Road Segment Sinuous Driving Metric for Autonomous Route Safety

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in navigating road segments with unpredictable dynamics, such as those involving human-driven vehicles that may engage in unpredictable maneuvers like overtaking, sudden braking, or parking. Existing technologies lack a comprehensive metric to assess driver behavior and driving patterns on specific road segments, which hinders the ability of autonomous vehicles to anticipate and avoid such unpredictable scenarios.

Innovation Solution

A method is developed to determine a sinuous driving metric for road segments, which assesses the sinuosity of driving based on probe data. This metric represents a measure of driver behavior and driving patterns, indicating how smooth or aggressive driving is on a particular road segment. The method involves processing probe data, which includes position information and trajectory data, to calculate lateral and forward movements, thereby determining the sinuous driving metric.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If autonomous vehicles avoid road segments with unpredictable dynamics, then safety is improved, but navigation flexibility and route options are reduced

Engineering Contradiction:
ImprovesafetyVSAvoidnavigation flexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary analysis of road segment characteristics and driver behavior patterns before navigation decisions are made. By pre-calculating sinuous driving metrics and storing them in a database, the system can quickly query and use this information during route planning without real-time delays, thus maintaining both safety and navigation flexibility

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The navigation system dynamically adjusts route selection based on real-time queries of sinuous driving metrics for different road segments. Rather than statically avoiding all complex roads, the system adaptively chooses paths that balance safety concerns with navigation efficiency, allowing flexible route optimization based on current traffic and road conditions

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If a comprehensive metric for driver behavior is developed, then assessment accuracy is improved, but data processing complexity increases

Engineering Contradiction:
Improveassessment accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The driver behavior assessment is segmented into distinct measurable components: lateral movement distance, forward movement distance, and sinuous driving metric. Each component is calculated independently from probe data points, allowing the complex assessment to be broken down into manageable computational steps that can be processed efficiently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A database serves as an intermediary layer between raw probe data collection and the navigation decision-making process. The sinuous driving metrics are pre-calculated and stored in this database, decoupling the complex data processing from real-time navigation queries and reducing overall system complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If probe data is collected and processed to determine sinuous driving metrics, then driver behavior assessment is improved, but computational resources and time are consumed

Engineering Contradiction:
Improvedriver behavior assessmentVSAvoidcomputational time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary calculation and storage of sinuous driving metrics from probe data in advance, before navigation decisions are required. By pre-processing the probe data and storing results in a database, the system avoids repeated real-time calculations during navigation queries, significantly reducing computational time when routes need to be planned

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system maintains continuous collection and processing of probe data from multiple vehicles, continuously updating the database of sinuous driving metrics. This continuous data accumulation improves the quality and reliability of driver behavior assessment over time, while the pre-processed nature of the data ensures that navigation queries remain computationally efficient

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3432287B1Navigation driving metric
Publication Date: 2025.02.19 HERE GLOBAL BV
  • EP3432287B1 patent drawingFigure 1
  • EP3432287B1 patent drawingFigure 2
  • EP3432287B1 patent drawingFigure 3

AI summary

A method is disclosed comprising: obtaining data associated with each road segment of at least one road segment, said data comprising: a representative of at least one link associated with the respective road segment; obtaining probe data associated with the respective road segment, the probe data comprising: at least one piece of position information; determining a sinuous driving metric, which is a value being indicative of a sinuosity of driving on the respective road segment based at least partially on the probe data and its allocation with respect to the respective road segment. It is further disclosed an according apparatus, computer program and system.