Edge calculation-based high-precision map crowdsourcing updating system

An edge computing, high-precision technology, applied in the field of high-precision map crowdsourcing update system based on edge computing, can solve the problems of large data transmission volume and congestion at the vehicle end and central node, and achieve the goal of reducing delay and data volume Effect

Pending Publication Date: 2019-08-23
小米汽车科技有限公司
View PDF11 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem that the data transmission volume of the vehicle end and the ce

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Edge calculation-based high-precision map crowdsourcing updating system
  • Edge calculation-based high-precision map crowdsourcing updating system
  • Edge calculation-based high-precision map crowdsourcing updating system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0037] Such as figure 1 As shown, the high-precision map crowdsourcing update and release system based on edge computing includes at least one information collection terminal 1 , a central node 2 , and at least one map use terminal 3 .

[0038] Information collection terminal 1 can be installed on, for example, a plurality of crowdsourcing vehicles, such as figure 2As shown, the information collection terminal 1 includes a sensor unit 11 , a vehicle-mounted computing unit 12 , a communication unit 13 , a storage unit 14 , and a positioning unit 15 . Wherein, the sensor unit 11 includes one or more sensors, which are used to collect traffic information such as roads and road conditions during the driving of the vehicle, the storage unit 14 is used to store the current version of the high-precision map, and the vehicle-mounted computing unit 12 is used to receive sensor The road information collected by the unit 11, and build a local high-precision map in the current field of ...

no. 2 example

[0048] Similar to Embodiment 1, the present invention provides a second embodiment, wherein the same features as Embodiment 1 will not be described here.

[0049] Since the high-precision map has the characteristics of local construction and local use, the one-layer architecture of the direct communication between the central node 3 and the information collection terminal 1 described in the first embodiment can be further expanded into a multi-layer architecture. One or more intermediate nodes 4 are added between the central node 3 and multiple information collection terminals 1 to be responsible for updating high-precision maps of local areas. Through the distributed architecture of computing node space, the delay of high-precision map update can be further reduced.

[0050] Such as Figure 5 As shown, compared with Embodiment 1, this embodiment adds one or more intermediate nodes 4 between the central node 3 and multiple information collection terminals 1 . The intermediat...

no. 3 example

[0052] Similar to Embodiment 1, the present invention provides a third embodiment, wherein the same features as Embodiment 1 will not be described here again.

[0053] The difference from Embodiment 1 is that in this implementation, the vehicles can directly communicate with each other, and the first vehicle as the information collection terminal 1 can directly generate incremental map update data through its on-board computing unit 22, and update the incremental map Quantitative map update data is directly sent to the surrounding second vehicles as information collection terminal 1 and / or map use terminal 3 . And the second vehicle can send the incremental map update data to third vehicles around it.

[0054] Therefore, in a local area, the update of the high-precision map can be realized through communication between multiple vehicles without going through the central node 1 or the intermediate node 4, thereby further reducing the delay of updating the high-precision map.

...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an edge calculation-based high-precision map crowdsourcing updating system. The system comprises at least one information collecting terminal, a central node and at least one map using terminal, wherein the information collecting terminal is arranged at a vehicle end and used for constructing a partial high-precision map in a current visual field of a vehicle in real time and sending differentiated data of the partial high-definition map and a high-precision map at the position, of a current-version high-precision map, to the central node; the central node is used for summarizing the differentiated data of the maps from one or more information collecting terminals and generating incremental map update data of the current-version high-precision map according to the summarized data; and the map using terminal is used for obtaining the incremental map update data from the central node. The system has the technical effects that by adopting an edge calculation mode,the data processing is carried out in advance at a place near a position where original data are generated to reduce the amount of data transmitted from the vehicle end to the central node; moreover,incremental updating is carried out on the high-precision map and only the differentiated content of the current high-precision map is needed to be returned at the vehicle end, thereby further reducing the amount of data sent to the central node.

Description

[0001] Technical field [0002] The invention belongs to the technical field of urban intelligent transportation, and relates to a high-precision map update system and method, in particular to a high-precision map crowdsourcing update system based on edge computing. Background technique [0003] High-precision maps are the basic modules for autonomous driving, and can be applied to high-precision positioning, lane-level path planning, high-precision simulation, and beyond-the-horizon environment perception. High-precision maps are high-precision, high-fidelity modeling of traffic scenes, which rely on the aggregation of a large number of local observations. When building a high-precision map for the first time, a small number of high-cost professional map collection vehicles equipped with sensors generally scan the traffic scene and store the original data. After each job is completed, the data is sent to the data center by offline copying or network uploading. transfer, and ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01C21/32
CPCG01C21/32
Inventor 杨奎元蔡锐
Owner 小米汽车科技有限公司
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