CN116758502A - Intersection identification method, device, equipment and storage medium - Google Patents

Intersection identification method, device, equipment and storage medium Download PDF

Info

Publication number
CN116758502A
CN116758502A CN202310710168.0A CN202310710168A CN116758502A CN 116758502 A CN116758502 A CN 116758502A CN 202310710168 A CN202310710168 A CN 202310710168A CN 116758502 A CN116758502 A CN 116758502A
Authority
CN
China
Prior art keywords
lane line
effective length
road
vehicle
lane
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
Application number
CN202310710168.0A
Other languages
Chinese (zh)
Inventor
杨晓飞
于玉祥
卢玉坤
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.)
Imotion Automotive Technology Suzhou Co Ltd
Original Assignee
Imotion Automotive Technology Suzhou 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 Imotion Automotive Technology Suzhou Co Ltd filed Critical Imotion Automotive Technology Suzhou Co Ltd
Priority to CN202310710168.0A priority Critical patent/CN116758502A/en
Publication of CN116758502A publication Critical patent/CN116758502A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses a crossing identification method, a device, equipment and a storage medium, and relates to the technical field of intelligent driving. The method comprises the following steps: acquiring lane information in real time in the running process of the vehicle; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening according to the effective length of the lane line and the first judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule; and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule. The accuracy of crossing identification is improved.

Description

Intersection identification method, device, equipment and storage medium
Technical Field
The application relates to the technical field of intelligent driving, in particular to a crossing identification method, a device, equipment and a storage medium.
Background
At present, by utilizing an intelligent driving technology, a driver can start a lane keeping function to assist driving under intelligent driving, but the lane keeping function is possibly suddenly out of control in the face of a road junction, such as a crossroad and other scenes, and the safety of the driver is endangered by steering wheel steering, so that a vehicle control strategy under the road junction scene is required to be formulated in a targeted manner, and better man-machine co-driving is further realized, therefore, the identification of the road junction is very important, and how to accurately identify the road junction is a problem which needs to be solved at present.
Disclosure of Invention
In view of the above, the present application aims to provide a method, a device and a medium for identifying an intersection, which can improve the accuracy of identifying the intersection. The specific scheme is as follows:
in a first aspect, the application discloses an intersection identification method, which comprises the following steps:
acquiring lane information in real time in the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type;
judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule;
Judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule;
judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule;
judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule;
and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule.
Optionally, the determining, according to the effective length of the lane line and the first determination rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening includes:
if the effective length of the lane line corresponding to the vehicle continuously descends in the first target period and the effective length of the lane line is smaller than the first preset threshold value in the second target period, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the lane line in the road opening scene.
Optionally, the determining, according to the lane line quality and the second determining rule, whether the vehicle driving scene meets the change rule corresponding to the lane line quality of the road opening includes:
If the lane line quality corresponding to the vehicle continuously decreases in the third target period and the lane line quality is smaller than the second preset threshold value in the fourth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the lane line quality in the road opening scene.
Optionally, the determining, according to the effective length of the road edge and the third determining rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening includes:
if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period and the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the effective length of the road edge in the road opening scene.
Optionally, the determining, according to the effective length of the road edge and the third determining rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening includes:
if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period, the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, and the effective length of the road edge when the effective length of the road edge starts to descend is smaller than the fourth preset threshold value, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the road edge in the road opening scene.
Optionally, the determining, according to the lane line type and the fourth determination rule, whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening includes:
determining the lane type of a lane where the vehicle is located according to the lane line types at two sides of the vehicle; the lane types include a left lane, a middle lane, and a right lane;
judging whether the vehicle driving scene meets the change rule corresponding to the lane line type in the road opening scene or not by utilizing the lane line change judgment rule corresponding to the lane line type; the lane-change determination rule is a determination rule that changes from a broken line to a solid line for the target-side lane line.
Optionally, the determining, according to the determination result of each change rule, whether the vehicle is about to drive into the road junction further includes:
after judging that the vehicle is about to drive into the road junction, judging whether the vehicle drives out of the road junction according to a fifth judging rule; the fifth judgment rule is that the effective length of the current lane line of the vehicle is larger than a fifth preset threshold value and the quality of the current lane line is larger than a sixth preset threshold value, or the driving distance of the vehicle is larger than the target distance.
Optionally, the determining whether the vehicle is about to drive into the road opening according to the determination result of each change rule includes:
And if the vehicle driving scene meets the change rule corresponding to the road mouth lane line quality and the change rule corresponding to the road mouth lane line type, and meets the change rule corresponding to the effective length of the road mouth lane line or the change rule corresponding to the effective length of the road edge of the road mouth, judging that the vehicle is about to drive into the road mouth.
In a second aspect, the present application discloses an intersection recognition device, comprising:
the information acquisition module is used for acquiring lane information in real time in the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type;
the first judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening according to the effective length of the lane line and the first judging rule;
the second judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule;
the third judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule;
The fourth judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judging rule;
and the comprehensive judging module is used for judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule.
In a third aspect, the present application discloses an electronic device, comprising:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the intersection identification method.
In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program when executed by the processor implements the aforementioned intersection recognition method.
In the application, lane information is acquired in real time in the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule; and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule. Therefore, by combining the lane information of the effective length of the lane line, the quality of the lane line, the effective length of the road edge and the type of the lane line, according to the change rule of various lane information at the road junction, corresponding judgment rules are configured for various lane information, and finally, whether the vehicle is about to drive into the road junction or not is judged by integrating the judgment result of each type of lane information, so that the accuracy of identifying the road junction is improved, and the intelligent driving vehicle can conveniently adopt a formulated vehicle control strategy by identifying the road junction in advance, and better man-machine co-driving is realized.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying intersections;
FIG. 2 is a flowchart of a specific intersection identification method provided by the application;
FIG. 3 is a schematic diagram of a specific intersection identification provided by the present application;
FIG. 4 is a schematic diagram of a crossing recognition device according to the present application;
fig. 5 is a block diagram of an electronic device according to the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the prior art, by using the intelligent driving technology, a driver can start the lane keeping function to assist driving under the intelligent driving, but the lane line is suddenly lost in the scenes such as an intersection, so that the lane keeping function is probably suddenly lost, the safety of the driver is endangered due to the fact that the lane line is suddenly lost, and the steering wheel is in disorder, so that a vehicle control strategy under the scene of the intersection is formulated in a targeted mode, and further better man-machine co-driving is realized, therefore, the identification of the intersection is very important, and how to accurately identify the intersection is a problem to be solved at present. In order to overcome the technical problems, the application provides the intersection identification method, which improves the accuracy of intersection identification.
The embodiment of the application discloses an intersection identification method, which is shown in fig. 1, and can comprise the following steps:
step S11: acquiring lane information in real time in the running process of the vehicle; the lane information includes a lane line effective length, a lane line quality, a road edge effective length, and a lane line type.
In this embodiment, first, real-time lane information of a vehicle during driving of the vehicle is acquired, where the lane information includes a lane line effective length (lineview end), a lane line quality (LineQuality), a road edge effective length (roadedgeview end), and a lane line type (LineType). The effective length of the lane line refers to the length of the uninterrupted lane lines at two sides of the lane where the front of the vehicle is located, and can be a solid line or a broken line. The lane line quality characterizes the plausibility of the identified lane line. The effective length of the road edge can be the length of the road shoulder stone which is uninterrupted at the side of the lane.
In this embodiment, the acquiring lane information in real time during the running process of the vehicle may include: acquiring original lane information output by a chip in real time in the running process of a vehicle; and filtering the original lane information to obtain the processed lane information.
In order to better observe the change trend, the effective length of the lane line, the quality of the lane line, the effective length of the road edge and the type of the lane line are required to be subjected to filtering treatment, such as first-order low-pass filtering treatment, and then a prediction algorithm of the intersection is performed based on the treated lane information. Wherein the filter function may be as follows:
Y(n)＝∝X(n)+(1-∝)Y(n-1)；
where, oc is a filter coefficient, X (n) is an input at the current time, and Y (n-1) is an output value of the previous time filter.
Step S12: and judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule.
In this embodiment, according to the obtained effective length of the lane line and the first preset judgment rule, it is judged whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line at the road opening. It can be understood that the change rule of the effective length of the lane line at the road opening is different from usual, so that the first judgment rule can be generated according to the change rule corresponding to the effective length of the lane line of the road opening, so that the vehicle driving scene can be analyzed according to the effective length of the lane line, and the road opening can be an intersection.
In this embodiment, the determining, according to the effective length of the lane line and the first determination rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road junction may include: if the effective length of the lane line corresponding to the vehicle continuously descends in the first target period and the effective length of the lane line is smaller than the first preset threshold value in the second target period, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the lane line in the road opening scene. When the vehicle is about to arrive at the road junction, the effective length of the lane line is continuously reduced, and the effective length of the lane line in the last journey is necessarily lower than a certain threshold value, so that whether the rule of the road junction is met or not is judged by combining the descending trend of the effective length of the lane line and the length value.
Specifically, comparing the effective length of the lane line of the current lane line with the effective length of the lane line at the last moment, if the effective length of the lane line of the current lane line is lower than the effective length of the lane line at the last moment and is continuous for ten frames, the effective length of the lane line of the current lane line is indicated to be in a descending trend, and a lane line effective length descending trend sign signal is set to true; when the effective length of the lane line is smaller than 10m and lasts for a certain time, the effective length of the lane line of the current lane line is lower, and a sign signal with the lower effective length of the lane line is set as true; when the effective length decreasing trend sign signal of the lane line is set to true, and the lower effective length sign signal of the lane line is set to true, the change rule of the effective length of the lane line when the vehicle is at the intersection is met. The first preset threshold, the first target period and the second target period may be customized according to urban road conditions, for example, customized according to the sparseness of the road junction.
Step S13: and judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule.
In this embodiment, according to the obtained lane line quality and the second preset judgment rule, it is judged whether the vehicle driving scene meets the change rule corresponding to the lane line quality of the road opening. It can be understood that the change rule of the lane line quality at the road opening is different from usual, so that the second judgment rule can be generated according to the change rule corresponding to the lane line quality at the road opening, so as to analyze the driving scene of the vehicle according to the lane line quality.
In this embodiment, the determining, according to the lane line quality and the second determining rule, whether the vehicle driving scene meets the change rule corresponding to the lane line quality of the road opening may include: if the lane line quality corresponding to the vehicle continuously decreases in the third target period and the lane line quality is smaller than the second preset threshold value in the fourth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the lane line quality in the road opening scene. Namely, when the vehicle is about to arrive at the road junction, the quality of the lane line is continuously reduced, and the quality of the lane line in the last journey is lower than a certain threshold value, so that whether the rule of the road junction is met or not is judged by combining the descending trend of the quality of the lane line and the numerical value.
Specifically, comparing the current lane line quality with the lane line quality at the last moment, if the current lane line quality is lower than the lane line quality at the last moment and is continuous for ten frames, the current lane line quality is indicated to be in a descending trend, and a lane line quality descending trend sign signal is set to true; when the quality of the lane line is lower than 0.8 and a certain time is continued, the current lane line quality is lower, and a signal of a sign with lower lane line quality is set as true; when the lane line quality decreasing trend sign signal is set to true, and the lane line quality lower sign signal is set to true, the change rule of the lane line quality when the vehicle is at the intersection is met. The second preset threshold, the third target period and the fourth target period may be customized according to the degree of freshness of the lane line of the city.
Step S14: and judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule.
In this embodiment, according to the obtained effective length of the road edge and a third preset judgment rule, it is judged whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening. It can be understood that the change rule of the effective length of the road edge at the road opening is different from usual, so that the third judgment rule can be generated according to the change rule corresponding to the effective length of the road edge, so as to analyze the driving scene of the vehicle according to the effective length of the road edge.
In this embodiment, the determining, according to the effective length of the road edge and the third determining rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening may include: if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period and the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the effective length of the road edge in the road opening scene. When the vehicle is about to arrive at the road junction, the effective length of the road edge is continuously reduced, and the effective length of the road edge in the last path is necessarily lower than a certain threshold value, so that whether the rule of the road junction is met or not is judged by combining the descending trend of the effective length of the road edge and the length value.
Specifically, comparing the effective length of the current road edge with the effective length of the road edge at the last moment, if the effective length of the current road edge is lower than the effective length of the road edge at the last moment and ten frames are continued, the effective length of the current road edge is indicated to be in a descending trend, and a sign signal of the descending trend of the effective length of the road edge is set to true; when the effective length of the road edge is lower than 25m and lasts for a certain time, the effective length of the current road edge is lower, and a sign signal with the lower effective length of the road edge is set as true; when a longer road edge exists before, the effective length decreasing trend sign signal of the road edge is set to true, and meanwhile, the effective length decreasing sign signal of the road edge is set to true, the change rule of the effective length of the road edge when the vehicle is at the intersection is met. The third preset threshold, the fourth preset threshold, the fifth target period and the sixth target period may be customized according to the urban road edge construction law.
In this embodiment, the determining, according to the effective length of the road edge and the third determining rule, whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening may include: if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period, the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, and the effective length of the road edge when the effective length of the road edge starts to descend is larger than the fourth preset threshold value, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the road edge in the road opening scene.
It can be understood that, because parking spaces are planned on two sides of some streets in the city, there may be parking vehicles on two sides of the road, that is, when there are stationary vehicles on two sides of the road, for example, a scene that a vehicle may be parked every ten or more meters may be set, at this time, the effective length of the road edge identified by the camera may be continuously reduced from ten or more meters to zero, and then a road edge of ten or more meters is identified and continuously reduced to zero, so that the continuously repeated curve satisfies that the effective length of the road edge is in a downward trend, and if there is a scene of a broken line cutting solid line at this time, the continuously erroneous identification is an intersection scene. In order to reduce such misidentification it is therefore required that the starting point at which the effective length of the road edge decreases is at least greater than a fourth preset threshold value, for example 30m, i.e. only the process of decreasing from a longer road edge to 0 is identified.
Step S15: and judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening or not according to the lane line type and the fourth judgment rule.
In this embodiment, according to the obtained lane line type and a fourth preset judgment rule, it is judged whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening. It can be understood that the change rule of the lane line type at the road opening is different from usual, so that the fourth judgment rule can be generated according to the change rule corresponding to the lane line type, so as to analyze the driving scene of the vehicle according to the lane line type.
In this embodiment, the determining, according to the lane line type and the fourth determination rule, whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening may include: determining the lane type of a lane where the vehicle is located according to the lane line types at two sides of the vehicle; the lane types include a left lane, a middle lane, and a right lane; judging whether the vehicle driving scene meets the change rule corresponding to the lane line type in the road opening scene or not by utilizing the lane line change judgment rule corresponding to the lane line type; the lane-change determination rule is a determination rule that changes from a broken line to a solid line for the target-side lane line.
It can be understood that the lane types are different, and the change rules corresponding to the lane line types in the road junction scene are different. For example, the type of the lane line at the left side and the right side of the lane is judged by comparing the type of the current lane line with the type of the lane line at the last moment, and if the type of the lane line at the left side is a solid line or a road edge and the type of the lane line at the right side is a broken line within a certain time, the fact that the self-vehicle probability is at the leftmost lane at the moment is indicated; if the type of the left lane line is a broken line and the type of the right lane line is also a broken line within a certain time, the self-vehicle is indicated to be in the middle lane with high probability; if the type of the left lane line is a broken line and the type of the right lane line is a solid line or a road edge within a certain time, the fact that the self-vehicle is in the rightmost lane with high probability at the moment is indicated, and if the self-vehicle is in other cases, whether the current self-vehicle has lane change behavior is judged, and if the current self-vehicle is not in the lane change behavior, the self-vehicle position at the last moment is kept.
Therefore, when the vehicle is positioned on the leftmost lane, only the process of judging whether the lane line on the right side is virtual to real or not is needed; when the vehicle is in the middle lane, the process of changing from virtual to real is needed to judge whether the lane lines on the left side and the right side exist at the same time; when the vehicle is positioned on the rightmost lane, only the process of judging whether the left lane line is in the virtual-real state or not is needed. That is, the lane change judgment rule corresponding to the lane type is utilized to judge whether the vehicle driving scene meets the change rule corresponding to the lane type in the road opening scene. If the situation of the virtual change is caused, the lane line type is changed to the mark position wire.
In this embodiment, the determining, by using the lane change determining rule corresponding to the lane type, whether the vehicle driving scene meets the change rule corresponding to the lane type in the road junction scene may include: and when the lane line type is changed, recording the vehicle driving distance, and judging whether the vehicle driving scene meets the change rule corresponding to the lane line type in the road opening scene according to the lane line change judging rule and the vehicle driving distance. It can be understood that, in order to reasonably plan the running of the vehicle in the urban road, some roads also control the vehicle by changing the lane line type, and in order to avoid the misidentification caused by the situation, in this embodiment, the comprehensive analysis is performed by combining the continuous running distance of the vehicle after the lane line type is changed. For example, when the type of the left lane line at the previous moment is a broken line, the type of the left lane line at the current moment is a solid line, the distance of the left lane line driven by the driver after the virtual change is started to be recorded, and when the distance is greater than a preset threshold value, such as 100m, the change rule corresponding to the type of the lane line at the road opening is considered to be not met.
Step S16: and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule.
In this embodiment, whether the vehicle is about to drive into the road opening is determined based on the determination result of the change rule corresponding to the effective length of the lane line, the quality of the lane line, the effective length of the road edge, and the type of the lane line. Namely, as shown in fig. 2, the identification of the scene of the crossroad is completed by recording the effective length of the lane line, the quality of the lane line, the change trend of the effective length of the road edge, the process of changing the lane line from virtual to real and the change rule of the road opening. For example, when the effective length of the lane line, the quality of the lane line and the effective length of the road edge simultaneously meet the change rule of the vehicle at the road junction, and the lane line type is in a process of changing from virtual to real at the moment, the condition that the vehicle reaches the road junction is indicated. For example, fig. 3 shows an intersection recognition effect diagram. Therefore, when the driver starts the lane keeping function under intelligent driving and drives on a road, the vehicle can properly decelerate in advance through identifying the intersection in advance, and can also have no vehicle in front and be a green light, when the lane line disappears, the steering wheel can keep the angle at the previous moment to continue to drive forwards, so that a more comfortable and safer driving experience is provided for the driver, and better man-machine co-driving is realized.
In this embodiment, the determining, according to the determination result of each change rule, whether the vehicle is about to drive into the road junction may include: and if the vehicle driving scene meets the change rule corresponding to the road mouth lane line quality and the change rule corresponding to the road mouth lane line type, and meets the change rule corresponding to the effective length of the road mouth lane line or the change rule corresponding to the effective length of the road edge of the road mouth, judging that the vehicle is about to drive into the road mouth. Namely, the effective length of the lane line and the effective length of the roadside edge are basically the same in judging principle, so that mutual auxiliary judgment can be realized, the judging accuracy is extremely high under the condition that the change rule is met, but the change rule corresponding to the effective length of the lane line at the road opening and the change rule value corresponding to the effective length of the road edge at the road opening meet one, and the obvious effect can be realized.
In this embodiment, the determining, according to the determination result of each change rule, whether the vehicle is about to drive into the road junction may further include: after judging that the vehicle is about to drive into the road junction, judging whether the vehicle drives out of the road junction according to a fifth judging rule; the fifth judgment rule is that the effective length of the current lane line of the vehicle is larger than a fifth preset threshold value and the quality of the current lane line is larger than a sixth preset threshold value, or the driving distance of the vehicle is larger than the target distance. After the vehicle is judged to be driven to the intersection, whether the vehicle is driven to leave the intersection can be judged according to the effective length of the current lane line of the vehicle and the quality of the lane line or the driving distance of the vehicle. Specifically, when the road junction zone bit is true, the distance travelled by the own vehicle is recorded, and when the distance travelled by the own vehicle is greater than 60m, or the effective length of the lane line is longer and the quality of the lane line is higher, the condition that the vehicle has travelled away from the road junction at this time is indicated, and the road junction zone bit is false is indicated.
From the above, in this embodiment, lane information is obtained in real time during the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule; and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule. Therefore, by combining the lane information of the effective length of the lane line, the quality of the lane line, the effective length of the road edge and the type of the lane line, according to the change rule of various lane information at the road junction, corresponding judgment rules are configured for various lane information, and finally, whether the vehicle is about to drive into the road junction or not is judged by integrating the judgment result of each type of lane information, so that the accuracy of identifying the road junction is improved, and the intelligent driving vehicle can conveniently adopt a formulated vehicle control strategy by identifying the road junction in advance, and better man-machine co-driving is realized.
On the basis of the embodiment, the application also discloses a specific intersection identification method, and the vehicle specifically comprises the following steps from an entrance intersection to an exit intersection:
1. acquiring a lane line effective length (lineViewEnd), a lane line quality (LineQuality), a road edge effective length (RoadEdgeViewEnd) and a lane line type (lineType), and performing simple first-order low-pass filtering processing on LineViewEnd, lineQuality, roadEdgeViewEnd;
2. comparing the ViewEnd of the current lane line with the ViewEnd of the lane line at the last moment, if the ViewEnd of the current lane line is lower than the ViewEnd of the lane line at the last moment and is continuous for ten frames, the ViewEnd of the current lane line is shown to be in a descending trend, and a LineViewEnd descending trend sign signal is set to true;
3. when the ViewEnd of the lane line is lower than 40m and lasts for a certain time, indicating that the ViewEnd of the current lane line is lower, setting a LineViewEnd lower flag signal to true;
4. when the LineViewEnd descending trend flag signal is set to true, and the LineViewEnd lower flag signal is set to true, the change rule of the lane line ViewEnd when the vehicle is at the crossroad is satisfied;
5. comparing the Quality of the current lane line with the Quality of the lane line at the last moment, if the Quality of the current lane line is lower than the Quality of the lane line at the last moment and the Quality is continuous for ten frames, the condition that the Quality of the current lane line is in a descending trend is indicated, and a Linequality descending trend sign signal is set to true;
6. When the Quality of the lane line is lower than 0.8 and the current lane line lasts for a certain time, the Quality of the current lane line is lower, and a lower line Quality flag signal is set to true;
7. when the LineQuaity descending trend flag signal is set to true, and meanwhile, the LineQuaity lower flag signal is set to true, the change rule of the lane line Quality when the vehicle is at the intersection is met;
8. when the ViewEnd of the road edge is greater than 30m, a longer road edge is considered to exist at the moment;
9. comparing the ViewEnd of the current road edge with the ViewEnd of the road edge at the last moment, if the ViewEnd of the current road edge is lower than the ViewEnd of the road edge at the last moment and is continuous for ten frames, the ViewEnd of the current road edge is shown to be in a descending trend, and a RoadEdgeViewEnd descending trend sign signal is set as true;
10. when the ViewEnd of the road edge is lower than 25m and lasts for a certain time, indicating that the ViewEnd of the current road edge is lower, setting a RoadEdgeViewEnd lower flag signal to true;
11. when a longer road edge exists before, and the RoadEdgeViewEnd descending trend marking signal is set to true, and meanwhile, the RoadEdgeViewEnd lower marking signal is set to true, the change rule of the road edge ViewEnd when the vehicle is at the crossroad is described;
12. Comparing the current lane line type with the lane line type at the previous moment, judging the types of lane lines at the left side and the right side of the lane, and if the type of the lane line at the left side is a solid line or a road edge within a certain time and the type of the lane line at the right side is a broken line, indicating that the self-vehicle probability is in the leftmost lane at the moment; if the type of the left lane line is a broken line and the type of the right lane line is also a broken line within a certain time, the self-vehicle is indicated to be in the middle lane with high probability; if the type of the left lane line is a broken line and the type of the right lane line is a solid line or a road edge within a certain time, the fact that the vehicle is in the rightmost lane with high probability at the moment is indicated, and if the vehicle is in other conditions, whether the current vehicle has lane change behavior is judged, and if the current vehicle is not in the lane change behavior, the vehicle is kept at the last moment;
13. when the type of the left lane line at the previous moment is a dotted line and the type of the left lane line at the current moment is a solid line, recording the distance of the left lane line from virtual change to real time and the driving of the vehicle. When the type of the right lane line at the previous moment is a dotted line and the type of the right lane line at the current moment is a solid line, recording the distance of the right lane line from virtual to real time, and when the distance is more than 100m, setting the signal to be 0;
14. When the vehicle is in the leftmost lane, only the process of changing from virtual to real is needed to judge whether the right lane line exists, when the vehicle is in the middle lane, the process of changing from virtual to real is needed to judge whether the left lane line and the right lane line exist simultaneously, and when the vehicle is in the rightmost lane, only the process of changing from virtual to real is needed to judge whether the left lane line exists;
15. when LineViewEnd, lineQuality, roadEdgeViewEnd meets the change rule of the vehicle at the intersection at the same time, and the process of changing the lane line type from virtual to real exists at the moment, the fact that the vehicle reaches the intersection at the moment is indicated;
16. when the crossroad zone bit is true, the distance of the vehicle driving is recorded, when the distance of the vehicle driving is more than 60m or the distance of the vehicle driving is longer in lineViewEnd and the LineQuality quality is higher at the moment, or when the ViewEnd of the road edge is equal to 0 and lasts for 5 frames, the road edge is considered to be absent, the condition that the vehicle has driven away from the crossroad at the moment is indicated, and the crossroad zone bit is false.
Correspondingly, the embodiment of the application also discloses an intersection recognition device, which is shown in fig. 4, and comprises:
an information acquisition module 11 for acquiring lane information in real time during the running of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type;
The first judging module 12 is configured to judge whether the vehicle driving scene meets a change rule corresponding to the effective length of the lane line of the road opening according to the effective length of the lane line and the first judging rule;
the second judging module 13 is configured to judge whether the driving scene of the vehicle meets a change rule corresponding to the lane line quality of the road opening according to the lane line quality and the second judging rule;
the third judging module 14 is configured to judge whether the vehicle driving scene meets a change rule corresponding to the effective length of the road edge of the road opening according to the effective length of the road edge and a third judging rule;
the fourth judging module 15 is configured to judge, according to the lane line type and a fourth judging rule, whether the vehicle driving scene meets a change rule corresponding to the lane line type of the road opening;
the comprehensive judgment module 16 is configured to judge whether the vehicle is about to drive into the road opening according to the judgment result of each change rule.
From the above, in this embodiment, lane information is obtained in real time during the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule; judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule; and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule. Therefore, by combining the lane information of the effective length of the lane line, the quality of the lane line, the effective length of the road edge and the type of the lane line, according to the change rule of various lane information at the road junction, corresponding judgment rules are configured for various lane information, and finally, whether the vehicle is about to drive into the road junction or not is judged by integrating the judgment result of each type of lane information, so that the accuracy of identifying the road junction is improved, and the intelligent driving vehicle can conveniently adopt a formulated vehicle control strategy by identifying the road junction in advance, and better man-machine co-driving is realized.
In some embodiments, the first determining module 12 may be specifically configured to determine that the current driving scenario of the vehicle satisfies the change rule corresponding to the effective length of the lane line under the road junction scenario if the effective length of the lane line corresponding to the vehicle continuously decreases in the first target period and the effective length of the lane line is smaller than the first preset threshold in the second target period.
In some embodiments, the second determining module 13 may be specifically configured to determine that the current driving scene of the vehicle meets the change rule corresponding to the lane line quality in the road opening scene if the lane line quality corresponding to the vehicle continuously decreases in the third target period and the lane line quality is smaller than the second preset threshold in the fourth target period.
In some embodiments, the third determining module 14 may be specifically configured to determine that the current driving scenario of the vehicle satisfies the change rule corresponding to the effective length of the road edge in the road junction scenario if the effective length of the road edge corresponding to the vehicle continuously decreases in the fifth target period and the effective length of the road edge is smaller than the third preset threshold in the sixth target period.
In some embodiments, the third determining module 14 may be specifically configured to determine that the current driving scenario of the vehicle satisfies the change rule corresponding to the effective length of the road edge in the road junction scenario if the effective length of the road edge corresponding to the vehicle continuously decreases in the fifth target period, the effective length of the road edge is smaller than the third preset threshold in the sixth target period, and the effective length of the road edge when the effective length of the road edge starts to decrease is greater than the fourth preset threshold.
In some embodiments, the fourth determining module 15 may be specifically configured to determine a lane type of a lane where the vehicle is located according to lane line types on both sides of the vehicle; the lane types include a left lane, a middle lane, and a right lane;
judging whether the vehicle driving scene meets the change rule corresponding to the lane line type in the road opening scene or not by utilizing the lane line change judgment rule corresponding to the lane line type; the lane-change determination rule is a determination rule that changes from a broken line to a solid line for the target-side lane line.
In some specific embodiments, the intersection recognition device may specifically include:
the road junction judging unit is used for judging whether the vehicle drives out of the road junction according to a fifth judging rule after judging that the vehicle is about to drive into the road junction; the fifth judgment rule is that the effective length of the current lane line of the vehicle is larger than a fifth preset threshold value and the quality of the current lane line is larger than a sixth preset threshold value, or the driving distance of the vehicle is larger than the target distance.
In some embodiments, the comprehensive determining module 16 may be specifically configured to determine that the vehicle is about to drive into the road junction if the vehicle driving scene satisfies a change rule corresponding to the quality of the road junction lane line and a change rule corresponding to the type of the road junction lane line, and satisfies a change rule corresponding to the effective length of the road junction lane line or a change rule corresponding to the effective length of the road edge of the road junction.
Further, the embodiment of the application also discloses an electronic device, and referring to fig. 5, the content in the drawing should not be considered as any limitation on the application scope of the application.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. The memory 22 is configured to store a computer program, which is loaded and executed by the processor 21 to implement relevant steps in the intersection identification method disclosed in any of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon include an operating system 221, a computer program 222, and data 223 including lane information, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and the computer program 222, so as to implement the operation and processing of the processor 21 on the mass data 223 in the memory 22, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the intersection identification method performed by the electronic device 20 as disclosed in any of the foregoing embodiments.
Further, the embodiment of the application also discloses a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by a processor, the steps of the intersection identification method disclosed in any embodiment are realized.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further 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.
The above description of the intersection recognition method, device, equipment and medium provided by the invention applies specific examples to illustrate the principle and implementation of the invention, and the above examples are only used for helping to understand the method and core ideas of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims (11)

1. An intersection identification method, comprising:
acquiring lane information in real time in the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type;
judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening or not according to the effective length of the lane line and the first judging rule;
judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule;
judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule;
Judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judgment rule;
and judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule.
2. The intersection identification method according to claim 1, wherein the determining whether the vehicle driving scene satisfies the change rule corresponding to the effective length of the lane line of the intersection according to the effective length of the lane line and the first determination rule includes:
if the effective length of the lane line corresponding to the vehicle continuously descends in the first target period and the effective length of the lane line is smaller than the first preset threshold value in the second target period, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the lane line in the road opening scene.
3. The intersection identification method according to claim 1, wherein the determining whether the vehicle driving scene satisfies the change rule corresponding to the road intersection lane line quality according to the lane line quality and the second determination rule includes:
if the lane line quality corresponding to the vehicle continuously decreases in the third target period and the lane line quality is smaller than the second preset threshold value in the fourth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the lane line quality in the road opening scene.
4. The intersection identification method according to claim 1, wherein the determining whether the vehicle driving scene satisfies the change rule corresponding to the effective length of the road edge of the intersection according to the effective length of the road edge and the third determination rule includes:
if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period and the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, judging that the current running scene of the vehicle meets the change rule corresponding to the effective length of the road edge in the road opening scene.
5. The intersection identification method according to claim 4, wherein the determining whether the vehicle driving scene satisfies the change rule corresponding to the effective length of the road edge of the intersection according to the effective length of the road edge and the third determination rule includes:
if the effective length of the road edge corresponding to the vehicle continuously descends in the fifth target period, the effective length of the road edge is smaller than the third preset threshold value in the sixth target period, and the effective length of the road edge when the effective length of the road edge starts to descend is larger than the fourth preset threshold value, the current running scene of the vehicle is judged to meet the change rule corresponding to the effective length of the road edge in the road opening scene.
6. The intersection identification method according to claim 1, wherein the determining whether the vehicle driving scene satisfies the change rule corresponding to the lane line type of the road intersection according to the lane line type and the fourth determination rule includes:
determining the lane type of a lane where the vehicle is located according to the lane line types at two sides of the vehicle; the lane types include a left lane, a middle lane, and a right lane;
judging whether the vehicle driving scene meets the change rule corresponding to the lane line type in the road opening scene or not by utilizing the lane line change judgment rule corresponding to the lane line type; the lane-change determination rule is a determination rule that changes from a broken line to a solid line for the target-side lane line.
7. The intersection identification method according to claim 1, wherein the determining whether the vehicle is about to drive into the road entrance according to the determination result of each change rule further comprises:
after judging that the vehicle is about to drive into the road junction, judging whether the vehicle drives out of the road junction according to a fifth judging rule; the fifth judgment rule is that the effective length of the current lane line of the vehicle is larger than a fifth preset threshold value and the quality of the current lane line is larger than a sixth preset threshold value, or the driving distance of the vehicle is larger than the target distance.
8. The intersection recognition method according to any one of claims 1 to 7, wherein the determining whether the vehicle is about to drive into the road entrance based on the determination result of each change rule includes:
and if the vehicle driving scene meets the change rule corresponding to the road mouth lane line quality and the change rule corresponding to the road mouth lane line type, and meets the change rule corresponding to the effective length of the road mouth lane line or the change rule corresponding to the effective length of the road edge of the road mouth, judging that the vehicle is about to drive into the road mouth.
9. An intersection identification device, comprising:
the information acquisition module is used for acquiring lane information in real time in the running process of the vehicle; the lane information comprises a lane line effective length, a lane line quality, a road edge effective length and a lane line type;
the first judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the lane line of the road opening according to the effective length of the lane line and the first judging rule;
the second judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the road opening lane line quality according to the lane line quality and the second judging rule;
The third judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the effective length of the road edge of the road opening or not according to the effective length of the road edge and the third judging rule;
the fourth judging module is used for judging whether the vehicle driving scene meets the change rule corresponding to the lane line type of the road opening according to the lane line type and the fourth judging rule;
and the comprehensive judging module is used for judging whether the vehicle is about to drive into the road opening or not according to the judging result of each change rule.
10. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the intersection identification method as claimed in any one of claims 1 to 8.
11. A computer-readable storage medium storing a computer program; wherein the computer program when executed by the processor implements the intersection identification method as claimed in any one of claims 1 to 8.
CN202310710168.0A 2023-06-15 2023-06-15 Intersection identification method, device, equipment and storage medium Pending CN116758502A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310710168.0A CN116758502A (en) 2023-06-15 2023-06-15 Intersection identification method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310710168.0A CN116758502A (en) 2023-06-15 2023-06-15 Intersection identification method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116758502A true CN116758502A (en) 2023-09-15

Family

ID=87947241

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310710168.0A Pending CN116758502A (en) 2023-06-15 2023-06-15 Intersection identification method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116758502A (en)

Similar Documents

Publication Publication Date Title
US10703362B2 (en) Autonomous driving autonomous system, automated driving assistance method, and computer program
CN110182209B (en) Vehicle control device and vehicle control method
US10642268B2 (en) Method and apparatus for generating automatic driving strategy
EP3859278A1 (en) Road feature point extraction method and system
CN110182210B (en) Vehicle control device and vehicle control method
CN110751847B (en) Decision-making method and system for automatically driving vehicle behaviors
CN108133484B (en) Automatic driving processing method and device based on scene segmentation and computing equipment
CN112373474B (en) Lane line fusion and transverse control method, system, vehicle and storage medium
JP2015022499A (en) Driving characteristic determination system
CN115292435B (en) High-precision map updating method and device, electronic equipment and storage medium
US9725092B2 (en) Method, host vehicle and following space management unit for managing following space
CN110986994B (en) Automatic lane change intention marking method based on high-noise vehicle track data
CN117184126A (en) Automatic driving method and device and computer readable storage medium
CN112896166A (en) Vehicle lane changing method and device and electronic equipment
CN115257771B (en) Intersection identification method, electronic equipment and storage medium
JP2010140265A (en) Travel support device, method, and program
CN116758502A (en) Intersection identification method, device, equipment and storage medium
CN114067569B (en) Vehicle left-turning auxiliary early warning method in V2X vehicle networking environment
CN114582153B (en) Ramp entry long solid line reminding method, system and vehicle
CN107121147B (en) Navigation method and equipment
CN113156923B (en) Road data generation, navigation and running control method, device, equipment and medium
CN112810604A (en) Intelligent vehicle behavior decision method and system based on parking lot scene
CN115431981B (en) Driving auxiliary identification system based on high-precision map
CN114913710B (en) Human-vehicle interaction decision-making method and device, storage medium and terminal
CN114820691B (en) Method, device and equipment for detecting motion state of vehicle and storage 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