KR-20260065255-A - 3-tier Hybrid Infrastructure System For Autonomous Driving Operation Platform

KR20260065255AKR 20260065255 AKR20260065255 AKR 20260065255AKR-20260065255-A

Abstract

The present invention relates to an infrastructure structure of an autonomous driving operation platform, and more specifically, proposes a three-layer hybrid infrastructure system for an autonomous driving operation platform that enables efficient operation by operating the infrastructure structure in three layers while considering scalability and availability, and allows for the urgent expansion of servers in a public cloud to extract desired simulation results and deliver guidance to autonomous vehicles when additional server infrastructure is required due to rapidly increasing traffic congestion and a surge in users, thereby presenting a method optimized for real-time traffic flow with ultra-low latency.

Inventors

양희수
임우현

Assignees

주식회사 아이티센씨티에스

Dates

Publication Date: 20260508
Application Date: 20241101

Claims (10)

On-premises that receives data collected through edge RSUs collecting weather and traffic flow data, anonymizes and processes the received data, and transmits it to a hybrid cloud; A hybrid cloud that operates a service operation platform by processing and simulating data based on data received from the above-mentioned on-premises system, and provides guidance to autonomous vehicles; and If infrastructure expansion is required in the above hybrid cloud, it includes a public cloud that generates guidance by simulating including additional data through infrastructure expansion; A three-layer hybrid infrastructure system for an autonomous driving operation platform, characterized by data simulated and processed in the above-mentioned public cloud being transmitted to a hybrid cloud, and guidance suitable for traffic flow being transmitted from the hybrid cloud to an autonomous vehicle.
In claim 1, When the above hybrid cloud provides guidance to autonomous vehicles, A three-layer hybrid infrastructure system for an autonomous driving operation platform that provides guidance after simulation by expanding infrastructure via a public cloud in cases corresponding to at least one of traffic congestion, a surge in service users, or a need for additional model training.
In claim 1, A three-tiered hybrid infrastructure system for an autonomous driving operation platform that implements a flexible infrastructure through organic linkage between on-premises, hybrid cloud, and public cloud domains, and can respond to increased usage by adjusting infrastructure scale through ratio analysis between hybrid cloud and public cloud.
In claim 1, The above public cloud is a three-layer hybrid infrastructure system for an autonomous driving operation platform that uses a digital twin to simulate traffic congestion situations to recommend real-time traffic responses, and predicts inspection cycles based on the operation of autonomous vehicles to provide guidance.
In claim 4, When providing route guidance based on the above real-time traffic response recommendation, guidance is provided to allow selection of one of time priority, distance priority, or safety priority; The above safety priority is a three-layer hybrid infrastructure system for an autonomous driving operation platform that recommends routes with a low frequency of sudden events and accidents.
In claim 1, The above public cloud is a three-layer hybrid infrastructure system for an autonomous driving operation platform that provides guidance for autonomous vehicles and road infrastructure by simulating a precision map based on a real-time road environment reflecting traffic, sudden events, signals, and weather conditions through a virtual test environment.
In claim 1, The above public cloud is, In situations where short-term measures are possible during infrastructure expansion, guidance is delivered through real-time simulation; A three-layer hybrid infrastructure system for an autonomous driving operation platform that periodically checks data received from on-premises to verify changed conditions and delivers guidance through simulation in situations where short-term action is not possible.
In claim 1, The above hybrid cloud is, It provides infrastructure scalability services that are difficult to implement on-premises; A three-tiered hybrid infrastructure system for an autonomous driving operation platform that enables flexible service integration without lead time through resource expansion and guarantees the stability of autonomous driving services in the event of data center or regional disasters.
In claim 1, The above hybrid cloud is, It provides infrastructure scalability services that are difficult to implement on-premises; A three-tiered hybrid infrastructure system for an autonomous driving operation platform that enables payment only for what is used as infrastructure expands, and allows for easy integration and use of new technologies from infrastructure providers.
In claim 1, The above hybrid cloud is, It is possible to control the system through various services and signals that are difficult to apply in the public cloud; A three-tiered hybrid infrastructure system for an autonomous driving operation platform that can be customized to meet user requirements.

Description

3-tier Hybrid Infrastructure System For Autonomous Driving Operation Platform The present invention relates to an infrastructure structure of an autonomous driving operation platform, and more specifically, to a three-layer hybrid infrastructure system for an efficient autonomous driving operation platform that operates the infrastructure structure in three layers to consider scalability and availability. In conventional autonomous vehicles, situational judgment and action decisions were performed according to fixed methods. That is, situational judgment and action decisions regarding missions such as lane changes, driving on curved roads, driving through intersections, maintaining distance between vehicles, and lane keeping were executed only under predetermined conditions. For example, to perform a lane change (to turn left or right, overtake, or make a U-turn), a judgment and action decision are made based on the speed and distance to the vehicle ahead in the driving lane and the vehicles in front and behind in the target lane, provided that the predetermined conditions are met. Furthermore, speed control on curved roads is also determined by fixed parameters. However, when making judgments based on fixed conditions, flexible situational judgment and decision-making may be lacking. Furthermore, if data from autonomous vehicles is collected, verified, and processed directly on cloud servers, issues regarding physical security and data control may arise, and regulations requiring the storage of sensitive information within local data centers present difficulties in processing necessary data. In addition, there were issues such as difficulty in responding to infrastructure expansion required due to increased usage, and difficulty in responding to unexpected events and anomalies occurring externally other than those involving autonomous vehicles. FIG. 1 is a block diagram illustrating the concept of a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. FIG. 2 is a diagram showing the architectural design principles of a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. FIG. 3 is a diagram showing the role of each layer of a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. FIGS. 4 and 5 are diagrams illustrating the guidance flow of a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. FIG. 6 is a diagram showing the main scope of the construction and operation of a living lab for a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. FIG. 7 is a diagram showing the external linkage security configuration design of a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. Detailed information regarding the purpose, technical configuration, and the resulting operation and effects of the present invention will be more clearly understood through the detailed description based on the drawings attached to the specification of the present invention. The terms used in this specification are used merely to describe specific embodiments and are not intended to limit the invention. For example, terms such as "composed of" or "comprising" used in this specification should not be interpreted as necessarily including all of the various components or steps described in the invention, but should be interpreted as excluding some of the components or steps, or potentially including additional components or steps. Furthermore, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. The present invention will be described in detail below by explaining preferred embodiments with reference to the attached drawings. The embodiments described below are provided to enable those skilled in the art to easily understand the technical concept of the present invention, and should not be interpreted as limiting the present invention; it is obvious to those skilled in the art that the embodiments of the present invention can have various applications. Referring to FIGS. 1 to 7, we will examine a three-layer hybrid infrastructure system for an autonomous driving operation platform according to the present invention. First, as illustrated in FIG. 1, a three-layer hybrid infrastructure system for an autonomous driving operation platform may include an on-premise (100) that receives weather and traffic flow-related data through an edge RSU (10) and performs data anonymization and processing, a hybrid cloud (200) that provides guidance to an autonomous vehicle (50) through simulation based on processed data, and a public cloud (300) configured to expand the infrastru