CN112612284B - Data storage method and device - Google Patents

Data storage method and device Download PDF

Info

Publication number
CN112612284B
CN112612284B CN202011554343.4A CN202011554343A CN112612284B CN 112612284 B CN112612284 B CN 112612284B CN 202011554343 A CN202011554343 A CN 202011554343A CN 112612284 B CN112612284 B CN 112612284B
Authority
CN
China
Prior art keywords
data
obstacle
automatic driving
automatic
obstacle information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011554343.4A
Other languages
Chinese (zh)
Other versions
CN112612284A (en
Inventor
雷绳光
蔡春明
剧学铭
周鹏
张卫涛
郝哲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Liangdao Intelligent Vehicle Technology Co ltd
Original Assignee
Beijing Liangdao Intelligent Vehicle Technology Co ltd
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 Beijing Liangdao Intelligent Vehicle Technology Co ltd filed Critical Beijing Liangdao Intelligent Vehicle Technology Co ltd
Priority to CN202011554343.4A priority Critical patent/CN112612284B/en
Publication of CN112612284A publication Critical patent/CN112612284A/en
Application granted granted Critical
Publication of CN112612284B publication Critical patent/CN112612284B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0259—Control of position or course in two dimensions specially adapted to land vehicles using magnetic or electromagnetic means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)

Abstract

The embodiment of the invention provides a data storage method and a data storage device, which relate to the technical field of data processing, and the method comprises the following steps: and acquiring original object data and/or original environment data of the automatic driving object in the automatic driving process as driving data, wherein the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing the surrounding environment. And detecting whether a preset attention event exists in the automatic running process according to the acquired running data. If so, the travel data used to detect the event of interest is stored. The scheme provided by the embodiment of the invention can provide data with larger information quantity for the research of the automatic driving technology.

Description

Data storage method and device
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data storage method and apparatus.
Background
In the automatic traveling process, an automatic traveling object such as an automatic driving vehicle or a robot can continuously acquire traveling data related to the automatic traveling. For example, the driving data may include: environmental data around the automatic traveling object, object data of the automatic traveling object itself, and the like, which are collected by the data collection device. The automatic traveling object can obtain information of objects such as obstacles, road signs, lane lines and the like around the automatic traveling object as target level data, such as the position, the movement speed and the like of the obstacle by analyzing the traveling data, so that the automatic traveling object is controlled to safely travel according to the target level data.
In addition, in order to further study the automatic driving technology and continuously improve the safety of the automatic driving object in the driving process, manufacturers of the automatic driving object often require the automatic driving object to store the information of the target object, so that the automatic driving object can feed back the information of the target object to the manufacturers, and the manufacturers can further iterate and train algorithms, models and the like related to the automatic driving technology according to the information of the target object. For example, the automatic driving obstacle avoidance model is further trained by the information of the target object. However, since the information of the object is the object level data for describing the object obtained by analysis, and the object level data can be regarded as comprehensive data, the data volume is limited, so that the information volume which can be provided by such data in subsequent researches is limited.
Disclosure of Invention
The embodiment of the invention aims to provide a data storage method and device for providing data with larger information quantity for the research of automatic driving technology. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a data storage method, where the method includes:
Acquiring original object data and/or original environment data of an automatic driving object in an automatic driving process as driving data, wherein the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing surrounding environment;
detecting whether a preset attention event exists in the automatic driving process according to the acquired driving data;
if yes, storing running data used for detecting the attention event.
In one embodiment of the present invention, the detecting whether a preset attention event exists in the automatic driving process according to the acquired driving data includes:
identifying obstacle information of obstacles around the automatic traveling object according to the acquired traveling data;
and detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle.
In one embodiment of the present invention, the detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle includes:
Determining an obstacle movement track of the obstacle according to the obstacle position contained in the obstacle information;
determining an object motion trail of the automatic driving object according to the original object data contained in the driving data;
and if the distance between the obstacle movement track and the object movement track is smaller than the preset distance, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle includes:
determining movement indication information set in the environment around the automatic traveling object according to the original environment data contained in the traveling data;
determining whether the motion state of the obstacle represented by the obstacle information accords with the motion state indicated by the motion indication information according to the determined obstacle information of the obstacle;
if not, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle includes:
Determining whether an accident occurs to an automatic driving object in the automatic driving process according to the obstacle information of the identified obstacle and the original object data contained in the driving data;
if yes, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, in a case where the automatic traveling object is mounted with at least two data collection devices, the identifying obstacle information of obstacles around the automatic traveling object based on the acquired traveling data includes:
identifying obstacles around the automatic driving object according to the original environment data collected by different data collecting devices contained in the driving data;
detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle comprises the following steps:
and if the obstacles obtained by identification according to the original environment data acquired by different data acquisition equipment are different, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the storing of the travel data used to detect the event of interest includes:
Identifying offline obstacle information of obstacles around the automatic driving object according to the acquired driving data at offline time, wherein the offline time is: a time of presetting an offline time period after an acquisition time of running data used when the attention event is detected;
and comparing the obstacle information with the offline obstacle information, and storing running data used for detecting the concerned event if the difference between the obstacle information and the offline obstacle information meets the preset difference requirement.
In a second aspect, an embodiment of the present invention provides a data storage device, the device including:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original object data and/or original environment data of an automatic driving object in an automatic driving process as driving data, the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing surrounding environment;
the event detection module is used for detecting whether a preset attention event exists in the automatic driving process according to the acquired driving data;
And the data storage module is used for storing the driving data used for detecting the concerned event when the detection result of the event detection module is yes.
In one embodiment of the present invention, the event detection module includes:
an obstacle recognition sub-module for recognizing obstacle information of obstacles around the automatic traveling object according to the acquired traveling data;
and the event detection sub-module is used for detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle.
In one embodiment of the present invention, the event detection submodule is specifically configured to:
determining an obstacle movement track of the obstacle according to the obstacle position contained in the obstacle information;
determining an object motion trail of the automatic driving object according to the original object data contained in the driving data;
and if the distance between the obstacle movement track and the object movement track is smaller than the preset distance, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the event detection submodule is specifically configured to:
Determining movement indication information set in the environment around the automatic traveling object according to the original environment data contained in the traveling data;
determining whether the motion state of the obstacle represented by the obstacle information accords with the motion state indicated by the motion indication information according to the determined obstacle information of the obstacle;
if not, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the event detection submodule is specifically configured to:
determining whether an accident occurs to an automatic driving object in the automatic driving process according to the obstacle information of the identified obstacle and the original object data contained in the driving data;
if yes, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, when the automatic traveling object is mounted with at least two data acquisition devices, the obstacle recognition sub-module is specifically configured to:
identifying obstacles around the automatic driving object according to the original environment data collected by different data collecting devices contained in the driving data;
The event detection submodule is specifically configured to:
and if the obstacles obtained by identification according to the original environment data acquired by different data acquisition equipment are different, determining that a preset attention event exists in the automatic driving process.
In one embodiment of the present invention, the data storage module is specifically configured to:
identifying offline obstacle information of obstacles around the automatic driving object according to the acquired driving data at offline time, wherein the offline time is: a time of presetting an offline time period after an acquisition time of running data used when the attention event is detected;
and comparing the obstacle information with the offline obstacle information, and storing running data used for detecting the concerned event if the difference between the obstacle information and the offline obstacle information meets the preset difference requirement.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of the first aspects when executing a program stored on a memory.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having a computer program stored therein, which when executed by a processor, implements the method steps of any of the first aspects.
In a fifth aspect, embodiments of the present invention also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method steps of any of the first aspects described above.
The embodiment of the invention has the beneficial effects that:
in the data storage scheme provided by the embodiment of the invention, after the running data of the automatic running object is acquired, whether a preset attention event exists in the automatic running process is determined according to the running data. The travel data is stored only when there is an event of interest.
From the above, since the running data stored in the scheme provided by the embodiment of the present invention is the original data, but not the target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is large, and the data with large information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating a first data storage method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a second data storage method according to an embodiment of the present invention;
FIG. 3A is a flowchart illustrating a third data storage method according to an embodiment of the present invention;
FIG. 3B is a flowchart illustrating a fourth data storage method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a first data storage device according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a second data storage device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Because the data volume of the target level data in the prior art is limited, the information volume which can be provided for subsequent research is limited, and in order to solve the problem, the embodiment of the invention provides a data storage method and a data storage device, thereby providing data with larger information volume for the research of the automatic driving technology.
The embodiment of the invention provides a data storage method, which comprises the following steps:
and acquiring original object data and/or original environment data of an automatic driving object in the automatic driving process as driving data, wherein the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing surrounding environment.
And detecting whether a preset attention event exists in the automatic running process according to the acquired running data.
If so, storing the driving data used for detecting the attention event.
From the above, since the running data stored in the scheme provided by the embodiment of the present invention is the original data, but not the target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is large, and the data with large information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
The data storage method and the data storage device provided by the embodiment of the invention are explained by specific embodiments.
Referring to fig. 1, an embodiment of the present invention provides a flowchart of a first data storage method, which includes the following steps S101 to S103.
S101: and acquiring original object data and/or original environment data of the automatic driving object in the automatic driving process as driving data.
The automatic driving object may be an automatic driving car, a robot or other devices capable of driving automatically.
The raw object data is used to describe the state of the automatic traveling object. Specifically, the raw object data may include a travel speed, an object position, an object orientation, and the like of the automatic travel object.
The original environment data is data which is collected by the data collection device of the automatic driving object and used for describing the surrounding environment. Specifically, the surrounding environment includes an obstacle around the automatic traveling object, a road on which the automatic traveling object is located, and the like.
The data acquisition device may be: one or more of the above-mentioned automatic traveling object-mounted cameras, lidar, millimeter wave radar and other devices. The original environmental data collected by the camera are as follows: image or video data. The original environmental data collected by the laser radar are as follows: laser point cloud data. The original environmental data collected by the millimeter wave radar are as follows: millimeter wave point cloud data.
S102: and detecting whether a preset attention event exists in the automatic running process according to the acquired running data.
Specifically, the preset attention event may be: new events different from events represented by stored travel data. That is, since the new event is not studied during the automatic travel technology study, which is an event in which the corresponding travel data is never stored, the new event plays a significant role in the automatic travel technology study. By storing the travel data of the new event, the stored travel data can be used for development in the subsequent development, so that the new event can be processed when the automatic traveling object experiences the new event again in the traveling process. By continuously storing the running data of different new events, the processing capability of the automatic running object on various different new events can be improved, and the safety of the automatic running object in the running process is improved as a whole.
In addition, the preset attention event may be: an accident event indicating an accident of the automatic traveling object. For example, the automatic traveling object collides with an obstacle in the environment, the automatic traveling object itself turns on its side, or the like. Since the automatic driving technique related to the description of the occurrence of an accident by an automatic driving object has a problem that further improvement is required, the accident event described above also plays a significant role in the study of the automatic driving technique.
Furthermore, the predetermined attention event may be: a dangerous event indicating that the automatic driving object has a hidden trouble of accident. For example, an obstacle located before the automatic traveling object may be suddenly stopped, the obstacle may be rapidly redirected into a planned route of the automatic traveling object, etc., and the dangerous event may cause the automatic traveling object to have a hidden trouble in an accident. Although the automatic traveling object does not have an accident, the probability of the accident is high, and the automatic traveling technology needs to study dangerous events so as to prevent the accident of the automatic traveling object when the hidden danger of the accident occurs.
Specifically, whether a preset attention event exists in the automatic driving process within a preset time period before the preset time interval is detected.
The preset time interval may be the same as the preset time period, but since the time period of occurrence of the concerned event may be longer than the preset time interval, if the preset time period is the same as the preset time interval, the traveling data related to the concerned event may be divided into multiple sets of data for multiple detection, so that the preset time period may be longer than the preset time interval.
For example, the preset time interval may be 15s, 30s, 60s, etc., and the preset time period may be 30s, 45s, 60s, etc.
In the embodiment of the present invention, the step S102 may be implemented through steps S102A-S102B, which will not be described in detail herein.
If the determination result in step S102 is yes, step S103 is executed. Otherwise, the travel data used to detect the above-described event of interest may be deleted.
S103: and storing the driving data used for detecting the attention event.
In one embodiment of the present invention, the running data may be stored in the automatic running apparatus, and the automatic running apparatus may transmit the stored running data to the server every time a preset storage period elapses, or may transmit the stored running data to the server in a case where the data amount of the running data stored by the automatic running apparatus reaches the preset data amount, because the data storage capability of the automatic running apparatus is limited.
In addition, the automatic traveling device may directly transmit the stored traveling data to the server after storing the traveling data each time.
Specifically, the automatic driving device may send the driving data to the server through a 4G network, a 5G network, a WiFi network, or other networks.
After the stored travel data is transmitted to the server, the automatic travel device may delete the transmitted travel data, so that the data storage resources of the automatic travel device occupied by the travel data may be reduced.
From the above, since the running data stored in the scheme provided by the embodiment of the present invention is the original data, but not the target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is large, and the data with large information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
Referring to fig. 2, a flow chart of a second data storage method according to an embodiment of the present invention is shown, and compared with the embodiment shown in fig. 1, the step S102 may be implemented by steps S102A-S102B.
S102A: and identifying obstacle information of obstacles around the automatic traveling object according to the acquired traveling data.
Specifically, the obstacle may be a pedestrian, a vehicle, an animal, a tree, a building, a falling stone, or other objects that may prevent the automatic traveling object from traveling normally around the automatic traveling object.
The obstacle information of the obstacle may include: the position of the obstacle, the relative position with the above-described automatic running device, the movement speed of the obstacle, the type of the obstacle, the size of the obstacle, and the like.
The method for identifying the obstacle information of the obstacle around the automatic driving object according to the data, such as video data, laser point cloud data, millimeter wave point cloud data and the like, in the original environment data included in the driving data, acquired by the data acquisition device can be realized through an algorithm in the prior art, and the method is not limited.
S102B: and detecting whether a preset attention event exists in the automatic running process according to the obstacle information of the identified obstacle.
Wherein, whether the obstacle has influence on the running of the automatic running vehicle can be determined according to the information such as the obstacle position, the obstacle speed, the obstacle size and the like contained in the obstacle information of the obstacle, so that whether a preset attention event exists in the automatic running process is determined.
In one embodiment of the present invention, when detecting whether a preset attention event exists during automatic traveling, at least one of the following information may be considered in addition to the obstacle information of the identified obstacle:
first kind of information: original object data.
In this case, specifically, a motion trajectory of the automatic traveling object obtained from the original object data, a result of whether or not an accident has occurred in the automatic traveling object detected from the original object data, and the like are considered.
Second kind of information: raw environmental data.
In this case, it is specifically considered that the movement indication information obtained from the original environment data, the result of whether or not the obstacles determined from the original environment data acquired by the different acquisition devices are identical, and the like.
Specifically, whether a preset attention event exists in the automatic driving process can be detected through the steps A-C, D-E or F, which are not described in detail herein.
From the above, since the obstacle is an important factor affecting the safe running of the automatic running object, the preset attention event of the automatic running object during the automatic running is often related to the obstacle, so that the obstacle in the surrounding environment of the automatic running object can be identified, and whether the preset attention event exists during the automatic running is detected according to the state of the obstacle.
In one embodiment of the present invention, the following steps a to C may be used to detect whether a preset attention event exists in the automatic driving process.
Step A: and determining an obstacle movement track of the obstacle according to the obstacle position contained in the obstacle information.
Specifically, the obstacle movement track of the obstacle may be determined by other algorithms such as linear interpolation or curve fitting according to the obstacle position of the obstacle included in the obstacle information at the acquisition time of each driving data in the first preset period.
And (B) step (B): and determining the object motion trail of the automatic driving object according to the original object data contained in the driving data.
Similar to step a, the obstacle movement track of the obstacle may be determined by linear interpolation or other algorithms according to the object position of the automatic driving object included in the original object data in the second preset period at the time of collecting each driving data.
Step C: if the distance between the obstacle movement track and the object movement track is smaller than the preset distance, determining that a preset attention event exists in the automatic driving process.
Specifically, the minimum distance between the movement track of the obstacle and the movement track of the object may be calculated, if the minimum distance is smaller than the preset distance, it is considered that a dangerous event or an accident event of collision, in which the distance between the object and the obstacle is relatively close, may exist in the automatic driving process, that is, the preset attention event exists in the automatic driving process.
In addition, the distances between the obstacle movement track and the object movement track at each moment can be calculated respectively, and if the calculated minimum distance is smaller than the preset distance, the preset attention event exists in the automatic driving process.
From the above, if the distance between the movement track of the obstacle and the movement track of the object is smaller than the preset distance, it can be considered that the distance between the object and the obstacle during the automatic driving may be smaller, so that the collision between the object and the obstacle may occur or nearly occur during the automatic driving, that is, a dangerous event or an accident event occurs, which indicates that the preset attention event exists during the automatic driving. By storing the running data of the dangerous event or the accident event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event or the accident event is improved, so that the processing capability of the automatic running object on the dangerous event or the accident time is improved, and the safety of the automatic running object is improved.
In another embodiment of the present invention, the following step D-step E may be used to detect whether a preset attention event exists in the automatic driving process.
Step D: and determining movement instruction information set in the environment around the automatic driving object according to the original environment data contained in the driving data.
In particular, the motion indication information may be information indicating safe motion of an object in the environment.
In the case where the automatic traveling object is an automatic driving vehicle, the environment around the automatic traveling object may be a road, and the movement indication information may be object traffic information indicated by a traffic light or a traffic sign, such as an intersection where a red light indicates that the object cannot pass through the traffic light, an intersection where a green light indicates that the object can pass through the traffic light, speed limit information indicated by a speed sign, and the like.
In the case where the automatic traveling object is a robot, the environment around the automatic traveling object may be an environment in which the robot operates. For example, the robot is an express robot, the environment in which the robot operates may be a warehouse, and the movement indication information may be movement information of the robot indicated by a movement indication board set in the warehouse. For example, the above-described movement signs may indicate a maximum speed, a movement direction, etc. of the robot.
In one embodiment of the present invention, an image of the environment around the automatic traveling object collected by the camera, which is included in the original environment data, may be identified, an area of a traffic light, a traffic sign, a movement sign, or the like, which is included in the image, may be determined, the identified area may be identified, and movement indication information set in the environment around the automatic traveling object may be determined. The identification of the image to determine the motion indication information may be implemented by an existing algorithm, which is not limited in the embodiment of the present invention.
Step E: and determining whether the motion state of the obstacle represented by the obstacle information is consistent with the motion state indicated by the motion indication information according to the determined obstacle information of the obstacle.
Specifically, the movement instruction information may be information for instructing safe movement of the object in the environment, and if the movement state of the obstacle does not conform to the movement state indicated by the movement instruction information, it is indicated that the movement state of the obstacle does not conform to the regulation of safe movement of the object, and if the obstacle is considered to move in the movement state, it is likely to affect the running safety of the automatic running object, and a dangerous event occurs during the automatic running.
Therefore, if the movement state of the obstacle does not conform to the movement state indicated by the movement indication information, it may be determined that a predetermined attention event exists during the automatic traveling.
For example, when the movement instruction information is speed limit information, it may be determined whether or not the obstacle speed of the obstacle is outside the speed range indicated by the speed limit information, and if so, it may be determined that the obstacle speed of the obstacle does not meet the regulation of the speed limit information, and it may be determined that the movement state of the obstacle indicated by the obstacle information does not meet the movement state indicated by the movement instruction information.
For example, when the movement instruction information is information indicating that the object cannot pass through an intersection corresponding to the traffic light, it is determined whether or not an obstacle passes through the intersection within a time period in which the object cannot pass through the intersection corresponding to the traffic light, and if so, it is determined that the passage of the obstacle does not meet the regulation of the traffic light. It is determined that the motion state of the obstacle indicated by the obstacle information does not conform to the motion state indicated by the motion indication information.
From the above, it is apparent that the movement instruction information set in the environment around the automatic traveling object is determined, and if the movement state of the obstacle represented by the obstacle information does not conform to the movement state indicated by the movement instruction information, it is determined that the movement state of the obstacle does not conform to the object safety movement specification represented by the movement instruction information, the obstacle is liable to be dangerous, and the traveling safety of the automatic traveling object is liable to be affected, that is, the automatic traveling object has a dangerous event during traveling, and it is determined that the automatic traveling object has a preset attention event. By storing the running data of the dangerous event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event is improved, so that the processing capability of the automatic running object for the dangerous event is improved, and the safety of the automatic running object is improved.
In one embodiment of the present invention, the following step F may be used to detect whether a preset attention event exists in the automatic driving process.
Step F: and determining whether an accident occurs to the automatic driving object in the automatic driving process according to the obstacle information of the identified obstacle and the original object data contained in the driving data.
Specifically, the collision between the automatic traveling object and the obstacle may be determined according to whether or not the obstacle position included in the obstacle information coincides with the object position included in the original object data, and if so. The accident of the automatic driving object in the automatic driving process is determined.
In addition, whether the automatic traveling object is damaged, malfunctions or the like may be determined according to the original object data, and if so, an accident of the automatic traveling object during the automatic traveling may be determined.
If the accident occurs to the automatic driving object in the automatic driving process, the accident event is considered to exist in the automatic driving process, and the preset attention event exists in the automatic driving process.
From the above, it can be determined whether a preset attention event exists in the automatic traveling process by determining whether an accident occurs in the automatic traveling object in the automatic traveling process. If the accident occurs to the automatic driving object in the automatic driving process, the accident event exists in the automatic driving process, and the preset attention event exists in the automatic driving process. By storing the driving data of the accident event, the stored driving data can be continuously used for development in the subsequent development, and the capability of the automatic driving object for identifying the accident event is improved, so that the processing capability of the automatic driving object for the accident event is improved, and the safety of the automatic driving object is improved.
Referring to fig. 3A, a flow chart of a third data storage method according to an embodiment of the present invention is shown, where the automatic driving object is equipped with at least two data acquisition devices, compared to the embodiment shown in fig. 2, the step S102A may be implemented by the following step S102A1, and the step S102B may be implemented by the following step S102B 1.
S102A1: and respectively identifying obstacles around the automatic driving object according to the original environment data collected by different data collecting devices contained in the driving data.
Specifically, since the original environmental data collected by the different data collecting devices carried by the automatic traveling object are different, the obstacles around the automatic traveling object can be identified by different algorithms according to the original environmental data collected by the different data collecting devices, so that the obstacles around the automatic traveling object can be identified, and the obstacle information of the identified obstacles can be determined.
S102B1: if the obstacles obtained by identification according to the original environment data acquired by different data acquisition devices are different, determining that a preset attention event exists in the automatic driving process.
Specifically, if the obstacles obtained by identification according to the original environmental data collected by different data collection devices are different, it is indicated that the data collection devices may malfunction, or more interference exists in the current environment, such as rain, snow, sand, haze and other weather, which makes it difficult for the data collection devices to collect the original environmental data. The original environment data acquired by the data acquisition equipment is not accurate enough, and the obstacle information acquired by recognition is not accurate enough. And the automatic driving object can not control the self-safe driving according to the accurate obstacle information, and is easy to be dangerous, so that the dangerous event exists in the automatic driving process, namely the preset attention event exists in the automatic driving process. By storing the running data of the dangerous event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event is improved, so that the processing capability of the automatic running object for the dangerous event is improved, and the safety of the automatic running object is improved.
Referring to fig. 3B, a flow chart of a fourth data storage method according to an embodiment of the present invention is shown, and compared with the embodiment shown in fig. 2, the above step S103 may be implemented by the following steps S103A-S103B.
S103A: and identifying offline obstacle information of obstacles around the automatic driving object according to the acquired offline driving data.
The offline time is as follows: and detecting the time of the preset duration after the acquisition time of the driving data used in the attention event.
Specifically, the data acquisition device is affected by the capability of the data acquisition device mounted on the automatic driving object, the richness and the detection range of information displayed by the original environmental data acquired by the data acquisition device at a time are limited, the obstacle information identified according to the acquired original environmental data may not be accurate, and the result of whether a preset attention event exists in the automatic driving process or not is also inaccurate according to the inaccurate obstacle information. For example, in the case where the distance between the obstacle and the automatic traveling object is long, the richness and detection range of the information of the obstacle shown by the image of the obstacle at the long distance acquired by the image acquisition apparatus are limited, for example, the color, size, and the like of the obstacle are displayed insufficiently clearly, and a partial area of the obstacle is not displayed in the image, and the like. The richness and detection range of the information of the obstacle displayed by the laser point cloud of the obstacle acquired by the laser radar are often limited, so that a vehicle with a long distance from an automatic driving object can be identified as an animal, and the information of the obstacle obtained by identification is inaccurate.
Because the preset offline time length exists between the offline time and the acquisition time of the driving data used when the attention event is detected, the automatic driving object can continue to drive within the preset offline time length, and the original environment data can be continuously acquired. The obstacle represented by the offline obstacle information obtained by identifying the raw environment data acquired at the offline time may also include the obstacle represented by the obstacle information. For the same obstacle, the offline obstacle information obtained by re-identification is more accurate.
For example, since the automatic traveling object continues traveling within the preset offline time period, the relative distance from the obstacle decreases, the original environmental data acquired by the data acquisition device becomes more accurate, and the above-described vehicle erroneously identified as an animal may be newly accurately identified as a vehicle.
In one embodiment of the present invention, the manner of identifying the offline obstacle information according to the acquired travel data before the offline time is similar to the manner of identifying the obstacle information according to the acquired travel data as described above, and only the specific values of the referenced travel data are different, which is not described herein.
In another embodiment of the present invention, the offline obstacle information of the obstacle may be jointly identified according to the travel data in the preset identification duration before the offline time. The off-line obstacle information of the obstacle at different acquisition moments can be respectively identified according to the driving data acquired at each acquisition moment in the preset identification time, and the off-line obstacle information is jointly used as the off-line obstacle information.
S103B: and comparing the obstacle information with the offline obstacle information, and storing running data used for detecting the concerned event if the difference between the obstacle information and the offline obstacle information meets the preset difference requirement.
Specifically, the preset difference requirement may be: the number of obstacles in the obstacle information, which is the same as the category of each obstacle in the off-line obstacle information, is smaller than a preset number. Or the ratio of the number of the obstacles in the obstacle information, which is the same as the category of each obstacle in the off-line obstacle information, to the total number of the obstacles in the obstacle information is smaller than a preset ratio. If the difference between the obstacle information and the offline obstacle information meets the preset difference requirement, a large number of types of obstacles in the obstacle information can be considered to be wrongly identified, the obstacle information is inaccurate, and the driving data need to be stored for further researching the problem, developing the technology related to automatic driving and improving the accuracy of identifying the obstacle information. The comparing the obstacle information with the offline obstacle information is: and comparing the category of each obstacle in the obstacle information with the category of each obstacle in the off-line obstacle information.
In addition, the preset difference requirement may also be: the similarity between the obstacle information and the offline obstacle information does not reach the preset similarity. For example, the preset similarity is: 80%, etc. If the difference between the obstacle information and the offline obstacle information meets the preset difference requirement, the obstacle information can be considered inaccurate, and the driving data needs to be stored for further researching the problem, developing the technology related to automatic driving, and improving the accuracy of identifying the obstacle information.
The comparing the obstacle information with the offline obstacle information is: and sequentially comparing each item of information in the obstacle information and the offline obstacle information, and determining the similarity between the obstacle information and the offline obstacle information by dividing the number of items of the same information by the total number of items of the obstacle information.
Furthermore, if it is determined that the automatic traveling object has a dangerous event or an accident event during traveling according to the obstacle information or the offline obstacle information, the obstacle is an obstacle that causes the automatic traveling object to have a dangerous event or an accident event during automatic traveling, that is, a dangerous obstacle that affects safe traveling of the automatic traveling object, the preset difference requirement may be: there is a difference between the above-mentioned obstacle information and the off-line obstacle information.
Since, in the case where the obstacle is a dangerous obstacle, if there is a difference between the obstacle information and the offline obstacle information, it is considered that when the obstacle information is recognized, information of a dangerous obstacle having a large influence on safe running of the automatic running object is not accurately recognized. Some problems may exist in the manner of identifying the obstacle information, and further research is required to continue subsequent development. Therefore, it is considered that the difference between the obstacle information and the offline obstacle information meets the preset difference requirement, and it is necessary to store the driving data used for detecting the noted event.
The driving data is stored only when the difference between the obstacle information and the off-line obstacle information meets a preset difference requirement. Otherwise, the running data is not considered to meet the requirement of the preset difference, and the running data is not stored.
From the above, it can be seen that, in the case that the preset attention event exists in the automatic driving process according to the driving data, the scheme provided by the embodiment of the invention does not directly store the driving data. But after determining that a preset attention event exists, the acquired driving data at the offline moment is applied to identify offline obstacle information, and the offline obstacle information is compared with the obstacle information used when the attention event is detected to determine whether the obstacle information meets the preset difference requirement. If the obstacle information is inaccurate compared with the offline obstacle information, indicating that it is necessary to further develop an automatic driving technique related to the obstacle information identification, the travel data is stored. Or if the obstacle information does not accurately represent the dangerous obstacle as compared with the offline obstacle information, it is described that it is necessary to further develop a technique related to the obstacle information identification, and it is necessary to store the travel data. The driving data are stored only when the obstacle information meets the preset difference requirement, so that further development and research can be conveniently carried out later.
Corresponding to the foregoing data storage method, referring to fig. 4, an embodiment of the present invention provides a schematic structural diagram of a first data storage device, where the device includes:
the data acquisition module 401 is configured to acquire, as driving data, original object data and/or original environment data of an automatic driving object during an automatic driving process, where the original object data is used to describe a state of the automatic driving object, and the original environment data is data acquired by a data acquisition device carried on the automatic driving object and is used to describe a surrounding environment;
the event detection module 402 is configured to detect whether a preset attention event exists in the automatic driving process according to the acquired driving data;
a data storage module 403, configured to store driving data used for detecting the attention event when the detection result of the event detection module 402 is yes.
From the above, since the running data stored in the scheme provided by the embodiment of the present invention is the original data, but not the target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is large, and the data with large information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
Referring to fig. 5, a schematic structural diagram of a second data storage device according to an embodiment of the present invention, compared to the embodiment shown in fig. 4, the event detection module 402 includes:
an obstacle recognition submodule 402A for recognizing obstacle information of obstacles around the automatic traveling object based on the acquired traveling data;
the event detection submodule 402B is configured to detect whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle.
From the above, since the obstacle is an important factor affecting the safe running of the automatic running object, the preset attention event of the automatic running object during the automatic running is often related to the obstacle, so that the obstacle in the surrounding environment of the automatic running object can be identified, and whether the preset attention event exists during the automatic running is detected according to the state of the obstacle.
In one embodiment of the present invention, the event detection submodule 402B is specifically configured to:
determining an obstacle movement track of the obstacle according to the obstacle position contained in the obstacle information;
determining an object motion trail of the automatic driving object according to the original object data contained in the driving data;
And if the distance between the obstacle movement track and the object movement track is smaller than the preset distance, determining that a preset attention event exists in the automatic driving process.
From the above, if the distance between the movement track of the obstacle and the movement track of the object is smaller than the preset distance, it can be considered that the distance between the object and the obstacle during the automatic driving may be smaller, so that the collision between the object and the obstacle may occur or nearly occur during the automatic driving, that is, a dangerous event or an accident event occurs, which indicates that the preset attention event exists during the automatic driving. By storing the running data of the dangerous event or the accident event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event or the accident event is improved, so that the processing capability of the automatic running object on the dangerous event or the accident time is improved, and the safety of the automatic running object is improved.
In one embodiment of the present invention, the event detection submodule 402B is specifically configured to:
determining movement indication information set in the environment around the automatic traveling object according to the original environment data contained in the traveling data;
Determining whether the motion state of the obstacle represented by the obstacle information accords with the motion state indicated by the motion indication information according to the determined obstacle information of the obstacle;
if not, determining that a preset attention event exists in the automatic driving process.
From the above, it is apparent that the movement instruction information set in the environment around the automatic traveling object is determined, and if the movement state of the obstacle represented by the obstacle information does not conform to the movement state indicated by the movement instruction information, it is determined that the movement state of the obstacle does not conform to the object safety movement specification represented by the movement instruction information, the obstacle is liable to be dangerous, and the traveling safety of the automatic traveling object is liable to be affected, that is, the automatic traveling object has a dangerous event during traveling, and it is determined that the automatic traveling object has a preset attention event. By storing the running data of the dangerous event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event is improved, so that the processing capability of the automatic running object for the dangerous event is improved, and the safety of the automatic running object is improved.
In one embodiment of the present invention, the event detection submodule 402B is specifically configured to:
determining whether an accident occurs to an automatic driving object in the automatic driving process according to the obstacle information of the identified obstacle and the original object data contained in the driving data;
if yes, determining that a preset attention event exists in the automatic driving process.
From the above, it can be determined whether a preset attention event exists in the automatic traveling process by determining whether an accident occurs in the automatic traveling object in the automatic traveling process. If the accident occurs to the automatic driving object in the automatic driving process, the accident event exists in the automatic driving process, and the preset attention event exists in the automatic driving process. By storing the driving data of the accident event, the stored driving data can be continuously used for development in the subsequent development, and the capability of the automatic driving object for identifying the accident event is improved, so that the processing capability of the automatic driving object for the accident event is improved, and the safety of the automatic driving object is improved.
In one embodiment of the present invention, the obstacle recognition submodule 402A is specifically configured to:
Identifying obstacles around the automatic driving object according to the original environment data collected by different data collecting devices contained in the driving data;
the event detection submodule 402B is specifically configured to:
and if the obstacles obtained by identification according to the original environment data acquired by different data acquisition equipment are different, determining that a preset attention event exists in the automatic driving process.
From the above, if the obstacles obtained by identifying the original environmental data collected by different data collecting devices are different, it is indicated that the data collecting devices may malfunction, or that more interference exists in the current environment, such as rain, snow, dust, haze, etc., which makes it difficult for the data collecting devices to collect the original environmental data. The original environment data acquired by the data acquisition equipment is not accurate enough, and the obstacle information acquired by recognition is not accurate enough. And the automatic driving object can not control the self-safe driving according to the accurate obstacle information, and is easy to be dangerous, so that the dangerous event exists in the automatic driving process, namely the preset attention event exists in the automatic driving process. By storing the running data of the dangerous event, the stored running data can be continuously used for development in the subsequent development, and the capability of the automatic running object for identifying the dangerous event is improved, so that the processing capability of the automatic running object for the dangerous event is improved, and the safety of the automatic running object is improved.
In one embodiment of the present invention, based on the embodiment shown in fig. 5, the data storage module 403 is specifically configured to:
identifying offline obstacle information of obstacles around the automatic driving object according to the acquired driving data at offline time, wherein the offline time is: a time of presetting an offline time period after an acquisition time of running data used when the attention event is detected;
and comparing the obstacle information with the offline obstacle information, and storing running data used for detecting the concerned event if the difference between the obstacle information and the offline obstacle information meets the preset difference requirement.
From the above, it can be seen that, in the case that the preset attention event exists in the automatic driving process according to the driving data, the scheme provided by the embodiment of the invention does not directly store the driving data. But after determining that a preset attention event exists, the acquired driving data at the offline moment is applied to identify offline obstacle information, and the offline obstacle information is compared with the obstacle information used when the attention event is detected to determine whether the obstacle information meets the preset difference requirement. If the obstacle information is inaccurate compared with the offline obstacle information, indicating that it is necessary to further develop an automatic driving technique related to the obstacle information identification, the travel data is stored. Or if the obstacle information does not accurately represent the dangerous obstacle as compared with the offline obstacle information, it is described that it is necessary to further develop a technique related to the obstacle information identification, and it is necessary to store the travel data. The driving data are stored only when the obstacle information meets the preset difference requirement, so that further development and research can be conveniently carried out later.
The embodiment of the invention also provides an electronic device, as shown in fig. 6, which comprises a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602 and the memory 603 complete communication with each other through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to implement any of the method steps described above in the data storage method when executing the program stored in the memory 603.
Under the condition that the electronic equipment provided by the embodiment of the invention stores data, because the running data stored in the scheme provided by the embodiment of the invention is the original data, but not the target level data, the data size of the running data stored in the scheme provided by the embodiment of the invention is larger, and the data with larger information size can be provided for the research of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In yet another embodiment of the present invention, a computer readable storage medium is provided, in which a computer program is stored, which when executed by a processor, implements the steps of any of the data storage methods described above.
In the case of executing the computer program stored in the computer readable storage medium provided by the embodiment of the present invention to store data, because the running data stored in the scheme provided by the embodiment of the present invention is original data, rather than target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is larger, and data with larger information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of any of the data storage methods of the above embodiments.
In the case of executing the computer program provided by the embodiment of the present invention to store data, because the running data stored in the scheme provided by the embodiment of the present invention is original data, rather than target level data, the data size of the running data stored in the scheme provided by the embodiment of the present invention is larger, and data with larger information size can be provided for the study of the automatic running technology. In addition, in the running process of the automatic running object, the influence degree of the concerned event on the running safety of the automatic running object is high, so that the storage of the running data acquired when the concerned event occurs plays an important role in the research of the automatic running technology. In addition, since the occurrence probability of the attention event during the running of the automatic running object is often low, only the running data acquired when the attention event occurs is stored, and the storage space required for storing the running data can be reduced.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, the electronic device, the computer-readable storage medium and the computer program product, the description is relatively simple, as it is substantially similar to the method embodiments, and relevant points are found in the partial description of the method embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims (8)

1. A method of data storage, the method comprising:
acquiring original object data and/or original environment data of an automatic driving object in an automatic driving process as driving data, wherein the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing surrounding environment;
identifying obstacle information of obstacles around the automatic traveling object according to the acquired traveling data;
detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle;
if so, identifying offline obstacle information of obstacles around the automatic driving object according to the acquired driving data at offline time, wherein the offline time is: a time of presetting an offline time period after an acquisition time of running data used when the attention event is detected;
Comparing the obstacle information with the offline obstacle information, and if the difference between the obstacle information and the offline obstacle information meets a preset difference requirement, storing running data used for detecting the concerned event, wherein the preset difference requirement is determined according to the identification information of the same category of obstacle and the offline obstacle.
2. The method according to claim 1, wherein detecting whether a preset event of interest exists in the automatic driving process according to the obstacle information of the identified obstacle comprises:
determining an obstacle movement track of the obstacle according to the obstacle position contained in the obstacle information;
determining an object motion trail of the automatic driving object according to the original object data contained in the driving data;
and if the distance between the obstacle movement track and the object movement track is smaller than the preset distance, determining that a preset attention event exists in the automatic driving process.
3. The method according to claim 1, wherein detecting whether a preset event of interest exists in the automatic driving process according to the obstacle information of the identified obstacle comprises:
Determining movement indication information set in the environment around the automatic traveling object according to the original environment data contained in the traveling data;
determining whether the motion state of the obstacle represented by the obstacle information accords with the motion state indicated by the motion indication information according to the determined obstacle information of the obstacle;
if not, determining that a preset attention event exists in the automatic driving process.
4. The method according to claim 1, wherein detecting whether a preset event of interest exists in the automatic driving process according to the obstacle information of the identified obstacle comprises:
determining whether an accident occurs to an automatic driving object in the automatic driving process according to the obstacle information of the identified obstacle and the original object data contained in the driving data;
if yes, determining that a preset attention event exists in the automatic driving process.
5. The method according to claim 1, wherein, in a case where the automatic traveling object is equipped with at least two data collection devices, the identifying obstacle information of obstacles around the automatic traveling object based on the acquired traveling data includes:
Identifying obstacles around the automatic driving object according to the original environment data collected by different data collecting devices contained in the driving data;
detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle comprises the following steps:
and if the obstacles obtained by identification according to the original environment data acquired by different data acquisition equipment are different, determining that a preset attention event exists in the automatic driving process.
6. A data storage device, the device comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original object data and/or original environment data of an automatic driving object in an automatic driving process as driving data, the original object data is used for describing the state of the automatic driving object, and the original environment data is data which is acquired by data acquisition equipment carried on the automatic driving object and is used for describing surrounding environment;
the event detection module is used for identifying obstacle information of obstacles around the automatic driving object according to the acquired driving data; detecting whether a preset attention event exists in the automatic driving process according to the obstacle information of the identified obstacle;
The data storage module is used for identifying offline obstacle information of obstacles around the automatic driving object according to the acquired driving data at offline time if the judging result of the event detection module is yes, wherein the offline time is: a time of presetting an offline time period after an acquisition time of running data used when the attention event is detected; comparing the obstacle information with the offline obstacle information, and if the difference between the obstacle information and the offline obstacle information meets a preset difference requirement, storing running data used for detecting the concerned event, wherein the preset difference requirement is determined according to the identification information of the same category of obstacle and the offline obstacle.
7. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for carrying out the method steps of any one of claims 1-5 when executing a program stored on a memory.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-5.
CN202011554343.4A 2020-12-24 2020-12-24 Data storage method and device Active CN112612284B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011554343.4A CN112612284B (en) 2020-12-24 2020-12-24 Data storage method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011554343.4A CN112612284B (en) 2020-12-24 2020-12-24 Data storage method and device

Publications (2)

Publication Number Publication Date
CN112612284A CN112612284A (en) 2021-04-06
CN112612284B true CN112612284B (en) 2024-01-16

Family

ID=75245286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011554343.4A Active CN112612284B (en) 2020-12-24 2020-12-24 Data storage method and device

Country Status (1)

Country Link
CN (1) CN112612284B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05108149A (en) * 1991-10-14 1993-04-30 Mazda Motor Corp Environment recognizing device of moving vehicle
US7692573B1 (en) * 2008-07-01 2010-04-06 The United States Of America As Represented By The Secretary Of The Navy System and method for classification of multiple source sensor measurements, reports, or target tracks and association with uniquely identified candidate targets
CN111563979A (en) * 2020-05-08 2020-08-21 奇瑞汽车股份有限公司 Storage method, device, terminal and storage medium of automatic driving data

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102636741B1 (en) * 2018-12-24 2024-02-16 현대자동차주식회사 Automatic Driving control apparatus, vehicle having the same and method for controlling the same

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05108149A (en) * 1991-10-14 1993-04-30 Mazda Motor Corp Environment recognizing device of moving vehicle
US7692573B1 (en) * 2008-07-01 2010-04-06 The United States Of America As Represented By The Secretary Of The Navy System and method for classification of multiple source sensor measurements, reports, or target tracks and association with uniquely identified candidate targets
CN111563979A (en) * 2020-05-08 2020-08-21 奇瑞汽车股份有限公司 Storage method, device, terminal and storage medium of automatic driving data

Also Published As

Publication number Publication date
CN112612284A (en) 2021-04-06

Similar Documents

Publication Publication Date Title
CN111712829B (en) Detecting a blocking stationary vehicle
US10713490B2 (en) Traffic monitoring and reporting system and method
CN109598066B (en) Effect evaluation method, apparatus, device and storage medium for prediction module
US20190079527A1 (en) Planning autonomous motion
CN110738857B (en) Vehicle violation evidence obtaining method, device and equipment
CN111382768A (en) Multi-sensor data fusion method and device
CN109871787B (en) Obstacle detection method and device
CN109270524B (en) Unmanned-vehicle-based multi-data fusion obstacle detection device and detection method thereof
CN111898491B (en) Identification method and device for reverse driving of vehicle and electronic equipment
RU2769921C2 (en) Methods and systems for automated detection of the presence of objects
CN111025297A (en) Vehicle monitoring method and device, electronic equipment and storage medium
CN115618932A (en) Traffic incident prediction method and device based on internet automatic driving and electronic equipment
CN113253299B (en) Obstacle detection method, obstacle detection device and storage medium
US20230400859A1 (en) Predicting Jaywaking Behaviors of Vulnerable Road Users
CN114074667A (en) Stationary object detection
CN114771548A (en) Data logging for advanced driver assistance system testing and verification
CN109285381A (en) For detecting the method and system of the free area in parking lot
CN114895250A (en) Radar data processing method and device, electronic equipment and storage medium
CN112447060A (en) Method and device for recognizing lane and computing equipment
CN114475656A (en) Travel track prediction method, travel track prediction device, electronic device, and storage medium
Singh et al. An intelligent realtime traffic control based on vehicle density
US20190389456A1 (en) Transportation infrastructure communication and control
CN117315624A (en) Obstacle detection method, vehicle control method, device, apparatus, and storage medium
CN112612284B (en) Data storage method and device
CN113393675A (en) Vehicle ID determination method, device, equipment and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant