CN117576947A - Collision early warning method, system and storage medium - Google Patents
Collision early warning method, system and storage medium Download PDFInfo
- Publication number
- CN117576947A CN117576947A CN202311413067.3A CN202311413067A CN117576947A CN 117576947 A CN117576947 A CN 117576947A CN 202311413067 A CN202311413067 A CN 202311413067A CN 117576947 A CN117576947 A CN 117576947A
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- target vehicle
- early warning
- collision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000009471 action Effects 0.000 claims abstract description 125
- 238000001514 detection method Methods 0.000 claims abstract description 69
- 230000008447 perception Effects 0.000 claims abstract description 32
- 238000004590 computer program Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 14
- 238000004364 calculation method Methods 0.000 description 10
- 239000000523 sample Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000004438 eyesight Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000035484 reaction time Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000016776 visual perception Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
- G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/0969—Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/90—Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a collision early warning method, a system and a storage medium, comprising the following steps: constructing a target detection area in the electronic map based on target vehicle action information of the target vehicle; defining at least one auxiliary vehicle in the target detection area, and determining an auxiliary vehicle blind area for each auxiliary vehicle; collecting road side perception data of the blind area of the auxiliary vehicle through road side perception equipment; when the road side perception data of the blind area contains early warning target action information, calculating a target vehicle action track of a target vehicle, and calculating an early warning target action track of an early warning target; and generating collision early warning information corresponding to the early warning target according to the action track of the target vehicle and the action track of the early warning target. The road side sensing equipment on two sides of the road can acquire global visual field information of the blind area, effectively predicts whether a target vehicle collides with an early-warning target, sends collision early-warning information to remind the target vehicle before predicting collision, and helps the target vehicle to avoid collision events in advance.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a collision early warning method, a collision early warning system and a storage medium.
Background
During the running of the vehicle, the vehicle inevitably has a blind spot in view due to the influence of the own structure of the vehicle. At the same time, the vehicle is also prone to forming blind areas of view due to the shielding of terrain, buildings, and other vehicles.
The traffic participants with the disadvantages of pedestrians, non-motor vehicles and the like have larger potential safety hazards in the process of traffic travel, in particular to a common name of 'ghost probe' event, namely, on the premise that vehicles or other obstacles in front block the sight, the pedestrians or the non-motor vehicles are suddenly jumped out from the blind areas of the visual field.
In order to avoid traffic safety problems caused by the 'ghost probe' event, the following scheme is adopted in the related art: detecting whether a barrier with a 'ghost probe' type risk exists in front of the vehicle or not in real time, identifying and judging whether the vehicle or a non-vehicle barrier exists, acquiring visual blind area images in a direct and indirect mode respectively, judging whether a pedestrian exists in a blind area according to the visual blind area images, dividing an assumed collision area by combining the current position of the vehicle, the current movement speed of the vehicle, the position of the pedestrian in the blind area and the movement speed of the pedestrian when the pedestrian exists, and finally making a decision of limiting the vehicle speed based on the assumed collision area.
In the above scheme, most of vehicles on the market do not have complete perceptibility, and even high-grade intelligent vehicles cannot open data links between enterprises due to factors such as privacy safety, technical barriers and the like; second, the surrounding environment does not necessarily have a vehicle or a vehicle with the ability to acquire images, or the acquired images do not necessarily cover all the area of the blind area. For the above scheme, how to obtain accurate and effective blind zone data has great difficulty in solving the 'ghost probe' event.
Disclosure of Invention
Accordingly, the present invention is directed to a collision early warning method, system and storage medium, which can obtain the road side perception data of the blind area of the auxiliary vehicle in real time through the road side perception devices on both sides of the road, and the target vehicle can obtain the global visual field information of the blind area of the auxiliary vehicle, so as to solve the problem of difficult acquisition of the blind area data.
In a first aspect, the present application provides a collision early warning method, including the steps of:
constructing a target detection area corresponding to a target vehicle in an electronic map based on target vehicle action information of the target vehicle;
defining at least one auxiliary vehicle in the target detection area, and determining an auxiliary vehicle blind area of the auxiliary vehicle relative to the target vehicle for each auxiliary vehicle; the auxiliary vehicle blind area is a view range which is shielded by the auxiliary vehicle relative to the target vehicle;
Collecting road side perception data of the auxiliary vehicle blind area through road side perception equipment corresponding to the auxiliary vehicle blind area; when the road side perception data of the blind area comprises early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and calculating the early warning target action track of the early warning target based on the early warning target action information;
and generating collision early warning information corresponding to the early warning target according to the target vehicle action track and the early warning target action track.
In an embodiment, the constructing, in an electronic map, a target detection area corresponding to the target vehicle based on target vehicle action information of the target vehicle specifically includes:
determining current position coordinates of the target vehicle based on the target vehicle action information, defining the current position coordinates of the target vehicle as first position coordinates, and determining a current lane corresponding to the target vehicle in the electronic map according to the first position coordinates;
determining a second position coordinate which is positioned on the current lane and has a preset first length from the first position coordinate, and determining an area covered by the current lane between the first position coordinate and the second position coordinate as a reference detection area;
In the electronic map, determining areas which are arranged on two opposite sides of the reference detection area and are not more than a preset first width away from the edge of the reference detection area as auxiliary detection areas;
the target vehicle detection area is generated based on the reference detection area and the auxiliary detection area.
In an embodiment, the determining, for each of the auxiliary vehicles, an auxiliary vehicle blind area of the auxiliary vehicle relative to the target vehicle specifically includes:
determining a blind area direction of the blind area of the auxiliary vehicle according to the target vehicle action information of the target vehicle and the auxiliary vehicle action information of the auxiliary vehicle;
determining current position coordinates of the auxiliary vehicle based on the auxiliary vehicle action information, defining the current position coordinates of the auxiliary vehicle as third position coordinates, and determining fourth position coordinates which are in the blind area direction and have a preset second length from the third position coordinates;
and establishing rectangular areas with the second length and the preset second width as side lengths between the third position coordinates and the fourth position coordinates along the blind area direction, and defining the rectangular areas as auxiliary vehicle blind areas.
In an embodiment, when the road side perception data of the blind area includes early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and before calculating the early warning target action track of the early warning target based on the early warning target action information, further includes:
determining the current position coordinate of the early warning target according to the early warning target action information, and defining the current position coordinate of the early warning target as a fifth position coordinate;
judging whether the early warning target is positioned in the target detection area or not based on the fifth position coordinate; if so, determining an auxiliary vehicle blind area where the early warning target is currently located according to the fifth position coordinate, and defining the auxiliary vehicle blind area where the early warning target is currently located as a target blind area;
acquiring the geometric range of the target blind area according to the road side perception data of the target blind area;
and writing the geometric range of the target blind area into collision early warning information.
In an embodiment, after writing the geometric range of the target blind area into collision pre-warning information, the method further includes:
judging whether the target vehicle is stationary or not based on the target vehicle action information; if yes, the collision early warning information is sent to the target vehicle; if not, judging whether the early warning target is static or not based on the early warning target action information; when the early warning target is stationary, the collision early warning information is sent to the target vehicle; and when the early warning target is not stationary, calculating the action track of the target vehicle and the action track of the early warning target.
In an embodiment, before generating collision warning information corresponding to the warning target according to the target vehicle action track and the warning target action track, the method further includes:
judging whether an intersection point exists between the action track of the target vehicle and the action track of the early warning target; if yes, defining the intersection point as a collision point, calculating a collision distance between the collision point and the target vehicle and a minimum safety distance between the target vehicle and the early warning target, and writing the collision distance and the minimum safety distance into target vehicle control information; if not, collision early warning information is sent to the target vehicle.
In an embodiment, after calculating the collision distance between the collision point and the target vehicle and the minimum safety distance between the target vehicle and the early warning target, and generating target vehicle control information according to the collision distance and the minimum safety distance, the method further includes:
generating a safe distance coordinate based on the minimum safe distance;
calculating an expected deceleration speed and an expected deceleration distance of the target vehicle reaching a safe distance coordinate, and writing the expected deceleration speed and the expected deceleration distance into the target vehicle control information;
Judging whether the collision distance is greater than the minimum safety distance; if yes, calculating the action time of the early warning target reaching a collision point, and writing the action time into the collision early warning information; if not, the target vehicle control information is sent to the target vehicle, a target vehicle control instruction is generated according to the target vehicle control information, and the target vehicle is driven to execute the target vehicle control instruction.
In an embodiment, after the target vehicle control information is sent to the target vehicle, and a target vehicle control instruction is generated according to the target vehicle control information, and the target vehicle is driven to execute the target vehicle control instruction, the method further includes:
determining at least one surrounding vehicle located in a preset distance range of the target vehicle, and calculating position relation data of the surrounding vehicle and the target vehicle;
generating surrounding vehicle control information according to the position relation data and the target vehicle control information, sending the surrounding vehicle control information to the surrounding vehicle, generating a surrounding vehicle control instruction according to the surrounding vehicle control information, and driving the surrounding vehicle to execute the surrounding vehicle control instruction.
In a second aspect, the present application provides a collision warning system comprising: a processor and a memory; wherein the memory stores a computer program for loading and executing the collision warning method according to any one of the first aspects by the processor.
In a third aspect, the present application provides a computer-readable storage medium storing instructions for loading and executing the collision warning method according to any one of the first aspects by a processor.
In the collision early warning method of the embodiment, road side perception data of the blind area of the auxiliary vehicle can be obtained in real time through road side perception equipment on two sides of a road, the target vehicle can obtain global visual field information of the blind area of the auxiliary vehicle in the target detection area, the problem that the blind area data are difficult to obtain is solved, whether the target vehicle collides with an early warning target or not is effectively predicted based on action information of the target vehicle and the early warning target, collision early warning information is sent to remind the target vehicle before the collision is predicted, the driver of the target vehicle can conveniently and timely make parking or deceleration and other operations, and the target vehicle is helped to avoid collision events in advance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system architecture diagram of a collision early warning method of the present application.
Fig. 2 is a flow chart of a collision early warning method in an embodiment of the present application.
FIG. 3 is a schematic diagram of the construction of a detection region in an embodiment of the present application.
Fig. 4 is a schematic diagram of creating a blind zone in an embodiment of the present application.
Fig. 5 is a schematic structural diagram of a collision early warning system based on road side perception in an embodiment of the present application.
Detailed Description
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
In the description of the present invention, unless explicitly stated and limited otherwise, the terms "disposed," "mounted," "connected," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the terms described above will be understood to those of ordinary skill in the art in a specific context.
The terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," and the like are used as references to orientations or positional relationships based on the orientation or positional relationships shown in the drawings, or the orientation or positional relationships in which the inventive product is conventionally disposed in use, merely for convenience of description and simplicity of description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be configured and operated in a particular orientation, and therefore are not to be construed as limiting the invention.
The terms "first," "second," "third," and the like, are merely used for distinguishing between similar elements and not necessarily for indicating or implying a relative importance or order.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a list of elements does not include only those elements but may include other elements not expressly listed.
The "collision risk of the weak traffic participant" (the weak traffic participant refers to pedestrians or non-motor vehicles in this embodiment, simply referred to as an early warning target) is a major potential safety hazard in the traffic trip, and has been paid attention to, especially for the event commonly called "ghost probe", in order to effectively cope with the problem of "ghost probe", different ideas are proposed in the industry from the multidimensional view of management or technology, and mainly include:
a. from a management view, a visual space is reserved by modifying facility equipment of a risk intersection, for example, adjusting the position of a stop line of a motor vehicle lane adjacent to a pavement; or the pedestrians and the non-motor vehicles at the road opening/road section pass through to carry out strengthening management and the like;
b. from the perspective of the traditional technology, aiming at the situation that a single management means cannot effectively avoid the passing of pedestrians or non-motor vehicles, intelligent perceived roadside facilities such as infrared correlation or visual perception are additionally arranged, collision event monitoring and early warning (voice prompt) are carried out on the pedestrians or the non-motor vehicles, and the probability of collision of the ghost probe is reduced as much as possible;
c. The novel technical view angle surrounds the core problem that main traffic participants such as vehicle drivers, pedestrians or non-motor vehicles can not effectively find risks because of vision blind areas, and the novel technical view angle utilizes vision perception + vehicle road cooperation technology to monitor and forecast and analyze the heavy spot area by 360 degrees without dead angles through AI energized means so as to provide early warning prompt for a risk main body in time.
The method a and the method b realize safety guarantee mainly by sensing and reminding early warning targets such as pedestrians, non-motor vehicles and the like, but are difficult to reach and control effectively for vehicles and drivers, and the method c adopts a system thought of vehicle-road cooperation, can realize real-time linkage with the vehicle drivers, but has quite different effects due to algorithm differences in the aspects of blind area sensing, risk judgment, early warning strategies and the like related to 'ghost probes'.
In the related scheme, a vehicle end is taken as a main part, whether an obstacle with a 'ghost probe' risk exists in front is detected in real time, the obstacle is identified and judged to be a vehicle or a non-vehicle obstacle, visual blind area images are respectively obtained in a direct and indirect mode, then whether pedestrians exist in the blind areas or not is judged according to the visual blind area images, when the pedestrians exist, an assumed collision area is divided by combining the current position of the vehicle, the current movement speed of the vehicle, the positions of the pedestrians in the blind areas and the movement speed of the pedestrians, and finally a decision for limiting the vehicle speed is made based on the assumed collision area. According to the method, other vehicles are communicated with the vehicle, so that the perception capability of the vehicle can be expanded to a certain extent, different and effective decisions can be made for different obstacles and vision blind areas, and the application range is expanded.
The scheme is that the visual blind area image is obtained in a direct and indirect mode, and the blind area image is obtained by calling cameras of vehicles around the blind area, and then decision judgment is carried out. The above method has the following limitations:
(1) Blind zone data are difficult to obtain. On one hand, most of vehicles on the market do not have complete perceptibility, and even high-grade intelligent driving vehicles cannot get through data links among enterprises due to factors such as privacy safety, technical barriers and the like; second, the surrounding environment does not necessarily have a vehicle or a vehicle with the ability to acquire images, or the acquired images do not necessarily cover all the area of the blind area.
(2) The calculation power of the vehicle end and the network bandwidth are difficult to meet. In theory, after the host vehicle detects the obstacle, the blind area image request after the obstacle is transmitted to the auxiliary vehicle (obstacle vehicle), the auxiliary vehicle calls the auxiliary vehicle camera to shoot the image of the appointed area and transmits the shot image back to the host vehicle, and the host vehicle performs collision detection. From the global perspective, dead zones between vehicles on the road exist at any time, if dead zone images are calculated and uploaded continuously or larger pressure is caused on a vehicle end network and calculation force, and the network bandwidth and calculation capacity of the vehicle end are relatively limited.
(3) The problem of untimely braking. 80% of traffic accidents are caused by misoperation or untimely reaction of human beings, and if collision risk information received by a driver is not observed or timely reacted, collision risk can be possibly caused.
(4) Fewer pre-warning coverage objects. The vehicles are mutually independent, information sharing is not achieved, only the vehicle obtains blind area information, the vehicle behind possibly cannot obtain blind area pedestrian or non-motor vehicle information, and when the vehicle predicts the risk of blind area collision and suddenly decelerates, traffic accidents caused by rear-end collision of the vehicle behind can be caused.
In the collision early warning method of the embodiment, road side perception data of the blind area of the auxiliary vehicle can be obtained in real time through road side perception equipment on two sides of a road, the target vehicle can obtain global visual field information of the blind area of the auxiliary vehicle in the target detection area, the problem that the blind area data are difficult to obtain is solved, whether the target vehicle collides with an early warning target or not is effectively predicted based on action information of the target vehicle and the early warning target, collision early warning information is sent to remind the target vehicle before the collision is predicted, the driver of the target vehicle can conveniently and timely make parking or deceleration and other operations, and the target vehicle is helped to avoid collision events in advance.
Fig. 1 is a system architecture diagram of a collision early warning method according to an embodiment. The early warning command center establishes connection with a vehicle-mounted terminal cluster and a road side sensing device, the vehicle-mounted terminal cluster comprises a plurality of vehicle-mounted terminals, each target vehicle 10 is provided with at least one vehicle-mounted terminal, and the road side sensing device can comprise: image acquisition devices such as camera 20, and signal acquisition devices such as millimeter wave radar and laser radar. The early warning command center may include a server 40 with data processing and storage and a cloud platform 30, where the vehicle-mounted terminal is a monitoring terminal for monitoring and managing the target vehicle 10, and the vehicle-mounted terminal is installed in the target vehicle 10, and may collect real-time action information of the target vehicle 10 and interact with the cloud platform to implement early warning and control of the target vehicle 10.
As shown in fig. 2, the present invention provides a collision early warning method, which includes the following steps:
step S100: constructing a target detection area corresponding to a target vehicle in an electronic map based on target vehicle action information of the target vehicle;
step S200: defining at least one auxiliary vehicle in the target detection area, and determining an auxiliary vehicle blind area of the auxiliary vehicle relative to the target vehicle for each auxiliary vehicle; the auxiliary vehicle blind area is a view range which is shielded by the auxiliary vehicle relative to the target vehicle;
Step S300: collecting road side perception data of the auxiliary vehicle blind area through road side perception equipment corresponding to the auxiliary vehicle blind area; when the road side perception data of the blind area comprises early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and calculating the early warning target action track of the early warning target based on the early warning target action information;
step S400: and generating collision early warning information corresponding to the early warning target according to the target vehicle action track and the early warning target action track.
In step S100, the vehicle-mounted terminal of the target vehicle registers an early warning function in the cloud platform of the early warning command center, and the attribute information such as the size, color, license plate number, etc. of the target vehicle is stored in the memory of the server of the early warning command center. When the target vehicle runs, the vehicle-mounted terminal of the target vehicle acquires target vehicle action information of the target vehicle in real time and sends the target vehicle action information to the cloud platform, wherein the target vehicle action information comprises attribute information, position information, speed information, acceleration information, heading information and the like of the target vehicle.
The server of the early warning command center can construct a target detection area corresponding to the target vehicle in a preset electronic map according to the target vehicle action information of the target vehicle, and specifically comprises the following steps:
step S101: determining current position coordinates of the target vehicle based on the target vehicle action information, defining the current position coordinates of the target vehicle as first position coordinates, and determining a current lane corresponding to the target vehicle in the electronic map according to the first position coordinates;
step S102: determining a second position coordinate which is positioned on the current lane and has a preset first length from the first position coordinate, and determining an area covered by the current lane between the first position coordinate and the second position coordinate as a reference detection area;
step S103: in the electronic map, determining areas which are arranged on two opposite sides of the reference detection area and are not more than a preset first width away from the edge of the reference detection area as auxiliary detection areas;
step S104: the target vehicle detection area is generated based on the reference detection area and the auxiliary detection area.
In step S101, as shown in fig. 3, the first position coordinate is the real longitude and latitude coordinate of the target vehicle 51, the vehicle-mounted terminal sends the first position coordinate to the cloud platform, and the server finds a coordinate point corresponding to the first position coordinate in the electronic map according to the first position coordinate received by the cloud platform, and uses the coordinate point as the position coordinate of the target vehicle 51. The electronic map of the embodiment is a high-precision map, the absolute precision of the map is not lower than 50cm, the relative error of each 100m is not more than 20cm, and the current lane of the target vehicle can be accurately positioned according to the first position coordinates. The current lane is the actual lane position where the target vehicle is currently located.
In steps S102 to S104, the second position coordinates having the first length L1 from the first position coordinates are determined on the current lane, the reference detection region 61 is constructed on the first lane with the first position coordinates and the second position coordinates as end points, the auxiliary detection region 62 having the first width W1 is widened on each of the left and right sides of the reference detection region 61, and the reference detection region 61 and the auxiliary detection region 62 are combined to generate the target detection region. The reference detection area is an area on a track line in front of the target vehicle, and collision between the target vehicle and the early warning target is most likely to occur in the reference detection area. The early warning targets such as pedestrians, non-motor vehicles and the like easily enter the reference detection region 61 through the auxiliary detection regions on the left side and the right side, and the target detection region constructed by the embodiment can effectively monitor the early warning targets positioned in the region in front of the vehicle and timely send collision early warning information to the target vehicle.
Alternatively, the current lane may be a straight linear lane, and the reference detection area and the auxiliary detection area, and the target detection area obtained by combining the two are rectangular areas adapted to the current lane. The current lane can also be a nonlinear lane with radian or corner, and the reference detection area and the auxiliary detection area and the target detection area obtained by combining the reference detection area and the auxiliary detection area are non-rectangular areas which are matched with the current lane.
Alternatively, the first length L1 of the present embodiment may be selected to be a fixed value of 20m, 50m, 100m, or the like, and the first length L1 may be adaptively generated according to the speed of the target vehicle. For example, the first length L1 is provided with three gears, and when the speed of the target vehicle is between 0 and 30 yards, the first length L1 is selected to be 20m; when the speed of the target vehicle is 30-60 yards, the first length L1 is 50m; when the speed of the target vehicle exceeds 60 yards, the first length L1 is selected to be 100m. It is understood that the value of the first length L1 is merely taken as an example, and may be adaptively set according to the actual conditions of the target vehicle and the road.
Alternatively, the first width W1 of the present embodiment may be set according to the width of the current lane, or may be set according to the body width of the target vehicle. Preferably, because the early warning targets in the lanes on the left and right sides of the current lane are difficult for the driver of the target vehicle to directly acquire the action conditions of the early warning targets on the left and right sides before entering the current lane, the first width W1 of the embodiment is equal to the width of the current lane, so that the action conditions of the early warning targets on the left and right sides can be accurately acquired, and collision early warning information can be timely sent to the target vehicle.
In step S200, as shown in fig. 3 and 4, the assist vehicle 52 is another vehicle that is located in front of the target vehicle 51 and that can block the line of sight of the target vehicle 51, and the assist vehicle blind area 70 is an area located in the assist vehicle 52 that blocks the view of the target vehicle.
The auxiliary vehicle blind area of the auxiliary vehicle relative to the target vehicle is created for each auxiliary vehicle in the target detection area, and specifically comprises the following steps:
step S201: determining a blind area direction of the blind area of the auxiliary vehicle according to the target vehicle action information of the target vehicle and the auxiliary vehicle action information of the auxiliary vehicle;
step S202: determining current position coordinates of the auxiliary vehicle based on the auxiliary vehicle action information, defining the current position coordinates of the auxiliary vehicle as third position coordinates, and determining fourth position coordinates which are in the blind area direction and have a preset second length from the third position coordinates;
step S203: and establishing rectangular areas with the second length and the preset second width as side lengths between the third position coordinates and the fourth position coordinates along the blind area direction, and defining the rectangular areas as auxiliary vehicle blind areas.
In step S201, the target vehicle action information of the target vehicle includes a first position coordinate of the target vehicle, the auxiliary vehicle action information of the auxiliary vehicle includes a third position coordinate of the auxiliary vehicle, and the blind area direction of the blind area of the auxiliary vehicle can be determined according to the connecting line between the first position coordinate and the third position coordinate.
In step S202 and step S203, fourth position coordinates having a second length L2 from the third position coordinates are determined in the blind area direction, and an auxiliary vehicle blind area is constructed in front of the auxiliary vehicle with the third position coordinates and the fourth position coordinates as end points.
Optionally, as shown in fig. 4, the auxiliary vehicle blind area 70 is a rectangular area, the second width W2 of the auxiliary vehicle blind area 70 is the hypotenuse length of the target vehicle 51, the target vehicle action information of the target vehicle 51 includes the hypotenuse length, the second length L2 of the auxiliary vehicle blind area 70 is the maximum value of the minimum safe distance S and the preset safe distance length of the target vehicle 51, the minimum safe distance S is the current speed, the expression is l2=max (S, length), and the calculation formula of the minimum safe distance S can be referred to the "T/CSAE 246-2022 intelligent network car V2X system early warning application function test and evaluation method" as follows:
Wherein V is s The current speed of the target vehicle (unit is m/s), the reaction time of the driver (the range of the T is 0.3 s-2 s) and T 1 For braking coordination time (t 1 The value range of (2) is 0.35 s-0.6 s), t 2 For the deceleration increase time (t 2 Typically 0.2 s), a) s Braking the average deceleration (a) for the driver s The range of the value of (2) is 3.6m 2 /s~7.9m 2 /s),d 0 For the safe distance (d) of the target vehicle when stationary 0 Default to 3 m), t 3 Calculating a link delay (t 3 Default to 0.5 s).
In step S300, the road side sensing device of the auxiliary vehicle blind area at least includes an image acquisition device such as a camera, and the server can accurately identify whether an early warning target such as a non-motor vehicle and a pedestrian exists in the auxiliary vehicle blind area through an intelligent identification technology based on the image information acquired by the image acquisition device, and generate a target vehicle action track of the target vehicle according to the current speed, acceleration, heading and other data of the target vehicle, and generate an early warning target action track of the early warning target according to the current speed, acceleration and moving direction of the early warning target. The target vehicle action track and the early warning target action track can be generated by a multi-order Bezier curve, an MPC prediction model, a spline curve and the like, and the embodiment is not limited in any way.
The image acquisition equipment of the embodiment is arranged on two sides of a road and has visual perception algorithm capability, image data of detected early warning targets such as vehicles and pedestrians are converted into structural data through local perception, multi-view track fusion is carried out through a cloud platform big data computing center, global perception target track data is formed, all auxiliary vehicle blind areas in a target detection area are covered, and the problem that the auxiliary vehicle blind area data are difficult to acquire is solved.
When the road side perception data of the blind area comprises early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and before calculating the early warning target action track of the early warning target based on the early warning target action information, further comprising:
step S501: determining the current position coordinate of the early warning target according to the early warning target action information, and defining the current position coordinate of the early warning target as a fifth position coordinate;
step S502: judging whether the early warning target is positioned in the target detection area or not based on the fifth position coordinate; if so, determining an auxiliary vehicle blind area where the early warning target is currently located according to the fifth position coordinate, and defining the auxiliary vehicle blind area where the early warning target is currently located as a target blind area;
Step S503: acquiring the geometric range of the target blind area according to the road side perception data of the target blind area;
step S504: and writing the geometric range of the target blind area into collision early warning information.
In steps S501 to S504, the early warning target action information of the early warning target includes attribute information, position information, speed information, acceleration information, moving direction information, and the like of the early warning target, where the position information includes current longitude and latitude coordinate data, that is, a fifth position coordinate, of the early warning target. The server compares the fifth position coordinate with the position range of the detection area, whether the early warning target is located in the target detection area or not can be identified, if the early warning target is not located in the target detection area, the probability that the early warning target collides with the target vehicle is smaller, and the early warning command center does not need to calculate the collision point of the action track of the target vehicle and the action track of the early warning target.
When the early warning target is located in the target detection area, whether the early warning target is located in the auxiliary vehicle blind area or not needs to be judged. When the early warning target is not located in the auxiliary vehicle blind area, namely the action track of the early warning target is in the visual field range of the target vehicle, the driver of the target vehicle can directly obtain the position information of the early warning target, and the early warning command center is not required to make collision reminding. When the early warning target is positioned in the auxiliary vehicle blind area, the auxiliary vehicle blind area where the early warning target is positioned is marked as a target blind area, and the geometric range data of the target blind area is written into collision early warning information, so that a driver of the target vehicle can early warn the action information of the early warning target in advance or timely execute operations such as parking and slow running, and the risk of collision between the early warning target and the target vehicle is effectively avoided.
Optionally, when a plurality of early warning targets exist in a driving road section of the target vehicle, an auxiliary vehicle blind area where each early warning target is located needs to be judged, and a mark of a 'target blind area' is marked on the corresponding auxiliary vehicle blind area. Meanwhile, in order to distinguish the target blind area from the non-target blind area, a 'YES' mark can be marked on the target blind area, so that the early warning target exists in the auxiliary vehicle blind area, and a driver needs to carefully travel when passing through the vicinity of the auxiliary vehicle blind area; and the non-target blind area is marked with NO, which indicates that NO early warning target exists in the auxiliary vehicle blind area, and a driver can safely pass near the auxiliary vehicle blind area. Through the YES mark and the NO mark, a driver of the target vehicle can intuitively obtain which auxiliary vehicle blind area has an early warning target, so that the driver of the target vehicle can conveniently and timely make parking or deceleration and other vehicle control operations, and the target vehicle is helped to avoid the occurrence of a collision event in advance.
After writing the geometric range of the target blind area into collision early warning information, the method further comprises step S505: judging whether the target vehicle is stationary or not based on the target vehicle action information; if yes, the collision early warning information is sent to the target vehicle; if not, judging whether the early warning target is static or not based on the early warning target action information; when the early warning target is stationary, the collision early warning information is sent to the target vehicle; and when the early warning target is not stationary, calculating the action track of the target vehicle and the action track of the early warning target.
In step S505, there is a scene in which the auxiliary vehicle located before the target vehicle has been parked, and the target vehicle also follows the parking of the auxiliary vehicle. For example, at a traffic light intersection, a traffic lane is a red light, a pedestrian lane is a green light, at this time, a target vehicle and an auxiliary vehicle are stopped at the traffic lane and wait for the red light, and early warning targets such as pedestrians, non-motor vehicles and the like pass through the pedestrian lane. Even if the target vehicle has a blind area, the target vehicle can hardly collide with the early warning target on the pedestrian path because the target vehicle is stopped, and in the scene, the collision between the target vehicle and the early warning target is not required to be additionally predicted and collision early warning information is generated.
In addition, there is also a scene in which the early warning target has stopped, waiting for the target vehicle and the auxiliary vehicle located in front of the target vehicle to preferentially pass through the road section. For example, at a traffic light intersection, a traffic light channel is green light, a pedestrian channel is red light, at the moment, an early warning target stops waiting for the red light, the early warning target does not have a trend of passing through the pedestrian channel, and at the moment, no additional prediction of collision between a target vehicle and the early warning target and generation of collision early warning information are needed.
In the embodiment, the early warning command center is provided with the cloud platform with big data computing capability, so that the computing capability of the early warning command center can be remarkably improved. The big data cloud platform has the characteristics of large calculation power and large bandwidth, and the big data platform is used for carrying out collision risk calculation of auxiliary vehicle blind areas, so that the problem that the vehicle end calculation power is low in bandwidth and small can be solved, and the data with larger and more distant vision can be obtained, so that the method is beneficial to finding out the risk in advance and helping a target vehicle avoid collision events in advance.
Before generating collision warning information corresponding to the warning target according to the target vehicle action track and the warning target action track, the method further comprises step S600: judging whether an intersection point exists between the action track of the target vehicle and the action track of the early warning target; if yes, defining the intersection point as a collision point, calculating a collision distance between the collision point and the target vehicle and a minimum safety distance between the target vehicle and the early warning target, and writing the collision distance and the minimum safety distance into target vehicle control information; if not, collision early warning information is sent to the target vehicle.
In step S600, the server generates a target vehicle track curve based on the target vehicle action track, generates an early warning target track curve based on the early warning target action track, and the collision point is the intersection point of the target vehicle track curve and the early warning target track curve, and carries predicted collision coordinates and collision time, and based on the collision coordinates, the collision distance between the collision point and the target vehicle and the minimum safety distance between the target vehicle and the early warning target can be calculated.
After calculating the collision distance between the collision point and the target vehicle and the minimum safety distance between the target vehicle and the early warning target, and generating target vehicle control information according to the collision distance and the minimum safety distance, the method further comprises the steps of:
Step S601: generating a safe distance coordinate based on the minimum safe distance;
step S602: calculating an expected deceleration speed and an expected deceleration distance of the target vehicle reaching a safe distance coordinate, and writing the expected deceleration speed and the expected deceleration distance into the target vehicle control information;
step S603: judging whether the collision distance is greater than the minimum safety distance; if yes, calculating the action time of the early warning target reaching a collision point, and writing the action time into the collision early warning information; if not, the target vehicle control information is sent to the target vehicle, a target vehicle control instruction is generated according to the target vehicle control information, and the target vehicle is driven to execute the target vehicle control instruction.
In steps S601 to S603, the calculation formula of the minimum safe distance S is as follows:
wherein V is s The current speed of the target vehicle (unit is m/s), the reaction time of the driver (the range of the T is 0.3 s-2 s) and T 1 For braking coordination time (t 1 The value range of (2) is 0.35 s-0.6 s), t 2 For the deceleration increase time (t 2 Typically 0.2 s), a) s Braking the average deceleration (a) for the driver s The range of the value of (2) is 3.6m 2 /s~7.9m 2 /s),d 0 For the safe distance (d) of the target vehicle when stationary 0 Default to 3 m), t 3 Calculating a link delay (t 3 Default to 0.5 s).
When the target vehicle runs on the current lane, the distance between the safety distance coordinate and the collision point is the minimum safety distance, and the coordinate of the target vehicleThe distance between the safety distance coordinate and the safety distance coordinate is the expected deceleration distance S target According to the expected deceleration distance S target Speed V of target vehicle s And driver brake average deceleration a s Can pass through the formulaObtaining the expected deceleration speed V target Wherein V is s For the current speed of the target vehicle, a s Braking the average deceleration (a) for the driver s The range of the value of (2) is 3.6m 2 /s~7.9m 2 /s). The action time of the early-warning target reaching the collision point can be generated according to the current position coordinate of the early-warning target, the coordinate of the collision point, the current speed of the early-warning target, the average speed of the early-warning target and other data.
Optionally, the collision early-warning information at least includes the position of the early-warning target, the relative direction of the early-warning target and the target vehicle, the distance between the early-warning target and the target vehicle, which auxiliary vehicle blind area the early-warning target is located in, and the geometric range information of the corresponding auxiliary vehicle blind area.
Optionally, the first vehicle control information at least includes a position of the pre-warning target, a relative direction between the pre-warning target and the target vehicle, a distance between the pre-warning target and the target vehicle, a blind area of an auxiliary vehicle in which the pre-warning target is located, and geometric range information of the blind area of the corresponding auxiliary vehicle, a time to action TTC for the pre-warning target to reach the collision point, and an expected deceleration speed V target And an expected deceleration distance S target 。
In this embodiment, when the collision risk is high, the cloud platform automatically issues control information of the target vehicle, and makes the target vehicle execute speed-down, parking and other vehicle control instructions, so as to avoid a collision event caused by untimely response or braking of the driver when the target vehicle receives the collision risk.
After the target vehicle control information is sent to the target vehicle, and a target vehicle control instruction is generated according to the target vehicle control information, and the target vehicle is driven to execute the target vehicle control instruction, the method further comprises the steps of:
step S701: determining at least one surrounding vehicle located in a preset distance range of the target vehicle, and calculating position relation data of the surrounding vehicle and the target vehicle;
step S702: generating surrounding vehicle control information according to the position relation data and the target vehicle control information, sending the surrounding vehicle control information to the surrounding vehicle, generating a surrounding vehicle control instruction according to the surrounding vehicle control information, and driving the surrounding vehicle to execute the surrounding vehicle control instruction.
In step S701 and step S702, the preset distance range of the target vehicle is usually a distance range of vehicles behind the target vehicle and on the left and right sides, the preset distance range may be set by user according to the running condition of the road, when the road is crowded, the preset distance range may be smaller, and when the road is open, the preset distance range may be larger.
The positional relationship data between the nearby vehicle and the target vehicle generally includes a distance between the nearby vehicle and the target vehicle, and an orientation of the target vehicle at the nearby vehicle. There are typically a plurality of nearby vehicles within the predetermined range, so that the received nearby vehicle control information is not the same for each nearby vehicle. For example, when the target vehicle is located in the rightmost lane of the three-lane road, the surrounding vehicle a is located in the leftmost lane, the surrounding vehicle B is located in the rightmost lane, the auxiliary vehicle is located in the middle lane, the early warning target is a pedestrian and is traveling to the right, the surrounding vehicle a receives the surrounding vehicle control information without a parking instruction because the early warning target does not have a tendency to move to the left at this time, only needs to decelerate, and the surrounding vehicle B receives the surrounding vehicle control information with a parking instruction.
Optionally, the implementation realizes the low-delay information sharing of the vehicle-to-vehicle through the 5G network, and when the collision risk is about to occur, the control information of the surrounding vehicles is issued to the surrounding vehicles behind and nearby based on the 5G network, so that the information of sufficient auxiliary vehicle blind areas is provided for the vehicles behind. The surrounding vehicles can adopt the same control strategy as the target vehicles according to the received surrounding vehicle control information, so that the rear-end collision accident caused by untimely braking of the rear vehicles is avoided.
In summary, in the collision early warning method of the present embodiment, in the first aspect, the road side sensing devices on both sides of the road may acquire the road side sensing data of the blind area of the auxiliary vehicle in real time, and the target vehicle may acquire the global visual field information of the blind area of the auxiliary vehicle in the target detection area, so as to solve the problem of difficult acquisition of the blind area data. According to the second aspect, the early warning command center is provided with the cloud platform with big data computing capability, the computing capability of the early warning command center can be remarkably improved, the big data cloud platform has the characteristics of big computing power and big bandwidth, the problem that the dead zone collision risk calculation is low in vehicle end computing power and small in bandwidth can be solved by utilizing the big data platform, and the data with larger and farther vision can be acquired, so that the advantage of risk finding in advance is facilitated, and the vehicle is helped to avoid collision events in advance. In the third aspect, the cloud platform is used for controlling the vehicle, when the collision risk is high, the cloud platform automatically issues control information of the target vehicle, and the vehicle end is enabled to execute speed reduction, parking and other vehicle control instructions, so that collision events caused by untimely response or braking of a driver when the vehicle receives the collision risk are avoided. In a fourth aspect, the present implementation realizes low-delay vehicle-to-vehicle information sharing through a 5G network, and when a collision risk is about to occur, issues surrounding vehicle control information to surrounding vehicles behind and nearby based on the 5G network, provides sufficient blind area information for the rear vehicles, and the surrounding vehicles can simultaneously take the same control strategy as the target vehicle according to the received surrounding vehicle control information, so as to avoid rear-end collision accidents caused by untimely braking of the rear vehicles.
As shown in fig. 5, based on the same conception manner as the foregoing embodiment, the present invention further provides a collision early warning device based on road side sensing, including:
a target detection area construction module M10, configured to construct a target detection area corresponding to a target vehicle in an electronic map based on target vehicle action information of the target vehicle;
an auxiliary vehicle blind area creation module M20 configured to define at least one auxiliary vehicle within the target detection area, and determine an auxiliary vehicle blind area of the auxiliary vehicle with respect to the target vehicle for each of the auxiliary vehicles; the auxiliary vehicle blind area is a view range which is shielded by the auxiliary vehicle relative to the target vehicle;
a movement track calculation module M30, configured to collect, by using a road side sensing device corresponding to the auxiliary vehicle blind area, road side sensing data of the auxiliary vehicle blind area; when the road side perception data of the blind area comprises early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and calculating the early warning target action track of the early warning target based on the early warning target action information;
And the collision early-warning information generation module M40 is used for generating collision early-warning information corresponding to the early-warning target according to the target vehicle action track and the early-warning target action track.
In the collision early warning device based on road side perception, road side perception data of the blind area of the auxiliary vehicle can be obtained in real time through road side perception equipment on two sides of a road, the target vehicle can obtain global visual field information of the blind area of the auxiliary vehicle in the target detection area, the problem that the blind area data are difficult to obtain is solved, whether the target vehicle collides with the early warning target or not is effectively predicted based on action information of the target vehicle and the early warning target, collision early warning information is sent to remind the target vehicle before the collision is predicted, the driver of the target vehicle can conveniently and timely make parking or decelerating and other operations, and the occurrence of collision events is helped to be avoided by the target vehicle in advance.
The application also provides a collision early warning system, including: a processor and a memory; wherein the memory stores a computer program for loading and executing the collision pre-warning method as described above by the processor.
The present application also provides a computer readable storage medium storing instructions for loading and executing a collision warning method as described above by a processor.
Embodiments of the mobile terminal and the computer readable storage medium provided in the present application include all technical features of each embodiment of the control method, and the expansion and explanation contents of the description are substantially the same as those of each embodiment of the method, which are not repeated herein.
The present embodiments also provide a computer program product comprising computer program code which, when run on a computer, causes the computer to perform the method in the various possible implementations as above.
The embodiments also provide a chip including a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that a device on which the chip is mounted performs the method in the above possible embodiments.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In this application, the same or similar term concept, technical solution, and/or application scenario description will generally be described in detail only when first appearing, and when repeated later, for brevity, will not generally be repeated, and when understanding the content of the technical solution of the present application, etc., reference may be made to the previous related detailed description thereof for the same or similar term concept, technical solution, and/or application scenario description, etc., which are not described in detail later.
In this application, the descriptions of the embodiments are focused on, and the details or descriptions of one embodiment may be found in the related descriptions of other embodiments.
The technical features of the technical solutions of the present application may be arbitrarily combined, and for brevity of description, all possible combinations of the technical features in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the present application.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium as above, comprising several instructions for causing a terminal device to perform the method of each embodiment of the present application. The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the present invention. Accordingly, the scope of the invention should be assessed as that of the appended claims.
Claims (10)
1. The collision early warning method is characterized by comprising the following steps of:
constructing a target detection area corresponding to a target vehicle in an electronic map based on target vehicle action information of the target vehicle;
defining at least one auxiliary vehicle in the target detection area, and determining an auxiliary vehicle blind area of the auxiliary vehicle relative to the target vehicle for each auxiliary vehicle; the auxiliary vehicle blind area is a view range which is shielded by the auxiliary vehicle relative to the target vehicle;
collecting road side perception data of the auxiliary vehicle blind area through road side perception equipment corresponding to the auxiliary vehicle blind area; when the road side perception data of the blind area comprises early warning target action information of an early warning target of a preset type, calculating a target vehicle action track of the target vehicle based on the target vehicle action information, and calculating the early warning target action track of the early warning target based on the early warning target action information;
And generating collision early warning information corresponding to the early warning target according to the target vehicle action track and the early warning target action track.
2. The collision warning method according to claim 1, wherein the constructing a target detection area corresponding to the target vehicle in an electronic map based on target vehicle behavior information of the target vehicle specifically includes:
determining current position coordinates of the target vehicle based on the target vehicle action information, defining the current position coordinates of the target vehicle as first position coordinates, and determining a current lane corresponding to the target vehicle in the electronic map according to the first position coordinates;
determining a second position coordinate which is positioned on the current lane and has a preset first length from the first position coordinate, and determining an area covered by the current lane between the first position coordinate and the second position coordinate as a reference detection area;
in the electronic map, determining areas which are arranged on two opposite sides of the reference detection area and are not more than a preset first width away from the edge of the reference detection area as auxiliary detection areas;
The target vehicle detection area is generated based on the reference detection area and the auxiliary detection area.
3. The method according to claim 1, wherein the determining an auxiliary vehicle blind area of the auxiliary vehicle with respect to the target vehicle for each of the auxiliary vehicles specifically includes:
determining a blind area direction of the blind area of the auxiliary vehicle according to the target vehicle action information of the target vehicle and the auxiliary vehicle action information of the auxiliary vehicle;
determining current position coordinates of the auxiliary vehicle based on the auxiliary vehicle action information, defining the current position coordinates of the auxiliary vehicle as third position coordinates, and determining fourth position coordinates which are in the blind area direction and have a preset second length from the third position coordinates;
and establishing rectangular areas with the second length and the preset second width as side lengths between the third position coordinates and the fourth position coordinates along the blind area direction, and defining the rectangular areas as auxiliary vehicle blind areas.
4. The collision warning method according to claim 1, characterized in that when the road side awareness data of the blind area contains warning target action information of a warning target of a preset type, calculating a target vehicle action trajectory of the target vehicle based on the target vehicle action information, and before calculating the warning target action trajectory of the warning target based on the warning target action information, further comprising:
Determining the current position coordinate of the early warning target according to the early warning target action information, and defining the current position coordinate of the early warning target as a fifth position coordinate;
judging whether the early warning target is positioned in the target detection area or not based on the fifth position coordinate; if so, determining an auxiliary vehicle blind area where the early warning target is currently located according to the fifth position coordinate, and defining the auxiliary vehicle blind area where the early warning target is currently located as a target blind area;
acquiring the geometric range of the target blind area according to the road side perception data of the target blind area;
and writing the geometric range of the target blind area into collision early warning information.
5. The collision warning method according to claim 4, further comprising, after writing the geometric range of the target blind area in collision warning information:
judging whether the target vehicle is stationary or not based on the target vehicle action information; if yes, the collision early warning information is sent to the target vehicle; if not, judging whether the early warning target is static or not based on the early warning target action information; when the early warning target is stationary, the collision early warning information is sent to the target vehicle; and when the early warning target is not stationary, calculating the action track of the target vehicle and the action track of the early warning target.
6. The collision warning method according to claim 1, further comprising, before generating collision warning information corresponding to the warning target from the target vehicle action trajectory and the warning target action trajectory:
judging whether an intersection point exists between the action track of the target vehicle and the action track of the early warning target; if yes, defining the intersection point as a collision point, calculating a collision distance between the collision point and the target vehicle and a minimum safety distance between the target vehicle and the early warning target, and writing the collision distance and the minimum safety distance into target vehicle control information; if not, collision early warning information is sent to the target vehicle.
7. The collision warning method according to claim 6, further comprising, after calculating a collision distance between the collision point and the target vehicle and a minimum safe distance between the target vehicle and the warning target, and generating target vehicle control information based on the collision distance and the minimum safe distance:
generating a safe distance coordinate based on the minimum safe distance;
calculating an expected deceleration speed and an expected deceleration distance of the target vehicle reaching the safe distance coordinate, and writing the expected deceleration speed and the expected deceleration distance into the target vehicle control information;
Judging whether the collision distance is greater than the minimum safety distance; if yes, calculating the action time of the early warning target reaching a collision point, and writing the action time into the collision early warning information; if not, the target vehicle control information is sent to the target vehicle, a target vehicle control instruction is generated according to the target vehicle control information, and the target vehicle is driven to execute the target vehicle control instruction.
8. The collision warning method according to claim 7, further comprising, after transmitting the target vehicle control information to the target vehicle, generating a target vehicle control instruction from the target vehicle control information, and driving the target vehicle to execute the target vehicle control instruction:
determining at least one surrounding vehicle located in a preset distance range of the target vehicle, and calculating position relation data of the surrounding vehicle and the target vehicle;
generating surrounding vehicle control information according to the position relation data and the target vehicle control information, sending the surrounding vehicle control information to the surrounding vehicle, generating a surrounding vehicle control instruction according to the surrounding vehicle control information, and driving the surrounding vehicle to execute the surrounding vehicle control instruction.
9. A collision warning system, comprising: a processor and a memory; wherein the memory stores a computer program for loading and executing the collision warning method according to any one of claims 1 to 8 by the processor.
10. A computer readable storage medium storing instructions for loading and executing the collision warning method according to any one of claims 1 to 8 by a processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311413067.3A CN117576947A (en) | 2023-10-27 | 2023-10-27 | Collision early warning method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311413067.3A CN117576947A (en) | 2023-10-27 | 2023-10-27 | Collision early warning method, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117576947A true CN117576947A (en) | 2024-02-20 |
Family
ID=89892598
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311413067.3A Pending CN117576947A (en) | 2023-10-27 | 2023-10-27 | Collision early warning method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117576947A (en) |
-
2023
- 2023-10-27 CN CN202311413067.3A patent/CN117576947A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113320532B (en) | Cooperative lane change control method, device and equipment | |
CN113129622B (en) | Cooperative intersection traffic control method, device and equipment | |
US10800455B2 (en) | Vehicle turn signal detection | |
EP3086990B1 (en) | Method and system for driver assistance for a vehicle | |
US20180239361A1 (en) | Autonomous Driving At Intersections Based On Perception Data | |
CN108698594A (en) | The method and apparatus of automatic Pilot | |
CN114750783A (en) | Operating an automated vehicle according to road user reaction modeling under occlusion | |
EP4086875A1 (en) | Self-driving method and related device | |
CN110562222B (en) | Emergency braking control method for curve scene, vehicle-mounted device and storage medium | |
US20200020231A1 (en) | In-vehicle infotainment system communicating with unmanned aerial vehicle and method of operating the same | |
CN111788104B (en) | Known lane spacing for automated driving | |
JP7207256B2 (en) | vehicle control system | |
US11938965B2 (en) | Information service method for vehicle dispatch system, vehicle dispatch system, and information service device | |
JP2022504430A (en) | Vehicle control at multiple lane turns | |
US11753035B2 (en) | Vehicle control system | |
WO2024022003A1 (en) | Vehicle avoidance method and apparatus, terminal device and storage medium | |
US12030512B2 (en) | Collision warning system for a motor vehicle having an augmented reality head up display | |
CN117576947A (en) | Collision early warning method, system and storage medium | |
US20240085209A1 (en) | Display control device and display control method | |
CN115167367A (en) | Reversing collision avoidance system based on active safety and V2X technology | |
Takatori et al. | Stand-alone collision warning systems based on information from on-board sensors: Evaluating performance relative to system penetration rate | |
JP7291015B2 (en) | Surrounding object recognition method and surrounding object recognition device | |
Ioannou | Evaluation of mixed automated/manual traffic | |
CN114394090B (en) | Virtual front obstacle induction system of vehicle-road cooperation | |
KR102345965B1 (en) | Traffic dispersion system for self driving cars |
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 |