CN115311898A - Vehicle obstacle avoidance method and related equipment - Google Patents
Vehicle obstacle avoidance method and related equipment Download PDFInfo
- Publication number
- CN115311898A CN115311898A CN202210956687.0A CN202210956687A CN115311898A CN 115311898 A CN115311898 A CN 115311898A CN 202210956687 A CN202210956687 A CN 202210956687A CN 115311898 A CN115311898 A CN 115311898A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- current vehicle
- model
- information
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- 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]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
Abstract
The embodiment of the invention provides a vehicle obstacle avoidance method, which comprises the following steps: acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a current vehicle communication range; modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance model comprises a contour model of the current vehicle and a contour model of the target vehicle; and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model. The method comprises the steps of modeling in a preset projection space through current vehicle information and target vehicle information to obtain a vehicle obstacle avoidance model of a current vehicle and a target vehicle, controlling the current vehicle to avoid obstacles based on the vehicle obstacle avoidance model, and fully considering the information of the current vehicle and the target vehicle to enable a perception result to be more reliable, so that obstacle avoidance accuracy between the vehicles is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a vehicle obstacle avoidance method and related equipment.
Background
In an automatic driving scene, obstacle avoidance between vehicles needs to be considered, so that the position, the posture and the occupied space of nearby vehicles can be accurately acquired, and the obstacle avoidance processing between the vehicles is particularly important. According to the traditional method, nearby vehicles are sensed through sensors such as image recognition or microwave radars, so that obstacles are avoided according to sensing results, and the sensing results are relatively unilateral due to the fact that the sensing results only depend on the sensing results of the current vehicles, so that the problem that the sensing results are unreliable due to low accuracy exists.
Disclosure of Invention
The embodiment of the invention provides a vehicle obstacle avoidance method, and aims to solve the problems that in an automatic driving scene, the conventional obstacle avoidance technology only depends on the sensing result of a current vehicle, so that the sensing result is relatively unilateral, the accuracy of the sensing result is low, and the sensing result is unreliable. The method comprises the steps of modeling in a preset projection space through current vehicle information and target vehicle information to obtain a vehicle obstacle avoidance model of a current vehicle and a target vehicle, controlling the current vehicle to avoid an obstacle based on the vehicle obstacle avoidance model, and fully considering the information of the current vehicle and the target vehicle to enable a perception result to be more reliable, so that the obstacle avoidance accuracy between the vehicles is improved.
In a first aspect, an embodiment of the present invention provides a vehicle obstacle avoidance method, including the following steps:
acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a current vehicle communication range;
modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain vehicle obstacle avoidance models of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance models comprise a contour model of the current vehicle and a contour model of the target vehicle;
and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
Optionally, the step of obtaining the target vehicle information of the target vehicle within the current vehicle communication range includes:
when a target vehicle exists in the current vehicle communication range, establishing a short-range communication link between the current vehicle and the target vehicle;
and acquiring the target vehicle information through the short-range communication link.
Optionally, the step of obtaining the target vehicle information through the short-range communication link includes:
the model information of the target vehicle and the motion information of the target vehicle are obtained through the short-range communication link, the model information of the target vehicle is preset in the target vehicle, and the motion information of the target vehicle is obtained in real time by carrying a double-antenna or multi-antenna navigation system in the target vehicle.
Optionally, the current vehicle information includes model information of the current vehicle and motion information of the current vehicle, and the step of modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle includes:
matching the contour model of the current vehicle and the contour model of the target vehicle in a preset model library according to the model information of the current vehicle and the model information of the target vehicle, wherein the contour model in the model library is constructed according to different vehicle models, and the contour model and the vehicle of the corresponding model have the same contour;
and modeling in a preset projection space according to the contour model of the current vehicle, the motion information of the current vehicle, the contour model of the target vehicle and the motion information of the target vehicle to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
Optionally, the step of controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model includes:
calculating an early warning area corresponding to the contour model of the current vehicle according to the contour model of the current vehicle and the motion information of the current vehicle;
and if the contour model of the target vehicle appears in the early warning area, controlling the current vehicle to avoid the obstacle.
Optionally, the step of calculating the early warning region corresponding to the profile model of the current vehicle according to the profile model of the current vehicle and the motion information of the current vehicle includes:
calculating a contour curved surface of the contour model of the current vehicle in the direction facing the extension line according to the contour model of the current vehicle and the motion information of the current vehicle;
and determining the contour curved surface as an early warning area corresponding to the contour model of the current vehicle.
Optionally, the motion information of the current vehicle includes an orientation of the current vehicle, and the step of calculating, according to the profile model of the current vehicle and the motion information of the current vehicle, a profile curved surface of the profile model of the current vehicle in an extension line direction includes:
taking the geometric center of the contour model of the current vehicle as an origin, wherein the z-axis direction is vertical to the space ground of the projection space, the x-axis direction is the north direction, and the y-axis direction is the east direction, so as to obtain a space coordinate system;
in the space coordinate system, the projection of the contour model of the current vehicle on the zy axis is taken as a curve, the orientation of the contour model of the current vehicle is taken as a constraint, a contour curved surface of the contour model of the current vehicle in the direction of the extension line is obtained, and the orientation of the contour model of the current vehicle is determined by the orientation of the current vehicle.
In a second aspect, an embodiment of the present invention provides a vehicle obstacle avoidance apparatus, including:
the system comprises an acquisition module, a communication module and a display module, wherein the acquisition module is used for acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a communication range of the current vehicle;
the modeling module is used for modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, and the vehicle obstacle avoidance model comprises a profile model of the current vehicle and a profile model of the target vehicle;
and the control module is used for controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the invention further provides a vehicle obstacle avoidance method, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the vehicle obstacle avoidance method provided by the embodiment of the invention.
In a fourth aspect, the embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the vehicle obstacle avoidance method provided by the embodiment of the present invention are implemented.
In the embodiment of the invention, the current vehicle information of the current vehicle is acquired, and the target vehicle information of the target vehicle in the communication range of the current vehicle is acquired; modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance model comprises a contour model of the current vehicle and a contour model of the target vehicle; and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model. The method comprises the steps of modeling in a preset projection space through current vehicle information and target vehicle information to obtain a vehicle obstacle avoidance model of a current vehicle and a target vehicle, controlling the current vehicle to avoid an obstacle based on the vehicle obstacle avoidance model, and fully considering the information of the current vehicle and the target vehicle to enable a perception result to be more reliable, so that the obstacle avoidance accuracy between the vehicles is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a vehicle obstacle avoidance method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vehicle obstacle avoidance device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Specifically, referring to fig. 1, fig. 1 is a flowchart of a vehicle obstacle avoidance method according to an embodiment of the present invention, and as shown in fig. 1, the vehicle obstacle avoidance method includes:
101. the method includes acquiring current vehicle information of a current vehicle, and acquiring target vehicle information of a target vehicle within a current vehicle communication range.
In the embodiment of the present invention, the current vehicle and the target vehicle may be vehicles participating in an internet of vehicles, the current vehicle may be understood as a vehicle driven by a current user, and the target vehicle may be understood as all vehicles within a communication range of the current vehicle. The vehicle obstacle avoidance method in the embodiment of the invention is executed by a vehicle obstacle avoidance device in the current vehicle.
In the internet of vehicles, when a target vehicle appears in the communication range of the current vehicle, a communication link between the current vehicle and the target vehicle can be suggested, so that data can be exchanged between the current vehicle and the target vehicle, and the content of the exchanged data is vehicle information, namely the current vehicle sends the current vehicle information to the target vehicle, and the target vehicle also sends the target vehicle information to the current vehicle.
102. And modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
In an embodiment of the present invention, the vehicle obstacle avoidance model includes a contour model of a current vehicle and a contour model of a target vehicle.
Further, the current vehicle information may include contour model information of the current vehicle, the target vehicle information may include contour model information of the target vehicle, and the preset projection space may be a projection space in which a road surface on which the current vehicle is located is a space ground, that is, the space ground of the projection space is parallel to the road surface on which the current vehicle is located.
The contour model of the current vehicle can be constructed and obtained according to the contour model information of the current vehicle, and the contour model of the target vehicle can be constructed and obtained according to the contour model information of the target vehicle.
The current vehicle information can also comprise the motion information of the current vehicle, the target vehicle information can also comprise the motion information of the target vehicle, the motion condition of the contour model of the current vehicle in the projection space can be obtained according to the contour model of the current vehicle and the motion information of the current vehicle, the motion condition of the contour model of the target vehicle in the projection space can be obtained according to the contour model of the target vehicle and the motion information of the target vehicle, and therefore the vehicle obstacle avoidance model of the current vehicle and the target vehicle is obtained.
103. And controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
In the embodiment of the present invention, the vehicle obstacle avoidance model includes a contour model of the current vehicle and a contour model of the target vehicle, and specifically, the vehicle obstacle avoidance model includes a motion situation of the contour model of the current vehicle in the projection space and a motion situation of the contour model of the target vehicle in the projection space, and the current vehicle may be controlled to avoid an obstacle according to the motion situation of the contour model of the current vehicle in the projection space and the motion situation of the contour model of the target vehicle in the projection space, so as to avoid collision between the current vehicle and the target vehicle.
In the embodiment of the invention, the current vehicle information of a current vehicle is acquired, and the target vehicle information of a target vehicle in the communication range of the current vehicle is acquired; modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance model comprises a contour model of the current vehicle and a contour model of the target vehicle; and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model. The method comprises the steps of modeling in a preset projection space through current vehicle information and target vehicle information to obtain a vehicle obstacle avoidance model of a current vehicle and a target vehicle, controlling the current vehicle to avoid obstacles based on the vehicle obstacle avoidance model, and fully considering the information of the current vehicle and the target vehicle to enable a perception result to be more reliable, so that obstacle avoidance accuracy between the vehicles is improved.
Optionally, in the step of obtaining the target vehicle information of the target vehicle within the current vehicle communication range, when the target vehicle exists within the current vehicle communication range, a short-range communication link between the current vehicle and the target vehicle may be established; and acquiring the target vehicle information through the short-range communication link.
In the embodiment of the present invention, both the current vehicle and the target vehicle join the internet of vehicles, which may be based on DSR (dedicated Short Range Communications) or C-V2X (Cellular-V2X) Short Range communication protocol. The current vehicle communication range is the same as that of the DSRC or C-V2X short-range communication protocol.
The vehicle networking in the embodiment of the invention is preferably based on a DSRC short-range communication protocol to serve as the vehicle networking. The DSRC short range communication link may be implemented by a DSRC signal processing unit in the vehicle that has both the ability to broadcast DSRC signals to other vehicles and the ability to receive DSRC signals broadcast by other vehicles. When any vehicle appears in the communication range of the current vehicle, the vehicle can be determined as a target vehicle, a link is initiated to the target vehicle through the internet of vehicles, and a short-range communication link between the current vehicle and the target vehicle is established.
Vehicle information can be exchanged between the current vehicle and the target vehicle through a short-range communication link to acquire the vehicle information of the opposite side. Specifically, the current vehicle transmits current vehicle information to the target vehicle, and receives target vehicle information transmitted by the target vehicle.
The current vehicle obtains target vehicle information through the short-range communication link, need not current vehicle and passes through sensor to carry out perception and survey and drawing to target vehicle information, fully considers current vehicle and target vehicle's information for the perception result is more reliable, thereby improves keeping away the barrier degree of accuracy between the vehicle.
Optionally, in the step of obtaining the information of the target vehicle through the short-range communication link, the model information of the target vehicle and the motion information of the target vehicle may be obtained through the short-range communication link, the model information of the target vehicle is preset in the target vehicle, and the motion information of the target vehicle is obtained in real time by a dual-antenna or multi-antenna navigation system carried in the target vehicle.
In the embodiment of the invention, after a short-range communication link between the current vehicle and the target vehicle is established, the current vehicle can receive model information and motion information sent by the target vehicle, wherein the model information of the target vehicle can be prestored in the target vehicle, and when the vehicle information needs to be sent, the target vehicle sends the model information and the motion information of the target vehicle to the current vehicle. Of course, the current vehicle also sends the model information and the motion information of the current vehicle to the target vehicle, so that the target vehicle implements the vehicle obstacle avoidance method of the embodiment of the invention.
The motion information may include information such as a vehicle position, a vehicle orientation, and a vehicle motion state, and the motion information may be acquired by a high-precision navigation system, which may be a dual-antenna or multi-antenna navigation system. Furthermore, the high-precision navigation system can combine double antennas or multiple antennas, a satellite navigation technology, an RTK positioning technology and an inertial navigation technology, can reach centimeter-level positioning precision, and can acquire information such as vehicle position, vehicle orientation, vehicle motion state and the like.
Centimeter-level vehicle positions acquired in real time through the dual-antenna or multi-antenna navigation system can acquire vehicle orientation and vehicle motion states according to the dual-antenna or multi-antenna positions, and therefore accuracy of vehicle information is improved.
Optionally, in the step of modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, a profile model of the current vehicle and a profile model of the target vehicle may be matched in a preset model library according to the model information of the current vehicle and the model information of the target vehicle, where the profile models in the model library are constructed according to various different vehicle models, and the profile models have the same profile as vehicles of corresponding models; and modeling in a preset projection space according to the profile model of the current vehicle, the motion information of the current vehicle, the profile model of the target vehicle and the motion information of the target vehicle to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
In the embodiment of the invention, the model information can comprise brand information and model information, and for vehicles of different brands and models, the contour modeling can be performed in advance, wherein the contour modeling can be scanning modeling or manual modeling so as to obtain a contour model of the vehicle, and the contour model corresponds to the vehicle of the same brand and the same model.
The contour model includes each part of the vehicle such as a rear view mirror, a vehicle bumper, and a posture of a wheel when turning.
The contour model can be a three-dimensional model or a two-dimensional model, and after the contour model of each brand and model of vehicle is obtained, the contour model of each brand and model of vehicle can be stored in a model library.
Correspondingly, the projection space may be a three-dimensional space or a two-dimensional space, and when the contour model is a three-dimensional model, the projection space is a three-dimensional space, and when the contour model is a two-dimensional model, the projection space is a two-dimensional space.
The corresponding contour model can be matched in the model base according to the model information of the target vehicle, and the matched contour model is modeled according to the motion information of the target vehicle, so that the position, the orientation and the motion state of the contour model of the target vehicle in the projection space are obtained. Similarly, according to the model information of the current vehicle, matching a corresponding outline model in the model base, and modeling the matched outline model according to the motion information of the current vehicle to obtain the position, the orientation and the motion state of the outline model of the current vehicle in the projection space, so as to obtain the vehicle obstacle avoidance model of the current vehicle and the target vehicle.
Different vehicle model information corresponds different profile models, can be accurate describe the vehicle profile, in keeping away the barrier process, can utilize the profile model to judge whether there is the risk that the vehicle collided.
Optionally, in the step of controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model, the early warning area corresponding to the profile model of the current vehicle may be calculated according to the profile model of the current vehicle and the motion information of the current vehicle; and if the contour model of the target vehicle appears in the early warning area, controlling the current vehicle to avoid the obstacle.
In the embodiment of the present invention, in the projection space, the motion information of the current vehicle may be converted onto the contour model of the current vehicle, so that the contour model of the current vehicle has corresponding motion information, for example, the orientation of the current vehicle may be converted into the orientation of the contour model of the current vehicle, and the early warning area corresponding to the contour model of the current vehicle is determined according to the orientation of the contour model of the current vehicle.
For example, an extended line area of the orientation of the profile model of the current vehicle may be used as an early warning area, and when the profile model of the target vehicle appears in the early warning area, it indicates that the current vehicle and the target vehicle are at risk of colliding.
When the current vehicle and the target vehicle have the risk of collision, the current vehicle can be controlled under the safety condition, so that the direction or the speed of the current vehicle is changed, and the target vehicle is separated from the early warning area of the current vehicle.
In a possible embodiment, when the direction or the speed of the current vehicle is controlled to change under the safe condition and the target vehicle cannot be separated from the early warning area of the current vehicle, the target vehicle is informed to control, so that the target vehicle controls the direction and the speed of the target vehicle, and obstacle avoidance is completed.
Optionally, in the step of calculating the early warning area corresponding to the current vehicle profile model according to the current vehicle profile model and the current vehicle motion information, a profile curved surface of the current vehicle profile model in the direction toward the extension line may be calculated according to the current vehicle profile model and the current vehicle motion information; and determining the contour curved surface as an early warning area corresponding to the contour model of the current vehicle.
In an embodiment of the present invention, the projection space is a three-dimensional space, the contour model is a three-dimensional model, in the three-dimensional space, the motion information of the current vehicle may be converted onto the contour model of the current vehicle, so that the contour model of the current vehicle has corresponding motion information, for example, the orientation of the current vehicle may be converted into the orientation of the contour model of the current vehicle, and the contour curved surface of the contour model of the current vehicle in the direction of the extension line is determined according to the orientation of the contour model of the current vehicle.
For example, the contour curved surface of the contour model of the current vehicle facing the extension line direction may be used as the early warning area, and when the contour model of the target vehicle appears in the contour curved surface, it indicates that the current vehicle and the target vehicle are at risk of colliding with each other.
Taking the current vehicle to avoid the obstacle to the right as an example, when the target vehicle is detected to appear on the left side contour curve on the extension line of the current vehicle body. And steering the current vehicle body to the right side until the outer contour of the target vehicle and the left side contour curved surface on the left side vehicle body extension line of the current vehicle do not have an intersection point, and stopping steering. And (4) straight running is carried out until the left rear side wheel of the current vehicle exceeds the right side vehicle body of the target vehicle, no intersection point exists on the left rear contour curved surface of the vehicle body of the current vehicle towards the extension line direction, and the straight running is stopped. And steering the current vehicle to the left side until the direction of the body orientation of the current vehicle is parallel to the direction of the body orientation of the target vehicle, and stopping steering. And (6) obstacle avoidance is completed.
Optionally, the motion information of the current vehicle includes a direction of the current vehicle, and in the step of calculating the contour curved surface of the contour model of the current vehicle in the direction of the extension line according to the contour model of the current vehicle and the motion information of the current vehicle, a spatial ground of a space is vertically projected in the z-axis direction with a geometric center of the contour model of the current vehicle as an origin, the x-axis direction is the north direction, and the y-axis direction is the east direction, so as to obtain a spatial coordinate system; in a space coordinate system, the projection of the contour model of the current vehicle on the zy axis is taken as a curve, the orientation of the contour model of the current vehicle is taken as a constraint, a contour curved surface of the contour model of the current vehicle in the direction of the extension line is obtained, and the orientation of the contour model of the current vehicle is determined according to the orientation of the current vehicle.
In the embodiment of the present invention, the projection space is a three-dimensional space, and the geometric center of the three-dimensional model corresponding to the current vehicle is used as an origin (0,0), the z-axis direction is vertically upward, the x-axis direction is the north direction, and the y-axis direction is the east direction. The contour curved surface of the three-dimensional model corresponding to the current vehicle, which faces the extension line direction, can be calculated by the following method: the projection of the three-dimensional model corresponding to the current vehicle on the zy axis can be represented as a curve 0=F (z, y), the orientation of the three-dimensional model corresponding to the current vehicle can be represented as a straight line on the xy axis, and can be specifically represented as a constraint form x = ay, and a curved surface equation in a three-dimensional space can be obtained by combining 0=F (z, y) and the constraint x = ay. For the three-dimensional model corresponding to the target vehicle, the projection of the zy axis can be represented as a curve 0=H (z, y), the projection of the zx axis can be represented as 0=G (z, x), the orientation of the three-dimensional model corresponding to the target vehicle relative to the three-dimensional model corresponding to the current vehicle can be represented as a constraint form a = by, and the equations of a section of curve in a three-dimensional space can be obtained by combining 0=H (z, y), 0=G (z, x) and the constraint a = by. Taking the rightward avoidance of the current vehicle as an example, substituting x and z coordinates of points on a curve into a curved surface equation, if the obtained y is greater than 0, indicating that the avoidance is not successful, and needing to steer; if y is less than 0, it indicates successful avoidance.
The method comprises the steps of modeling in a preset projection space through current vehicle information and target vehicle information to obtain a vehicle obstacle avoidance model of a current vehicle and a target vehicle, controlling the current vehicle to avoid obstacles based on the vehicle obstacle avoidance model, and fully considering the information of the current vehicle and the target vehicle to enable a perception result to be more reliable, so that obstacle avoidance accuracy between the vehicles is improved.
It should be noted that the vehicle obstacle avoidance method provided by the embodiment of the present invention may be applied to smart phones, navigation devices, vehicle-mounted devices, computers, servers, and other devices.
Optionally, referring to fig. 2, fig. 2 is a schematic structural diagram of a vehicle obstacle avoidance device according to an embodiment of the present invention, and as shown in fig. 2, the device includes:
the system comprises an acquisition module 201, a communication module and a processing module, wherein the acquisition module is used for acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a communication range of the current vehicle;
the modeling module 202 is configured to perform modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, where the vehicle obstacle avoidance model includes a profile model of the current vehicle and a profile model of the target vehicle;
and the control module 203 is configured to control the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
Optionally, the obtaining module 201 includes:
the establishing submodule is used for establishing a short-range communication link between the current vehicle and a target vehicle when the target vehicle exists in the communication range of the current vehicle;
and the acquisition submodule is used for acquiring the target vehicle information through the short-range communication link.
Optionally, the obtaining sub-module includes:
the acquisition unit is used for acquiring the model information of the target vehicle and the motion information of the target vehicle through the short-range communication link, the model information of the target vehicle is preset in the target vehicle, and the motion information of the target vehicle is acquired in real time by carrying a dual-antenna or multi-antenna navigation system in the target vehicle.
Optionally, the current vehicle information includes model information of the current vehicle and motion information of the current vehicle, and the modeling module 202 includes:
the matching submodule is used for matching the contour model of the current vehicle and the contour model of the target vehicle in a preset model library according to the model information of the current vehicle and the model information of the target vehicle, wherein the contour model in the model library is constructed according to different vehicle models, and the contour model and the vehicle with the corresponding model have the same contour;
and the modeling submodule is used for modeling in a preset projection space according to the profile model of the current vehicle, the motion information of the current vehicle, the profile model of the target vehicle and the motion information of the target vehicle to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
Optionally, the control module 203 includes:
the calculation submodule is used for calculating an early warning area corresponding to the contour model of the current vehicle according to the contour model of the current vehicle and the motion information of the current vehicle;
and the control submodule is used for controlling the current vehicle to avoid the obstacle if the contour model of the target vehicle appears in the early warning area.
Optionally, the calculation sub-module includes:
the calculating unit is used for calculating a contour curved surface of the contour model of the current vehicle in the direction facing the extension line according to the contour model of the current vehicle and the motion information of the current vehicle;
and the determining unit is used for determining the contour curved surface as an early warning area corresponding to the contour model of the current vehicle.
Optionally, the motion information of the current vehicle includes an orientation of the current vehicle, and the calculation unit includes:
the first projection subunit is used for obtaining a space coordinate system by taking the geometric center of the current vehicle contour model as an origin, the z-axis direction is vertical to the space ground of the projection space, the x-axis direction is the north direction, and the y-axis direction is the east direction;
and the second projection subunit is used for obtaining a contour curved surface of the contour model of the current vehicle in the direction of the extension line by taking the projection of the contour model of the current vehicle on the zy axis as a curve and the direction of the contour model of the current vehicle as a constraint in the space coordinate system, and the direction of the contour model of the current vehicle is determined by the direction of the current vehicle.
It should be noted that the vehicle obstacle avoidance device provided by the embodiment of the present invention may be applied to a smart phone, a navigation device, a vehicle system device, a computer, a server, and other devices that can perform navigation and positioning.
The vehicle obstacle avoidance device provided by the embodiment of the invention can realize each process realized by the vehicle obstacle avoidance method in the method embodiment, and can achieve the same beneficial effects. To avoid repetition, further description is omitted here.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, including: memory 302, processor 301 and a computer program for a vehicle obstacle avoidance method stored on the memory 302 and operable on the processor 301, wherein:
the processor 301 is configured to call the computer program stored in the memory 302, and execute the following steps:
acquiring current vehicle information of a current vehicle and target vehicle information of a target vehicle in a current vehicle communication range;
modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance model comprises a contour model of the current vehicle and a contour model of the target vehicle;
and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
Optionally, the step of acquiring the target vehicle information of the target vehicle in the current vehicle communication range executed by the processor 301 includes:
when a target vehicle exists in the current vehicle communication range, establishing a short-range communication link between the current vehicle and the target vehicle;
and acquiring the target vehicle information through the short-range communication link.
Optionally, the step of acquiring the target vehicle information through the short-range communication link, which is performed by the processor 301, includes:
the model information of the target vehicle and the motion information of the target vehicle are obtained through the short-range communication link, the model information of the target vehicle is preset in the target vehicle, and the motion information of the target vehicle is obtained in real time by carrying a double-antenna or multi-antenna navigation system in the target vehicle.
Optionally, the current vehicle information includes model information of the current vehicle and motion information of the current vehicle, and the step of modeling in a preset projection space according to the current vehicle information and the target vehicle information by the processor 301 to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle includes:
matching the contour model of the current vehicle and the contour model of the target vehicle in a preset model library according to the model information of the current vehicle and the model information of the target vehicle, wherein the contour model in the model library is constructed according to different vehicle models, and the contour model and the vehicle of the corresponding model have the same contour;
and modeling in a preset projection space according to the profile model of the current vehicle, the motion information of the current vehicle, the profile model of the target vehicle and the motion information of the target vehicle to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
Optionally, the step, executed by the processor 301, of controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model includes:
calculating an early warning area corresponding to the contour model of the current vehicle according to the contour model of the current vehicle and the motion information of the current vehicle;
and if the contour model of the target vehicle appears in the early warning area, controlling the current vehicle to avoid the obstacle.
Optionally, the step, executed by the processor 301, of calculating the early warning area corresponding to the profile model of the current vehicle according to the profile model of the current vehicle and the motion information of the current vehicle includes:
calculating a contour curved surface of the contour model of the current vehicle in the direction facing the extension line according to the contour model of the current vehicle and the motion information of the current vehicle;
and determining the contour curved surface as an early warning area corresponding to the contour model of the current vehicle.
Optionally, the motion information of the current vehicle includes an orientation of the current vehicle, and the step of calculating, by the processor 301, a contour curved surface of the contour model of the current vehicle in an extension line direction according to the contour model of the current vehicle and the motion information of the current vehicle includes:
taking the geometric center of the contour model of the current vehicle as an origin, wherein the z-axis direction is vertical to the space ground of the projection space, the x-axis direction is the north direction, and the y-axis direction is the east direction, so as to obtain a space coordinate system;
in the space coordinate system, the projection of the contour model of the current vehicle on the zy axis is taken as a curve, the orientation of the contour model of the current vehicle is taken as a constraint, a contour curved surface of the contour model of the current vehicle in the direction of the extension line is obtained, and the orientation of the contour model of the current vehicle is determined by the orientation of the current vehicle.
It should be noted that the electronic device provided in the embodiment of the present invention may be applied to a smart phone, a navigation device, a computer, a server, and other devices that can perform vehicle obstacle avoidance.
The electronic equipment provided by the embodiment of the invention can realize each process realized by the vehicle obstacle avoidance method in the method embodiment, and can achieve the same beneficial effect. To avoid repetition, further description is omitted here.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program realizes each process of the vehicle obstacle avoidance method or the application-side vehicle obstacle avoidance method provided by the embodiment of the invention, can achieve the same technical effect, and is not repeated here to avoid repetition.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. A vehicle obstacle avoidance method is characterized by comprising the following steps:
acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a current vehicle communication range;
modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, wherein the vehicle obstacle avoidance model comprises a contour model of the current vehicle and a contour model of the target vehicle;
and controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
2. The method of claim 1, wherein the step of acquiring target vehicle information of a target vehicle within the current vehicle communication range comprises:
when a target vehicle exists in the communication range of the current vehicle, establishing a short-range communication link between the current vehicle and the target vehicle;
and acquiring the target vehicle information through the short-range communication link.
3. The method of claim 2, wherein the step of obtaining the target vehicle information over the short-range communication link comprises:
the model information of the target vehicle and the motion information of the target vehicle are obtained through the short-range communication link, the model information of the target vehicle is preset in the target vehicle, and the motion information of the target vehicle is obtained in real time by carrying a double-antenna or multi-antenna navigation system in the target vehicle.
4. The method of claim 3, wherein the current vehicle information includes model information of the current vehicle and motion information of the current vehicle, and the step of modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle comprises:
matching the contour model of the current vehicle and the contour model of the target vehicle in a preset model library according to the model information of the current vehicle and the model information of the target vehicle, wherein the contour model in the model library is constructed according to various different vehicle models, and the contour model and the vehicle of the corresponding model have the same contour;
and modeling in a preset projection space according to the contour model of the current vehicle, the motion information of the current vehicle, the contour model of the target vehicle and the motion information of the target vehicle to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle.
5. The method of claim 4, wherein the step of controlling the current vehicle to avoid an obstacle based on the vehicle obstacle avoidance model comprises:
calculating an early warning area corresponding to the contour model of the current vehicle according to the contour model of the current vehicle and the motion information of the current vehicle;
and if the contour model of the target vehicle appears in the early warning area, controlling the current vehicle to avoid the obstacle.
6. The method of claim 5, wherein the step of calculating the early warning region corresponding to the contour model of the current vehicle according to the contour model of the current vehicle and the motion information of the current vehicle comprises:
calculating a contour curved surface of the contour model of the current vehicle in the direction facing the extension line according to the contour model of the current vehicle and the motion information of the current vehicle;
and determining the contour curved surface as an early warning area corresponding to the contour model of the current vehicle.
7. The method according to claim 6, wherein the motion information of the current vehicle includes an orientation of the current vehicle, and the step of calculating the contour curved surface of the contour model of the current vehicle in the direction of the extension line from the contour model of the current vehicle and the motion information of the current vehicle includes:
taking the geometric center of the contour model of the current vehicle as an origin, wherein the z-axis direction is vertical to the space ground of the projection space, the x-axis direction is the north direction, and the y-axis direction is the east direction, so as to obtain a space coordinate system;
in the space coordinate system, the projection of the current vehicle contour model on the zy axis is taken as a curve, the direction of the current vehicle contour model is taken as a constraint, a contour curved surface of the current vehicle contour model in the direction of the extension line is obtained, and the direction of the current vehicle contour model is determined by the direction of the current vehicle.
8. A vehicle obstacle avoidance device, comprising:
the system comprises an acquisition module, a communication module and a display module, wherein the acquisition module is used for acquiring current vehicle information of a current vehicle and acquiring target vehicle information of a target vehicle in a communication range of the current vehicle;
the modeling module is used for modeling in a preset projection space according to the current vehicle information and the target vehicle information to obtain a vehicle obstacle avoidance model of the current vehicle and the target vehicle, and the vehicle obstacle avoidance model comprises a profile model of the current vehicle and a profile model of the target vehicle;
and the control module is used for controlling the current vehicle to avoid the obstacle based on the vehicle obstacle avoidance model.
9. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the vehicle obstacle avoidance method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the vehicle obstacle avoidance method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210956687.0A CN115311898A (en) | 2022-08-10 | 2022-08-10 | Vehicle obstacle avoidance method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210956687.0A CN115311898A (en) | 2022-08-10 | 2022-08-10 | Vehicle obstacle avoidance method and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115311898A true CN115311898A (en) | 2022-11-08 |
Family
ID=83861490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210956687.0A Pending CN115311898A (en) | 2022-08-10 | 2022-08-10 | Vehicle obstacle avoidance method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115311898A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355948A (en) * | 2015-07-17 | 2017-01-25 | 本田技研工业株式会社 | Turn predictions |
| CN108062600A (en) * | 2017-12-18 | 2018-05-22 | 北京星云互联科技有限公司 | A kind of vehicle collision prewarning method and device based on rectangle modeling |
| CN108447308A (en) * | 2018-05-17 | 2018-08-24 | 中交信息技术国家工程实验室有限公司 | A kind of intersection vehicles risk of collision prediction technique and system based on bus or train route collaboration |
| CN111882665A (en) * | 2020-09-28 | 2020-11-03 | 蘑菇车联信息科技有限公司 | Vehicle driving assistance system and method |
| CN114495574A (en) * | 2021-12-16 | 2022-05-13 | 联通智网科技股份有限公司 | Collision early warning method and device |
| CN114852069A (en) * | 2022-05-24 | 2022-08-05 | 岚图汽车科技有限公司 | Vehicle, and method and device for controlling vehicle to run |
-
2022
- 2022-08-10 CN CN202210956687.0A patent/CN115311898A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355948A (en) * | 2015-07-17 | 2017-01-25 | 本田技研工业株式会社 | Turn predictions |
| CN108062600A (en) * | 2017-12-18 | 2018-05-22 | 北京星云互联科技有限公司 | A kind of vehicle collision prewarning method and device based on rectangle modeling |
| CN108447308A (en) * | 2018-05-17 | 2018-08-24 | 中交信息技术国家工程实验室有限公司 | A kind of intersection vehicles risk of collision prediction technique and system based on bus or train route collaboration |
| CN111882665A (en) * | 2020-09-28 | 2020-11-03 | 蘑菇车联信息科技有限公司 | Vehicle driving assistance system and method |
| CN114495574A (en) * | 2021-12-16 | 2022-05-13 | 联通智网科技股份有限公司 | Collision early warning method and device |
| CN114852069A (en) * | 2022-05-24 | 2022-08-05 | 岚图汽车科技有限公司 | Vehicle, and method and device for controlling vehicle to run |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7124117B2 (en) | Trailer detection and autonomous hitching | |
| JP7021372B2 (en) | Detection of couplers and traction bars through group points for automated trailer hitting | |
| EP3091338B1 (en) | Misrecognition determination device | |
| US9121717B1 (en) | Collision avoidance for vehicle control | |
| US9096233B2 (en) | Visual confirmation evaluating apparatus and method | |
| US20180137376A1 (en) | State estimating method and apparatus | |
| JP2022501032A (en) | Autonomous farm equipment connected to the tractor | |
| US11287879B2 (en) | Display control device, display control method, and program for display based on travel conditions | |
| US10733889B2 (en) | Method and device for parking assistance | |
| US10023227B2 (en) | Steering assistance control apparatus | |
| Monaco et al. | Radarodo: Ego-motion estimation from doppler and spatial data in radar images | |
| KR20200010393A (en) | Parking Control Method And Parking Control Device | |
| US10740592B2 (en) | Three-dimensional object ground-contact determining apparatus | |
| US11623641B2 (en) | Following target identification system and following target identification method | |
| US20220229168A1 (en) | Axial deviation estimating device | |
| JP2017102861A (en) | Article recognition apparatus | |
| JP2004120661A (en) | Moving object periphery monitoring apparatus | |
| CN110555801A (en) | Correction method, terminal and storage medium for track deduction | |
| US11607999B2 (en) | Method and apparatus for invisible vehicle underbody view | |
| CN112215214A (en) | Method and system for adjusting camera offset of intelligent vehicle-mounted terminal | |
| CN115311898A (en) | Vehicle obstacle avoidance method and related equipment | |
| JP7056379B2 (en) | Vehicle driving control device | |
| WO2020230314A1 (en) | Self-positioning correction method and self-positioning correction device | |
| US10249056B2 (en) | Vehicle position estimation system | |
| US20220171063A1 (en) | Target detection apparatus and vehicle having the same mounted thereon |
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 |