Vehicle Risk Prediction Using Route-Aware Intersection Path Determination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing risk prediction systems for vehicle driving fail to accurately determine potential risks based on traveling direction after intersections due to lack of high-precision map information, leading to unnecessary risk notifications when vehicles do not actually traverse risky locations.

Innovation Solution

A risk prediction determination device that specifies a predicted traveling route using traveling lane, road type, and road link information, combined with risk location identification based on road shape and obstacle information, to accurately determine if a vehicle will traverse a risky location.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If risk prediction is performed without considering predicted traveling route, then risk notification is provided to all potential risks, but false risk notifications increase when vehicles do not actually traverse risky locations

Engineering Contradiction:

Improverisk prediction accuracyVSAvoidfalse risk notifications

Core Design Contradiction:

ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The system performs preliminary action by specifying the predicted traveling route in advance before conducting risk prediction. The predicted traveling route specifying unit determines the future path of the vehicle based on current lane, road type, and link information. This preliminary route specification enables the risk prediction determination unit to filter risks that are not relevant to the actual traveling path, thereby reducing false notifications while maintaining reliable risk detection for actual threats.

Inventive Principle:

Principle #10Preliminary action

2Device complexity

If high-precision map information is not provided, then system complexity is reduced, but risk prediction accuracy deteriorates due to inability to determine traveling direction after intersections

Engineering Contradiction:

Improvemap information requirementVSAvoidtraveling direction determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system applies dimensionality change by transitioning from two-dimensional map information to three-dimensional road link information. Instead of relying on detailed high-precision maps, the system uses road link information that includes connection relationships between roads, intersections, and destinations. This additional dimensional data (road connections and destination information) enables accurate traveling direction determination after intersections without requiring complex high-precision map data, thus resolving the contradiction between system simplicity and prediction accuracy.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Productivity

If risk prediction is performed without considering predicted traveling route, then processing speed is maintained, but unnecessary risk notifications are generated

Engineering Contradiction:

Improverisk prediction processing speedVSAvoidtraveling direction information

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system extracts only the essential traveling direction information needed for risk prediction from the available data. Instead of processing complete high-precision map information, the system extracts key elements (road link connections, intersections, and destination relationships) to determine the predicted traveling route. This extraction approach maintains processing speed by avoiding unnecessary data processing while still providing sufficient information to eliminate false risk notifications.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS12548447B2Risk prediction determination device and risk prediction determination program product

Publication Date: 2026.02.10 DENSO CORP

AI summary

A risk prediction determination device includes a predicted traveling route specifying unit, a risk location specifying unit, and a risk prediction determination unit. The predicted traveling route specifying unit specifies a predicted traveling route of a subject vehicle based on traveling lane information indicating a traveling lane of the subject vehicle, road type information indicating a type of a road around the subject vehicle, road link information related to a road link, and sensor information of the subject vehicle. The risk location specifying unit specifies a location with risk based on road shape information around the subject vehicle and location information of an obstacle. The risk prediction determination unit performs a risk prediction determination based on a specified result of the predicted traveling route specifying unit and a specified result of the risk location specifying unit.