Digital Map Alignment Correction for Linear and Planar Features

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing digital maps struggle to accurately align positions of points affiliated with objects, particularly those with linear or planar features, in images of locations, which is crucial for precise vehicle navigation and control.

Innovation Solution

A system and method that utilize a processor and memory to identify and correct the alignment of positions of points affiliated with objects in images, specifically recognizing linear or planar features, and producing a digital map for vehicle navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional point alignment methods are used for digital maps, then general positioning accuracy can be maintained, but alignment accuracy for objects with linear or planar features deteriorates

Engineering Contradiction:
Improvealignment accuracy of points with linear or planar featuresVSAvoidcomplexity of alignment correction system
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by implementing feature-specific alignment correction. The system identifies whether points belong to linear features (using linear regression to calculate deviation from expected linear arrangement) or planar features (using RANSAC to fit planes), and applies appropriate correction methods tailored to each feature type. This localized approach improves alignment accuracy for specific feature types without requiring complete system redesign.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If high-definition maps with decimeter-level accuracy are produced, then vehicle control automation becomes feasible, but the complexity of position alignment and correction increases

Engineering Contradiction:
Improveposition accuracy of objects in digital mapVSAvoidcomplexity of alignment correction process
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs parameter changes by transforming point cloud data into different feature representations. Linear features are characterized by parameters such as line equation coefficients and deviation distances, while planar features are represented by plane equation parameters and point-to-plane distances. These parameter transformations enable specialized alignment correction for each feature type, achieving decimeter-level accuracy required for vehicle automation.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If traditional alignment methods are used without recognizing feature types, then processing simplicity is maintained, but alignment accuracy for linear and planar features deteriorates

Engineering Contradiction:
Improvealignment accuracy of points affiliated with objectsVSAvoiddifficulty of identifying and correcting alignment of points with linear or planar features
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies segmentation by dividing the point cloud data into distinct feature categories (linear features and planar features) based on geometric characteristics. This segmentation enables the system to apply appropriate alignment correction methods to each category, improving overall alignment accuracy while maintaining manageable processing complexity through systematic classification.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20250086984A1Correcting an alignment of positions of points affiliated with an object, in images of a location, that has a linear feature or a planar feature
Publication Date: 2025.03.13 WOVEN BY TOYOTA INC
  • US20250086984A1 patent drawing
  • US20250086984A1 patent drawing
  • US20250086984A1 patent drawing

AI summary

A system for correcting an alignment of positions of points affiliated with an object, in images of a location, that has one or more of a linear feature or a planar feature can include a processor and a memory. The memory can store an alignment module and a communications module. The alignment module can include instructions to: (1) identify, within data affiliated with the images, the positions of the points affiliated with the object that has the one or more of the linear feature or the planar feature and (2) correct, in a manner that recognizes that the object has the one or more of the linear feature or the planar feature, the alignment of the positions to produce a digital map of the location. The communications module can include instructions to transmit the digital map to a vehicle to be used to control a movement of the vehicle.