CN115158337A - Driving assistance method and system based on crowdsourcing map updating and readable storage medium - Google Patents
Driving assistance method and system based on crowdsourcing map updating and readable storage medium Download PDFInfo
- Publication number
- CN115158337A CN115158337A CN202210687496.9A CN202210687496A CN115158337A CN 115158337 A CN115158337 A CN 115158337A CN 202210687496 A CN202210687496 A CN 202210687496A CN 115158337 A CN115158337 A CN 115158337A
- Authority
- CN
- China
- Prior art keywords
- map
- driving assistance
- crowdsourcing
- data
- precision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 29
- 230000000007 visual effect Effects 0.000 claims description 14
- 238000007726 management method Methods 0.000 claims description 8
- 230000010365 information processing Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- G01C21/32—Structuring or formatting of map data
-
- 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
- G06F16/23—Updating
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Bioethics (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of driving assistance management, in particular to a method and a system for driving assistance based on crowdsourcing map updating and a readable storage medium. The method comprises the following steps: acquiring crowdsourcing map data on a preset route in the running process of a target vehicle; updating a high-precision map of a current version of the target vehicle based on crowdsourcing map data on a preset route acquired by multiple driving of the target vehicle to generate a corresponding optimized high-precision map; matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade; the driving assistance level used by the target vehicle on the preset route is adjusted based on the available driving assistance level. The invention also discloses a readable storage medium. The method and the device can update the high-precision map of the common route of the own vehicle based on the crowdsourcing map data of the own vehicle, and guarantee the effectiveness and accuracy of crowdsourcing update of the precision map, so that the application and management of the vehicle driving assisting function can be assisted.
Description
Technical Field
The invention relates to the technical field of driving assistance management, in particular to a method and a system for driving assistance based on crowdsourcing map updating and a readable storage medium.
Background
The high-precision map is the basis for realizing the automatic driving function and the driving assistance function, and can be applied to high-precision positioning, lane-level path planning, high-precision simulation, beyond-the-horizon environmental perception and the like. The high-precision map is a high-precision and high-fidelity model for the traffic scene and depends on the summarization of a large number of local observations.
However, in addition to high accuracy, high activity is required for the high-accuracy map, that is, a change in traffic scene can be updated to the high-accuracy map in time and distributed to vehicles using the high-accuracy map. This requires a large number of vehicles to cover the traffic scene, and high-frequency updates to the high-precision map are performed in a crowd-sourced manner. For example, chinese patent publication No. CN110160544A discloses "a high-precision map crowdsourcing update system based on edge calculation", which includes at least one information acquisition terminal installed at a vehicle end, and configured to construct a local high-precision map in a current view of a vehicle in real time, and to send differential data between the local high-precision map and a high-precision map of a current version at the position to a central node; the central node is used for summarizing map differential data from one or more information acquisition terminals and generating incremental map updating data of a high-precision map of a current version according to the summarized data; and at least one map using terminal for acquiring incremental map updating data from the central node.
The high-precision map is one of important guarantees of the function safety of the automatic driving system. The user vehicle generally has its own usual route in a daily use scenario (e.g., commuting to work) and needs to use the driving assistance function on its usual route. That is, it is more important that users use crowd-sourced updates of high-precision maps on routes. However, the common route of the user is likely to be a cold route (few vehicles pass through), so that it is difficult to effectively acquire crowdsourcing map data of other vehicles, so that the effectiveness and accuracy of crowdsourcing update of the high-precision map of the common route of the user are difficult to guarantee, and further the vehicle driving assistance function is difficult to effectively apply. Therefore, how to design a method for realizing high-precision map updating of a common route of a self-vehicle based on self-vehicle crowdsourcing map data and guarantee effectiveness and accuracy of the high-precision map crowdsourcing updating is a technical problem to be solved urgently.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to provide a driving assistance method based on crowdsourcing map updating is to update a high-precision map of a common route of a vehicle based on vehicle crowdsourcing map data, and guarantee effectiveness and accuracy of the crowdsourcing updating of the precision map, so that application and management of a vehicle driving assistance function can be assisted.
In order to solve the technical problems, the invention adopts the following technical scheme:
the driving assistance method based on the crowdsourcing map updating comprises the following steps:
s1: acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
s2: updating the high-precision map of the current version to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple times of driving of the target vehicle;
s3: matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
s4: the driving assistance level used by the target vehicle on the preset route is adjusted based on the available driving assistance level.
Preferably, in step S1, the crowd-sourced map data includes visual image data, road elements, and vehicle control state information.
Preferably, the visual image data is acquired by a tachograph or other video image capture device on the target vehicle.
Preferably, the road element of interest and the vehicle control status information are acquired by an onboard camera, a positioning device and/or inertial devices on the subject vehicle.
Preferably, in step S1, the preset route includes an urban main road and other unstructured roads.
Preferably, the step S2 specifically includes the following steps:
s201: local map building is carried out on the basis of the acquired crowdsourcing map data, and local map data of a preset route are generated;
s202: local map data of a preset route are encrypted and separated from personal information processing, and then are uploaded to a cloud end;
s203: and carrying out data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud so as to update and generate a corresponding optimized high-precision map.
Preferably, in step S3, a matching rule between the high-precision map and the driving assistance level is set in advance in accordance with a request for the high-precision map by the driving assistance function of each level.
Preferably, step S3 specifically includes the following steps:
s301: after acquiring crowdsourcing map data of a section of route on a preset route, carrying out weighted mean statistics on the section of the route according to the confidence coefficient of the crowdsourcing map data acquired each time;
s302: when the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map;
s303: and matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
Preferably, in step S4, the driving assistance level used by the target vehicle is upgraded when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route.
The invention also discloses a driving assistance system based on crowdsourcing map updating, and the driving assistance management method based on the invention is implemented and specifically comprises the following steps:
the data acquisition module is used for acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
the map updating module is used for updating the high-precision map of the current version to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple times of driving of the target vehicle;
the grade matching module is used for matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
a level adjustment module to adjust a driving assistance level used by the target vehicle on a preset route based on the available driving assistance level.
Preferably, the crowd-sourced map data includes visual image data, road elements, and vehicle control status information.
Preferably, the visual image data is acquired by a tachograph or other video image capture device on the target vehicle.
Preferably, the road-of-view element and vehicle control status information is acquired by an onboard camera, positioning device and/or inertial device on the subject vehicle.
Preferably, the preset routes include urban arterial roads and other unstructured roads.
Preferably, the map updating module firstly performs local map building based on the acquired crowd-sourced map data to generate local map data of a preset route; then, local map data of the preset route are encrypted and processed without personal information, and then are uploaded to the cloud; and finally, performing data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud end to update and generate the corresponding optimized high-precision map.
Preferably, the level matching module sets a matching rule of the high-precision map and the driving assistance level in advance according to the requirement of the driving assistance function of each level on the high-precision map.
Preferably, the level matching module firstly obtains crowdsourcing map data of a section of route on a preset route, and then performs weighted mean statistics on the section of route according to the confidence coefficient of the crowdsourcing map data obtained each time; then, after the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map; and finally, matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
Preferably, the level adjustment module upgrades the driving assistance level used by the target vehicle when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route.
The invention also discloses a readable storage medium on which a computer management program is stored, which when executed by a processor implements the steps of the inventive driving assistance method based on crowdsourced map updating.
Compared with the prior art, the driving assistance method based on the crowdsourcing map updating has the following beneficial effects:
the method comprises the steps of obtaining crowdsourcing map data on a preset route (namely a common route of a user) in the vehicle driving process, updating a current version of high-precision map based on the crowdsourcing map data on the preset route obtained by multiple times of vehicle driving, generating an optimized high-precision map, matching available driving assistance levels through the optimized high-precision map, and adjusting the currently used driving assistance levels. According to the method, the crowdsourcing map data are obtained by the self-vehicle for multiple times so as to meet the crowdsourcing updating requirement of the high-precision map, so that the high-precision map of the self-vehicle common route can be updated based on the crowdsourcing map data of the self-vehicle, the effectiveness and accuracy of the crowdsourcing updating of the precision map are ensured, and the application and management of the vehicle driving assisting function can be assisted.
Because the crowdsourcing map data inevitably relates to the privacy data of the user, compared with other existing schemes, the crowdsourcing map data of a large number of other vehicles does not need to be acquired, and therefore the safety of the privacy data of the user can be effectively guaranteed.
Drawings
For a better understanding of the objects, solutions and advantages of the present invention, reference will now be made in detail to the present invention, which is illustrated in the accompanying drawings, in which:
FIG. 1 is a logic block diagram of a driving assistance method based on crowd sourced map updates;
FIG. 2 is a schematic diagram of collecting crowd-sourced map data;
FIG. 3 is a schematic diagram of an update generation optimized high precision map;
fig. 4 is a schematic architecture diagram of a driver assistance system based on crowd-sourced map updates.
Detailed Description
The following is further detailed by the specific embodiments:
the first embodiment is as follows:
the embodiment discloses a driving assistance method based on crowdsourcing map updating.
As shown in fig. 1, the driving assistance method based on the update of the crowd-sourced map includes the following steps:
s1: acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
s2: updating the current version of the high-precision map to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple times of driving of the target vehicle;
as shown in fig. 2, information acquired by a target vehicle for the first time is uploaded to an exclusive cloud space, information acquired for the second time and more times is also uploaded to the same exclusive cloud space, data splicing and fusion are performed at the cloud by using a specific algorithm, a high-precision map with complete information and reliable quality is obtained, and the high-precision map of the current version is updated to generate an optimized high-precision map;
s3: matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
in the present embodiment, the matching rule between the high-precision map and the driving assistance level is set in advance in accordance with the requirement of the driving assistance function of each level on the high-precision map. For example, when the lane line information in the high-precision map is missing, the driving assistance function of the L2 level is adopted, and when the lane line information in the high-precision map is complete, the driving assistance function of the L3 level is adopted. Similar matching rules can be set according to actual requirements.
S4: the driving assistance level used by the target vehicle on the preset route is adjusted based on the available driving assistance levels.
In the present embodiment, when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route, the driving assistance level used by the target vehicle is upgraded. For example, the driving assistance function is upgraded from the driving assistance function of the L2 level to the driving assistance function of the L3 level.
It should be noted that, the driving assistance method based on the crowd-sourced map update in the present invention can generate corresponding software codes or software services in a program programming manner, and further can be run and implemented on a server and a computer.
The method comprises the steps of obtaining crowdsourcing map data on a preset route (namely a common route of a user) in the vehicle driving process, updating a current version of a high-precision map based on the crowdsourcing map data on the preset route obtained by multiple times of vehicle driving, generating an optimized high-precision map, matching available driving assistance levels through the optimized high-precision map, and adjusting the currently used driving assistance levels. According to the method, the crowdsourcing map data are obtained by the self-vehicle for multiple times so as to meet the crowdsourcing updating requirement of the high-precision map, so that the high-precision map of the self-vehicle common route can be updated based on the crowdsourcing map data of the self-vehicle, the effectiveness and accuracy of the crowdsourcing updating of the precision map are ensured, and the application and management of the vehicle driving assisting function can be assisted. Meanwhile, the crowdsourcing map data inevitably relates to the privacy data of the user, so that compared with other existing schemes, the crowdsourcing map data of other vehicles does not need to be acquired in a high-precision map updating mode based on the self-vehicle crowdsourcing map data, and the safety of the privacy data of the user can be effectively guaranteed.
In a specific implementation, the crowd-sourced map data includes visual image data, road elements, and vehicle control status information. Visual image data is acquired by a vehicle event recorder or other video image acquisition equipment on the target vehicle. The road-of-view elements and vehicle control status information are acquired by onboard cameras, positioning devices and/or inertial devices on the subject vehicle.
In this embodiment, the crowd-sourced map data is road network data collected by a crowd-sourced drawing mode, and the crowd-sourced drawing mode adopts a visual mode (a camera and a camera) to replace a device of a professional collection vehicle for data collection, so that a vehicle data recorder of a vehicle can be used as a crowd-sourced collection device to complete data collection and upload. Meanwhile, the sensor based on the target vehicle comprises an on-board camera, a positioning device and an inertia device to acquire road elements required for driving assistance, and comprises steering wheel steering angle information of the vehicle. As shown in fig. 2, the pedestrian crosswalk, the ground arrow (including but not limited to), and the steering angle of the steering wheel at the current time, the vehicle speed information, etc. on the road are acquired and recorded using a specific algorithm using the sensor of the target vehicle itself.
In the specific implementation process, the preset route comprises an urban arterial road and other unstructured roads.
In this case, the preset route is a common route of the user, such as a commuting route from home to company or any other common driving route. However, the crowd-sourced map generally adopts a large number of crowd-sourced vehicles to acquire basic data of the high-precision map, and the high-precision map is updated only based on the crowd-sourced map data of the self-vehicle (the data volume is small), so that the self-vehicle is required to travel on a path of a common route (a preset route) for multiple times, and the requirements of crowd-sourced map data acquisition and high-precision map updating are met. In addition, the preset route is a road with relatively simple road conditions.
In step S2, the method specifically includes the following steps:
s201: performing local map building based on the acquired crowdsourcing map data to generate local map data of a preset route;
in this embodiment, the generation of the local map data based on the crowd-sourced map data is realized by adopting the existing mature means, which is not described herein again. Specifically, reference may be made to the disclosure in patent "a high-precision map crowdsourcing update system based on edge calculation" with publication number CN 110160544A: the vehicle-mounted computing unit based on the existing intelligent driving auxiliary vehicle receives crowdsourcing map data and constructs a local high-precision map in the current field of the vehicle in real time according to the crowdsourcing map data.
S202: local map data of a preset route are encrypted and separated from personal information processing, and then are uploaded to a cloud;
in this embodiment, encryption and separation from personal information processing are implemented by using existing mature means, which are not described herein again.
S203: and performing data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud end to update and generate a corresponding optimized high-precision map (as shown in fig. 2).
According to the method, the local map data of the preset route are generated and are spliced with the high-precision map of the current version to generate the optimized high-precision map, so that the efficiency and accuracy of crowdsourcing updating of the high-precision map can be guaranteed. Meanwhile, the invention can further improve the safety of the user privacy data by encrypting the local map data of the preset route and separating from the personal information processing mode.
With reference to fig. 3, step S3 specifically includes the following steps:
s301: after acquiring crowdsourcing map data of a section of route on a preset route, carrying out weighted mean statistics on the section of the route according to the confidence coefficient of the crowdsourcing map data acquired each time;
s302: when the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map;
s303: and matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
For example, whether the condition of upgrading the L2 level function to the L3 level function is satisfied is determined based on the issued data, and the driver assistance function is recommended or prompted to the user under the authorization condition of the target vehicle user, and the current road may be turned on.
Example two:
the embodiment discloses a driving assistance system based on crowd-sourced map updating, which is implemented based on the driving assistance management method in the first embodiment.
As shown in fig. 4, the driving assistance system based on the crowdsourcing map update specifically includes:
the data acquisition module is used for acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
the map updating module is used for updating the high-precision map of the current version to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple driving of the target vehicle;
as shown in fig. 2, information acquired by a target vehicle for the first time is uploaded to an exclusive cloud space, information acquired for the second time and more times is also uploaded to the same exclusive cloud space, data splicing and fusion are performed at the cloud by using a specific algorithm, a high-precision map with complete information and reliable quality is obtained, and the high-precision map of the current version is updated to generate an optimized high-precision map;
the grade matching module is used for matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
in the present embodiment, the matching rule between the high-precision map and the driving assistance level is set in advance in accordance with the requirement of the driving assistance function of each level on the high-precision map. For example, when the lane line information in the high-precision map is missing, the driving assistance function of the L2 level is adopted, and when the lane line information in the high-precision map is complete, the driving assistance function of the L3 level is adopted. Similar matching rules can be set according to actual requirements.
A level adjustment module to adjust a driving assistance level used by the target vehicle on a preset route based on the available driving assistance level.
In the present embodiment, when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route, the driving assistance level used by the target vehicle is upgraded. For example, the driving assistance function is upgraded from the driving assistance function of the L2 level to the driving assistance function of the L3 level.
The method comprises the steps of obtaining crowdsourcing map data on a preset route (namely a common route of a user) in the vehicle driving process, updating a current version of a high-precision map based on the crowdsourcing map data on the preset route obtained by multiple times of vehicle driving, generating an optimized high-precision map, matching available driving assistance levels through the optimized high-precision map, and adjusting the currently used driving assistance levels. According to the method, the crowdsourcing map data are obtained by the self-vehicle for multiple times so as to meet the crowdsourcing updating requirement of the high-precision map, so that the high-precision map of the self-vehicle common route can be updated based on the crowdsourcing map data of the self-vehicle, the effectiveness and accuracy of the crowdsourcing updating of the precision map are ensured, and the application and management of the vehicle driving assisting function can be assisted. Meanwhile, the crowdsourcing map data inevitably relates to the privacy data of the user, so that compared with other existing schemes, the crowdsourcing map data of other vehicles does not need to be acquired in a high-precision map updating mode based on the self-vehicle crowdsourcing map data, and the safety of the privacy data of the user can be effectively guaranteed.
In a specific implementation, the crowd-sourced map data includes visual image data, road elements, and vehicle control status information. Visual image data is acquired by a vehicle event recorder or other video image acquisition equipment on the target vehicle. The road-of-view element and vehicle control status information is acquired by onboard cameras, positioning devices, and/or inertial devices on the target vehicle.
In this embodiment, the crowd-sourced map data is road network data collected by a crowd-sourced drawing mode, and the crowd-sourced drawing adopts a visual mode (a camera and a camera) to replace equipment of a professional collection vehicle for data collection, so that the automobile data recorder of the vehicle can be used as crowd-sourced collection equipment to complete data collection and upload. Meanwhile, the sensor based on the target vehicle comprises an on-board camera, a positioning device and an inertia device to acquire road elements required for driving assistance, and comprises steering wheel steering angle information of the vehicle. As shown in fig. 2, using the sensor of the target vehicle itself, a crosswalk, a ground arrow (including but not limited to) and a steering angle of a steering wheel, vehicle speed information, etc. at the current time on the road are acquired and recorded using a specific algorithm.
In the specific implementation process, the preset route comprises an urban arterial road and other unstructured roads.
In this case, the preset route is a common route of the user, such as a commuting route from home to company or any other common driving route. However, the crowd-sourced map generally adopts a large number of crowd-sourced vehicles to acquire basic data of the high-precision map, and the high-precision map is updated only based on the crowd-sourced map data of the self-vehicle (the data volume is small), so that the self-vehicle is required to travel on a path of a common route (a preset route) for multiple times, and the requirements of crowd-sourced map data acquisition and high-precision map updating are met. In addition, the preset route is a road with relatively simple road conditions.
In a specific implementation process, a map updating module firstly carries out local map building based on the acquired crowdsourcing map data to generate local map data of a preset route; then, local map data of the preset route are encrypted and processed without personal information, and then are uploaded to the cloud; and finally, performing data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud so as to update and generate a corresponding optimized high-precision map (as shown in fig. 2).
In this embodiment, the generation of the local map data based on the crowdsourcing map data is implemented by adopting the existing mature means, which is not described herein again. Specifically, reference may be made to the disclosure in patent "a high-precision map crowdsourcing update system based on edge calculation" with publication number CN 110160544A: the vehicle-mounted computing unit based on the existing intelligent driving auxiliary vehicle receives crowdsourcing map data and constructs a local high-precision map in the current field of the vehicle in real time according to the crowdsourcing map data.
According to the method, the local map data of the preset route are generated and are spliced with the high-precision map of the current version to generate the optimized high-precision map, so that the efficiency and accuracy of crowdsourcing updating of the high-precision map can be guaranteed. Meanwhile, the invention can further improve the safety of the user privacy data by encrypting the local map data of the preset route and separating from the personal information processing mode.
In a specific implementation process, as shown in fig. 3, after the level matching module first obtains crowdsourcing map data of a section of route on a preset route, a weighted average statistics is performed on the section of route according to a confidence of the crowdsourcing map data obtained each time; then, after the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map; and finally, matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
Example three:
disclosed in the present embodiment is a readable storage medium.
A readable storage medium, on which a computer management-like program is stored, which when executed by a processor, implements the steps of the inventive driving assistance method based on crowd-sourced map updates. The readable storage medium can be a device with readable storage function such as a U disk or a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and those skilled in the art should understand that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all that should be covered by the claims of the present invention.
Claims (19)
1. The driving assistance method based on the crowdsourcing map update is characterized by comprising the following steps:
s1: acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
s2: updating the high-precision map of the current version to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple times of driving of the target vehicle;
s3: matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
s4: the driving assistance level used by the target vehicle on the preset route is adjusted based on the available driving assistance levels.
2. The drive assist method based on crowdsourcing map update of claim 1, wherein: in step S1, the crowd-sourced map data includes visual image data, road elements, and vehicle control state information.
3. The driver assistance method based on the crowdsourcing map update of claim 2, wherein: visual image data is acquired by a vehicle event recorder or other video image acquisition equipment on the target vehicle.
4. The driver assistance method based on the crowdsourcing map update of claim 2, wherein: the road-of-view element and vehicle control status information is acquired by onboard cameras, positioning devices, and/or inertial devices on the target vehicle.
5. The driver assistance method based on the crowdsourcing map update of claim 1, wherein: in step S1, the preset route includes an urban main road and other unstructured roads.
6. The driver assistance method based on the crowdsourcing map update of claim 1, wherein: in step S2, the method specifically includes the following steps:
s201: local map building is carried out on the basis of the acquired crowdsourcing map data, and local map data of a preset route are generated;
s202: local map data of a preset route are encrypted and separated from personal information processing, and then are uploaded to a cloud;
s203: and carrying out data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud so as to update and generate a corresponding optimized high-precision map.
7. The drive assist method based on crowdsourcing map update of claim 1, wherein: in step S3, a matching rule between the high-precision map and the driving assistance level is set in advance according to the requirement of the driving assistance function of each level on the high-precision map.
8. The drive assist method based on crowdsourcing map update of claim 1, wherein: in step S3, the following steps are specifically included:
s301: after acquiring crowdsourcing map data of a section of route on a preset route, carrying out weighted mean statistics on the section of the route according to the confidence coefficient of the crowdsourcing map data acquired each time;
s302: when the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map;
s303: and matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
9. The drive assist method based on crowdsourcing map update of claim 1, wherein: in step S4, when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route, the driving assistance level used by the target vehicle is upgraded.
10. A driving assistance system based on crowd-sourced map update is characterized in that: the driving assistance management method according to claim 1 is implemented, and specifically includes:
the data acquisition module is used for acquiring crowdsourcing map data on a preset route in the running process of a target vehicle;
the map updating module is used for updating the high-precision map of the current version to generate an optimized high-precision map based on crowdsourcing map data on a preset route acquired by multiple driving of the target vehicle;
the grade matching module is used for matching the optimized high-precision map with the driving assistance grade to obtain an available driving assistance grade;
and the grade adjusting module is used for adjusting the driving assistance grade used by the target vehicle on the preset route based on the available driving assistance grade.
11. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the crowd-sourced map data includes visual image data, road elements, and vehicle control status information.
12. The driver assistance system based on a crowdsourced map update of claim 11, wherein: visual image data is acquired by a tachograph or other video image acquisition device on the target vehicle.
13. The driver assistance system based on a crowdsourced map update of claim 11, wherein: the road-of-view elements and vehicle control status information are acquired by onboard cameras, positioning devices and/or inertial devices on the subject vehicle.
14. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the preset routes include urban arterial roads and other unstructured roads.
15. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the map updating module firstly carries out local map building based on the acquired crowdsourcing map data to generate local map data of a preset route; then, local map data of the preset route are encrypted and processed without personal information, and then are uploaded to the cloud; and finally, performing data splicing on the local map data of the preset route and the high-precision map of the current version at the cloud so as to update and generate a corresponding optimized high-precision map.
16. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the grade matching module sets matching rules of the high-precision map and the driving assistance grade in advance according to requirements of the driving assistance functions of all grades on the high-precision map.
17. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the grade matching module firstly acquires crowdsourcing map data of a section of route on a preset route, and then carries out weighted mean statistics on the section of route according to confidence coefficient of the crowdsourcing map data acquired each time; then, after the weighted average value reaches a preset target, data release is carried out on the road section through optimizing a high-precision map; and finally, matching the data issued by the optimized high-precision map with the driving assistance grade to obtain the available driving assistance grade.
18. The crowd-sourced map update-based drive-assist system of claim 10, wherein: the level adjustment module upgrades the driving assistance level used by the target vehicle when the available driving assistance level is higher than the driving assistance level used by the target vehicle on the preset route.
19. A readable storage medium, characterized in that a computer management-like program is stored thereon, which when executed by a processor, implements the steps of the driver assistance method based on crowdsourced map update of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210687496.9A CN115158337A (en) | 2022-06-17 | 2022-06-17 | Driving assistance method and system based on crowdsourcing map updating and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210687496.9A CN115158337A (en) | 2022-06-17 | 2022-06-17 | Driving assistance method and system based on crowdsourcing map updating and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115158337A true CN115158337A (en) | 2022-10-11 |
Family
ID=83486164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210687496.9A Pending CN115158337A (en) | 2022-06-17 | 2022-06-17 | Driving assistance method and system based on crowdsourcing map updating and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115158337A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107430591A (en) * | 2015-01-26 | 2017-12-01 | Trw汽车美国有限责任公司 | Vehicle driver assistance system |
| US20180273032A1 (en) * | 2015-11-30 | 2018-09-27 | Huawei Technologies Co., Ltd. | Automatic Driving Navigation Method, Apparatus, and System, In-Vehicle Terminal, and Server |
| CN108688666A (en) * | 2017-04-05 | 2018-10-23 | 现代自动车株式会社 | Automatic driving control system and the control method for using the automated driving system |
| CN109643367A (en) * | 2016-07-21 | 2019-04-16 | 御眼视觉技术有限公司 | Crowdsourcing and the sparse map of distribution and lane measurement for autonomous vehicle navigation |
| WO2019152049A1 (en) * | 2018-02-02 | 2019-08-08 | Ford Global Technologies, Llc | Map discrepancy identification with centralized map data |
| CN110160544A (en) * | 2019-06-12 | 2019-08-23 | 北京深思敏行科技有限责任公司 | A kind of high-precision map crowdsourcing more new system based on edge calculations |
| CN110660218A (en) * | 2019-09-29 | 2020-01-07 | 上海莫吉娜智能信息科技有限公司 | High-precision map making method and system by using millimeter wave radar |
| US20200141748A1 (en) * | 2018-11-01 | 2020-05-07 | Here Global B.V. | Method, apparatus, and computer program product for creating traffic information for specialized vehicle types |
| CN112862881A (en) * | 2021-02-24 | 2021-05-28 | 清华大学 | Road map construction and fusion method based on crowd-sourced multi-vehicle camera data |
| CN113052966A (en) * | 2021-03-05 | 2021-06-29 | 清华大学 | Automatic driving crowdsourcing high-precision map updating method, system and medium |
| CN114090594A (en) * | 2020-08-25 | 2022-02-25 | 阿里巴巴集团控股有限公司 | Map fusion method and device, electronic equipment and storage medium |
| CN114385661A (en) * | 2022-01-29 | 2022-04-22 | 重庆长安汽车股份有限公司 | High-precision map updating system based on V2X technology |
| CN114608592A (en) * | 2022-02-10 | 2022-06-10 | 上海追势科技有限公司 | Crowdsourcing method, system, equipment and storage medium for map |
-
2022
- 2022-06-17 CN CN202210687496.9A patent/CN115158337A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107430591A (en) * | 2015-01-26 | 2017-12-01 | Trw汽车美国有限责任公司 | Vehicle driver assistance system |
| US20180273032A1 (en) * | 2015-11-30 | 2018-09-27 | Huawei Technologies Co., Ltd. | Automatic Driving Navigation Method, Apparatus, and System, In-Vehicle Terminal, and Server |
| CN109643367A (en) * | 2016-07-21 | 2019-04-16 | 御眼视觉技术有限公司 | Crowdsourcing and the sparse map of distribution and lane measurement for autonomous vehicle navigation |
| CN108688666A (en) * | 2017-04-05 | 2018-10-23 | 现代自动车株式会社 | Automatic driving control system and the control method for using the automated driving system |
| WO2019152049A1 (en) * | 2018-02-02 | 2019-08-08 | Ford Global Technologies, Llc | Map discrepancy identification with centralized map data |
| US20200141748A1 (en) * | 2018-11-01 | 2020-05-07 | Here Global B.V. | Method, apparatus, and computer program product for creating traffic information for specialized vehicle types |
| CN110160544A (en) * | 2019-06-12 | 2019-08-23 | 北京深思敏行科技有限责任公司 | A kind of high-precision map crowdsourcing more new system based on edge calculations |
| CN110660218A (en) * | 2019-09-29 | 2020-01-07 | 上海莫吉娜智能信息科技有限公司 | High-precision map making method and system by using millimeter wave radar |
| CN114090594A (en) * | 2020-08-25 | 2022-02-25 | 阿里巴巴集团控股有限公司 | Map fusion method and device, electronic equipment and storage medium |
| CN112862881A (en) * | 2021-02-24 | 2021-05-28 | 清华大学 | Road map construction and fusion method based on crowd-sourced multi-vehicle camera data |
| CN113052966A (en) * | 2021-03-05 | 2021-06-29 | 清华大学 | Automatic driving crowdsourcing high-precision map updating method, system and medium |
| CN114385661A (en) * | 2022-01-29 | 2022-04-22 | 重庆长安汽车股份有限公司 | High-precision map updating system based on V2X technology |
| CN114608592A (en) * | 2022-02-10 | 2022-06-10 | 上海追势科技有限公司 | Crowdsourcing method, system, equipment and storage medium for map |
Non-Patent Citations (1)
| Title |
|---|
| 秦志嫒;黎宇科;刘宇;: "高精度地图众包更新合规问题初探", 汽车与配件, no. 16, 28 August 2020 (2020-08-28), pages 56 - 58 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11941976B2 (en) | System and method for sharing data collected from the street sensors | |
| CN110958567B (en) | Sharing classified objects perceived by autonomous vehicles | |
| US10095237B2 (en) | Driverless vehicle steering control method and apparatus | |
| JP7059362B2 (en) | Map data construction method, vehicle terminal, and server | |
| CN111999752B (en) | Method, apparatus and computer storage medium for determining road information data | |
| EP3219564A1 (en) | Driving prediction with a deep neural network | |
| CN112033425B (en) | Vehicle driving assisting method, device, computer equipment and storage medium | |
| JP2022020044A (en) | Method and device for autonomous parking, electronic device, computer readable storage medium and computer program | |
| CN112712717A (en) | Information fusion method and system | |
| US11604075B2 (en) | Systems and methods for deriving planned paths for vehicles using path priors | |
| JP7420734B2 (en) | Data distribution systems, sensor devices and servers | |
| US20210325898A1 (en) | Using drone data to generate high-definition map for autonomous vehicle navigation | |
| CN111351498A (en) | Optimized navigation method, device and related equipment | |
| EP4155680A1 (en) | Navigation system with independent positioning mechanism and method of operation thereof | |
| CN114179829A (en) | Multi-end cooperative vehicle driving method, device, system and medium | |
| CN115339453A (en) | Vehicle lane change decision information generation method, device, equipment and computer medium | |
| Chandrasekaran et al. | Computer vision based parking optimization system | |
| CN115158337A (en) | Driving assistance method and system based on crowdsourcing map updating and readable storage medium | |
| CN112414416A (en) | ADAS map data system based on four-level automatic driving high precision | |
| US20210088340A1 (en) | Inferring lane boundaries via high speed vehicle telemetry | |
| EP3989031A1 (en) | Systems and methods for fusing road friction data to enhance vehicle maneuvering | |
| JP2019101806A (en) | Running field survey support system | |
| JP2023043957A (en) | On-vehicle device, image recognition system, support device for on-vehicle device, image recognition method, and model data transmission method | |
| US12007786B2 (en) | System and method for real-time lane validation | |
| CN112698372A (en) | Spatio-temporal data processing 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 |