KR-20260064209-A - Autonomous driving risk minimization support system and method thereof

Abstract

The present invention provides a system for supporting risk minimization in autonomous driving, characterized by a control center (20) that is linked to an autonomous vehicle (10) and provides auxiliary support when a dangerous situation is detected during operation, receiving information from an edge infrastructure (30) and surrounding vehicles (40) to detect a dangerous situation of the autonomous vehicle (10) linked to the control center, and transmitting a response strategy for a risk minimization operation and a risk minimization state to resolve the dangerous situation of the target autonomous vehicle (10).

Inventors

• 이명수
• 윤형석
• 황영서
• 윤윤기
• 김봉섭
• 윤경수

Assignees

• 재단법인 지능형자동차부품진흥원

Dates

Publication Date

20260507

Application Date

20241031

Claims (6)

1. An autonomous vehicle that detects status and event information of the vehicle and autonomous driving system; A control center linked to autonomous vehicles to provide auxiliary support when dangerous situations are detected during operation; Edge infrastructure that detects at least one of road conditions, weather, road surface conditions, and event information and transmits it to a control center; and A surrounding vehicle that detects status and fault information of its own vehicle and other vehicles, as well as road operation information and event information, and transmits them to a control center; The control center A risk minimization support system for autonomous driving characterized by receiving information from edge infrastructure and surrounding vehicles to detect a dangerous situation of an autonomous vehicle linked to control, and transmitting a risk minimization maneuver and a response strategy for a risk minimization state to resolve the dangerous situation of the target autonomous vehicle.
2. In claim 1, the edge infrastructure is Risk minimization maneuver information including cumulative event information by section, road operation information by section, and at least one of acceleration, deceleration, and lane change of a vehicle to avoid an event in the target section; and A risk minimization support system for autonomous driving characterized by transmitting risk minimization state response information including response information of a vehicle capable of maintaining a risk minimization state in response to a dangerous situation.
3. In claim 1, the control center Information collection module that collects information; A data management module that verifies information collected from an information collection module and classifies it into information on the target autonomous vehicle and surrounding vehicles, and information on the movement path segments of the target autonomous vehicle; and A risk minimization support system for autonomous driving comprising: a risk situation response module that detects a risk situation of a target autonomous vehicle and transmits a response strategy through information on the target autonomous vehicle and surrounding vehicles classified in a data management module and information on the movement path segment of the target autonomous vehicle.
4. In claim 3, the target autonomous vehicle and surrounding vehicle information A risk minimization support system for autonomous driving characterized by at least one of status information including performance and failure status of a vehicle and an autonomous driving system, current road operation information, and information on the ability to perform risk minimization maneuvers and risk minimization states.
5. In claim 3, the movement path segment information of the target autonomous vehicle A risk minimization support system for autonomous driving comprising at least one of cumulative event information by section, road operation information by section, and risk minimization maneuver and risk minimization state response information.
6. a) A step of linking the autonomous vehicle with the control center, and collecting and analyzing information from the autonomous vehicle, edge infrastructure, and surrounding vehicles; b) A step of analyzing information collected from the control center to detect or predict dangerous situations of the autonomous vehicle linked to the control center; c) a step of transmitting to the target autonomous vehicle a risk-minimizing maneuver and a response strategy for responding to the risk-minimizing state when a dangerous situation of the target autonomous vehicle is detected or predicted by the control center; and d) a step of verifying whether the safety of the target autonomous vehicle is secured at the control center, and if safety is not secured, continuing control linkage to respond to a state of risk minimization; a method for supporting risk minimization of autonomous driving including

Description

Autonomous driving risk minimization support system and method thereof The present invention relates to a system and method for supporting the minimization of risks in autonomous driving. Autonomous driving technology is attracting attention as a technology capable of increasing traffic efficiency for logistics and delivery services and reducing economic losses resulting from social issues such as traffic accidents. The Society of Automotive Engineers (SAE International) defines an autonomous driving system as hardware and software capable of continuously performing the entire Dynamic Driving Task (DDT), regardless of whether it is limited to a specific Operational Design Domain (ODD), and the Dynamic Driving Task includes real-time operational and tactical functions necessary for vehicle operation in road traffic. Currently, vehicle automation functions are classified into 6 levels from Lv.0 to Lv.5 depending on the combination of driving assistance and autonomous driving functions, and the Automated Driving System (ADS) refers to levels 3 through 5. Recently, in order to commercialize Level 4 or higher autonomous driving technology, active development is underway to develop technologies that complement the physical limitations of existing autonomous vehicles and respond to dangerous situations (Fallback) that may occur during operation by integrating artificial intelligence technologies such as reinforcement learning with road infrastructure and communication technologies. DDT Fallback refers to a situation where the operation and functioning of the ADS cannot be performed safely, and it occurs due to causes such as performance-related system failures or deviations from the operational design area. And the ADS establishes a Minimal Risk Maneuver (MRM) strategy and performs a process to reach a safe stopping state, which is the Minimal Risk Condition (MRC). The National Highway Traffic Safety Administration (NHTSA), through its Automated Driving Systems 2.0 Voluntary Guidance, identified fallback response strategies as a safety factor that must be considered and recommends establishing a documented process for this. Conventionally, in order to enhance the operational safety of autonomous vehicles, it is important to have technology that can satisfy the vehicle's safety status, such as MRC, through safe and reasonable MRM and OEDR (Object and Event Detection and Response) in dangerous situations equivalent to sudden events and DDT Fallback situations, as well as DDT Fallback situations caused by deviation from the operational design area and system failure. Therefore, conventionally, technology has been proposed that includes a 3-Tier based risk situation response strategy integrating the target vehicle, surrounding infrastructure, and control. However, with the recent increase in the adoption of autonomous vehicles and the consequent changes in traffic conditions, the capability of the target vehicle (autonomous vehicle) is crucial for achieving DDT Fallback and MRC in similar hazardous road situations; yet, relying solely on the target vehicle faces limitations in sensor perception range and physical limitations due to weather conditions, making it highly likely that a lack of response capability will occur. Therefore, autonomous vehicles require a 3-Tier based risk response strategy alone, and furthermore, a 4-Tier based risk response strategy technology is needed to address the capability limitations of ADS according to complex factors of the risk situation, but it has not yet been commercialized. FIG. 1 is a block diagram illustrating a risk minimization support system for autonomous driving according to the present invention. Figure 2 is a block diagram illustrating the control linkage section. Figure 3 is a flowchart illustrating a method to support risk minimization in autonomous driving. Figure 4 is a flowchart illustrating step S200. Figure 5 is a diagram illustrating an example of a dangerous situation and the support provided therefrom. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. Throughout the specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. The terms used in the embodiments of the present invention have been selected to be as widely used as possible, taking into account their functions in the invention; however, these terms may vary depending on the intent of those skilled in the