Parking Sensor Fusion Grid Mapping for Low-Load Obstacle Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional sensor fusion methods for parking assistance systems in transportation apparatuses face high computational load due to complex mathematical equations, leading to processor overload and difficulty in enhancing performance when fusing ultrasonic and camera sensor data.

Innovation Solution

A sensor fusion apparatus and method using a grid map for preprocessing and clustering, which includes Time of Flight preprocessing for ultrasonic sensors and object detection preprocessing for camera sensors, followed by clustering using an integrated grid map to reduce computational load and improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If Probabilistic Data Association Filter (PDAF) is used for sensor fusion, then identification accuracy is improved, but computational load increases causing processor overload

Engineering Contradiction:
Improveidentification accuracyVSAvoidcomputational load
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent extracts and removes the complex PDAF mathematical equations from the sensor fusion process, replacing them with a simplified grid map-based clustering approach that maintains identification accuracy while eliminating excessive computational requirements

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the fundamental parameters of the sensor fusion method by transitioning from continuous probabilistic calculations to discrete grid-based occupancy scoring, fundamentally altering how sensor data is processed and fused

Inventive Principle:
Principle #35Parameter changes

2Reliability

If conventional sensor fusion method is used, then obstacle detection capability is improved, but device complexity increases making it difficult to add new features

Engineering Contradiction:
Improveobstacle detection capabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the sensor fusion process into distinct modular components: ultrasonic preprocessing module, camera preprocessing module, grid map generation module, and clustering module. This segmentation maintains detection capability while reducing overall system complexity and enabling easier feature addition

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The grid map structure serves multiple functions simultaneously: it represents obstacle occupancy, provides a common coordinate system for fusion, enables clustering operations, and supports ghost object detection, thereby reducing the need for separate specialized modules

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The method reduces processor load and enhances identification accuracy by utilizing the field of view of ultrasonic sensors and the intersection area of direct waves, making the system robust against noise and improving overall performance.

Implementation Method 1

the first preprocessing module performs Time of Flight (TOF) preprocessing and grid mapping for an object detected through an ultrasonic sensor

Methodology Applied
Scientific EffectTime of Flight: Time of Flight

Data Source

PatentEP4628937A1Sensor fusion apparatus and method for transportation apparatus
Publication Date: 2025.10.08 HYUNDAI MOBIS CO LTD
  • EP4628937A1 patent drawingFigure 1
  • EP4628937A1 patent drawingFigure 2
  • EP4628937A1 patent drawingFigure 3(a)~3(d)

AI summary

A sensor fusion apparatus for a transportation apparatus includes: at least two sensors having different characteristics; a first preprocessing module and a second preprocessing module performing grid mapping for each object through preprocessing, corresponding to the at least two sensors having different characteristics, respectively; and a processor performing sensor fusion through clustering using an integrated grid map for the each object grid-mapped by the first preprocessing module and the second preprocessing module.