Road Data Fusion for Accurate Automated Map Generation

Solution Overview

Problem

Current methods for fusing road data to generate maps require manual splicing and marking of point cloud data, leading to high costs, low accuracy, and low efficiency.

Innovation Solution

A method involving determining benchmark road data and road data to be fused, establishing association relationships between sub road data and the benchmark data, and fusing them to update the benchmark data, using higher positioning signal quality data to improve accuracy and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual splicing and marking of point cloud data is used, then the process can be performed with simple equipment, but the cost is high, accuracy is low, and efficiency is low

Engineering Contradiction:

Improvemap generation accuracyVSAvoiddata fusion system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual mechanical operations (splicing and marking point cloud data) with an automated computational system. The system uses algorithmic processing to automatically associate road elements across multiple point cloud datasets, eliminating the need for manual intervention while achieving higher accuracy and efficiency in map generation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the data fusion process occurs autonomously. The algorithm automatically processes multiple point cloud datasets, establishes associations between road elements, and generates the final map without requiring human operators to manually splice data or mark features, thereby reducing costs and improving efficiency.

Inventive Principle:

Principle #25Self-service

2Productivity

If manual splicing and marking of point cloud data is used, then the system can be simple, but the efficiency is low

Engineering Contradiction:

Improvemap generation efficiencyVSAvoiddata fusion automation level

Core Design Contradiction:

ProductivityVSExtent of automation

Solution Approach 1:

The patent replaces manual mechanical operations (splicing and marking point cloud data) with an automated computational system. The system uses algorithmic processing to automatically associate road elements across multiple point cloud datasets, eliminating the need for manual intervention while achieving higher accuracy and efficiency in map generation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the data fusion process occurs autonomously. The algorithm automatically processes multiple point cloud datasets, establishes associations between road elements, and generates the final map without requiring human operators to manually splice data or mark features, thereby reducing costs and improving efficiency.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If manual splicing and marking of point cloud data is used, then the process requires less technology, but the accuracy is low

Engineering Contradiction:

Improveroad element association precisionVSAvoiddata fusion method adaptability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces manual mechanical operations (splicing and marking point cloud data) with an automated computational system. The system uses algorithmic processing to automatically associate road elements across multiple point cloud datasets, eliminating the need for manual intervention while achieving higher accuracy and efficiency in map generation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent employs parameter changes in the data fusion process by weighting different point cloud datasets according to their positioning signal quality. The system dynamically adjusts the influence of each dataset based on its quality metrics, enabling precise association of road elements while adapting to varying data conditions across different datasets.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12498248B2Method for fusing road data to generate a map, electronic device, and storage medium

Publication Date: 2025.12.16 APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD

AI summary

A method for fusing road data to generate a map, includes: determining benchmark road data and at least one road data to be fused in a target road area; establishing, successively for each road data to be fused, a first road element association relationship between the first sub road data and the benchmark road data; establishing a second road element association relationship between the second sub road data and the benchmark road data according to the first road element association relationship; and fusing the benchmark road data and the road data to be fused according to the above association relationships to update the benchmark road data.