Map error information detection method, device and equipment, vehicle and storage medium

A technology of error information and detection method, which is applied in the direction of measuring device, geographic information database, vehicle position/route/height control, etc., can solve the problem of low detection efficiency of map error information, improve timeliness and efficiency, and improve driving safety sexual effect

Pending Publication Date: 2019-05-21
APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
3 Cites 10 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0004] The present application provides a map error information detection method, device, equipment, vehicle a...
View more

Method used

According to the computer equipment of this embodiment, during the actual driving process of the vehicle, whether the map data is detected based on the current environmental feature information in real time is wrong, and the timeliness and efficiency of map error detection are improved, so that the map data can be corrected in time, and the vehicle is improved. driving safety. Moreover, the vehicle can detect unmarked objects in the map data, which can supplement the map data and make the map data more accurate. It also improves the control flexibility of the vehicle by taking fault-tolerant measures to continue driving when the road ahead is found to be inconsistent with the map data.
According to the vehicle of this embodiment, during the actual driving process of the vehicle, whether the map data is detected based on the current environmental characteristic information in real time is wrong, and the timeliness and efficiency of map error detection can be improved, so that the map data can be corrected in time, and the vehicle driving can be improved. safety. Moreover, the vehicle can detect unmarked objects in the map data, which can supplement the map data and make the map data more accurate. It also improves the control flexibility of the vehicle by taking fault-tolerant measures to continue driving when the road ahead is found to be inconsistent with the map data.
The error information detection method of the map that present embodiment provides, through vehicle in actual driving process, detects whether map data is wrong based on current environment characteristic information in real time, improves the timeliness and efficiency of map error detection, thereby can correct map in time data to imp...
View more

Abstract

The invention provides a map error information detection method, device and equipment, a vehicle and a storage medium. The method comprises: acquiring current environment feature information around the vehicle; And detecting whether the map data is wrong based on the current environment feature information and the map data. Whether map data is wrong or not is detected in real time based on the current environment feature information in the actual driving process of the vehicle, the timeliness and efficiency of map error detection are improved, and therefore the map data can be corrected in time, and the vehicle driving safety is improved.

Application Domain

Character and pattern recognitionNavigation instruments +5

Technology Topic

Real-time computingTime based +1

Image

  • Map error information detection method, device and equipment, vehicle and storage medium
  • Map error information detection method, device and equipment, vehicle and storage medium
  • Map error information detection method, device and equipment, vehicle and storage medium

Examples

  • Experimental program(7)

Example Embodiment

[0029] Example one
[0030] This embodiment provides a method for detecting map error information, which is used to detect map errors in real time. The execution subject of this embodiment is a map error information detection device, which can be installed in a computer device, which is installed on a vehicle.
[0031] Such as figure 2 As shown, this embodiment provides a schematic flowchart of a method for detecting error information of a map, and the method includes:
[0032] Step 101: Acquire current environmental feature information around the vehicle.
[0033] Specifically, cameras (such as binocular cameras, monocular cameras, etc.), radar, lidar, millimeter wave radar and other sensors are provided on the vehicle. During the actual driving of the vehicle, the current environmental feature information around the vehicle can be obtained in real time.
[0034] The current environment feature information may include lane line feature information, intersection feature information, traffic lane number feature information, roadside object feature information, and so on.
[0035] Among them, the lane line feature information may include the position information of the lane line, how many lane lines are in different positions on the road ahead, and so on. The intersection feature information may include the location information of the intersection, how many forks the intersection is, which buildings are in the direction of the intersection, and traffic light information at the intersection, and so on. The characteristic information of the number of traffic lanes may include how many traffic lanes correspond to the front blocked position. The feature information of roadside objects may include various objects appearing beside the road, such as buildings, signs, telephone poles, and so on. The environmental feature information may also include some other feature information, which can be specifically set according to actual requirements. This is only an example for description, and this embodiment does not limit it.
[0036] Optionally, the current environmental characteristic information may be obtained by performing certain processing according to the detection information of each sensor, and the specific processing method may be any implementable method in the prior art. For example, the position of the lane line, the number of lanes on different road sections, the location of roadside buildings, etc. can be obtained through the combination of lidar and camera with GPS positioning or point cloud visual positioning.
[0037] Among them, the vehicle may be an autonomous driving vehicle, or a semi-autonomous driving vehicle or a smart vehicle equipped with corresponding sensors, as long as it can obtain surrounding environment feature information, and is not limited to an autonomous driving vehicle.
[0038] Step 102: Detect whether the map data is wrong based on the current environmental feature information and the map data.
[0039] Specifically, after acquiring the current environmental feature information around the vehicle, the current environmental feature information can be compared with the subway data, and it can be judged whether the label in the map data is wrong or not through the comparison.
[0040] Among them, the map data may be high-precision map data.
[0041] Exemplarily, if the vehicle detects that there is a telephone pole at a certain location on the side of the road, but it is not displayed on the map, it may indicate that the labeling error in the map data is incorrect.
[0042] Optionally, after the error is detected, the related information of the utility pole can be reported to the server, so that the server can add the label data about the utility pole to the map data, so that the map data can be supplemented.
[0043] Exemplarily, if the vehicle detects that the number of driving lanes ahead is 3 lanes, and compared with the map data, it is found that 4 lanes are marked in the map data, which may indicate that the map data is marked incorrectly.
[0044] Optionally, relevant error information may be reported to the server, so that the server can correct the map data according to the error information. A warning can also be issued to remind passengers in the vehicle. Corresponding safety measures can also be taken, such as controlling the vehicle to slow down, stop, pull over and so on.
[0045] Exemplarily, if the vehicle detects that the road ahead is blocked, but a row of fences, and the map data marks the driving road, it means that the map is marked incorrectly. Optionally, the vehicle can be controlled to park, and the detected error information can be reported to the server to correct the map data.
[0046] Optionally, the confidence levels of different lanes in the current environment can be determined according to the comparison result of the current environment feature information and the map data, fault tolerance measures are taken according to the different confidence levels, and the lane with high confidence is selected to continue driving, and so on.
[0047] After the map data error is detected, the specific measures to be taken can be selected according to different situations, which is not limited in this embodiment.
[0048] The method for detecting map error information provided by this embodiment detects whether the map data is wrong based on the current environmental feature information in real time during the actual driving of the vehicle, thereby improving the timeliness and efficiency of map error detection, so that the map data can be corrected in time. Vehicle driving safety.

Example Embodiment

[0049] Example two
[0050] This embodiment further supplements the method provided in the first embodiment.
[0051] Such as image 3 As shown, the schematic flow chart of the method for detecting error information of the map provided in this embodiment.
[0052] As an implementable manner, on the basis of the foregoing embodiment 1, optionally, step 101 specifically includes:
[0053] Step 1011: Obtain detection information of each sensor from multiple sensors on the vehicle.
[0054] Step 1012: Acquire current environmental feature information according to the detection information of each sensor.
[0055] Specifically, the sensors may include cameras (such as binocular cameras, monocular cameras, etc.), radar, lidar, millimeter wave radar and other sensors.
[0056] Exemplarily, each sensor collects environmental information in different directions around the vehicle. Through image recognition, point cloud visual positioning, GPS positioning, and point cloud fusion technologies, it can obtain partial or complete environmental feature information around the vehicle, which can be combined with map data. Compared.
[0057] As another implementable manner, on the basis of the foregoing embodiment 1, optionally, after step 102, the method may further include:
[0058] Step 103: If it is confirmed that the map data is wrong, the driving state of the vehicle is controlled accordingly.
[0059] Specifically, when it is found that the map data is marked incorrectly, in order to avoid the danger of continuing to drive, the vehicle can be controlled to decelerate and stop to ensure safety.
[0060] Optionally, the vehicle can be controlled to stop only when the map of the road ahead is incorrectly marked. If only a certain position on the roadside is marked incorrectly and does not affect the driving of the vehicle, you can continue to drive and report the error information.
[0061] Optionally, step 103 may specifically include:
[0062] Step 1031: If it is confirmed that the map data is incorrect, obtain the lane confidence of the current road according to the current environmental feature information and the map data.
[0063] Step 1032: Determine the target lane according to the lane confidence of the current road.
[0064] Step 1033: Control the vehicle to continue driving along the target lane at a speed corresponding to the confidence level of the target lane.
[0065] Specifically, when it is confirmed that the driving road ahead is inconsistent with the map data, the lane confidence of the current road can be obtained according to the current environmental feature information and the map data. For example, there are actually 3 lanes on the road ahead, and 4 lanes are marked on the map. Based on the comparison of the position information of the lane with the position information of the lane in the map data, the confidence of the consistent lane with the map data is high, and the confidence of the inconsistent lanes The speed is low, the target lane is selected according to the confidence of different lanes, and the speed of the vehicle is controlled. Different speeds can be set for different confidences. Control the vehicle to continue driving along the target lane at a speed corresponding to the confidence level of the target lane. For example, it can be controlled to drive slowly at a lower speed.
[0066] Optionally, when driving on the target lane, the consistency between the road ahead and the map data during driving can be detected in real time. When driving to a certain location and detecting that the road ahead is consistent with the map data annotation, normal driving can be resumed.
[0067] Illustratively, such as Figure 4 As shown, the schematic diagram of the driving process of the vehicle provided in this embodiment. When the vehicle reaches point A, it is detected that the road ahead becomes 3 lanes, and the map is marked as 4 lanes. In fact, one lane may be under maintenance. The vehicle can choose to drive slowly in any of the three lanes on the left. When driving to point B, it is found that the road ahead is restored to 4 lanes, which is consistent with the map data, and the normal driving state can be restored.
[0068] As another implementable manner, on the basis of the foregoing embodiment 1, optionally, the method may further include:
[0069] In step 201, if it is confirmed that the map data is wrong, the error information is reported to the server so that the server can correct the map data.
[0070] Exemplarily, if the vehicle detects that there is a telephone pole at a certain location on the roadside, but it is not displayed on the map, it can indicate that there is an error in the map data. The related information of the telephone pole can be reported to the server, so that the server can display the map data Add the annotation data about the pole to add the map data.
[0071] Exemplarily, if the vehicle detects that the number of lanes ahead is 3 lanes and compares with the map data, it is found that 4 lanes are marked in the map data, which can indicate that the map data is marked incorrectly, and the relevant error information can be reported to the server. Make the server correct the map data based on the error information.
[0072] Exemplarily, if the vehicle detects that the road ahead is blocked, but a row of fences, and the map data indicates a driving road, it means that the map is labeled incorrectly, and the detected error information can be reported to the server to correct the map data.
[0073] As another implementable manner, on the basis of the foregoing embodiment 1, optionally, the method may further include:
[0074] Step 202: If it is confirmed that the map data is wrong, an alarm message is issued.
[0075] Specifically, when a map data error is found, an alarm message can be issued through the display screen on the vehicle, voice broadcast equipment, etc., which can display the alarm information or voice broadcast alarm information to remind the passengers on the vehicle, for example, the vehicle can be reminded The passengers on board take over the driving.
[0076] Optionally, the alarm may be issued when the road in front of the vehicle is inconsistent with the map and other situations that may cause driving danger, and the alarm may not be issued when there is an object on the roadside that does not affect the driving of the vehicle. Specifically, it can be set according to actual needs, which is not limited in this embodiment.
[0077] In some embodiments, the environment feature information includes at least one of lane line feature information, intersection feature information, traffic lane number feature information, and roadside object feature information.
[0078] Among them, the lane line feature information may include the position information of the lane line, how many lane lines are in different positions on the road ahead, and so on. The intersection feature information may include the location information of the intersection, how many forks the intersection is, which buildings are in the direction of the intersection, and traffic light information at the intersection, and so on. The characteristic information of the number of traffic lanes may include how many traffic lanes correspond to the front blocked position. The feature information of roadside objects may include various objects appearing beside the road, such as buildings, signs, telephone poles, and so on. The environmental characteristic information may also include some other characteristic information, which can be specifically set according to actual needs, which is only illustrative here.
[0079] It should be noted that each implementable manner in this embodiment can be implemented separately, or can be implemented in any combination without conflict. This application is not limited.
[0080] The method for detecting map error information provided by this embodiment detects whether the map data is wrong based on the current environmental feature information in real time during the actual driving of the vehicle, thereby improving the timeliness and efficiency of map error detection, so that the map data can be corrected in time. Vehicle driving safety. In addition, by detecting objects that are not marked in the map data by the vehicle, the map data can be supplemented to make the map data more accurate. Furthermore, when the road ahead is found to be inconsistent with the map data, fault-tolerant measures are taken to continue driving, which improves the flexibility of vehicle control.

Example Embodiment

[0081] Example three
[0082] This embodiment provides a map error information detection device, which is used to implement the method in the first embodiment above.
[0083] Such as Figure 5 As shown, the schematic diagram of the structure of the map error information detection device provided in this embodiment. The error information detection device 30 of the map includes an acquisition module 31 and a processing module 32.
[0084] Among them, the acquisition module 31 is used to acquire current environmental feature information around the vehicle; the processing module 32 is used to detect whether the map data is wrong based on the current environmental feature information and map data.
[0085] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and detailed description will not be given here.
[0086] According to the map error information detection device provided in this embodiment, the map data is detected in real time based on the current environmental feature information during the actual driving process to improve the timeliness and efficiency of map error detection, so that the map data can be corrected in time. Improve vehicle driving safety.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.

Similar technology patents

Detection method and device for page availability

InactiveCN104993943Aavoid wastingImprove timeliness and efficiency
Owner:BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD

Interactive system fusing digital twinning and virtual reality and method thereof

PendingCN114740969AImprove timeliness and efficiencyImprove efficiency
Owner:北京德信电通科技有限公司

Multi-modal knowledge graph construction and retrieval system and method

PendingCN114741466AImprove timeliness and efficiencyEfficient knowledge map construction
Owner:北京德信电通科技有限公司

Remote restart device and system

PendingCN113602327AGuaranteed safety and reliability of outputImprove timeliness and efficiency
Owner:TRAFFIC CONTROL TECH CO LTD

Method and device for determining resource allowance, storage medium and electronic equipment

PendingCN111209118AImprove timeliness and efficiency
Owner:BEIJING SANKUAI ONLINE TECH CO LTD

Classification and recommendation of technical efficacy words

  • Improve driving safety
  • Improve timeliness and efficiency

Running instant anti-collision warning system and method

ActiveCN101908283AReduce the chance of collisionImprove driving safety
Owner:AUTOMOTIVE RES & TESTING CENT

Processing unit, system and method for suggesting crossroad driving

InactiveCN104658290AImprove driving safetyImproved traffic flow
Owner:BOSCH AUTOMOTIVE PROD SUZHOU

Active anti-dazzle method and vehicle active anti-dazzle device

PendingCN106985640AReduce the incidence of traffic accidentsImprove driving safety
Owner:HASCO VISION TECHNOLOGY CO LTD

Video monitoring and recording system for carrying tool

InactiveCN102968902AImprove driving safety
Owner:SUZHOU QUNKAI INFORMATION SYST

Message pushing method and device, storage medium and server

ActiveCN110300175AImprove driving safetyMeet service needs
Owner:TENCENT TECH (SHENZHEN) CO LTD

Sale platform based on smart phone platform

InactiveCN103971279AImprove timeliness and efficiencyincrease breadth
Owner:CHONGQING AOLU E COMMERCE

Method and system for monitoring surface roughness of magnetic control spattering target

InactiveCN101819030AReduce the chance of defective productsImprove timeliness and efficiency
Owner:BOE TECH GRP CO LTD +1

Digitized quantitative evaluation method of oilfield waterflooding process

ActiveCN107965301AImprove timeliness and efficiencyStrengthen the supervision of water injection process
Owner:PETROCHINA CO LTD

Static processing method and device for portal website

PendingCN111783000AImprove timeliness and efficiencyincrease breadth
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Method and system for task distribution

InactiveCN107479963AImprove timeliness and efficiencyImprove operational efficiency
Owner:NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products