CN115164928A - Navigation method, system and vehicle based on local relative map passing intersection - Google Patents
Navigation method, system and vehicle based on local relative map passing intersection Download PDFInfo
- Publication number
- CN115164928A CN115164928A CN202210862262.3A CN202210862262A CN115164928A CN 115164928 A CN115164928 A CN 115164928A CN 202210862262 A CN202210862262 A CN 202210862262A CN 115164928 A CN115164928 A CN 115164928A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- intersection
- map
- information
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
Abstract
The invention discloses a navigation method and a system for passing through an intersection based on a local relative map, wherein the navigation method comprises the following steps: acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when navigation is performed on the adjacent intersection, wherein the relative map does not include longitude and latitude data; determining the vehicle course according to the positioning module, and matching the vehicle course with the road course to determine the road on which the vehicle runs currently; identifying peripheral information of a vehicle running on a current road, and determining a target lane of the vehicle on the current road according to the peripheral information and the relative map data; and outputting crossing guiding line information based on the target lane, and navigating vehicles to pass through the crossing according to the crossing guiding line information. The invention does not depend on the longitude and latitude information of the map, uses the local relative map and outputs the guide lines in the road junction, and compared with the method of simply sensing the passing road junction, the invention does not depend on whether vehicles in the front can pass or not and does not depend on the type of the road junction.
Description
Technical Field
The invention relates to the field of map navigation, in particular to a method and a system for navigating through intersections based on local relative maps.
Background
In order to reduce the fatigue feeling of the driver and improve the driving comfort, the vehicle can realize vehicle auxiliary driving in an adaptive cruise mode. Different from a common cruise system, the self-adaptive cruise system can automatically lock the speed of a front vehicle, accelerate along with the acceleration of the front vehicle, decelerate along with the deceleration of the front vehicle, and is more dependent on a head vehicle.
The self-adaptive cruise-assisted automatic driving is realized by millimeter wave radar detection, a camera detection mode and a mode of fusing millimeter waves and a camera. The millimeter wave radar mode is limited by whether a vehicle exists in front or not, and if no vehicle exists, the function use is limited. The mode of adopting the camera is easily influenced by the environment, and the distance detection precision is not so high compared with that of a millimeter wave radar.
The current automatic driving auxiliary system usually adopts a mode of millimeter wave radar plus a front view camera to realize self-adaptive cruise, and can comprehensively cover the scenes of expressways and most scenes of urban expressways. In the intersection scene, assuming that no vehicle exists in front of the vehicle, a lane line is detected through a camera, the lane line is output, and then a local path is planned by the prediction and planning control module so that the vehicle can drive along the planned out-of-track line. The planning of the trajectory line depends on the recognition of the lane line, and after the stopping range is exceeded, the lane line is usually not arranged in the intersection, the lane line is compensated for a certain distance in the virtual brain of the planning and control module, and then the algorithm trajectory line passes through the intersection. However, the method is limited in that the lane line energy prolonged by brain complement can be connected with the lane line of the object, and once the connection cannot be carried out, the road can not pass through the intersection; and can only be used for straight going and can not be used for left turning and right turning. Another method for passing through the intersection in the intersection scene is to assume that the vehicle in front is also going to pass through the intersection, detect and track the vehicle in front through a camera and a millimeter wave radar, and pass through the intersection following the vehicle. However, the number of vehicles in the intersection is large, and the tracking of the front vehicle passing through the intersection is easy to cause an emergency situation to cause target tracking.
Therefore, the prior art has great limitation in crossing by means of supplementing lane lines or following vehicles, and cannot pass when facing left-turn, right-turn and large special-shaped crossings in the crossing. The crossroads are often large due to the limitation of vehicle perception, and the detection distance of the camera to the lane line is often limited. Due to limited regulation and restriction, the high-precision map of the urban area cannot provide a high-precision map carrying latitude and longitude information at present.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for navigating through an intersection based on a local relative map, which can assist a vehicle to navigate through the intersection by using the map.
In a first aspect of the present invention, a method for navigating through an intersection based on a local relative map is provided, which includes:
acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when navigation approaches the intersection, wherein the relative map does not comprise longitude and latitude data;
determining the vehicle course according to the positioning module, and matching the vehicle course with the road course to determine the road on which the vehicle runs currently;
identifying peripheral information of a vehicle running on a current road, and determining a target lane of the vehicle on the current road according to the peripheral information and the relative map data;
and outputting the crossroad guiding line information based on the target lane, and navigating the vehicle to pass through the crossroad according to the crossroad guiding line information.
Optionally, the method for generating intersection map index information and relative map data includes:
collecting image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data;
intercepting the vectorized map data to generate relative map data of intersections and intersection index information;
pushing intersection index information and intersection center coordinates to a navigation map as interest points of the navigation map;
the vectorized map comprises at least one of information of a lane line, a traffic light, a street lamp, a stop line, a zebra crossing, a road edge, a crossing range, a crossing leading line and a road course.
Optionally, the matching the vehicle heading with the road heading to determine the road on which the vehicle is currently traveling comprises:
determining the course of the vehicle according to the course information of the GPS data of the vehicle, and acquiring the road course information of all roads according to the intersection map; and if the vehicle course is similar to or the same as that of a certain road of the intersection relative to the map, determining that the certain road in the relative map is the road on which the vehicle runs currently.
Optionally, the determining that the vehicle is located in the target lane of the current road according to the surrounding information and the relative map data includes:
and acquiring vehicle peripheral information by using the vehicle-mounted camera and the laser radar, processing the vehicle peripheral information into map data and then matching the map data with the relative map data, and positioning the specific lane position of the road where the vehicle is positioned by using the laser radar and/or the vehicle-mounted camera after successfully matching attribute data of ground objects contained in the vehicle peripheral information with partial data in the relative map data.
Optionally, the matching of the vehicle periphery information with the relative map data after processing the vehicle periphery information into the map data includes:
and identifying whether the attribute information in the vehicle periphery information is matched with the position of the attribute data in the map data, and determining the position of the vehicle in the relative map.
In a second aspect of the present invention, there is provided a navigation system for passing an intersection based on a local relative map, comprising:
the loading module is used for acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when the navigation approaches the intersection, wherein the relative map does not include longitude and latitude data;
the road determining module is used for determining the vehicle course according to the positioning module and matching the vehicle course with the road course so as to determine the road on which the vehicle runs at present;
the lane determining module is used for identifying the peripheral information of the vehicle running on the current road and determining a target lane of the vehicle on the current road according to the peripheral information and the relative map data;
and the navigation module is used for outputting the crossroad guidance line information based on the target lane and navigating the vehicle to pass through the crossroad according to the crossroad guidance line information.
In a third aspect of the present invention, a method for navigating through an intersection based on a local relative map is provided, which includes:
relative map data and intersection map index information of a plurality of intersections are constructed in advance and are associated to a navigation map;
displaying driving navigation, and loading relative map data according to intersection map index information corresponding to an intersection when driving to approach the intersection;
determining a road on which a current vehicle runs based on the current vehicle course, identifying the peripheral information of the road, converting the peripheral information into map data to be matched with the relative map data, and determining a target lane of the vehicle on the current road after matching;
and outputting the crossing internal guide line information based on the target lane, and navigating the vehicle to pass through the crossing according to the crossing internal guide line information and the relative map data.
Optionally, the method for constructing the intersection map index information and the relative map data includes:
collecting image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data;
intercepting the vectorized map data to generate relative map data of intersections and intersection index information;
pushing intersection index information and intersection center coordinates to a navigation map as interest points of the navigation map;
the vectorized map comprises at least one of lane lines, traffic lights, street lamps, stop lines, zebra crossings, road edges, crossing ranges, crossing leading lines and road headings.
In a fourth aspect of the invention, there is provided a vehicle comprising a processor, a memory and a computer program stored on the memory and operable on the processor, the computer program, when executed by the processor, implementing a method as provided in the first aspect of the invention or a method as provided in the third aspect of the invention.
In a fifth aspect of the invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a computer, performs the method as provided in the first aspect of the invention or the method as provided in the third aspect of the invention.
The invention does not depend on the longitude and latitude information of the map, uses the local relative map, utilizes the matching of the perception information and the local relative map to realize the positioning of the vehicle in the range of the current intersection, and outputs the guide lines in the intersection to assist in passing various intersections. Compared with the situation that the vehicle passes through the intersection by simply sensing, more scenes of the intersection can be covered, and the condition that whether a vehicle passes through the front or not and the type of the intersection are not depended on is avoided.
Drawings
Fig. 1 is a schematic flow chart of a navigation method for passing through an intersection based on a local relative map according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a process for constructing a local relative map according to an embodiment of the present invention;
FIG. 3 is a block diagram of a navigation system for navigating through intersections based on local relative maps in an embodiment of the present invention;
fig. 4 is a schematic flow chart of another navigation method for passing through an intersection based on a local relative map according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As known from the related art, the automatic driving method in the prior art usually uses the sensing capability of the camera to identify the lane line of the current intersection or track the vehicle ahead to pass through the intersection. All have certain limitation, receive the restriction of camera perception ability, often can not see clearly to crossing lane line, track the vehicle and often lose when not having lane line auxiliary information.
In addition, a global high-precision map is utilized, the lane where the vehicle is located is distinguished through positioning and sensing, and then the vehicle is assisted to pass through the intersection through intersection guide line information of the global high-precision map. However, the global high-precision map is limited by the safety requirements of relevant regulations, cannot be provided in the urban area, cannot use relevant functions in the urban area, and is very inconvenient to use.
Therefore, the method adopts a local relative coordinate map mode, map data of local coordinates without longitude and latitude information is provided only after the vehicle enters a certain range of the intersection, the position of the vehicle at the intersection is positioned through sensing of a camera and a laser radar and matching of map elements, the passing of the vehicle through the intersection is assisted, and a brand-new navigation mode is provided.
Referring to fig. 1, the present invention provides a method for navigating through an intersection based on a local relative map, comprising:
step 110: and acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when the navigation approaches the intersection, wherein the relative map does not include longitude and latitude data.
The automatic driving assistance system acquires the navigation information in real time according to the navigation driving. Intersection locations on the navigation route can thus be identified. For example, the relative map is invoked at a relative distance L from the intersection. The map index can quickly call the relative map data corresponding to the intersections in the navigation map, and the relative map data and the navigation map can be bound in an index mode. The relative map can be loaded under preset conditions when the navigation map is operated. The relative map is constructed based on the sensing technology of the camera and the laser radar, so that the relative map does not contain longitude and latitude data, but a Cartesian coordinate system map is established based on sensing, and a WGS84 coordinate system is adopted in the navigation map.
The relative map is formed by sensing scene data of each intersection in advance by adopting a millimeter wave radar and a front-view camera, for example, track lines of vehicles running to different directions on different lanes of the intersection are constructed, and a local path is formed. Based on the method, the driving path can still be planned under the condition of no lane line and no front vehicle.
Step 120: and determining the vehicle course according to the positioning module, and matching the vehicle course with the road course to determine the road on which the vehicle runs currently.
Determining the course of the vehicle according to the course information in the GPS data of the vehicle, and acquiring the course information of all roads according to the intersection map; and if the vehicle course is similar to or the same as that of a certain road of the intersection relative to the map, determining that the certain road in the relative map is the road on which the vehicle runs currently.
In one embodiment, the vehicle heading information is obtained by a GPS positioning module of the vehicle, such as the included angle between the centroid speed and the horizontal axis of the vehicle in the ground coordinate system XOY. And then calculating the road on which the vehicle is positioned by matching the vehicle course with the road course. It will be appreciated that the road is a parallel bidirectional lane, and the directions of travel are opposite, so that navigation requires determining the particular road to be traveled.
Step 130: and identifying the peripheral information of the vehicle running on the current road, and determining the target lane of the vehicle on the current road according to the peripheral information and the relative map data.
When a particular road is determined, then a particular lane needs to be determined. The lanes are generally divided into a straight lane, a left-turn lane and a right-turn lane. If the specific lane is not determined, the specific navigation guidance cannot be performed.
In this step, information such as lane lines, traffic lights, street lights, stop lines, zebra crossings, road edges, etc. may be identified using a camera and a laser radar. For example, the attributes included in the lane line include a lane edge line, a lane boundary line, and a lane center line, and the common attributes include a solid line, a dotted line, and a double yellow line; by identifying this type of lane marking autopilot, the current lane position can be identified. The traffic light comprises red light, green light and yellow light, and the vehicle runs based on the traffic light during navigation assistance. The information such as street lamps, stop lines, zebra crossings and road edges can be used for guiding an automatic driving assistance system to control the vehicle to run, and meanwhile, the information can be combined with a laser radar based on the information to identify obstacles and the like, so that the vehicle can be better controlled to pass.
The laser radar is not only used for avoiding obstacles, but also can position the vehicle at the position of the lane based on a laser radar ranging mode in some special scenes. The laser radar can measure the distance of the two sides of the vehicle, the lane width is fixed, and the current lane position of the vehicle can be judged. Similarly, the laser radar can also calculate the distance of the vehicle relative to the intersection by identifying the street lamp position and the road edge at the intersection, and can calculate and calculate within a certain distance so as to judge the lane position of the road where the vehicle is located. The laser radar and the camera can continuously use the navigation map to execute the functions of road identification, obstacle avoidance and the like in the automatic driving mode after passing through the intersection. The vehicle can also be navigated to travel based on the point cloud data, if possible.
Step 140: and outputting the crossroad guiding line information based on the target lane, and navigating the vehicle to pass through the crossroad according to the crossroad guiding line information.
Since the relative map of the intersection is known, it is possible to output a guide line based on the position of the vehicle in the current relative map, thereby navigating the vehicle to travel. The guideline information may be planned out using known navigation techniques when constructing the relative map. Of course, the guidance line information may be output along with the vehicle driving plan after the specific lane position of the vehicle is determined.
For better understanding of the present invention, please refer to fig. 2, in which fig. 2 is a flow chart of a method for generating intersection map index information and relative map data. The method for generating the intersection map index information and the relative map data comprises the following steps:
step 210: and acquiring image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data.
A plurality of data information of the intersection are collected in advance, and a relative map is constructed. For example, a camera is used for collecting image data of intersections, a laser radar is used for collecting point cloud data of the intersections, and vectorized map data are formed by using the data. The vehicle body attitude data comprises vehicle speed, acceleration, angular speed, roll angle, pitch angle and the like, and is beneficial to vehicle navigation calculation and planning of vehicle guide lines.
In some embodiments, the vectorized map includes at least one of lane lines, traffic lights, street lights, stop lines, zebra crossings, road edges, intersection ranges, guidance lines in intersections, and road headings to match the location of the vehicle.
Step 220: and intercepting the vectorized map data to generate relative map data of intersections and intersection index information.
And intercepting the map data initially acquired and constructed to form map data of a single intersection, and deleting other data to form local relative map data corresponding to the intersection. The intersection index may be implemented in the form of numbers, labels, e.g., in an index table of numbers corresponding to intersection relative map data, etc. Of course, the intersection name may be in an index form such as intersection name-corresponding relative map data.
Step 230: and pushing the intersection index information and the intersection center coordinates to a navigation map as the interest points of the navigation map.
In order to facilitate navigation and data loading, the intersection relative map data and the navigation map are bound, and intersection index information and an intersection center point are given to the navigation map data to serve as an interest point of the navigation map.
Based on the above, it can be understood that when a vehicle drives to an intersection, image information and point cloud data of the intersection can be acquired through a camera or a laser radar, and are nearly the same as data for creating a relative map, so that the acquired peripheral information (including the intersection and the periphery thereof) of the vehicle at the current intersection can be matched with map data in the relative map, and the position of a lane where the vehicle on the current road is located can be judged after matching. Especially when one of the camera or the laser radar does not work well, the lane where the vehicle is located can be better located by performing data matching. The camera can determine the lane by identifying information such as lane lines of a road where a vehicle runs, and the camera can perform information interaction with the relative map data, so that which lane of the relative map data is used for intersection navigation is determined.
Further, in the step 130, the determining that the vehicle is located in the target lane of the current road according to the surrounding information and the relative map data includes:
and acquiring vehicle surrounding information by using the vehicle-mounted camera and the laser radar, processing the vehicle surrounding information into map data, matching the map data with the relative map data, and positioning the specific lane position of the road where the vehicle is located by using the laser radar and/or the vehicle-mounted camera after the attribute data of the ground objects (the ground and the objects) contained in the vehicle surrounding information is successfully matched with part of data in the relative map data.
The above description of the steps is combined, and the purpose of the step is to match the intersection and surrounding image information and laser radar information acquired by the current vehicle with the constructed relative map data. Therefore, in this step, the vehicle-mounted camera and the laser radar respectively acquire image data and point cloud data, then vectorize the image data and the point cloud data, and output map data identical to the relative map data, wherein the data content of the map data can be at least partially matched with part of the relative map data. Illustratively, the lane lines of the two are matched, and a part of the point cloud data of the two is matched. After matching, the position of the vehicle in the data sensed by the current camera and the laser radar can be determined, which is equivalent to the position in the relative map, so that the specific lane position of the vehicle can be determined.
The attribute data of the feature included in the vehicle periphery information includes attributes of information such as a lane line, a traffic light, a street lamp, a stop line, a zebra crossing, a road edge, and the like, including but not limited to type, number, distance, and the like. And identifying whether the attribute information in the vehicle periphery information is matched with the position of the attribute data in the map data, and determining the position of the vehicle in the relative map. For example, if there are four lane lines, three lanes, one lane line on the left side, and three lane lines on the right side in the vehicle peripheral information, it may be determined that the vehicle is currently in the left-turn lane and the first lane on the left side; and (4) recognizing that obstacles are arranged on two sides of a right lane entering the tutoring from the point cloud data, and driving along the guide line if the front is smooth.
The invention can realize the positioning of the vehicle in the current intersection range, and output the guide lines in the intersection based on the local relative map so as to assist in passing various intersections. Compared with the method of simply sensing the crossing, the method has the advantages that more crossing scenes can be covered, the method does not depend on whether vehicles pass in front or not, and the method can assist in passing through the crossing without depending on the type of the crossing, such as a large-scale crossing, a multi-branch crossing and the like.
Referring to fig. 3, the present invention further provides a navigation system based on local relative maps passing through intersections, including:
the loading module 31 is configured to acquire navigation information, and when a navigation approaches an intersection, load relative map data according to intersection map index information corresponding to the intersection, where the relative map does not include longitude and latitude data. The relative map adopts a Cartesian coordinate system.
And the road determining module 32 is used for determining the vehicle heading according to the positioning module and matching the vehicle heading with the road heading so as to determine the road on which the vehicle runs currently. Exemplarily, determining the vehicle course according to course information in GPS data of the vehicle, and acquiring course information of all roads according to the intersection map; and if the vehicle course is similar to or the same as that of a certain road of the intersection relative to the map, determining that the certain road in the relative map is the road on which the vehicle runs currently.
And the lane determining module 33 is configured to identify peripheral information of a current road on which the vehicle is traveling, and determine a target lane of the current road on which the vehicle is located according to the peripheral information and the relative map data. For example, the position of the vehicle in the relative map is determined by identifying whether the attribute information in the vehicle surrounding information matches the position of the attribute data in the map data. And acquiring vehicle peripheral information by using the vehicle-mounted camera and the laser radar, processing the vehicle peripheral information into map data and then matching the map data with the relative map data, and positioning the specific lane position of the road where the vehicle is positioned by using the laser radar and/or the vehicle-mounted camera after successfully matching attribute data of ground objects contained in the vehicle peripheral information with partial data in the relative map data.
And the navigation module 34 is used for outputting the crossroad guidance line information based on the target lane and navigating the vehicle to pass through the crossroad according to the crossroad guidance line information.
Referring to fig. 4, the invention further provides a method for navigating through an intersection based on a local relative map, which includes constructing the local relative map in advance, loading relative map data when a vehicle is positioned to pass through the intersection, forming the local relative map, and then positioning a lane position of the vehicle in the local relative map by using vehicle-mounted sensing to navigate; the method specifically comprises the following steps:
step 410: and pre-constructing relative map data and intersection map index information of a plurality of intersections, and associating the relative map data and the intersection map index information to a navigation map. The method realizes that the navigation map is constructed and bound with the local relative map which is used as a point of interest (POI) of the navigation map, and the relative map data can be loaded by using the intersection map index through driving and positioning to show the relative map.
Step 420: and displaying the driving navigation, and loading relative map data according to the intersection map index information corresponding to the intersection when the vehicle approaches the intersection.
Step 430: determining a road on which the current vehicle runs based on the current vehicle course, identifying the peripheral information of the road, converting the peripheral information into map data to be matched with the relative map data, and determining that the vehicle is positioned in a target lane of the current road after matching.
The road on which the vehicle runs can be determined according to the running mode of the vehicle, or the lane is directly determined based on the current navigation, and the running direction of the vehicle is consistent with the navigation and is easy to obtain. Then, acquiring surrounding environment information including intersection data information by using a vehicle-mounted camera and a laser radar; and then the data is converted into map data and then is matched with the loaded relative map, after the matching is successful, the position and the lane of the vehicle in the relative map can be positioned, and then the navigation can be carried out by using the relative map. The specific determination method may refer to step 130 described above.
Step 440: and outputting the crossing internal guide line information based on the target lane, and navigating the vehicle to pass through the crossing according to the crossing internal guide line information and the relative map data.
The method for constructing the intersection map index information and the relative map data comprises the following steps:
collecting image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data; intercepting the vectorized map data to generate relative map data of intersections and intersection index information; pushing intersection index information and intersection center coordinates to a navigation map as interest points of the navigation map; the vectorized map needs to include relevant information such as lane lines, traffic lights, street lamps, stop lines, zebra crossings, road edges, intersection ranges, intersection guidance lines, road course and the like. In particular, reference may be made to the description of the embodiment of fig. 2.
The invention also provides a vehicle comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program when executed by the processor implementing the steps of the navigation method through intersections based on local relative maps as described above.
The present invention also provides a computer readable storage medium on which a computer program is stored, which computer program, when executed by a processor, implements the steps of the method for navigating through intersections based on local relative maps as described above.
It is to be understood that the computer-readable storage medium may include: any entity or device capable of carrying a computer program, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), and software distribution medium. The computer program includes computer program code. The computer program code may be in the form of source code, object code, an executable file or some intermediate form, and the like. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), software distribution medium, and the like.
In some embodiments of the present invention, the apparatus may include a controller, which is a single chip integrated with a processor, a memory, a communication module, and the like. The processor may refer to a processor included in the controller. The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A navigation method based on local relative maps through intersections is characterized by comprising the following steps:
acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when navigation approaches the intersection, wherein the relative map does not comprise longitude and latitude data;
determining the vehicle course according to the positioning module, and matching the vehicle course with the road course to determine the road on which the vehicle runs currently;
identifying peripheral information of a vehicle running on a current road, and determining a target lane of the vehicle on the current road according to the peripheral information and the relative map data;
and outputting the crossroad guiding line information based on the target lane, and navigating the vehicle to pass through the crossroad according to the crossroad guiding line information.
2. The navigation method according to claim 1, wherein the method of generating intersection map index information and relative map data includes:
collecting image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data;
intercepting the vectorized map data to generate relative map data of intersections and intersection index information;
pushing intersection index information and intersection center coordinates to a navigation map as interest points of the navigation map;
the vectorized map comprises at least one of information of a lane line, a traffic light, a street lamp, a stop line, a zebra crossing, a road edge, a crossing range, a crossing leading line and a road course.
3. The method of claim 1, wherein matching the vehicle heading to the road heading to determine the road on which the vehicle is currently traveling comprises:
determining the vehicle course according to course information in GPS data of the vehicle, and acquiring course information of all roads according to the intersection map; and if the vehicle course is similar to or the same as that of a certain road of the intersection relative to the map, determining that the certain road in the relative map is the road on which the vehicle runs currently.
4. The navigation method according to claim 1, wherein the determining that the vehicle is located in a target lane of a current road according to the surrounding information and the relative map data includes:
and acquiring vehicle peripheral information by using the vehicle-mounted camera and the laser radar, processing the vehicle peripheral information into map data and then matching the map data with the relative map data, and positioning the specific lane position of the road where the vehicle is positioned by using the laser radar and/or the vehicle-mounted camera after successfully matching attribute data of ground objects contained in the vehicle peripheral information with partial data in the relative map data.
5. The navigation method according to claim 1, wherein the matching with the relative map data after the vehicle surroundings information is processed into the map data includes:
and identifying whether the attribute information in the vehicle periphery information is matched with the position of the attribute data in the map data, and determining the position of the vehicle in the relative map.
6. A navigation system through an intersection based on a local relative map, comprising:
the loading module is used for acquiring navigation information, and loading relative map data according to intersection map index information corresponding to an intersection when the navigation approaches the intersection, wherein the relative map does not include longitude and latitude data;
the road determining module is used for determining the vehicle course according to the positioning module and matching the vehicle course with the road course so as to determine the road on which the vehicle runs at present;
the lane determining module is used for identifying the peripheral information of the vehicle running on the current road and determining a target lane of the vehicle on the current road according to the peripheral information and the relative map data;
and the navigation module is used for outputting the crossroad guidance line information based on the target lane and navigating the vehicle to pass through the crossroad according to the crossroad guidance line information.
7. A navigation method based on local relative maps through intersections is characterized by comprising the following steps:
relative map data and intersection map index information of a plurality of intersections are constructed in advance and are associated to a navigation map;
displaying driving navigation, and loading relative map data according to intersection map index information corresponding to an intersection when driving to approach the intersection;
determining a road on which the current vehicle runs based on the current vehicle course, identifying the peripheral information of the road, converting the peripheral information into map data to be matched with the relative map data, and determining that the vehicle is positioned in a target lane of the current road after matching;
and outputting the crossing internal guide line information based on the target lane, and navigating the vehicle to pass through the crossing according to the crossing internal guide line information and the relative map data.
8. The navigation method according to claim 7, wherein the method of constructing intersection map index information and relative map data comprises:
collecting image data, point cloud data and vehicle body posture data of the intersection, and processing the image data and the point cloud data of the intersection into vectorized map data;
intercepting the vectorized map data to generate relative map data of intersections and intersection index information;
pushing intersection index information and intersection center coordinates to a navigation map as interest points of the navigation map;
the vectorized map comprises at least one of information of a lane line, a traffic light, a street lamp, a stop line, a zebra crossing, a road edge, a crossing range, a crossing leading line and a road course.
9. A vehicle comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the method of any one of claims 1 to 5 or the method of any one of claims 7 to 8.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a computer, performs the method of any of claims 1 to 5 or the method of any of claims 7 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210862262.3A CN115164928A (en) | 2022-07-22 | 2022-07-22 | Navigation method, system and vehicle based on local relative map passing intersection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210862262.3A CN115164928A (en) | 2022-07-22 | 2022-07-22 | Navigation method, system and vehicle based on local relative map passing intersection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115164928A true CN115164928A (en) | 2022-10-11 |
Family
ID=83495852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210862262.3A Pending CN115164928A (en) | 2022-07-22 | 2022-07-22 | Navigation method, system and vehicle based on local relative map passing intersection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115164928A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115839723A (en) * | 2023-01-12 | 2023-03-24 | 江苏龙威中科技术有限公司 | Data processing method suitable for vehicle navigation |
| CN116698054A (en) * | 2023-08-03 | 2023-09-05 | 腾讯科技（深圳）有限公司 | Road matching method, device, electronic equipment and storage medium |
-
2022
- 2022-07-22 CN CN202210862262.3A patent/CN115164928A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115839723A (en) * | 2023-01-12 | 2023-03-24 | 江苏龙威中科技术有限公司 | Data processing method suitable for vehicle navigation |
| CN116698054A (en) * | 2023-08-03 | 2023-09-05 | 腾讯科技（深圳）有限公司 | Road matching method, device, electronic equipment and storage medium |
| CN116698054B (en) * | 2023-08-03 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Road matching method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11307040B2 (en) | Map information provision system | |
| US11829138B1 (en) | Change detection using curve alignment | |
| EP3699048A1 (en) | Travelling track prediction method and device for vehicle | |
| US11636362B1 (en) | Predicting trajectory intersection by another road user | |
| US10118614B2 (en) | Detailed map format for autonomous driving | |
| US9921585B2 (en) | Detailed map format for autonomous driving | |
| US10401859B1 (en) | Stop sign detection and response | |
| US11029697B2 (en) | Systems and methods for vehicular navigation | |
| US10048699B2 (en) | Vehicle control apparatus | |
| US11727692B2 (en) | Detection of emergency vehicles | |
| CN109426256A (en) | The lane auxiliary system based on driver intention of automatic driving vehicle | |
| CN115164928A (en) | Navigation method, system and vehicle based on local relative map passing intersection | |
| JP6956268B2 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
| US11772646B2 (en) | Driving assist method and driving assist device | |
| US20210268957A1 (en) | Driving assist method and driving assist device | |
| JP2020125988A (en) | Entrance lane estimation system, entrance lane estimation method, and entrance lane estimation program | |
| US11414102B2 (en) | Systems and methods for vehicle communication consistency | |
| RU2763452C1 (en) | Method for driving assistance and apparatus for driving assistance | |
| EP4019351A1 (en) | Vehicle control method and device, vehicle and storage medium | |
| CN114944073A (en) | Map generation device and vehicle control device | |
| US20020169528A1 (en) | Electronically tracked road-map system | |
| US11508159B2 (en) | Object tracking algorithm selection system and method | |
| US20230343109A1 (en) | Systems and methods for detecting traffic lights of driving lanes using a camera and multiple models | |
| JP6885977B2 (en) | Data structure of map data and vehicle driving control device | |
| WO2023157274A1 (en) | Lane recognition method and lane recognition device |
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 |