Point Cloud Attribute Matching for Similar-Scene Indoor Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current indoor positioning technologies, such as those using ICP matching, struggle with low accuracy due to similar scenes in environments like underground parking garages, as point clouds of different locations are highly approximate.

Innovation Solution

Extracting attribute features like projection, normal vector, and curvature features from point clouds to improve matching accuracy, using methods like projecting onto coordinate planes, calculating normal vectors, and employing ICP algorithms after filtering and clustering to enhance pose determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple sensors are mounted on the moving object to obtain motion information from multiple directions, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvemotion information measurement precisionVSAvoidsensor mounting complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies the universality principle by enabling a single sensor to perform multiple measurement functions through dynamic coordinate transformation. The sensor measures physical quantities in its own local coordinate system, and the system transforms these measurements into various global coordinate systems (device coordinate system, map coordinate system, etc.), allowing one sensor to provide information equivalent to multiple sensors would provide in different directions and reference frames.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If motion information is transformed to multiple coordinate systems for comprehensive positioning, then measurement precision is improved, but calculation complexity increases

Engineering Contradiction:
Improvepositioning precisionVSAvoidcoordinate transformation calculation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-establishing the transformation relationship between the sensor's local coordinate system and the device's global coordinate system. This transformation matrix is calculated and stored in advance based on the known geometric relationship between the sensor mounting position and the device coordinate origin. During actual operation, the system only needs to perform simple matrix multiplication rather than complex real-time calculations, significantly reducing computational complexity while maintaining high positioning precision.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If a single sensor is used to reduce device complexity, then device complexity is reduced, but measurement precision deteriorates due to limited measurement directions

Engineering Contradiction:
Improvesensor system complexityVSAvoidmotion information measurement precision
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies the dimensionality change principle by transitioning from measuring motion in a single fixed coordinate system to measuring motion across multiple coordinate systems through mathematical transformation. The sensor physically measures only in its local coordinate system, but the system virtually extends measurement capabilities to multiple global coordinate systems by applying coordinate transformation matrices, effectively adding dimensional freedom without adding physical sensors.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4215874B1Positioning method, electronic device and storage medium
Publication Date: 2026.05.20 YINWANG INTELLIGENT TECHNOLOGIES CO LTD
  • EP4215874B1 patent drawingFigure 1
  • EP4215874B1 patent drawingFigure 2~3
  • EP4215874B1 patent drawingFigure 4

AI summary

Provided are a positioning method and apparatus, an electronic device, and a storage medium. The method includes: (S301) collecting a current point cloud, where the current point cloud includes a point cloud of a to-be-positioned object and a point cloud of an environment of the to-be-positioned object; (S302) extracting an attribute feature of the current point cloud; and (S303) obtaining a pose of the to-be-positioned object based on the attribute feature of the current point cloud and an attribute feature of a point cloud on a point cloud map of the environment of the to-be-positioned object. Because an attribute feature of a point cloud is an intrinsic feature of the point cloud, even if scenes are similar, attributes or attribute features of point clouds in the similar scenes are different. Therefore, the positioning method can match an attribute feature of a current point cloud around a to-be-positioned object and an attribute feature of a point cloud on a point cloud map to improve indoor positioning accuracy.