CN117131150B - Electronic map generation method, device, vehicle and storage medium - Google Patents
Electronic map generation method, device, vehicle and storage medium Download PDFInfo
- Publication number
- CN117131150B CN117131150B CN202311399921.5A CN202311399921A CN117131150B CN 117131150 B CN117131150 B CN 117131150B CN 202311399921 A CN202311399921 A CN 202311399921A CN 117131150 B CN117131150 B CN 117131150B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- semantic
- around
- semantic elements
- environment
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000007613 environmental effect Effects 0.000 claims abstract description 103
- 230000015654 memory Effects 0.000 claims abstract description 33
- 230000036544 posture Effects 0.000 claims description 44
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 25
- 230000006870 function Effects 0.000 description 14
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010040844 Skin exfoliation Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000035618 desquamation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Graphics (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
Abstract
The application discloses a method and a device for generating an electronic map, a vehicle and a storage medium, and belongs to the technical field of vehicles. According to the technical scheme provided by the embodiment of the application, the electronic map is automatically generated under the condition that the vehicle enters the underground parking lot, and the environment type of the current position of the vehicle is determined based on the semantic elements, the element positions and the element types around the vehicle, namely whether the semantic elements of the current position of the vehicle are reliable or not is determined. And acquiring the environmental characteristic points around the vehicle under the condition that the environmental type of the current position is unreliable in semantic elements. And generating an electronic map for memorizing the vehicle current position based on the vehicle current pose, the element positions and element types of semantic elements around the vehicle and the environment characteristic points. The generation process of the electronic map does not need manual operation of a user, and is silent in the whole process, so that the learning cost of generating the electronic map required by memory parking is reduced, and the energy and time of the user are saved.
Description
Technical Field
The present invention relates to the field of vehicle technologies, and in particular, to a method and apparatus for generating an electronic map in the field of vehicle technologies, a vehicle, and a storage medium.
Background
With the development of vehicle technology, more and more vehicles provide a memory parking function. Memory parking is a driving assistance technology, and a driver only needs to start memory parking at a proper position at the entrance of a parking lot, so that a vehicle can automatically search for a parking space and park.
In the related art, in order to use the function of memorizing parking, it is necessary to generate an electronic map of a parking lot in advance. In the process of generating the electronic map, the user often triggers an interaction instruction to start or stop the generation process of the electronic map, and meanwhile, certain learning cost is also required in the operation required in the process of generating the electronic map, so that the energy and time of the user are wasted, and the use frequency of the memory parking function is reduced.
Disclosure of Invention
The embodiment of the application provides a method, a device, a vehicle and a storage medium for generating an electronic map, which can reduce the learning cost for generating the electronic map required by memory parking and save the energy and time of a user.
In one aspect, a method for generating an electronic map is provided, the method including:
determining an environment type of a current position of a vehicle based on element parameters of semantic elements around the vehicle under the condition that the vehicle enters an underground parking lot, wherein the element parameters comprise element positions and element types, and the environment type comprises reliable semantic elements and unreliable semantic elements;
Acquiring environmental feature points around the vehicle under the condition that the environment type is unreliable;
and generating an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environmental feature points, wherein the electronic map is used for memorizing and parking in the underground parking lot.
In one aspect, there is provided a generating apparatus of an electronic map, the apparatus including:
the environment type determining module is used for determining the environment type of the current position of the vehicle based on element parameters of semantic elements around the vehicle when the vehicle enters the underground parking garage, wherein the element parameters comprise element positions and element types, and the environment types comprise reliable semantic elements and unreliable semantic elements;
the characteristic point acquisition module is used for acquiring the environmental characteristic points around the vehicle under the condition that the environment type is unreliable;
the electronic map generation module is used for generating an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environment feature points, and the electronic map is used for memorizing and parking in the underground parking lot.
In one possible implementation manner, the environment type determining module is configured to determine, when the vehicle enters an underground parking garage, semantic elements in N first neighboring areas around the vehicle based on element positions of the semantic elements around the vehicle, where N is a positive integer; determining the region type of each first adjacent region based on the element types of semantic elements in N first adjacent regions around the vehicle, wherein the region type comprises strong semantic constraints and weak semantic constraints; and determining the environment type of the current position of the vehicle based on the region types of the N first adjacent regions.
In a possible implementation manner, the environment type determining module is configured to determine, for any one of the N first neighboring areas, an area type of the first neighboring area as a strong semantic constraint if a semantic element of a preset semantic type exists in the first neighboring area; and determining the region type of the first adjacent region as weak semantic constraint under the condition that the semantic elements of the preset semantic types do not exist in the first adjacent region.
In a possible implementation manner, the environment type determining module is configured to determine, in a case where there are at least M first neighboring regions of the N first neighboring regions, that are strong semantic constraints, an environment type of the current position of the vehicle as a semantic element reliable, M < N, and M is a positive integer; and determining the environment type of the current position of the vehicle as unreliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types do not exist in the N first adjacent areas.
In a possible implementation manner, the feature point obtaining module is configured to identify feature points of environmental information acquired by the vehicle to obtain initial feature points around the vehicle when the environmental type is unreliable due to semantic elements; and filtering the initial feature points around the vehicle based on the feature point parameters of the initial feature points around the vehicle to obtain the environment feature points around the vehicle, wherein the environment feature points are the initial feature points with feature point parameters meeting the preset parameter conditions, and the feature point parameters comprise at least one of feature point types, feature point priorities and feature point confidence.
In a possible implementation manner, the electronic map generating module is further configured to generate, when the environment type is that the semantic element is reliable, an electronic map of the current location based on element parameters of the semantic element around the vehicle and the current pose of the vehicle.
In a possible implementation manner, the electronic map generating module is used for determining whether a blocked target position exists around the vehicle or not under the condition that the environment type is reliable in terms of semantic elements;
Determining position description information of the target position based on the position type of the target position and element parameters of semantic elements around the target position when the target position exists around the vehicle; and generating an electronic map of the current position based on element parameters of semantic elements around the vehicle, the current pose of the vehicle and the position description information of the target position.
In a possible implementation manner, the electronic map generating module is configured to determine, in a case where the target location exists around the vehicle, a topological relation of semantic elements around the target location based on element locations and element types of the semantic elements around the target location, where the topological relation is used to represent a distribution situation of the semantic elements; and fusing the position type of the target position and the topological relation of semantic elements around the target position to obtain the position description information of the target position.
In a possible implementation manner, the electronic map generating module is configured to determine, when the target location exists around the vehicle, semantic elements in K second neighboring areas around the target location based on element positions of the semantic elements around the target location, where K is a positive integer; determining target element types of the K second adjacent areas around the vehicle based on element types of semantic elements of the second adjacent areas, wherein the target element types are element types meeting preset semantic type conditions; and determining the topological relation of semantic elements around the target position based on the relative position relation of the K second adjacent areas and the type of the target element.
In one possible implementation manner, the device further comprises a position judging module, configured to acquire a plurality of historical postures of the vehicle, signal quality of positioning signals and environmental information acquired by the vehicle; based on a plurality of historical poses of the vehicle, a signal quality of the positioning signal, and the environmental information, it is determined whether the vehicle enters an underground parking garage.
In one possible implementation manner, the location determining module is configured to determine, based on the environmental information, an environmental type of a location where the vehicle is located, when a plurality of historical poses of the vehicle indicate that the vehicle is driving in and out of a downward slope and a signal quality of the positioning signal is less than or equal to a preset signal quality; determining that the vehicle enters an underground parking garage under the condition that the environment type is reliable in semantic elements; and determining that the vehicle does not enter an underground parking garage under the condition that a plurality of historical postures of the vehicle indicate that the vehicle enters but does not exit a downward slope, or the signal quality of the positioning signal is larger than the preset signal quality, or the environment type is unreliable due to semantic elements.
In one possible implementation manner, the position determining module is further configured to determine that the vehicle is driving into a downward slope when a gradient corresponding to a first posture of the plurality of historical postures is greater than or equal to a slope entering angle, and a difference between the gradient corresponding to the first posture and a gradient corresponding to a historical posture before a preset duration is greater than or equal to a gradient difference threshold; the gradient corresponding to a second gesture in the plurality of historical gestures is smaller than or equal to a slope outlet angle, the difference value between the gradient corresponding to the second gesture and the gradient corresponding to the historical gesture before the preset time period is larger than or equal to the gradient difference value threshold value, the condition that the vehicle drives out of a downward ramp is determined, and the acquisition time of the second gesture is after the first gesture;
and determining that the signal quality of the positioning signal is smaller than or equal to the preset signal quality under the condition that the carrier-to-noise ratio of the positioning signal is smaller than or equal to a carrier-to-noise ratio threshold and the number of effective satellites of the positioning signal is smaller than or equal to a satellite number threshold.
In a possible implementation manner, the device further comprises an element parameter obtaining module, configured to perform semantic recognition on environment information collected by the vehicle, so as to obtain element types of semantic elements around the vehicle, where the environment information is used to reflect an environment state around the vehicle; element positions of semantic elements around the vehicle are determined based on the environmental information.
In one aspect, a vehicle is provided that includes one or more processors and one or more memories having at least one program code stored therein, the program code loaded and executed by the one or more processors to implement operations performed by the method of generating an electronic map.
In one aspect, a computer-readable storage medium having at least one program code stored therein is loaded and executed by a processor to implement operations performed by the electronic map generation method.
According to the technical scheme provided by the embodiment of the application, the electronic map is automatically generated under the condition that the vehicle enters the underground parking lot, and the environment type of the current position of the vehicle is determined based on the semantic elements, the element positions and the element types around the vehicle, namely whether the semantic elements of the current position of the vehicle are reliable or not is determined. And acquiring the environmental characteristic points around the vehicle under the condition that the environmental type of the current position is unreliable in semantic elements. And generating an electronic map for memorizing the vehicle current position based on the vehicle current pose, the element positions and element types of semantic elements around the vehicle and the environment characteristic points. The generation process of the electronic map does not need manual operation of a user, and is silent in the whole process, so that the learning cost of generating the electronic map required by memory parking is reduced, and the energy and time of the user are saved.
Drawings
Fig. 1 is a schematic diagram of an implementation environment of a method for generating an electronic map according to an embodiment of the present application;
fig. 2 is a flowchart of a method for generating an electronic map according to an embodiment of the present application;
fig. 3 is a flowchart of another method for generating an electronic map according to an embodiment of the present application;
FIG. 4 is a schematic illustration of an access to an underground parking garage provided in an embodiment of the present application;
FIG. 5 is a flow chart for determining that a vehicle is entering an underground parking garage provided in an embodiment of the present application;
FIG. 6 is a schematic diagram of a first proximity area provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of a second vicinity provided in an embodiment of the present application;
FIG. 8 is a schematic diagram of determining location description information according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic map generating device according to an embodiment of the present application;
fig. 10 is a schematic structural view of a vehicle according to an embodiment of the present application.
Detailed Description
The technical solutions in the present application will be clearly and thoroughly described below with reference to the accompanying drawings. Wherein, in the description of the embodiments of the present application, "/" means or is meant unless otherwise indicated, for example, a/B may represent a or B: the text "and/or" is merely an association relation describing the associated object, and indicates that three relations may exist, for example, a and/or B may indicate: the three cases where a exists alone, a and B exist together, and B exists alone, and in addition, in the description of the embodiments of the present application, "plural" means two or more than two.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be construed as implying or implying relative importance or implying a number of reflected technical features. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.
Auxiliary driving: the auxiliary driving means that the vehicle is provided with a series of advanced technologies and systems, so that a driver can be assisted to complete the driving process, and the driving safety and the driving comfort are improved. In the embodiment of the application, the memory parking belongs to auxiliary driving.
Memory parking: the memory parking is based on automatic parking, realizes more comprehensive reversing scene application, has the function of memory parking, can carry out memory setting in front of a garage or a parking lot door, can record and finish the operation from a gate to a specified parking space only by manually finishing the operation once, can wake up the memory parking function only by starting to the specified position when driving later, can search for the recorded fixed parking space in the parking lot by the vehicle, and finally finishes parking, and the whole operation is full-automatic operation.
Path planning: path planning is one of the main study contents of motion planning. The motion planning consists of path planning and track planning, the sequence points or curves connecting the start position and the end position are called paths, and the strategy for forming the paths is called path planning.
Referring to fig. 1, an implementation environment of a method for generating an electronic map according to an embodiment of the present application includes an in-vehicle terminal 101, an environment information sensor 102, an attitude sensor 103, and a positioning system 104.
The in-vehicle terminal 101 is a terminal provided on a vehicle for processing acquired data. The in-vehicle terminal 101 is connected to the environmental information sensor 102, the posture sensor 103, and the positioning system 104, and can acquire data from the environmental information sensor 102, the posture sensor 103, and the positioning system 104. In the embodiment of the application, the vehicle-mounted terminal 101 can generate an electronic map and control the vehicle to perform memory parking.
The environmental information sensor 102 is used for collecting environmental information around the vehicle, the posture sensor 103 is used for determining the posture of the vehicle, and the positioning system 104 is used for determining the position of the vehicle based on the positioning signals. The number and types of the environmental information sensor 102, the posture sensor 103, and the positioning system 104 are set by a technician according to actual situations, which are not limited in this embodiment, and in order to facilitate understanding, in the following description, the environmental information sensor 102, the posture sensor 103, and the positioning system 104 are described as one example.
After the implementation environment of the embodiment of the present application is introduced, the application scenario of the technical solution provided by the embodiment of the present application is described below. The technical scheme provided by the embodiment of the application can be applied to various vehicles with the memory driving function, for example, the technical scheme provided by the embodiment of the application can be applied to electric vehicles with the memory driving function, hybrid vehicles with the memory driving function and fuel vehicles with the memory driving function, and the embodiment of the application is not limited to the above.
In the case that the technical scheme provided by the embodiment of the application is applied to an electric vehicle with a travelling memory function, when the vehicle enters an underground parking lot, the environment type of the current position of the vehicle is determined based on element parameters of semantic elements around the vehicle, the environment type comprises reliable semantic elements and unreliable semantic elements, and the reliability and the unreliability are for an electronic map generated based on the semantic elements. Under the condition that the environment type is unreliable, the reliability degree of generating the electronic map based on the semantic elements is low, and at the moment, the environment characteristic points around the vehicle are acquired, wherein the environment characteristic points refer to points with obvious differences from the surrounding environment elements in the environment. Based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environmental feature points, an electronic map of the current position is generated, and the electronic map is used for memorizing parking in the underground parking garage. The electronic map is not a complete electronic map, more semantic elements or characteristic points can be obtained along with the running of the vehicle in the underground parking garage, and the complete electronic map of the underground parking garage can be finally obtained by continuously updating the electronic map by utilizing the semantic elements and the characteristic points. In addition, in the process of generating the electronic map, some local indexes associated with the positions are added in the electronic map to perform feature retrieval, so that a large number of repeated storage can be avoided.
It should be noted that, the foregoing is described by taking the application of the technical solution provided by the embodiment of the present application to an electric vehicle as an example, and the implementation process and the foregoing description belong to the same inventive concept and are not repeated herein when the technical solution provided by the embodiment of the present application is applied to other types of vehicles.
In addition, the technical solution provided in the embodiment of the present application can be applied to other types of vehicles besides the above types of vehicles, and the embodiment of the present application is not limited thereto.
After the implementation environment and the application scenario of the embodiments of the present application are described, the technical solution provided in the embodiments of the present application is described below, referring to fig. 2, taking the implementation subject as an example of a vehicle-mounted terminal, and the method includes the following steps.
201. In the case that the vehicle enters the underground parking garage, the vehicle-mounted terminal determines an environment type of the current position of the vehicle based on element parameters of semantic elements around the vehicle, wherein the element parameters comprise element positions and element types, and the environment type comprises that the semantic elements are reliable and the semantic elements are unreliable.
Among them, an underground parking garage refers to a building built underground for parking motor vehicles of various sizes. Underground parking lot includes ramp, access, and parking areas, and in the present embodiment, access to underground parking refers to access to a parking area. The semantic element refers to an environmental element with a specific meaning, the element parameters comprise an element position and an element type, and the element position refers to a relative position between the semantic element and the vehicle. The semantic elements are reliable and the semantic elements are unreliable, so that the probability that a vehicle is in an underground parking lot is high under the condition that the semantic elements are reliable, the semantic elements are directly utilized to generate an electronic map of the underground parking lot, and the generated electronic map is high in reliability; under the condition that the semantic elements are unreliable, whether the vehicles are in the underground parking lot or not cannot be accurately identified, and the reliability degree of generating the electronic map of the underground parking lot by directly utilizing the semantic elements is low.
202. And under the condition that the environment type is unreliable, the vehicle-mounted terminal acquires the environment feature points around the vehicle.
The environmental characteristic points refer to points in the environment, which are obviously different from surrounding environmental elements. The environmental feature points have no specific meaning and are therefore not semantic elements.
203. The vehicle-mounted terminal generates an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environmental feature points, and the electronic map is used for memorizing and parking in the underground parking lot.
Wherein the attitude includes pitch angle, roll angle and yaw angle. The electronic map is not a complete electronic map, more semantic elements or characteristic points can be obtained along with the running of the vehicle in the underground parking garage, and the complete electronic map of the underground parking garage can be finally obtained by continuously updating the electronic map by utilizing the semantic elements and the characteristic points. The memory parking refers to a driving assisting function of searching a recorded fixed parking space in a parking lot by utilizing an electronic map and finally completing parking.
According to the technical scheme provided by the embodiment of the application, the electronic map is automatically generated under the condition that the vehicle enters the underground parking lot, and the environment type of the current position of the vehicle is determined based on the semantic elements, the element positions and the element types around the vehicle, namely whether the semantic elements of the current position of the vehicle are reliable or not is determined. And acquiring the environmental characteristic points around the vehicle under the condition that the environmental type of the current position is unreliable in semantic elements. And generating an electronic map for memorizing the vehicle current position based on the vehicle current pose, the element positions and element types of semantic elements around the vehicle and the environment characteristic points. The generation process of the electronic map does not need manual operation of a user, and is silent in the whole process, so that the learning cost of generating the electronic map required by memory parking is reduced, and the energy and time of the user are saved.
It should be noted that, the foregoing steps 201 to 203 are simple descriptions of the method for generating an electronic map provided in the embodiment of the present application, and the method for generating an electronic map provided in the embodiment of the present application will be described in more detail below with reference to fig. 3, taking an execution subject as an example of a vehicle-mounted terminal, and the method includes the following steps.
301. The vehicle-mounted terminal acquires a plurality of historical postures of the vehicle, signal quality of positioning signals and environmental information acquired by the vehicle.
Wherein the vehicle is an electric vehicle, a hybrid vehicle or a fuel vehicle. The plurality of historical postures of the vehicle refer to a plurality of postures of the vehicle in a period of time before the current moment, and the plurality of historical postures have time sequence. The attitude includes roll angle, pitch angle and yaw angle, and in the embodiment of the application, the pitch angle in the attitude is mainly used for detecting the ramp so as to determine whether the vehicle enters and leaves the ramp, and the roll angle and the yaw angle play an auxiliary role in the process of checking the ramp. The positioning signal is a satellite signal for positioning the vehicle, the signal quality is used for evaluating the advantages and disadvantages of the positioning signal, and the advantages and disadvantages of the positioning signal determine the accuracy of positioning the vehicle. In some embodiments, the signal quality of the positioning signal is determined by the carrier-to-noise ratio of the positioning signal and the number of active satellites. The environmental information collected by the vehicle refers to environmental information surrounding the vehicle for reflecting environmental conditions surrounding the vehicle, which in some embodiments is also referred to as visual environmental information or perceived environmental information.
In one possible implementation, the vehicle-mounted terminal acquires a plurality of historical postures of the vehicle through a posture sensor, acquires signal quality of a positioning signal through a positioning system, and acquires environmental information around the vehicle through an environmental sensor.
Wherein the attitude sensor is used to determine the attitude of the vehicle, in some embodiments the attitude sensor includes an inertial measurement unit (Inertial Measurement Unit, IMU) and a wheel speed meter. The positioning system is used for positioning the vehicle through the positioning signal, and the positioning system can determine the signal quality of the positioning signal, and in some embodiments, the positioning system is a GPS (Global Positioning System ) positioning system or a beidou positioning system, etc., which is not limited in this embodiment. The environmental sensor is used to collect environmental information around the vehicle, and accordingly, the environmental sensor is mounted around the vehicle, and in some embodiments, is a camera, and accordingly, the environmental sensor is also referred to as a vision sensor or a perception sensor. In some embodiments, the camera is a pan around camera.
In the embodiment, the attitude sensor, the positioning system and the environment sensor on the vehicle can be used for acquiring a plurality of historical attitudes of the vehicle, signal quality of positioning signals and surrounding environment information, hardware is not required to be additionally installed on the vehicle, and the scheme is low in application cost.
302. The in-vehicle terminal determines whether the vehicle enters an underground parking garage based on a plurality of historical poses of the vehicle, signal quality of the positioning signal, and the environmental information.
Among them, an underground parking garage refers to a building built underground for parking motor vehicles of various sizes. Underground parking lot includes ramp, access, and parking areas, and in the present embodiment, access to underground parking refers to access to a parking area.
In one possible embodiment, in a case where a plurality of historical postures of the vehicle indicate that the vehicle is driving in and out of a downward slope and the signal quality of the positioning signal is less than or equal to a preset signal quality, the vehicle-mounted terminal determines an environment type of a position where the vehicle is located based on the environment information. And under the condition that the environment type is reliable in semantic elements, the vehicle-mounted terminal determines that the vehicle enters the underground parking garage. And under the condition that a plurality of historical postures of the vehicle indicate that the vehicle is driven in but not driven out of a downward slope, or the signal quality of the positioning signal is larger than the preset signal quality, or the environment type is unreliable as a semantic element, the vehicle-mounted terminal determines that the vehicle does not enter an underground parking garage.
In this case, since it is generally necessary to pass a downward slope for entering the underground parking garage, the vehicle is driven into and into the downward slope, which means that the vehicle may enter the underground parking garage. Because the underground parking garage is located below the building, the building can shelter from the positioning signal, and the signal quality of the positioning signal is poor, and in the case that the signal quality of the positioning signal is less than or equal to the preset signal quality, the vehicle possibly enters the underground parking garage. The preset signal quality is set by a technician according to actual conditions, which is not limited in the embodiment of the present application. In the case where the positioning system is a GPS positioning system, a signal quality less than or equal to a preset signal quality is also referred to as GPS desquamation. The environment types comprise reliable semantic elements and unreliable semantic elements, the semantic elements and the unreliable semantic elements are specific to the scene of the underground parking lot, under the condition that the semantic elements are reliable, the probability of representing that a vehicle is in the underground parking lot is high, the semantic elements are directly utilized to generate an electronic map of the underground parking lot, and the reliability degree of the generated electronic map is high; under the condition that the semantic elements are unreliable, whether the vehicles are in the underground parking lot or not cannot be accurately identified, and the reliability degree of generating the electronic map of the underground parking lot by directly utilizing the semantic elements is low.
In the embodiment, the comprehensive judgment is performed by utilizing a plurality of historical postures of the vehicle, the signal quality of the positioning signals and the environment type of the position, so that whether the vehicle is in the underground parking garage can be accurately determined.
In order to more clearly describe the above embodiments, the above embodiments will be described below in sections.
The first part, the vehicle terminal, determines whether the vehicle is driving in and out of the downward ramp.
In one possible implementation manner, the gradient corresponding to the first gesture in the plurality of historical gestures is greater than or equal to the entrance slope angle, and the difference between the gradient corresponding to the first gesture and the gradient corresponding to the historical gesture before the preset duration is greater than or equal to the gradient difference threshold value, and the vehicle-mounted terminal determines that the vehicle is driven into the downward slope. And the gradient corresponding to a second gesture in the plurality of historical gestures is smaller than or equal to the slope outlet angle, the difference value between the gradient corresponding to the second gesture and the gradient corresponding to the historical gesture before the preset duration is larger than or equal to the gradient difference value threshold value, the vehicle-mounted terminal determines that the vehicle drives out of the downward ramp, and the acquisition time of the second gesture is after the first gesture.
The slope corresponding to the posture refers to the slope corresponding to the pitch angle in the posture, and the slope refers to the slope of the vehicle because the chassis and the ground are kept parallel in the normal running process of the vehicle, and the slope can be replaced by the pitch angle. The slope entering angle, the slope exiting angle, the gradient difference threshold value and the preset time length are all set by the technician according to actual conditions, and the embodiment of the application is not limited to the above.
In this embodiment, the slope of the vehicle is determined by using the historical posture of the vehicle, and the slope at different moments is used to determine whether the vehicle is driving in or out of the downward slope, so that the accuracy is high.
For example, the in-vehicle terminal determines whether the vehicle is driving on a downward slope by the following formula (1), and determines whether the vehicle is driving off the downward slope by the following formula (2).
(1)
(2)
Wherein,for the slope corresponding to the posture at the current moment, +.>For a gradient before a preset time period k +.>For entering the slope angle->For going out the slope angle, & lt & gt>Is a gradient difference threshold.
In one possible embodiment, the in-vehicle terminal determines a historical track of the vehicle based on the plurality of historical poses. The in-vehicle terminal determines whether the vehicle enters an underground parking garage based on the history track.
The historical track is not an actual track when the vehicle runs, but is continuously displayed on the posture of the vehicle at different moments, and the historical track can reflect the posture change condition of the vehicle. In some embodiments, the plurality of historical postures are a plurality of postures after the vehicle terminal detects that the vehicle starts to run on the downward slope, the gradient corresponding to any posture of the vehicle is detected to be greater than or equal to the entering angle, the difference between the gradient corresponding to the first posture and the gradient corresponding to the historical posture before the preset duration is greater than or equal to the gradient difference threshold, and the vehicle terminal determines that the vehicle is driving into the downward slope. The posture continuously acquired by the vehicle-mounted terminal after the vehicle enters the downward slope is the above-mentioned history posture. The vehicle-mounted terminal can generate a history track based on the acquired history gesture, update the history track according to the subsequently acquired history gesture, and continuously determine whether the vehicle enters the underground parking garage based on the updated history track in the process of updating the history track. Under the condition that the vehicle enters the underground parking garage is determined, the vehicle-mounted terminal can release the cached historical gesture so as to save storage resources.
In this embodiment, the historical track of the vehicle is determined based on the plurality of historical poses, and whether the vehicle enters the underground parking garage is determined based on the historical track, with high accuracy.
For example, the vehicle-mounted terminal splices the plurality of historical postures based on the acquisition time of the plurality of historical postures to obtain a historical track of the vehicle. The vehicle-mounted terminal inputs the historical track of the vehicle into a track recognition model, recognizes the historical track through the track recognition model, and determines whether the historical track is a track entering an underground parking garage. In the case that the history track is a track entering an underground parking garage, the vehicle-mounted terminal determines that the vehicle enters the underground parking garage; in the case where the history track is not a track entering the underground parking garage, the in-vehicle terminal determines that the vehicle has not entered the underground parking garage. The acquisition time refers to the time when the historical gesture is acquired.
For example, the vehicle-mounted terminal connects the plurality of historical postures according to the order from the early to the late of the acquisition time to obtain the historical track of the vehicle. The vehicle-mounted terminal inputs the historical track of the vehicle into a track recognition model, and track characteristics of the historical track are obtained by extracting track characteristics of the historical track through the track recognition model. And the vehicle-mounted terminal carries out full connection and normalization on the track characteristics through the track recognition model to obtain the probability that the historical track is the track entering the underground parking garage. And under the condition that the probability is greater than or equal to a probability threshold value, the vehicle-mounted terminal determines that the historical track is the track entering the underground parking garage. In the case where the probability is smaller than the probability threshold, the in-vehicle terminal determines that the history track is not a track entering the underground parking garage. In the case that the history track is a track entering an underground parking garage, the vehicle-mounted terminal determines that the vehicle enters the underground parking garage; in the case where the history track is not a track entering the underground parking garage, the in-vehicle terminal determines that the vehicle has not entered the underground parking garage. The probability threshold is set by a technician according to actual situations, which is not limited in the embodiment of the present application.
And the second part and the vehicle-mounted terminal determine whether the signal quality of the positioning signal is smaller than or equal to the preset signal quality.
In one possible implementation manner, the signal quality of the positioning signal includes a carrier-to-noise ratio and an effective satellite number, and the vehicle-mounted terminal determines that the signal quality of the positioning signal is less than or equal to a preset signal quality when the carrier-to-noise ratio of the positioning signal is less than or equal to a carrier-to-noise ratio threshold and the effective satellite number of the positioning signal is less than or equal to a satellite number threshold.
The carrier-to-noise ratio refers to the ratio of the average power of a signal to the average power of noise, and is a parameter used for representing the relation between carrier and carrier noise, and the carrier-to-noise ratio is used for representing the quality of the signal. The effective number of satellites refers to the number of satellites that can be utilized by the positioning system. The preset signal quality includes a carrier-to-noise ratio threshold rth and a satellite number threshold nth, which are set by a technician according to actual conditions, which are not limited in the embodiment of the present application.
In the embodiment, whether the signal quality of the positioning signal is smaller than or equal to the preset signal quality or not can be determined through the carrier-to-noise ratio of the positioning signal and the number of effective satellites, so that the efficiency and the accuracy are high.
And the third part, the vehicle-mounted terminal, determines the environment type of the position of the vehicle based on the environment information.
In one possible implementation manner, the vehicle-mounted terminal performs semantic recognition on the environment information to obtain semantic elements around the vehicle. And the vehicle-mounted terminal determines the environment type of the position of the vehicle based on the semantic elements around the vehicle.
Under the implementation mode, semantic elements around the vehicle can be obtained by carrying out semantic recognition on the environment information, the environment type of the position of the vehicle is classified by utilizing the semantic elements around the vehicle, and the accuracy of the environment type is high.
For example, the vehicle-mounted terminal inputs the environmental information into a semantic recognition model, and performs semantic recognition on the environmental information through the semantic recognition model to obtain semantic elements around the vehicle. The vehicle-mounted terminal determines semantic elements in N first adjacent areas around the vehicle based on element positions of the semantic elements around the vehicle, wherein N is a positive integer. The vehicle-mounted terminal determines the region type of each first adjacent region based on the element types of the semantic elements in N first adjacent regions around the vehicle, wherein the region type comprises strong semantic constraints and weak semantic constraints. And the vehicle-mounted terminal determines the environment type of the current position of the vehicle based on the region types of the N first adjacent regions.
The position of the semantic element refers to the relative position between the semantic element and the vehicle, and the position of the semantic element can be obtained from the environment information. The first adjacent area is a three-dimensional area around the vehicle, and the first adjacent area is an open area. N is set by the skilled person according to the actual situation, and the embodiment of the application is not limited to this. The strong semantic constraint and the weak semantic constraint are also aimed at the underground parking garage, the probability that the corresponding first adjacent area belongs to the underground parking garage is high by the strong semantic constraint, and the probability that the corresponding first adjacent area belongs to the underground parking garage cannot be judged by the weak semantic constraint.
In order to more clearly describe the above embodiment, the above embodiment will be described with reference to fig. 4 and 5.
Referring to fig. 4, comprising a ground surface 401 and an underground region 402, the underground region 402 comprises a hill exit point 4021 and a parking environment 4022, and at least one hill entry point 403 is included in the process from the ground surface 401 to the underground region 402. In the process of driving the vehicle from the ground 401 to the parking area environment 4022, the signal quality of the positioning signal may be less than or equal to the preset signal quality at the point a, or may be less than or equal to the preset signal quality at the point B. Whether the vehicle enters and exits the downward ramp or the signal quality of the positioning signal is less than or equal to the preset signal quality cannot be accurately determined by separately determining whether the vehicle enters the parking area 4022 (underground parking garage). In addition, as can also be seen from fig. 4, it is also not possible to accurately determine whether the vehicle enters the parking area 4022 (underground parking) in combination with the conditions that the vehicle is driving in and out of the downward slope and the signal quality of the positioning signal is less than or equal to the preset signal quality. Therefore, in the embodiment of the present application, a third condition for determining whether the vehicle enters the underground parking garage, that is, the above-described determination of the environment type based on the environment information, is also provided. The accuracy of judging whether the vehicle enters the underground parking garage or not by combining the three conditions is high.
Referring to fig. 5, taking an example in which the attitude sensor includes an inertial measurement unit and a wheel speed meter, the positioning system is a GPS positioning system, and the environmental sensor is a camera, the vehicle-mounted terminal determines a plurality of historical attitudes of the vehicle through the inertial measurement unit and the wheel speed meter during running of the vehicle. Whether the vehicle is driving into a downward slope is determined based on the plurality of historical poses. In the case where the vehicle is driven in and out of the downward slope, it is determined that the vehicle satisfies the first judgment condition for entering the underground parking garage. Meanwhile, the vehicle-mounted terminal detects the quality of the positioning signal of the GPS positioning system, and the signal quality of the positioning signal is obtained. In the case where the signal quality of the positioning signal is less than or equal to the preset signal quality (the signal quality is poor), it is determined that the vehicle satisfies the second judgment condition for entering the underground parking garage. The vehicle-mounted terminal collects environmental information around the vehicle through the camera, and determines the environment type of the position of the vehicle based on the environmental information. And under the condition that the environment type is reliable in semantic elements, the vehicle-mounted terminal determines that the vehicle meets a third judging condition for entering the underground parking garage. Under the condition that all three judging conditions are met, the vehicle-mounted terminal determines that the vehicle enters the underground parking garage.
The judgment of whether the vehicle enters the underground parking garage is a judging condition for starting to generate the electronic map, the judging process is automatically and silently executed by the vehicle-mounted terminal, and the user does not feel the judgment and does not influence the normal driving of the user.
303. In the case that the vehicle enters the underground parking garage, the vehicle-mounted terminal determines an environment type of the current position of the vehicle based on element parameters of semantic elements around the vehicle, wherein the element parameters comprise element positions and element types, and the environment type comprises that the semantic elements are reliable and the semantic elements are unreliable.
The semantic elements refer to environment elements with specific meanings, the element parameters comprise element positions and element types, and the element positions refer to relative positions between the semantic elements and vehicles. In the environment of an underground parking garage, element types of semantic elements include pillars, parking spaces, ground lines, parking garage road marks, vehicles and the like. The number of semantic elements around the vehicle is a natural number, that is, a non-negative integer that may be 0, 1, 2, 3 …, etc. In the case where the number of semantic elements around the vehicle is 0, the element parameters of the above semantic elements are null.
In one possible implementation manner, in a case that the vehicle enters the underground parking garage, the vehicle-mounted terminal determines semantic elements in N first neighboring areas around the vehicle based on element positions of the semantic elements around the vehicle, where N is a positive integer. The vehicle-mounted terminal determines the region type of each first adjacent region based on the element types of the semantic elements in N first adjacent regions around the vehicle, wherein the region type comprises strong semantic constraints and weak semantic constraints. And the vehicle-mounted terminal determines the environment type of the current position of the vehicle based on the region types of the N first adjacent regions.
The position of the semantic element refers to the relative position between the semantic element and the vehicle, and the position of the semantic element can be obtained from the environment information. The first adjacent area is a three-dimensional area around the vehicle, and the first adjacent area is an open area. N is set by the skilled person according to the actual situation, and the embodiment of the application is not limited to this. The strong semantic constraint and the weak semantic constraint are also aimed at the underground parking garage, the probability that the corresponding first adjacent area belongs to the underground parking garage is high by the strong semantic constraint, and the probability that the corresponding first adjacent area belongs to the underground parking garage cannot be judged by the weak semantic constraint.
In this embodiment, the semantic elements around the vehicle are divided into N first neighboring areas around the vehicle based on the element positions of the semantic elements around the vehicle. And determining the region type of each first adjacent region according to the element type of the semantic element in each first adjacent region. And the environment type of the current position of the vehicle is determined based on the region types of the plurality of adjacent regions, so that the accuracy of the environment type is higher.
In order to more clearly describe the above embodiments, the above embodiments will be described below in sections.
And the first part is used for determining semantic elements in N first adjacent areas around the vehicle based on element positions of the semantic elements around the vehicle under the condition that the vehicle enters the underground parking garage.
In a possible implementation manner, when the vehicle enters the underground parking garage, the vehicle-mounted terminal determines a first adjacent area to which the semantic elements around the vehicle belong based on element positions of the semantic elements around the vehicle, and obtains the semantic elements in the N first adjacent areas.
Wherein a semantic element belongs to a first neighborhood, and an element position representing the semantic element is located in the first neighborhood. In some embodiments, the first vicinity is in a range of 10 or 15 meters outward from the vehicle body. The location of the N first adjacent areas around the vehicle will vary with the vehicle location, for example, referring to fig. 6, where n=4 is taken as an example, the vehicle 600 includes four first adjacent areas 601-604, which are respectively a front adjacent area 601, a left adjacent area 602, a rear adjacent area 603, and a right adjacent area 604 of the vehicle 600.
In this embodiment, the first neighboring area to which the semantic element around the vehicle belongs is determined based on the element position of the semantic element around the vehicle, which facilitates the subsequent classification of the first neighboring area.
For example, for any one of the semantic elements around the vehicle, the in-vehicle terminal compares the element position of the semantic element with the region positions of the N first neighboring regions. And under the condition that the element position of the semantic element belongs to the region position of any one of the N first adjacent regions, the vehicle-mounted terminal belongs to the first adjacent region.
The second part and the vehicle-mounted terminal determine the region type of each first adjacent region based on the element types of semantic elements in N first adjacent regions around the vehicle.
In one possible implementation manner, for any one of the N first neighboring areas, the in-vehicle terminal determines the area type of the first neighboring area as a strong semantic constraint if a semantic element of a preset semantic type exists in the first neighboring area. And under the condition that the semantic elements of the preset semantic types do not exist in the first adjacent area, the vehicle-mounted terminal determines the area type of the first adjacent area as weak semantic constraint.
The preset semantic types are set by a technician according to actual conditions, and the embodiment of the application is not limited to the preset semantic types. For example, the preset semantic types include element types, such as pillars, parking spaces, crossed ground wires and the like, which are strongly associated with the underground parking lot. The element types such as common ground wires and the like do not belong to preset semantic types because the element types cannot be related to the underground parking field intensity.
In this embodiment, the classification of the first neighboring area is achieved by using the types of the semantic elements in the first neighboring area, and the classification efficiency is high.
For example, for any one of the N first neighboring areas, the in-vehicle terminal determines an element type of the semantic element within the first neighboring area. And under the condition that semantic elements of a preset semantic type exist in the first adjacent area, the vehicle-mounted terminal determines the area type of the first adjacent area as a strong semantic constraint. And under the condition that the semantic elements of the preset semantic types do not exist in the first adjacent area, the vehicle-mounted terminal determines the area type of the first adjacent area as weak semantic constraint.
And the third part and the vehicle-mounted terminal determine the environment type of the current position of the vehicle based on the region types of the N first adjacent regions.
In one possible implementation manner, in a case that at least M first neighboring regions exist in the N first neighboring regions, where the region types are strong semantic constraints, the in-vehicle terminal determines the environment type of the current position of the vehicle as a reliable semantic element, M < N, and M is a positive integer. And under the condition that at least M first adjacent areas with strong semantic constraint area types do not exist in the N first adjacent areas, the vehicle-mounted terminal determines the environment type of the current position of the vehicle as unreliable semantic elements.
In some embodiments, m=n-1, where n=4, that is, where the region type of at least three of the four first neighboring regions is a strong semantic constraint, the environment type of the current location of the vehicle is determined to be a reliable semantic element. In the case where the region types of three or less of the four first neighboring regions are strongly semantically constrained, the environment type of the current position of the vehicle is determined to be unreliable as a semantic element. In some embodiments, semantic element reliability is also referred to as semantic element sufficiency.
Optionally, the method for acquiring element parameters of the semantic elements around the vehicle includes:
in one possible implementation manner, the vehicle-mounted terminal performs semantic recognition on the environmental information collected by the vehicle to obtain element types of semantic elements around the vehicle, wherein the environmental information is used for reflecting environmental states around the vehicle. The in-vehicle terminal determines element positions of semantic elements around the vehicle based on the environment information.
The environment parameters are acquired by an environment sensor.
For example, the vehicle-mounted terminal inputs the environmental information into a semantic recognition model, and performs semantic recognition on the environmental information through the semantic recognition model to obtain semantic elements around the vehicle. And the vehicle-mounted terminal performs position identification on the environment information to obtain element positions of semantic elements around the vehicle.
Optionally, after step 303, the vehicle-mounted terminal performs steps 304 to 305 or performs step 306 described below according to the actual situation, which is not limited in the embodiment of the present application.
304. And under the condition that the environment type is unreliable, the vehicle-mounted terminal acquires the environment feature points around the vehicle.
The environmental characteristic points refer to points in the environment, which are obviously different from surrounding environmental elements. The environmental feature points have no specific meaning and are therefore not semantic elements. For example, the edges of roads, the textures of road cracks and object edges all have environmental feature points, while a pure white wall surface may not have environmental feature points. The environmental feature points are more common than the semantic elements, for example, there may be no post around the vehicle, but there may be a road crack on which the environmental feature points are present.
In a possible implementation manner, under the condition that the environment type is unreliable, the vehicle-mounted terminal performs feature point identification on the environment information collected by the vehicle to obtain environment feature points around the vehicle.
In the embodiment, under the condition that the environment type is unreliable, the characteristic points of the collected environment information can be identified, so that the environment characteristic points around the vehicle can be obtained, and the identification efficiency of the environment characteristic points is high.
Taking environmental information as an environmental image as an example, the vehicle-mounted terminal extracts characteristic points of the environmental image based on the distribution condition of pixel points in the environmental image to obtain environmental characteristic points around the vehicle. The distribution condition comprises an average pixel value of the pixel points and the pixel points in the environment image, a pixel value variance, a pixel value standard deviation and a pixel value difference value of the pixel points and the adjacent pixel points in the environment image.
For example, the vehicle-mounted terminal converts the environment image into a gray image, and extracts feature points of the gray image by adopting a preset operator to obtain environment feature points around the vehicle, wherein the preset operator is a Forstner operator, a SUSAN (Small Univalue Segment Assimilating Nucleus, small unified value segment absorption core) operator or a SIFT operator (Scale Invariant Feature Transform, scale-invariant feature transform).
In a possible implementation manner, under the condition that the environment type is unreliable, the vehicle-mounted terminal performs feature point identification on the environment information collected by the vehicle to obtain initial feature points around the vehicle. The vehicle-mounted terminal filters the initial feature points around the vehicle based on the feature point parameters of the initial feature points around the vehicle to obtain the environment feature points around the vehicle, wherein the environment feature points are the initial feature points with the feature point parameters meeting the preset parameter conditions, and the feature point parameters comprise at least one of feature point types, feature point priorities and feature point confidence degrees.
The preset parameter conditions are set by a technician according to actual situations, which is not limited in the embodiment of the present application.
In this embodiment, the feature point identification is performed on the environmental information to obtain the initial feature point around the vehicle, and then the initial feature point around the vehicle is filtered based on the feature point parameter of the initial feature point around the vehicle to obtain the environmental feature point around the vehicle, and part of the initial feature point is removed through the filtering step, so that the number of the environmental feature points is reduced on the premise of ensuring the stability of the environmental feature point, and the pressure of subsequent operation is reduced.
Taking environmental information as an environmental image as an example, the vehicle-mounted terminal extracts feature points of the environmental image based on the distribution condition of pixel points in the environmental image to obtain initial feature points around the vehicle. The vehicle-mounted terminal determines whether the characteristic point parameters of the initial characteristic points around the vehicle meet preset parameter conditions. And the vehicle-mounted terminal determines the initial characteristic points with the characteristic point parameters meeting the preset parameter conditions as environment characteristic points. For example, the feature point parameters include a feature point type, a feature point priority and a feature point confidence coefficient, and when the feature point type of any initial feature point is a preset feature point type, or the feature point priority is greater than or equal to the preset feature point priority, or the feature point confidence coefficient is greater than or equal to the preset confidence coefficient, the vehicle-mounted terminal determines the initial feature point as an environmental feature point.
305. The vehicle-mounted terminal generates an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environmental feature points, and the electronic map is used for memorizing and parking in the underground parking lot.
The position comprises a position and a posture, and the upper posture comprises a pitch angle, a roll angle and a yaw angle. In some embodiments, the current position of the vehicle is determined by a wheel speed meter and an inertial navigation unit. When the electronic map is not the complete electronic map, more semantic elements or characteristic points can be acquired along with the running of the vehicle in the underground parking garage, and the complete electronic map of the underground parking garage can be finally obtained by continuously updating the electronic map by utilizing the semantic elements and the characteristic points. In addition, in the process of generating the electronic map, some local indexes associated with the positions are added in the electronic map to perform feature retrieval, so that a large number of repeated storage can be avoided. The memory parking refers to a driving assisting function of searching a recorded fixed parking space in a parking lot by utilizing an electronic map and finally completing parking.
In one possible implementation manner, the vehicle-mounted terminal performs binding storage based on the current pose of the vehicle and element parameters and environment characteristic points of semantic elements around the vehicle to obtain the electronic map of the current position.
Under the implementation mode, under the condition that the environment type is unreliable in semantic elements, environment feature points are adopted to assist in building the electronic map so as to meet the dependence on the electronic map when the user is memorizing the parking.
For example, the vehicle-mounted terminal determines the position of the vehicle when the electronic map starts to be generated as the origin of the electronic map coordinate system, and then transfers the semantic elements and the environmental characteristic points to the electronic map coordinate system according to the change of the pose of the vehicle, so that the semantic elements and the environmental characteristic points are written into the map. In addition, when the electronic map is generated, the pose of the vehicle when the signal quality of the positioning signal is smaller than or equal to the preset signal quality is recorded and used as a reference of the electronic map coordinate system under the world coordinate system.
306. And under the condition that the environment type is reliable in semantic elements, generating an electronic map of the current position based on element parameters of the semantic elements around the vehicle and the current pose of the vehicle.
In one possible implementation manner, in the case that the environment type is reliable in semantic elements, the vehicle-mounted terminal determines whether there is an occluded target position around the vehicle. In the case that the target position exists around the vehicle, the vehicle-mounted terminal determines position description information of the target position based on the position type of the target position and element parameters of semantic elements around the target position. The vehicle-mounted terminal generates an electronic map of the current position based on element parameters of semantic elements around the vehicle, the current pose of the vehicle and the position description information of the target position.
The target position may be a position where a parking space is located, or may be a position where an obstacle is located, which is not limited in the embodiment of the present application.
In this embodiment, when the vehicle has an occluded target position, the element parameters of the semantic elements around the target position are used to generate the position description information of the target position, and the element parameters of the target position are replaced by the position description information, so that the map of the target position is built.
In order to more clearly describe the above embodiments, the above embodiments will be described below in sections.
And the first part, under the condition that the environment type is reliable in semantic elements, the vehicle-mounted terminal determines whether the occluded target position exists around the vehicle.
In one possible implementation, in a case where the environment type is that the semantic element is reliable, the in-vehicle terminal determines whether there is an occluded semantic element. In the case that the occluded semantic element exists, determining the position of the semantic element as a target position.
The method for shielding the semantic elements includes that the semantic elements are shielded by other semantic elements, such as parking spaces are shielded by vehicles, and also includes that the semantic elements are shielded by non-semantic element features, which is not limited in the embodiment of the present application. Non-semantic elements refer to unrecognized environmental elements.
And a second part, in the case that the target position exists around the vehicle, determining the position description information of the target position by the vehicle-mounted terminal based on the position type of the target position and element parameters of semantic elements around the target position.
The position description information records the topological relation of semantic elements around the target position, and most of false matching pairs obtained by neighbor searching due to inaccurate initial values can be filtered when the electronic map is used for matching, so that the robustness of semantic matching is greatly improved.
In a possible implementation manner, in a case that the target position exists around the vehicle, the vehicle-mounted terminal determines a topological relation of the semantic elements around the target position based on the element positions and the element types of the semantic elements around the target position, wherein the topological relation is used for representing the distribution situation of the semantic elements. And the vehicle-mounted terminal fuses the position type of the target position and the topological relation of semantic elements around the target position to obtain the position description information of the target position.
The position type is the same as the element type of the semantic element corresponding to the target position, for example, the target position is used for describing the characteristic of the semantic element corresponding to the target position, for example, when the target position is the position of the parking space, the type of the target position comprises a transverse parking space and a longitudinal parking space.
In such an embodiment, the element positions and element types of the semantic elements around the target position are utilized to determine the topological relationship of the semantic elements around the target position. The topological relation and the position type of the target position are fused to obtain the position description information of the target position, and the target position can be positioned by utilizing the position description information, so that the map of the blocked position is built.
For example, in the case where the target position exists around the vehicle, the in-vehicle terminal determines semantic elements in K second neighboring areas around the target position based on element positions of the semantic elements around the target position, K being a positive integer. The vehicle-mounted terminal determines the target element types of the second adjacent areas based on the element types of the semantic elements of the K second adjacent areas around the vehicle, wherein the target element types are element types meeting the preset semantic type conditions. And the vehicle-mounted terminal determines the topological relation of the semantic elements around the target position based on the relative position relation of the K second adjacent areas and the type of the target element. And the vehicle-mounted terminal splices the position type of the target position and the topological relation of semantic elements around the target position to obtain the position description information of the target position.
The preset semantic types are set by a technician according to actual conditions, and the embodiment of the application is not limited to the preset semantic types.
Taking k=8, the target position is the position of the parking space as an example, and the position description information of the parking space is composed of 8 topological relation descriptors and 9 horizontal/vertical flag bits. The longitudinal parking space starts from the opening direction of the parking space, the space around the parking space is divided into 8 second adjacent areas, 8 topological relation descriptors are corresponding to the space, and different marker bits are assigned to the topological relation descriptors according to the types of target elements, for example, the corresponding relation is 0-space, 1-grounding wire, 2-parking space and 3-column; the transverse parking space starts from the direction that the parking space opening rotates 90 degrees clockwise, and the construction mode of the position description information is the same as that of the longitudinal parking space. Referring to fig. 7, eight second adjacent areas 7011-7018 exist around the horizontal parking space 701, and eight second adjacent areas 7021-7028 exist around the vertical parking space 702. The topological relation is used for describing the arrangement sequence of the target element types corresponding to the eight second adjacent areas.
Referring to fig. 8, taking parking space 1 as an example, taking parking space 1 as a center, dividing the periphery of the parking space 1 into 8 second adjacent areas, describing in a counterclockwise sequence, and if no shielding exists right in front of the parking space 1, then the flag bit of the topological relation descriptor right in front is 0; a pillar exists at the left front of the parking space 1 as shielding, and the zone bit of the topological relation descriptor at the left front is 3; the left side, the left rear side and the rear side of the parking space 1 are provided with grounding wires as shielding, and the marker bits of the topological relation descriptors at the left side, the left rear side and the rear side are 1; the vehicles exist at the right rear, the right side and the right front of the parking space 1 as shielding, and the zone bits of the topological relation descriptors at the right rear, the right side and the right front are all 2; and the parking space 1 is a longitudinal parking space, and the transverse/longitudinal flag bit is 0. In combination, the position description information of the parking space 1 is 031112220.
And the third part and the vehicle-mounted terminal generate an electronic map of the current position based on element parameters of semantic elements around the vehicle, the current pose of the vehicle and the position description information of the target position.
In one possible implementation manner, the vehicle-mounted terminal performs binding storage based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and position description information of the target position to obtain an electronic map of the current position.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein in detail.
According to the technical scheme provided by the embodiment of the application, the electronic map is automatically generated under the condition that the vehicle enters the underground parking lot, and the environment type of the current position of the vehicle is determined based on the semantic elements, the element positions and the element types around the vehicle, namely whether the semantic elements of the current position of the vehicle are reliable or not is determined. And acquiring the environmental characteristic points around the vehicle under the condition that the environmental type of the current position is unreliable in semantic elements. And generating an electronic map for memorizing the vehicle current position based on the vehicle current pose, the element positions and element types of semantic elements around the vehicle and the environment characteristic points. The generation process of the electronic map does not need manual operation of a user, and is silent in the whole process, so that the learning cost of generating the electronic map required by memory parking is reduced, and the energy and time of the user are saved.
Compared with the prior art that a user is required to trigger an interaction instruction to start or stop generation of the electronic map, by adopting the technical scheme provided by the embodiment of the application, whether the vehicle enters the underground parking lot or not can be automatically and silently judged, and after the vehicle enters the underground parking lot, the generation of the electronic map is silently performed, so that the user does not feel in the whole process, and the driving of the user is not influenced.
Fig. 9 is a schematic structural diagram of an electronic map generating apparatus provided in an embodiment of the present application, referring to fig. 9, the apparatus includes: an environment type determining module 901, a feature point acquiring module 902 and an electronic map generating module 903.
The environment type determining module 901 is configured to determine, in a case where a vehicle enters an underground parking garage, an environment type of a current location of the vehicle based on element parameters of semantic elements around the vehicle, where the element parameters include an element location and an element type, and the environment type includes that the semantic elements are reliable and that the semantic elements are unreliable.
And the feature point obtaining module 902 is configured to obtain an environmental feature point around the vehicle when the environment type is unreliable.
The electronic map generating module 903 is configured to generate an electronic map of the current location based on the current pose of the vehicle, element parameters of semantic elements around the vehicle, and environmental feature points, where the electronic map is used for memorizing parking in the underground parking garage.
In a possible implementation manner, the environment type determining module 901 is configured to determine, when the vehicle enters the underground parking garage, semantic elements in N first neighboring areas around the vehicle based on element positions of the semantic elements around the vehicle, where N is a positive integer. Based on element types of semantic elements within N first neighboring regions around the vehicle, determining a region type of each of the first neighboring regions, the region type including a strong semantic constraint and a weak semantic constraint. Based on the region types of the N first adjacent regions, determining the environment type of the current position of the vehicle.
In a possible implementation manner, the environment type determining module 901 is configured to determine, for any one of the N first neighboring areas, an area type of the first neighboring area as a strong semantic constraint if a semantic element of a preset semantic type exists in the first neighboring area. And determining the region type of the first adjacent region as weak semantic constraint under the condition that the semantic element of the preset semantic type does not exist in the first adjacent region.
In a possible implementation manner, the environment type determining module 901 is configured to determine, in a case where there are at least M first neighboring regions of the N first neighboring regions, where the at least M region types are strong semantic constraints, that the environment type of the current position of the vehicle is reliable as a semantic element, M < N, and M is a positive integer. And determining the environment type of the current position of the vehicle as unreliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types do not exist in the N first adjacent areas.
In a possible implementation manner, the feature point obtaining module 902 is configured to perform feature point identification on the environmental information collected by the vehicle to obtain initial feature points around the vehicle when the environmental type is unreliable due to a semantic element. And filtering the initial feature points around the vehicle based on the feature point parameters of the initial feature points around the vehicle to obtain the environmental feature points around the vehicle, wherein the environmental feature points are the initial feature points with the feature point parameters conforming to the preset parameter conditions, and the feature point parameters comprise at least one of feature point types, feature point priorities and feature point confidence degrees.
In a possible implementation manner, the electronic map generating module 903 is further configured to, when the environment type is that the semantic element is reliable, generate the electronic map of the current location based on element parameters of the semantic element around the vehicle and the current pose of the vehicle.
In a possible implementation manner, the electronic map generating module 903 is configured to determine whether there is an occluded target location around the vehicle if the environment type is reliable due to the semantic element.
In the case where the target position exists around the vehicle, position description information of the target position is determined based on the position type of the target position and element parameters of semantic elements around the target position. And generating an electronic map of the current position based on element parameters of semantic elements around the vehicle, the current pose of the vehicle and the position description information of the target position.
In a possible implementation manner, the electronic map generating module 903 is configured to determine, in a case where the target location exists around the vehicle, a topological relationship of the semantic elements around the target location based on the element locations and the element types of the semantic elements around the target location, where the topological relationship is used to represent a distribution situation of the semantic elements. And fusing the position type of the target position and the topological relation of semantic elements around the target position to obtain the position description information of the target position.
In a possible implementation manner, the electronic map generating module 903 is configured to determine, when the target location exists around the vehicle, semantic elements in K second neighboring areas around the target location based on element positions of the semantic elements around the target location, where K is a positive integer. And determining the target element type of each second adjacent area based on the element types of the semantic elements of the K second adjacent areas around the vehicle, wherein the target element type is an element type meeting the preset semantic type condition. Based on the relative positional relationships of the K second neighboring areas and the target element type, determining the topological relationship of the semantic elements around the target position.
In one possible embodiment, the apparatus further comprises a position determination module for acquiring a plurality of historical poses of the vehicle, signal quality of the positioning signal, and environmental information acquired by the vehicle. Based on a plurality of historical poses of the vehicle, a signal quality of the positioning signal, and the environmental information, it is determined whether the vehicle enters an underground parking garage.
In one possible implementation manner, the position determining module is configured to determine, based on the environmental information, an environmental type of a position where the vehicle is located, when a plurality of historical postures of the vehicle indicate that the vehicle is driving in and out of a downward slope, and a signal quality of the positioning signal is less than or equal to a preset signal quality. In the event that the environment type is a reliable semantic element, it is determined that the vehicle is entering an underground parking garage. And determining that the vehicle does not enter the underground parking garage when the plurality of historical postures of the vehicle indicate that the vehicle enters but does not exit the downward ramp, or the signal quality of the positioning signal is greater than the preset signal quality, or the environment type is unreliable due to semantic elements.
In one possible implementation manner, the position determining module is further configured to determine that the vehicle is driving into a downward slope when a gradient corresponding to a first gesture in the plurality of historical gestures is greater than or equal to a driving-in angle, and a difference between the gradient corresponding to the first gesture and a gradient corresponding to a historical gesture before the preset duration is greater than or equal to a gradient difference threshold. And determining that the vehicle exits the downward ramp by determining that a gradient corresponding to a second gesture in the plurality of historical gestures is less than or equal to a slope exit angle, and a difference value between the gradient corresponding to the second gesture and a gradient corresponding to the historical gesture before the preset duration is greater than or equal to the gradient difference value threshold value, wherein the acquisition time of the second gesture is after the first gesture.
And determining that the signal quality of the positioning signal is smaller than or equal to the preset signal quality under the condition that the carrier-to-noise ratio of the positioning signal is smaller than or equal to a carrier-to-noise ratio threshold and the number of effective satellites of the positioning signal is smaller than or equal to a satellite number threshold.
In a possible implementation manner, the device further comprises an element parameter obtaining module, configured to perform semantic recognition on environmental information collected by the vehicle, so as to obtain element types of semantic elements around the vehicle, where the environmental information is used to reflect an environmental state around the vehicle. Based on the environmental information, element positions of semantic elements around the vehicle are determined.
It should be noted that: in the electronic map generating apparatus provided in the above embodiment, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the apparatus for generating an electronic map provided in the foregoing embodiment and the method embodiment for generating an electronic map belong to the same concept, and specific implementation processes of the apparatus and the method embodiment are detailed in the detailed description of the method embodiment, which is not repeated here.
According to the technical scheme provided by the embodiment of the application, the electronic map is automatically generated under the condition that the vehicle enters the underground parking lot, and the environment type of the current position of the vehicle is determined based on the semantic elements, the element positions and the element types around the vehicle, namely whether the semantic elements of the current position of the vehicle are reliable or not is determined. And acquiring the environmental characteristic points around the vehicle under the condition that the environmental type of the current position is unreliable in semantic elements. And generating an electronic map for memorizing the vehicle current position based on the vehicle current pose, the element positions and element types of semantic elements around the vehicle and the environment characteristic points. The generation process of the electronic map does not need manual operation of a user, and is silent in the whole process, so that the learning cost of generating the electronic map required by memory parking is reduced, and the energy and time of the user are saved.
The embodiment of the application also provides a vehicle, and fig. 10 is a schematic structural diagram of the vehicle provided by the embodiment of the application.
In general, the vehicle 1000 includes: one or more processors 1001 and one or more memories 1002.
The processor 1001 may include one or more processing cores, such as a 4-core processor, a 10-core processor, and so on. The processor 1001 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 1001 may also include a main processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1001 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 1001 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
Memory 1002 may include one or more computer-readable storage media, which may be non-transitory. Memory 1002 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 1002 is used to store at least one computer program for execution by processor 1001 to implement the method of generating an electronic map provided by the method embodiments in the present application.
Those skilled in the art will appreciate that the configuration shown in fig. 10 is not limiting of the vehicle 1000 and may include more or fewer components than shown, or may combine certain components, or may employ a different arrangement of components.
In addition, the apparatus provided by the embodiments of the present application may be a chip, a component, or a module, where the chip may include a processor and a memory connected to each other; the memory is used for storing instructions, and when the processor calls and executes the instructions, the chip can be caused to execute the method for generating the electronic map provided by the embodiment.
The present embodiment also provides a computer-readable storage medium having stored therein computer program code which, when run on a computer, causes the computer to perform the above-described related method steps to implement a method for generating an electronic map provided in the above-described embodiments.
The present embodiment also provides a computer program product, which when run on a computer, causes the computer to perform the above-mentioned related steps to implement a method for generating an electronic map provided in the above-mentioned embodiments.
The apparatus, the computer readable storage medium, the computer program product, or the chip provided in this embodiment are used to execute the corresponding method provided above, and therefore, the advantages achieved by the apparatus, the computer readable storage medium, the computer program product, or the chip can refer to the advantages of the corresponding method provided above, which are not described herein.
It will be appreciated by those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (13)
1. A method for generating an electronic map, the method comprising:
Under the condition that a vehicle enters an underground parking garage, determining semantic elements in N first adjacent areas around the vehicle based on element positions of the semantic elements around the vehicle, wherein N is a positive integer, and element parameters of the semantic elements comprise element positions and element types;
for any first adjacent region in the N first adjacent regions, determining the region type of the first adjacent region as a strong semantic constraint under the condition that semantic elements with the element type of a preset semantic type exist in the first adjacent region; determining the region type of the first adjacent region as weak semantic constraint under the condition that no semantic element with the element type being the preset semantic type exists in the first adjacent region, wherein the strong semantic constraint is used for indicating that the probability that the corresponding first adjacent region belongs to an underground parking lot is high, and the weak semantic constraint is used for indicating that whether the corresponding first adjacent region belongs to the underground parking lot cannot be judged;
determining the environment type of the current position of the vehicle as reliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types exist in the N first adjacent areas, wherein M is less than N and M is a positive integer; determining the environment type of the current position of the vehicle as unreliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types do not exist in the N first adjacent areas, wherein the reliable semantic elements and the unreliable semantic elements are respectively used for representing the reliability degree of directly generating the electronic map by utilizing the semantic elements;
Under the condition that the environment type is unreliable in semantic elements, carrying out feature point identification on the environment information acquired by the vehicle to obtain environment feature points around the vehicle, wherein the environment feature points refer to points with differences with surrounding environment elements in the environment;
and generating an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environmental feature points, wherein the electronic map is used for memorizing and parking in the underground parking lot.
2. The method according to claim 1, wherein, in the case that the environment type is unreliable, performing feature point recognition on the environment information collected by the vehicle, and obtaining the environment feature points around the vehicle includes:
under the condition that the environment type is unreliable in semantic elements, feature point identification is carried out on the environment information acquired by the vehicle, and initial feature points around the vehicle are obtained;
and filtering the initial feature points around the vehicle based on the feature point parameters of the initial feature points around the vehicle to obtain the environment feature points around the vehicle, wherein the environment feature points are the initial feature points with feature point parameters meeting the preset parameter conditions, and the feature point parameters comprise at least one of feature point types, feature point priorities and feature point confidence.
3. The method of claim 1, wherein in the event that the vehicle enters an underground parking garage, the method further comprises:
and under the condition that the environment type is reliable in semantic elements, generating an electronic map of the current position based on element parameters of the semantic elements around the vehicle and the current pose of the vehicle.
4. The method of claim 3, wherein, in the case where the environment type is that the semantic element is reliable, generating the electronic map of the current location based on element parameters of the semantic element around the vehicle and the current pose of the vehicle comprises:
determining whether a blocked target position exists around the vehicle under the condition that the environment type is reliable in semantic elements;
determining position description information of the target position based on the position type of the target position and element parameters of semantic elements around the target position when the target position exists around the vehicle;
and generating an electronic map of the current position based on element parameters of semantic elements around the vehicle, the current pose of the vehicle and the position description information of the target position.
5. The method of claim 4, wherein the determining location description information of the target location based on a location type of the target location and element parameters of semantic elements around the target location in the presence of the target location around the vehicle comprises:
determining a topological relation of semantic elements around the target position based on element positions and element types of the semantic elements around the target position when the target position exists around the vehicle, wherein the topological relation is used for representing the distribution situation of the semantic elements;
and fusing the position type of the target position and the topological relation of semantic elements around the target position to obtain the position description information of the target position.
6. The method of claim 5, wherein the determining the topological relationship of the semantic elements around the target location based on the element locations and element types of the semantic elements around the target location in the presence of the target location around the vehicle comprises:
determining semantic elements in K second adjacent areas around the target position based on element positions of the semantic elements around the target position when the target position exists around the vehicle, wherein K is a positive integer;
Determining target element types of the K second adjacent areas around the vehicle based on element types of semantic elements of the second adjacent areas, wherein the target element types are element types meeting preset semantic type conditions;
and determining the topological relation of semantic elements around the target position based on the relative position relation of the K second adjacent areas and the type of the target element.
7. The method of claim 1, wherein, in the event that the vehicle enters an underground parking garage, before determining semantic elements within N first vicinity around the vehicle based on element positions of semantic elements around the vehicle, the method further comprises:
acquiring a plurality of historical postures of the vehicle, signal quality of positioning signals and environmental information acquired by the vehicle;
based on a plurality of historical poses of the vehicle, a signal quality of the positioning signal, and the environmental information, it is determined whether the vehicle enters an underground parking garage.
8. The method of claim 7, wherein the determining whether the vehicle enters an underground parking garage based on a plurality of historical poses of the vehicle, signal quality of the positioning signals, and the environmental information comprises:
Determining an environment type of a position where the vehicle is located based on the environment information when a plurality of historical postures of the vehicle indicate that the vehicle is driven in and out of a downward slope and the signal quality of the positioning signal is less than or equal to a preset signal quality; determining that the vehicle enters an underground parking garage under the condition that the environment type is reliable in semantic elements;
and determining that the vehicle does not enter an underground parking garage under the condition that a plurality of historical postures of the vehicle indicate that the vehicle enters but does not exit a downward slope, or the signal quality of the positioning signal is larger than the preset signal quality, or the environment type is unreliable due to semantic elements.
9. The method of claim 8, wherein the signal quality of the positioning signal comprises a carrier-to-noise ratio and an effective number of satellites, the method further comprising:
determining that the vehicle is driven into a downward slope when the gradient corresponding to a first gesture in the plurality of historical gestures is greater than or equal to a slope entering angle and the difference between the gradient corresponding to the first gesture and the gradient corresponding to the historical gesture before a preset duration is greater than or equal to a gradient difference threshold;
The gradient corresponding to a second gesture in the plurality of historical gestures is smaller than or equal to a slope outlet angle, the difference value between the gradient corresponding to the second gesture and the gradient corresponding to the historical gesture before the preset time period is larger than or equal to the gradient difference value threshold value, the condition that the vehicle drives out of a downward ramp is determined, and the acquisition time of the second gesture is after the first gesture;
and determining that the signal quality of the positioning signal is smaller than or equal to the preset signal quality under the condition that the carrier-to-noise ratio of the positioning signal is smaller than or equal to a carrier-to-noise ratio threshold and the number of effective satellites of the positioning signal is smaller than or equal to a satellite number threshold.
10. The method according to claim 1, wherein the method for acquiring element parameters of semantic elements around the vehicle comprises:
carrying out semantic recognition on the environment information acquired by the vehicle to obtain element types of semantic elements around the vehicle, wherein the environment information is used for reflecting the environment state around the vehicle;
element positions of semantic elements around the vehicle are determined based on the environmental information.
11. An electronic map generating apparatus, characterized in that the apparatus comprises:
The environment type determining module is used for determining semantic elements in N first adjacent areas around the vehicle based on element positions of the semantic elements around the vehicle under the condition that the vehicle enters an underground parking lot, N is a positive integer, and element parameters of the semantic elements comprise element positions and element types; for any first adjacent region in the N first adjacent regions, determining the region type of the first adjacent region as a strong semantic constraint under the condition that semantic elements with the element type of a preset semantic type exist in the first adjacent region; determining the region type of the first adjacent region as weak semantic constraint under the condition that no semantic element with the element type being the preset semantic type exists in the first adjacent region, wherein the strong semantic constraint is used for indicating that the probability that the corresponding first adjacent region belongs to an underground parking lot is high, and the weak semantic constraint is used for indicating that whether the corresponding first adjacent region belongs to the underground parking lot cannot be judged; determining the environment type of the current position of the vehicle as reliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types exist in the N first adjacent areas, wherein M is less than N and M is a positive integer; determining the environment type of the current position of the vehicle as unreliable semantic elements under the condition that at least M first adjacent areas with strong semantic constraint area types do not exist in the N first adjacent areas, wherein the reliable semantic elements and the unreliable semantic elements are respectively used for representing the reliability degree of directly generating the electronic map by utilizing the semantic elements;
The characteristic point acquisition module is used for carrying out characteristic point identification on the environmental information acquired by the vehicle to obtain environmental characteristic points around the vehicle, wherein the environmental characteristic points are points with differences from surrounding environmental elements in the environment;
the electronic map generation module is used for generating an electronic map of the current position based on the current pose of the vehicle, element parameters of semantic elements around the vehicle and environment feature points, and the electronic map is used for memorizing and parking in the underground parking lot.
12. A vehicle, characterized in that the vehicle comprises:
a memory for storing executable program code;
a processor for calling and running the executable program code from the memory to cause the vehicle to perform the method of generating an electronic map as claimed in any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that at least one program code is stored in the computer-readable storage medium, which program code is loaded by a processor and executes the method of generating an electronic map according to any one of claims 1 to 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311399921.5A CN117131150B (en) | 2023-10-26 | 2023-10-26 | Electronic map generation method, device, vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311399921.5A CN117131150B (en) | 2023-10-26 | 2023-10-26 | Electronic map generation method, device, vehicle and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117131150A CN117131150A (en) | 2023-11-28 |
CN117131150B true CN117131150B (en) | 2023-12-26 |
Family
ID=88863167
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311399921.5A Active CN117131150B (en) | 2023-10-26 | 2023-10-26 | Electronic map generation method, device, vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117131150B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118225075A (en) * | 2024-05-27 | 2024-06-21 | 长城汽车股份有限公司 | Parking lot map generation method, electronic equipment and vehicle |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112484744A (en) * | 2020-12-07 | 2021-03-12 | 广州小鹏自动驾驶科技有限公司 | Evaluation method and device for autonomous parking semantic map |
DE102020213831A1 (en) * | 2020-11-03 | 2022-05-05 | Volkswagen Aktiengesellschaft | Method for determining an existence probability of a possible element in an environment of a motor vehicle, driver assistance system and motor vehicle |
CN115146013A (en) * | 2022-06-16 | 2022-10-04 | 集度科技有限公司 | Vehicle parking memory map display method, device, equipment and storage medium |
CN115493602A (en) * | 2022-09-28 | 2022-12-20 | 智道网联科技(北京)有限公司 | Semantic map construction method and device, electronic equipment and storage medium |
EP4124828A1 (en) * | 2021-07-28 | 2023-02-01 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Map processing method and apparatus |
WO2023071029A1 (en) * | 2021-11-01 | 2023-05-04 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and apparatus, and electronic device and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111274974B (en) * | 2020-01-21 | 2023-09-01 | 阿波罗智能技术(北京)有限公司 | Positioning element detection method, device, equipment and medium |
-
2023
- 2023-10-26 CN CN202311399921.5A patent/CN117131150B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102020213831A1 (en) * | 2020-11-03 | 2022-05-05 | Volkswagen Aktiengesellschaft | Method for determining an existence probability of a possible element in an environment of a motor vehicle, driver assistance system and motor vehicle |
CN112484744A (en) * | 2020-12-07 | 2021-03-12 | 广州小鹏自动驾驶科技有限公司 | Evaluation method and device for autonomous parking semantic map |
EP4124828A1 (en) * | 2021-07-28 | 2023-02-01 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Map processing method and apparatus |
WO2023071029A1 (en) * | 2021-11-01 | 2023-05-04 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and apparatus, and electronic device and storage medium |
CN115146013A (en) * | 2022-06-16 | 2022-10-04 | 集度科技有限公司 | Vehicle parking memory map display method, device, equipment and storage medium |
CN115493602A (en) * | 2022-09-28 | 2022-12-20 | 智道网联科技(北京)有限公司 | Semantic map construction method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
动态环境下基于深度学习的语义SLAM 算法;郑思诚 等;《计算机应用》;第41卷(第10期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117131150A (en) | 2023-11-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
CN106873441A (en) | The method and system of electron assistant track entrance | |
CN112967283B (en) | Target identification method, system, equipment and storage medium based on binocular camera | |
CN113561963B (en) | Parking method and device and vehicle | |
CN117131150B (en) | Electronic map generation method, device, vehicle and storage medium | |
CN112444258A (en) | Method for judging drivable area, intelligent driving system and intelligent automobile | |
CN111401255A (en) | Method and device for identifying divergent intersection | |
CN114194180A (en) | Method, device, equipment and medium for determining auxiliary parking information | |
CN115205803A (en) | Automatic driving environment sensing method, medium and vehicle | |
CN115402322A (en) | Intersection driving assistance method and system, electronic device and storage medium | |
CN111599217B (en) | Autonomous parking system architecture, architecture implementation method, terminal and storage medium | |
CN110784680B (en) | Vehicle positioning method and device, vehicle and storage medium | |
CN113954834A (en) | Lane changing planning method and vehicle-mounted device | |
CN112185157A (en) | Roadside parking space detection method, system, computer equipment and storage medium | |
CN114722931A (en) | Vehicle-mounted data processing method and device, data acquisition equipment and storage medium | |
CN113762030A (en) | Data processing method and device, computer equipment and storage medium | |
CN112706159A (en) | Robot control method and device and robot | |
CN116503482B (en) | Vehicle position acquisition method and device and electronic equipment | |
CN115861976B (en) | Vehicle control method and device and vehicle | |
EP4336467A1 (en) | Method and apparatus for modeling object, storage medium, and vehicle control method | |
CN117593719A (en) | Parking space labeling method, model training method, parking method and related devices | |
CN118323110A (en) | Method, device, equipment and readable storage medium for generating parking and feature map | |
CN113899378A (en) | Lane changing processing method and device, storage medium and electronic equipment | |
CN118230593A (en) | Parking space detection method, electronic equipment, storage medium and vehicle | |
CN114419602A (en) | Traffic light identification method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |