Layered ODD Risk Updates for Autonomous Driving Safety

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous driving systems face safety challenges due to the lack of updates and complementary settings in operation design domains (ODDs), which can lead to reduced safety as they fail to adapt to changing road conditions and traffic dynamics, resulting in cumbersome and outdated risk assessments across different vehicles.

Innovation Solution

An autonomous driving safety system that employs a risk-based operation design domain sharing method, utilizing vehicle-to-vehicle communication and a control server to evaluate and update ODDs in real-time, by layering attributes and calculating risks across various domains such as road geometry, social infrastructure, temporary restricted areas, objects, environmental conditions, and connectivity, ensuring that each autonomous vehicle receives updated and accurate ODD information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If operation design domain (ODD) is designed based on real roads with complementary settings for each layer, then autonomous driving operational safety is secured, but the complexity of defining detailed attribute values and classification for each layer increases

Engineering Contradiction:
Improveautonomous driving operational safetyVSAvoidODD classification and attribute definition complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The ODD is segmented into multiple hierarchical layers including static ODD (road geometry, infrastructure) and dynamic ODD (traffic conditions, weather, objects). Each layer is independently classified and defined with specific attribute values, allowing systematic management of complexity while ensuring comprehensive safety coverage for autonomous driving operations

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a hierarchical dimensional structure for ODD classification, organizing attributes across different layers (static/dynamic, geometric/functional). This multi-dimensional framework transforms the complex single-layer ODD definition into a structured hierarchical system, making it more manageable while maintaining comprehensive safety requirements

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If ODD characteristics are updated to reflect changes in traffic and environment over time, then autonomous driving safety is improved, but the burden of continuous updating and complementation increases

Engineering Contradiction:
Improveautonomous driving safetyVSAvoidtime for ODD update and complementation
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary classification and definition of ODD attributes for each layer in advance, establishing a structured framework before actual autonomous driving operations begin. This preliminary setup enables faster real-time updates by providing a pre-organized structure that only requires population with current data rather than complete re-definition

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The ODD system is designed to be dynamic, with automatic updating mechanisms that reflect changes in traffic conditions, weather, and environmental factors in real-time. The hierarchical structure allows selective updates at different layers based on what has changed, reducing the overall time and effort required for continuous maintenance

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If different ODD designs are created for each vehicle with specific response strategies, then vehicle-specific autonomous driving requirements are met, but the complexity of managing and synchronizing multiple ODD characteristics across different vehicles increases

Engineering Contradiction:
Improvevehicle-specific ODD adaptationVSAvoidmulti-vehicle ODD management complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal hierarchical ODD framework that can be applied across different vehicles while allowing vehicle-specific customizations. The standardized layer structure and attribute definitions serve as a common foundation that all vehicles can use, ensuring consistency and reducing management complexity while still permitting individual vehicle adaptations through the same framework

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4369323A1Autonomous driving safety system for sharing risk-based operation design domain and method thereof
Publication Date: 2024.05.15 KOREA INTELLIGENT AUTOMOTIVE PARTS PROMOTION INST
  • EP4369323A1 patent drawingFigure 1~2
  • EP4369323A1 patent drawingFigure 3~5
  • EP4369323A1 patent drawingFigure 6~8

AI summary

The present disclosure relates to an autonomous driving safety system for sharing a risk-based operation design domain including: an autonomous driving system 110 configured to control a vehicle driving unit 140 according to information detected by a sensor unit 120 to perform autonomous driving, in which the autonomous driving system 110 includes an operation design domain (ODD) update unit 111 configured to evaluate a risk of at least one of a static operation design domain and a dynamic operation design domain recognized by the sensor unit 120 while driving to update the operation design domain (ODD).