CN116772887A - Vehicle course initialization method, system, device and readable storage medium - Google Patents
Vehicle course initialization method, system, device and readable storage medium Download PDFInfo
- Publication number
- CN116772887A CN116772887A CN202311077504.9A CN202311077504A CN116772887A CN 116772887 A CN116772887 A CN 116772887A CN 202311077504 A CN202311077504 A CN 202311077504A CN 116772887 A CN116772887 A CN 116772887A
- Authority
- CN
- China
- Prior art keywords
- target
- point cloud
- feature vector
- vehicle
- yard
- 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.)
- Granted
Links
- 238000011423 initialization method Methods 0.000 title claims abstract description 12
- 239000013598 vector Substances 0.000 claims abstract description 243
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000009826 distribution Methods 0.000 claims description 24
- 238000000513 principal component analysis Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 11
- 238000012986 modification Methods 0.000 description 10
- 230000004048 modification Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000000611 regression analysis Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the specification provides a vehicle course initialization method, a system, a device and a readable storage medium, and belongs to the technical field of navigation. The method comprises the steps of obtaining a reference feature vector related to a target storage yard; acquiring a target point cloud related to a target storage yard under a vehicle coordinate system through a target vehicle; determining at least one target feature vector associated with the target yard based on the target point cloud; and determining a target vehicle heading of the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector. The method can be realized through a vehicle course initializing system and a device. The method may also be run after being read by computer instructions stored on a computer readable storage medium. According to the invention, the heading of the target vehicle is determined by referring to the feature vector and the target feature vector, so that the problem of initializing the heading of the unmanned vehicle in the container yard can be effectively solved.
Description
Technical Field
The present disclosure relates to the field of navigation technologies, and in particular, to a method, a system, an apparatus, and a readable storage medium for initializing a vehicle heading.
Background
The unmanned vehicle can greatly improve the transportation efficiency and save the transportation cost in the container transportation process. The unmanned basis of the vehicle is that the current positioning information of the vehicle can be accurately acquired, the vehicle course is initialized, and then the planning and control of the vehicle are realized. Therefore, these unmanned vehicles are typically equipped with various sensors of global positioning system (Global Positioning System, GPS), lidar, cameras, millimeter waves, and the like. In the current course initialization method, the course initialization is usually realized through a GPS double antenna, but the GPS signal can be greatly shielded and interfered in the face of a scene that the two sides of a container yard are fully piled with metal containers, so that the course initialization cannot be realized. Meanwhile, once the unmanned vehicle loads the container for operation, GPS signal reception is greatly affected, so that heading initialization cannot be smoothly carried out. In addition, for the method of directly matching the on-line point cloud with the pre-established point cloud map to obtain the initial course, the pre-established point cloud map usually fails to match due to the fact that the container yard is a scene with larger variation, so that course initialization cannot be accurately performed.
Accordingly, it is desirable to provide a vehicle heading initialization method, system, apparatus, and readable storage medium that can address the heading initialization problem of unmanned vehicles in container yards.
Disclosure of Invention
One or more embodiments of the present specification provide a vehicle heading initialization method. The method comprises the following steps: acquiring a reference feature vector related to a target storage yard, wherein the reference feature vector reflects the storage yard heading of the target storage yard under a target coordinate system; acquiring a target point cloud related to the target storage yard under a vehicle coordinate system by a target vehicle; determining at least one target feature vector related to the target yard based on the target point cloud, wherein the at least one target feature vector represents a yard heading of the target yard under the vehicle coordinate system; and determining a target vehicle heading of the target vehicle under the target coordinate system based on the reference feature vector and the at least one target feature vector.
One of the embodiments of the present description provides a vehicle heading initialization system. The system comprises: a first vector determination module configured to determine a reference feature vector associated with a target yard, the reference feature vector representing a yard heading of the target yard in a target coordinate system; an acquisition module configured to acquire, by a target vehicle, a target point cloud related to the target yard in a vehicle coordinate system; a second vector determination module configured to determine, based on the target point cloud, at least one target feature vector associated with the target yard, the at least one target feature vector embodying a yard heading of the target yard in the vehicle coordinate system; a heading determination module configured to determine a heading of the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector.
One or more embodiments of the present specification provide a vehicle heading initialization apparatus comprising at least one processor and at least one memory, the at least one memory to store computer instructions, the at least one processor to execute at least some of the computer instructions to implement a vehicle heading initialization method as described in any of the embodiments of the present specification.
One or more embodiments of the present description provide a computer-readable storage medium storing computer instructions that, when read by a computer, perform a method of initializing a heading of a vehicle as described in any of the embodiments of the present description.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a block diagram of a vehicle heading initialization system shown in accordance with some embodiments of the present description;
FIG. 2 is an exemplary flow chart of a vehicle heading initialization method according to some embodiments of the present disclosure;
FIG. 3 is a schematic illustration of a vehicle coordinate system shown in accordance with some embodiments of the present disclosure;
fig. 4 is an exemplary flow chart for determining a target feature vector according to some embodiments of the present description.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.
Furthermore, while the systems and methods disclosed in this specification are primarily described with respect to a transport vehicle in an autopilot system, it should be understood that this is merely one exemplary embodiment. The systems and methods of the present description may be applied to any other type of transportation system. For example, the systems and methods of the present description may be applied to transportation systems in different environments, including land, sea, aerospace, and the like, or any combination thereof. The autopilot vehicles of the transport system may include taxis, private cars, windmills, buses, trains, motor cars, high-speed rails, subways, watercraft, aircraft, spacecraft, hot air balloons, and the like, or any combination thereof.
FIG. 1 is a block diagram of a vehicle heading initialization system according to some embodiments of the present description. In some embodiments, the vehicle heading initialization system 100 may include a first acquisition module 110, a second acquisition module 120, a feature vector determination module 130, and a heading determination module 140.
The first acquisition module 110 may be configured to acquire a reference feature vector associated with the target yard, which may embody a yard heading of the target yard in the target coordinate system. In some embodiments, the first acquisition module 110 may be further configured to acquire a reference point cloud associated with the target yard and determine a reference feature vector associated with the target yard based on a distribution of the reference point cloud. In some embodiments, the first obtaining module 110 may be further configured to perform principal component analysis on the reference point cloud, and use a feature vector corresponding to a maximum feature value in the principal component analysis result as the reference feature vector.
The second acquisition module 120 may be configured to acquire, by a target vehicle, a cloud of target points related to the target yard in a vehicle coordinate system.
The feature vector determination module 130 may be configured to determine at least one target feature vector associated with the target yard, based on the target point cloud, the at least one target feature vector embodying a yard heading of the target yard under the vehicle coordinate system. In some embodiments, feature vector determination module 130 may be further configured to filter the target point cloud based on a normal vector of the target point cloud; clustering the screened target point cloud, and determining at least one target point cloud cluster; and determining a target feature vector corresponding to the target point cloud cluster based on the distribution of the target point cloud clusters for each of the at least one target point cloud cluster.
The heading determination module 140 may be configured to determine a target vehicle heading of the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector. In some embodiments, the heading determination module 140 may be further configured to determine, for each target feature vector, an angle between the target feature vector and the reference feature vector, and determine a target vehicle heading of the target vehicle in the target coordinate system based on at least one angle to which the at least one target feature vector corresponds, respectively.
In some embodiments, the vehicle heading initialization system 100 may also include other modules. For example, a communication module may also be included. The communication module can exchange information with other external data sources and/or external systems through a network.
For a detailed description of the various modules, reference is made to fig. 2-4 and their associated descriptions.
It should be noted that the above description of the vehicle heading initialization system 100 and its modules is for descriptive convenience only and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the first acquisition module 110, the second acquisition module 120, the feature vector determination module 130, and the heading determination module 140 disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules described above. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description. In some embodiments, the first acquisition module 110 and the second acquisition module 120 may be combined.
FIG. 2 is an exemplary flow chart of a vehicle heading initialization method according to some embodiments of the present description. In some embodiments, the process 200 may be performed by the vehicle heading initialization system 100. As shown in fig. 2, the process 200 includes the steps of:
step 210, obtaining a reference feature vector associated with the target storage yard.
The target yard is a container yard in which a target vehicle requiring course initialization is located. Among them, a container yard is a place for handing over and keeping containers, and there are generally a large number of containers that are constantly stored or transported out. The container can be transported in various transportation modes such as air and sea, and in order to accelerate the loading and unloading of the container, the target storage yard can be arranged at a port, a wharf, an airport, a railway station and the like.
The reference feature vector is used for reflecting the yard heading of the target yard under the target coordinate system. Since the target yard is a container yard and a large number of containers with uniform specifications are piled up, the overall distribution trend of the target yard is fixed. For example, the distribution of the target yard is a rectangular corridor distribution. Further, the yard heading of the target yard may be a direction of the target yard.
The target coordinate system is the coordinate system at the target heap location. The target coordinate system may be a planar rectangular coordinate system. For example, the target coordinate system may be a universal cross-ink katuger (Universal Transverse Mercator, UTM) coordinate system. For example, the reference feature vector may be determined byAnd (3) representing. The target coordinate system may be another coordinate system such as a space rectangular coordinate system and a polar coordinate system.
In some embodiments, the first acquisition module 110 may acquire a reference feature vector associated with the target yard entered by a user, wherein the user is the manager of the vehicle heading initialization system 100.
In some embodiments, the first obtaining module 110 may further obtain a reference point cloud of the target yard, and determine the reference feature vector related to the target yard based on the reference point cloud of the target yard. For example, the first obtaining module 110 may perform analysis processing on the reference point cloud of the target storage yard by using various data analysis algorithms, such as a regression analysis method, a discriminant analysis method, and the like, to determine a reference feature vector corresponding to the reference point cloud.
The reference point cloud is the yard point cloud data of the pre-established target yard under the target coordinate system. The reference point cloud may include a set of data points associated with one or more objects within a target yard. The one or more objects within the aforementioned target yard range may include, for example, the ground, at least one container, and the like. In the present description embodiment, the reference point cloud may include primarily data points associated with containers in the target yard.
In some embodiments, the first acquisition module 110 may acquire the reference point cloud through a detection device. For example, an in-vehicle lidar may be used to acquire a reference point cloud. The first acquisition module 110 may acquire the reference point cloud in advance to be taken.
In some embodiments, the first obtaining module 110 may obtain a predetermined reference feature vector from the storage device, and may also determine the reference feature vector related to the target yard online based on the reference point cloud of the target yard. For example, the first acquisition module 110 may acquire a reference point cloud of the target yard online, and determine a reference feature vector related to the target yard based on the reference point cloud of the target yard acquired online. For another example, the first acquisition module 110 may acquire a reference point cloud of the target yard in advance, determine a reference feature vector related to the target yard based on the reference point cloud acquired in advance, and the determined reference feature vector may be stored in the storage device. When step 210 needs to be performed, the first obtaining module 110 may obtain a predetermined reference feature vector from the storage device.
Since the overall distribution trend of the target yard is fixed, the distribution of the target yard is not affected even if there are some container variations, and thus the predetermined reference feature vector is substantially identical to the reference feature vector determined on line.
In some embodiments, the first acquisition module 110 may determine a reference feature vector associated with the target yard based on a distribution of the reference point cloud.
It will be appreciated that the distribution of the reference point cloud may represent the overall trend of the target yard. In a target yard, the distribution of the reference point cloud can also be considered as a substantially rectangular corridor distribution due to the specificity of the yard. Thus, the reference feature vector of the target yard can be determined by the distribution of the reference point cloud. For example, the yard heading of the target yard may be the direction of the target yard.
In the embodiment of the specification, the reference point cloud distribution represents the overall trend of the target storage yard, and the reference feature vector is determined by determining the reference point cloud distribution of the target storage yard, so that the influence of the change of the individual containers on the overall target storage yard can be effectively avoided.
In some embodiments, the first acquisition module 110 may determine the distribution of the reference point cloud using various data analysis algorithms, such as regression analysis, discriminant analysis, and the like, and determine the reference feature vector associated with the target yard based on the distribution of the reference point cloud.
In some embodiments, the first obtaining module 110 may perform principal component analysis on the reference point cloud, and use a feature vector corresponding to a maximum feature value in the principal component analysis result as the reference feature vector.
Principal component analysis (Principal Component Analysis, PCA) is a data statistical method. Principal component analysis can reduce the dimensionality of the data set while maintaining the features of the data set that contribute most to the variance. In the embodiment of the present disclosure, due to the specificity of the target storage yard, the principal component analysis is performed on the reference point cloud, so that the distribution of the reference point cloud of the target storage yard, that is, the overall trend of the target storage yard, can be obtained.
In some embodiments, a 3 x 3 matrix may be obtained by principal component analysis of the reference point cloud, the matrix including features and feature vectors. The feature vector corresponding to the maximum feature value can be determined as the reference feature vector of the target storage yard. The larger the number of point cloud data along a certain direction in the reference point cloud, the larger the feature value corresponding to the feature vector of the direction obtained through principal component analysis will be. Therefore, the number of the point cloud data of the feature vector corresponding to the maximum feature value is the largest in the reference point cloud, and the feature vector corresponding to the maximum feature value is the reference feature vector capable of reflecting the yard heading of the target yard.
In the embodiment of the present disclosure, the reference feature vector is determined by principal component analysis, so that the influence of the change of the individual containers (for example, how many containers are or the individual containers are skewed) on the whole target storage yard can be effectively avoided.
Step 220, acquiring a target point cloud related to a target storage yard under a vehicle coordinate system by a target vehicle.
The target vehicle refers to a vehicle for which heading initialization needs to be performed. The target vehicle may be any type of autonomous vehicle, and may include a taxi, a private car, etc., or any combination thereof. In the present description, the target vehicle may be a vehicle transporting a container. The target vehicle includes a detection device in addition to the structure of the conventional vehicle. The detection means comprise at least radar. The detection means may also comprise other structures. For example, cameras, global positioning system modules, acceleration sensors, speed sensors (e.g., hall sensors), steering angle sensors (e.g., tilt sensors), traction-related sensors (e.g., force sensors), and the like.
The target point cloud refers to point cloud data related to a target storage yard acquired through a target vehicle. In some embodiments, the target point cloud may include point cloud data related to containers in the target yard. For example only, the second acquisition module 120 may acquire a target yard-related initial point cloud via the target vehicle and screen out container-related point cloud data from the initial point cloud as the target point cloud. Wherein the initial point cloud includes all point cloud data of the surroundings of the target vehicle.
It can be understood that the target point cloud acquired by the target vehicle is point cloud data in the vehicle coordinate system. The vehicle coordinate system is a coordinate system established with reference to the target vehicle. For example, the vehicle coordinate system may be a coordinate system C as shown in fig. 3, the origin of the vehicle coordinate system may coincide with the centroid of the target vehicle, the forward direction of the target vehicle is taken as the positive X-axis direction, the left side of the target vehicle is taken as the positive Y-axis direction, and the upper side of the target vehicle is taken as the positive Z-axis direction.
In some embodiments, the second acquisition module 120 may acquire the target point cloud in real-time by the target vehicle. The target point cloud may be acquired by a lidar mounted on the target vehicle. For example, as the target vehicle scans the surroundings of the object by emitting laser pulses, the laser pulses may be reflected by physical points in the surroundings and returned. Point cloud data representing the surrounding environment may be generated from one or more characteristics of the returned laser pulses, and during collection of the point cloud data, the surrounding environment may be scanned over a range of scan angles (e.g., 360 degrees, 180 degrees, 120 degrees) and at a particular scan frequency (e.g., 10Hz, 15Hz, 20 Hz). The second acquisition module 120 may screen out point cloud data related to the container from the initial point cloud as the target point cloud.
At step 230, at least one target feature vector associated with the target yard is determined based on the target point cloud.
The target feature vector is used for reflecting the yard heading of the target yard under the vehicle coordinate system, namely the angle of the container in the target yard relative to the target vehicle. It will be appreciated that there may be one or more stacks of containers within the target yard, each stack including at least one container, the containers within each stack having a connection relationship. As shown in fig. 3, the target yard includes three containers thereon. For each container pile, the characteristic vector determining module 130 may analyze the target point cloud by adopting various data analysis algorithms, such as regression analysis, discriminant analysis, and the like, to divide different container piles to obtain at least one target point cloud cluster corresponding to the container pile, and further determine a target characteristic vector corresponding to each target point cloud cluster. A related description of the target point cloud cluster can be seen in fig. 4.
In some embodiments, feature vector determination module 130 may screen the target point cloud based on a normal vector of the target point cloud; clustering the screened target point cloud, and determining at least one target point cloud cluster; and determining a target feature vector corresponding to the target point cloud cluster based on the distribution of the target point cloud clusters for each of the at least one target point cloud cluster. For more on the above embodiments reference is made to fig. 4 and its related description.
Step 240, determining a target vehicle heading of the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector.
The heading of the target vehicle is the vehicle running direction of the target vehicle under the target coordinate system. The determined heading of the target vehicle is one of the current positioning information of the target vehicle, and can be used for realizing unmanned driving of the target vehicle subsequently.
In some embodiments, for each target feature vector, the heading determination module 140 may process the target feature vector and the reference feature vector by a variety of methods (e.g., regression analysis, discriminant analysis, etc.), determine an angle between the target feature vector and the reference feature vector, and thereby determine a target vehicle heading of the target vehicle in the target coordinate system. In some embodiments, when there is only one target feature vector, the heading determination module 140 may directly determine an angle between the target feature vector and the reference feature vector and determine a target vehicle heading of the target vehicle in the target coordinate system based on the aforementioned angle. In some embodiments, when there are multiple target feature vectors, the heading determination module 140 may calculate a mean of angles between the multiple target feature vectors and the reference feature vector and determine a target vehicle heading for the target vehicle in the target coordinate system based on the mean of the aforementioned angles.
In some embodiments, for each target feature vector, the heading determination module 140 may determine an angle between the target feature vector and the reference feature vector and determine a target vehicle heading of the target vehicle in the target coordinate system based on at least one angle to which the at least one target feature vector corresponds, respectively.
The angle between the target feature vector and the reference feature vector can reflect the direction difference of the target storage yard under the vehicle coordinate system and the target coordinate system. By determining the angle between the target feature vector and the reference feature vector, the actual heading of the target vehicle can be determined by taking the target storage yard as a reference.
In some embodiments, for each target feature vector, the angle between the target feature vector and the reference feature vector may be determined by the following equation (1):
（1）
wherein, the liquid crystal display device comprises a liquid crystal display device,indicate->The angle between the respective target feature vector and the reference feature vector, < >>Representation->Cosine value of>Representing reference feature vectors>Indicate->Target feature vector->Modulo length representing reference feature vector, +.>Represent the first/>Modulo length of each target feature vector.
In the embodiment of the specification, the heading of the target vehicle is determined through the angle between the target feature vector and the reference feature vector, so that the problem of failure of the pre-established point cloud map caused by the change of the container position in the target storage yard can be avoided.
As described above, the angle between the target feature vector and the reference feature vector is determined for each target feature vector. In some embodiments, the heading determination module 140 may determine an average of at least one angle as the target vehicle heading, each of the at least one angle corresponding to one target feature vector. In other words, for the target feature vectors corresponding to the containers with different distributions and the angles corresponding to the target feature vectors, the average value of the angle values may be selected as the target vehicle heading.
In the embodiment of the present disclosure, the average value of the angles corresponding to the respective target feature vectors is used as the target vehicle heading, so that a more accurate target vehicle heading can be obtained.
In some embodiments, for each target feature vector, the heading determination module 140 may also determine a distance of a target yard location corresponding to a target point cloud cluster associated with the target feature vector from the target vehicle. Further, the heading determination module 140 may determine a weight corresponding to the target feature vector based on the distance, thereby determining a heading of the target vehicle in the target coordinate system based on at least one weight and at least one angle respectively corresponding to the at least one target feature vector.
The distance between the target yard position corresponding to the target point cloud cluster related to the target feature vector and the target vehicle can be understood as the distance between the container or containers connected with each other corresponding to the target point cloud cluster and the target vehicle. If the distance between the container corresponding to the cluster point cloud and the target vehicle is closer, the number of the point cloud data of the target point cloud cluster acquired by the target vehicle is larger, and the calculation result is more accurate.
The weight corresponding to the target feature vector may represent a ratio of importance degrees of the target feature vector. The weight corresponding to the target feature vector is related to the distance between the target storage yard position corresponding to the target point cloud cluster related to the target feature vector and the target vehicle. In some embodiments, the heading determination module 140 may determine a weight ratio from the distance ratio, and the sum of the weights corresponding to all target feature vectors is 1. If the distance is closer, the weight corresponding to the target feature vector can be set to be larger, otherwise, the weight is related. In some embodiments, the heading determination module 140 may determine the heading of the target vehicle in the target coordinate system by weighted summing based on the weights and angles corresponding to the at least one target feature vector.
In the embodiment of the present disclosure, the weight of the target feature vector is determined by determining the distance between the target yard position corresponding to the related target point cloud cluster of the target feature vector and the target vehicle, and finally, the target vehicle heading is determined by weighted average, so that a more accurate target vehicle heading can be obtained.
In the embodiment of the specification, the target vehicle course of the target vehicle under the target coordinate system is determined based on the yard course of the target yard under the target coordinate system and the yard course of the target yard under the vehicle coordinate system, compared with the method for directly matching the on-line point cloud with the pre-established point cloud map to obtain the initial course, the problem that the pre-established point cloud map fails due to the change of the container position in the target yard is avoided, and the problem of course initialization of the unmanned vehicle in the container yard can be effectively solved.
It should be noted that the above description of the process 200 is only for illustration and description, and is not intended to limit the application scope of the present disclosure. Various modifications and changes to flow 200 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description. For example, steps 210 and 220 may be performed simultaneously.
Fig. 4 is an exemplary flow chart for determining a target feature vector according to some embodiments of the present description. In some embodiments, the process 400 may be performed by the feature vector determination module 130. As shown in fig. 4, the process 400 includes the steps of:
step 410, screening the target point cloud based on the normal vector of the target point cloud, and determining the target heading point cloud.
The normal vector of the target point cloud refers to the normal vector of the plane corresponding to the target point cloud. It should be noted that, the feature vector determining module 130 may determine, based on the target point clouds, planes corresponding to the respective target point clouds, and thus each target point cloud has a unique vertical normal vector. It will be appreciated that, as shown in fig. 3, the target yard as a whole presents an elongate straight corridor structure due to the particular geometric characteristics of the target yard, i.e. the containers in the target yard are of substantially rectangular parallelepiped configuration. Therefore, the point cloud planes formed by the outer walls of all containers in the target storage yard are only in parallel or perpendicular relation, and therefore most normal vectors of the target point cloud can be distributed in two perpendicular directions.
In some embodiments, the feature vector determining module 130 may first determine a plane corresponding to the target point cloud, and then use a normal vector corresponding to the plane as a normal vector of the target point cloud. For example, the feature vector module 130 may determine the normal vector of the plane corresponding to the target point cloud by a pending coefficient method, an outer product method, a plane intercept equation method, or the like.
The target heading point cloud is a target point cloud corresponding to a class of normal vectors with more pointing cloud data. The target point cloud corresponding to the normal vector with more point cloud data may be the point cloud data of the L plane of the container in fig. 3, where the point cloud data of the plane is more.
In some embodiments, the feature vector determination module 130 may screen the target heading point cloud by a normal vector of the target point cloud, thereby removing interference from point cloud data on the container side.
In some embodiments, the feature vector determination module 130 may determine a normal vector of the point cloud unit for each of a plurality of point cloud units of the target point cloud.
The point cloud unit refers to point cloud data of one point cloud unit. Each point cloud unit determines a corresponding point cloud plane and has a unique corresponding normal vector, so the feature vector determining module 130 may screen the target heading point cloud according to the normal vector corresponding to each point cloud unit.
In some embodiments, before screening, the feature vector determination module 130 may normalize a plurality of normal vectors of a plurality of point cloud units. The normalization process may unify the features of all values into one value interval, i.e. may be mapped between (0, 1). Therefore, the normalization processing of the plurality of normal vectors of the plurality of point cloud units can avoid that the individual abnormal data has a larger influence on the course initialization result.
In some embodiments, the feature vector determination module 130 may determine the categories of the plurality of point cloud units based on the association between the plurality of normalized normal vectors.
In some embodiments, the association relationship between normalized normal vectors may be embodied by dot multiplication. The feature vector determination module 130 may determine a class of the point cloud unit based on an association relationship between the plurality of normalized normal vectors. In some embodiments, the categories of point cloud units may include a direction category. For example, the feature vector determining module 130 may determine point clouds in different directions according to an association relationship between normal vectors, for example, point clouds on a side of a container, point clouds on an upper surface of the container, and point clouds on a front surface of the container, so as to screen out point clouds on a surface with more point cloud data.
In some embodiments, for each normal vector of the plurality of normalized normal vectors, the feature vector determination module 130 may point multiply the normal vector with a reference normal vector to obtain a point multiplication result, and determine a class of the point cloud unit according to the point multiplication result. The direction category corresponding to the reference normal vector is a first type direction. In some embodiments, the feature vector determination module 130 may determine the direction category of the normal vector as the second-class direction when the dot product is less than the dot product threshold; when the dot multiplication result is greater than or equal to or less than the dot multiplication threshold, the feature vector determination module 130 may determine the direction category of the normal vector as the first type direction.
In some embodiments, the direction categories of the normal vector may include a first type of direction and a second type of direction. Wherein the feature vector determination module 130 may determine the direction category corresponding to the reference normal vector as a first type of direction (e.g., may be noted as) The direction category corresponding to the normal vector perpendicular to the reference normal vector is determined as the second type direction (for example, may be noted +.>). In some embodiments, the feature vector determining module 130 may use the normal vector corresponding to an arbitrarily selected point cloud unit as the reference normal vector, which is denoted as +.>。
In some embodiments, feature vector determination module 130 may normalize each normal vectorAnd reference normal vector->Dot multiplication is performed to determine each normal vector +.>Of the direction category of>Ordinal numbers that are normal vectors. If the normal vector->And reference normal vector->Perpendicular to each other, the dot product should be theoretically 0; if the normal vector->And reference normal vector->Parallel to each other, the dot product is theoretically 1. Thus, it is possible to +_ according to each normal vector>And reference normal vector->To determine the normal vector +.>Is a direction of (2).
Since there may be a case where the containers in the target yard are not stacked in order, a dot product threshold may be set. The dot product threshold value is the judgment normal vector A threshold parameter for the direction category of (c). In some embodiments, the dot product threshold may be predetermined by a preset, for example, the dot product threshold may be preset to 0.02, 0.03, or 0.05. The dot product threshold value can also be adjusted according to the placement condition of the container in the target storage yard, for example, a container image in the target storage yard is obtained, the container image is processed based on a machine learning model, and a corresponding dot product threshold value is determined, wherein the machine learning model can be obtained through training, a training sample can be a sample container image, and a training label can be a sample dot product threshold value obtained through labeling the sample container image through manual labeling.
Exemplary, for the firstNormal vector, if normal vector->And reference normal vector->The dot product is less than the dot product thresholdThe value can then determine the normal vector +.>The direction category of (2) belongs to the second category of direction, and is +.>Vertical; if normal vectorAnd reference normal vector->If the dot product of (2) is greater than or equal to the dot product threshold, the normal vector +.>The direction category of (2) belongs to the first category of direction, and is +.>Parallel.
In the embodiment of the specification, the target course point cloud can be rapidly and accurately screened by carrying out point multiplication on the normal vector to determine the direction category of the normal vector.
In some embodiments, the feature vector determination module 130 may screen the plurality of point cloud units based on the categories of the plurality of point cloud units to determine the target heading point cloud. The feature vector determining module 130 may screen each point cloud unit based on the direction category of the normal vector corresponding to each point cloud unit.
In some embodiments, the direction category of the normal vector corresponding to each point cloud unit may include a first type direction and a second type direction, and the feature vector determining module 130 may reserve a type with a larger number of point clouds in the two direction categories, and screen out a type with a smaller number of point clouds. For example, the feature vector determining module 130 may respectively count the total number of point cloud data belonging to the first direction and the total number of point cloud data belonging to the second direction, and reserve one type of direction in which the total number of point cloud data in the two direction types is greater. It should be noted that, as shown in fig. 3, due to the special geometry of the target yard, the overall long and straight corridor structure is presented, and the point cloud data in the direction class of the L plane parallel to the road in the target yard is the most, so that the target heading point cloud can be screened accordingly.
In the embodiment of the specification, the point cloud units are classified through the normal vector of the point cloud units, so that point cloud data of a main plane, namely target heading point cloud, are screened, and the point cloud data of the side face of the container are removed from interfering the point cloud data of the main plane. In addition, the normal vector of the point cloud unit is normalized, so that the great influence of individual abnormal data on the course initialization result can be avoided.
Step 420, clustering the target course point cloud, and determining at least one target point cloud cluster.
The target point cloud cluster is formed by clustering the screened target course point cloud. Each target point cloud cluster may be a point cloud corresponding to one container or a plurality of interconnected containers. Because the containers in the target yard are empty and not necessarily connected together when they are placed, there may be one or more stacks of containers in the target yard. Different stacks of containers may correspond to different target point cloud clusters. Therefore, the screened target heading point clouds are clustered, and the mean value can be calculated to obtain more accurate heading of the target vehicle.
In some embodiments, the feature vector determination module 130 may employ various clustering methods, such as, for example, european clustering, hierarchical clustering-based methods, and the like, to cluster the target heading point clouds to determine at least one target point cloud cluster.
Step 430, for each of the at least one target point cloud cluster, determining a target feature vector corresponding to the target point cloud cluster based on the distribution of the target point cloud clusters.
In some embodiments, the feature vector determination module 130 may perform principal component analysis on each target point cloud cluster to obtain a distribution of each target point cloud cluster, thereby determining a corresponding target feature vector. In some embodiments, feature vector determination module 130 may And obtaining a feature vector corresponding to the maximum feature value of each target point cloud cluster through principal component analysis, and taking the feature vector as a target feature vector corresponding to the target point cloud cluster. For a more description of principal component analysis, see fig. 1. In some embodiments, the target feature vector may be determined byRepresentation of->Ordinals of cloud clusters of different target points.
In the embodiment of the present disclosure, the normal vector of the target point cloud is used to screen the target point cloud, so that interference of the point cloud data on the side of the container can be removed. In addition, the point cloud information can be processed more conveniently and rapidly by using the point to replace the surface in a mode of clustering to form the target point cloud cluster.
It should be noted that the above description of the process 400 is only for illustration and description, and is not intended to limit the application scope of the present disclosure. Various modifications and changes to flow 400 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description.
One or more embodiments of the present specification provide a vehicle heading initialization apparatus including at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the vehicle heading initialization method of any of the above-described embodiments.
One or more embodiments of the present specification provide a computer-readable storage medium storing computer instructions that, when read by a computer, perform a vehicle heading initialization method as in any of the embodiments above.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.
Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.
Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (10)
1. A method for initializing a heading of a vehicle, the method comprising:
acquiring a reference feature vector related to a target storage yard, wherein the reference feature vector reflects the storage yard heading of the target storage yard under a target coordinate system;
acquiring a target point cloud related to the target storage yard under a vehicle coordinate system by a target vehicle;
determining at least one target feature vector related to the target yard based on the target point cloud, wherein the at least one target feature vector represents a yard heading of the target yard under the vehicle coordinate system;
and determining a target vehicle heading of the target vehicle under the target coordinate system based on the reference feature vector and the at least one target feature vector.
2. The method of claim 1, wherein the obtaining a reference feature vector associated with a target yard comprises:
acquiring a reference point cloud related to the target storage yard;
and determining the reference feature vector related to the target storage yard based on the distribution of the reference point cloud.
3. The method of claim 2, wherein the determining the reference feature vector associated with the target yard based on the distribution of the reference point cloud comprises:
performing principal component analysis on the reference point cloud;
and determining a feature vector corresponding to the maximum feature value in the principal component analysis result as the reference feature vector.
4. The method of claim 1, wherein the determining at least one target feature vector associated with the target yard based on the target point cloud comprises:
screening the target point cloud based on the normal vector of the target point cloud to determine a target heading point cloud;
clustering the target course point cloud to determine at least one target point cloud cluster;
and determining a target feature vector corresponding to each target point cloud cluster in the at least one target point cloud cluster based on the distribution of the target point cloud clusters.
5. The method of claim 4, wherein the screening the target point cloud based on the normal vector of the target point cloud to determine a target heading point cloud comprises:
determining a normal vector of each point cloud unit in a plurality of point cloud units of the target point cloud;
normalizing a plurality of normal vectors of the plurality of point cloud units;
determining the category of the plurality of point cloud units based on the association relation among the plurality of normalized normal vectors;
and screening the plurality of point cloud units based on the categories of the plurality of point cloud units, and determining the target heading point cloud.
6. The method of claim 1, wherein the determining a target vehicle heading for the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector comprises:
for each target feature vector, determining an angle between the target feature vector and the reference feature vector;
and determining the heading of the target vehicle under the target coordinate system based on at least one angle respectively corresponding to the at least one target feature vector.
7. The method of claim 6, wherein the determining the target vehicle heading for the target vehicle in the target coordinate system based on the at least one angle to which the at least one target feature vector corresponds, respectively, comprises:
for each of the target feature vectors,
determining the distance between a target storage yard position corresponding to a target point cloud cluster related to the target feature vector and the target vehicle;
determining the weight corresponding to the target feature vector based on the distance;
and determining the heading of the target vehicle under the target coordinate system based on at least one weight and at least one angle respectively corresponding to the at least one target feature vector.
8. A vehicle heading initialization system, comprising:
the system comprises a first acquisition module, a second acquisition module and a storage yard detection module, wherein the first acquisition module is configured to acquire a reference feature vector related to a target storage yard, and the reference feature vector reflects the storage yard heading of the target storage yard under a target coordinate system;
a second acquisition module configured to acquire, by a target vehicle, a target point cloud related to the target yard in a vehicle coordinate system;
a feature vector determination module configured to determine at least one target feature vector associated with the target yard, based on the target point cloud, the at least one target feature vector reflecting a yard heading of the target yard in the vehicle coordinate system;
A heading determination module configured to determine a heading of the target vehicle in the target coordinate system based on the reference feature vector and the at least one target feature vector.
9. A vehicle heading initialization apparatus, said apparatus comprising at least one processor and at least one memory;
the at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement a vehicle heading initialization method as recited in any one of claims 1-7.
10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform a vehicle heading initialisation method as claimed in any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311077504.9A CN116772887B (en) | 2023-08-25 | 2023-08-25 | Vehicle course initialization method, system, device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311077504.9A CN116772887B (en) | 2023-08-25 | 2023-08-25 | Vehicle course initialization method, system, device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116772887A true CN116772887A (en) | 2023-09-19 |
| CN116772887B CN116772887B (en) | 2023-11-14 |
Family
ID=87993480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311077504.9A Active CN116772887B (en) | 2023-08-25 | 2023-08-25 | Vehicle course initialization method, system, device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116772887B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190323844A1 (en) * | 2018-04-18 | 2019-10-24 | Faraday&Future Inc. | System and method for lidar-based vehicular localization relating to autonomous navigation |
| US20210103040A1 (en) * | 2019-10-02 | 2021-04-08 | Korea University Research And Business Foundation | EXTRINSIC CALIBRATION METHOD OF MULTIPLE 3D LiDAR SENSORS FOR AUTONOMOUS NAVIGATION SYSTEM |
| CN112950781A (en) * | 2021-03-19 | 2021-06-11 | 中山大学 | Point cloud map construction method for multi-sensor dynamic weighting fusion of special scene |
| CN113536883A (en) * | 2021-03-23 | 2021-10-22 | 长沙智能驾驶研究院有限公司 | Obstacle detection method, vehicle, device, and computer storage medium |
| CN113609914A (en) * | 2021-07-09 | 2021-11-05 | 北京经纬恒润科技股份有限公司 | Obstacle identification method and device and vehicle control system |
| CN113835101A (en) * | 2021-09-30 | 2021-12-24 | 同济大学 | Vehicle positioning method and device based on radar point cloud and storage medium |
| CN114241448A (en) * | 2021-12-31 | 2022-03-25 | 深圳市镭神智能系统有限公司 | Method and device for obtaining heading angle of obstacle, electronic equipment and vehicle |
| CN114459471A (en) * | 2022-01-30 | 2022-05-10 | 中国第一汽车股份有限公司 | Positioning information determination method and device, electronic equipment and storage medium |
| CN114964275A (en) * | 2022-05-24 | 2022-08-30 | 无锡八英里电子科技有限公司 | Ground-air cooperative map construction method, device, equipment and storage medium |
| US20220324437A1 (en) * | 2020-01-03 | 2022-10-13 | Mobileye Vision Technologies Ltd. | LIDAR-Camera Fusion Where LIDAR and Camera Validly See Different Things |
| CN115655288A (en) * | 2022-10-28 | 2023-01-31 | 东风汽车股份有限公司 | Intelligent laser positioning method and device, electronic equipment and storage medium |
| CN115892068A (en) * | 2022-11-23 | 2023-04-04 | 北京斯年智驾科技有限公司 | Vehicle control method, device, equipment, medium and vehicle |
| CN116087979A (en) * | 2023-02-02 | 2023-05-09 | 福勤智能科技（昆山）有限公司 | Container loading and unloading robot positioning navigation method, device, equipment and medium |
| CN116503474A (en) * | 2023-02-08 | 2023-07-28 | 腾讯科技（深圳）有限公司 | Pose acquisition method, pose acquisition device, electronic equipment, storage medium and program product |
| CN116533998A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Automatic driving method, device, equipment, storage medium and vehicle of vehicle |
-
2023
- 2023-08-25 CN CN202311077504.9A patent/CN116772887B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190323844A1 (en) * | 2018-04-18 | 2019-10-24 | Faraday&Future Inc. | System and method for lidar-based vehicular localization relating to autonomous navigation |
| US20210103040A1 (en) * | 2019-10-02 | 2021-04-08 | Korea University Research And Business Foundation | EXTRINSIC CALIBRATION METHOD OF MULTIPLE 3D LiDAR SENSORS FOR AUTONOMOUS NAVIGATION SYSTEM |
| US20220324437A1 (en) * | 2020-01-03 | 2022-10-13 | Mobileye Vision Technologies Ltd. | LIDAR-Camera Fusion Where LIDAR and Camera Validly See Different Things |
| CN112950781A (en) * | 2021-03-19 | 2021-06-11 | 中山大学 | Point cloud map construction method for multi-sensor dynamic weighting fusion of special scene |
| CN113536883A (en) * | 2021-03-23 | 2021-10-22 | 长沙智能驾驶研究院有限公司 | Obstacle detection method, vehicle, device, and computer storage medium |
| CN113609914A (en) * | 2021-07-09 | 2021-11-05 | 北京经纬恒润科技股份有限公司 | Obstacle identification method and device and vehicle control system |
| CN113835101A (en) * | 2021-09-30 | 2021-12-24 | 同济大学 | Vehicle positioning method and device based on radar point cloud and storage medium |
| CN114241448A (en) * | 2021-12-31 | 2022-03-25 | 深圳市镭神智能系统有限公司 | Method and device for obtaining heading angle of obstacle, electronic equipment and vehicle |
| CN114459471A (en) * | 2022-01-30 | 2022-05-10 | 中国第一汽车股份有限公司 | Positioning information determination method and device, electronic equipment and storage medium |
| CN114964275A (en) * | 2022-05-24 | 2022-08-30 | 无锡八英里电子科技有限公司 | Ground-air cooperative map construction method, device, equipment and storage medium |
| CN115655288A (en) * | 2022-10-28 | 2023-01-31 | 东风汽车股份有限公司 | Intelligent laser positioning method and device, electronic equipment and storage medium |
| CN115892068A (en) * | 2022-11-23 | 2023-04-04 | 北京斯年智驾科技有限公司 | Vehicle control method, device, equipment, medium and vehicle |
| CN116087979A (en) * | 2023-02-02 | 2023-05-09 | 福勤智能科技（昆山）有限公司 | Container loading and unloading robot positioning navigation method, device, equipment and medium |
| CN116503474A (en) * | 2023-02-08 | 2023-07-28 | 腾讯科技（深圳）有限公司 | Pose acquisition method, pose acquisition device, electronic equipment, storage medium and program product |
| CN116533998A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Automatic driving method, device, equipment, storage medium and vehicle of vehicle |
Non-Patent Citations (2)
| Title |
|---|
| 胡修祥等: "结合NARF特征的改进型3D-NDT多视点云配准", 《信号处理》, no. 12 * |
| 赵佳等: "自动驾驶汽车高精定位导航技术路线分析", 《客车技术与研究》, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116772887B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190180467A1 (en) | Systems and methods for identifying and positioning objects around a vehicle | |
| US9759809B2 (en) | LIDAR-based shipboard tracking and state estimation for autonomous landing | |
| US11945499B2 (en) | Method and apparatus for trailer angle measurement and vehicle | |
| CN111754625A (en) | Collaborative 3-D environment map for computer-assisted or autonomous driving vehicles | |
| CN112313703B (en) | Incremental Segmentation of Point Clouds | |
| CN113412505A (en) | System and method for ordered representation and feature extraction of point clouds obtained by detection and ranging sensors | |
| CN117607841A (en) | Calibration and positioning of vehicle sensors | |
| WO2019046383A1 (en) | An autonomous yard vehicle system | |
| US11069080B1 (en) | Collaborative airborne object tracking systems and methods | |
| US11798427B2 (en) | Auto-labeling sensor data for machine learning | |
| CN110160528B (en) | Mobile device pose positioning method based on angle feature recognition | |
| US11157867B1 (en) | Selecting flight routes based on historical exposure | |
| CN115144825A (en) | External parameter calibration method and device for vehicle-mounted radar | |
| CN115880252B (en) | Container sling detection method, device, computer equipment and storage medium | |
| EP3703008A1 (en) | Object detection and 3d box fitting | |
| KR20210061971A (en) | Method and apparatus for vehicle avoiding obstacle, electronic device, and computer storage medium | |
| CN109839633B (en) | Multi-frame pre-detection tracking method of airborne early warning radar based on minimum coverage airspace | |
| US20130338858A1 (en) | Method for three dimensional perception processing and classification | |
| CN116772887B (en) | Vehicle course initialization method, system, device and readable storage medium | |
| Kaufmann et al. | Shadow-based matching for precise and robust absolute self-localization during lunar landings | |
| CN112577481B (en) | Ground target positioning method for rotor unmanned aerial vehicle | |
| US11640764B1 (en) | Optimal occupancy distribution for route or path planning | |
| JP2020190814A (en) | Trajectory generation device | |
| US20230072966A1 (en) | Systems and methods for providing and using confidence estimations for semantic labeling | |
| US11891195B2 (en) | Mitigating damage to multi-layer networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |