cloud server, wherein the second target data is processed by the cloud server.
10. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to perform the data processing method of the autonomous vehicle of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210483017.1A CN114780349A (en) | 2022-05-05 | 2022-05-05 | Data processing method and device for automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210483017.1A CN114780349A (en) | 2022-05-05 | 2022-05-05 | Data processing method and device for automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114780349A true CN114780349A (en) | 2022-07-22 |
Family
ID=82434211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210483017.1A Pending CN114780349A (en) | 2022-05-05 | 2022-05-05 | Data processing method and device for automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114780349A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115659088A (en) * | 2022-12-12 | 2023-01-31 | 亿海蓝（北京）数据技术股份公司 | Navigation track display method and device and readable storage medium |
| CN115793993A (en) * | 2023-01-28 | 2023-03-14 | 禾多科技（北京）有限公司 | Data processing method and device, storage medium and electronic device |
| CN115842819A (en) * | 2023-02-22 | 2023-03-24 | 禾多科技（北京）有限公司 | Method, device and equipment for downloading test data of automatic driving system |
| CN116382597A (en) * | 2023-06-05 | 2023-07-04 | 禾多科技（北京）有限公司 | Vehicle operation data storage method, apparatus and computer medium |
-
2022
- 2022-05-05 CN CN202210483017.1A patent/CN114780349A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115659088A (en) * | 2022-12-12 | 2023-01-31 | 亿海蓝（北京）数据技术股份公司 | Navigation track display method and device and readable storage medium |
| CN115793993A (en) * | 2023-01-28 | 2023-03-14 | 禾多科技（北京）有限公司 | Data processing method and device, storage medium and electronic device |
| CN115842819A (en) * | 2023-02-22 | 2023-03-24 | 禾多科技（北京）有限公司 | Method, device and equipment for downloading test data of automatic driving system |
| CN116382597A (en) * | 2023-06-05 | 2023-07-04 | 禾多科技（北京）有限公司 | Vehicle operation data storage method, apparatus and computer medium |
| CN116382597B (en) * | 2023-06-05 | 2023-09-12 | 禾多科技（北京）有限公司 | Vehicle operation data storage method, apparatus and computer medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114780349A (en) | Data processing method and device for automatic driving vehicle | |
| CN107316353B (en) | A kind of unmanned plane inspection approaches to IM, system and server | |
| CN102314916B (en) | Video processing method and system | |
| CN107085519B (en) | Behavior tree debugging processing method, device and system, storage medium and processor | |
| EP3253042A1 (en) | Intelligent processing method and system for video data | |
| CN100430906C (en) | Library system, virtual library apparatus, cache restoring method, and computer readable recording medium | |
| CN109145065A (en) | Methods of exhibiting and device, the computer readable storage medium of vehicle driving trace | |
| CN102947829B (en) | Data processing equipment and data processing method | |
| CN206133290U (en) | Production line monitoring system | |
| CN102595103B (en) | Method based on geographic information system (GIS) map deduction intelligent video | |
| CN112346998B (en) | Automatic driving simulation test method and device based on scene | |
| EP2735984A1 (en) | Video query method, device and system | |
| CN102231820B (en) | Monitoring image processing method, device and system | |
| CN102289520A (en) | Traffic video retrieval system and realization method thereof | |
| CN103167265A (en) | Video processing method and video processing system based on intelligent image identification | |
| CN102855369A (en) | Method and system for collecting failure information and medical equipment | |
| CN104952273A (en) | Warning method, device and system aiming at vehicle behaviors | |
| JPWO2017138620A1 (en) | Memory device, edge device for handling storable data, and data management method | |
| CN110750311A (en) | Data classification method, device and equipment | |
| CN104270605A (en) | Method and device for processing video monitoring data | |
| CN111881320A (en) | Video query method, device, equipment and readable storage medium | |
| CN102682498B (en) | For the information-recording apparatus of vehicle | |
| CN114579646A (en) | Visual control method, device and equipment for multidimensional data display platform | |
| WO2008032992A1 (en) | Method for downloading multimedia contents to electronic picture frame | |
| JP2003196601A (en) | Method and system for storing using state information in memory card |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |