CN115237121A - Scene reconstruction-based remote calling method and system and readable storage medium - Google Patents
Scene reconstruction-based remote calling method and system and readable storage medium Download PDFInfo
- Publication number
- CN115237121A CN115237121A CN202210706143.9A CN202210706143A CN115237121A CN 115237121 A CN115237121 A CN 115237121A CN 202210706143 A CN202210706143 A CN 202210706143A CN 115237121 A CN115237121 A CN 115237121A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- path
- information
- target vehicle
- planning
- 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 48
- 230000008447 perception Effects 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 11
- 230000007246 mechanism Effects 0.000 claims abstract description 7
- 230000004888 barrier function Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007726 management method Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention particularly relates to a scene reconstruction-based remote calling method, a scene reconstruction-based remote calling system and a readable storage medium. The method comprises the following steps: acquiring a corresponding calling end position and vehicle-mounted sensing information; carrying out scene reconstruction to generate a road topological structure; establishing a global coordinate system by taking the starting point of the target vehicle as the origin of coordinates, and calculating the real-time pose of the target vehicle under the global coordinate system; carrying out coordinate conversion and generating a grid map to obtain a corresponding planning space; performing path search planning based on the planning space and the calling terminal position to generate a local planning path; performing path following control based on the local planned path to generate vehicle control information; and controlling the whole vehicle actuating mechanism of the target vehicle to act to realize the automatic driving of the target vehicle. The invention also discloses a remote calling system and a readable storage medium. The method and the system can realize scene reconstruction based on vehicle-mounted perception information, and further can realize automatic driving and remote calling of complex scenes without depending on high-precision maps and positioning.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a remote calling method and system based on scene reconstruction and a readable storage medium.
Background
An AV (Automated Vehicle) is a motor Vehicle that automatically performs a driving task without human operation by the cooperation of machine vision, radar, a supervisory system, a global positioning system, and artificial intelligence. Currently, autonomous vehicle descriptions are typically classified into 6 levels, i.e., L0-L5, to clarify the differences between different levels of autonomous driving technology. Among them, remote summoning technology of autonomous vehicles is one of the most common functions, for example, remote summoning of vehicles in a parking lot.
For the problem of remote calling of the automatic driving vehicle, a Chinese patent with a publication number of CN111098863A discloses a remote driving request method, a device and a user terminal of the automatic driving vehicle, and the method comprises the following steps: sending a remote driving request to a remote control center; receiving an autonomous vehicle list and a remote operator list fed back by a remote control center in response to a remote driving request; determining a target autonomous vehicle from a list of autonomous vehicles and a target remote operator from a list of remote operators in response to a user selection and generating driving confirmation information based on the determination; and transmitting the driving confirmation information to a remote control center so that the target remote operator can carry out remote driving and/or remote supervision. In this prior art solution, the remote operator can intervene in the driving or supervision of the autonomous vehicle.
The applicant finds that the existing automatic driving technology has strong dependence on a high-precision map and high-precision positioning, a global path generated by the high-precision map can be used as a reference line for planning a local path of an automatic driving vehicle, and the high-precision positioning can provide the current pose of the vehicle. However, in practical application scenarios, most parking lots and roads do not have high-precision maps at present, and high-precision positioning cannot be provided, so that the effectiveness of remote calling of existing automatic driving vehicles is poor. Meanwhile, the existing scheme which does not depend on Lai Gao precision maps and positioning generally only depends on information formed by sensing environments to search a path, and direction guidance is not performed to realize path search of a whole area, so that the generated path easily falls into local optimal solution, a vehicle falls into trouble and fails in summoning, and further the accuracy of remote summoning of an automatic driving vehicle is poor. Therefore, how to design a method capable of improving the effectiveness and accuracy of remote calling of an automatic driving vehicle is an urgent technical problem to be solved.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to provide a remote calling method based on scene reconstruction to realize scene reconstruction based on vehicle-mounted perception information, and further realize automatic driving and remote calling of complex scenes under the condition of not depending on high-precision maps and positioning, so that the effectiveness and accuracy of remote calling of automatic driving vehicles can be improved.
In order to solve the technical problems, the invention adopts the following technical scheme:
the remote calling method based on scene reconstruction comprises the following steps:
s1: receiving a remote calling signal of a target vehicle, and acquiring a corresponding calling end point position and vehicle-mounted sensing information;
s2: reconstructing a scene based on vehicle-mounted perception information to generate a road topological structure; then, establishing a global coordinate system by taking the starting point of the target vehicle as the origin of coordinates, and further calculating the real-time pose of the target vehicle under the global coordinate system; finally, according to the road topological structure, coordinate conversion is carried out and a grid map is generated by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle, so that a corresponding planning space is obtained;
s3: performing path search planning based on the planning space and the calling terminal position to generate a local planning path;
s4: performing path following control based on the local planned path to generate vehicle control information;
s5: controlling the whole vehicle executing mechanism of the target vehicle to act based on the vehicle control information to realize the automatic driving of the target vehicle;
s6: and repeating the steps S4 to S5 until the target vehicle reaches the call end position.
Preferably, in the step S1, a vehicle-mounted navigation path, a vehicle memory path and a cloud memory path of the target vehicle are further obtained;
in the step S2, based on the vehicle-mounted perception information, scene reconstruction is carried out by combining a vehicle-mounted navigation path of the target vehicle, a vehicle memory path and a cloud memory path, and a road topological structure is generated.
Preferably, in step S2, the real-time pose of the target vehicle in the global coordinate system is calculated according to a vehicle kinematics algorithm, and then the real-time pose of the target vehicle is corrected through the vehicle-mounted sensing information.
Preferably, in step S2, the cost value generation in the planning space grid map depends on the road topology, the obstacle information and the distance to the call end position.
Preferably, in step S3, when performing route search planning based on the planning space and the call end position, the raster map cost value, the minimum turning radius constraint, the gear shift and the angle request change of the target vehicle are comprehensively considered to generate the corresponding local planned route.
Preferably, in step S3, the generated local planned path is subjected to a smoothing optimization process.
Preferably, in step S4, the path following control includes a lateral control and a longitudinal control; the vehicle control information includes angle request information, torque request information, deceleration request information, and gear request information.
Preferably, the step S5 specifically includes the following steps:
s501: detecting whether a collision risk exists between the target vehicle and the obstacle, if so, returning to the step S3; otherwise, executing the next step;
s502: judging whether the following error of the target vehicle is larger than a calibrated value or not, if so, returning to the step S3; otherwise, executing the next step;
s503: judging whether the current gear request of the target vehicle is changed or not, if so, returning to the step S3; otherwise, the process proceeds to step S6.
The invention also discloses a remote calling system based on the limited path guide information, and the implementation of the remote calling method based on the invention specifically comprises the following steps:
the information acquisition module is used for acquiring a corresponding calling end position and vehicle-mounted sensing information when receiving a remote calling signal of a target vehicle;
the scene reconstruction module is used for reconstructing a scene based on the vehicle-mounted perception information to generate a road topological structure;
the pose calculation module is used for establishing a global coordinate system by taking the starting point of the target vehicle as a coordinate origin, and further calculating the real-time pose of the target vehicle under the global coordinate system;
the planning space module is used for carrying out coordinate conversion and generating a grid map by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle according to the road topological structure to obtain a corresponding planning space;
the route planning module is used for searching and planning a route based on the planning space and the calling terminal position to generate a local planning route;
the path tracking control module is used for carrying out path following control based on the local planned path and generating vehicle control information;
and the whole vehicle executing mechanism is used for controlling the action of the target vehicle based on the vehicle control information so as to realize automatic driving.
The invention also discloses a readable storage medium, on which a computer management program is stored, wherein the computer management program realizes the steps of the scene reconstruction-based remote calling method when being executed by the processor.
The remote calling method based on scene reconstruction has the following beneficial effects:
the method comprises the steps of reconstructing a scene based on vehicle-mounted sensing information to generate a road topological structure, performing coordinate conversion and generating a grid map by combining barrier information and the real-time pose of a target vehicle to obtain a planning space, performing path search planning based on the planning space and a calling terminal position to generate a local planning path, and performing path following control to generate vehicle control information so as to realize automatic driving of the target vehicle. On one hand, scene reconstruction is realized based on vehicle-mounted sensing information, and then a planning space is generated to realize path search planning, so that automatic driving and remote calling of complex scenes can be realized without depending on high-precision maps and positioning, and the remote calling effectiveness of automatic driving vehicles can be improved. On the other hand, the planning space is obtained by combining the road topological structure with the barrier information and the real-time pose of the target vehicle to perform coordinate transformation and generate a grid map, so that when the path search planning is performed based on the planning space and the calling end position, the path search planning can be performed based on the reconstructed scene environment, and the direction guidance can be performed based on the grid map and the global coordinate system of the planning space and the calling end position, so that the path search planning in the whole area can be realized to obtain the globally optimal local planning path, and the accuracy of remote calling of the automatic driving vehicle can be improved.
Meanwhile, scene reconstruction is carried out on the road topological structure by introducing the vehicle or cloud memory path, the road identification and other information and the global path information of the vehicle navigation path, so that a more scientific planning space can be formed based on the road topological structure, the success rate of path search planning can be improved, the searched path can be maximally ensured to accord with the driving habits of conventional drivers, and the accuracy of automatic vehicle remote calling can be further improved.
Drawings
For purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made in detail to the present invention as illustrated in the accompanying drawings, in which:
FIG. 1 is a logic block diagram of a remote call method based on scene reconstruction;
FIG. 2 is a flow chart of a remote summoning method based on scene reconstruction;
fig. 3 is a system architecture diagram of a remote summoning system based on limited route guidance information.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or the orientations or positional relationships that the products of the present invention are conventionally placed in use, and are only used for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance. Furthermore, the terms "horizontal", "vertical" and the like do not imply that the components are required to be absolutely horizontal or pendant, but rather may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined. In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The following is further detailed by the specific embodiments:
the first embodiment is as follows:
the embodiment discloses a remote calling method based on scene reconstruction.
As shown in fig. 1 and 2, the remote summoning method based on scene reconstruction includes the following steps:
s1: receiving a remote calling signal of a target vehicle, and acquiring a corresponding calling end point position and vehicle-mounted sensing information;
in the embodiment, the user can send the remote calling signal to the vehicle-mounted machine system of the target vehicle through the mobile phone APP. The vehicle-mounted perception information is mainly based on sensors such as a vision sensor, a laser radar, a millimeter wave radar and an ultrasonic radar, and is used for detecting information such as an obstacle target and a lane line and outputting information such as a target rectangular frame, freeScae, the lane line and a road mark.
And further acquiring a vehicle-mounted navigation path, a vehicle memory path and a cloud memory path of the target vehicle.
S2: reconstructing a scene based on vehicle-mounted perception information to generate a road topological structure; then, establishing a global coordinate system by taking the starting point of the target vehicle as the origin of coordinates, and further calculating the real-time pose of the target vehicle under the global coordinate system; finally, according to a road topological structure, coordinate conversion is carried out and a grid map is generated by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle, so that a corresponding planning space is obtained;
in this embodiment, based on the vehicle-mounted perception information, scene reconstruction is performed by combining the vehicle-mounted navigation path of the target vehicle, the vehicle memory path and the cloud memory path, so as to generate a road topology structure.
The cost value generation in the planning space grid map depends on the road topology, the obstacle information and the distance to the call end position. The grid cost value on the road topological structure is small, the grid cost value with the obstacle is maximum, and the grid cost value farther away from the calling terminal is larger.
S3: performing path search planning based on the planning space and the calling terminal position to generate a local planning path;
s4: performing path following control based on the local planned path to generate vehicle control information;
in the present embodiment, the path following control includes lateral control and longitudinal control; the vehicle control information includes angle request information, torque request information, deceleration request information, and gear request information.
S5: controlling the whole vehicle executing mechanism of the target vehicle to act based on the vehicle control information to realize the automatic driving of the target vehicle;
in this embodiment, the vehicle actuator includes an EMS (engine management system), an ESP (stabilization system of the vehicle), an EPS (power steering system), a gear, and a BCM (vehicle body control system), where the EMS receives the longitudinal control torque request information, the ESP receives the longitudinal control deceleration request information, the EPS receives the lateral control angle request information, and the gear receives the gear request information.
S6: and repeating the steps S4 to S5 until the target vehicle reaches the call end position.
In the embodiment, whether the target vehicle reaches the calling terminal position is judged, and if yes, the remote calling is finished; otherwise, return to step S4.
It should be noted that the remote calling method based on scene reconstruction in the present invention can generate corresponding software code or software service in a program programming manner, and further can be run and implemented on a server and a computer.
The method comprises the steps of reconstructing a scene based on vehicle-mounted sensing information to generate a road topological structure, performing coordinate conversion and generating a grid map by combining barrier information and the real-time pose of a target vehicle to obtain a planning space, performing path search planning based on the planning space and a calling terminal position to generate a local planning path, and performing path following control to generate vehicle control information so as to realize automatic driving of the target vehicle. On one hand, the method and the device realize scene reconstruction based on vehicle-mounted perception information, further generate a planning space to realize path search planning, realize automatic driving and remote calling of complex scenes under the condition of not depending on high-precision maps and positioning, and further improve the effectiveness of remote calling of the automatic driving vehicle. On the other hand, the planning space is obtained by combining the road topological structure with the obstacle information and the real-time pose of the target vehicle to perform coordinate conversion and generate a grid map, so that when path search planning is performed based on the planning space and the calling end point position, path search planning can be performed based on a reconstructed scene environment, direction guidance can be performed based on the grid map and the global coordinate system of the planning space and the calling end point position, further path search planning in the whole area can be realized to obtain a globally optimal local planning path, and the accuracy of remote calling of the automatic driving vehicle can be improved.
Meanwhile, scene reconstruction is carried out on the road topological structure by introducing the vehicle or cloud memory path, the road identification and other information and the global path information of the vehicle navigation path, so that a more scientific planning space can be formed based on the road topological structure, the success rate of path search planning can be improved, the searched path can be maximally ensured to accord with the driving habits of conventional drivers, and the accuracy of automatic vehicle remote calling can be further improved.
In the specific implementation process, scene reconstruction is carried out by combining a vehicle-mounted navigation path of a target vehicle, a vehicle memory path and a cloud memory path based on vehicle-mounted perception information, and a road topological structure is generated.
In this embodiment, according to the real-time vehicle-mounted perception information, scene reconstruction is performed on the road topology structure of the (parking lot) by combining the recorded vehicle memory path and the lane related identification, the cloud memory path and the lane related identification, and the vehicle-mounted navigation path which may exist, wherein the completeness of the scene reconstruction depends on the completeness of various memory paths and road identifications and whether the vehicle-mounted navigation path exists. Meanwhile, the cloud-end memory path and lane mark mainly comprise the history time record of the vehicle and the path information (of the parking lot) memorized by other networked vehicles.
And (3) loading a global path in the environment of the vehicle-mounted navigation map, namely the vehicle-mounted navigation path, according to the current vehicle position and the calling terminal position information aiming at the environment of the part (parking lot). This path, although not highly accurate, may be used to plan directions for subsequent path searches.
The vehicle memory path determines whether the vehicle enters (parking lot) or not according to vehicle navigation positioning, and the like, specifies an area with an available calling function, once the vehicle enters the area, the path memory function is started, namely the information of the track where the vehicle runs is recorded, and visually detectable lane lines, vehicle bit lines, lane guide lines and the like are recorded, wherein the lane guide lines need to record indication directions and positions, and the arrow directions of the lane guide lines need to be converted to the global coordinate system where the memory track is located.
And the cloud memory path is used for uploading the information such as the memory track, the lane guide line, the lane line and the like recorded by the vehicle to the cloud.
According to the method, scene reconstruction is carried out on the road topological structure of the parking lot by introducing the information such as the vehicle or cloud memory path and the road mark and the global path information of the vehicle navigation path, so that a more scientific planning space can be formed based on the road topological structure, the success rate of path search planning can be improved, the searched path can be maximally ensured to be in line with the driving habits of conventional drivers, and the accuracy of automatic driving vehicle remote calling can be further improved.
In the specific implementation process, the real-time pose of the target vehicle under the global coordinate system is calculated according to a vehicle kinematics algorithm, and then the real-time pose of the target vehicle is corrected through vehicle-mounted sensing information. Because of no high-precision map and positioning, the vehicle only depends on the common navigation and positioning, and the error is larger. Therefore, the real-time pose of the vehicle under the determined global coordinate system is calculated according to the vehicle kinematics, and the real-time pose is corrected by using the perception information, so that the accuracy of the calculated pose is improved.
The method and the device calculate the real-time pose of the target vehicle under the global coordinate system through vehicle kinematics, correct the real-time pose through the perception information, and can improve the accuracy of real-time pose calculation, so that a more scientific planning space can be formed based on the real-time pose, the success rate of path search planning can be improved, and the accuracy of remote calling of the automatic driving vehicle can be further improved.
In the specific implementation process, when the route search planning is carried out based on the planning space and the calling terminal position, the raster map cost value, the minimum turning radius constraint, the gear switching and the angle request change of the target vehicle are comprehensively considered, so that the corresponding local planning route is generated. If the current gear is the forward gear D, the gear cost function for switching to the gear R is larger when the route is searched and planned. The cost function of the change in angle is determined by the difference between the current vehicle heading and the possible existing path corresponding to the requested angle. The operation mode of path planning adopts equal-time real-time planning or event trigger planning, and the trigger event mainly comprises gear change, large tracking error, collision risk and other factors. After the path search is completed, the generated local planning path needs to be subjected to smooth optimization processing.
In this embodiment, the path search planning is implemented by the existing path search planning algorithm in the automatic driving technology.
When the route searching and planning are carried out, the grid map cost value, the minimum turning radius constraint, the gear switching and the angle request change of the target vehicle are comprehensively considered, so that the route searching and planning can be carried out based on the reconstructed scene environment, the grid map and the global coordinate system based on the planning space can be combined with the calling terminal position for direction guidance, the route searching and planning in the whole area can be better realized, the globally optimal local planning route can be obtained, and the accuracy of remote calling of the automatic driving vehicle can be further improved.
In step S5, the method specifically includes the following steps:
s501: detecting whether a collision risk exists between the target vehicle and the obstacle, if so, returning to the step S3; otherwise, executing the next step;
s502: judging whether the following error of the target vehicle is larger than a calibrated value PathError or not, if so, returning to the step S3; otherwise, executing the next step;
s503: judging whether the current gear request of the target vehicle is changed or not, if so, returning to the step S3; otherwise, the process proceeds to step S6.
According to the invention, the collision risk of the target vehicle and the obstacle, the following error of the target vehicle and the current gear request change of the target vehicle are detected, so that the path following control can be better completed to realize the automatic driving of the target vehicle, and the effectiveness of the remote calling of the automatic driving vehicle can be further improved.
Example two:
the embodiment discloses a remote calling system based on limited route guide information, which is implemented based on the remote calling method in the first embodiment.
As shown in fig. 3, the remote summoning system based on the limited route guidance information specifically includes:
the information acquisition module is used for acquiring a corresponding calling end position and vehicle-mounted sensing information when receiving a remote calling signal of a target vehicle;
in the embodiment, the user can send the remote calling signal to the vehicle-mounted machine system of the target vehicle through the mobile phone APP. The vehicle-mounted perception information is mainly based on sensors such as a vision sensor, a laser radar, a millimeter wave radar and an ultrasonic radar, and is used for detecting information such as an obstacle target and a lane line and outputting information such as a target rectangular frame, freeScae, the lane line and a road mark.
The information acquisition module also acquires a vehicle-mounted navigation path, a vehicle memory path and a cloud memory path of the target vehicle.
The scene reconstruction module is used for reconstructing a scene based on the vehicle-mounted perception information to generate a road topological structure;
in this embodiment, the scene reconstruction module performs scene reconstruction based on the vehicle-mounted sensing information in combination with the vehicle-mounted navigation path, the vehicle memory path and the cloud memory path of the target vehicle, and generates a road topology structure.
The pose calculation module is used for establishing a global coordinate system by taking the starting point of the target vehicle as a coordinate origin, and further calculating the real-time pose of the target vehicle under the global coordinate system;
the planning space module is used for carrying out coordinate conversion and generating a grid map by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle according to the road topological structure to obtain a corresponding planning space;
in this embodiment, the cost value generation in the planning space grid map depends on the road topology, the obstacle information, and the distance from the call end position. The grid cost value on the road topological structure is small, the grid cost value with the obstacle is maximum, and the grid cost value farther away from the calling terminal is larger.
The route planning module is used for searching and planning a route based on the planning space and the calling terminal position to generate a local planning route;
the path tracking control module is used for carrying out path following control based on the local planned path and generating vehicle control information;
in the present embodiment, the path following control includes lateral control and longitudinal control; the vehicle control information includes angle request information, torque request information, deceleration request information, and gear request information.
And the whole vehicle executing mechanism is used for controlling the action of the target vehicle based on the vehicle control information so as to realize automatic driving.
In this embodiment, the vehicle actuator includes an EMS (engine management system), an ESP (stabilization system of the vehicle), an EPS (power steering system), a gear, and a BCM (vehicle body control system), where the EMS receives the longitudinal control torque request information, the ESP receives the longitudinal control deceleration request information, the EPS receives the lateral control angle request information, and the gear receives the gear request information.
The method comprises the steps of reconstructing a scene based on vehicle-mounted sensing information to generate a road topological structure, performing coordinate conversion and generating a grid map by combining barrier information and the real-time pose of a target vehicle to obtain a planning space, performing path search planning based on the planning space and a calling terminal position to generate a local planning path, and performing path following control to generate vehicle control information so as to realize automatic driving of the target vehicle. On one hand, the method and the device realize scene reconstruction based on vehicle-mounted perception information, further generate a planning space to realize path search planning, realize automatic driving and remote calling of complex scenes under the condition of not depending on high-precision maps and positioning, and further improve the effectiveness of remote calling of the automatic driving vehicle. On the other hand, the planning space is obtained by combining the road topological structure with the barrier information and the real-time pose of the target vehicle to perform coordinate transformation and generate a grid map, so that when the path search planning is performed based on the planning space and the calling end position, the path search planning can be performed based on the reconstructed scene environment, and the direction guidance can be performed based on the grid map and the global coordinate system of the planning space and the calling end position, so that the path search planning in the whole area can be realized to obtain the globally optimal local planning path, and the accuracy of remote calling of the automatic driving vehicle can be improved.
Meanwhile, scene reconstruction is carried out on the road topological structure by introducing the vehicle or the information such as the cloud memory path, the road identification and the like and the global path information of the vehicle navigation path, so that a more scientific planning space can be formed based on the road topological structure, the success rate of path search planning can be improved, the searched path can be maximally ensured to be in line with the driving habits of conventional drivers, and the accuracy of automatic vehicle remote calling can be further improved.
Example three:
disclosed in the present embodiment is a readable storage medium.
A readable storage medium, on which a computer management class program is stored, which when executed by a processor implements the steps of the scene reconstruction based remote summoning method of the present invention. The readable storage medium can be a device with readable storage function such as a U disk or a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and those skilled in the art should understand that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all that should be covered by the claims of the present invention.
Claims (10)
1. The remote calling method based on scene reconstruction is characterized by comprising the following steps:
s1: receiving a remote calling signal of a target vehicle, and acquiring a corresponding calling end point position and vehicle-mounted sensing information;
s2: reconstructing a scene based on vehicle-mounted perception information to generate a road topological structure; then, establishing a global coordinate system by taking the starting point of the target vehicle as the origin of coordinates, and further calculating the real-time pose of the target vehicle under the global coordinate system; finally, according to the road topological structure, coordinate conversion is carried out and a grid map is generated by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle, so that a corresponding planning space is obtained;
s3: performing path search planning based on the planning space and the calling terminal position to generate a local planning path;
s4: performing path following control based on the local planned path to generate vehicle control information;
s5: controlling the whole vehicle executing mechanism of the target vehicle to act based on the vehicle control information to realize the automatic driving of the target vehicle;
s6: and repeating the steps S4 to S5 until the target vehicle reaches the call end position.
2. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: in the step S1, a vehicle-mounted navigation path, a vehicle memory path and a cloud memory path of a target vehicle are also obtained;
in the step S2, based on the vehicle-mounted perception information, scene reconstruction is carried out by combining a vehicle-mounted navigation path of the target vehicle, a vehicle memory path and a cloud memory path, and a road topological structure is generated.
3. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: and S2, calculating the real-time pose of the target vehicle under the global coordinate system according to a vehicle kinematics algorithm, and correcting the real-time pose of the target vehicle through vehicle-mounted perception information.
4. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: in step S2, the cost value generated in the planning space grid map depends on the road topology, the obstacle information and the distance from the calling terminal position.
5. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: in step S3, when a route search is planned based on the planned space and the call end point position, the raster map cost value, the minimum turning radius constraint, the shift switching, and the angle request change of the target vehicle are comprehensively considered to generate a corresponding local planned route.
6. The remote summoning method based on scene reconstruction as claimed in claim 5, wherein: in step S3, the generated local planned path is subjected to a smoothing optimization process.
7. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: in step S4, the path following control comprises transverse control and longitudinal control; the vehicle control information includes angle request information, torque request information, deceleration request information, and gear request information.
8. The remote summoning method based on scene reconstruction as claimed in claim 1, wherein: in step S5, the method specifically includes the following steps:
s501: detecting whether a collision risk exists between the target vehicle and the obstacle, if so, returning to the step S3; otherwise, executing the next step;
s502: judging whether the following error of the target vehicle is larger than a calibrated value or not, if so, returning to the step S3; otherwise, executing the next step;
s503: judging whether the current gear request of the target vehicle is changed or not, if so, returning to the step S3; otherwise, the process proceeds to step S6.
9. The remote calling system based on the limited path guiding information is characterized in that: the implementation of the remote summoning method according to claim 1, specifically comprising:
the information acquisition module is used for acquiring a corresponding calling end position and vehicle-mounted sensing information when receiving a remote calling signal of a target vehicle;
the scene reconstruction module is used for reconstructing a scene based on the vehicle-mounted perception information to generate a road topological structure;
the pose calculation module is used for establishing a global coordinate system by taking the starting point of the target vehicle as a coordinate origin, and further calculating the real-time pose of the target vehicle under the global coordinate system;
the planning space module is used for carrying out coordinate conversion and generating a grid map by combining barrier information in the vehicle-mounted sensing information and the real-time pose of the target vehicle according to the road topological structure to obtain a corresponding planning space;
the route planning module is used for searching and planning a route based on the planning space and the calling terminal position to generate a local planning route;
the path tracking control module is used for carrying out path following control based on the local planned path and generating vehicle control information;
and the whole vehicle executing mechanism is used for controlling the action of the target vehicle based on the vehicle control information so as to realize automatic driving.
10. A readable storage medium, on which a computer management class program is stored, which when executed by a processor implements the steps of the scene reconstruction based remote summoning method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706143.9A CN115237121A (en) | 2022-06-21 | 2022-06-21 | Scene reconstruction-based remote calling method and system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706143.9A CN115237121A (en) | 2022-06-21 | 2022-06-21 | Scene reconstruction-based remote calling method and system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115237121A true CN115237121A (en) | 2022-10-25 |
Family
ID=83670222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210706143.9A Pending CN115237121A (en) | 2022-06-21 | 2022-06-21 | Scene reconstruction-based remote calling method and system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115237121A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115892067A (en) * | 2022-11-23 | 2023-04-04 | 禾多科技（北京）有限公司 | Target vehicle driving method, target vehicle driving device, storage medium, and electronic device |
| CN116153083A (en) * | 2023-04-20 | 2023-05-23 | 江铃汽车股份有限公司 | Vehicle calling method and system applied to underground parking garage |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105620473A (en) * | 2014-10-27 | 2016-06-01 | 同致电子科技（厦门）有限公司 | Parking track correcting method |
| CN110244738A (en) * | 2019-06-26 | 2019-09-17 | 广州小鹏汽车科技有限公司 | Vehicle running control method and device and vehicle |
| CN111413959A (en) * | 2018-12-18 | 2020-07-14 | 初速度（苏州）科技有限公司 | Global path planning and parking method and system from any point to any point |
| CN111497829A (en) * | 2020-04-14 | 2020-08-07 | 浙江吉利汽车研究院有限公司 | Full-automatic parking path determination method, device, equipment and storage medium |
| CN111746517A (en) * | 2020-05-25 | 2020-10-09 | 中国第一汽车股份有限公司 | Vehicle parking-out control method and device |
| CN111880533A (en) * | 2020-07-16 | 2020-11-03 | 华人运通(上海)自动驾驶科技有限公司 | Driving scene reconstruction method, device, system, vehicle, equipment and storage medium |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
| CN112802346A (en) * | 2020-12-28 | 2021-05-14 | 苏州易航远智智能科技有限公司 | Autonomous parking system and method based on cloud sharing and map fusion |
| CN113009912A (en) * | 2021-02-20 | 2021-06-22 | 中国重汽集团济南动力有限公司 | Low-speed commercial unmanned vehicle path planning calculation method based on mixed A star |
-
2022
- 2022-06-21 CN CN202210706143.9A patent/CN115237121A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105620473A (en) * | 2014-10-27 | 2016-06-01 | 同致电子科技（厦门）有限公司 | Parking track correcting method |
| CN111413959A (en) * | 2018-12-18 | 2020-07-14 | 初速度（苏州）科技有限公司 | Global path planning and parking method and system from any point to any point |
| CN110244738A (en) * | 2019-06-26 | 2019-09-17 | 广州小鹏汽车科技有限公司 | Vehicle running control method and device and vehicle |
| CN111497829A (en) * | 2020-04-14 | 2020-08-07 | 浙江吉利汽车研究院有限公司 | Full-automatic parking path determination method, device, equipment and storage medium |
| CN111746517A (en) * | 2020-05-25 | 2020-10-09 | 中国第一汽车股份有限公司 | Vehicle parking-out control method and device |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
| CN111880533A (en) * | 2020-07-16 | 2020-11-03 | 华人运通(上海)自动驾驶科技有限公司 | Driving scene reconstruction method, device, system, vehicle, equipment and storage medium |
| CN112802346A (en) * | 2020-12-28 | 2021-05-14 | 苏州易航远智智能科技有限公司 | Autonomous parking system and method based on cloud sharing and map fusion |
| CN113009912A (en) * | 2021-02-20 | 2021-06-22 | 中国重汽集团济南动力有限公司 | Low-speed commercial unmanned vehicle path planning calculation method based on mixed A star |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115892067A (en) * | 2022-11-23 | 2023-04-04 | 禾多科技（北京）有限公司 | Target vehicle driving method, target vehicle driving device, storage medium, and electronic device |
| CN115892067B (en) * | 2022-11-23 | 2024-01-26 | 禾多科技（北京）有限公司 | Driving method and device of target vehicle, storage medium and electronic device |
| CN116153083A (en) * | 2023-04-20 | 2023-05-23 | 江铃汽车股份有限公司 | Vehicle calling method and system applied to underground parking garage |
| CN116153083B (en) * | 2023-04-20 | 2023-10-17 | 江铃汽车股份有限公司 | Vehicle calling method and system applied to underground parking garage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111746504B (en) | Memory parking method, system, device and computer readable storage medium | |
| CN115237121A (en) | Scene reconstruction-based remote calling method and system and readable storage medium | |
| CN109426261B (en) | Automatic driving device | |
| US20170305467A1 (en) | Method and apparatus for the assisted guidance of a vehicle | |
| CN113950703B (en) | Method, device and data processing system for determining whether external parameter matrix is accurate | |
| US11584248B2 (en) | Method of parking an autonomous driving vehicle for autonomous charging | |
| JP2016192150A (en) | Vehicle travel control device | |
| US11541890B2 (en) | Vehicle control device and storage medium which stores a computer program for vehicle control | |
| US11760356B2 (en) | Lane change planning device and storage medium storing computer program for the same | |
| CN114137948B (en) | Method, device, computer device and storage medium for driving formation vehicle | |
| US11467584B2 (en) | Multi-layer grid based open space planner | |
| EP3914492B1 (en) | A parking-trajectory generation method combined with offline and online solutions | |
| JP2019095210A (en) | Vehicle controller, method for controlling vehicle, and program | |
| CN111650604B (en) | Method for realizing accurate detection of self-vehicle and surrounding obstacle by using accurate positioning | |
| US20200183415A1 (en) | System and method for control of an autonomous vehicle | |
| CN115268427A (en) | Vehicle control method, vehicle control device, vehicle, and storage medium | |
| CN112445221A (en) | Automatic working system and regression method | |
| WO2023009688A1 (en) | Method, system, and computer program product for resolving level ambiguity for radar systems of autonomous vehicles | |
| US20210354689A1 (en) | Parking Assistant and Method for Adaptive Parking of a Vehicle to Optimize Overall Sensing Coverage of a Traffic Environment | |
| US20210303874A1 (en) | A point cloud-based low-height obstacle detection system | |
| US20230242148A1 (en) | Vehicle controller and vehicle control method | |
| CN117268425B (en) | Accurate navigation method and system of vehicle, medium, computing equipment and vehicle | |
| EP4220580A1 (en) | Method for vehicle driving assistance within delimited area | |
| EP4386448A1 (en) | Drivable path determination for a vehicle | |
| US20230314167A1 (en) | Method and apparatus for generating map data, and non-transitory computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |