Road Soft Point Detection Using Hard Points and Sliding Windows

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing mapping systems struggle to accurately identify soft points, such as painted boundaries and taper points, at road junctions due to data discrepancies and lack of reliable reference points, leading to incomplete maps that compromise the safety and reliability of automated driving and navigation systems.

Innovation Solution

A detection system that utilizes a sliding window approach to search a rasterized representation of road data, starting from a hard point, to identify soft points by detecting peak patterns in lane boundaries, thereby enhancing map information and improving navigation safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If mapping systems process vehicle data to generate maps, then map coverage is improved, but measurement precision of soft points deteriorates due to data discrepancies

Engineering Contradiction:

Improvemap coverageVSAvoidsoft point detection accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent introduces a sliding window as an intermediary mechanism that processes rasterized road data to detect peak patterns. This sliding window acts as a mediator between the raw vehicle data and the final soft point detection, allowing the system to maintain both broad map coverage and high measurement precision by analyzing local patterns within the window while covering extensive road areas.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary rasterization of road data before soft point detection. By converting vehicle data into a rasterized representation first, the system prepares the data in a format that enables efficient pattern matching and peak detection, thereby improving both map coverage and measurement precision in subsequent processing stages.

Inventive Principle:

Principle #10Preliminary action

2Device complexity

If mapping systems rely on vehicle data alone, then system complexity is reduced, but reliability of soft point detection deteriorates due to lack of reference points

Engineering Contradiction:

Improvesystem complexityVSAvoidsoft point detection reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system uses hard points detected from the same vehicle data as reference points for detecting soft points. This self-service approach allows the system to improve its own detection reliability using internally generated reference information, maintaining low system complexity while enhancing soft point detection reliability through self-referenced pattern matching.

Inventive Principle:

Principle #25Self-service

3Ease of operation

If mapping systems use simple detection methods, then ease of operation is improved, but manufacturing precision of map data deteriorates

Engineering Contradiction:

Improvedetection method simplicityVSAvoidmap data accuracy

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The patent replaces complex mechanical or manual detection methods with an automated computational approach using sliding window analysis on rasterized data. This substitution maintains ease of operation through automated processing while achieving high manufacturing precision of map data through systematic peak pattern detection and analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Ease of manufacture

If mapping systems process all road areas uniformly, then ease of manufacture is improved, but loss of information about complex junctions increases

Engineering Contradiction:

Improvemap generation easeVSAvoidjunction information completeness

Core Design Contradiction:

Ease of manufactureVSLoss of information

Solution Approach 1:

The patent applies local quality by using the sliding window to focus detection efforts on specific local patterns within the rasterized data. This allows the system to maintain ease of manufacture through standardized processing while preventing information loss at complex junctions by intensively analyzing local peak patterns that characterize these important road features.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250246004A1Systems and methods for detecting a soft point on a road using a hard point

Publication Date: 2025.07.31 TOYOTA JIDOSHA KK

AI summary

Systems, methods, and other embodiments described herein relate to detecting a soft point on a road starting from a hard point using a sliding window for searching a rasterized representation. In one embodiment, a method includes identifying a hard point using rasterized data of a road derived from vehicle data. The method also includes searching a rasterized representation of the road using a sliding window along lane boundaries starting at the hard point, the rasterized representation generated with the vehicle data. The method also includes detecting a soft point from peak patterns of the lane boundaries within the sliding window among the rasterized representation.